The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-gener...The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-generation(5G)networks transformed mobile broadband and machine-type communications at massive scales,their properties of scaling,interference management,and latency remain a limitation in dense high mobility settings.To overcome these limitations,artificial intelligence(AI)and unmanned aerial vehicles(UAVs)have emerged as potential solutions to develop versatile,dynamic,and energy-efficient communication systems.The study proposes an AI-based UAV architecture that utilizes cooperative reinforcement learning(CoRL)to manage an autonomous network.The UAVs collaborate by sharing local observations and real-time state exchanges to optimize user connectivity,movement directions,allocate power,and resource distribution.Unlike conventional centralized or autonomous methods,CoRL involves joint state sharing and conflict-sensitive reward shaping,which ensures fair coverage,less interference,and enhanced adaptability in a dynamic urban environment.Simulations conducted in smart city scenarios with 10 UAVs and 50 ground users demonstrate that the proposed CoRL-based UAV system increases user coverage by up to 10%,achieves convergence 40%faster,and reduces latency and energy consumption by 30%compared with centralized and decentralized baselines.Furthermore,the distributed nature of the algorithm ensures scalability and flexibility,making it well-suited for future large-scale 6G deployments.The results highlighted that AI-enabled UAV systems enhance connectivity,support ultra-reliable low-latency communications(URLLC),and improve 6G network efficiency.Future work will extend the framework with adaptive modulation,beamforming-aware positioning,and real-world testbed deployment.展开更多
Reagents are optimized for the simultaneous determination of trace amounts of Cu^(2+), Cd^(2+) and Co^(2+) in zinc sulfate solution, which contains an extremely large excess of Zn^(2+). First, the reagents and their d...Reagents are optimized for the simultaneous determination of trace amounts of Cu^(2+), Cd^(2+) and Co^(2+) in zinc sulfate solution, which contains an extremely large excess of Zn^(2+). First, the reagents and their doses for the experiment are selected according to the characteristics of the zinc sulfate solution. Then, the reagent doses are optimized by analyzing the influence of reagent dose on the polarographic parameters(i.e. half-wave potential E_(1/2) and limiting diffusion current I_p). Finally, the optimization results are verified by simultaneously determining trace amounts of Cu^(2+), Cd^(2+) and Co^(2+) in the presence of an extremely large excess of Zn^(2+). The determination results indicate that the optimized reagents exhibit wide linearity, low detection limits, high accuracy and good precision for the simultaneous determination of trace amounts of Cu^(2+), Cd^(2+) and Co^(2+) in the presence of an extremely large excess of Zn^(2+).展开更多
A strategy of developing on-line optimization intelligent systems based on combiningflowsheeting simulation and optimization package with artificial neural networks(ANN)is presented inthis paper.A number of optimizati...A strategy of developing on-line optimization intelligent systems based on combiningflowsheeting simulation and optimization package with artificial neural networks(ANN)is presented inthis paper.A number of optimization cases for a certain chemical plant are obtained off-line byusing PROCESS-Ⅱ or other flowsheeting programming with optimization.Then,taking these cases astraining examples,we establish a neural network systems which can be used on-line as an optimizer toobtain setpoints from input data sampled from distributed control system through gross error detectionand data reconciliation procedures.Such an on-line optimizer possesses two advantages over nonlinearprogramming package:first of all,there is no convergence problem for the trained ANN to be usedonline;secondly,the frequency for setpoints updating is not limited because only algebraic calculationrather than optimization is required to be carried out on-line.Here two key problems ofimplementing ANN approaches to the on-line optimization展开更多
This paper presents a new non-linear formulation of the classical Vortex Lattice Method （VLM） approach for calculating the aerodynamic properties of lifting surfaces. The method accounts for the effects of viscosity...This paper presents a new non-linear formulation of the classical Vortex Lattice Method （VLM） approach for calculating the aerodynamic properties of lifting surfaces. The method accounts for the effects of viscosity, and due to its low computational cost, it represents a very good tool to perform rapid and accurate wing design and optimization procedures. The mathematical model is constructed by using two-dimensional viscous analyses of the wing span-wise sections, according to strip theory, and then coupling the strip viscous forces with the forces generated by the vortex rings distributed on the wing camber surface, calculated with a fully three-dimensional vortex lifting law. The numerical results obtained with the proposed method are validated with experimental data and show good agreement in predicting both the lift and pitching moment, as well as in predicting the wing drag. The method is applied to modifying the wing of an Unmanned Aerial System to increase its aerodynamic efficiency and to calculate the drag reductions obtained by an upper surface morphing technique for an adaptable regional aircraft wing.展开更多
The characteristics and distribution law of electromagnetic environment around substations with different levels of voltage were studied,and the main influencing factors were discussed. Meanwhile,a scheme for locating...The characteristics and distribution law of electromagnetic environment around substations with different levels of voltage were studied,and the main influencing factors were discussed. Meanwhile,a scheme for locating monitoring points suitable for an on-line monitoring system of electromagnetic environment was proposed.展开更多
6-DOF non-linear mechanics model of powerplant hydraulic mount system isestablished. Optimum design of the powerplant hydraulic mount system is made with the hydraulicmount parameters as variables and with uncoupling ...6-DOF non-linear mechanics model of powerplant hydraulic mount system isestablished. Optimum design of the powerplant hydraulic mount system is made with the hydraulicmount parameters as variables and with uncoupling of energy, rational disposition of naturefrequency and minimum of reactive force at mount's location as objective functions. And based on theoptimum design, software named ODPHMS (optimum design of powerplant hydraulic mount system) used inpowerplant mount system optimum design is developed.展开更多
