Wind farm layout optimization is a critical challenge in renewable energy development,especially in regions with complex terrain.Micro-siting of wind turbines has a significant impact on the overall efficiency and eco...Wind farm layout optimization is a critical challenge in renewable energy development,especially in regions with complex terrain.Micro-siting of wind turbines has a significant impact on the overall efficiency and economic viability of wind farm,where the wake effect,wind speed,types of wind turbines,etc.,have an impact on the output power of the wind farm.To solve the optimization problem of wind farm layout under complex terrain conditions,this paper proposes wind turbine layout optimization using different types of wind turbines,the aim is to reduce the influence of the wake effect and maximize economic benefits.The linear wake model is used for wake flow calculation over complex terrain.Minimizing the unit energy cost is taken as the objective function,considering that the objective function is affected by cost and output power,which influence each other.The cost function includes construction cost,installation cost,maintenance cost,etc.Therefore,a bi-level constrained optimization model is established,in which the upper-level objective function is to minimize the unit energy cost,and the lower-level objective function is to maximize the output power.Then,a hybrid evolutionary algorithm is designed according to the characteristics of the decision variables.The improved genetic algorithm and differential evolution are used to optimize the upper-level and lower-level objective functions,respectively,these evolutionary operations search for the optimal solution as much as possible.Finally,taking the roughness of different terrain,wind farms of different scales and different types of wind turbines as research scenarios,the optimal deployment is solved by using the algorithm in this paper,and four algorithms are compared to verify the effectiveness of the proposed algorithm.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
Accurate parameter extraction of photovoltaic(PV)models plays a critical role in enabling precise performance prediction,optimal system sizing,and effective operational control under diverse environmental conditions.W...Accurate parameter extraction of photovoltaic(PV)models plays a critical role in enabling precise performance prediction,optimal system sizing,and effective operational control under diverse environmental conditions.While a wide range of metaheuristic optimisation techniques have been applied to this problem,many existing methods are hindered by slow convergence rates,susceptibility to premature stagnation,and reduced accuracy when applied to complex multi-diode PV configurations.These limitations can lead to suboptimal modelling,reducing the efficiency of PV system design and operation.In this work,we propose an enhanced hybrid optimisation approach,the modified Spider Wasp Optimization(mSWO)with Opposition-Based Learning algorithm,which integrates the exploration and exploitation capabilities of the Spider Wasp Optimization(SWO)metaheuristic with the diversityenhancing mechanism of Opposition-Based Learning(OBL).The hybridisation is designed to dynamically expand the search space coverage,avoid premature convergence,and improve both convergence speed and precision in highdimensional optimisation tasks.The mSWO algorithm is applied to three well-established PV configurations:the single diode model(SDM),the double diode model(DDM),and the triple diode model(TDM).Real experimental current-voltage(I-V)datasets from a commercial PV module under standard test conditions(STC)are used for evaluation.Comparative analysis is conducted against eighteen advanced metaheuristic algorithms,including BSDE,RLGBO,GWOCS,MFO,EO,TSA,and SCA.Performance metrics include minimum,mean,and maximum root mean square error(RMSE),standard deviation(SD),and convergence behaviour over 30 independent runs.The results reveal that mSWO consistently delivers superior accuracy and robustness across all PV models,achieving the lowest RMSE values of 0.000986022(SDM),0.000982884(DDM),and 0.000982529(TDM),with minimal SD values,indicating remarkable repeatability.Convergence analyses further show that mSWO reaches optimal solutions more rapidly and with fewer oscillations than all competing methods,with the performance gap widening as model complexity increases.These findings demonstrate that mSWO provides a scalable,computationally efficient,and highly reliable framework for PV parameter extraction.Its adaptability to models of growing complexity suggests strong potential for broader applications in renewable energy systems,including performance monitoring,fault detection,and intelligent control,thereby contributing to the optimisation of next-generation solar energy solutions.展开更多
The moving morphable component(MMC)topology optimization method,as a typical explicit topology optimization method,has been widely concerned.In the MMC topology optimization framework,the surrogate material model is m...The moving morphable component(MMC)topology optimization method,as a typical explicit topology optimization method,has been widely concerned.In the MMC topology optimization framework,the surrogate material model is mainly used for finite element analysis at present,and the effectiveness of the surrogate material model has been fully confirmed.However,there are some accuracy problems when dealing with boundary elements using the surrogate material model,which will affect the topology optimization results.In this study,a boundary element reconstruction(BER)model is proposed based on the surrogate material model under the MMC topology optimization framework to improve the accuracy of topology optimization.The proposed BER model can reconstruct the boundary elements by refining the local meshes and obtaining new nodes in boundary elements.Then the density of boundary elements is recalculated using the new node information,which is more accurate than the original model.Based on the new density of boundary elements,the material properties and volume information of the boundary elements are updated.Compared with other finite element analysis methods,the BER model is simple and feasible and can improve computational accuracy.Finally,the effectiveness and superiority of the proposed method are verified by comparing it with the optimization results of the original surrogate material model through several numerical examples.展开更多
In response to the challenges of inadequate predictive accuracy and limited generalization capability in data-driven modeling for the mechanical properties of the cold-rolled strip steel,a predictive modeling method n...In response to the challenges of inadequate predictive accuracy and limited generalization capability in data-driven modeling for the mechanical properties of the cold-rolled strip steel,a predictive modeling method named RFR-WOA is developed based on random forest regression(RFR)and whale optimization algorithm(WOA).Firstly,using Pearson and Spearman correlation analysis and Gini coefficient importance ranking on an actual production dataset containing 37,878 samples,22 key variables are selected as model inputs from 112 variables that affect mechanical properties.Subsequently,an RFR-based predictive model for the mechanical properties of cold-rolled strip steel is constructed.Then,with the combination of the coefficient of determination(R^(2))and root mean square error as the optimization objective,the hyperparameters of RFR model are iteratively optimized using WOA,and better predictive effectiveness is obtained.Finally,the mechanical properties prediction model based on RFR-WOA is compared with models established using deep neural networks,convolutional neural networks,and other methods.The test results on 9469 samples of actual production data show that the model developed present has better predictive accuracy and generalization capability.展开更多
