In multi-component systems,the components are dependent,rather than degenerating independently,leading to changes inmaintenance schedules.In this situation,this study proposes a grouping dynamicmaintenance strategy.Co...In multi-component systems,the components are dependent,rather than degenerating independently,leading to changes inmaintenance schedules.In this situation,this study proposes a grouping dynamicmaintenance strategy.Considering the structure of multi-component systems,the maintenance strategy is determined according to the importance of the components.The strategy can minimize the expected depreciation cost of the system and divide the system into optimal groups that meet economic requirements.First,multi-component models are grouped.Then,a failure probability model of multi-component systems is established.The maintenance parameters in each maintenance cycle are updated according to the failure probability of the components.Second,the component importance indicator is introduced into the grouping model,and the optimization model,which aimed at a maximum economic profit,is established.A genetic algorithm is used to solve the non-deterministic polynomial(NP)-complete problem in the optimization model,and the optimal grouping is obtained through the initial grouping determined by random allocation.An 11-component series and parallel system is used to illustrate the effectiveness of the proposed strategy,and the influence of the system structure and the parameters on the maintenance strategy is discussed.展开更多
Radial Basis Function Neural Network(RBFNN)ensembles have long suffered from non-efficient training,where incorrect parameter settings can be computationally disastrous.This paper examines different evolutionary algor...Radial Basis Function Neural Network(RBFNN)ensembles have long suffered from non-efficient training,where incorrect parameter settings can be computationally disastrous.This paper examines different evolutionary algorithms for training the Symbolic Radial Basis Function Neural Network(SRBFNN)through the behavior’s integration of satisfiability programming.Inspired by evolutionary algorithms,which can iteratively find the nearoptimal solution,different Evolutionary Algorithms(EAs)were designed to optimize the producer output weight of the SRBFNN that corresponds to the embedded logic programming 2Satisfiability representation(SRBFNN-2SAT).The SRBFNN’s objective function that corresponds to Satisfiability logic programming can be minimized by different algorithms,including Genetic Algorithm(GA),Evolution Strategy Algorithm(ES),Differential Evolution Algorithm(DE),and Evolutionary Programming Algorithm(EP).Each of these methods is presented in the steps in the flowchart form which can be used for its straightforward implementation in any programming language.With the use of SRBFNN-2SAT,a training method based on these algorithms has been presented,then training has been compared among algorithms,which were applied in Microsoft Visual C++software using multiple metrics of performance,including Mean Absolute Relative Error(MARE),Root Mean Square Error(RMSE),Mean Absolute Percentage Error(MAPE),Mean Bias Error(MBE),Systematic Error(SD),Schwarz Bayesian Criterion(SBC),and Central Process Unit time(CPU time).Based on the results,the EP algorithm achieved a higher training rate and simple structure compared with the rest of the algorithms.It has been confirmed that the EP algorithm is quite effective in training and obtaining the best output weight,accompanied by the slightest iteration error,which minimizes the objective function of SRBFNN-2SAT.展开更多
Nonlinear equations systems(NESs)are widely used in real-world problems and they are difficult to solve due to their nonlinearity and multiple roots.Evolutionary algorithms(EAs)are one of the methods for solving NESs,...Nonlinear equations systems(NESs)are widely used in real-world problems and they are difficult to solve due to their nonlinearity and multiple roots.Evolutionary algorithms(EAs)are one of the methods for solving NESs,given their global search capabilities and ability to locate multiple roots of a NES simultaneously within one run.Currently,the majority of research on using EAs to solve NESs focuses on transformation techniques and improving the performance of the used EAs.By contrast,problem domain knowledge of NESs is investigated in this study,where we propose the incorporation of a variable reduction strategy(VRS)into EAs to solve NESs.The VRS makes full use of the systems of expressing a NES and uses some variables(i.e.,core variable)to represent other variables(i.e.,reduced variables)through variable relationships that exist in the equation systems.It enables the reduction of partial variables and equations and shrinks the decision space,thereby reducing the complexity of the problem and improving the search efficiency of the EAs.To test the effectiveness of VRS in dealing with NESs,this paper mainly integrates the VRS into two existing state-of-the-art EA methods(i.e.,MONES and DR-JADE)according to the integration framework of the VRS and EA,respectively.Experimental results show that,with the assistance of the VRS,the EA methods can produce better results than the original methods and other compared methods.Furthermore,extensive experiments regarding the influence of different reduction schemes and EAs substantiate that a better EA for solving a NES with more reduced variables tends to provide better performance.展开更多
To realize a better automatic train driving operation control strategy for urban rail trains,an automatic train driving method with improved DQN algorithm(classical deep reinforcement learning algorithm)is proposed as...To realize a better automatic train driving operation control strategy for urban rail trains,an automatic train driving method with improved DQN algorithm(classical deep reinforcement learning algorithm)is proposed as a research object.Firstly,the train control model is established by considering the train operation requirements.Secondly,the dueling network and DDQN ideas are introduced to prevent the value function overestimation problem.Finally,the priority experience playback and“restricted speed arrival time”are used to reduce the useless experience utilization.The experiments are carried out to verify the train operation strategy method by simulating the actual line conditions.From the experimental results,the train operation meets the ATO requirements,the energy consumption is 15.75%more energy-efficient than the actual operation,and the algorithm convergence speed is improved by about 37%.The improved DQN method not only enhances the efficiency of the algorithm but also forms a more effective operation strategy than the actual operation,thereby contributing meaningfully to the advancement of automatic train operation intelligence.展开更多