For high-purity distillation processes,it is difficult to achieve a good direct product quality control using traditional proportional-integral-differential(PID)control or multivariable predictive control technique du...For high-purity distillation processes,it is difficult to achieve a good direct product quality control using traditional proportional-integral-differential(PID)control or multivariable predictive control technique due to some difficulties,such as long response time,many un-measurable disturbances,and the reliability and precision issues of product quality soft-sensors.In this paper,based on the first principle analysis and dynamic simulation of a distillation process,a new predictive control scheme is proposed by using the split ratio of distillate flow rate to that of bottoms as an essential controlled variable.Correspondingly,a new strategy with integrated control and on-line optimization is developed,which consists of model predictive control of the split ratio,surrogate model based on radial basis function neural network for optimization,and modified differential evolution optimization algorithm. With the strategy,the process achieves its steady state quickly,so more profit can be obtained.The proposed strategy has been successfully applied to a gas separation plant for more than three years,which shows that the strategy is feasible and effective.展开更多
On-line heating rolling mill which could efficiently preheat sheet and apply tensile force on both ends of the sheet along rolling direction(RD)was used to investigate the effect of tension on mechanical behavior and ...On-line heating rolling mill which could efficiently preheat sheet and apply tensile force on both ends of the sheet along rolling direction(RD)was used to investigate the effect of tension on mechanical behavior and shape quality of magnesium sheets.For revealing the infl uence mechanism,many analysis techniques including optical microscope,electron backscattered diffraction,macrotexture and transmission electron microscope were performed.The shape defect,edge wave,could be eliminated under higher tension along RD,which was attributed to more uniform distribution of microstructure and microstrain.Nevertheless,it is undesirable that the forward tensile force exceeds 3 kN in present work because the strength decreased for high recrystallization level when the tensile force is beyond this value.Furthermore,the main deformation mode was still slip during rolling process despite of accompanying twining,e.g.,double twins,but more prismatic slip activated when tensile force exceeds 3 kN.The distribution of shear bands was affected by the applied tensile force that they appear as"V"shape along RD at a low forward or backward tensile force,while they appear as reticulate shape under applied tensile force of 5 kN.展开更多
A relevance vector machine (RVM) based fault diagnosis method was presented for non-linear circuits. In order to simplify RVM classifier, parameters selection based on particle swarm optimization (PSO) and preprocessi...A relevance vector machine (RVM) based fault diagnosis method was presented for non-linear circuits. In order to simplify RVM classifier, parameters selection based on particle swarm optimization (PSO) and preprocessing technique based on the kurtosis and entropy of signals were used. Firstly, sinusoidal inputs with different frequencies were applied to the circuit under test (CUT). Then, the resulting frequency responses were sampled to generate features. The frequency response was sampled to compute its kurtosis and entropy, which can show the information capacity of signal. By analyzing the output signals, the proposed method can detect and identify faulty components in circuits. The results indicate that the fault classes can be classified correctly for at least 99% of the test data in example circuit. And the proposed method can diagnose hard and soft faults.展开更多
The ratooning system enhances agricultural efficiency by reducing secondary sowing and resource input while maintaining rice yield parity with double cropping.However,the prolonged growth duration of the rice ratoonin...The ratooning system enhances agricultural efficiency by reducing secondary sowing and resource input while maintaining rice yield parity with double cropping.However,the prolonged growth duration of the rice ratooning system extends the exposure window to Magnaporthe oryzae infection,thereby elevating the probability of disease incidence.展开更多
Burundi faces major agricultural constraints, including land fragmentation, soil erosion, limited access to inputs, inadequate infrastructure and demographic pressures that exacerbate food insecurity. In order to addr...Burundi faces major agricultural constraints, including land fragmentation, soil erosion, limited access to inputs, inadequate infrastructure and demographic pressures that exacerbate food insecurity. In order to address the multiple challenges faced by farmers in rural areas, a study on improving agricultural productivity and food security in Burundi through optimized land use and diversified farming practices in agroforestry systems has been carried out. The study area is the communes of Giheta and Rutegama, all located in Burundi’s humid plateau livelihood zone, and involved 164 households grouped in coffee growing cooperatives supervised by the cooperative consortium COCOCA. The study uses a mathematical programming model to determine optimal crop selection based on factors such as production costs, yields and market demand. The findings of the study revealed significant insights into the demographic and socio-economic characteristics of the sampled population. Notably, 98.8% of respondents were engaged in agriculture, confirming the predominantly agricultural nature of Burundi. The results indicated that maize is the most important crop, occupying 33.9% of the average total cultivated area, followed by cassava at 26.5% and bananas at 19.4%. Together, these three crops accounted for a substantial portion of the total cultivated area, highlighting their significance in local agriculture. Beans and potatoes also play a role, occupying 14.4% and smaller areas, respectively. In terms of profitability, the study provides a detailed analysis of profit margins by crop. Bananas emerges as the most profitable crop, with a profit margin of 97.3%, followed closely by cassava at 96.1% and rice at 90.5%. These crops not only offered substantial yields relative to their production costs but also benefited from strong market demand. Other crops, such as beans (71.3%), coffee (70.3%), and vegetables (54.5%), also demonstrated considerable profitability, although they occupied smaller cultivated areas. Conversely, crops like pigeon peas (4.1%), potatoes (7.6%), and sweet potatoes (7.6%) exhibited the lowest profit margins, which may discourage farmers from investing in them unless other incentives, such as ecological benefits or local consumption needs, are present. Regarding the results, we therefore recommend to promote policies supporting agroforestry, improve market access and develop infrastructure to exploit these benefits.展开更多
