A variational autoencoders approach for process monitoring and fault diagnosis

With the development of modernization, the application of seamless tube becomes widespread. As the first process of seamless tube, piercing is vital for the quality of the tube. The solid round billet will be transformed into a hollow shell after the piercing process. The defects of hollow shell cannot be cleared in the following process, so a monitoring model for the quality of the hollow shell is important. But the piercing process is very complicated, and a mechanism model is difficult to build between the qualities of the hollow shell and measurement variables. Furthermore, an intelligent model is needed. We established two piercing process monitoring and fault diagnosis models based on the multiway principal component analysis (MPCA) model and the multistage MPCA model, respectively, and furthermore we made a comparison between these two concepts. We took three ways to divide the period based on process,K-means, and GA, respectively. Simulation experiments have shown that the multistate MPCA method has advantage over the MPCA method and the model based on the genetic algorithm (GA) can monitor the process effectively and detect the faults.

Download Full-text

Process Monitoring and Fault Diagnosis of Penicillin Fermentation Based on Improved MICA

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.591-593.1783 ◽

2012 ◽

Vol 591-593 ◽

pp. 1783-1788 ◽

Cited By ~ 4

Author(s):

Zhi Yang Jia ◽

Pu Wang ◽

Xue Jin Gao

Keyword(s):

Fault Diagnosis ◽

Process Monitoring ◽

Gaussian Distribution ◽

Component Analysis ◽

Higher Order ◽

Process Variables ◽

Multivariate Gaussian Distribution ◽

Independent Components ◽

Multivariate Gaussian ◽

Penicillin Fermentation

In the process monitoring and fault diagnosis of batch processes, traditional principal component analysis (PCA) and least-squares (PLS), are assuming that the process variables are multivariate Gaussian distribution. But in the practical industrial process, the data observed of process variables do not necessarily be the multivariate Gaussian distribution. Independent component analysis (ICA), as a higher-order statistical method, is more suitable for dynamic systems. Observational data are decomposed into a linear combination of the independent components under statistical significance. The higher order statistics will be extracted and the mixed signals are decomposed into independent non-Gaussian components. Traditional method of ICA has to predefine the number of independent components. This paper proposed an improved MICA method of realizing the automatically choosing the independent components through setting the threshold value of the negentropy. The method can solve the problem of predefining the number of independent components in traditional methods and meanwhile it reduces the complexity of the monitoring model. The proposed method is used to do the process monitoring and fault diagnosis of penicillin fermentation and the results verify the feasibility and effectiveness of the method.

Download Full-text

Joint Data-Driven Fault Diagnosis Integrating Causality Graph With Statistical Process Monitoring for Complex Industrial Processes

IEEE Access ◽

10.1109/access.2017.2766235 ◽

2017 ◽

Vol 5 ◽

pp. 25217-25225 ◽

Cited By ~ 9

Author(s):

Jie Dong ◽

Mengyuan Wang ◽

Xiong Zhang ◽

Liang Ma ◽

Kaixiang Peng

Keyword(s):

Fault Diagnosis ◽

Process Monitoring ◽

Data Driven ◽

Industrial Processes ◽

Statistical Process ◽

Statistical Process Monitoring

Download Full-text

Fault Detection and Diagnosis in Industrial Processes with Variational Autoencoder: A Comprehensive Study

Sensors ◽

10.3390/s22010227 ◽

2021 ◽

Vol 22 (1) ◽

pp. 227

Author(s):

Jinlin Zhu ◽

Muyun Jiang ◽

Zhong Liu

Keyword(s):

Fault Diagnosis ◽

Fault Detection ◽

Process Monitoring ◽

Industrial Process ◽

Fault Detection And Diagnosis ◽

Propagation Mechanism ◽

Tennessee Eastman Process ◽

Variational Autoencoder ◽

Detection And Diagnosis ◽

Detection Schemes

This work considers industrial process monitoring using a variational autoencoder (VAE). As a powerful deep generative model, the variational autoencoder and its variants have become popular for process monitoring. However, its monitoring ability, especially its fault diagnosis ability, has not been well investigated. In this paper, the process modeling and monitoring capabilities of several VAE variants are comprehensively studied. First, fault detection schemes are defined in three distinct ways, considering latent, residual, and the combined domains. Afterwards, to conduct the fault diagnosis, we first define the deep contribution plot, and then a deep reconstruction-based contribution diagram is proposed for deep domains under the fault propagation mechanism. In a case study, the performance of the process monitoring capability of four deep VAE models, namely, the static VAE model, the dynamic VAE model, and the recurrent VAE models (LSTM-VAE and GRU-VAE), has been comparatively evaluated on the industrial benchmark Tennessee Eastman process. Results show that recurrent VAEs with a deep reconstruction-based diagnosis mechanism are recommended for industrial process monitoring tasks.

Download Full-text