A Knowledge-Guided Process Planning Approach with Reinforcement Learning

Abstract

With the wide application of computer-aided technologies such as CAD and CAM in the manufacturing industry, more and more process documents and design documents generate multi-source process knowledge and expert experience. However, due to the diverse and complex representation of process knowledge, more effective methods are needed to mine a large amount of multi-source information and the explicit and implicit relationships between knowledge. Effective knowledge reuse in process planning still needs to be improved. This paper proposes a reinforcement learning approach that combines knowledge graphs and process decision-making activities in process planning to exploit the learning potential of process knowledge graphs. Firstly, a reinforcement learning environment for process planning is introduced to model the process planning problem as a sequential recommendation of process knowledge. Secondly, this paper designs in detail the state representation that combines process sequences and potential relationships between processes. This paper also creates a composite reward function that combines the process planning environment. In addition, a new algorithm is proposed for learning the proposed model more efficiently. Experimental results show that the network structure proposed in this paper has more accurate recommendation results than other methods. Finally, this paper takes flange as an example to verify the feasibility and effectiveness of the proposed method.