Deep learning technique for process fault detection and diagnosis in the presence of incomplete data
| Autor: | Dexian Huang, Fan Yang, Wenkai Hu, Cen Guo |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Environmental Engineering
Computer science business.industry General Chemical Engineering Deep learning 02 engineering and technology General Chemistry 021001 nanoscience & nanotechnology computer.software_genre Missing data Biochemistry Data treatment Autoencoder Fault detection and isolation Fault recognition 020401 chemical engineering Imputation (statistics) Data mining Artificial intelligence 0204 chemical engineering 0210 nano-technology business computer Process operation |
| Zdroj: | Chinese Journal of Chemical Engineering. 28:2358-2367 |
| ISSN: | 1004-9541 |
| Popis: | In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis (FDD) methods have been proposed and implemented, the performance of which, however, could be drastically influenced by the common presence of incomplete or missing data in real industrial scenarios. This paper presents a new FDD approach based on an incomplete data imputation technique for process fault recognition. It employs the modified stacked autoencoder, a deep learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification. A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect