Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis
The products of a batch process have high economic value. Meanwhile, a batch process involves complex chemicals and equipment. The variability of its operation leads to a high failure rate. Therefore, early fault diagnosis of batch processes is of great significance. Usually, the available informati...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/23/8075 |
| _version_ | 1797507132281585664 |
|---|---|
| author | Yuman Yao Yiyang Dai Wenjia Luo |
| author_facet | Yuman Yao Yiyang Dai Wenjia Luo |
| author_sort | Yuman Yao |
| collection | DOAJ |
| description | The products of a batch process have high economic value. Meanwhile, a batch process involves complex chemicals and equipment. The variability of its operation leads to a high failure rate. Therefore, early fault diagnosis of batch processes is of great significance. Usually, the available information of the sensor data in batch processing is obscured by its noise. The multistage variation of data results in poor diagnostic performance. This paper constructed a standardized method to enlarge fault information as well as a batch fault diagnosis method based on trend analysis. First, an adaptive standardization based on the time window was created; second, utilizing quadratic fitting, we extracted a data trend under the window; third, a new trend recognition method based on the Euclidean distance calculation principle was composed. The method was verified in penicillin fermentation. We constructed two test datasets: one based on an existing batch, and one based on an unknown batch. The average diagnostic rate of each group was 100% and 87.5%; the mean diagnosis time was the same; 0.2083 h. Compared with traditional fault diagnosis methods, this algorithm has better fault diagnosis ability and feature extraction ability. |
| first_indexed | 2024-03-10T04:44:16Z |
| format | Article |
| id | doaj.art-423f72c8a4234e3cbcd4f8564152f385 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T04:44:16Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-423f72c8a4234e3cbcd4f8564152f3852023-11-23T03:03:39ZengMDPI AGSensors1424-82202021-12-012123807510.3390/s21238075Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend AnalysisYuman Yao0Yiyang Dai1Wenjia Luo2College of Chemistry and Chemical Engineering, Southwest Petroleum University, Chengdu 610500, ChinaSchool of Chemical Engineering, Sichuan University, Chengdu 610065, ChinaCollege of Chemistry and Chemical Engineering, Southwest Petroleum University, Chengdu 610500, ChinaThe products of a batch process have high economic value. Meanwhile, a batch process involves complex chemicals and equipment. The variability of its operation leads to a high failure rate. Therefore, early fault diagnosis of batch processes is of great significance. Usually, the available information of the sensor data in batch processing is obscured by its noise. The multistage variation of data results in poor diagnostic performance. This paper constructed a standardized method to enlarge fault information as well as a batch fault diagnosis method based on trend analysis. First, an adaptive standardization based on the time window was created; second, utilizing quadratic fitting, we extracted a data trend under the window; third, a new trend recognition method based on the Euclidean distance calculation principle was composed. The method was verified in penicillin fermentation. We constructed two test datasets: one based on an existing batch, and one based on an unknown batch. The average diagnostic rate of each group was 100% and 87.5%; the mean diagnosis time was the same; 0.2083 h. Compared with traditional fault diagnosis methods, this algorithm has better fault diagnosis ability and feature extraction ability.https://www.mdpi.com/1424-8220/21/23/8075QTAbatch processesincipient fault detection |
| spellingShingle | Yuman Yao Yiyang Dai Wenjia Luo Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis Sensors QTA batch processes incipient fault detection |
| title | Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis |
| title_full | Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis |
| title_fullStr | Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis |
| title_full_unstemmed | Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis |
| title_short | Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis |
| title_sort | early fault diagnosis method for batch process based on local time window standardization and trend analysis |
| topic | QTA batch processes incipient fault detection |
| url | https://www.mdpi.com/1424-8220/21/23/8075 |
| work_keys_str_mv | AT yumanyao earlyfaultdiagnosismethodforbatchprocessbasedonlocaltimewindowstandardizationandtrendanalysis AT yiyangdai earlyfaultdiagnosismethodforbatchprocessbasedonlocaltimewindowstandardizationandtrendanalysis AT wenjialuo earlyfaultdiagnosismethodforbatchprocessbasedonlocaltimewindowstandardizationandtrendanalysis |