Pipeline isolation plugging robot (PIPR) is an important tool in pipeline maintenance operation. During the plugging process, the violent vibration will occur by the flow field, which can cause serious damage to the p...Pipeline isolation plugging robot (PIPR) is an important tool in pipeline maintenance operation. During the plugging process, the violent vibration will occur by the flow field, which can cause serious damage to the pipeline and PIPR. In this paper, we propose a dynamic regulating strategy to reduce the plugging-induced vibration by regulating the spoiler angle and plugging velocity. Firstly, the dynamic plugging simulation and experiment are performed to study the flow field changes during dynamic plugging. And the pressure difference is proposed to evaluate the degree of flow field vibration. Secondly, the mathematical models of pressure difference with plugging states and spoiler angles are established based on the extreme learning machine (ELM) optimized by improved sparrow search algorithm (ISSA). Finally, a modified Q-learning algorithm based on simulated annealing is applied to determine the optimal strategy for the spoiler angle and plugging velocity in real time. The results show that the proposed method can reduce the plugging-induced vibration by 19.9% and 32.7% on average, compared with single-regulating methods. This study can effectively ensure the stability of the plugging process.展开更多
This paper addresses the micro wind-hydrogen coupled system,aiming to improve the power tracking capability of micro wind farms,the regulation capability of hydrogen storage systems,and to mitigate the volatility of w...This paper addresses the micro wind-hydrogen coupled system,aiming to improve the power tracking capability of micro wind farms,the regulation capability of hydrogen storage systems,and to mitigate the volatility of wind power generation.A predictive control strategy for the micro wind-hydrogen coupled system is proposed based on the ultra-short-term wind power prediction,the hydrogen storage state division interval,and the daily scheduled output of wind power generation.The control strategy maximizes the power tracking capability,the regulation capability of the hydrogen storage system,and the fluctuation of the joint output of the wind-hydrogen coupled system as the objective functions,and adaptively optimizes the control coefficients of the hydrogen storage interval and the output parameters of the system by the combined sigmoid function and particle swarm algorithm(sigmoid-PSO).Compared with the real-time control strategy,the proposed predictive control strategy can significantly improve the output tracking capability of the wind-hydrogen coupling system,minimize the gap between the actual output and the predicted output,significantly enhance the regulation capability of the hydrogen storage system,and mitigate the power output fluctuation of the wind-hydrogen integrated system,which has a broad practical application prospect.展开更多
Aiming at the problems that the original Harris Hawk optimization algorithm is easy to fall into local optimum and slow in finding the optimum,this paper proposes an improved Harris Hawk optimization algorithm(GHHO).F...Aiming at the problems that the original Harris Hawk optimization algorithm is easy to fall into local optimum and slow in finding the optimum,this paper proposes an improved Harris Hawk optimization algorithm(GHHO).Firstly,we used a Gaussian chaotic mapping strategy to initialize the positions of individuals in the population,which enriches the initial individual species characteristics.Secondly,by optimizing the energy parameter and introducing the cosine strategy,the algorithm's ability to jump out of the local optimum is enhanced,which improves the performance of the algorithm.Finally,comparison experiments with other intelligent algorithms were conducted on 13 classical test function sets.The results show that GHHO has better performance in all aspects compared to other optimization algorithms.The improved algorithm is more suitable for generalization to real optimization problems.展开更多
We introduce the potential-decomposition strategy (PDS), which can be used in Markov chain Monte Carlosampling algorithms.PDS can be designed to make particles move in a modified potential that favors diffusion in pha...We introduce the potential-decomposition strategy (PDS), which can be used in Markov chain Monte Carlosampling algorithms.PDS can be designed to make particles move in a modified potential that favors diffusion in phasespace, then, by rejecting some trial samples, the target distributions can be sampled in an unbiased manner.Furthermore,if the accepted trial samples are insufficient, they can be recycled as initial states to form more unbiased samples.Thisstrategy can greatly improve efficiency when the original potential has multiple metastable states separated by largebarriers.We apply PDS to the 2d Ising model and a double-well potential model with a large barrier, demonstrating inthese two representative examples that convergence is accelerated by orders of magnitude.展开更多
Despite the series-parallel hybrid electric vehicle inherits the performance advantages from both series and parallel hybrid electric vehicle, few researches about the series-parallel hybrid electric vehicle have been...Despite the series-parallel hybrid electric vehicle inherits the performance advantages from both series and parallel hybrid electric vehicle, few researches about the series-parallel hybrid electric vehicle have been revealed because of its complex co nstruction and control strategy. In this paper, a series-parallel hybrid electric bus as well as its control strategy is revealed, and a control parameter optimization approach using the real-valued genetic algorithm is proposed. The optimization objective is to minimize the fuel consumption while sustain the battery state of charge, a tangent penalty function of state of charge(SOC) is embodied in the objective function to recast this multi-objective nonlinear optimization problem as a single linear optimization problem. For this strategy, the vehicle operating mode is switched based on the vehicle speed, and an "optimal line" typed strategy is designed for the parallel control. The optimization parameters include the speed threshold for mode switching, the highest state of charge allowed, the lowest state of charge allowed and the scale factor of the engine optimal torque to the engine maximum torque at a rotational speed. They are optimized through numerical experiments based on real-value genes, arithmetic crossover and mutation operators. The hybrid bus has been evaluated at the Chinese Transit Bus City Driving Cycle via road test, in which a control area network-based monitor system was used to trace the driving schedule. The test result shows that this approach is feasible for the control parameter optimization. This approach can be applied to not only the novel construction presented in this paper, but also other types of hybrid electric vehicles.展开更多
