In this paper,an adaptive cubic regularisation algorithm based on affine scaling methods(ARCBASM)is proposed for solving nonlinear equality constrained programming with nonnegative constraints on variables.From the op...In this paper,an adaptive cubic regularisation algorithm based on affine scaling methods(ARCBASM)is proposed for solving nonlinear equality constrained programming with nonnegative constraints on variables.From the optimality conditions of the problem,we introduce appropriate affine matrix and construct an affine scaling ARC subproblem with linearized constraints.Composite step methods and reduced Hessian methods are applied to tackle the linearized constraints.As a result,a standard unconstrained ARC subproblem is deduced and its solution can supply sufficient decrease.The fraction to the boundary rule maintains the strict feasibility(for nonnegative constraints on variables)of every iteration point.Reflection techniques are employed to prevent the iterations from approaching zero too early.Under mild assumptions,global convergence of the algorithm is analysed.Preliminary numerical results are reported.展开更多
The outstanding growth in the applications of large language models(LLMs)demonstrates the significance of adaptive and efficient prompt engineering tactics.The existing methods may not be variable,vigorous and streaml...The outstanding growth in the applications of large language models(LLMs)demonstrates the significance of adaptive and efficient prompt engineering tactics.The existing methods may not be variable,vigorous and streamlined in different domains.The offered study introduces an immediate optimization outline,named PROMPTx-PE,that is going to yield a greater level of precision and strength when it comes to the assignments that are premised on LLM.The proposed systemfeatures a timely selection schemewhich is informed by reinforcement learning,a contextual layer and a dynamic weighting module which is regulated by Lyapunov-based stability guidelines.The PROMPTx-PE dynamically varies the exploration and exploitation of the prompt space,depending on real-time feedback and multi-objective reward development.Extensive testing on both benchmark(GLUE,SuperGLUE)and domain-specific data(Healthcare-QA and Industrial-NER)demonstrates a large best performance to be 89.4%and a strong robustness disconnect with under 3%computation expense.The results confirm the effectiveness,consistency,and scalability of PROMPTx-PE as a platform of adaptive prompt engineering based on recent uses of LLMs.展开更多
Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning sc...Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning scenarios.In this work,we propose an Adaptive Meta-Loss Network(Adaptive-MLN)that learns to generate taskagnostic loss functions tailored to evolving classification problems.Unlike traditional methods that rely on static objectives,Adaptive-MLN treats the loss function itself as a trainable component,parameterized by a shallow neural network.To enable flexible,gradient-free optimization,we introduce a hybrid evolutionary approach that combines GeneticAlgorithms(GA)for global exploration and Evolution Strategies(ES)for local refinement.This co-evolutionary process dynamically adjusts the loss landscape,improvingmodel generalization without relying on analytic gradients or handcrafted heuristics.Experimental evaluations on synthetic tasks and the CIFAR-10 andMNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy,convergence,and adaptability.展开更多
The healthcare field is fraught with challenges associated with severe class imbalance,wherein such critical conditions like sepsis,cardiac arrest,and drug adverse reactions are rare but have dire clinical consequence...The healthcare field is fraught with challenges associated with severe class imbalance,wherein such critical conditions like sepsis,cardiac arrest,and drug adverse reactions are rare but have dire clinical consequences.This paper presents a new framework,Deep Reinforcement Adaptive Gradient Optimization Network to Mining Rare Events(DRAGON-MINE),to demonstrate how deep reinforcement learning can be used synergistically with adaptive gradient optimization and address the inherent weaknesses of current methods in the prediction of rare health events.The suggested architecture uses a dual-pathway consisting of a reinforcement learning agent to dynamically reweigh samples and an adaptive gradient optimizer to follow novel learning rates.With extensive experiments on the MIMIC-IV and eICU-CRD datasets,DRAGON-MINE consistently outperforms recent state-of-the-art methods for sepsis,cardiac arrest,and adverse drug reaction prediction,achieving AUROC values of 92.3%and 91.6%for sepsis prediction on MIMIC-IV and eICU-CRD,respectively,while consistently outperforming Transformer-,CNN-RNN-,and Fed-Ensemble-based methods across all evaluated tasks and datasets,with particularly strong gains observed in precision-recall performance under severe class imbalance.With its high sensitivity(88.4%)and specificity(90.2%),DRAGON-MINE enables reliable early warning of rare clinical events in critical care settings while minimizing false alarms,supporting safer clinical decision support systems,and demonstrating strong potential for scalable deployment across multi-institutional intensive care environments through federated learning.展开更多
To address the limitations of the sand cat swarm optimization(SCSO) algorithm which are slow convergence and low accuracy in complex problems,this study proposes an improved SCSO(ISCSO) algorithm that integrates multi...To address the limitations of the sand cat swarm optimization(SCSO) algorithm which are slow convergence and low accuracy in complex problems,this study proposes an improved SCSO(ISCSO) algorithm that integrates multiple enhancement strategies.Firstly,Kent chaotic mapping initializes the population for uniform distribution.Secondly,somersault foraging strategy is introduced during the search and attack phases,allowing the algorithm to escape local optima by intercepting evasive prey.Simultaneously,an adaptive Lévy flight strategy is incorporated into the attack phase to bolster global exploration.Finally,the vertical and horizontal crossover strategy is implemented to enhance population diversity.The performance of the proposed algorithm is evaluated using 16 benchmark test functions.The experimental results demonstrate that ISCSO significantly outperforms the original SCSO and shows notable advantages over other metaheuristic algorithms.Furthermore,application to a pressure vessel design problem verifies ISCSO's effectiveness in solving practical engineering optimization challenges.展开更多
An optimization model has been established and solved to determine the optimal threshold value for the event-triggered self-adaptive optimization strategy,which aims to strike a balance between optimization performanc...An optimization model has been established and solved to determine the optimal threshold value for the event-triggered self-adaptive optimization strategy,which aims to strike a balance between optimization performance and control load while ensuring continuous optimization.First,evaluation indicators are introduced to comprehensively analyze the impact of power fluctuations on the objective function and system voltage at both the system-wide and local levels.Based on these indicators,a multi-stage centralized optimization(MCO)is selectively applied,addressing system state deviations to achieve optimal operating states while maintaining a voltage security margin to ensure system safety.Then,distributed optimization(DO)is carried out at each bus with a renewable energy source or random load integration to accommodate short-term uncertainties using a self-adaptive reactive power algorithm.The optimal threshold value for event-triggered DO is calculated to balance control burden and optimization effectiveness.Utilizing the local state deviation evaluation indicator,unnecessary DOs are skipped when minor power fluctuations occur at the local level.Finally,following the linear superposition principle,event-triggered DOs executed at all distributed controllers collectively constitute the self-adaptive optimization strategy for the entire system.A case study on the IEEE New England 39-bus power system illustrates the effectiveness of the proposed strategy.展开更多
