Deep neural network and random forest classifier for source tracking of chemical leaks using fence monitoring data. (November 2018)

• Record Type: Journal Article
• Authors: Cho, Jaehoon; Kim, Hyunseung; Gebreselassie, Addis Lulu; Shin, Dongil
• Is Part Of: Journal of loss prevention in the process industries. Volume 56(2018)
• Page Start: 548
• Page End: 558
• Publication Date: 2018-11
• Subjects: Chemical accident -- Chemical release -- Leak source tracking -- Deep-learning network -- Random Forest -- Artificial intelligence; Chemical industries -- Safety measures -- Periodicals; 660.2804
• DOI: 10.1016/j.jlp.2018.01.011
• Languages: English
• ISSNs: 0950-4230

Abstract

Abstract: Chemical plant leak accidents are classified as one of the major industrial accidents that can spread secondary and tertiary major disasters. It is very important to keep track and diagnose the source location(s) and notify the plant manager and emergency responders promptly to alleviate secondary and tertiary damages, improving the effectiveness of emergency responses. In this study, we propose an emergency response system that can cope with leak accidents of a chemical plant by monitoring sensor data and track down the suspected leak source using machine learning: Deep-learning and Random Forest classifiers. It is also difficult to get enough chemical leak accident scenario data or perform actual leak experiments on real plants due to high risk and cost factors. Consequently, Computational Fluid Dynamics (CFD) simulations are used to derive fence monitoring data for chemical leak accident scenarios. These data are to train the machine learning models to predict leak source locations. Six time-series Deep Neural Network (DNN) structures and three Random Forest (RF) structures are trained using CFD dispersion simulation results for 640 leak accident scenarios of a real chemical plant, divided as training and test datasets. As a result, on DNN model using 25 hidden layers and on RF model using 100 decision trees, 75.43% and 86.33% prediction accuracy are achieved, respectively, classifying the most probable leak source out of 40 potential leak source locations. Analyzing the predicted leak source locations that are wrongly classified, those predicted leak sources are also quite adjacent to the actual leak location and hardly called as misclassifications. Considering the superb performance of DNN and RF classifiers for chemical leak tracking, the proposed method would be very useful for chemical emergency management and is highly recommended for real-time diagnosis of the chemical leak sources. Highlights: Source Tracking approaches based on Deep-learning and Random Forest have been developed to cope with chemical leak accidents. The proposed approaches predict the location of leak source with fairly high accuracy for the multiple sources. If providing the top-5 probable leak points, the probability of reporting false prediction is less than 5%. It is diagnosed that even wrongly predicted location is also adjacent to the actual location of leak source.