Process Knowledge-Guided Autonomous Evolutionary Optimization for Constrained Multiobjective Problems

Zuo, Mingcheng; Gong, Dunwei; Wang, Yan; Ye, Xianming; Zeng, Bo; Meng, Fanyong

doi:10.1109/tevc.2023.3243109

Cited by 24 publications

(5 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tian et al [37] employed deep reinforcement learning to select different operators at different stages, striking a balance between the diversity and convergence of the population. Zuo et al [38] also used deep reinforcement learning to dynamically employ reproduction operators, which can be embedded into existing evolutionary algorithms and improve their performance.…”

Section: The Multi-operator Methodsmentioning

confidence: 99%

“…Therefore, employing different reproduction operators for different population states has a significant impact on population regulation. Among various evolutionary algorithms, Differential Evolution (DE) [38] and Genetic Algorithm (GA) [9] are very typical and have been widely applied. The reproduction operator in DE typically exhibits good convergence, while the reproduction operator in GA possesses strong global search capabilities.…”

Section: Reproduction Operator For Regulating Population Statementioning

confidence: 99%

See 1 more Smart Citation

Population Feasibility State Guided Autonomous Constrained Multi-Objective Evolutionary Optimization

Zuo,

Xue

2024

Mathematics

Self Cite

View full text Add to dashboard Cite

Many practical problems can be classified as constrained multi-objective optimization problems. Although various methods have been proposed for solving constrained multi-objective optimization problems, there is still a lack of research considering the integration of multiple constraint handling techniques. Given this, this paper combines the objective and constraint separation method with the multi-operator method, proposing a population feasibility state guided autonomous constrained evolutionary optimization method. This method first defines the feasibility state of the population based on both feasibility and ε feasibility of the solutions. Subsequently, a reinforcement learning model is employed to construct a mapping model between the population state and reproduction operators. Finally, based on the real-time population state, the mapping model is utilized to recommend the promising reproduction operator for the next generation. This approach demonstrates significant performance improvement for ε constrained mechanisms in constrained multi-objective optimization algorithms, and shows considerable advantages in comparison with state-of-the-art constrained multi-objective optimization algorithms.

show abstract

Section: The Multi-operator Methodsmentioning

confidence: 99%

Section: Reproduction Operator For Regulating Population Statementioning

confidence: 99%

Population Feasibility State Guided Autonomous Constrained Multi-Objective Evolutionary Optimization

Zuo,

Xue

2024

Mathematics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Tis framework designed parameter sets in advance for each evolutionary algorithm, and q-learning will help choose one parameter-based state in each iteration. Te authors of [35] combined DRL with MOEA for solving constrained multiobjective optimization problems, which took into account both population's convergence and diversity in their inputs to DRL.…”

Section: Transfer Learning-based Parameter Control Methodmentioning

confidence: 99%

Parameter Control Framework for Multiobjective Evolutionary Computation Based on Deep Reinforcement Learning

Zhou,

Zhang,

Niu

et al. 2024

International Journal of Intelligent Systems

View full text Add to dashboard Cite

To address the challenge of parameter adjustment in complex environments, this paper introduces a transfer learning-based parameter control framework via deep reinforcement learning for multiobjective evolutionary algorithms (MOEAs). To avoid the requirement for accurate Pareto front information, this framework is proposed with comprehensive global-state information, including basic problem features, the relative position of individuals, the distribution of fitness value, and the grid-IGD. Building on this framework, four reinforced multiobjective evolutionary algorithms (r-MOEAs) are proposed and tested on four DTLZ benchmarks and eight WFG benchmarks. The results of the comparative analyses reveal that compared with the original MOEAs, the four r-MOEAs exhibit faster convergence and stronger robustness. It is also confirmed that our proposed parameter control framework has the capability to learn knowledge from different experiences and improve the performance of MOEAs.

show abstract

“…Unlike the deep reinforcement learning generating regulatory strategies, evolutionary computation does not require known jig states, i.e., s t , but only a surrogate model evaluating candidate solutions and parameter boundaries is needed. Evolutionary algorithms, such as diferential evolution (DE) [16][17][18][19], are efective in solving the highdimensional optimization problems. However, to avoid large adjustment of equipment parameters, DE can only locally fne-tune the control parameters.…”

Section: Regulatory Strategies With Auto-diferential Evolutionmentioning

confidence: 99%

Deep Reinforcement Learning and Auto-Differential Evolution Co-Guided Coal Washing

Zuo

2024

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

Background. Coal washing is a complicated process and difficult to control, which has many controlling parameters with strong coupling relationship. It is still a challenge to realize the self-perception, self-adjustment, and self-evaluation of coal washing machine, improve the quality of coal washing, ensure production safety, and reduce labor cost. Methods. Through the intelligent transformation of jig, this paper proposes an intelligent washing method with cooperated deep reinforcement learning and evolutionary computation. First, it designs a fault warning method based on statistical analysis, helping to recover the normal running state of jig with manual maintenance. Then, it constructs a regulation strategy generation method with deep reinforcement learning supported by the fusion of artificial experience and historical data. Last, for the lack of monitoring data caused by poor communication quality and environment, the regulation strategy prediction method with evolutionary computation and surrogate model is proposed. Results. In practice, this method shows accurate fault warning accuracy and rapid cleaned coal ash adjustment response ability. Conclusions. This shows that the method proposed in this paper is of great significance for intelligent washing and can better cope with the special situation when the washing equipment sensing data are missing.

show abstract

Process Knowledge-Guided Autonomous Evolutionary Optimization for Constrained Multiobjective Problems

Cited by 24 publications

References 74 publications

Population Feasibility State Guided Autonomous Constrained Multi-Objective Evolutionary Optimization

Population Feasibility State Guided Autonomous Constrained Multi-Objective Evolutionary Optimization

Parameter Control Framework for Multiobjective Evolutionary Computation Based on Deep Reinforcement Learning

Deep Reinforcement Learning and Auto-Differential Evolution Co-Guided Coal Washing

Contact Info

Product

Resources

About