In this paper,the optimal control of non-linear switching system is investigated without knowing the system dynamics.First,the Hamilton-Jacobi-Bellman(HJB)equation is derived with the consideration of hybrid action sp...In this paper,the optimal control of non-linear switching system is investigated without knowing the system dynamics.First,the Hamilton-Jacobi-Bellman(HJB)equation is derived with the consideration of hybrid action space.Then,a novel data-based hybrid Q-learning(HQL)algorithm is proposed to find the optimal solution in an iterative manner.In addition,the theoretical analysis is provided to illustrate the convergence and optimality of the proposed algorithm.Finally,the algorithm is implemented with the actor-critic(AC)structure,and two linear-in-parameter neural networks are utilized to approximate the functions.Simulation results validate the effectiveness of the data-driven method.展开更多
Dynamic soaring,inspired by the wind-riding flight of birds such as albatrosses,is a biomimetic technique which leverages wind fields to enhance the endurance of unmanned aerial vehicles(UAVs).Achieving a precise soar...Dynamic soaring,inspired by the wind-riding flight of birds such as albatrosses,is a biomimetic technique which leverages wind fields to enhance the endurance of unmanned aerial vehicles(UAVs).Achieving a precise soaring trajectory is crucial for maximizing energy efficiency during flight.Existing nonlinear programming methods are heavily dependent on the choice of initial values which is hard to determine.Therefore,this paper introduces a deep reinforcement learning method based on a differentially flat model for dynamic soaring trajectory planning and optimization.Initially,the gliding trajectory is parameterized using Fourier basis functions,achieving a flexible trajectory representation with a minimal number of hyperparameters.Subsequently,the trajectory optimization problem is formulated as a dynamic interactive process of Markov decision-making.The hyperparameters of the trajectory are optimized using the Proximal Policy Optimization(PPO2)algorithm from deep reinforcement learning(DRL),reducing the strong reliance on initial value settings in the optimization process.Finally,a comparison between the proposed method and the nonlinear programming method reveals that the trajectory generated by the proposed approach is smoother while meeting the same performance requirements.Specifically,the proposed method achieves a 34%reduction in maximum thrust,a 39.4%decrease in maximum thrust difference,and a 33%reduction in maximum airspeed difference.展开更多
In response to the increasing global energy demand and environmental pollution,microgrids have emerged as an innovative solution by integrating distributed energy resources(DERs),energy storage systems,and loads to im...In response to the increasing global energy demand and environmental pollution,microgrids have emerged as an innovative solution by integrating distributed energy resources(DERs),energy storage systems,and loads to improve energy efficiency and reliability.This study proposes a novel hybrid optimization algorithm,DE-HHO,combining differential evolution(DE)and Harris Hawks optimization(HHO)to address microgrid scheduling issues.The proposed method adopts a multi-objective optimization framework that simultaneously minimizes operational costs and environmental impacts.The DE-HHO algorithm demonstrates significant advantages in convergence speed and global search capability through the analysis of wind,solar,micro-gas turbine,and battery models.Comprehensive simulation tests show that DE-HHO converges rapidly within 10 iterations and achieves a 4.5%reduction in total cost compared to PSO and a 5.4%reduction compared to HHO.Specifically,DE-HHO attains an optimal total cost of$20,221.37,outperforming PSO($21,184.45)and HHO($21,372.24).The maximum cost obtained by DE-HHO is$23,420.55,with a mean of$21,615.77,indicating stability and cost control capabilities.These results highlight the effectiveness of DE-HHO in reducing operational costs and enhancing system stability for efficient and sustainable microgrid operation.展开更多
This study introduces a comprehensive and automated framework that leverages data-driven method-ologies to address various challenges in shale gas development and production.Specifically,it harnesses the power of Auto...This study introduces a comprehensive and automated framework that leverages data-driven method-ologies to address various challenges in shale gas development and production.Specifically,it harnesses the power of Automated Machine Learning(AutoML)to construct an ensemble model to predict the estimated ultimate recovery(EUR)of shale gas wells.To demystify the“black-box”nature of the ensemble model,KernelSHAP,a kernel-based approach to compute Shapley values,is utilized for elucidating the influential factors that affect shale gas production at both global and local scales.Furthermore,a bi-objective optimization algorithm named NSGA-Ⅱ is seamlessly incorporated to opti-mize hydraulic fracturing designs for production boost and cost control.This innovative framework addresses critical limitations often encountered in applying machine learning(ML)to shale gas pro-duction:the challenge of achieving sufficient model accuracy with limited samples,the multidisciplinary expertise required for developing robust ML models,and the need for interpretability in“black-box”models.Validation with field data from the Fuling shale gas field in the Sichuan Basin substantiates the framework's efficacy in enhancing the precision and applicability of data-driven techniques.The test accuracy of the ensemble ML model reached 83%compared to a maximum of 72%of single ML models.The contribution of each geological and engineering factor to the overall production was quantitatively evaluated.Fracturing design optimization raised EUR by 7%-34%under different production and cost tradeoff scenarios.The results empower domain experts to conduct more precise and objective data-driven analyses and optimizations for shale gas production with minimal expertise in data science.展开更多
