Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks
Solenoid operated valves (SOV) play important roles in industrial process to control the flow of fluids. Solenoid valves can be found in so many industries as well as the nuclear plant. The ability to be able to detect the presence of faults and predicting the remaining useful life (RUL) of the SOV...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-09-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573319308435 |
| _version_ | 1811286127423782912 |
|---|---|
| author | M.N. Utah J.C. Jung |
| author_facet | M.N. Utah J.C. Jung |
| author_sort | M.N. Utah |
| collection | DOAJ |
| description | Solenoid operated valves (SOV) play important roles in industrial process to control the flow of fluids. Solenoid valves can be found in so many industries as well as the nuclear plant. The ability to be able to detect the presence of faults and predicting the remaining useful life (RUL) of the SOV is important in maintenance planning and also prevent unexpected interruptions in the flow of process fluids. This paper proposes a fault diagnosis method for the alternating current (AC) powered SOV. Previous research work have been focused on direct current (DC) powered SOV where the current waveform or vibrations are monitored. There are many features hidden in the AC waveform that require further signal analysis. The analysis of the AC powered SOV waveform was done in the time and frequency domain. A total of sixteen features were obtained and these were used to classify the different operating modes of the SOV by applying a machine learning technique for classification. Also, a deep neural network (DNN) was developed for the prediction of RUL based on the failure modes of the SOV. The results of this paper can be used to improve on the condition based monitoring of the SOV. |
| first_indexed | 2024-04-13T02:54:27Z |
| format | Article |
| id | doaj.art-773e3629e50c4a0597076e5f7bf244de |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-04-13T02:54:27Z |
| publishDate | 2020-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-773e3629e50c4a0597076e5f7bf244de2022-12-22T03:05:43ZengElsevierNuclear Engineering and Technology1738-57332020-09-0152919982008Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networksM.N. Utah0J.C. Jung1KEPCO International Nuclear Graduate School (KINGS), 658-91 Haemaji-ro, Seosaeng-myeon, Ulju-gun, Ulsan, 45014, Republic of KoreaCorresponding author.; KEPCO International Nuclear Graduate School (KINGS), 658-91 Haemaji-ro, Seosaeng-myeon, Ulju-gun, Ulsan, 45014, Republic of KoreaSolenoid operated valves (SOV) play important roles in industrial process to control the flow of fluids. Solenoid valves can be found in so many industries as well as the nuclear plant. The ability to be able to detect the presence of faults and predicting the remaining useful life (RUL) of the SOV is important in maintenance planning and also prevent unexpected interruptions in the flow of process fluids. This paper proposes a fault diagnosis method for the alternating current (AC) powered SOV. Previous research work have been focused on direct current (DC) powered SOV where the current waveform or vibrations are monitored. There are many features hidden in the AC waveform that require further signal analysis. The analysis of the AC powered SOV waveform was done in the time and frequency domain. A total of sixteen features were obtained and these were used to classify the different operating modes of the SOV by applying a machine learning technique for classification. Also, a deep neural network (DNN) was developed for the prediction of RUL based on the failure modes of the SOV. The results of this paper can be used to improve on the condition based monitoring of the SOV.http://www.sciencedirect.com/science/article/pii/S1738573319308435Predictive maintenanceCondition based maintenanceRemaining useful lifeSupport vector machinesSolenoid operated valveDeep neural network |
| spellingShingle | M.N. Utah J.C. Jung Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks Nuclear Engineering and Technology Predictive maintenance Condition based maintenance Remaining useful life Support vector machines Solenoid operated valve Deep neural network |
| title | Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks |
| title_full | Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks |
| title_fullStr | Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks |
| title_full_unstemmed | Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks |
| title_short | Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks |
| title_sort | fault state detection and remaining useful life prediction in ac powered solenoid operated valves based on traditional machine learning and deep neural networks |
| topic | Predictive maintenance Condition based maintenance Remaining useful life Support vector machines Solenoid operated valve Deep neural network |
| url | http://www.sciencedirect.com/science/article/pii/S1738573319308435 |
| work_keys_str_mv | AT mnutah faultstatedetectionandremainingusefullifepredictioninacpoweredsolenoidoperatedvalvesbasedontraditionalmachinelearninganddeepneuralnetworks AT jcjung faultstatedetectionandremainingusefullifepredictioninacpoweredsolenoidoperatedvalvesbasedontraditionalmachinelearninganddeepneuralnetworks |