Reactive distillation integrates reaction and distillation to achieve process intensification. And the increasing process complexity urgently requires fault diagnosis system to ensure its safe and efficient operation. However, establishing fault diagnosis model is facing intractable challenges, e.g. scarce labeled data, operating mode changeover due to product proportion variation. To tackle absent labeled data problem, pseudo-labeled database is established by integrating data mining, density-based spatial clustering of applications with noise algorithm and process knowledge, based on which unsupervised deep learning is developed. Besides, to make intelligent fault diagnosis system adaptive for multimode operation changeover, transfer learning with domain adaptation strategy is adopted, which could mitigate different data distributions in various operating states and transfer knowledge learned from source domain to target domain. Taking carbonate ester process with reactive distillation as benchmark, the performance and superiority of unsupervised learning and transfer learning is verified and demonstrated in solving the corresponding puzzle.
Read full abstract