Water power is one of the key renewable energy resources,whose efficiency is often hampered due to inefficient water flow management,turbine performance,and environmental variations.Most existing optimization techniqu...Water power is one of the key renewable energy resources,whose efficiency is often hampered due to inefficient water flow management,turbine performance,and environmental variations.Most existing optimization techniques lack the real-time adaptability to sufficiently allocate resources in terms of location and time.Hence,a novel Scalable Tas-manian Devil Optimization(STDO)algorithm is introduced to optimize hydropower generation for maximum power efficiency.Using the STDO to model important system characteristics including water flow,turbine changes,and energy conversion efficiency is part of the process.In the final analysis,optimizing these settings in would help reduce inefficiencies and maximize power generation output.Following that,simulations based on actual hydroelectric data are used to analyze the algorithm's effectiveness.The simulation results provide evidence that the STDO algorithm can enhance hydropower plant efficiency tremendously translating to considerable energy output augmentation compared to conven-tional optimization methods.STDO achieves the reliability(92.5),resiliency(74.3),and reduced vulnerability(9.3).To guarantee increased efficiency towards ecologically friendly power generation,the STDO algorithm may thus offer efficient resource optimization for hydropower.A clear route is made available for expanding the efficiency of current hydropower facilities while tackling the long-term objectives of reducing the environmental impact and increasing the energy output of energy produced from renewable sources.展开更多
This study investigates the mechanical behavior of polyurethane(PU)nanocomposites reinforced with nanodiamonds(NDs)and proposes an integrated optimization-prediction framework that combines the Taguchi method with mac...This study investigates the mechanical behavior of polyurethane(PU)nanocomposites reinforced with nanodiamonds(NDs)and proposes an integrated optimization-prediction framework that combines the Taguchi method with machine learning(ML).The Taguchi design of experiments(DOE),based on an L9 orthogonal array,was applied to investigate the influence of composite type(pure PU,0.1 wt.%ND,0.5 wt.%ND),temperature(145℃-165℃),screw speed(50-70 rpm),and pressure(40-60 bar).The mechanical tests included tensile,hardness,and modulus measurements,performed under varying process parameters.Results showed that the addition of 0.5 wt.%ND substantially improved PU performance,with tensile strength increasing by 117%,Young’s modulus by 10%,and hardness by 21%at optimal conditions of 145℃,70 rpm,and 50 bar.SEM analysis revealed ductile fracture in pure PU and brittle fracture in the optimized PU/ND composite.ANOVA confirmed that composite type was the most influential factor,contributing 70.27%,87.14%,and 74.16%to tensile strength,modulus,and hardness,respectively.Regression modeling demonstrated a deviation of less than 10%between predicted and experimental values,validating the framework.To further strengthen predictive capability,computational modeling and analytical procedureswere employed throughmachine learning frameworks.RandomForest achieved R2/MSE values of 0.95/0.53(tensile),0.95/4.03(modulus),and 0.94/2.44(hardness).XGBoost performed better,with 0.98/0.12,0.98/0.77,and 0.98/0.60,while Gradient Boosting provided the highest accuracy with 0.99/0.03,0.99/0.02,and 0.99/0.01.Residual plots supported these results,showing wide fluctuations for RF and tightly clustered residuals near zero for GB and XGB,highlighting their superior accuracy,precision,and generalization.Overall,the integrated Taguchi-ML framework demonstrates a robust and efficient strategy for optimizing processing parameters and accurately predicting the performance of high-strength PU-ND nanocomposites.展开更多
The rapid expansion of the Internet of Things(IoT)has led to the widespread adoption of sensor networks,with Long-Range Wide-Area Networks(LoRaWANs)emerging as a key technology due to their ability to support long-ran...The rapid expansion of the Internet of Things(IoT)has led to the widespread adoption of sensor networks,with Long-Range Wide-Area Networks(LoRaWANs)emerging as a key technology due to their ability to support long-range communication while minimizing power consumption.However,optimizing network performance and energy efficiency in dynamic,large-scale IoT environments remains a significant challenge.Traditional methods,such as the Adaptive Data Rate(ADR)algorithm,often fail to adapt effectively to rapidly changing network conditions and environmental factors.This study introduces a hybrid approach that leverages Deep Learning(DL)techniques,namely Long Short-Term Memory(LSTM)networks,and Machine Learning(ML)techniques,namely Artificial Neural Networks(ANNs),to optimize key network parameters such as Signal-to-Noise Ratio(SNR)and Received Signal Strength Indicator(RSSI).LSTM-ANN model trained on the“LoRaWAN Path Loss Dataset including Environmental Variables”from Medellín,Colombia,and the model demonstrated exceptional predictive accuracy,achieving an R2 score of 0.999,Mean Squared Error(MSE)of 0.041,Root Mean Squared Error(RMSE)of 0.203,and Mean Absolute Error(MAE)of 0.167,significantly outperforming traditional regression-based approaches.These findings highlight the potential of combining advanced ML and DL techniques to address the limitations of traditional optimization strategies in LoRaWAN.By providing a scalable and adaptive solution for large-scale IoT deployments,this work lays the foundation for real-world implementation,emphasizing the need for continuous learning frameworks to further enhance energy efficiency and network resilience in dynamic environments.展开更多
Predictive control has recently received much attention from researchers. However a challenging problem to be solved is how to tune the parameters of the predictive controller. So far, only few guidelines related to t...Predictive control has recently received much attention from researchers. However a challenging problem to be solved is how to tune the parameters of the predictive controller. So far, only few guidelines related to tuning of the parameters of predictive controllers have been provided in literature. In practice, these parameters are generally off-line determined by the designers' experience. From the point of view of process control, it is difficult to find out the optimal parameters for the control system based on a single quadratic performance index, which is used in the standard predictive control algorithm. The fuzzy decision-making function is investigated in this paper. Firstly, M control actions are achieved by unconstrained predictive control algorithm, and fuzzy goals and fuzzy constraints are then calculated and the global satisfaction degree is obtained by fuzzy inference. Moreover, the weighting coefficient λ in the cost function is tuned using simulation optimization according to the fuzzy criteria.展开更多
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(RS-2025-00559546)supported by the IITP(Institute of Information&Coummunications Technology Planning&Evaluation)-ITRC(Information Technology Research Center)grant funded by the Korea government(Ministry of Science and ICT)(IITP-2025-RS-2023-00259004).