The determination of optimal values for three parameters required in the original particle swarm optimization algorithm is very difficult. It is proposed that two new parameters simulating the harmony search strategy ...The determination of optimal values for three parameters required in the original particle swarm optimization algorithm is very difficult. It is proposed that two new parameters simulating the harmony search strategy can be adopted instead of the three parameters which are required in the original particle swarm optimization algorithm to update the positions of all the particles. The improved particle swarm optimization is used in the location of the critical slip surface of soil slope, and it is found that the improved particle swarm optimization algorithm is insensitive to the two parameters while the original particle swarm optimization algorithm can be sensitive to its three parameters.展开更多
Population-based algorithms have been used in many real-world problems.Bat algorithm(BA)is one of the states of the art of these approaches.Because of the super bat,on the one hand,BA can converge quickly;on the other...Population-based algorithms have been used in many real-world problems.Bat algorithm(BA)is one of the states of the art of these approaches.Because of the super bat,on the one hand,BA can converge quickly;on the other hand,it is easy to fall into local optimum.Therefore,for typical BA algorithms,the ability of exploration and exploitation is not strong enough and it is hard to find a precise result.In this paper,we propose a novel bat algorithm based on cross boundary learning(CBL)and uniform explosion strategy(UES),namely BABLUE in short,to avoid the above contradiction and achieve both fast convergence and high quality.Different from previous opposition-based learning,the proposed CBL can expand the search area of population and then maintain the ability of global exploration in the process of fast convergence.In order to enhance the ability of local exploitation of the proposed algorithm,we propose UES,which can achieve almost the same search precise as that of firework explosion algorithm but consume less computation resource.BABLUE is tested with numerous experiments on unimodal,multimodal,one-dimensional,high-dimensional and discrete problems,and then compared with other typical intelligent optimization algorithms.The results show that the proposed algorithm outperforms other algorithms.展开更多
Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields,including stock market investment.However,few studies have focused on f...Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields,including stock market investment.However,few studies have focused on forecasting daily stock market returns,especially when using powerful machine learning techniques,such as deep neural networks(DNNs),to perform the analyses.DNNs employ various deep learning algorithms based on the combination of network structure,activation function,and model parameters,with their performance depending on the format of the data representation.This paper presents a comprehensive big data analytics process to predict the daily return direction of the SPDR S&P 500 ETF(ticker symbol:SPY)based on 60 financial and economic features.DNNs and traditional artificial neural networks(ANNs)are then deployed over the entire preprocessed but untransformed dataset,along with two datasets transformed via principal component analysis(PCA),to predict the daily direction of future stock market index returns.While controlling for overfitting,a pattern for the classification accuracy of the DNNs is detected and demonstrated as the number of the hidden layers increases gradually from 12 to 1000.Moreover,a set of hypothesis testing procedures are implemented on the classification,and the simulation results show that the DNNs using two PCA-represented datasets give significantly higher classification accuracy than those using the entire untransformed dataset,as well as several other hybrid machine learning algorithms.In addition,the trading strategies guided by the DNN classification process based on PCA-represented data perform slightly better than the others tested,including in a comparison against two standard benchmarks.展开更多
Noises widely exist in interactive genetic algorithms. However, there is no effective method to solve this problem up to now. There are two kinds of noises, one is the noise existing in visual systems and the other is...Noises widely exist in interactive genetic algorithms. However, there is no effective method to solve this problem up to now. There are two kinds of noises, one is the noise existing in visual systems and the other is resulted from user’s preference mechanisms. Characteristics of the two noises are presented aiming at the application of interac- tive genetic algorithms in dealing with images. The evolutionary phases of interactive genetic algorithms are determined according to differences in the same individual’s fitness among different generations. Models for noises in different phases are established and the corresponding strategies for reducing noises are given. The algorithm proposed in this paper has been applied to fashion design, which is a typical example of image processing. The results show that the strategies can reduce noises in interactive genetic algorithms and improve the algorithm’s performance effectively. However, a further study is needed to solve the problem of determining the evolution phase by using suitable objective methods so as to find out an effective method to decrease noises.展开更多
The Swarm intelligence algorithm is a very prevalent field in which some scholars have made outstanding achievements.As a representative,Slime mould algorithm(SMA)is widely used because of its superior initial perform...The Swarm intelligence algorithm is a very prevalent field in which some scholars have made outstanding achievements.As a representative,Slime mould algorithm(SMA)is widely used because of its superior initial performance.Therefore,this paper focuses on the improvement of the SMA and the mitigation of its stagnation problems.For this aim,the structure of SMA is adjusted to develop the efficiency of the original method.As a stochastic optimizer,SMA mainly stimulates the behavior of slime mold in nature.For the harmony of the exploration and exploitation of SMA,the paper proposed an enhanced algorithm of SMA called ECSMA,in which two mechanisms are embedded into the structure:elite strategy,and chaotic stochastic strategy.The details of the original SMA and the two introduced strategies are given in this paper.Then,the advantages of the improved SMA through mechanism comparison,balance-diversity analysis,and contrasts with other counterparts are validated.The experimental results demonstrate that both mechanisms have a significant enhancing effect on SMA.Also,SMA is applied to four structural design issues of the welded beam design problem,PV design problem,I-beam design problem,and cantilever beam design problem with excellent results.展开更多
