A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders
Condition monitoring of industrial equipment, combined with machine learning algorithms, may significantly improve maintenance activities on modern cyber-physical production systems. However, data of proper quality and of adequate quantity, modeling both good operational conditions as well as abnorm...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/3/972 |
| _version_ | 1797416829586505728 |
|---|---|
| author | Xanthi Bampoula Georgios Siaterlis Nikolaos Nikolakis Kosmas Alexopoulos |
| author_facet | Xanthi Bampoula Georgios Siaterlis Nikolaos Nikolakis Kosmas Alexopoulos |
| author_sort | Xanthi Bampoula |
| collection | DOAJ |
| description | Condition monitoring of industrial equipment, combined with machine learning algorithms, may significantly improve maintenance activities on modern cyber-physical production systems. However, data of proper quality and of adequate quantity, modeling both good operational conditions as well as abnormal situations throughout the operational lifecycle, are required. Nevertheless, this is difficult to acquire in a non-destructive approach. In this context, this study investigates an approach to enable a transition from preventive maintenance activities, that are scheduled at predetermined time intervals, into predictive ones. In order to enable such approaches in a cyber-physical production system, a deep learning algorithm is used, allowing for maintenance activities to be planned according to the actual operational status of the machine and not in advance. An autoencoder-based methodology is employed for classifying real-world machine and sensor data, into a set of condition-related labels. Real-world data collected from manufacturing operations are used for training and testing a prototype implementation of Long Short-Term Memory autoencoders for estimating the remaining useful life of the monitored equipment. Finally, the proposed approach is evaluated in a use case related to a steel industry production process. |
| first_indexed | 2024-03-09T06:09:51Z |
| format | Article |
| id | doaj.art-e44b5ce1765142698bf4af41165eb91e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T06:09:51Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e44b5ce1765142698bf4af41165eb91e2023-12-03T11:59:55ZengMDPI AGSensors1424-82202021-02-0121397210.3390/s21030972A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM AutoencodersXanthi Bampoula0Georgios Siaterlis1Nikolaos Nikolakis2Kosmas Alexopoulos3Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, GreeceLaboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, GreeceLaboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, GreeceLaboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, GreeceCondition monitoring of industrial equipment, combined with machine learning algorithms, may significantly improve maintenance activities on modern cyber-physical production systems. However, data of proper quality and of adequate quantity, modeling both good operational conditions as well as abnormal situations throughout the operational lifecycle, are required. Nevertheless, this is difficult to acquire in a non-destructive approach. In this context, this study investigates an approach to enable a transition from preventive maintenance activities, that are scheduled at predetermined time intervals, into predictive ones. In order to enable such approaches in a cyber-physical production system, a deep learning algorithm is used, allowing for maintenance activities to be planned according to the actual operational status of the machine and not in advance. An autoencoder-based methodology is employed for classifying real-world machine and sensor data, into a set of condition-related labels. Real-world data collected from manufacturing operations are used for training and testing a prototype implementation of Long Short-Term Memory autoencoders for estimating the remaining useful life of the monitored equipment. Finally, the proposed approach is evaluated in a use case related to a steel industry production process.https://www.mdpi.com/1424-8220/21/3/972cyber-physical production systemsdeep learningartificial intelligenceLong Short-Term Memory (LSTM)predictive maintenanceremaining useful life |
| spellingShingle | Xanthi Bampoula Georgios Siaterlis Nikolaos Nikolakis Kosmas Alexopoulos A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders Sensors cyber-physical production systems deep learning artificial intelligence Long Short-Term Memory (LSTM) predictive maintenance remaining useful life |
| title | A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders |
| title_full | A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders |
| title_fullStr | A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders |
| title_full_unstemmed | A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders |
| title_short | A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders |
| title_sort | deep learning model for predictive maintenance in cyber physical production systems using lstm autoencoders |
| topic | cyber-physical production systems deep learning artificial intelligence Long Short-Term Memory (LSTM) predictive maintenance remaining useful life |
| url | https://www.mdpi.com/1424-8220/21/3/972 |
| work_keys_str_mv | AT xanthibampoula adeeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders AT georgiossiaterlis adeeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders AT nikolaosnikolakis adeeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders AT kosmasalexopoulos adeeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders AT xanthibampoula deeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders AT georgiossiaterlis deeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders AT nikolaosnikolakis deeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders AT kosmasalexopoulos deeplearningmodelforpredictivemaintenanceincyberphysicalproductionsystemsusinglstmautoencoders |