Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly Detection
Within the context of Industry 4.0, quality assessment procedures using data-driven techniques are becoming more critical due to the generation of massive amounts of production data. In this paper, we address the detection of abnormal screw tightening processes, which is a key industrial task. Since...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/11/4/54 |
| _version_ | 1797436266764042240 |
|---|---|
| author | Diogo Ribeiro Luís Miguel Matos Guilherme Moreira André Pilastri Paulo Cortez |
| author_facet | Diogo Ribeiro Luís Miguel Matos Guilherme Moreira André Pilastri Paulo Cortez |
| author_sort | Diogo Ribeiro |
| collection | DOAJ |
| description | Within the context of Industry 4.0, quality assessment procedures using data-driven techniques are becoming more critical due to the generation of massive amounts of production data. In this paper, we address the detection of abnormal screw tightening processes, which is a key industrial task. Since labeling is costly, requiring a manual effort, we focus on unsupervised detection approaches. In particular, we assume a computationally light low-dimensional problem formulation based on angle–torque pairs. Our work is focused on two unsupervised machine learning (ML) algorithms: isolation forest (IForest) and a deep learning autoencoder (AE). Several computational experiments were held by assuming distinct datasets and a realistic rolling window evaluation procedure. First, we compared the two ML algorithms with two other methods, a local outlier factor method and a supervised Random Forest, on older data related with two production days collected in November 2020. Since competitive results were obtained, during a second stage, we further compared the AE and IForest methods by adopting a more recent and larger dataset (from February to March 2021, totaling 26.9 million observations and related to three distinct assembled products). Both anomaly detection methods obtained an excellent quality class discrimination (higher than 90%) under a realistic rolling window with several training and testing updates. Turning to the computational effort, the AE is much lighter than the IForest for training (around 2.7 times faster) and inference (requiring 3.0 times less computation). This AE property is valuable within this industrial domain since it tends to generate big data. Finally, using the anomaly detection estimates, we developed an interactive visualization tool that provides explainable artificial intelligence (XAI) knowledge for the human operators, helping them to better identify the angle–torque regions associated with screw tightening failures. |
| first_indexed | 2024-03-09T10:59:09Z |
| format | Article |
| id | doaj.art-5e4653427bd0479abc89cc30fefa28ef |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-09T10:59:09Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-5e4653427bd0479abc89cc30fefa28ef2023-12-01T01:22:26ZengMDPI AGComputers2073-431X2022-04-011145410.3390/computers11040054Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly DetectionDiogo Ribeiro0Luís Miguel Matos1Guilherme Moreira2André Pilastri3Paulo Cortez4ALGORITMI R&D Centre, Department of Information Systems, University of Minho, 4804-533 Guimarães, PortugalALGORITMI R&D Centre, Department of Information Systems, University of Minho, 4804-533 Guimarães, PortugalBosch Car Multimedia, 4705-820 Braga, PortugalEPMQ-IT CCG ZGDV Institute, 4804-533 Guimarães, PortugalALGORITMI R&D Centre, Department of Information Systems, University of Minho, 4804-533 Guimarães, PortugalWithin the context of Industry 4.0, quality assessment procedures using data-driven techniques are becoming more critical due to the generation of massive amounts of production data. In this paper, we address the detection of abnormal screw tightening processes, which is a key industrial task. Since labeling is costly, requiring a manual effort, we focus on unsupervised detection approaches. In particular, we assume a computationally light low-dimensional problem formulation based on angle–torque pairs. Our work is focused on two unsupervised machine learning (ML) algorithms: isolation forest (IForest) and a deep learning autoencoder (AE). Several computational experiments were held by assuming distinct datasets and a realistic rolling window evaluation procedure. First, we compared the two ML algorithms with two other methods, a local outlier factor method and a supervised Random Forest, on older data related with two production days collected in November 2020. Since competitive results were obtained, during a second stage, we further compared the AE and IForest methods by adopting a more recent and larger dataset (from February to March 2021, totaling 26.9 million observations and related to three distinct assembled products). Both anomaly detection methods obtained an excellent quality class discrimination (higher than 90%) under a realistic rolling window with several training and testing updates. Turning to the computational effort, the AE is much lighter than the IForest for training (around 2.7 times faster) and inference (requiring 3.0 times less computation). This AE property is valuable within this industrial domain since it tends to generate big data. Finally, using the anomaly detection estimates, we developed an interactive visualization tool that provides explainable artificial intelligence (XAI) knowledge for the human operators, helping them to better identify the angle–torque regions associated with screw tightening failures.https://www.mdpi.com/2073-431X/11/4/54autoencoderdeep learningIndustry 4.0isolation forestone-class classificationunsupervised learning |
| spellingShingle | Diogo Ribeiro Luís Miguel Matos Guilherme Moreira André Pilastri Paulo Cortez Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly Detection Computers autoencoder deep learning Industry 4.0 isolation forest one-class classification unsupervised learning |
| title | Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly Detection |
| title_full | Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly Detection |
| title_fullStr | Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly Detection |
| title_full_unstemmed | Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly Detection |
| title_short | Isolation Forests and Deep Autoencoders for Industrial Screw Tightening Anomaly Detection |
| title_sort | isolation forests and deep autoencoders for industrial screw tightening anomaly detection |
| topic | autoencoder deep learning Industry 4.0 isolation forest one-class classification unsupervised learning |
| url | https://www.mdpi.com/2073-431X/11/4/54 |
| work_keys_str_mv | AT diogoribeiro isolationforestsanddeepautoencodersforindustrialscrewtighteninganomalydetection AT luismiguelmatos isolationforestsanddeepautoencodersforindustrialscrewtighteninganomalydetection AT guilhermemoreira isolationforestsanddeepautoencodersforindustrialscrewtighteninganomalydetection AT andrepilastri isolationforestsanddeepautoencodersforindustrialscrewtighteninganomalydetection AT paulocortez isolationforestsanddeepautoencodersforindustrialscrewtighteninganomalydetection |