Event correlation analysis for alarm system rationalization

With the progressing complexity of process industries, alarm flooding has become a critical problem in alarm management. Granger causality (GC) analysis provides a pivotal role in investigating anomalous propagations and identifying alarm sources to reduce nuisance alarms. This paper proposes a novel attention-based long short-term memory (ALSTM) method for improved design of GC models to diagnose the alarm root-cause and identify the alarm propagation pathways. A novel training strategy is proposed for ALSTM-GC to enhance noise robustness and prevent overfitting. Also, a sensitivity-based method is presented to alleviate the spurious causalities caused by unobservable factors and slight indirect relationships. Compared with the traditional GC models, the main contribution of the proposed approach is 3-fold: (i) ALSTM-GC can effectively identify causality of process variables from varying and long-term delays without any prior data assumptions; (ii) with the incorporation of attention mechanism, ALSTM-GC can avoid the nested loops in causality analysis to reduce the computational complexity; (iii) ALSTM-GC can provide a more accurate and simplified network structure for late alarm traceability based on the sensitivity identification. The innovativeness of ALSTM-GC is discussed on a stochastic process based on comparative studies with different GC methods. In addition, the practicability of the proposed method is validated on a complicated case of the Tennessee Eastman process (TEP).

Section: Introductionmentioning

confidence: 99%

Attention-Based Long Short-Term Memory Method for Alarm Root-Cause Diagnosis in Chemical Processes

Chen

Sun

et al. 2020

“…Safety is one of the most important factors in the process industry. A good alarm system plays a helpful role in keeping the safety of industrial processes. − In the alarm systems of industrial processes, alarm floods are often involved. − As a result, the performance of alarm systems is much limited. Facing many alarm floods, alarm systems tend to be unpractical.…”

Section: Introductionmentioning

confidence: 99%

Novel Multiblock Transfer Entropy Based Bayesian Network and Its Application to Root Cause Analysis

Zhu

Luo

2019

Bayesian network has been widely used as a powerful reasoning and knowledge expression tool to analyze toot causes. With the increasing scale and integration of modern process industries, building an accurate Bayesian network is more and more difficult but important. To solve this problem, a novel multiblock transfer entropy based Bayesian network model is proposed to make root cause analyses. Developing the proposed methodology consists of three simple steps: modular decomposition of processes based on process knowledge, Bayesian network structure learning using the proposed multiblock transfer entropy, and root cause analysis. The accuracy of structure learning is influenced by the transfer entropy between the alarm variable and itself at the previous sampling time. To solve this problem, an improved transfer entropy method is presented, where the influence of the variable itself between sampling time is eliminated for correct Bayesian network structure scoring. Moreover, a regular penalty item is adopted to avoid overfitting during training the Bayesian network structure. To validate the performance of the proposed methodology, simulations on the Tennessee Eastman Process are carried out. Simulation results confirm the effectiveness of the proposed methodology.

“…Additionally, Grainger causality is recognized as an effective method of alarm correlation analysis. Noda et al 13 proposed an effective alarm correlation detection method to reduce the number of alarms and operations. Xu 14 introduced a spectral transfer entropy and formulated its relations with frequency to the domain Grainger causality.…”

Section: Introductionmentioning

confidence: 99%

Novel Correlation Analysis of Alarms Based on Block Matching Similarities

Yang

Chu

et al. 2019

Correlation analysis has been widely applied for process detection and alarm analysis. However, traditional correlation analysis methods have been found inefficient due to the influence of process time delays on analysis results. In this paper, we propose an alarm correlation analysis method based on block matching similarities. By converting alarm data sequences to time node sequences, the block matching similarity (BMS) method is able to reduce the calculation burden of the correlation analysis. Considering time delays between the alarm variables, the improved maximal correlation coefficient method is presented to reduce the effect of time delays and to improve the accuracy of the correlation analysis. A numerical case and the Tennessee Eastman process are employed to demonstrate the effectiveness and efficiency of the proposed method.