Ship air emissions are recognized as one of the key concerns of the maritime industry.Competent authorities have issued various regulations to manage air emissions from ships.Although the authorities are policy makers...Ship air emissions are recognized as one of the key concerns of the maritime industry.Competent authorities have issued various regulations to manage air emissions from ships.Although the authorities are policy makers,the effectiveness of policies is up to the shipping industry who operates the vessels and terminals to fulfill maritime transportation works.Given this characteristic,bi-level optimization model has been widely adopted in studies that optimize policy design or evaluate its effectiveness.The framework of a typical bi-level optimization model for ship emission management problem is given to show the basic structure of similar issues.A series of applications of bi-level optimization model in managing ship emissions is reviewed,including cases of Energy Efficiency Design Index,Emissions Control Area,Market Based Measure,Carbon Intensity Indicator,and Vessel Speed Reduction Incentive Program.We hope this paper can enlighten scholars interested in this area and provide help for them.展开更多
Electrical parking lots(EPLs)play a vital role in the current energy system to achieve the decarbonization goal.This paper proposes a novel structure for integrating EPLs into a multi-carrier energy system(MCES)using ...Electrical parking lots(EPLs)play a vital role in the current energy system to achieve the decarbonization goal.This paper proposes a novel structure for integrating EPLs into a multi-carrier energy system(MCES)using a Stackelberg game theory approach.The bi-level optimization is used to model the Stackelberg game.Within this bi-level optimization model,the MCES operator minimizes the MCES cost by participating in the upstream energy market at the upper level,and the EPL operators maximize their profits by participating in the local energy market between the MCES operator and themselves at the lower level.At the upper level,the MCES operator faces uncertainties in the wind and PV systems.The bi-level multi-objective information gap decision theory(MO-IGDT)is employed to address uncertainties at the upper level of the Stackelberg game problem,resulting in a nested bi-level optimization model.The nested bi-level optimization problem is converted into a mixed-integer linear programming(MILP)optimization problem using Karush–Kuhn–Tucker(KKT)conditions.The main research assumptions pertain to EPLs’privacy and the KKT-based approach.The results demonstrate that increasing the incentive/penalty price for self-sufficiency programs from 0.0$/%to 0.2$/%,with a 50%self-sufficiency target,can reduce MCES operation costs by 10.19%.展开更多
In the era of massive data,the study of distributed data is a significant topic.Model averaging can be effectively applied to distributed data by combining information from all machines.For linear models,the model ave...In the era of massive data,the study of distributed data is a significant topic.Model averaging can be effectively applied to distributed data by combining information from all machines.For linear models,the model averaging approach has been developed in the context of distributed data.However,further investigation is needed for more complex models.In this paper,the authors propose a distributed optimal model averaging approach based on multivariate additive models,which approximates unknown functions using B-splines allowing each machine to have a different smoothing degree.To utilize the information from the covariance matrix of dependent errors in multivariate multiple regressions,the authors use the Mahalanobis distance to construct a Mallows-type weight choice criterion.The criterion can be computed by transmitting information between the local machines and the center machine in two steps.The authors demonstrate the asymptotic optimality of the proposed model averaging estimator when the covariates are subject to uncertainty,and obtain the convergence rate of the weight vector to the theoretically optimal weights.The results remain novel even for additive models with a single response variable.The numerical examples show that the proposed method yields good performance.展开更多
The roller is one of the fundamental elements of ore belt conveyor systems since it supports,guides,and directs material on the belt.This component comprises a body(the external tube)that rotates around a fixed shaft ...The roller is one of the fundamental elements of ore belt conveyor systems since it supports,guides,and directs material on the belt.This component comprises a body(the external tube)that rotates around a fixed shaft supported by easels.The external tube and shaft of rollers used in ore conveyor belts are mostly made of steel,resulting in high mass,hindering maintenance and replacement.Aiming to achieve mass reduction,we conducted a structural optimization of a roller with a polymeric external tube(hereafter referred to as a polymeric roller),seeking the optimal values for two design parameters:the inner diameter of the external tube and the shaft diameter.The optimization was constrained by admissible values for maximum stress,maximum deflection and misalignment angle between the shaft and bearings.A finite element model was built in Ansys Workbench to obtain the structural response of the system.The roller considered is composed of an external tube made of high-density polyethylene(HDPE),bearing seats of polyamide 6(PA6),and a steel shaft.To characterize the polymeric materials(HDPE and PA6),stress relaxation tests were conducted,and the data on shear modulus variation over time were inserted into the model to calculate Prony series terms to account for viscoelastic effects.The roller optimization was performed using surrogate modeling based on radial basis functions,with the Globalized Bounded Nelder-Mead(GBNM)algorithm as the optimizer.Two optimization cases were conducted.In the first case,concerning the roller’s initial material settings,the designs found violated the constraints and could not reduce mass.In the second case,by using PA6 in both bearing seats and the tube,a design configuration was found that respected all constraints and reduced the roller mass by 15.5%,equivalent to 5.15 kg.This study is among the first to integrate experimentally obtained viscoelastic data into the surrogate-based optimization of polymeric rollers,combining methodological innovation with industrial relevance.展开更多
Transformer models face significant computational challenges in private inference(PI).Existing optimization methods often rely on isolated techniques,neglecting joint structural and operational improvements.We propose...Transformer models face significant computational challenges in private inference(PI).Existing optimization methods often rely on isolated techniques,neglecting joint structural and operational improvements.We propose IG-3D,a unified framework that integrates structured compression and operator approximation through accurate importance assessment.Our approach first evaluates attention head importance using Integrated Gradients(IG),offering greater stability and theoretical soundness than gradient-based methods.We then apply a threedimensional optimization:(1)structurally pruning redundant attention heads;(2)replacing Softmax with adaptive polynomial approximation to avoid exponential computations;(3)implementing layer-wise GELU substitution to accommodate different layer characteristics.A joint thresholdmechanism coordinates compression across dimensions under accuracy constraints.Experimental results on the GLUE benchmark show that our method achieves an average 2.9×speedup in inference latency and a 50%reduction in communication cost,while controlling the accuracy loss within 2.3%,demonstrating significant synergistic effects and a superior accuracy-efficiency trade-off compared to single-technique optimization strategies.展开更多