文摘The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-generation(5G)networks transformed mobile broadband and machine-type communications at massive scales,their properties of scaling,interference management,and latency remain a limitation in dense high mobility settings.To overcome these limitations,artificial intelligence(AI)and unmanned aerial vehicles(UAVs)have emerged as potential solutions to develop versatile,dynamic,and energy-efficient communication systems.The study proposes an AI-based UAV architecture that utilizes cooperative reinforcement learning(CoRL)to manage an autonomous network.The UAVs collaborate by sharing local observations and real-time state exchanges to optimize user connectivity,movement directions,allocate power,and resource distribution.Unlike conventional centralized or autonomous methods,CoRL involves joint state sharing and conflict-sensitive reward shaping,which ensures fair coverage,less interference,and enhanced adaptability in a dynamic urban environment.Simulations conducted in smart city scenarios with 10 UAVs and 50 ground users demonstrate that the proposed CoRL-based UAV system increases user coverage by up to 10%,achieves convergence 40%faster,and reduces latency and energy consumption by 30%compared with centralized and decentralized baselines.Furthermore,the distributed nature of the algorithm ensures scalability and flexibility,making it well-suited for future large-scale 6G deployments.The results highlighted that AI-enabled UAV systems enhance connectivity,support ultra-reliable low-latency communications(URLLC),and improve 6G network efficiency.Future work will extend the framework with adaptive modulation,beamforming-aware positioning,and real-world testbed deployment.
基金Projects(61533021,61321003,61273185)supported by the National Natural Science Foundation of ChinaProject(2015CX007)supported by the Innovation-driven Plan in Central South University,ChinaProject(13JJ8003)supported by the Joint Fund of Hunan Provincial Natural Science Foundation of China
文摘Reagents are optimized for the simultaneous determination of trace amounts of Cu^(2+), Cd^(2+) and Co^(2+) in zinc sulfate solution, which contains an extremely large excess of Zn^(2+). First, the reagents and their doses for the experiment are selected according to the characteristics of the zinc sulfate solution. Then, the reagent doses are optimized by analyzing the influence of reagent dose on the polarographic parameters(i.e. half-wave potential E_(1/2) and limiting diffusion current I_p). Finally, the optimization results are verified by simultaneously determining trace amounts of Cu^(2+), Cd^(2+) and Co^(2+) in the presence of an extremely large excess of Zn^(2+). The determination results indicate that the optimized reagents exhibit wide linearity, low detection limits, high accuracy and good precision for the simultaneous determination of trace amounts of Cu^(2+), Cd^(2+) and Co^(2+) in the presence of an extremely large excess of Zn^(2+).
基金Supported by the National Nature Science Foundation of China,the Research Foundation of General Corporation of China Petro-Chemical Industry and the Natural Science and Engineering Research Council of Canada.
文摘A strategy of developing on-line optimization intelligent systems based on combiningflowsheeting simulation and optimization package with artificial neural networks(ANN)is presented inthis paper.A number of optimization cases for a certain chemical plant are obtained off-line byusing PROCESS-Ⅱ or other flowsheeting programming with optimization.Then,taking these cases astraining examples,we establish a neural network systems which can be used on-line as an optimizer toobtain setpoints from input data sampled from distributed control system through gross error detectionand data reconciliation procedures.Such an on-line optimizer possesses two advantages over nonlinearprogramming package:first of all,there is no convergence problem for the trained ANN to be usedonline;secondly,the frequency for setpoints updating is not limited because only algebraic calculationrather than optimization is required to be carried out on-line.Here two key problems ofimplementing ANN approaches to the on-line optimization
基金the Natural Sciences and Engineering Research Council of Canada (NSERC) for the funding of the Canada Research Chair in Aircraft Modeling and Simulation Technologiesthe Canada Foundation of Innovation (CFI), the Ministerèdu Développement économique, de l’Innovation et de l’Exportation (MDEIE) and Hydra Technologies for the acquisition of the UAS-S4 using the Leaders Opportunity Funds+2 种基金the financial support obtained in the framework of the CRIAQ MDO-505 projectthe implication of our industrial partners Bombardier Aerospace and Thales CanadaNSERC for their support
文摘This paper presents a new non-linear formulation of the classical Vortex Lattice Method （VLM） approach for calculating the aerodynamic properties of lifting surfaces. The method accounts for the effects of viscosity, and due to its low computational cost, it represents a very good tool to perform rapid and accurate wing design and optimization procedures. The mathematical model is constructed by using two-dimensional viscous analyses of the wing span-wise sections, according to strip theory, and then coupling the strip viscous forces with the forces generated by the vortex rings distributed on the wing camber surface, calculated with a fully three-dimensional vortex lifting law. The numerical results obtained with the proposed method are validated with experimental data and show good agreement in predicting both the lift and pitching moment, as well as in predicting the wing drag. The method is applied to modifying the wing of an Unmanned Aerial System to increase its aerodynamic efficiency and to calculate the drag reductions obtained by an upper surface morphing technique for an adaptable regional aircraft wing.