The meta-heuristic algorithm is a global probabilistic search algorithm for the iterative solution.It has good performance in global optimization fields such as maximization.In this paper,a new adaptive parameter stra...The meta-heuristic algorithm is a global probabilistic search algorithm for the iterative solution.It has good performance in global optimization fields such as maximization.In this paper,a new adaptive parameter strategy and a parallel communication strategy are proposed to further improve the Cuckoo Search(CS)algorithm.This strategy greatly improves the convergence speed and accuracy of the algorithm and strengthens the algorithm’s ability to jump out of the local optimal.This paper compares the optimization performance of Parallel Adaptive Cuckoo Search(PACS)with CS,Parallel Cuckoo Search(PCS),Particle Swarm Optimization(PSO),Sine Cosine Algorithm(SCA),Grey Wolf Optimizer(GWO),Whale Optimization Algorithm(WOA),Differential Evolution(DE)and Artificial Bee Colony(ABC)algorithms by using the CEC-2013 test function.The results show that PACS algorithmoutperforms other algorithms in 20 of 28 test functions.Due to the superior performance of PACS algorithm,this paper uses it to solve the problem of the rectangular layout.Experimental results show that this scheme has a significant effect,and the material utilization rate is improved from89.5%to 97.8%after optimization.展开更多
This paper describes an efficient solution to parallelize softwareprogram instructions, regardless of the programming language in which theyare written. We solve the problem of the optimal distribution of a set ofinst...This paper describes an efficient solution to parallelize softwareprogram instructions, regardless of the programming language in which theyare written. We solve the problem of the optimal distribution of a set ofinstructions on available processors. We propose a genetic algorithm to parallelize computations, using evolution to search the solution space. The stagesof our proposed genetic algorithm are: The choice of the initial populationand its representation in chromosomes, the crossover, and the mutation operations customized to the problem being dealt with. In this paper, geneticalgorithms are applied to the entire search space of the parallelization ofthe program instructions problem. This problem is NP-complete, so thereare no polynomial algorithms that can scan the solution space and solve theproblem. The genetic algorithm-based method is general and it is simple andefficient to implement because it can be scaled to a larger or smaller number ofinstructions that must be parallelized. The parallelization technique proposedin this paper was developed in the C# programming language, and our resultsconfirm the effectiveness of our parallelization method. Experimental resultsobtained and presented for different working scenarios confirm the theoreticalresults, and they provide insight on how to improve the exploration of a searchspace that is too large to be searched exhaustively.展开更多
Genetic algorithm (GA) is one of the alternative approaches for solving the shortest path routing problem. In previous work, we have developed a coarse-grained parallel GA-based shortest path routing algorithm. With p...Genetic algorithm (GA) is one of the alternative approaches for solving the shortest path routing problem. In previous work, we have developed a coarse-grained parallel GA-based shortest path routing algorithm. With parallel GA, there is a GA operator called migration, where a chromosome is taken from one sub-population to replace a chromosome in another sub-population. Which chromosome to be taken and replaced is subjected to the migration strategy used. There are four different migration strategies that can be employed: best replace worst, best replace random, random replace worst, and random replace random. In this paper, we are going to evaluate the effect of different migration strategies on the parallel GA-based routing algorithm that has been developed in the previous work. Theoretically, the migration strategy best replace worst should perform better than the other strategies. However, result from simulation shows that even though the migration strategy best replace worst performs better most of the time, there are situations when one of the other strategies can perform just as well, or sometimes better.展开更多
To deal with the problems of premature convergence and tending to jump into the local optimum in the traditional particle swarm optimization, a novel improved particle swarm optimization algorithm was proposed. The se...To deal with the problems of premature convergence and tending to jump into the local optimum in the traditional particle swarm optimization, a novel improved particle swarm optimization algorithm was proposed. The self-adaptive inertia weight factor was used to accelerate the converging speed, and chaotic sequences were used to tune the acceleration coefficients for the balance between exploration and exploitation. The performance of the proposed algorithm was tested on four classical multi-objective optimization functions by comparing with the non-dominated sorting genetic algorithm and multi-objective particle swarm optimization algorithm. The results verified the effectiveness of the algorithm, which improved the premature convergence problem with faster convergence rate and strong ability to jump out of local optimum.展开更多
As a new intelligent optimization method,brain storm optimization(BSO)algorithm has been widely concerned for its advantages in solving classical optimization problems.Recently,an evolutionary classification optimizat...As a new intelligent optimization method,brain storm optimization(BSO)algorithm has been widely concerned for its advantages in solving classical optimization problems.Recently,an evolutionary classification optimization model based on BSO algorithm has been proposed,which proves its effectiveness in solving the classification problem.However,BSO algorithm also has defects.For example,large-scale datasets make the structure of the model complex,which affects its classification performance.In addition,in the process of optimization,the information of the dominant solution cannot be well preserved in BSO,which leads to its limitations in classification performance.Moreover,its generation strategy is inefficient in solving a variety of complex practical problems.Therefore,we briefly introduce the optimization model structure by feature selection.Besides,this paper retains the brainstorming process of BSO algorithm,and embeds the new generation strategy into BSO algorithm.Through the three generation methods of global optimal,local optimal and nearest neighbor,we can better retain the information of the dominant solution and improve the search efficiency.To verify the performance of the proposed generation strategy in solving the classification problem,twelve datasets are used in experiment.Experimental results show that the new generation strategy can improve the performance of BSO algorithm in solving classification problems.展开更多
基金supported by the National Natural Science Foundation of China under Grant No.12172100.