Spaceborne antennas are essential for remote sensing,deep-space communication,and Earth observation,yet their trajectory planning is complicated by nonlinear base-manipulator coupling and antenna flexibility.To addres...Spaceborne antennas are essential for remote sensing,deep-space communication,and Earth observation,yet their trajectory planning is complicated by nonlinear base-manipulator coupling and antenna flexibility.To address these challenges,this paper proposes a multi-objective trajectory optimization framework.The system dynamics capture both nonlinear rigid-flexible coupling and antenna deformation through a reduced-order formulation.To enhance discretization efficiency,a predictive-terminal hp-adaptive pseudospectral method is employed,assigning collocation density based on task-phase characteristics:finer resolution is applied to dynamic segments requiring higher accuracy,especially near the terminal phase.This enables efficient transcription of the continuous-time problem into a Nonlinear Programming Problem(NLP).The resulting NLP is then solved using a multi-objective optimization strategy based on the nondominated sorting genetic algorithm II,which explores trade-offs among antenna pointing accuracy,energy consumption,and structural vibration.Numerical results demonstrate that the proposed method achieves a reduction of approximately 14.0% in control energy and 41.8%in peak actuation compared to a GPOPS-II baseline,while significantly enhancing vibration suppression.The resulting Pareto front reveals structured trade-offs and clustered solutions,offering robust and diverse options for precision,low-disturbance mission planning.展开更多
To address the persistent challenge of dynamic mismatch between wellbore lifting capacity and reservoir fluid supply,and to establish a robust optimization framework for drainage operations in high-water-cut tight san...To address the persistent challenge of dynamic mismatch between wellbore lifting capacity and reservoir fluid supply,and to establish a robust optimization framework for drainage operations in high-water-cut tight sandstone gas reservoirs,this study systematically investigates the graded optimization and dynamic adaptation of drainage gas recovery technologies.Production data from a representative tight gas field were first employed to forecast reservoir performance.The predictive reliability was rigorously validated through high-precision history matching,thereby providing a quantitatively consistent foundation for subsequent wellbore optimization.Building on this characterization,a coupled simulation framework was developed that integrates wellbore multiphase flow modeling with nodal analysis based on the Inflow Performance Relationship,IPR,and the Vertical Lift Performance,VLP.This coordinated approach enables comprehensive evaluation of process adaptability and dynamic optimization of foam-assisted drainage,mechanical pumping,and jet pumping systems under evolving water-gas ratio,WGR conditions.The results reveal that a progressively increasing water-gas ratio is the dominant factor driving the transition from chemically assisted drainage methods to mechanically enhanced lifting technologies.A distinct quantitative threshold is identified at WGR≈0.002,beyond which mechanical intervention becomes more effective and economically justified.For mechanical pumping and jet pumping systems,a parameter inversion optimization strategy constrained by the target bottomhole flowing pressure,Pwf,is proposed to ensure stable production while maintaining reservoir drawdown control.In particular,the nozzle-to-throat area ratio of the jet pump is identified as the key governing parameter influencing entrainment capacity and lifting efficiency.Moreover,a configuration characterized by small pump diameter,long stroke length,and low operating speed is demonstrated to satisfy drainage requirements while mitigating torque fluctuations,enhancing volumetric efficiency,and improving pump fillage stability.展开更多
Parameterized level-set method(PLSM)has been proposed and developed for many years,and is renowned for its efficacy in ad-dressing topology optimization challenges associated with intricate boundaries and nucleation o...Parameterized level-set method(PLSM)has been proposed and developed for many years,and is renowned for its efficacy in ad-dressing topology optimization challenges associated with intricate boundaries and nucleation of new holes.However,most pertinent investigations in the field rely predominantly on fixed background mesh,which is never remeshed.Consequently,the mesh element partitioned by material interface during the optimization process necessitates approximation by using artificial interpolation models to obtain its element stiffness or other properties.This paper introduces a novel approach to topology op-timization by integrating the PLSM with body-fitted adaptive mesh and Helmholtz-type filter.Primarily,combining the PLSM with body-fitted adaptive mesh enables the regeneration of mesh based on the zero level-set interface.This not only precludes the direct traversal of the material interface through the mesh element during the topology optimization process,but also improves the accuracy of calculation.Additionally,the incorporation of a Helmholtz-type partial differential equation filter,relying solely on mesh information essential for finite element discretization,serves to regulate the topological complexity and the minimum feature size of the optimized structure.Leveraging these advantages,the topology optimization program demonstrates its versa-tility by successfully addressing various design problems,encompassing the minimum mean compliance problem and minimum energy dissipation problem.Ultimately,the result of numerical example indicates that the optimized structure exhibits a dis-tinct and smooth boundary,affirming the effective control over both topological complexity and the minimum feature size of the optimized structure.展开更多
As optimization problems continue to grow in complexity,the need for effective metaheuristic algorithms becomes increasingly evident.However,the challenge lies in identifying the right parameters and strategies for th...As optimization problems continue to grow in complexity,the need for effective metaheuristic algorithms becomes increasingly evident.However,the challenge lies in identifying the right parameters and strategies for these algorithms.In this paper,we introduce the adaptive multi-strategy Rabbit Algorithm(RA).RA is inspired by the social interactions of rabbits,incorporating elements such as exploration,exploitation,and adaptation to address optimization challenges.It employs three distinct subgroups,comprising male,female,and child rabbits,to execute a multi-strategy search.Key parameters,including distance factor,balance factor,and learning factor,strike a balance between precision and computational efficiency.We offer practical recommendations for fine-tuning five essential RA parameters,making them versatile and independent.RA is capable of autonomously selecting adaptive parameter settings and mutation strategies,enabling it to successfully tackle a range of 17 CEC05 benchmark functions with dimensions scaling up to 5000.The results underscore RA’s superior performance in large-scale optimization tasks,surpassing other state-of-the-art metaheuristics in convergence speed,computational precision,and scalability.Finally,RA has demonstrated its proficiency in solving complicated optimization problems in real-world engineering by completing 10 problems in CEC2020.展开更多
Cloud computing has become an essential technology for the management and processing of large datasets,offering scalability,high availability,and fault tolerance.However,optimizing data replication across multiple dat...Cloud computing has become an essential technology for the management and processing of large datasets,offering scalability,high availability,and fault tolerance.However,optimizing data replication across multiple data centers poses a significant challenge,especially when balancing opposing goals such as latency,storage costs,energy consumption,and network efficiency.This study introduces a novel Dynamic Optimization Algorithm called Dynamic Multi-Objective Gannet Optimization(DMGO),designed to enhance data replication efficiency in cloud environments.Unlike traditional static replication systems,DMGO adapts dynamically to variations in network conditions,system demand,and resource availability.The approach utilizes multi-objective optimization approaches to efficiently balance data access latency,storage efficiency,and operational costs.DMGO consistently evaluates data center performance and adjusts replication algorithms in real time to guarantee optimal system efficiency.Experimental evaluations conducted in a simulated cloud environment demonstrate that DMGO significantly outperforms conventional static algorithms,achieving faster data access,lower storage overhead,reduced energy consumption,and improved scalability.The proposed methodology offers a robust and adaptable solution for modern cloud systems,ensuring efficient resource consumption while maintaining high performance.展开更多