基金Supported by the Open Project of Jiangsu Key Laboratory of Environmental Engineering(ZX2017005)
文摘The characteristics and distribution law of electromagnetic environment around substations with different levels of voltage were studied,and the main influencing factors were discussed. Meanwhile,a scheme for locating monitoring points suitable for an on-line monitoring system of electromagnetic environment was proposed.
基金This project is supported by National Natural Science Foundation of China (No. 50075034).
文摘6-DOF non-linear mechanics model of powerplant hydraulic mount system isestablished. Optimum design of the powerplant hydraulic mount system is made with the hydraulicmount parameters as variables and with uncoupling of energy, rational disposition of naturefrequency and minimum of reactive force at mount's location as objective functions. And based on theoptimum design, software named ODPHMS (optimum design of powerplant hydraulic mount system) used inpowerplant mount system optimum design is developed.
基金Supported by the National High Technology Research and Development Program of China（2007AA04Z193） the National Natural Science Foundation of China（60974008 60704032）
文摘For high-purity distillation processes,it is difficult to achieve a good direct product quality control using traditional proportional-integral-differential(PID)control or multivariable predictive control technique due to some difficulties,such as long response time,many un-measurable disturbances,and the reliability and precision issues of product quality soft-sensors.In this paper,based on the first principle analysis and dynamic simulation of a distillation process,a new predictive control scheme is proposed by using the split ratio of distillate flow rate to that of bottoms as an essential controlled variable.Correspondingly,a new strategy with integrated control and on-line optimization is developed,which consists of model predictive control of the split ratio,surrogate model based on radial basis function neural network for optimization,and modified differential evolution optimization algorithm. With the strategy,the process achieves its steady state quickly,so more profit can be obtained.The proposed strategy has been successfully applied to a gas separation plant for more than three years,which shows that the strategy is feasible and effective.
基金financially supported by the National Science Foundation for Young Scientists of China(No.51701027)the National Key Research and Development Program of China(No.2017YFF0209100)+2 种基金the National Defense Basic Scientific Research Program of Chinathe Fundamental Research Funds for the Central Universities Project(No.2020CDJQY-A002)the Shanghai Rising—Star Program(No.18QB1401400)。
文摘On-line heating rolling mill which could efficiently preheat sheet and apply tensile force on both ends of the sheet along rolling direction(RD)was used to investigate the effect of tension on mechanical behavior and shape quality of magnesium sheets.For revealing the infl uence mechanism,many analysis techniques including optical microscope,electron backscattered diffraction,macrotexture and transmission electron microscope were performed.The shape defect,edge wave,could be eliminated under higher tension along RD,which was attributed to more uniform distribution of microstructure and microstrain.Nevertheless,it is undesirable that the forward tensile force exceeds 3 kN in present work because the strength decreased for high recrystallization level when the tensile force is beyond this value.Furthermore,the main deformation mode was still slip during rolling process despite of accompanying twining,e.g.,double twins,but more prismatic slip activated when tensile force exceeds 3 kN.The distribution of shear bands was affected by the applied tensile force that they appear as"V"shape along RD at a low forward or backward tensile force,while they appear as reticulate shape under applied tensile force of 5 kN.
基金Project(Z132012)supported by the Second Five Technology-based in Science and Industry Bureau of ChinaProject(YWF1103Q062)supported by the Fundemental Research Funds for the Central Universities in China
文摘A relevance vector machine (RVM) based fault diagnosis method was presented for non-linear circuits. In order to simplify RVM classifier, parameters selection based on particle swarm optimization (PSO) and preprocessing technique based on the kurtosis and entropy of signals were used. Firstly, sinusoidal inputs with different frequencies were applied to the circuit under test (CUT). Then, the resulting frequency responses were sampled to generate features. The frequency response was sampled to compute its kurtosis and entropy, which can show the information capacity of signal. By analyzing the output signals, the proposed method can detect and identify faulty components in circuits. The results indicate that the fault classes can be classified correctly for at least 99% of the test data in example circuit. And the proposed method can diagnose hard and soft faults.
基金supported by the Key Research and Development Program Project of Hunan Province, China (Grant No. 2023NK2003)the National Key Research and Development Program of China (Grant No. 2022YFD2301001-03)the National Key Research and Development Program of China (Grant No. 2022YFD2301003)
文摘The ratooning system enhances agricultural efficiency by reducing secondary sowing and resource input while maintaining rice yield parity with double cropping.However,the prolonged growth duration of the rice ratooning system extends the exposure window to Magnaporthe oryzae infection,thereby elevating the probability of disease incidence.
文摘Burundi faces major agricultural constraints, including land fragmentation, soil erosion, limited access to inputs, inadequate infrastructure and demographic pressures that exacerbate food insecurity. In order to address the multiple challenges faced by farmers in rural areas, a study on improving agricultural productivity and food security in Burundi through optimized land use and diversified farming practices in agroforestry systems has been carried out. The study area is the communes of Giheta and Rutegama, all located in Burundi’s humid plateau livelihood zone, and involved 164 households grouped in coffee growing cooperatives supervised by the cooperative consortium COCOCA. The study uses a mathematical programming model to determine optimal crop selection based on factors such as production costs, yields and market demand. The findings of the study revealed significant insights into the demographic and socio-economic characteristics of the sampled population. Notably, 98.8% of respondents were engaged in agriculture, confirming the predominantly agricultural nature of Burundi. The results indicated that maize is the most important crop, occupying 33.9% of the average total cultivated area, followed by cassava at 26.5% and bananas at 19.4%. Together, these three crops accounted for a substantial portion of the total cultivated area, highlighting their significance in local agriculture. Beans and potatoes also play a role, occupying 14.4% and smaller areas, respectively. In terms of profitability, the study provides a detailed analysis of profit margins by crop. Bananas emerges as the most profitable crop, with a profit margin of 97.3%, followed closely by cassava at 96.1% and rice at 90.5%. These crops not only offered substantial yields relative to their production costs but also benefited from strong market demand. Other crops, such as beans (71.3%), coffee (70.3%), and vegetables (54.5%), also demonstrated considerable profitability, although they occupied smaller cultivated areas. Conversely, crops like pigeon peas (4.1%), potatoes (7.6%), and sweet potatoes (7.6%) exhibited the lowest profit margins, which may discourage farmers from investing in them unless other incentives, such as ecological benefits or local consumption needs, are present. Regarding the results, we therefore recommend to promote policies supporting agroforestry, improve market access and develop infrastructure to exploit these benefits.
