Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming
Sensors are crucial in detecting equipment problems in various plant systems. In particular, detecting sensor abnormality is challenging in the case of utilizing the data which are acquired and stored offline (data logs). These data are normally acquired using Internet of Things (IoT) system and sto...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | e-Prime: Advances in Electrical Engineering, Electronics and Energy |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772671123001043 |
| _version_ | 1797674914130427904 |
|---|---|
| author | Pauline Wong W.K. Wong Filbert H. Juwono Basil Andy Lease Lenin Gopal I.M. Chew |
| author_facet | Pauline Wong W.K. Wong Filbert H. Juwono Basil Andy Lease Lenin Gopal I.M. Chew |
| author_sort | Pauline Wong |
| collection | DOAJ |
| description | Sensors are crucial in detecting equipment problems in various plant systems. In particular, detecting sensor abnormality is challenging in the case of utilizing the data which are acquired and stored offline (data logs). These data are normally acquired using Internet of Things (IoT) system and stored in a dedicated server. This situation presents both opportunities and challenges for exploration in sensor abnormality detection task. In this paper, we propose a multistage compressor sensor fault detection method using data logs. In the proposed method, the compressor sensor output is modeled as a function of other sensors using static approach. Subsequently, the model output is used for detecting abnormality by observing the residuals. It has been shown that the histogram of residuals offers rich information to predict abnormality of the targeted sensor. In particular, we explore the concept using Genetic Programming (GP) to generate regression model which offers more “white box” solution to the operators. There are various advantages in this approach. Firstly, the conventional “black box” approach lacks model transparency and, thus, is highly undesirable in critical systems. Secondly, equations are more easily applied in Programmable Logic Controller (PLC) if autonomous flagging is required. We also compare the proposed model with Multiple Linear Regression (MLR) and Neural Network Regression (ANN). Results show that the best generated models are comparable with the latter but with more crisp “white box” mathematical equations utilizing lesser feature inputs (four features only). This model yields R2 of 0.991 and RMSE of 2.1×10−2. |
| first_indexed | 2024-03-11T22:06:02Z |
| format | Article |
| id | doaj.art-965fbb0fd845439aa382e2ce8ec62b08 |
| institution | Directory Open Access Journal |
| issn | 2772-6711 |
| language | English |
| last_indexed | 2024-03-11T22:06:02Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | e-Prime: Advances in Electrical Engineering, Electronics and Energy |
| spelling | doaj.art-965fbb0fd845439aa382e2ce8ec62b082023-09-25T04:12:44ZengElseviere-Prime: Advances in Electrical Engineering, Electronics and Energy2772-67112023-09-015100209Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programmingPauline Wong0W.K. Wong1Filbert H. Juwono2Basil Andy Lease3Lenin Gopal4I.M. Chew5Department of Electrical and Computer Engineering, Curtin University Malaysia, CDT 250, Miri 98009, Sarawak, MalaysiaDepartment of Electrical and Computer Engineering, Curtin University Malaysia, CDT 250, Miri 98009, Sarawak, MalaysiaConnected Intelligence Research Group, University of Southampton Malaysia, Blok C Eko Galleria, 3, Jalan Eko Botani 3/2, Iskandar Puteri 79100, Johor, Malaysia; Corresponding author.Department of Electrical and Computer Engineering, Curtin University Malaysia, CDT 250, Miri 98009, Sarawak, MalaysiaConnected Intelligence Research Group, University of Southampton Malaysia, Blok C Eko Galleria, 3, Jalan Eko Botani 3/2, Iskandar Puteri 79100, Johor, MalaysiaDepartment of Electrical and Computer Engineering, Curtin University Malaysia, CDT 250, Miri 98009, Sarawak, MalaysiaSensors are crucial in detecting equipment problems in various plant systems. In particular, detecting sensor abnormality is challenging in the case of utilizing the data which are acquired and stored offline (data logs). These data are normally acquired using Internet of Things (IoT) system and stored in a dedicated server. This situation presents both opportunities and challenges for exploration in sensor abnormality detection task. In this paper, we propose a multistage compressor sensor fault detection method using data logs. In the proposed method, the compressor sensor output is modeled as a function of other sensors using static approach. Subsequently, the model output is used for detecting abnormality by observing the residuals. It has been shown that the histogram of residuals offers rich information to predict abnormality of the targeted sensor. In particular, we explore the concept using Genetic Programming (GP) to generate regression model which offers more “white box” solution to the operators. There are various advantages in this approach. Firstly, the conventional “black box” approach lacks model transparency and, thus, is highly undesirable in critical systems. Secondly, equations are more easily applied in Programmable Logic Controller (PLC) if autonomous flagging is required. We also compare the proposed model with Multiple Linear Regression (MLR) and Neural Network Regression (ANN). Results show that the best generated models are comparable with the latter but with more crisp “white box” mathematical equations utilizing lesser feature inputs (four features only). This model yields R2 of 0.991 and RMSE of 2.1×10−2.http://www.sciencedirect.com/science/article/pii/S2772671123001043Sensor abnormalityFault detectionGenetic programming |
| spellingShingle | Pauline Wong W.K. Wong Filbert H. Juwono Basil Andy Lease Lenin Gopal I.M. Chew Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming e-Prime: Advances in Electrical Engineering, Electronics and Energy Sensor abnormality Fault detection Genetic programming |
| title | Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming |
| title_full | Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming |
| title_fullStr | Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming |
| title_full_unstemmed | Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming |
| title_short | Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming |
| title_sort | sensor abnormality detection in multistage compressor units a white box approach using tree based genetic programming |
| topic | Sensor abnormality Fault detection Genetic programming |
| url | http://www.sciencedirect.com/science/article/pii/S2772671123001043 |
| work_keys_str_mv | AT paulinewong sensorabnormalitydetectioninmultistagecompressorunitsawhiteboxapproachusingtreebasedgeneticprogramming AT wkwong sensorabnormalitydetectioninmultistagecompressorunitsawhiteboxapproachusingtreebasedgeneticprogramming AT filberthjuwono sensorabnormalitydetectioninmultistagecompressorunitsawhiteboxapproachusingtreebasedgeneticprogramming AT basilandylease sensorabnormalitydetectioninmultistagecompressorunitsawhiteboxapproachusingtreebasedgeneticprogramming AT leningopal sensorabnormalitydetectioninmultistagecompressorunitsawhiteboxapproachusingtreebasedgeneticprogramming AT imchew sensorabnormalitydetectioninmultistagecompressorunitsawhiteboxapproachusingtreebasedgeneticprogramming |