文摘In multi-component systems,the components are dependent,rather than degenerating independently,leading to changes inmaintenance schedules.In this situation,this study proposes a grouping dynamicmaintenance strategy.Considering the structure of multi-component systems,the maintenance strategy is determined according to the importance of the components.The strategy can minimize the expected depreciation cost of the system and divide the system into optimal groups that meet economic requirements.First,multi-component models are grouped.Then,a failure probability model of multi-component systems is established.The maintenance parameters in each maintenance cycle are updated according to the failure probability of the components.Second,the component importance indicator is introduced into the grouping model,and the optimization model,which aimed at a maximum economic profit,is established.A genetic algorithm is used to solve the non-deterministic polynomial(NP)-complete problem in the optimization model,and the optimal grouping is obtained through the initial grouping determined by random allocation.An 11-component series and parallel system is used to illustrate the effectiveness of the proposed strategy,and the influence of the system structure and the parameters on the maintenance strategy is discussed.
基金This work is supported by Ministry of Higher Education(MOHE)through Fundamental Research Grant Scheme(FRGS)(FRGS/1/2020/STG06/UTHM/03/7).
文摘Radial Basis Function Neural Network(RBFNN)ensembles have long suffered from non-efficient training,where incorrect parameter settings can be computationally disastrous.This paper examines different evolutionary algorithms for training the Symbolic Radial Basis Function Neural Network(SRBFNN)through the behavior’s integration of satisfiability programming.Inspired by evolutionary algorithms,which can iteratively find the nearoptimal solution,different Evolutionary Algorithms(EAs)were designed to optimize the producer output weight of the SRBFNN that corresponds to the embedded logic programming 2Satisfiability representation(SRBFNN-2SAT).The SRBFNN’s objective function that corresponds to Satisfiability logic programming can be minimized by different algorithms,including Genetic Algorithm(GA),Evolution Strategy Algorithm(ES),Differential Evolution Algorithm(DE),and Evolutionary Programming Algorithm(EP).Each of these methods is presented in the steps in the flowchart form which can be used for its straightforward implementation in any programming language.With the use of SRBFNN-2SAT,a training method based on these algorithms has been presented,then training has been compared among algorithms,which were applied in Microsoft Visual C++software using multiple metrics of performance,including Mean Absolute Relative Error(MARE),Root Mean Square Error(RMSE),Mean Absolute Percentage Error(MAPE),Mean Bias Error(MBE),Systematic Error(SD),Schwarz Bayesian Criterion(SBC),and Central Process Unit time(CPU time).Based on the results,the EP algorithm achieved a higher training rate and simple structure compared with the rest of the algorithms.It has been confirmed that the EP algorithm is quite effective in training and obtaining the best output weight,accompanied by the slightest iteration error,which minimizes the objective function of SRBFNN-2SAT.
基金This work was supported by the National Natural Science Foundation of China(62073341)in part by the Natural Science Fund for Distinguished Young Scholars of Hunan Province(2019JJ20026).
文摘Nonlinear equations systems(NESs)are widely used in real-world problems and they are difficult to solve due to their nonlinearity and multiple roots.Evolutionary algorithms(EAs)are one of the methods for solving NESs,given their global search capabilities and ability to locate multiple roots of a NES simultaneously within one run.Currently,the majority of research on using EAs to solve NESs focuses on transformation techniques and improving the performance of the used EAs.By contrast,problem domain knowledge of NESs is investigated in this study,where we propose the incorporation of a variable reduction strategy(VRS)into EAs to solve NESs.The VRS makes full use of the systems of expressing a NES and uses some variables(i.e.,core variable)to represent other variables(i.e.,reduced variables)through variable relationships that exist in the equation systems.It enables the reduction of partial variables and equations and shrinks the decision space,thereby reducing the complexity of the problem and improving the search efficiency of the EAs.To test the effectiveness of VRS in dealing with NESs,this paper mainly integrates the VRS into two existing state-of-the-art EA methods(i.e.,MONES and DR-JADE)according to the integration framework of the VRS and EA,respectively.Experimental results show that,with the assistance of the VRS,the EA methods can produce better results than the original methods and other compared methods.Furthermore,extensive experiments regarding the influence of different reduction schemes and EAs substantiate that a better EA for solving a NES with more reduced variables tends to provide better performance.