High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of ...High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of labels.Moreover,an optimization problem that fully considers all dependencies between features and labels is difficult to solve.In this study,we propose a novel regression-basedmulti-label feature selectionmethod that integrates mutual information to better exploit the underlying data structure.By incorporating mutual information into the regression formulation,the model captures not only linear relationships but also complex non-linear dependencies.The proposed objective function simultaneously considers three types of relationships:(1)feature redundancy,(2)featurelabel relevance,and(3)inter-label dependency.These three quantities are computed usingmutual information,allowing the proposed formulation to capture nonlinear dependencies among variables.These three types of relationships are key factors in multi-label feature selection,and our method expresses them within a unified formulation,enabling efficient optimization while simultaneously accounting for all of them.To efficiently solve the proposed optimization problem under non-negativity constraints,we develop a gradient-based optimization algorithm with fast convergence.Theexperimental results on sevenmulti-label datasets show that the proposed method outperforms existingmulti-label feature selection techniques.展开更多
In mixture experiments,the observed response is determined by the relative proportions of the components,consequently rendering the experimental region a simplex.This paper focuses primarily on the optimal designs of ...In mixture experiments,the observed response is determined by the relative proportions of the components,consequently rendering the experimental region a simplex.This paper focuses primarily on the optimal designs of mixture experiments that involve process variables.Prior research has extensively delved into optimal orthogonal block designs for some classic mixture models with process variables.Based on the framework of general blending models,this paper proposes a class of symmetric linear mixture models,which can be regarded as a generalization of many existing ones.Under the orthogonal blocking conditions,orthogonal block designs are devised through Latin squares in the presence of process variables.TheD-,A-,and E-optimality criteria are utilized to obtain optimal designs at the boundary of the simplex in the case of 3 components.As the values of the exponents change,numerically derived optimal design points are presented to illustrate the pattern of their variations,and to verify the consistency of the results with previous research on some specific symmetric general blending models.展开更多
Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural ...Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural artifacts online.As an effective medium,posters serve to attract public attention and facilitate broader engagement with cultural artifacts.However,existing poster generation methods mainly rely on fixed templates and manual design,which limits their scalability and adaptability to the diverse visual and semantic features of the artifacts.Therefore,we propose CAPGen,an automated aesthetic Cultural Artifacts Poster Generation framework built on a Multimodal Large Language Model(MLLM)with integrated iterative optimization.During our research,we collaborated with designers to define principles of graphic design for cultural artifact posters,to guide the MLLM in generating layout parameters.Later,we generated these parameters into posters.Finally,we refined the posters using an MLLM integrated with a multi-round iterative optimization mechanism.Qualitative results show that CAPGen consistently outperforms baseline methods in both visual quality and aesthetic performance.Furthermore,ablation studies indicate that the prompt,iterative optimization mechanism,and design principles significantly enhance the effectiveness of poster generation.展开更多
Rapid development of power-to-gas technology provides a potential solution for virtual power plants(VPP)to achieve near-zero carbon emissions.In this paper,a bi-level hybrid stochastic/robust optimization model is pro...Rapid development of power-to-gas technology provides a potential solution for virtual power plants(VPP)to achieve near-zero carbon emissions.In this paper,a bi-level hybrid stochastic/robust optimization model is proposed for low-carbon VPP day-ahead dispatch considering uncertainties from renewable generation and market prices.First,Karush-Kuhn-Tucker optimality conditions are employed to convert the bi-level model to a single level one.Next,the single level problem is decomposed into a master problem in the base case and several subproblems in extreme cases,which can then be solved by using the column-and-constraint generation algorithm iteratively.Numerical results indicate the proposed approach can effectively satisfy system operation constraints including the carbon emission limit,enhance computational efficiency and algorithm robustness compared with the stochastic method,and improve VPP revenue compared with the robust method.展开更多
In the construction and maintenance for large space equipment,it is essential to ensure the control accuracy and improve the dexterity of the space manipulator.In this paper,a FiniteTime Convergence Kinematic Control(...In the construction and maintenance for large space equipment,it is essential to ensure the control accuracy and improve the dexterity of the space manipulator.In this paper,a FiniteTime Convergence Kinematic Control(FTCKC)added with Acceleration Level Dexterity Optimization(ALDO)scheme is proposed to solve the kinematic uncertainty and dexterity optimization problems of redundant space manipulators.Concretely,distinguishing from the asymptotic convergence property of traditional adaptive Jacobian methods,the FTCKC scheme is adopted to construct the equality constraint to address the model uncertainty problem,and its error can converge within a finite time.Subsequently,the dexterity index is reconstructed at acceleration level by a multi-level target handling method.Then,the equality constraint,optimization task,and limit constraints are reformulated as a quadratic programming problem.Moreover,a Recurrent Neural Network(RNN)is engineered for the constructed FTCKC-ALDO scheme.Finally,the superiority of the FTCKC-ALDO-RNN scheme is verified by experiments.展开更多
In the wireless energy transmission service composition optimization problem,a key challenge is accurately capturing users’preferences for service criteria under complex influencing factors,and optimally selecting a ...In the wireless energy transmission service composition optimization problem,a key challenge is accurately capturing users’preferences for service criteria under complex influencing factors,and optimally selecting a composition solution under their budget constraints.Existing studies typically evaluate satisfaction solely based on energy transmission capacity,while overlooking critical factors such as price and trustworthiness of the provider,leading to a mismatch between optimization outcomes and user needs.To address this gap,we construct a user satisfaction evaluation model for multi-user and multi-provider scenarios,systematically incorporating service price,transmission capacity,and trustworthiness into the satisfaction assessment framework.Furthermore,we propose a Budget-Aware Preference Adjustment Model that predicts users’baseline preference weights from historical data and dynamically adjusts them according to budget levels,thereby reflecting user preferences more realistically under varying budget constraints.In addition,to tackle the composition optimization problem,we develop a ReflectiveEvolutionary Large Language Model—Guided Ant Colony Optimization algorithm,which leverages the reflective evolution capability of large language models to iteratively generate and refine heuristic information that guides the search process.Experimental results demonstrate that the proposed framework effectively integrates personalized preferences with budget sensitivity,accurately predicts users’preferences,and significantly enhances their satisfaction under complex constraints.展开更多
