Wear state recognition of mechanical equipment based on stacked denoised auto-encoding network
Wear state recognition of mechanical equipment can be realized by image recognition of ferrography image of wear particle, but ferrography image of wear particle recognition based on machine learning has more manual intervention and poor universality. In order to solve the above problems, a wear sta...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Industry and Mine Automation
2020-11-01
|
| Series: | Gong-kuang zidonghua |
| Subjects: | |
| Online Access: | http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.17633 |
| _version_ | 1828491428853972992 |
|---|---|
| author | FAN Hongwei MA Ningge ZHANG Xuhui GAO Shuoqi CAO Xiangang MA Hongwei |
| author_facet | FAN Hongwei MA Ningge ZHANG Xuhui GAO Shuoqi CAO Xiangang MA Hongwei |
| author_sort | FAN Hongwei |
| collection | DOAJ |
| description | Wear state recognition of mechanical equipment can be realized by image recognition of ferrography image of wear particle, but ferrography image of wear particle recognition based on machine learning has more manual intervention and poor universality. In order to solve the above problems, a wear state recognition method of mechanical equipment based on stacked denoised auto-encoding network was proposed. Multiple denoised auto-encoding networks are stacked, that is, the output of hidden layer of upper-level denoised auto-encoding network is taken as the input of the next-level denoised auto-encoding network, and Softmax classifier is added after hidden layer of the last level denoised auto-encoding network, so as to construct the stacked denoised auto-encoding network. The ferrography images of wear particle are used for unsupervised pre-training of stacked denoised auto-encoding network, network parameters are optimized by supervised fine-tuning, and ferrography images of wear particle are classified to achieve intelligent wear state recognition of mechanical equipment. The experimental results show that the stacked denoised auto-encoding network achieves the best performance when activation function is Relu, optimizer is Adam and learning rate is 0.001, and recognition accuracy is 98.43%. |
| first_indexed | 2024-12-11T11:02:15Z |
| format | Article |
| id | doaj.art-1ff848e076be410bad5aceb02665a28c |
| institution | Directory Open Access Journal |
| issn | 1671-251X |
| language | zho |
| last_indexed | 2024-12-11T11:02:15Z |
| publishDate | 2020-11-01 |
| publisher | Editorial Department of Industry and Mine Automation |
| record_format | Article |
| series | Gong-kuang zidonghua |
| spelling | doaj.art-1ff848e076be410bad5aceb02665a28c2022-12-22T01:09:51ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2020-11-01461161110.13272/j.issn.1671-251x.17633Wear state recognition of mechanical equipment based on stacked denoised auto-encoding networkFAN HongweiMA NinggeZHANG XuhuiGAO ShuoqiCAO XiangangMA HongweiWear state recognition of mechanical equipment can be realized by image recognition of ferrography image of wear particle, but ferrography image of wear particle recognition based on machine learning has more manual intervention and poor universality. In order to solve the above problems, a wear state recognition method of mechanical equipment based on stacked denoised auto-encoding network was proposed. Multiple denoised auto-encoding networks are stacked, that is, the output of hidden layer of upper-level denoised auto-encoding network is taken as the input of the next-level denoised auto-encoding network, and Softmax classifier is added after hidden layer of the last level denoised auto-encoding network, so as to construct the stacked denoised auto-encoding network. The ferrography images of wear particle are used for unsupervised pre-training of stacked denoised auto-encoding network, network parameters are optimized by supervised fine-tuning, and ferrography images of wear particle are classified to achieve intelligent wear state recognition of mechanical equipment. The experimental results show that the stacked denoised auto-encoding network achieves the best performance when activation function is Relu, optimizer is Adam and learning rate is 0.001, and recognition accuracy is 98.43%.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.17633mechanical equipmentwear state recognitionferrography image of wear particlestacked denoised auto-encoding network |
| spellingShingle | FAN Hongwei MA Ningge ZHANG Xuhui GAO Shuoqi CAO Xiangang MA Hongwei Wear state recognition of mechanical equipment based on stacked denoised auto-encoding network Gong-kuang zidonghua mechanical equipment wear state recognition ferrography image of wear particle stacked denoised auto-encoding network |
| title | Wear state recognition of mechanical equipment based on stacked denoised auto-encoding network |
| title_full | Wear state recognition of mechanical equipment based on stacked denoised auto-encoding network |
| title_fullStr | Wear state recognition of mechanical equipment based on stacked denoised auto-encoding network |
| title_full_unstemmed | Wear state recognition of mechanical equipment based on stacked denoised auto-encoding network |
| title_short | Wear state recognition of mechanical equipment based on stacked denoised auto-encoding network |
| title_sort | wear state recognition of mechanical equipment based on stacked denoised auto encoding network |
| topic | mechanical equipment wear state recognition ferrography image of wear particle stacked denoised auto-encoding network |
| url | http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.17633 |
| work_keys_str_mv | AT fanhongwei wearstaterecognitionofmechanicalequipmentbasedonstackeddenoisedautoencodingnetwork AT maningge wearstaterecognitionofmechanicalequipmentbasedonstackeddenoisedautoencodingnetwork AT zhangxuhui wearstaterecognitionofmechanicalequipmentbasedonstackeddenoisedautoencodingnetwork AT gaoshuoqi wearstaterecognitionofmechanicalequipmentbasedonstackeddenoisedautoencodingnetwork AT caoxiangang wearstaterecognitionofmechanicalequipmentbasedonstackeddenoisedautoencodingnetwork AT mahongwei wearstaterecognitionofmechanicalequipmentbasedonstackeddenoisedautoencodingnetwork |