文摘To realize a better automatic train driving operation control strategy for urban rail trains,an automatic train driving method with improved DQN algorithm(classical deep reinforcement learning algorithm)is proposed as a research object.Firstly,the train control model is established by considering the train operation requirements.Secondly,the dueling network and DDQN ideas are introduced to prevent the value function overestimation problem.Finally,the priority experience playback and“restricted speed arrival time”are used to reduce the useless experience utilization.The experiments are carried out to verify the train operation strategy method by simulating the actual line conditions.From the experimental results,the train operation meets the ATO requirements,the energy consumption is 15.75%more energy-efficient than the actual operation,and the algorithm convergence speed is improved by about 37%.The improved DQN method not only enhances the efficiency of the algorithm but also forms a more effective operation strategy than the actual operation,thereby contributing meaningfully to the advancement of automatic train operation intelligence.
基金This work was financially supported by the National Natural Science Foundation of China(Grant No.51575528)the Science Foundation of China University of Petroleum,Beijing(No.2462022QEDX011).
文摘Pipeline isolation plugging robot (PIPR) is an important tool in pipeline maintenance operation. During the plugging process, the violent vibration will occur by the flow field, which can cause serious damage to the pipeline and PIPR. In this paper, we propose a dynamic regulating strategy to reduce the plugging-induced vibration by regulating the spoiler angle and plugging velocity. Firstly, the dynamic plugging simulation and experiment are performed to study the flow field changes during dynamic plugging. And the pressure difference is proposed to evaluate the degree of flow field vibration. Secondly, the mathematical models of pressure difference with plugging states and spoiler angles are established based on the extreme learning machine (ELM) optimized by improved sparrow search algorithm (ISSA). Finally, a modified Q-learning algorithm based on simulated annealing is applied to determine the optimal strategy for the spoiler angle and plugging velocity in real time. The results show that the proposed method can reduce the plugging-induced vibration by 19.9% and 32.7% on average, compared with single-regulating methods. This study can effectively ensure the stability of the plugging process.
基金the Key Research&Development Program of Xinjiang(Grant Number 2022B01003).
文摘This paper addresses the micro wind-hydrogen coupled system,aiming to improve the power tracking capability of micro wind farms,the regulation capability of hydrogen storage systems,and to mitigate the volatility of wind power generation.A predictive control strategy for the micro wind-hydrogen coupled system is proposed based on the ultra-short-term wind power prediction,the hydrogen storage state division interval,and the daily scheduled output of wind power generation.The control strategy maximizes the power tracking capability,the regulation capability of the hydrogen storage system,and the fluctuation of the joint output of the wind-hydrogen coupled system as the objective functions,and adaptively optimizes the control coefficients of the hydrogen storage interval and the output parameters of the system by the combined sigmoid function and particle swarm algorithm(sigmoid-PSO).Compared with the real-time control strategy,the proposed predictive control strategy can significantly improve the output tracking capability of the wind-hydrogen coupling system,minimize the gap between the actual output and the predicted output,significantly enhance the regulation capability of the hydrogen storage system,and mitigate the power output fluctuation of the wind-hydrogen integrated system,which has a broad practical application prospect.
文摘Aiming at the problems that the original Harris Hawk optimization algorithm is easy to fall into local optimum and slow in finding the optimum,this paper proposes an improved Harris Hawk optimization algorithm(GHHO).Firstly,we used a Gaussian chaotic mapping strategy to initialize the positions of individuals in the population,which enriches the initial individual species characteristics.Secondly,by optimizing the energy parameter and introducing the cosine strategy,the algorithm's ability to jump out of the local optimum is enhanced,which improves the performance of the algorithm.Finally,comparison experiments with other intelligent algorithms were conducted on 13 classical test function sets.The results show that GHHO has better performance in all aspects compared to other optimization algorithms.The improved algorithm is more suitable for generalization to real optimization problems.
基金Supported by the National Natural Science Foundation of China under Grant Nos.10674016,10875013the Specialized Research Foundation for the Doctoral Program of Higher Education under Grant No.20080027005
文摘We introduce the potential-decomposition strategy (PDS), which can be used in Markov chain Monte Carlosampling algorithms.PDS can be designed to make particles move in a modified potential that favors diffusion in phasespace, then, by rejecting some trial samples, the target distributions can be sampled in an unbiased manner.Furthermore,if the accepted trial samples are insufficient, they can be recycled as initial states to form more unbiased samples.Thisstrategy can greatly improve efficiency when the original potential has multiple metastable states separated by largebarriers.We apply PDS to the 2d Ising model and a double-well potential model with a large barrier, demonstrating inthese two representative examples that convergence is accelerated by orders of magnitude.
基金supported by National Hi-tech Research and Development Program of China (863 Program, Grant No. 2006AA11A127)
文摘Despite the series-parallel hybrid electric vehicle inherits the performance advantages from both series and parallel hybrid electric vehicle, few researches about the series-parallel hybrid electric vehicle have been revealed because of its complex co nstruction and control strategy. In this paper, a series-parallel hybrid electric bus as well as its control strategy is revealed, and a control parameter optimization approach using the real-valued genetic algorithm is proposed. The optimization objective is to minimize the fuel consumption while sustain the battery state of charge, a tangent penalty function of state of charge(SOC) is embodied in the objective function to recast this multi-objective nonlinear optimization problem as a single linear optimization problem. For this strategy, the vehicle operating mode is switched based on the vehicle speed, and an "optimal line" typed strategy is designed for the parallel control. The optimization parameters include the speed threshold for mode switching, the highest state of charge allowed, the lowest state of charge allowed and the scale factor of the engine optimal torque to the engine maximum torque at a rotational speed. They are optimized through numerical experiments based on real-value genes, arithmetic crossover and mutation operators. The hybrid bus has been evaluated at the Chinese Transit Bus City Driving Cycle via road test, in which a control area network-based monitor system was used to trace the driving schedule. The test result shows that this approach is feasible for the control parameter optimization. This approach can be applied to not only the novel construction presented in this paper, but also other types of hybrid electric vehicles.
