Optimization of complex part-machining services based on feature decomposition in cloud manufacturing

ABSTRACT

Cloud manufacturing (CM) is a new service-oriented networked manufacturing mode. The optimal configuration of manufacturing services is one of most challenging topics in CM. Most research focuses on service composition optimization algorithms. However, for different manufacturing tasks, the configuration mode of the manufacturing services is different. For complex parts, effectively using the appropriate optimization strategy to solve the optimization of machining services is still rare in CM. To solve the above problem, a new machining task decomposition and service optimization strategy is proposed. Under this mode, the features of the complex part are defined as the basic task granularity. Four machining service optimization modes are constructed, and a mathematical model of machining service optimization under the four modes is established. Subsequently, a particle swarm optimization algorithm based on simulated annealing (PSOBSA) is designed by combining the particle swarm optimization (PSO) and simulated annealing (SA). Finally, three groups of simulation experiments are conducted to simulate the optimization mode of complex parts machining services based on feature decomposition. The simulation results demonstrate the feasibility of the service optimization mode and the effectiveness of the PSOBSA. The research results presented in this paper provide an machining service outsourcing method for complex parts.

KEYWORDS:

• Cloud manufacturing
• optimizing configuration
• complex parts
• service optimization mode
• simulated annealing
• particle swarm optimization

Acknowledgments

We would like to thank the reviewers and the editor for their constructive comments and suggestions to this paper. We also acknowledge the Youth Science Foundation of National Natural Science Foundation (No.51705438), Sichuan science and technology project (No.2018JY0366), and open fund (No.OGE201702-20) of Key Laboratory of Oil & Gas Equipment, Ministry of Education (Southwest Petroleum University).

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [No.51705438]; Sichuan science and technology project of China [No.2018JY0366].