Fault diagnosis of chemical processes considering fault frequency via Bayesian network

Abstract

In the present study, data‐driven fault diagnosis (FD) systems of chemical plants dealing with frequent and rare faults are investigated. Although different faults occur with different frequencies in chemical plants, this issue has scarcely been addressed in developing a process FD system. A novel diagnostic framework based on the Bayesian network (BN) is proposed to incorporate fault frequencies. This probabilistic method can readily involve non‐uniform probability distribution of faults and non‐Gaussian probability distribution of features. The proposed approach includes not only a combination of tools but also information management. In fact, the imbalanced dataset, established by frequent and rare faults, promotes recursive updating of prior probabilities of faults. The performance of the BN was evaluated and compared with the conventional C4.5 method in the Tennessee‐Eastman process benchmark. It was shown in this work that the diagnostic performance of the proposed approach versus the C4.5 method is more efficient. The importance of taking into account non‐uniform probability distribution of faults for designing a FD system was highlighted. Furthermore, the effect of independent component analysis (ICA) of the imbalanced dataset on the FD was examined. The proposed framework versus the C4.5 method promises 37 % FD performance improvement for the dataset with a 10:1 imbalance index.

Batch process monitoring using multiway Laplacian autoencoders

“…For the sake of high process safety and product quality, it is extremely necessary to establish a monitoring system to detect abnormal conditions in batch process quickly and effectively 1–3 . Data‐driven multivariate statistical process monitoring (MSPM) techniques have been widely applied in batch process 4–10 …”

An improved intelligent early warning method based on MWSPCA and its application in complex chemical processes

“…Once a failure occurs, it can produce a chain reaction with serious catastrophic consequences, which affects product quality, increases equipment maintenance costs and production costs, and threatens personal safety. Therefore, how to monitor complex chemical processes online and in real‐time, find faults in time, and prevent accidents have become hot research topics for experts and scholars in China and abroad …”

Multimode processes monitoring based on hierarchical mode division and subspace decomposition

“…Process monitoring has a wide range of applications for modern industrial production processes as it can ensure stable production safety, maintain quality stabilization, and optimize production profit . The operating conditions often vary with raw materials, manufacturing parameters, production specifications, etc., which causes various operation modes .…”

“…P rocess monitoring has a wide range of applications for modern industrial production processes as it can ensure stable production safety, maintain quality stabilization, and optimize production profit. [1][2][3][4][5][6][7] The operating conditions often vary with raw materials, manufacturing parameters, production specifications, etc., which causes various operation modes. [8][9][10] Different modes have their similar, respective specific characteristics and duration times in which one mode is the long duration process with similar statistical characteristics.…”