基金supported by the National Natural Science Foundation of China (Grant No. 51008167)S&T Plan Project (Grant No. J10LE07) from Shandong Provincial Education Departmentthe Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20103721120001)
文摘The determination of optimal values for three parameters required in the original particle swarm optimization algorithm is very difficult. It is proposed that two new parameters simulating the harmony search strategy can be adopted instead of the three parameters which are required in the original particle swarm optimization algorithm to update the positions of all the particles. The improved particle swarm optimization is used in the location of the critical slip surface of soil slope, and it is found that the improved particle swarm optimization algorithm is insensitive to the two parameters while the original particle swarm optimization algorithm can be sensitive to its three parameters.
基金Supported by the National Natural Science Foundation of China(61472289)the Open Project Program of the State Key Laboratory of Digital Manufacturing Equipment and Technology(DMETKF2017016)
文摘Population-based algorithms have been used in many real-world problems.Bat algorithm(BA)is one of the states of the art of these approaches.Because of the super bat,on the one hand,BA can converge quickly;on the other hand,it is easy to fall into local optimum.Therefore,for typical BA algorithms,the ability of exploration and exploitation is not strong enough and it is hard to find a precise result.In this paper,we propose a novel bat algorithm based on cross boundary learning(CBL)and uniform explosion strategy(UES),namely BABLUE in short,to avoid the above contradiction and achieve both fast convergence and high quality.Different from previous opposition-based learning,the proposed CBL can expand the search area of population and then maintain the ability of global exploration in the process of fast convergence.In order to enhance the ability of local exploitation of the proposed algorithm,we propose UES,which can achieve almost the same search precise as that of firework explosion algorithm but consume less computation resource.BABLUE is tested with numerous experiments on unimodal,multimodal,one-dimensional,high-dimensional and discrete problems,and then compared with other typical intelligent optimization algorithms.The results show that the proposed algorithm outperforms other algorithms.
文摘Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields,including stock market investment.However,few studies have focused on forecasting daily stock market returns,especially when using powerful machine learning techniques,such as deep neural networks(DNNs),to perform the analyses.DNNs employ various deep learning algorithms based on the combination of network structure,activation function,and model parameters,with their performance depending on the format of the data representation.This paper presents a comprehensive big data analytics process to predict the daily return direction of the SPDR S&P 500 ETF(ticker symbol:SPY)based on 60 financial and economic features.DNNs and traditional artificial neural networks(ANNs)are then deployed over the entire preprocessed but untransformed dataset,along with two datasets transformed via principal component analysis(PCA),to predict the daily direction of future stock market index returns.While controlling for overfitting,a pattern for the classification accuracy of the DNNs is detected and demonstrated as the number of the hidden layers increases gradually from 12 to 1000.Moreover,a set of hypothesis testing procedures are implemented on the classification,and the simulation results show that the DNNs using two PCA-represented datasets give significantly higher classification accuracy than those using the entire untransformed dataset,as well as several other hybrid machine learning algorithms.In addition,the trading strategies guided by the DNN classification process based on PCA-represented data perform slightly better than the others tested,including in a comparison against two standard benchmarks.
基金Project 60575046 supported by the National Natural Science Foundation of China
文摘Noises widely exist in interactive genetic algorithms. However, there is no effective method to solve this problem up to now. There are two kinds of noises, one is the noise existing in visual systems and the other is resulted from user’s preference mechanisms. Characteristics of the two noises are presented aiming at the application of interac- tive genetic algorithms in dealing with images. The evolutionary phases of interactive genetic algorithms are determined according to differences in the same individual’s fitness among different generations. Models for noises in different phases are established and the corresponding strategies for reducing noises are given. The algorithm proposed in this paper has been applied to fashion design, which is a typical example of image processing. The results show that the strategies can reduce noises in interactive genetic algorithms and improve the algorithm’s performance effectively. However, a further study is needed to solve the problem of determining the evolution phase by using suitable objective methods so as to find out an effective method to decrease noises.
基金supported in part by the National Natural Science Foundation of China(J2124006,62076185)。
文摘The Swarm intelligence algorithm is a very prevalent field in which some scholars have made outstanding achievements.As a representative,Slime mould algorithm(SMA)is widely used because of its superior initial performance.Therefore,this paper focuses on the improvement of the SMA and the mitigation of its stagnation problems.For this aim,the structure of SMA is adjusted to develop the efficiency of the original method.As a stochastic optimizer,SMA mainly stimulates the behavior of slime mold in nature.For the harmony of the exploration and exploitation of SMA,the paper proposed an enhanced algorithm of SMA called ECSMA,in which two mechanisms are embedded into the structure:elite strategy,and chaotic stochastic strategy.The details of the original SMA and the two introduced strategies are given in this paper.Then,the advantages of the improved SMA through mechanism comparison,balance-diversity analysis,and contrasts with other counterparts are validated.The experimental results demonstrate that both mechanisms have a significant enhancing effect on SMA.Also,SMA is applied to four structural design issues of the welded beam design problem,PV design problem,I-beam design problem,and cantilever beam design problem with excellent results.