Current topology optimization methods for nonlinear continuum structures often suffer from low computational efficiency and limited applicability to complex nonlinear problems.To address these issues,this paper propos...Current topology optimization methods for nonlinear continuum structures often suffer from low computational efficiency and limited applicability to complex nonlinear problems.To address these issues,this paper proposes an improved bi-directional evolutionary structural optimization(BESO)method tailored for maximizing stiffness in nonlinear structures.The optimization program is developed in Python and can be combined with Abaqus software to facilitate finite element analysis(FEA).To accelerate the speed of optimization,a novel adaptive evolutionary ratio(ER)strategy based on the BESO method is introduced,with four distinct adaptive ER functions proposed.The Newton-Raphson method is utilized for iteratively solving nonlinear equilibrium equations,and the sensitivity information for updating design variables is derived using the adjoint method.Additionally,this study extends topology optimization to account for both material nonlinearity and geometric nonlinearity,analyzing the effects of various nonlinearities.A series of comparative studies are conducted using benchmark cases to validate the effectiveness of the proposed method.The results show that the BESO method with adaptive ER significantly improves the optimization efficiency.Compared to the BESO method with a fixed ER,the convergence speed of the four adaptive ER BESO methods is increased by 37.3%,26.7%,12%and 18.7%,respectively.Given that Abaqus is a powerful FEA platform,this method has the potential to be extended to large-scale engineering structures and to address more complex optimization problems.This research proposes an improved BESO method with novel adaptive ER,which significantly accelerates the optimization process and enables its application to topology optimization of nonlinear structures.展开更多
The increasing penetration of second-life battery energy storage systems(SLBESS)in power grids presents substantial challenges to system operation and control due to the heterogeneous characteristics and uncertain deg...The increasing penetration of second-life battery energy storage systems(SLBESS)in power grids presents substantial challenges to system operation and control due to the heterogeneous characteristics and uncertain degradation patterns of repurposed batteries.This paper presents a novel model-free adaptive voltage controlembedded dung beetle-inspired heuristic optimization algorithmfor optimal SLBESS capacity configuration and power dispatch.To simultaneously address the computational complexity and ensure system stability,this paper develops a comprehensive bilevel optimization framework.At the upper level,a dung beetle optimization algorithmdetermines the optimal SLBESS capacity configuration byminimizing total lifecycle costswhile incorporating the charging/discharging power trajectories derived from the model-free adaptive voltage control strategy.At the lower level,a health-priority power dispatch optimization model intelligently allocates power demands among heterogeneous battery groups based on their real-time operational states,state-of-health variations,and degradation constraints.The proposed model-free approach circumvents the need for complex battery charging/discharging power controlmodels and extensive historical data requirements whilemaintaining system stability through adaptive controlmechanisms.A novel cycle life degradation model is developed to quantify the relationship between remaining useful life,depth of discharge,and operational patterns.The integrated framework enables simultaneous strategic planning and operational control,ensuring both economic efficiency and extended battery lifespan.The effectiveness of the proposed method is validated through comprehensive case studies on hybrid energy storage systems,demonstrating superior computational efficiency,robust performance across different network configurations,and significant improvements in battery utilization compared to conventional approaches.展开更多
Accurate forecasting of wind power is crucial for ensuring the reliable operation of the electrical grid.Due to the impact of various factors,wind power forecasting presents a significant challenge.This paper presents...Accurate forecasting of wind power is crucial for ensuring the reliable operation of the electrical grid.Due to the impact of various factors,wind power forecasting presents a significant challenge.This paper presents the model that integrates Osprey and adaptive T-distribution dung beetle algorithm for optimizing a convolutional neural network.The CNN-BiLSTM-Attention model combines bidirectional long short-term memory neural networks with an attention mechanism,thereby improving the accuracy of wind power generation predictions.The original data is subjected to Variational Mode Decomposition(VMD)for analysis,taking into account the fluctuations in wind power across different periods.The BiLSTM network with short-term memory processes time-series wind power data,yielding an optimal predictive performance.The integration of the osprey algorithm and adaptive T-distribution within the Dung Beetle Optimization Algorithm was utilized to optimize the hyperparameters of the CNN-BiLSTM-Attention model,thereby enhancing its predictive performance.To assess the efficacy of the CNN-BiLSTM-Attention algorithm,enhanced by Ospreys and adaptive T-distributed dung beetle algorithm,we conducted experiments using the CEC2021 benchmark function.The integrated Osprey and adaptive T-distribution Dung Beetle algorithm has excellent global optimization performance when dealing with complex optimization problems.The fusion of Osprey and the adaptive T-distribution Dung beetle algorithm optimized the CNN-BiLSTM-Attention algorithm as well as other optimization algorithms for ablation experiments.The results show that the improved algorithm performs well in predicting wind power.The experimental findings suggest that the model’s predictive efficiency has enhanced by a minimum of 17.74%.展开更多
The production mode of manufacturing industry presents characteristics of multiple varieties,small-batch and personalization,leading to frequent disturbances in workshop.Traditional centralized scheduling methods are ...The production mode of manufacturing industry presents characteristics of multiple varieties,small-batch and personalization,leading to frequent disturbances in workshop.Traditional centralized scheduling methods are difficult to achieve efficient and real-time production management under dynamic disturbance.In order to improve the intelligence and adaptability of production scheduler,a novel distributed scheduling architecture is proposed,which has the ability to autonomously allocate tasks and handle disturbances.All production tasks are scheduled through autonomous collaboration and decision-making between intelligent machines.Firstly,the multi-agent technology is applied to build a self-organizing manufacturing system,enabling each machine to be equipped with the ability of active information interaction and joint-action execution.Secondly,various self-organizing collaboration strategies are designed to effectively facilitate cooperation and competition among multiple agents,thereby flexibly achieving global perception of environmental state.To ensure the adaptability and superiority of production decisions in dynamic environment,deep reinforcement learning is applied to build a smart production scheduler:Based on the perceived environment state,the scheduler intelligently generates the optimal production strategy to guide the task allocation and resource configuration.The feasibility and effectiveness of the proposed method are verified through three experimental scenarios using a discrete manufacturing workshop as the test bed.Compared to heuristic dispatching rules,the proposed method achieves an average performance improvement of 34.0%in three scenarios in terms of order tardiness.The proposed system can provide a new reference for the design of smart manufacturing systems.展开更多
This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts...This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts perturbation amplitude based on task complexity and optimizes the perturbation direction based on the gradient direction in real time to enhance attack efficiency.Experimental results demonstrate that AMA elevates attack success rates from approximately 78.95%to 89.56%on visual question answering and from78.82%to 84.96%on visual reasoning tasks across representative vision-language benchmarks.These findings demonstrate AMA’s superior attack efficiency and reveal the vulnerability of current visual language models to carefully crafted adversarial examples,underscoring the need to enhance their robustness.展开更多
