Quality consistency analysis for complex assembly process based on Bayesian networks

In recent years, assembly process has been rapidly pushing the envelope in building complex, optimized products, by taking advantage of big data mining and machine intelligence technologies. Along with such developments, it has become increasingly necessary to strictly control quality consistency level of the assembly activities. However, due to the difficulty of modelling, quality consistency improvement of complex assembly process has always been a challenge for academia and industry. This paper attempts to describe the assembly process by using Bayesian networks and to provide an effective data-based scheme for improving quality consistency. First of all, considering the nonlinear and coupling characteristics, we introduce the maximum information coefficient and network deconvolution method to detect the direct associations in the assembly process and get an undirected graph. Secondly, in order to obtain a complete Bayesian network, we derive the directions of edges based on the independence between causal variable distribution and function mechanism. Thus, the key influence factors on quality consistency and the latent causal mechanism can be analyzed. This data-based scheme is applied to power consistency analysis of a real diesel engine production line, where the effectiveness is further demonstrated from real industrial data. As a result, this study provides theoretical support and technical guarantee for the improvement of assembly process, quality control, product quality and enterprise benefit. (C) 2020 The Authors. Published by Elsevier Ltd.