基金funded by the NationalKey Research and Development Program of China under Grant No.11974373.
文摘The meta-heuristic algorithm is a global probabilistic search algorithm for the iterative solution.It has good performance in global optimization fields such as maximization.In this paper,a new adaptive parameter strategy and a parallel communication strategy are proposed to further improve the Cuckoo Search(CS)algorithm.This strategy greatly improves the convergence speed and accuracy of the algorithm and strengthens the algorithm’s ability to jump out of the local optimal.This paper compares the optimization performance of Parallel Adaptive Cuckoo Search(PACS)with CS,Parallel Cuckoo Search(PCS),Particle Swarm Optimization(PSO),Sine Cosine Algorithm(SCA),Grey Wolf Optimizer(GWO),Whale Optimization Algorithm(WOA),Differential Evolution(DE)and Artificial Bee Colony(ABC)algorithms by using the CEC-2013 test function.The results show that PACS algorithmoutperforms other algorithms in 20 of 28 test functions.Due to the superior performance of PACS algorithm,this paper uses it to solve the problem of the rectangular layout.Experimental results show that this scheme has a significant effect,and the material utilization rate is improved from89.5%to 97.8%after optimization.
文摘This paper describes an efficient solution to parallelize softwareprogram instructions, regardless of the programming language in which theyare written. We solve the problem of the optimal distribution of a set ofinstructions on available processors. We propose a genetic algorithm to parallelize computations, using evolution to search the solution space. The stagesof our proposed genetic algorithm are: The choice of the initial populationand its representation in chromosomes, the crossover, and the mutation operations customized to the problem being dealt with. In this paper, geneticalgorithms are applied to the entire search space of the parallelization ofthe program instructions problem. This problem is NP-complete, so thereare no polynomial algorithms that can scan the solution space and solve theproblem. The genetic algorithm-based method is general and it is simple andefficient to implement because it can be scaled to a larger or smaller number ofinstructions that must be parallelized. The parallelization technique proposedin this paper was developed in the C# programming language, and our resultsconfirm the effectiveness of our parallelization method. Experimental resultsobtained and presented for different working scenarios confirm the theoreticalresults, and they provide insight on how to improve the exploration of a searchspace that is too large to be searched exhaustively.
文摘Genetic algorithm (GA) is one of the alternative approaches for solving the shortest path routing problem. In previous work, we have developed a coarse-grained parallel GA-based shortest path routing algorithm. With parallel GA, there is a GA operator called migration, where a chromosome is taken from one sub-population to replace a chromosome in another sub-population. Which chromosome to be taken and replaced is subjected to the migration strategy used. There are four different migration strategies that can be employed: best replace worst, best replace random, random replace worst, and random replace random. In this paper, we are going to evaluate the effect of different migration strategies on the parallel GA-based routing algorithm that has been developed in the previous work. Theoretically, the migration strategy best replace worst should perform better than the other strategies. However, result from simulation shows that even though the migration strategy best replace worst performs better most of the time, there are situations when one of the other strategies can perform just as well, or sometimes better.
文摘To deal with the problems of premature convergence and tending to jump into the local optimum in the traditional particle swarm optimization, a novel improved particle swarm optimization algorithm was proposed. The self-adaptive inertia weight factor was used to accelerate the converging speed, and chaotic sequences were used to tune the acceleration coefficients for the balance between exploration and exploitation. The performance of the proposed algorithm was tested on four classical multi-objective optimization functions by comparing with the non-dominated sorting genetic algorithm and multi-objective particle swarm optimization algorithm. The results verified the effectiveness of the algorithm, which improved the premature convergence problem with faster convergence rate and strong ability to jump out of local optimum.
基金supported by the National Natural Science Foundation of China(61876089,61403206,61876185,61902281)the opening Project of Jiangsu Key Laboratory of Data Science and Smart Software(No.2019DS302)+2 种基金the Natural Science Foundation of Jiangsu Province(BK20141005)the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(14KJB520025)the Engineering Research Center of Digital Forensics,Ministry of Education,and the Priority Academic Program Development of Jiangsu Higher Education Institutions.
文摘As a new intelligent optimization method,brain storm optimization(BSO)algorithm has been widely concerned for its advantages in solving classical optimization problems.Recently,an evolutionary classification optimization model based on BSO algorithm has been proposed,which proves its effectiveness in solving the classification problem.However,BSO algorithm also has defects.For example,large-scale datasets make the structure of the model complex,which affects its classification performance.In addition,in the process of optimization,the information of the dominant solution cannot be well preserved in BSO,which leads to its limitations in classification performance.Moreover,its generation strategy is inefficient in solving a variety of complex practical problems.Therefore,we briefly introduce the optimization model structure by feature selection.Besides,this paper retains the brainstorming process of BSO algorithm,and embeds the new generation strategy into BSO algorithm.Through the three generation methods of global optimal,local optimal and nearest neighbor,we can better retain the information of the dominant solution and improve the search efficiency.To verify the performance of the proposed generation strategy in solving the classification problem,twelve datasets are used in experiment.Experimental results show that the new generation strategy can improve the performance of BSO algorithm in solving classification problems.