Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural Network
The head and flow rate of a pump characterize the pump performance, which help determine whether maintenance is needed. In the proposed method, instead of a traditional flowmeter and manometer, the operating points are identified using data collected from accelerometers and microphones. The dataset...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | International Journal of Turbomachinery, Propulsion and Power |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-186X/8/4/39 |
| _version_ | 1827574603179884544 |
|---|---|
| author | Hanbing Ma Oliver Kirschner Stefan Riedelbauch |
| author_facet | Hanbing Ma Oliver Kirschner Stefan Riedelbauch |
| author_sort | Hanbing Ma |
| collection | DOAJ |
| description | The head and flow rate of a pump characterize the pump performance, which help determine whether maintenance is needed. In the proposed method, instead of a traditional flowmeter and manometer, the operating points are identified using data collected from accelerometers and microphones. The dataset is created from a test rig consisting of a standard centrifugal water pump and measurement system. After implementing preprocessing techniques and Convolutional Neural Networks (CNNs), the trained models are obtained and evaluated. The influence of the sensor location and the performance of different signals or signal combinations are investigated. The proposed method achieves a mean relative error of 7.23% for flow rate and 2.37% for head with the best model. By employing two data augmentation techniques, performance is further improved, resulting in a mean relative error of 3.55% for flow rate and 1.35% for head with the sliding window technique. |
| first_indexed | 2024-03-08T20:40:30Z |
| format | Article |
| id | doaj.art-1222db057b09452d8c0a844e0b28f2dd |
| institution | Directory Open Access Journal |
| issn | 2504-186X |
| language | English |
| last_indexed | 2024-03-08T20:40:30Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Turbomachinery, Propulsion and Power |
| spelling | doaj.art-1222db057b09452d8c0a844e0b28f2dd2023-12-22T14:15:38ZengMDPI AGInternational Journal of Turbomachinery, Propulsion and Power2504-186X2023-10-01843910.3390/ijtpp8040039Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural NetworkHanbing Ma0Oliver Kirschner1Stefan Riedelbauch2Institute of Fluid Mechanics and Hydraulic Machinery, University of Stuttgart, 70569 Stuttgart, GermanyInstitute of Fluid Mechanics and Hydraulic Machinery, University of Stuttgart, 70569 Stuttgart, GermanyInstitute of Fluid Mechanics and Hydraulic Machinery, University of Stuttgart, 70569 Stuttgart, GermanyThe head and flow rate of a pump characterize the pump performance, which help determine whether maintenance is needed. In the proposed method, instead of a traditional flowmeter and manometer, the operating points are identified using data collected from accelerometers and microphones. The dataset is created from a test rig consisting of a standard centrifugal water pump and measurement system. After implementing preprocessing techniques and Convolutional Neural Networks (CNNs), the trained models are obtained and evaluated. The influence of the sensor location and the performance of different signals or signal combinations are investigated. The proposed method achieves a mean relative error of 7.23% for flow rate and 2.37% for head with the best model. By employing two data augmentation techniques, performance is further improved, resulting in a mean relative error of 3.55% for flow rate and 1.35% for head with the sliding window technique.https://www.mdpi.com/2504-186X/8/4/39standard water pumpoperating point estimationconvolutional neural network |
| spellingShingle | Hanbing Ma Oliver Kirschner Stefan Riedelbauch Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural Network International Journal of Turbomachinery, Propulsion and Power standard water pump operating point estimation convolutional neural network |
| title | Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural Network |
| title_full | Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural Network |
| title_fullStr | Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural Network |
| title_full_unstemmed | Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural Network |
| title_short | Systematic Comparison of Sensor Signals for Pump Operating Points Estimation Using Convolutional Neural Network |
| title_sort | systematic comparison of sensor signals for pump operating points estimation using convolutional neural network |
| topic | standard water pump operating point estimation convolutional neural network |
| url | https://www.mdpi.com/2504-186X/8/4/39 |
| work_keys_str_mv | AT hanbingma systematiccomparisonofsensorsignalsforpumpoperatingpointsestimationusingconvolutionalneuralnetwork AT oliverkirschner systematiccomparisonofsensorsignalsforpumpoperatingpointsestimationusingconvolutionalneuralnetwork AT stefanriedelbauch systematiccomparisonofsensorsignalsforpumpoperatingpointsestimationusingconvolutionalneuralnetwork |