基金supported by the National Key R&D Program of China(2018AAA0101400)the Natural Science Foundation of Jiangsu Province of China(BK20202006)the National Natural Science Foundation of China(61921004,62173251).
文摘In this paper,the optimal control of non-linear switching system is investigated without knowing the system dynamics.First,the Hamilton-Jacobi-Bellman(HJB)equation is derived with the consideration of hybrid action space.Then,a novel data-based hybrid Q-learning(HQL)algorithm is proposed to find the optimal solution in an iterative manner.In addition,the theoretical analysis is provided to illustrate the convergence and optimality of the proposed algorithm.Finally,the algorithm is implemented with the actor-critic(AC)structure,and two linear-in-parameter neural networks are utilized to approximate the functions.Simulation results validate the effectiveness of the data-driven method.
基金support received by the National Natural Science Foundation of China(Grant Nos.52372398&62003272).
文摘Dynamic soaring,inspired by the wind-riding flight of birds such as albatrosses,is a biomimetic technique which leverages wind fields to enhance the endurance of unmanned aerial vehicles(UAVs).Achieving a precise soaring trajectory is crucial for maximizing energy efficiency during flight.Existing nonlinear programming methods are heavily dependent on the choice of initial values which is hard to determine.Therefore,this paper introduces a deep reinforcement learning method based on a differentially flat model for dynamic soaring trajectory planning and optimization.Initially,the gliding trajectory is parameterized using Fourier basis functions,achieving a flexible trajectory representation with a minimal number of hyperparameters.Subsequently,the trajectory optimization problem is formulated as a dynamic interactive process of Markov decision-making.The hyperparameters of the trajectory are optimized using the Proximal Policy Optimization(PPO2)algorithm from deep reinforcement learning(DRL),reducing the strong reliance on initial value settings in the optimization process.Finally,a comparison between the proposed method and the nonlinear programming method reveals that the trajectory generated by the proposed approach is smoother while meeting the same performance requirements.Specifically,the proposed method achieves a 34%reduction in maximum thrust,a 39.4%decrease in maximum thrust difference,and a 33%reduction in maximum airspeed difference.
文摘In response to the increasing global energy demand and environmental pollution,microgrids have emerged as an innovative solution by integrating distributed energy resources(DERs),energy storage systems,and loads to improve energy efficiency and reliability.This study proposes a novel hybrid optimization algorithm,DE-HHO,combining differential evolution(DE)and Harris Hawks optimization(HHO)to address microgrid scheduling issues.The proposed method adopts a multi-objective optimization framework that simultaneously minimizes operational costs and environmental impacts.The DE-HHO algorithm demonstrates significant advantages in convergence speed and global search capability through the analysis of wind,solar,micro-gas turbine,and battery models.Comprehensive simulation tests show that DE-HHO converges rapidly within 10 iterations and achieves a 4.5%reduction in total cost compared to PSO and a 5.4%reduction compared to HHO.Specifically,DE-HHO attains an optimal total cost of$20,221.37,outperforming PSO($21,184.45)and HHO($21,372.24).The maximum cost obtained by DE-HHO is$23,420.55,with a mean of$21,615.77,indicating stability and cost control capabilities.These results highlight the effectiveness of DE-HHO in reducing operational costs and enhancing system stability for efficient and sustainable microgrid operation.
基金funded by the National Natural Science Foundation of China(42050104).
文摘This study introduces a comprehensive and automated framework that leverages data-driven method-ologies to address various challenges in shale gas development and production.Specifically,it harnesses the power of Automated Machine Learning(AutoML)to construct an ensemble model to predict the estimated ultimate recovery(EUR)of shale gas wells.To demystify the“black-box”nature of the ensemble model,KernelSHAP,a kernel-based approach to compute Shapley values,is utilized for elucidating the influential factors that affect shale gas production at both global and local scales.Furthermore,a bi-objective optimization algorithm named NSGA-Ⅱ is seamlessly incorporated to opti-mize hydraulic fracturing designs for production boost and cost control.This innovative framework addresses critical limitations often encountered in applying machine learning(ML)to shale gas pro-duction:the challenge of achieving sufficient model accuracy with limited samples,the multidisciplinary expertise required for developing robust ML models,and the need for interpretability in“black-box”models.Validation with field data from the Fuling shale gas field in the Sichuan Basin substantiates the framework's efficacy in enhancing the precision and applicability of data-driven techniques.The test accuracy of the ensemble ML model reached 83%compared to a maximum of 72%of single ML models.The contribution of each geological and engineering factor to the overall production was quantitatively evaluated.Fracturing design optimization raised EUR by 7%-34%under different production and cost tradeoff scenarios.The results empower domain experts to conduct more precise and objective data-driven analyses and optimizations for shale gas production with minimal expertise in data science.