Model checking is crucial in statistical analyses and has garnered significant attention in the academic literature.However,certain challenges persist in scenarios that involve large-scale datasets and limited resourc...Model checking is crucial in statistical analyses and has garnered significant attention in the academic literature.However,certain challenges persist in scenarios that involve large-scale datasets and limited resource allocations.This research introduces a novel subsampling methodology for testing regression models with continuous and categorical predictors,referred to as the Subsampling Adaptive Projection-Test(SAPT).This innovative approach demonstrates substantial improvements in test power for both local and global alternatives,outperforming conventional uniform subsampling mechanisms.The authors rigorously establish the asymptotic properties of SAPT and delineate its maximum achievable power under asymptotic conditions.Comprehensive simulations and real-world dataset applications provide robust validation of the proposed theoretical propositions.展开更多
This article presents an adaptive intelligent control strategy applied to a lumped-parameter evaporator model,i.e.,a simplified dynamic representation treating the evaporator as a single thermal node with uniform temp...This article presents an adaptive intelligent control strategy applied to a lumped-parameter evaporator model,i.e.,a simplified dynamic representation treating the evaporator as a single thermal node with uniform temperature distribution,suitable for control design due to its balance between physical fidelity and computational simplicity.The controller uses a wavelet-based neural proportional,integral,derivative(PID)controller with IIR filtering(infinite impulse response).The dynamic model captures the essential heat and mass transfer phenomena through a nonlinear energy balance,where the cooling capacity“Qevap”is expressed as a non-linear function of the compressor frequency and the temperature difference,specifically,Q_(evap)=k_(1)u(T_(in)−T_(e))with u as compressor frequency,Te evaporator temperature,and Tin inlet fluid temperature.The operating conditions of the system,in general terms,focus on the following variables,the overall thermal capacity is 1000 J/K,typical for small-capacity heat exchangers,The mass flow is 0.05 kg/s,typical for secondary liquid cooling circuits,the overall loss coefficient of 50 W/K that corresponds to small evaporators with partial insulation,the temperatures(inlet)of 10℃and the temperature of environment of 25℃,thermal load of 200 W that corresponds to a small-scaled air conditioning applications.To handle system nonlinearities and improve control performance,aMorlet wavelet-based neural network(Wavenet)is used to dynamically adjust the PID gains online.An IIR filter is incorporated to smooth the adaptive gains,improving stability and reducing oscillations.In contrast to prior wavelet-or neural-adaptive PID controllers in HVAC applications,which typically adjust gains without explicit filtering or not tailored to evaporator dynamics,this work introduces the first PID–Wavenet scheme augmented with an IIR-based stabilization layer,specifically designed to address the combined challenges of nonlinear evaporator behavior,gain oscillation,and real-time implementability.The proposed controller(PID-Wavenet+IIR)is implemented and validated inMATLAB/Simulink,demonstrating superior performance compared to a conventional PID tuned using Simulink’s auto-tuning function.Key results include a reduction in settling time from 13.3 to 8.2 s,a reduction in overshoot from 3.5%to 0.8%,a reduction in steady-state error from 0.12℃ to 0.02℃and a 13%reduction in energy overall consumption.The controller also exhibits greater robustness and adaptability under varying thermal loads.This explicit integration of wavelet-driven adaptation with IIR-filtered gain shaping constitutes the main methodological contribution and novelty of the work.These findings validate the effectiveness of the wavelet-based adaptive approach for advanced thermal management in refrigeration and HVAC systems,with potential applications in controlling variable-speed compressors,liquid chillers,and compact cooling units.展开更多
The acceleration and mode transition performance are two significant performances of Adaptive Cycle Engine(ACE).However,separating the processes of acceleration and mode transition will slow down the response speed of...The acceleration and mode transition performance are two significant performances of Adaptive Cycle Engine(ACE).However,separating the processes of acceleration and mode transition will slow down the response speed of thrust.Therefore,this paper proposes a multi-mode acceleration optimization control method that simultaneously performs ACE acceleration and mode transition.Firstly,an ACE component model with inlet flow characteristics was established,and the performance before and after mode transition were analyzed.Secondly,the principle of ACE acceleration optimization was analyzed,and the Front Variable Area Bypass Injector(FVABI)and Mode Selection Valve(MSV)were adopted in the acceleration process.Finally,based on the Sequential Quadratic Programming(SQP)algorithm,considering the degradation effects of engine components,we optimize the acceleration control plan for fuel and variable geometry mechanisms.The simulation results show that at the subsonic cruise point,the ACE multi-mode acceleration optimization control method can shorten the acceleration time from idle to middle state by 30.33%,and accelerate the thrust response speed by 33.72%.When the compressor flow rate of ACE deteriorates by 2% and the high-pressure turbine efficiency deteriorates by 4%,the adaptive acceleration control plan increases the high-pressure speed by 2.13% and thrust by about 6.82%;within the flight envelope,the acceleration time is reduced by more than 25%,and the thrust response speed is increased by more than 20%.展开更多
The exponential growth of data in recent years has introduced significant challenges in managing high-dimensional datasets,particularly in industrial contexts where efficient data handling and process innovation are c...The exponential growth of data in recent years has introduced significant challenges in managing high-dimensional datasets,particularly in industrial contexts where efficient data handling and process innovation are critical.Feature selection,an essential step in data-driven process innovation,aims to identify the most relevant features to improve model interpretability,reduce complexity,and enhance predictive accuracy.To address the limitations of existing feature selection methods,this study introduces a novel wrapper-based feature selection framework leveraging the recently proposed Arctic Puffin Optimization(APO)algorithm.Specifically,we incorporate a specialized conversion mechanism to effectively adapt APO from continuous optimization to discrete,binary feature selection problems.Moreover,we introduce a fully parallelized implementation of APO in which both the search operators and fitness evaluations are executed concurrently using MATLAB’s Parallel Computing Toolbox.This parallel design significantly improves runtime efficiency and scalability,particularly for high-dimensional feature spaces.Extensive comparative experiments conducted against 14 state-of-the-art metaheuristic algorithms across 15 benchmark datasets reveal that the proposed APO-based method consistently achieves superior classification accuracy while selecting fewer features.These findings highlight the robustness and effectiveness of APO,validating its potential for advancing process innovation,economic productivity and smart city application in real-world machine learning scenarios.展开更多
基金Supported by the National Natural Science Foundation of China(12071133)Natural Science Foundation of Henan Province(252300421993)Key Scientific Research Project of Higher Education Institutions in Henan Province(25B110005)。
文摘In this paper,an adaptive cubic regularisation algorithm based on affine scaling methods(ARCBASM)is proposed for solving nonlinear equality constrained programming with nonnegative constraints on variables.From the optimality conditions of the problem,we introduce appropriate affine matrix and construct an affine scaling ARC subproblem with linearized constraints.Composite step methods and reduced Hessian methods are applied to tackle the linearized constraints.As a result,a standard unconstrained ARC subproblem is deduced and its solution can supply sufficient decrease.The fraction to the boundary rule maintains the strict feasibility(for nonnegative constraints on variables)of every iteration point.Reflection techniques are employed to prevent the iterations from approaching zero too early.Under mild assumptions,global convergence of the algorithm is analysed.Preliminary numerical results are reported.
