Title: Automatic assembly cost control method of Industry 4.0 production line based on deep reinforcement learning

Authors: Hui Zhou

Addresses: College of Management, Hunan City University, Yiyang 13000, China

Abstract: Aiming at the problems of low cost closeness and poor benefit in traditional production line automatic assembly cost control method, an automatic assembly cost control method of Industry 4.0 production line based on deep reinforcement learning is proposed. The assembly cost status is represented by state value function, and the cost data is cascaded by attention model. Based on the analysis of the principle of deep reinforcement learning, a deep reinforcement learning model for automatic assembly cost control of Industry 4.0 production line is constructed by feed forward control, process control and feedback control of assembly cost. According to the model, the assembly cost data is controlled, and the error function is used to correct the model control results, so as to realise the automatic assembly cost control of the production line. The results show that the approach degree of automatic assembly cost control is about 97%.

Keywords: deep reinforcement learning; Industry 4.0; automatic assembly; production line; cost control.

DOI: 10.1504/IJMTM.2022.128729

International Journal of Manufacturing Technology and Management, 2022 Vol.36 No.5/6, pp.352 - 367

Received: 07 May 2021
Accepted: 27 Oct 2021
Published online: 02 Feb 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article