Early and accurate detection of bone cancer and marrow cell abnormalities is critical for timely intervention and improved patient outcomes.This paper proposes a novel hybrid deep learning framework that integrates a ...Early and accurate detection of bone cancer and marrow cell abnormalities is critical for timely intervention and improved patient outcomes.This paper proposes a novel hybrid deep learning framework that integrates a Convolutional Neural Network(CNN)with a Bidirectional Long Short-Term Memory(BiLSTM)architecture,optimized using the Firefly Optimization algorithm(FO).The proposed CNN-BiLSTM-FO model is tailored for structured biomedical data,capturing both local patterns and sequential dependencies in diagnostic features,while the Firefly Algorithm fine-tunes key hyperparameters to maximize predictive performance.The approach is evaluated on two benchmark biomedical datasets:one comprising diagnostic data for bone cancer detection and another for identifying marrow cell abnormalities.Experimental results demonstrate that the proposed method outperforms standard deep learning models,including CNN,LSTM,BiLSTM,and CNN-LSTM hybrids,significantly.The CNNBiLSTM-FO model achieves an accuracy of 98.55%for bone cancer detection and 96.04%for marrow abnormality classification.The paper also presents a detailed complexity analysis of the proposed algorithm and compares its performance across multiple evaluation metrics such as precision,recall,F1-score,and AUC.The results confirm the effectiveness of the firefly-based optimization strategy in improving classification accuracy and model robustness.This work introduces a scalable and accurate diagnostic solution that holds strong potential for integration into intelligent clinical decision-support systems.展开更多
Given the power system balancing challenges induced by high-penetration renewable energy integration,this study systematically reviews international balancing mechanism practices and conducts an in-depth deconstructio...Given the power system balancing challenges induced by high-penetration renewable energy integration,this study systematically reviews international balancing mechanism practices and conducts an in-depth deconstruction of Germany’s balancing group mechanism(BGM).Building on this foundation,this research pioneers the integration of virtual power plants(VPPs)with the BGM in the Chinese context to overcome the limitations of traditional single-entity regulation models in flexibility provision and economic efficiency.A balancing responsibility framework centered on VPPs is innovatively proposed and a regional multi-entity collaboration and bi-level responsibility transfer architecture is constructed.This architecture enables cross-layer coordinated optimization of regional system costs and VPP revenues.The upper layer minimizes regional operational costs,whereas the lower layer enhances the operational revenues of VPPs through dynamic gaming between deviation regulation service income and penalty costs.Compared with traditional centralized regulation models,the proposed method reduces system operational costs by 29.1%in typical regional cases and increases VPP revenues by 24.9%.These results validate its dual optimization of system economics and participant incentives through market mechanisms,providing a replicable theoretical paradigm and practical pathway for designing balancing mechanisms in new power systems.展开更多
Traditional demand response(DR)programs for energy-intensive industries(EIIs)primarily rely on electricity price signals and often overlook carbon emission factors,limiting their effectiveness in supporting lowcarbon ...Traditional demand response(DR)programs for energy-intensive industries(EIIs)primarily rely on electricity price signals and often overlook carbon emission factors,limiting their effectiveness in supporting lowcarbon transitions.To address this challenge,this paper proposes an electricity–carbon integratedDR strategy based on a bi-level collaborative optimization framework that coordinates the interaction between the grid and EIIs.At the upper level,the grid operatorminimizes generation and curtailment costs by optimizing unit commitment while determining real-time electricity prices and dynamic carbon emission factors.At the lower level,EIIs respond to these dual signals by minimizing their combined electricity and carbon trading costs,considering their participation in medium-and long-term electricity markets,day-ahead spot markets,and carbon emissions trading schemes.The model accounts for direct and indirect carbon emissions,distributed photovoltaic(PV)generation,and battery energy storage systems.This interaction is structured as a Stackelberg game,where the grid acts as the leader and EIIs as followers,enabling dynamic feedback between pricing signals and load response.Simulation studies on an improved IEEE 30-bus system,with a cement plant as a representative user form EIIs,show that the proposed strategy reduces user-side carbon emissions by 7.95% and grid-side generation cost by 4.66%,though the user’s energy cost increases by 7.80% due to carbon trading.Theresults confirmthat the joint guidance of electricity and carbon prices effectively reshapes user load profiles,encourages peak shaving,and improves PV utilization.This coordinated approach not only achieves emission reduction and cost efficiency but also offers a theoretical and practical foundation for integrating carbon pricing into demand-side energy management in future low-carbon power systems.展开更多
This study introduces a novel approach to addressing the challenges of high-dimensional variables and strong nonlinearity in reservoir production and layer configuration optimization.For the first time,relational mach...This study introduces a novel approach to addressing the challenges of high-dimensional variables and strong nonlinearity in reservoir production and layer configuration optimization.For the first time,relational machine learning models are applied in reservoir development optimization.Traditional regression-based models often struggle in complex scenarios,but the proposed relational and regression-based composite differential evolution(RRCODE)method combines a Gaussian naive Bayes relational model with a radial basis function network regression model.This integration effectively captures complex relationships in the optimization process,improving both accuracy and convergence speed.Experimental tests on a multi-layer multi-channel reservoir model,the Egg reservoir model,and a real-field reservoir model(the S reservoir)demonstrate that RRCODE significantly reduces water injection and production volumes while increasing economic returns and cumulative oil recovery.Moreover,the surrogate models employed in RRCODE exhibit lightweight characteristics with low computational overhead.These results highlight RRCODE's superior performance in the integrated optimization of reservoir production and layer configurations,offering more efficient and economically viable solutions for oilfield development.展开更多
基金supported by the National Natural Science Foundation of China[Grant No.12461035]Qinghai University Students Innovative Training Program Project[2024-QX-57].