基金supported by the National Science and Technology Council(NSTC),Taiwan,under grant number 114-2221-E-182-041-MY3by Chang Gung University and Chang Gung Memorial Hospital under project number NERPD4Q0021.
文摘The outstanding growth in the applications of large language models(LLMs)demonstrates the significance of adaptive and efficient prompt engineering tactics.The existing methods may not be variable,vigorous and streamlined in different domains.The offered study introduces an immediate optimization outline,named PROMPTx-PE,that is going to yield a greater level of precision and strength when it comes to the assignments that are premised on LLM.The proposed systemfeatures a timely selection schemewhich is informed by reinforcement learning,a contextual layer and a dynamic weighting module which is regulated by Lyapunov-based stability guidelines.The PROMPTx-PE dynamically varies the exploration and exploitation of the prompt space,depending on real-time feedback and multi-objective reward development.Extensive testing on both benchmark(GLUE,SuperGLUE)and domain-specific data(Healthcare-QA and Industrial-NER)demonstrates a large best performance to be 89.4%and a strong robustness disconnect with under 3%computation expense.The results confirm the effectiveness,consistency,and scalability of PROMPTx-PE as a platform of adaptive prompt engineering based on recent uses of LLMs.
基金supported by the National Natural Science Foundation of China(NSFC)under Grant number:82171965.
文摘Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning scenarios.In this work,we propose an Adaptive Meta-Loss Network(Adaptive-MLN)that learns to generate taskagnostic loss functions tailored to evolving classification problems.Unlike traditional methods that rely on static objectives,Adaptive-MLN treats the loss function itself as a trainable component,parameterized by a shallow neural network.To enable flexible,gradient-free optimization,we introduce a hybrid evolutionary approach that combines GeneticAlgorithms(GA)for global exploration and Evolution Strategies(ES)for local refinement.This co-evolutionary process dynamically adjusts the loss landscape,improvingmodel generalization without relying on analytic gradients or handcrafted heuristics.Experimental evaluations on synthetic tasks and the CIFAR-10 andMNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy,convergence,and adaptability.
文摘The healthcare field is fraught with challenges associated with severe class imbalance,wherein such critical conditions like sepsis,cardiac arrest,and drug adverse reactions are rare but have dire clinical consequences.This paper presents a new framework,Deep Reinforcement Adaptive Gradient Optimization Network to Mining Rare Events(DRAGON-MINE),to demonstrate how deep reinforcement learning can be used synergistically with adaptive gradient optimization and address the inherent weaknesses of current methods in the prediction of rare health events.The suggested architecture uses a dual-pathway consisting of a reinforcement learning agent to dynamically reweigh samples and an adaptive gradient optimizer to follow novel learning rates.With extensive experiments on the MIMIC-IV and eICU-CRD datasets,DRAGON-MINE consistently outperforms recent state-of-the-art methods for sepsis,cardiac arrest,and adverse drug reaction prediction,achieving AUROC values of 92.3%and 91.6%for sepsis prediction on MIMIC-IV and eICU-CRD,respectively,while consistently outperforming Transformer-,CNN-RNN-,and Fed-Ensemble-based methods across all evaluated tasks and datasets,with particularly strong gains observed in precision-recall performance under severe class imbalance.With its high sensitivity(88.4%)and specificity(90.2%),DRAGON-MINE enables reliable early warning of rare clinical events in critical care settings while minimizing false alarms,supporting safer clinical decision support systems,and demonstrating strong potential for scalable deployment across multi-institutional intensive care environments through federated learning.
基金Supported by the National Key R&D Program of China (No.2022ZD0119000)the Natural Science Foundation of Shaanxi Province (No.2025JC-YBMS-736,2025JC-YBMS-343)Shaanxi Province Key Research and Development Project (2025CY-YBXM-061)。
文摘To address the limitations of the sand cat swarm optimization(SCSO) algorithm which are slow convergence and low accuracy in complex problems,this study proposes an improved SCSO(ISCSO) algorithm that integrates multiple enhancement strategies.Firstly,Kent chaotic mapping initializes the population for uniform distribution.Secondly,somersault foraging strategy is introduced during the search and attack phases,allowing the algorithm to escape local optima by intercepting evasive prey.Simultaneously,an adaptive Lévy flight strategy is incorporated into the attack phase to bolster global exploration.Finally,the vertical and horizontal crossover strategy is implemented to enhance population diversity.The performance of the proposed algorithm is evaluated using 16 benchmark test functions.The experimental results demonstrate that ISCSO significantly outperforms the original SCSO and shows notable advantages over other metaheuristic algorithms.Furthermore,application to a pressure vessel design problem verifies ISCSO's effectiveness in solving practical engineering optimization challenges.
基金supported in part by National Key R&D Program of China(2022YFF0610600).
文摘An optimization model has been established and solved to determine the optimal threshold value for the event-triggered self-adaptive optimization strategy,which aims to strike a balance between optimization performance and control load while ensuring continuous optimization.First,evaluation indicators are introduced to comprehensively analyze the impact of power fluctuations on the objective function and system voltage at both the system-wide and local levels.Based on these indicators,a multi-stage centralized optimization(MCO)is selectively applied,addressing system state deviations to achieve optimal operating states while maintaining a voltage security margin to ensure system safety.Then,distributed optimization(DO)is carried out at each bus with a renewable energy source or random load integration to accommodate short-term uncertainties using a self-adaptive reactive power algorithm.The optimal threshold value for event-triggered DO is calculated to balance control burden and optimization effectiveness.Utilizing the local state deviation evaluation indicator,unnecessary DOs are skipped when minor power fluctuations occur at the local level.Finally,following the linear superposition principle,event-triggered DOs executed at all distributed controllers collectively constitute the self-adaptive optimization strategy for the entire system.A case study on the IEEE New England 39-bus power system illustrates the effectiveness of the proposed strategy.
