Cost-Sensitive Decision Support for Industrial Batch Processes
In this work, cost-sensitive decision support was developed. Using Batch Data Analytics (BDA) methods of the batch data structure and feature accommodation, the batch process property and sensor data can be accommodated. The batch data structure organises the batch processes’ data, and the feature a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/23/9464 |
| _version_ | 1797399582981750784 |
|---|---|
| author | Simon Mählkvist Jesper Ejenstam Konstantinos Kyprianidis |
| author_facet | Simon Mählkvist Jesper Ejenstam Konstantinos Kyprianidis |
| author_sort | Simon Mählkvist |
| collection | DOAJ |
| description | In this work, cost-sensitive decision support was developed. Using Batch Data Analytics (BDA) methods of the batch data structure and feature accommodation, the batch process property and sensor data can be accommodated. The batch data structure organises the batch processes’ data, and the feature accommodation approach derives statistics from the time series, consequently aligning the time series with the other features. Three machine learning classifiers were implemented for comparison: Logistic Regression (LR), Random Forest Classifier (RFC), and Support Vector Machine (SVM). It is possible to filter out the low-probability predictions by leveraging the classifiers’ probability estimations. Consequently, the decision support has a trade-off between accuracy and coverage. Cost-sensitive learning was used to implement a cost matrix, which further aggregates the accuracy–coverage trade into cost metrics. Also, two scenarios were implemented for accommodating out-of-coverage batches. The batch is discarded in one scenario, and the other is processed. The Random Forest classifier was shown to outperform the other classifiers and, compared to the baseline scenario, had a relative cost of 26%. This synergy of methods provides cost-aware decision support for analysing the intricate workings of a multiprocess batch data system. |
| first_indexed | 2024-03-09T01:43:11Z |
| format | Article |
| id | doaj.art-946547be7fab4308881f6ae3064aaea6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T01:43:11Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-946547be7fab4308881f6ae3064aaea62023-12-08T15:26:06ZengMDPI AGSensors1424-82202023-11-012323946410.3390/s23239464Cost-Sensitive Decision Support for Industrial Batch ProcessesSimon Mählkvist0Jesper Ejenstam1Konstantinos Kyprianidis2Kanthal AB, 73427 Hallstahammar, SwedenKanthal AB, 73427 Hallstahammar, SwedenFuture Energy Center, Mälardalen University, 72123 Västerås, SwedenIn this work, cost-sensitive decision support was developed. Using Batch Data Analytics (BDA) methods of the batch data structure and feature accommodation, the batch process property and sensor data can be accommodated. The batch data structure organises the batch processes’ data, and the feature accommodation approach derives statistics from the time series, consequently aligning the time series with the other features. Three machine learning classifiers were implemented for comparison: Logistic Regression (LR), Random Forest Classifier (RFC), and Support Vector Machine (SVM). It is possible to filter out the low-probability predictions by leveraging the classifiers’ probability estimations. Consequently, the decision support has a trade-off between accuracy and coverage. Cost-sensitive learning was used to implement a cost matrix, which further aggregates the accuracy–coverage trade into cost metrics. Also, two scenarios were implemented for accommodating out-of-coverage batches. The batch is discarded in one scenario, and the other is processed. The Random Forest classifier was shown to outperform the other classifiers and, compared to the baseline scenario, had a relative cost of 26%. This synergy of methods provides cost-aware decision support for analysing the intricate workings of a multiprocess batch data system.https://www.mdpi.com/1424-8220/23/23/9464Batch Data Analytics (BDA)feature-orientedcost-sensitive learningdecision supportmachine learning |
| spellingShingle | Simon Mählkvist Jesper Ejenstam Konstantinos Kyprianidis Cost-Sensitive Decision Support for Industrial Batch Processes Sensors Batch Data Analytics (BDA) feature-oriented cost-sensitive learning decision support machine learning |
| title | Cost-Sensitive Decision Support for Industrial Batch Processes |
| title_full | Cost-Sensitive Decision Support for Industrial Batch Processes |
| title_fullStr | Cost-Sensitive Decision Support for Industrial Batch Processes |
| title_full_unstemmed | Cost-Sensitive Decision Support for Industrial Batch Processes |
| title_short | Cost-Sensitive Decision Support for Industrial Batch Processes |
| title_sort | cost sensitive decision support for industrial batch processes |
| topic | Batch Data Analytics (BDA) feature-oriented cost-sensitive learning decision support machine learning |
| url | https://www.mdpi.com/1424-8220/23/23/9464 |
| work_keys_str_mv | AT simonmahlkvist costsensitivedecisionsupportforindustrialbatchprocesses AT jesperejenstam costsensitivedecisionsupportforindustrialbatchprocesses AT konstantinoskyprianidis costsensitivedecisionsupportforindustrialbatchprocesses |