文摘Water power is one of the key renewable energy resources,whose efficiency is often hampered due to inefficient water flow management,turbine performance,and environmental variations.Most existing optimization techniques lack the real-time adaptability to sufficiently allocate resources in terms of location and time.Hence,a novel Scalable Tas-manian Devil Optimization(STDO)algorithm is introduced to optimize hydropower generation for maximum power efficiency.Using the STDO to model important system characteristics including water flow,turbine changes,and energy conversion efficiency is part of the process.In the final analysis,optimizing these settings in would help reduce inefficiencies and maximize power generation output.Following that,simulations based on actual hydroelectric data are used to analyze the algorithm's effectiveness.The simulation results provide evidence that the STDO algorithm can enhance hydropower plant efficiency tremendously translating to considerable energy output augmentation compared to conven-tional optimization methods.STDO achieves the reliability(92.5),resiliency(74.3),and reduced vulnerability(9.3).To guarantee increased efficiency towards ecologically friendly power generation,the STDO algorithm may thus offer efficient resource optimization for hydropower.A clear route is made available for expanding the efficiency of current hydropower facilities while tackling the long-term objectives of reducing the environmental impact and increasing the energy output of energy produced from renewable sources.
基金supported and funded by theDeanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2503).
文摘This study investigates the mechanical behavior of polyurethane(PU)nanocomposites reinforced with nanodiamonds(NDs)and proposes an integrated optimization-prediction framework that combines the Taguchi method with machine learning(ML).The Taguchi design of experiments(DOE),based on an L9 orthogonal array,was applied to investigate the influence of composite type(pure PU,0.1 wt.%ND,0.5 wt.%ND),temperature(145℃-165℃),screw speed(50-70 rpm),and pressure(40-60 bar).The mechanical tests included tensile,hardness,and modulus measurements,performed under varying process parameters.Results showed that the addition of 0.5 wt.%ND substantially improved PU performance,with tensile strength increasing by 117%,Young’s modulus by 10%,and hardness by 21%at optimal conditions of 145℃,70 rpm,and 50 bar.SEM analysis revealed ductile fracture in pure PU and brittle fracture in the optimized PU/ND composite.ANOVA confirmed that composite type was the most influential factor,contributing 70.27%,87.14%,and 74.16%to tensile strength,modulus,and hardness,respectively.Regression modeling demonstrated a deviation of less than 10%between predicted and experimental values,validating the framework.To further strengthen predictive capability,computational modeling and analytical procedureswere employed throughmachine learning frameworks.RandomForest achieved R2/MSE values of 0.95/0.53(tensile),0.95/4.03(modulus),and 0.94/2.44(hardness).XGBoost performed better,with 0.98/0.12,0.98/0.77,and 0.98/0.60,while Gradient Boosting provided the highest accuracy with 0.99/0.03,0.99/0.02,and 0.99/0.01.Residual plots supported these results,showing wide fluctuations for RF and tightly clustered residuals near zero for GB and XGB,highlighting their superior accuracy,precision,and generalization.Overall,the integrated Taguchi-ML framework demonstrates a robust and efficient strategy for optimizing processing parameters and accurately predicting the performance of high-strength PU-ND nanocomposites.
基金funded by King Saud University Researchers Supporting Project Number(RSPD2025R1007),King Saud University,Riyadh,Saudi Arabia.
文摘The rapid expansion of the Internet of Things(IoT)has led to the widespread adoption of sensor networks,with Long-Range Wide-Area Networks(LoRaWANs)emerging as a key technology due to their ability to support long-range communication while minimizing power consumption.However,optimizing network performance and energy efficiency in dynamic,large-scale IoT environments remains a significant challenge.Traditional methods,such as the Adaptive Data Rate(ADR)algorithm,often fail to adapt effectively to rapidly changing network conditions and environmental factors.This study introduces a hybrid approach that leverages Deep Learning(DL)techniques,namely Long Short-Term Memory(LSTM)networks,and Machine Learning(ML)techniques,namely Artificial Neural Networks(ANNs),to optimize key network parameters such as Signal-to-Noise Ratio(SNR)and Received Signal Strength Indicator(RSSI).LSTM-ANN model trained on the“LoRaWAN Path Loss Dataset including Environmental Variables”from Medellín,Colombia,and the model demonstrated exceptional predictive accuracy,achieving an R2 score of 0.999,Mean Squared Error(MSE)of 0.041,Root Mean Squared Error(RMSE)of 0.203,and Mean Absolute Error(MAE)of 0.167,significantly outperforming traditional regression-based approaches.These findings highlight the potential of combining advanced ML and DL techniques to address the limitations of traditional optimization strategies in LoRaWAN.By providing a scalable and adaptive solution for large-scale IoT deployments,this work lays the foundation for real-world implementation,emphasizing the need for continuous learning frameworks to further enhance energy efficiency and network resilience in dynamic environments.
文摘Predictive control has recently received much attention from researchers. However a challenging problem to be solved is how to tune the parameters of the predictive controller. So far, only few guidelines related to tuning of the parameters of predictive controllers have been provided in literature. In practice, these parameters are generally off-line determined by the designers' experience. From the point of view of process control, it is difficult to find out the optimal parameters for the control system based on a single quadratic performance index, which is used in the standard predictive control algorithm. The fuzzy decision-making function is investigated in this paper. Firstly, M control actions are achieved by unconstrained predictive control algorithm, and fuzzy goals and fuzzy constraints are then calculated and the global satisfaction degree is obtained by fuzzy inference. Moreover, the weighting coefficient λ in the cost function is tuned using simulation optimization according to the fuzzy criteria.