基金supported by the National Natural Science Foundation of China(No.62173107).
文摘Spaceborne antennas are essential for remote sensing,deep-space communication,and Earth observation,yet their trajectory planning is complicated by nonlinear base-manipulator coupling and antenna flexibility.To address these challenges,this paper proposes a multi-objective trajectory optimization framework.The system dynamics capture both nonlinear rigid-flexible coupling and antenna deformation through a reduced-order formulation.To enhance discretization efficiency,a predictive-terminal hp-adaptive pseudospectral method is employed,assigning collocation density based on task-phase characteristics:finer resolution is applied to dynamic segments requiring higher accuracy,especially near the terminal phase.This enables efficient transcription of the continuous-time problem into a Nonlinear Programming Problem(NLP).The resulting NLP is then solved using a multi-objective optimization strategy based on the nondominated sorting genetic algorithm II,which explores trade-offs among antenna pointing accuracy,energy consumption,and structural vibration.Numerical results demonstrate that the proposed method achieves a reduction of approximately 14.0% in control energy and 41.8%in peak actuation compared to a GPOPS-II baseline,while significantly enhancing vibration suppression.The resulting Pareto front reveals structured trade-offs and clustered solutions,offering robust and diverse options for precision,low-disturbance mission planning.
基金supported by the Major Science and Technology Project of PetroChina Company Limited“Research on Key Technologies for Enhancing Recovery in Tight Sandstone Gas Reservoirs”,specifically under its third sub-project:“Research on Integrated Fracturing,Drainage,and Production Technology to Enhance Single-Well Production in Water-Bearing Gas Reservoirs”(Grant number:2023ZZ25YJ03).
文摘To address the persistent challenge of dynamic mismatch between wellbore lifting capacity and reservoir fluid supply,and to establish a robust optimization framework for drainage operations in high-water-cut tight sandstone gas reservoirs,this study systematically investigates the graded optimization and dynamic adaptation of drainage gas recovery technologies.Production data from a representative tight gas field were first employed to forecast reservoir performance.The predictive reliability was rigorously validated through high-precision history matching,thereby providing a quantitatively consistent foundation for subsequent wellbore optimization.Building on this characterization,a coupled simulation framework was developed that integrates wellbore multiphase flow modeling with nodal analysis based on the Inflow Performance Relationship,IPR,and the Vertical Lift Performance,VLP.This coordinated approach enables comprehensive evaluation of process adaptability and dynamic optimization of foam-assisted drainage,mechanical pumping,and jet pumping systems under evolving water-gas ratio,WGR conditions.The results reveal that a progressively increasing water-gas ratio is the dominant factor driving the transition from chemically assisted drainage methods to mechanically enhanced lifting technologies.A distinct quantitative threshold is identified at WGR≈0.002,beyond which mechanical intervention becomes more effective and economically justified.For mechanical pumping and jet pumping systems,a parameter inversion optimization strategy constrained by the target bottomhole flowing pressure,Pwf,is proposed to ensure stable production while maintaining reservoir drawdown control.In particular,the nozzle-to-throat area ratio of the jet pump is identified as the key governing parameter influencing entrainment capacity and lifting efficiency.Moreover,a configuration characterized by small pump diameter,long stroke length,and low operating speed is demonstrated to satisfy drainage requirements while mitigating torque fluctuations,enhancing volumetric efficiency,and improving pump fillage stability.
基金supported by the National Natural Science Foundation of China(Grant Nos.12372200 and 12072242).
文摘Parameterized level-set method(PLSM)has been proposed and developed for many years,and is renowned for its efficacy in ad-dressing topology optimization challenges associated with intricate boundaries and nucleation of new holes.However,most pertinent investigations in the field rely predominantly on fixed background mesh,which is never remeshed.Consequently,the mesh element partitioned by material interface during the optimization process necessitates approximation by using artificial interpolation models to obtain its element stiffness or other properties.This paper introduces a novel approach to topology op-timization by integrating the PLSM with body-fitted adaptive mesh and Helmholtz-type filter.Primarily,combining the PLSM with body-fitted adaptive mesh enables the regeneration of mesh based on the zero level-set interface.This not only precludes the direct traversal of the material interface through the mesh element during the topology optimization process,but also improves the accuracy of calculation.Additionally,the incorporation of a Helmholtz-type partial differential equation filter,relying solely on mesh information essential for finite element discretization,serves to regulate the topological complexity and the minimum feature size of the optimized structure.Leveraging these advantages,the topology optimization program demonstrates its versa-tility by successfully addressing various design problems,encompassing the minimum mean compliance problem and minimum energy dissipation problem.Ultimately,the result of numerical example indicates that the optimized structure exhibits a dis-tinct and smooth boundary,affirming the effective control over both topological complexity and the minimum feature size of the optimized structure.
文摘As optimization problems continue to grow in complexity,the need for effective metaheuristic algorithms becomes increasingly evident.However,the challenge lies in identifying the right parameters and strategies for these algorithms.In this paper,we introduce the adaptive multi-strategy Rabbit Algorithm(RA).RA is inspired by the social interactions of rabbits,incorporating elements such as exploration,exploitation,and adaptation to address optimization challenges.It employs three distinct subgroups,comprising male,female,and child rabbits,to execute a multi-strategy search.Key parameters,including distance factor,balance factor,and learning factor,strike a balance between precision and computational efficiency.We offer practical recommendations for fine-tuning five essential RA parameters,making them versatile and independent.RA is capable of autonomously selecting adaptive parameter settings and mutation strategies,enabling it to successfully tackle a range of 17 CEC05 benchmark functions with dimensions scaling up to 5000.The results underscore RA’s superior performance in large-scale optimization tasks,surpassing other state-of-the-art metaheuristics in convergence speed,computational precision,and scalability.Finally,RA has demonstrated its proficiency in solving complicated optimization problems in real-world engineering by completing 10 problems in CEC2020.
文摘Cloud computing has become an essential technology for the management and processing of large datasets,offering scalability,high availability,and fault tolerance.However,optimizing data replication across multiple data centers poses a significant challenge,especially when balancing opposing goals such as latency,storage costs,energy consumption,and network efficiency.This study introduces a novel Dynamic Optimization Algorithm called Dynamic Multi-Objective Gannet Optimization(DMGO),designed to enhance data replication efficiency in cloud environments.Unlike traditional static replication systems,DMGO adapts dynamically to variations in network conditions,system demand,and resource availability.The approach utilizes multi-objective optimization approaches to efficiently balance data access latency,storage efficiency,and operational costs.DMGO consistently evaluates data center performance and adjusts replication algorithms in real time to guarantee optimal system efficiency.Experimental evaluations conducted in a simulated cloud environment demonstrate that DMGO significantly outperforms conventional static algorithms,achieving faster data access,lower storage overhead,reduced energy consumption,and improved scalability.The proposed methodology offers a robust and adaptable solution for modern cloud systems,ensuring efficient resource consumption while maintaining high performance.
