Stable soft sensor modeling based on causality analysis

Data-driven soft sensors, aiming to estimate and predict hard-to-measure quality variables using easy-to-measure process variables, have now become the key foundation for monitoring the stable and safe operationof industrial processes. However, traditional machine-learning methods usually make an assumption thattraining data and test data share the same probability distribution or the probability distribution of test datais known, which is impractical in the fact that test data come from multi-unknown operating modes. Basedon causality analysis and stable learning, soft sensors for stable prediction, namely stable soft sensors, areproposed in this paper. To address this problem, three stable soft sensor frameworks based on causal variables, unsupervised causal features, and supervised causal features are designed. By introducing causality in softsensor modeling, the interpretability is enhanced and the prediction results in different operating modes getstable. The effectiveness of the proposed method is shown through case studies in the benchmark Tennessee Eastman process

Automated summary

Data-driven soft sensors are crucial for monitoring the stable and safe operation of industrial processes. However, traditional machine-learning methods face challenges when handling test data from unknown operating modes. This paper proposes stable soft sensor frameworks based on causality analysis and stable learning to address this issue.