An Intelligent Fault Detection Method Based on Sparse Auto-Encoder for Industrial Process Systems: A Case Study on Tennessee Eastman Process Chemical System

2018 ◽  
Author(s):  
Hao Ren ◽  
Yi Chai ◽  
Jianfeng Qu ◽  
Ke Zhang ◽  
Qiu Tang
Keyword(s):  
Fault Detection ◽  
Detection Method ◽  
Industrial Process ◽  
Chemical System ◽  
Tennessee Eastman Process ◽  
Process Systems

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

Sensors ◽  
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.

scholarly journals A Partial Robust M-Regression-Based Prediction and Fault Detection Method

2014 ◽  
Vol 2014 ◽  
pp. 1-7
Author(s):  
Jianfang Jiao ◽  
Jingxin Zhang ◽  
Hamid Reza Karimi
Keyword(s):  
Fault Detection ◽  
Least Squares ◽  
Large Scale ◽  
Detection Method ◽  
Industrial Process ◽  
Orthogonal Decomposition ◽  
Process Data ◽  
Robust Prediction ◽  
Monitoring Performance ◽  
Measured Process

Due to its simplicity and easy implementation, partial least squares (PLS) serves as an efficient approach in large-scale industrial process. However, like many data-based methods, PLS is quite sensitive to outliers, which is a common abnormal characteristic of the measured process data that can significantly affect the monitoring performance of PLS. In order to develop a robust prediction and fault detection method, this paper employs the partial robust M-regression (PRM) to deal with the outliers. Moreover, to eliminate the useless variations for prediction, an orthogonal decomposition is performed on the measurable variables space so as to allow the new method to serve as a powerful tool for quality-related prediction and fault detection. The proposed method is finally applied on the Tennessee Eastman (TE) process.

scholarly journals Utilization of Classical Scaling Technique in Sustaining Fault Detection Performance in Process Monitoring

2020 ◽  
Vol 6 (1) ◽  
pp. 1-11
Author(s):  
Mohd Yusri Mohd Yunus ◽  
Jie Zhang ◽  
Sajjad K Al-Amshawee
Keyword(s):  
Fault Detection ◽  
Process Monitoring ◽  
Industrial Process ◽  
Principal Component ◽  
Detection Performance ◽  
Multivariate Statistical ◽  
Statistical Process ◽  
Tennessee Eastman Process ◽  
Operating Modes ◽  
Main Challenge

Multivariate Statistical Process Monitoring (MSPM) fundamentally adopts the conventional Principal Component Analysis (cPCA) as the main platform for data compression. The main challenge though, the association nature of most industrial process variables are highly non-linear. As a result, the risks of applying the conventional approach of MSPM within this context may include sluggish or failed in detection, misinterpretation of signals, incorrect fault diagnosis and also inflexible as well as insensitive to changing of operating modes. In addressing the issue, this paper introduces new sets of monitoring parameters i.e. Sm2, Sr2 and Sr3, which have been derived within the frameworks of Classical Scaling (CMDS) and Procusters Analysis (PA) methods. The overall fault detection performance that applied based on the Tennessee Eastman Process (TEP) cases show that the Sr3 can detect the faults particularly for abnormal events number 3, 9, 15 and 19 in higher rate compared to the cPCA-MSPM system. This proves that the new monitoring statistics work effectively in avoiding missed detection during monitoring which cannot be addressed effectively by the traditional monitoring system.

Model for Unanticipated Fault Detection by OCPCA

2012 ◽  
Vol 591-593 ◽  
pp. 2108-2113 ◽  
Author(s):  
Zhang Ming He ◽  
Hai Yin Zhou ◽  
Jiong Qi Wang ◽  
Yuan Yuan Jiao
Keyword(s):  
Fault Detection ◽  
Health Management ◽  
Industrial Process ◽  
Principal Component ◽  
Critical Issue ◽  
Fault Detection And Diagnosis ◽  
Tennessee Eastman Process ◽  
Proposed Model ◽  
Single Pattern ◽  
Detection And Diagnosis

Detection and diagnosis of unanticipated fault has inevitably become a critical issue for PHM (Prognostics and Health Management), especially in the fields of robot, spacecraft and industrial system. It is difficult to overcome this problem since there is lack of history information, prior knowledge and dealing strategy for unanticipated fault. In this paper, a general processing model for unanticipated fault detection and diagnosis is constructed, then, a detection method, named OCPCA (One-class Principal Component Analysis), is proposed. Every OCPCA detector is trained by data from single pattern, and the testing task is to determine whether the testing data is from the very pattern. If the unanticipated fault data is rejected by all OCPCA detectors, then the detection task is accomplished. TEP (Tennessee-Eastman Process), a widely used simulated system based on an actual industrial process, is used to verify the detection of unanticipated fault. The results demonstrate the validity of the proposed model and method.

scholarly journals Adaptive Fault Detection with Two Time-Varying Control Limits for Nonlinear and Multimodal Processes

2014 ◽  
Vol 2014 ◽  
pp. 1-10
Author(s):  
Jinna Li ◽  
Yuan Li ◽  
Yanhong Xie ◽  
Xuejun Zong
Keyword(s):  
Fault Detection ◽  
Detection Method ◽  
Nearest Neighbors ◽  
Training Data ◽  
Time Varying ◽  
Training Samples ◽  
Mean And Variance ◽  
The Mean ◽  
Control Limits

A novel fault detection method is proposed for detection process with nonlinearity and multimodal batches. Calculating the Mahalanobis distance of samples, the data with the similar characteristics are replaced by the mean of them; thus, the number of training data is reduced easily. Moreover, the super ball regions of mean and variance of training data are presented, which not only retains the statistical properties of original training data but also avoids the reduction of data unlimitedly. To accurately identify faults, two control limits are determined during investigating the distributions of distances and angles between training samples to their nearest neighboring samples in the reduced database; thus, the traditionalk-nearest neighbors (only considering distances) fault detection (FD-kNN) method is developed. Another feature of the proposed detection method is that the control limits vary with updating database such that an adaptive fault detection technique is obtained. Finally, numerical examples and case study are given to illustrate the effectiveness and advantages of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document