文摘Wind farm layout optimization is a critical challenge in renewable energy development,especially in regions with complex terrain.Micro-siting of wind turbines has a significant impact on the overall efficiency and economic viability of wind farm,where the wake effect,wind speed,types of wind turbines,etc.,have an impact on the output power of the wind farm.To solve the optimization problem of wind farm layout under complex terrain conditions,this paper proposes wind turbine layout optimization using different types of wind turbines,the aim is to reduce the influence of the wake effect and maximize economic benefits.The linear wake model is used for wake flow calculation over complex terrain.Minimizing the unit energy cost is taken as the objective function,considering that the objective function is affected by cost and output power,which influence each other.The cost function includes construction cost,installation cost,maintenance cost,etc.Therefore,a bi-level constrained optimization model is established,in which the upper-level objective function is to minimize the unit energy cost,and the lower-level objective function is to maximize the output power.Then,a hybrid evolutionary algorithm is designed according to the characteristics of the decision variables.The improved genetic algorithm and differential evolution are used to optimize the upper-level and lower-level objective functions,respectively,these evolutionary operations search for the optimal solution as much as possible.Finally,taking the roughness of different terrain,wind farms of different scales and different types of wind turbines as research scenarios,the optimal deployment is solved by using the algorithm in this paper,and four algorithms are compared to verify the effectiveness of the proposed algorithm.
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funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R442)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Accurate parameter extraction of photovoltaic(PV)models plays a critical role in enabling precise performance prediction,optimal system sizing,and effective operational control under diverse environmental conditions.While a wide range of metaheuristic optimisation techniques have been applied to this problem,many existing methods are hindered by slow convergence rates,susceptibility to premature stagnation,and reduced accuracy when applied to complex multi-diode PV configurations.These limitations can lead to suboptimal modelling,reducing the efficiency of PV system design and operation.In this work,we propose an enhanced hybrid optimisation approach,the modified Spider Wasp Optimization(mSWO)with Opposition-Based Learning algorithm,which integrates the exploration and exploitation capabilities of the Spider Wasp Optimization(SWO)metaheuristic with the diversityenhancing mechanism of Opposition-Based Learning(OBL).The hybridisation is designed to dynamically expand the search space coverage,avoid premature convergence,and improve both convergence speed and precision in highdimensional optimisation tasks.The mSWO algorithm is applied to three well-established PV configurations:the single diode model(SDM),the double diode model(DDM),and the triple diode model(TDM).Real experimental current-voltage(I-V)datasets from a commercial PV module under standard test conditions(STC)are used for evaluation.Comparative analysis is conducted against eighteen advanced metaheuristic algorithms,including BSDE,RLGBO,GWOCS,MFO,EO,TSA,and SCA.Performance metrics include minimum,mean,and maximum root mean square error(RMSE),standard deviation(SD),and convergence behaviour over 30 independent runs.The results reveal that mSWO consistently delivers superior accuracy and robustness across all PV models,achieving the lowest RMSE values of 0.000986022(SDM),0.000982884(DDM),and 0.000982529(TDM),with minimal SD values,indicating remarkable repeatability.Convergence analyses further show that mSWO reaches optimal solutions more rapidly and with fewer oscillations than all competing methods,with the performance gap widening as model complexity increases.These findings demonstrate that mSWO provides a scalable,computationally efficient,and highly reliable framework for PV parameter extraction.Its adaptability to models of growing complexity suggests strong potential for broader applications in renewable energy systems,including performance monitoring,fault detection,and intelligent control,thereby contributing to the optimisation of next-generation solar energy solutions.
基金supported by the Science and Technology Research Project of Henan Province(242102241055)the Industry-University-Research Collaborative Innovation Base on Automobile Lightweight of“Science and Technology Innovation in Central Plains”(2024KCZY315)the Opening Fund of State Key Laboratory of Structural Analysis,Optimization and CAE Software for Industrial Equipment(GZ2024A03-ZZU).
文摘The moving morphable component(MMC)topology optimization method,as a typical explicit topology optimization method,has been widely concerned.In the MMC topology optimization framework,the surrogate material model is mainly used for finite element analysis at present,and the effectiveness of the surrogate material model has been fully confirmed.However,there are some accuracy problems when dealing with boundary elements using the surrogate material model,which will affect the topology optimization results.In this study,a boundary element reconstruction(BER)model is proposed based on the surrogate material model under the MMC topology optimization framework to improve the accuracy of topology optimization.The proposed BER model can reconstruct the boundary elements by refining the local meshes and obtaining new nodes in boundary elements.Then the density of boundary elements is recalculated using the new node information,which is more accurate than the original model.Based on the new density of boundary elements,the material properties and volume information of the boundary elements are updated.Compared with other finite element analysis methods,the BER model is simple and feasible and can improve computational accuracy.Finally,the effectiveness and superiority of the proposed method are verified by comparing it with the optimization results of the original surrogate material model through several numerical examples.
基金supported by National Natural Science Foundation of China(Grant 62573375)the Natural Science Foundation of Hebei Province(Grant F2024203038)+2 种基金the Science and Technology Research and Development Plan Project of Qinhuangdao City(Grant 202302B048)the Provincial Key Laboratory Performance Subsidy Project(Grant 22567612H)the Shandong Provincial Natural Science Foundation Youth Project(ZR2023QF044)。
文摘In response to the challenges of inadequate predictive accuracy and limited generalization capability in data-driven modeling for the mechanical properties of the cold-rolled strip steel,a predictive modeling method named RFR-WOA is developed based on random forest regression(RFR)and whale optimization algorithm(WOA).Firstly,using Pearson and Spearman correlation analysis and Gini coefficient importance ranking on an actual production dataset containing 37,878 samples,22 key variables are selected as model inputs from 112 variables that affect mechanical properties.Subsequently,an RFR-based predictive model for the mechanical properties of cold-rolled strip steel is constructed.Then,with the combination of the coefficient of determination(R^(2))and root mean square error as the optimization objective,the hyperparameters of RFR model are iteratively optimized using WOA,and better predictive effectiveness is obtained.Finally,the mechanical properties prediction model based on RFR-WOA is compared with models established using deep neural networks,convolutional neural networks,and other methods.The test results on 9469 samples of actual production data show that the model developed present has better predictive accuracy and generalization capability.