基金Supported by National Natural Science Foundation of China(Grant No.52105271).
文摘Current topology optimization methods for nonlinear continuum structures often suffer from low computational efficiency and limited applicability to complex nonlinear problems.To address these issues,this paper proposes an improved bi-directional evolutionary structural optimization(BESO)method tailored for maximizing stiffness in nonlinear structures.The optimization program is developed in Python and can be combined with Abaqus software to facilitate finite element analysis(FEA).To accelerate the speed of optimization,a novel adaptive evolutionary ratio(ER)strategy based on the BESO method is introduced,with four distinct adaptive ER functions proposed.The Newton-Raphson method is utilized for iteratively solving nonlinear equilibrium equations,and the sensitivity information for updating design variables is derived using the adjoint method.Additionally,this study extends topology optimization to account for both material nonlinearity and geometric nonlinearity,analyzing the effects of various nonlinearities.A series of comparative studies are conducted using benchmark cases to validate the effectiveness of the proposed method.The results show that the BESO method with adaptive ER significantly improves the optimization efficiency.Compared to the BESO method with a fixed ER,the convergence speed of the four adaptive ER BESO methods is increased by 37.3%,26.7%,12%and 18.7%,respectively.Given that Abaqus is a powerful FEA platform,this method has the potential to be extended to large-scale engineering structures and to address more complex optimization problems.This research proposes an improved BESO method with novel adaptive ER,which significantly accelerates the optimization process and enables its application to topology optimization of nonlinear structures.
基金Financial support was provided by the State Grid Sichuan Electric Power Company Science and Technology Project“Key Research on Development Path Planning and Key Operation Technologies of New Rural Electrification Construction”under Grant No.52199623000G.
文摘The increasing penetration of second-life battery energy storage systems(SLBESS)in power grids presents substantial challenges to system operation and control due to the heterogeneous characteristics and uncertain degradation patterns of repurposed batteries.This paper presents a novel model-free adaptive voltage controlembedded dung beetle-inspired heuristic optimization algorithmfor optimal SLBESS capacity configuration and power dispatch.To simultaneously address the computational complexity and ensure system stability,this paper develops a comprehensive bilevel optimization framework.At the upper level,a dung beetle optimization algorithmdetermines the optimal SLBESS capacity configuration byminimizing total lifecycle costswhile incorporating the charging/discharging power trajectories derived from the model-free adaptive voltage control strategy.At the lower level,a health-priority power dispatch optimization model intelligently allocates power demands among heterogeneous battery groups based on their real-time operational states,state-of-health variations,and degradation constraints.The proposed model-free approach circumvents the need for complex battery charging/discharging power controlmodels and extensive historical data requirements whilemaintaining system stability through adaptive controlmechanisms.A novel cycle life degradation model is developed to quantify the relationship between remaining useful life,depth of discharge,and operational patterns.The integrated framework enables simultaneous strategic planning and operational control,ensuring both economic efficiency and extended battery lifespan.The effectiveness of the proposed method is validated through comprehensive case studies on hybrid energy storage systems,demonstrating superior computational efficiency,robust performance across different network configurations,and significant improvements in battery utilization compared to conventional approaches.
基金supported by the National Natural Science Foundation of China[Grant No.12371378]the Fujian Natural Science Foundation[Grant No.2022J01378,Grant No.2023J011127].
文摘Accurate forecasting of wind power is crucial for ensuring the reliable operation of the electrical grid.Due to the impact of various factors,wind power forecasting presents a significant challenge.This paper presents the model that integrates Osprey and adaptive T-distribution dung beetle algorithm for optimizing a convolutional neural network.The CNN-BiLSTM-Attention model combines bidirectional long short-term memory neural networks with an attention mechanism,thereby improving the accuracy of wind power generation predictions.The original data is subjected to Variational Mode Decomposition(VMD)for analysis,taking into account the fluctuations in wind power across different periods.The BiLSTM network with short-term memory processes time-series wind power data,yielding an optimal predictive performance.The integration of the osprey algorithm and adaptive T-distribution within the Dung Beetle Optimization Algorithm was utilized to optimize the hyperparameters of the CNN-BiLSTM-Attention model,thereby enhancing its predictive performance.To assess the efficacy of the CNN-BiLSTM-Attention algorithm,enhanced by Ospreys and adaptive T-distributed dung beetle algorithm,we conducted experiments using the CEC2021 benchmark function.The integrated Osprey and adaptive T-distribution Dung Beetle algorithm has excellent global optimization performance when dealing with complex optimization problems.The fusion of Osprey and the adaptive T-distribution Dung beetle algorithm optimized the CNN-BiLSTM-Attention algorithm as well as other optimization algorithms for ablation experiments.The results show that the improved algorithm performs well in predicting wind power.The experimental findings suggest that the model’s predictive efficiency has enhanced by a minimum of 17.74%.
基金supported by the Scientific Research Foundation of Nanjing Institute of Technology(No.YKJ202425)the National Natural Science Foundation of China(No.72301130).
文摘The production mode of manufacturing industry presents characteristics of multiple varieties,small-batch and personalization,leading to frequent disturbances in workshop.Traditional centralized scheduling methods are difficult to achieve efficient and real-time production management under dynamic disturbance.In order to improve the intelligence and adaptability of production scheduler,a novel distributed scheduling architecture is proposed,which has the ability to autonomously allocate tasks and handle disturbances.All production tasks are scheduled through autonomous collaboration and decision-making between intelligent machines.Firstly,the multi-agent technology is applied to build a self-organizing manufacturing system,enabling each machine to be equipped with the ability of active information interaction and joint-action execution.Secondly,various self-organizing collaboration strategies are designed to effectively facilitate cooperation and competition among multiple agents,thereby flexibly achieving global perception of environmental state.To ensure the adaptability and superiority of production decisions in dynamic environment,deep reinforcement learning is applied to build a smart production scheduler:Based on the perceived environment state,the scheduler intelligently generates the optimal production strategy to guide the task allocation and resource configuration.The feasibility and effectiveness of the proposed method are verified through three experimental scenarios using a discrete manufacturing workshop as the test bed.Compared to heuristic dispatching rules,the proposed method achieves an average performance improvement of 34.0%in three scenarios in terms of order tardiness.The proposed system can provide a new reference for the design of smart manufacturing systems.
