Regular Papers

International Journal of Control, Automation, and Systems 2024; 22(7): 2327-2340

https://doi.org/10.1007/s12555-022-0784-2

© The International Journal of Control, Automation, and Systems

Application of a Hybrid Improved Particle Swarm Algorithm for Prediction of Cutting Energy Consumption in CNC Machine Tools

Jidong Du, Yan Wang*, and Zhicheng Ji

Jiangnan University

Abstract

Estimation and analysis of energy consumption for machine tool is the basis of energy efficiency improvement. To improve the accuracy of ELM algorithm in CNC machine tool energy consumption prediction, a prediction method based on an improved particle swarm optimization (CAPSO) algorithm and an extreme learning machine (ELM) is proposed. The contribution of the algorithm includes the following three aspects. First, sobol sequence is used to initialize the PSO population to make distribution of initial population more even in solution space. Second, the center wanders and boundary neighborhood updates strategy are used to improve the population quality and convergence rate of PSO. Then, to avoid the optimal local solution, the adaptive inertia weight is introduced to achieve the stochastic perturbation of the population. The performance of the algorithm is tested by ten benchmark function, indicating that the CAPSO ensures the search accuracy and improves the algorithm’s convergence rate. Finally, the CAPSO algorithm is used to optimize the weights and thresholds of an ELM, and the CAPSO-ELM cutting energy consumption prediction model is established. Case analysis and comparative experiments show that the stability, prediction accuracy and generalization ability of CAPSO-ELM model are better than those of other models.

Keywords CAPSO-ELM model, energy consumption, extreme learning machine, improved particle swarm optimization.

Article

Regular Papers

International Journal of Control, Automation, and Systems 2024; 22(7): 2327-2340

Published online July 1, 2024 https://doi.org/10.1007/s12555-022-0784-2

Copyright © The International Journal of Control, Automation, and Systems.

Application of a Hybrid Improved Particle Swarm Algorithm for Prediction of Cutting Energy Consumption in CNC Machine Tools

Jidong Du, Yan Wang*, and Zhicheng Ji

Jiangnan University

Abstract

Estimation and analysis of energy consumption for machine tool is the basis of energy efficiency improvement. To improve the accuracy of ELM algorithm in CNC machine tool energy consumption prediction, a prediction method based on an improved particle swarm optimization (CAPSO) algorithm and an extreme learning machine (ELM) is proposed. The contribution of the algorithm includes the following three aspects. First, sobol sequence is used to initialize the PSO population to make distribution of initial population more even in solution space. Second, the center wanders and boundary neighborhood updates strategy are used to improve the population quality and convergence rate of PSO. Then, to avoid the optimal local solution, the adaptive inertia weight is introduced to achieve the stochastic perturbation of the population. The performance of the algorithm is tested by ten benchmark function, indicating that the CAPSO ensures the search accuracy and improves the algorithm’s convergence rate. Finally, the CAPSO algorithm is used to optimize the weights and thresholds of an ELM, and the CAPSO-ELM cutting energy consumption prediction model is established. Case analysis and comparative experiments show that the stability, prediction accuracy and generalization ability of CAPSO-ELM model are better than those of other models.

Keywords: CAPSO-ELM model, energy consumption, extreme learning machine, improved particle swarm optimization.

IJCAS
July 2024

Vol. 22, No. 7, pp. 2055~2340

Stats or Metrics

Share this article on

  • line

Related articles in IJCAS

IJCAS

eISSN 2005-4092
pISSN 1598-6446