基金supported by the National Natural Science Foundation of China(72071173,71831008).
文摘Ship air emissions are recognized as one of the key concerns of the maritime industry.Competent authorities have issued various regulations to manage air emissions from ships.Although the authorities are policy makers,the effectiveness of policies is up to the shipping industry who operates the vessels and terminals to fulfill maritime transportation works.Given this characteristic,bi-level optimization model has been widely adopted in studies that optimize policy design or evaluate its effectiveness.The framework of a typical bi-level optimization model for ship emission management problem is given to show the basic structure of similar issues.A series of applications of bi-level optimization model in managing ship emissions is reviewed,including cases of Energy Efficiency Design Index,Emissions Control Area,Market Based Measure,Carbon Intensity Indicator,and Vessel Speed Reduction Incentive Program.We hope this paper can enlighten scholars interested in this area and provide help for them.
基金supported by the first Cycle of ARG Grant No.ARG01-0504-230073,from the Qatar Research,Development and Innovation(QRDI)Council,Qatar.The findings herein reflect the work,and are solely the responsibility,of the authors.The authors also gratefully acknowledge support from Qatar University.
文摘Electrical parking lots(EPLs)play a vital role in the current energy system to achieve the decarbonization goal.This paper proposes a novel structure for integrating EPLs into a multi-carrier energy system(MCES)using a Stackelberg game theory approach.The bi-level optimization is used to model the Stackelberg game.Within this bi-level optimization model,the MCES operator minimizes the MCES cost by participating in the upstream energy market at the upper level,and the EPL operators maximize their profits by participating in the local energy market between the MCES operator and themselves at the lower level.At the upper level,the MCES operator faces uncertainties in the wind and PV systems.The bi-level multi-objective information gap decision theory(MO-IGDT)is employed to address uncertainties at the upper level of the Stackelberg game problem,resulting in a nested bi-level optimization model.The nested bi-level optimization problem is converted into a mixed-integer linear programming(MILP)optimization problem using Karush–Kuhn–Tucker(KKT)conditions.The main research assumptions pertain to EPLs’privacy and the KKT-based approach.The results demonstrate that increasing the incentive/penalty price for self-sufficiency programs from 0.0$/%to 0.2$/%,with a 50%self-sufficiency target,can reduce MCES operation costs by 10.19%.
基金supported by Youth Academic Innocation Team Construction project of Capital University of Economics and Business under Grant No.QNTD202303supported by the Beijing Outstanding Young Scientist Program under Grant No.JWZQ20240101027the National Natural Science Foundation of China under Grant Nos.12031016,12531012 and 12426308。
文摘In the era of massive data,the study of distributed data is a significant topic.Model averaging can be effectively applied to distributed data by combining information from all machines.For linear models,the model averaging approach has been developed in the context of distributed data.However,further investigation is needed for more complex models.In this paper,the authors propose a distributed optimal model averaging approach based on multivariate additive models,which approximates unknown functions using B-splines allowing each machine to have a different smoothing degree.To utilize the information from the covariance matrix of dependent errors in multivariate multiple regressions,the authors use the Mahalanobis distance to construct a Mallows-type weight choice criterion.The criterion can be computed by transmitting information between the local machines and the center machine in two steps.The authors demonstrate the asymptotic optimality of the proposed model averaging estimator when the covariates are subject to uncertainty,and obtain the convergence rate of the weight vector to the theoretically optimal weights.The results remain novel even for additive models with a single response variable.The numerical examples show that the proposed method yields good performance.
基金funded by Vale S.A.company(www.vale.com)and the Institute of Technology Vale(ITV—www.itv.org),grant number SAP 4600048682.
文摘The roller is one of the fundamental elements of ore belt conveyor systems since it supports,guides,and directs material on the belt.This component comprises a body(the external tube)that rotates around a fixed shaft supported by easels.The external tube and shaft of rollers used in ore conveyor belts are mostly made of steel,resulting in high mass,hindering maintenance and replacement.Aiming to achieve mass reduction,we conducted a structural optimization of a roller with a polymeric external tube(hereafter referred to as a polymeric roller),seeking the optimal values for two design parameters:the inner diameter of the external tube and the shaft diameter.The optimization was constrained by admissible values for maximum stress,maximum deflection and misalignment angle between the shaft and bearings.A finite element model was built in Ansys Workbench to obtain the structural response of the system.The roller considered is composed of an external tube made of high-density polyethylene(HDPE),bearing seats of polyamide 6(PA6),and a steel shaft.To characterize the polymeric materials(HDPE and PA6),stress relaxation tests were conducted,and the data on shear modulus variation over time were inserted into the model to calculate Prony series terms to account for viscoelastic effects.The roller optimization was performed using surrogate modeling based on radial basis functions,with the Globalized Bounded Nelder-Mead(GBNM)algorithm as the optimizer.Two optimization cases were conducted.In the first case,concerning the roller’s initial material settings,the designs found violated the constraints and could not reduce mass.In the second case,by using PA6 in both bearing seats and the tube,a design configuration was found that respected all constraints and reduced the roller mass by 15.5%,equivalent to 5.15 kg.This study is among the first to integrate experimentally obtained viscoelastic data into the surrogate-based optimization of polymeric rollers,combining methodological innovation with industrial relevance.
文摘Transformer models face significant computational challenges in private inference(PI).Existing optimization methods often rely on isolated techniques,neglecting joint structural and operational improvements.We propose IG-3D,a unified framework that integrates structured compression and operator approximation through accurate importance assessment.Our approach first evaluates attention head importance using Integrated Gradients(IG),offering greater stability and theoretical soundness than gradient-based methods.We then apply a threedimensional optimization:(1)structurally pruning redundant attention heads;(2)replacing Softmax with adaptive polynomial approximation to avoid exponential computations;(3)implementing layer-wise GELU substitution to accommodate different layer characteristics.A joint thresholdmechanism coordinates compression across dimensions under accuracy constraints.Experimental results on the GLUE benchmark show that our method achieves an average 2.9×speedup in inference latency and a 50%reduction in communication cost,while controlling the accuracy loss within 2.3%,demonstrating significant synergistic effects and a superior accuracy-efficiency trade-off compared to single-technique optimization strategies.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2020-NR049579).
