A bayesian based process monitoring and fixture fault diagnosis approach in the auto body assembly process |
| |
Authors: | Yinhua Liu Xialiang Ye Sun Jin |
| |
Institution: | 1.School of Mechanical Engineering,University of Shanghai for Science and Technology,Shanghai,China;2.State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering,Shanghai Jiaotong University,Shanghai,China |
| |
Abstract: | The auto body process monitoring and the root cause diagnosis based on data-driven approaches are vital ways to improve the dimension quality of sheet metal assemblies. However, during the launch time of the process mass production with an off-line measurement strategy, the traditional statistical methods are difficult to perform process control effectively. Based on the powerful abilities in information fusion, a systematic Bayesian based quality control approach is presented to solve the quality problems in condition of incomplete dataset. For the process monitoring, a Bayesian estimation method is used to give out-of-control signals in the process. With the abnormal evidence, the Bayesian network (BN) approach is employed to identify the fixture root causes. A novel BN structure and the conditional probability training methods based on process knowledge representation are proposed to obtain the diagnostic model. Furthermore, based on the diagnostic performance analysis, a case study is used to evaluate the effectiveness of the proposed approach. Results show that the Bayesian based method has a better diagnostic performance for multi-fault cases. |
| |
Keywords: | |
本文献已被 CNKI SpringerLink 等数据库收录! |
|