Failure Detection in Chemical Processes Using Symbolic Machine Learning: A Case Study on Ethylene Oxidation

Researchers developed a symbolic machine learning approach for predicting failures in chemical processes, specifically testing on ethylene oxidation. The method outperformed traditional AI models while maintaining interpretability through rule-based systems, addressing safety concerns in chemical industries where black-box AI models are unsuitable.

• →Symbolic machine learning outperformed random forest and multilayer perceptron models in chemical process failure prediction.
• →The approach generates interpretable rule-based models suitable for safety-critical chemical industry applications.
• →Traditional large-scale neural networks are often unsuitable for chemical processes due to lack of explainability and brittleness.
• →Real-world failure datasets are scarce in the chemical industry, requiring simulation-based testing approaches.
• →The learned models can be integrated into decision-support systems for chemical plant operators during potential failures.