文摘High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of labels.Moreover,an optimization problem that fully considers all dependencies between features and labels is difficult to solve.In this study,we propose a novel regression-basedmulti-label feature selectionmethod that integrates mutual information to better exploit the underlying data structure.By incorporating mutual information into the regression formulation,the model captures not only linear relationships but also complex non-linear dependencies.The proposed objective function simultaneously considers three types of relationships:(1)feature redundancy,(2)featurelabel relevance,and(3)inter-label dependency.These three quantities are computed usingmutual information,allowing the proposed formulation to capture nonlinear dependencies among variables.These three types of relationships are key factors in multi-label feature selection,and our method expresses them within a unified formulation,enabling efficient optimization while simultaneously accounting for all of them.To efficiently solve the proposed optimization problem under non-negativity constraints,we develop a gradient-based optimization algorithm with fast convergence.Theexperimental results on sevenmulti-label datasets show that the proposed method outperforms existingmulti-label feature selection techniques.
基金supported by the National Natural Science Foundation of China[grant numbers 12071329,12471246].
文摘In mixture experiments,the observed response is determined by the relative proportions of the components,consequently rendering the experimental region a simplex.This paper focuses primarily on the optimal designs of mixture experiments that involve process variables.Prior research has extensively delved into optimal orthogonal block designs for some classic mixture models with process variables.Based on the framework of general blending models,this paper proposes a class of symmetric linear mixture models,which can be regarded as a generalization of many existing ones.Under the orthogonal blocking conditions,orthogonal block designs are devised through Latin squares in the presence of process variables.TheD-,A-,and E-optimality criteria are utilized to obtain optimal designs at the boundary of the simplex in the case of 3 components.As the values of the exponents change,numerically derived optimal design points are presented to illustrate the pattern of their variations,and to verify the consistency of the results with previous research on some specific symmetric general blending models.
基金supported by the National Key Research and Development Program of China(2023YFF0906502)the Postgraduate Research and Innovation Project of Hunan Province under Grant(CX20240473).
文摘Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural artifacts online.As an effective medium,posters serve to attract public attention and facilitate broader engagement with cultural artifacts.However,existing poster generation methods mainly rely on fixed templates and manual design,which limits their scalability and adaptability to the diverse visual and semantic features of the artifacts.Therefore,we propose CAPGen,an automated aesthetic Cultural Artifacts Poster Generation framework built on a Multimodal Large Language Model(MLLM)with integrated iterative optimization.During our research,we collaborated with designers to define principles of graphic design for cultural artifact posters,to guide the MLLM in generating layout parameters.Later,we generated these parameters into posters.Finally,we refined the posters using an MLLM integrated with a multi-round iterative optimization mechanism.Qualitative results show that CAPGen consistently outperforms baseline methods in both visual quality and aesthetic performance.Furthermore,ablation studies indicate that the prompt,iterative optimization mechanism,and design principles significantly enhance the effectiveness of poster generation.
基金supported by the Shenzhen Science and Technology Program(JCYJ20210324130811031)Tsinghua Shenzhen International Graduate School Interdisciplinary Research and Innovation Fund(JC2021004).
文摘Rapid development of power-to-gas technology provides a potential solution for virtual power plants(VPP)to achieve near-zero carbon emissions.In this paper,a bi-level hybrid stochastic/robust optimization model is proposed for low-carbon VPP day-ahead dispatch considering uncertainties from renewable generation and market prices.First,Karush-Kuhn-Tucker optimality conditions are employed to convert the bi-level model to a single level one.Next,the single level problem is decomposed into a master problem in the base case and several subproblems in extreme cases,which can then be solved by using the column-and-constraint generation algorithm iteratively.Numerical results indicate the proposed approach can effectively satisfy system operation constraints including the carbon emission limit,enhance computational efficiency and algorithm robustness compared with the stochastic method,and improve VPP revenue compared with the robust method.
基金supported by the National Natural Science Foundation of China(Nos.92148203 and T2388101)。
文摘In the construction and maintenance for large space equipment,it is essential to ensure the control accuracy and improve the dexterity of the space manipulator.In this paper,a FiniteTime Convergence Kinematic Control(FTCKC)added with Acceleration Level Dexterity Optimization(ALDO)scheme is proposed to solve the kinematic uncertainty and dexterity optimization problems of redundant space manipulators.Concretely,distinguishing from the asymptotic convergence property of traditional adaptive Jacobian methods,the FTCKC scheme is adopted to construct the equality constraint to address the model uncertainty problem,and its error can converge within a finite time.Subsequently,the dexterity index is reconstructed at acceleration level by a multi-level target handling method.Then,the equality constraint,optimization task,and limit constraints are reformulated as a quadratic programming problem.Moreover,a Recurrent Neural Network(RNN)is engineered for the constructed FTCKC-ALDO scheme.Finally,the superiority of the FTCKC-ALDO-RNN scheme is verified by experiments.
基金supported by the National Natural Science Foundation of China under Grant 62472264the Natural Science Distinguished Youth Foundation of Shandong Province under Grant ZR2025QA13。
文摘In the wireless energy transmission service composition optimization problem,a key challenge is accurately capturing users’preferences for service criteria under complex influencing factors,and optimally selecting a composition solution under their budget constraints.Existing studies typically evaluate satisfaction solely based on energy transmission capacity,while overlooking critical factors such as price and trustworthiness of the provider,leading to a mismatch between optimization outcomes and user needs.To address this gap,we construct a user satisfaction evaluation model for multi-user and multi-provider scenarios,systematically incorporating service price,transmission capacity,and trustworthiness into the satisfaction assessment framework.Furthermore,we propose a Budget-Aware Preference Adjustment Model that predicts users’baseline preference weights from historical data and dynamically adjusts them according to budget levels,thereby reflecting user preferences more realistically under varying budget constraints.In addition,to tackle the composition optimization problem,we develop a ReflectiveEvolutionary Large Language Model—Guided Ant Colony Optimization algorithm,which leverages the reflective evolution capability of large language models to iteratively generate and refine heuristic information that guides the search process.Experimental results demonstrate that the proposed framework effectively integrates personalized preferences with budget sensitivity,accurately predicts users’preferences,and significantly enhances their satisfaction under complex constraints.
