Fault diagnosis of Tennessee Eastman process using signal geometry matching technique

Abstract

This article employs adaptive rank-order morphological filter to develop a pattern classification algorithm for fault diagnosis in benchmark chemical process: Tennessee Eastman process. Rank-order filtering possesses desirable properties of dealing with nonlinearities and preserving details in complex processes. Based on these benefits, the proposed algorithm achieves pattern matching through adopting one-dimensional adaptive rank-order morphological filter to process unrecognized signals under supervision of different standard signal patterns. The matching degree is characterized by the evaluation of error between standard signal and filter output signal. Initial parameter settings of the algorithm are subject to random choices and further tuned adaptively to make output approach standard signal as closely as possible. Data fusion technique is also utilized to combine diagnostic results from multiple sources. Different fault types in Tennessee Eastman process are studied to manifest the effectiveness and advantages of the proposed method. The results show that compared with many typical multivariate statistics based methods, the proposed algorithm performs better on the deterministic faults diagnosis.

Bearing Fault Feature Selection Method Based on Weighted Multidimensional Feature Fusion

“…By conducing correlation analysis on the remaining parts of the four types of features and introducing (9), the linear correlation degree between any of the two features can be obtained. The results are shown in Table 4.…”

“…Generally, fault diagnosis can be divided into three types [7]- [9], namely, analytical model-based method, qualitative empirical knowledge based method, and data driven based method. The analytical model-based method is based on the mathematical model of the known diagnostic object, and the information of the measured object is processed according to a certain mathematical method.…”

Least Squares Sparse Principal Component Analysis and Parallel Coordinates for Real-Time Process Monitoring

“…On the other hand, Maurya et al 44 applied QTA to the PCs in place of the original measurements with significant savings in the computational effort. Li and Xiao 46 presented a signal geometry matching technique for diagnosing faults, which relies on a pattern matching approach.…”

Improved Random Forest Algorithm Based on Decision Paths for Fault Diagnosis of Chemical Process with Incomplete Data

“…This phenomenon makes the observed signal belonging to fault four similar to the signal under the normal state, resulting in the distinction of the fourth type of fault difficult. Therefore, it is difficult to improve the diagnostic accuracy of the fourth type of fault[69]. It is detected that fault one fails to be improved by DPRF if the missing rate is over 0.3; however, the real reason behind the phenomenon is not clear.…”