A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics
Oil sand pumps are widely used in the mining industry for the delivery of mixtures of abrasive solids and liquids. Because they operate under highly adverse conditions, these pumps usually experience significant wear. Consequently, equipment owners are quite often forced to invest substantially in s...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2013-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/13/9/12663 |
| _version_ | 1811277883518222336 |
|---|---|
| author | Peter W. Tse Jinfei Hu |
| author_facet | Peter W. Tse Jinfei Hu |
| author_sort | Peter W. Tse |
| collection | DOAJ |
| description | Oil sand pumps are widely used in the mining industry for the delivery of mixtures of abrasive solids and liquids. Because they operate under highly adverse conditions, these pumps usually experience significant wear. Consequently, equipment owners are quite often forced to invest substantially in system maintenance to avoid unscheduled downtime. In this study, an approach combining relevance vector machines (RVMs) with a sum of two exponential functions was developed to predict the remaining useful life (RUL) of field pump impellers. To handle field vibration data, a novel feature extracting process was proposed to arrive at a feature varying with the development of damage in the pump impellers. A case study involving two field datasets demonstrated the effectiveness of the developed method. Compared with standalone exponential fitting, the proposed RVM-based model was much better able to predict the remaining useful life of pump impellers. |
| first_indexed | 2024-04-13T00:24:36Z |
| format | Article |
| id | doaj.art-8f9138dcc075486fbd8afeaa8ff4056a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T00:24:36Z |
| publishDate | 2013-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8f9138dcc075486fbd8afeaa8ff4056a2022-12-22T03:10:38ZengMDPI AGSensors1424-82202013-09-01139126631268610.3390/s130912663A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump PrognosticsPeter W. TseJinfei HuOil sand pumps are widely used in the mining industry for the delivery of mixtures of abrasive solids and liquids. Because they operate under highly adverse conditions, these pumps usually experience significant wear. Consequently, equipment owners are quite often forced to invest substantially in system maintenance to avoid unscheduled downtime. In this study, an approach combining relevance vector machines (RVMs) with a sum of two exponential functions was developed to predict the remaining useful life (RUL) of field pump impellers. To handle field vibration data, a novel feature extracting process was proposed to arrive at a feature varying with the development of damage in the pump impellers. A case study involving two field datasets demonstrated the effectiveness of the developed method. Compared with standalone exponential fitting, the proposed RVM-based model was much better able to predict the remaining useful life of pump impellers.http://www.mdpi.com/1424-8220/13/9/12663pump impellerremaining useful life (RUL)prognosisrelevance vector machine (RVM)sum of two exponential functions |
| spellingShingle | Peter W. Tse Jinfei Hu A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics Sensors pump impeller remaining useful life (RUL) prognosis relevance vector machine (RVM) sum of two exponential functions |
| title | A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics |
| title_full | A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics |
| title_fullStr | A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics |
| title_full_unstemmed | A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics |
| title_short | A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics |
| title_sort | relevance vector machine based approach with application to oil sand pump prognostics |
| topic | pump impeller remaining useful life (RUL) prognosis relevance vector machine (RVM) sum of two exponential functions |
| url | http://www.mdpi.com/1424-8220/13/9/12663 |
| work_keys_str_mv | AT peterwtse arelevancevectormachinebasedapproachwithapplicationtooilsandpumpprognostics AT jinfeihu arelevancevectormachinebasedapproachwithapplicationtooilsandpumpprognostics AT peterwtse relevancevectormachinebasedapproachwithapplicationtooilsandpumpprognostics AT jinfeihu relevancevectormachinebasedapproachwithapplicationtooilsandpumpprognostics |