基金funded by the Natural Science Foundation of Jiangsu Province(Program BK20240699)National Natural Science Foundation of China(Program 62402228).
文摘This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts perturbation amplitude based on task complexity and optimizes the perturbation direction based on the gradient direction in real time to enhance attack efficiency.Experimental results demonstrate that AMA elevates attack success rates from approximately 78.95%to 89.56%on visual question answering and from78.82%to 84.96%on visual reasoning tasks across representative vision-language benchmarks.These findings demonstrate AMA’s superior attack efficiency and reveal the vulnerability of current visual language models to carefully crafted adversarial examples,underscoring the need to enhance their robustness.
基金supported by the National Social Science Foundation of China under Grant No.21 BT1048the National Scientific Foundation of China under Grant Nos.12371276 and 12131006。
文摘Model checking is crucial in statistical analyses and has garnered significant attention in the academic literature.However,certain challenges persist in scenarios that involve large-scale datasets and limited resource allocations.This research introduces a novel subsampling methodology for testing regression models with continuous and categorical predictors,referred to as the Subsampling Adaptive Projection-Test(SAPT).This innovative approach demonstrates substantial improvements in test power for both local and global alternatives,outperforming conventional uniform subsampling mechanisms.The authors rigorously establish the asymptotic properties of SAPT and delineate its maximum achievable power under asymptotic conditions.Comprehensive simulations and real-world dataset applications provide robust validation of the proposed theoretical propositions.
文摘This article presents an adaptive intelligent control strategy applied to a lumped-parameter evaporator model,i.e.,a simplified dynamic representation treating the evaporator as a single thermal node with uniform temperature distribution,suitable for control design due to its balance between physical fidelity and computational simplicity.The controller uses a wavelet-based neural proportional,integral,derivative(PID)controller with IIR filtering(infinite impulse response).The dynamic model captures the essential heat and mass transfer phenomena through a nonlinear energy balance,where the cooling capacity“Qevap”is expressed as a non-linear function of the compressor frequency and the temperature difference,specifically,Q_(evap)=k_(1)u(T_(in)−T_(e))with u as compressor frequency,Te evaporator temperature,and Tin inlet fluid temperature.The operating conditions of the system,in general terms,focus on the following variables,the overall thermal capacity is 1000 J/K,typical for small-capacity heat exchangers,The mass flow is 0.05 kg/s,typical for secondary liquid cooling circuits,the overall loss coefficient of 50 W/K that corresponds to small evaporators with partial insulation,the temperatures(inlet)of 10℃and the temperature of environment of 25℃,thermal load of 200 W that corresponds to a small-scaled air conditioning applications.To handle system nonlinearities and improve control performance,aMorlet wavelet-based neural network(Wavenet)is used to dynamically adjust the PID gains online.An IIR filter is incorporated to smooth the adaptive gains,improving stability and reducing oscillations.In contrast to prior wavelet-or neural-adaptive PID controllers in HVAC applications,which typically adjust gains without explicit filtering or not tailored to evaporator dynamics,this work introduces the first PID–Wavenet scheme augmented with an IIR-based stabilization layer,specifically designed to address the combined challenges of nonlinear evaporator behavior,gain oscillation,and real-time implementability.The proposed controller(PID-Wavenet+IIR)is implemented and validated inMATLAB/Simulink,demonstrating superior performance compared to a conventional PID tuned using Simulink’s auto-tuning function.Key results include a reduction in settling time from 13.3 to 8.2 s,a reduction in overshoot from 3.5%to 0.8%,a reduction in steady-state error from 0.12℃ to 0.02℃and a 13%reduction in energy overall consumption.The controller also exhibits greater robustness and adaptability under varying thermal loads.This explicit integration of wavelet-driven adaptation with IIR-filtered gain shaping constitutes the main methodological contribution and novelty of the work.These findings validate the effectiveness of the wavelet-based adaptive approach for advanced thermal management in refrigeration and HVAC systems,with potential applications in controlling variable-speed compressors,liquid chillers,and compact cooling units.
基金supported in part by the National Natural Science Foundation of China(No.52372389)the Jiangsu Province Excellent Postdoctoral Program of China(No.2023ZB494)+1 种基金the Basic Research Program of Jiangsu Province,China(No.BK20241412)the National Science Foundation for Post-doctoral Scientists of China(No.2024M754131)。
文摘The acceleration and mode transition performance are two significant performances of Adaptive Cycle Engine(ACE).However,separating the processes of acceleration and mode transition will slow down the response speed of thrust.Therefore,this paper proposes a multi-mode acceleration optimization control method that simultaneously performs ACE acceleration and mode transition.Firstly,an ACE component model with inlet flow characteristics was established,and the performance before and after mode transition were analyzed.Secondly,the principle of ACE acceleration optimization was analyzed,and the Front Variable Area Bypass Injector(FVABI)and Mode Selection Valve(MSV)were adopted in the acceleration process.Finally,based on the Sequential Quadratic Programming(SQP)algorithm,considering the degradation effects of engine components,we optimize the acceleration control plan for fuel and variable geometry mechanisms.The simulation results show that at the subsonic cruise point,the ACE multi-mode acceleration optimization control method can shorten the acceleration time from idle to middle state by 30.33%,and accelerate the thrust response speed by 33.72%.When the compressor flow rate of ACE deteriorates by 2% and the high-pressure turbine efficiency deteriorates by 4%,the adaptive acceleration control plan increases the high-pressure speed by 2.13% and thrust by about 6.82%;within the flight envelope,the acceleration time is reduced by more than 25%,and the thrust response speed is increased by more than 20%.
文摘The exponential growth of data in recent years has introduced significant challenges in managing high-dimensional datasets,particularly in industrial contexts where efficient data handling and process innovation are critical.Feature selection,an essential step in data-driven process innovation,aims to identify the most relevant features to improve model interpretability,reduce complexity,and enhance predictive accuracy.To address the limitations of existing feature selection methods,this study introduces a novel wrapper-based feature selection framework leveraging the recently proposed Arctic Puffin Optimization(APO)algorithm.Specifically,we incorporate a specialized conversion mechanism to effectively adapt APO from continuous optimization to discrete,binary feature selection problems.Moreover,we introduce a fully parallelized implementation of APO in which both the search operators and fitness evaluations are executed concurrently using MATLAB’s Parallel Computing Toolbox.This parallel design significantly improves runtime efficiency and scalability,particularly for high-dimensional feature spaces.Extensive comparative experiments conducted against 14 state-of-the-art metaheuristic algorithms across 15 benchmark datasets reveal that the proposed APO-based method consistently achieves superior classification accuracy while selecting fewer features.These findings highlight the robustness and effectiveness of APO,validating its potential for advancing process innovation,economic productivity and smart city application in real-world machine learning scenarios.
