Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes
In the manufacturing process, equipment failure is directly related to productivity, so predictive maintenance plays a very important role. Industrial parks are distributed, and data heterogeneity exists among heterogeneous equipment, which makes predictive maintenance of equipment challenging. In t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/17/7331 |
| _version_ | 1797581927251705856 |
|---|---|
| author | Jisu Ahn Younjeong Lee Namji Kim Chanho Park Jongpil Jeong |
| author_facet | Jisu Ahn Younjeong Lee Namji Kim Chanho Park Jongpil Jeong |
| author_sort | Jisu Ahn |
| collection | DOAJ |
| description | In the manufacturing process, equipment failure is directly related to productivity, so predictive maintenance plays a very important role. Industrial parks are distributed, and data heterogeneity exists among heterogeneous equipment, which makes predictive maintenance of equipment challenging. In this paper, we propose two main techniques to enable effective predictive maintenance in this environment. We propose a 1DCNN-Bilstm model for time series anomaly detection and predictive maintenance of manufacturing processes. The model combines a 1D convolutional neural network (1DCNN) and a bidirectional LSTM (Bilstm), which is effective in extracting features from time series data and detecting anomalies. In this paper, we combine a federated learning framework with these models to consider the distributional shifts of time series data and perform anomaly detection and predictive maintenance based on them. In this paper, we utilize the pump dataset to evaluate the performance of the combination of several federated learning frameworks and time series anomaly detection models. Experimental results show that the proposed framework achieves a test accuracy of 97.2%, which shows its potential to be utilized for real-world predictive maintenance in the future. |
| first_indexed | 2024-03-10T23:13:37Z |
| format | Article |
| id | doaj.art-a2addc84aa864af480c766039a8ec2e4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:13:37Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a2addc84aa864af480c766039a8ec2e42023-11-19T08:48:26ZengMDPI AGSensors1424-82202023-08-012317733110.3390/s23177331Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing ProcessesJisu Ahn0Younjeong Lee1Namji Kim2Chanho Park3Jongpil Jeong4Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of KoreaDepartment of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of KoreaDepartment of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of KoreaDepartment of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of KoreaDepartment of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of KoreaIn the manufacturing process, equipment failure is directly related to productivity, so predictive maintenance plays a very important role. Industrial parks are distributed, and data heterogeneity exists among heterogeneous equipment, which makes predictive maintenance of equipment challenging. In this paper, we propose two main techniques to enable effective predictive maintenance in this environment. We propose a 1DCNN-Bilstm model for time series anomaly detection and predictive maintenance of manufacturing processes. The model combines a 1D convolutional neural network (1DCNN) and a bidirectional LSTM (Bilstm), which is effective in extracting features from time series data and detecting anomalies. In this paper, we combine a federated learning framework with these models to consider the distributional shifts of time series data and perform anomaly detection and predictive maintenance based on them. In this paper, we utilize the pump dataset to evaluate the performance of the combination of several federated learning frameworks and time series anomaly detection models. Experimental results show that the proposed framework achieves a test accuracy of 97.2%, which shows its potential to be utilized for real-world predictive maintenance in the future.https://www.mdpi.com/1424-8220/23/17/7331federated learninganomaly detectiontime seriesLSTMdata distribution |
| spellingShingle | Jisu Ahn Younjeong Lee Namji Kim Chanho Park Jongpil Jeong Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes Sensors federated learning anomaly detection time series LSTM data distribution |
| title | Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes |
| title_full | Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes |
| title_fullStr | Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes |
| title_full_unstemmed | Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes |
| title_short | Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes |
| title_sort | federated learning for predictive maintenance and anomaly detection using time series data distribution shifts in manufacturing processes |
| topic | federated learning anomaly detection time series LSTM data distribution |
| url | https://www.mdpi.com/1424-8220/23/17/7331 |
| work_keys_str_mv | AT jisuahn federatedlearningforpredictivemaintenanceandanomalydetectionusingtimeseriesdatadistributionshiftsinmanufacturingprocesses AT younjeonglee federatedlearningforpredictivemaintenanceandanomalydetectionusingtimeseriesdatadistributionshiftsinmanufacturingprocesses AT namjikim federatedlearningforpredictivemaintenanceandanomalydetectionusingtimeseriesdatadistributionshiftsinmanufacturingprocesses AT chanhopark federatedlearningforpredictivemaintenanceandanomalydetectionusingtimeseriesdatadistributionshiftsinmanufacturingprocesses AT jongpiljeong federatedlearningforpredictivemaintenanceandanomalydetectionusingtimeseriesdatadistributionshiftsinmanufacturingprocesses |