文摘Early and accurate detection of bone cancer and marrow cell abnormalities is critical for timely intervention and improved patient outcomes.This paper proposes a novel hybrid deep learning framework that integrates a Convolutional Neural Network(CNN)with a Bidirectional Long Short-Term Memory(BiLSTM)architecture,optimized using the Firefly Optimization algorithm(FO).The proposed CNN-BiLSTM-FO model is tailored for structured biomedical data,capturing both local patterns and sequential dependencies in diagnostic features,while the Firefly Algorithm fine-tunes key hyperparameters to maximize predictive performance.The approach is evaluated on two benchmark biomedical datasets:one comprising diagnostic data for bone cancer detection and another for identifying marrow cell abnormalities.Experimental results demonstrate that the proposed method outperforms standard deep learning models,including CNN,LSTM,BiLSTM,and CNN-LSTM hybrids,significantly.The CNNBiLSTM-FO model achieves an accuracy of 98.55%for bone cancer detection and 96.04%for marrow abnormality classification.The paper also presents a detailed complexity analysis of the proposed algorithm and compares its performance across multiple evaluation metrics such as precision,recall,F1-score,and AUC.The results confirm the effectiveness of the firefly-based optimization strategy in improving classification accuracy and model robustness.This work introduces a scalable and accurate diagnostic solution that holds strong potential for integration into intelligent clinical decision-support systems.
基金supported by the National Natural Science Foundation of China(no.72471087)Beijing Nova Program(no.20250484853)+1 种基金Beijing Natural Science Foundation(no.9242015)National Social Science Foundation of China(no.24&ZD111).
文摘Given the power system balancing challenges induced by high-penetration renewable energy integration,this study systematically reviews international balancing mechanism practices and conducts an in-depth deconstruction of Germany’s balancing group mechanism(BGM).Building on this foundation,this research pioneers the integration of virtual power plants(VPPs)with the BGM in the Chinese context to overcome the limitations of traditional single-entity regulation models in flexibility provision and economic efficiency.A balancing responsibility framework centered on VPPs is innovatively proposed and a regional multi-entity collaboration and bi-level responsibility transfer architecture is constructed.This architecture enables cross-layer coordinated optimization of regional system costs and VPP revenues.The upper layer minimizes regional operational costs,whereas the lower layer enhances the operational revenues of VPPs through dynamic gaming between deviation regulation service income and penalty costs.Compared with traditional centralized regulation models,the proposed method reduces system operational costs by 29.1%in typical regional cases and increases VPP revenues by 24.9%.These results validate its dual optimization of system economics and participant incentives through market mechanisms,providing a replicable theoretical paradigm and practical pathway for designing balancing mechanisms in new power systems.
基金supported by the Science and Technology Project of Yunnan Power Grid Co.,Ltd.under Grant No.YNKJXM20222410.
文摘Traditional demand response(DR)programs for energy-intensive industries(EIIs)primarily rely on electricity price signals and often overlook carbon emission factors,limiting their effectiveness in supporting lowcarbon transitions.To address this challenge,this paper proposes an electricity–carbon integratedDR strategy based on a bi-level collaborative optimization framework that coordinates the interaction between the grid and EIIs.At the upper level,the grid operatorminimizes generation and curtailment costs by optimizing unit commitment while determining real-time electricity prices and dynamic carbon emission factors.At the lower level,EIIs respond to these dual signals by minimizing their combined electricity and carbon trading costs,considering their participation in medium-and long-term electricity markets,day-ahead spot markets,and carbon emissions trading schemes.The model accounts for direct and indirect carbon emissions,distributed photovoltaic(PV)generation,and battery energy storage systems.This interaction is structured as a Stackelberg game,where the grid acts as the leader and EIIs as followers,enabling dynamic feedback between pricing signals and load response.Simulation studies on an improved IEEE 30-bus system,with a cement plant as a representative user form EIIs,show that the proposed strategy reduces user-side carbon emissions by 7.95% and grid-side generation cost by 4.66%,though the user’s energy cost increases by 7.80% due to carbon trading.Theresults confirmthat the joint guidance of electricity and carbon prices effectively reshapes user load profiles,encourages peak shaving,and improves PV utilization.This coordinated approach not only achieves emission reduction and cost efficiency but also offers a theoretical and practical foundation for integrating carbon pricing into demand-side energy management in future low-carbon power systems.
基金supported by the National Natural Science Foundation of China under Grant 52325402,52274057,and 52074340the National Key R&D Program of China under Grant 2023YFB4104200+2 种基金the Major Scientific and Technological Projects of CNOOC under Grant CCL2022RCPS0397RSN111 Project under Grant B08028China Scholarship Council under Grant 202306450108.
文摘This study introduces a novel approach to addressing the challenges of high-dimensional variables and strong nonlinearity in reservoir production and layer configuration optimization.For the first time,relational machine learning models are applied in reservoir development optimization.Traditional regression-based models often struggle in complex scenarios,but the proposed relational and regression-based composite differential evolution(RRCODE)method combines a Gaussian naive Bayes relational model with a radial basis function network regression model.This integration effectively captures complex relationships in the optimization process,improving both accuracy and convergence speed.Experimental tests on a multi-layer multi-channel reservoir model,the Egg reservoir model,and a real-field reservoir model(the S reservoir)demonstrate that RRCODE significantly reduces water injection and production volumes while increasing economic returns and cumulative oil recovery.Moreover,the surrogate models employed in RRCODE exhibit lightweight characteristics with low computational overhead.These results highlight RRCODE's superior performance in the integrated optimization of reservoir production and layer configurations,offering more efficient and economically viable solutions for oilfield development.
