Using Semantic Segmentation Network to Measure Vibration Displacement of Rotating Body

被引:8
作者
Chai, Shanglei [1 ]
Wang, Sen [1 ]
Liu, Chang [1 ]
Liu, Tao [1 ]
Liu, Xiaoqin [1 ]
Xing, Kaizhe [1 ]
机构
[1] Kunming Univ Sci & Technol, Fac Mech & Elect Engn, Kunming 650500, Peoples R China
基金
中国国家自然科学基金;
关键词
Rotating body; rotor vibration; semantic segmentation; vibration displacement measurement; VISION-BASED DISPLACEMENT; LASER-DOPPLER VIBROMETRY;
D O I
10.1109/JSEN.2023.3245141
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Compared with traditional vibration measurement sensors, visual vibration displacement measurement technology has many advantages, such as long distance, non-contact, and non-interference. However, when it comes to complex working conditions or inconvenient preprocessing scene, visual measuring techniques usually cannot produce results with the high precision needed for vibration analysis. In this article, we proposed a visual measurement algorithm for vibration displacement of rotating body using semantic segmentation network by taking a high-speed industrial camera as the image acquisition medium and rotor as the experimental object. To make the network better applicable to segmentation of rotating body targets in different illumination, blur, and similarity contexts, the cross-stage partial (CSP) connections, concat channel fusion module, and shuffle attention (SA) are purposefully incorporated into proposed CMCS convolution module. During calculation of the loss in the training network stage, we add the binary cross-entropy loss and Dice-loss to solve the problem of serious imbalance between positive and negative samples caused by remote photography. The vibration signal synchronously collected by eddy current sensor is exploited as standard signal to compare the different segmentation algorithms quantitatively and qualitatively. The experimental results show that the root mean square error (RMSE) between vibration displacement signal regressed by our segmentation algorithm and standard signal is the smallest, and the time-domain diagram, frequency-domain diagram, and shaft orbit diagram are also more fitted to the standard signal curve, which provides valuable guidance for the visual vibration displacement measurement of rotating body in complex industrial setting.
引用
收藏
页码:7977 / 7991
页数:15
相关论文
共 50 条
[41]   A Deforestation Detection Network Using Deep Learning-Based Semantic Segmentation [J].
Das, Pradeep Kumar ;
Sahu, Adyasha ;
Xavy, Dias V. ;
Meher, Sukadev .
IEEE SENSORS LETTERS, 2024, 8 (01) :1-4
[42]   Semantic Point Cloud Segmentation Using Fast Deep Neural Network and DCRF [J].
Rao, Yunbo ;
Zhang, Menghan ;
Cheng, Zhanglin ;
Xue, Junmin ;
Pu, Jiansu ;
Wang, Zairong .
SENSORS, 2021, 21 (08)
[43]   MULTI-SOURCE POINT CLOUD SEMANTIC SEGMENTATION USING NEURAL NETWORK [J].
Montlahuc, Jeremy ;
Polette, Arnaud ;
Tahan, Antoine ;
Pernot, Jean-Philippe ;
Rivest, Louis .
XXIV ISPRS CONGRESS: IMAGING TODAY, FORESEEING TOMORROW, COMMISSION III, 2022, 43-B3 :515-522
[44]   GPNet: Gated pyramid network for semantic segmentation [J].
Zhang, Yu ;
Sun, Xin ;
Dong, Junyu ;
Chen, Changrui ;
Lv, Qingxuan .
PATTERN RECOGNITION, 2021, 115
[45]   Lightweight semantic segmentation network for underwater image [J].
Guo H.-R. ;
Guo J.-C. ;
Wang Y.-D. .
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2023, 57 (07) :1278-1286
[46]   Efficient Attention Pyramid Network for Semantic Segmentation [J].
Yang, Qirui ;
Ku, Tao ;
Hu, Kunyuan .
IEEE ACCESS, 2021, 9 :18867-18875
[47]   DENSELY CONNECTED DECONVOLUTIONAL NETWORK FOR SEMANTIC SEGMENTATION [J].
Fu, Jun ;
Liu, Jing ;
Wang, Yuhang ;
Lu, Hanqing .
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, :3085-3089
[48]   A Strip Dilated Convolutional Network for Semantic Segmentation [J].
Zhou, Yan ;
Zheng, Xihong ;
Ouyang, Wanli ;
Li, Baopu .
NEURAL PROCESSING LETTERS, 2023, 55 (04) :4439-4459
[49]   Sketch-and-Fill Network for Semantic Segmentation [J].
Jin, Youngsaeng ;
Eum, Sungmin ;
Han, David ;
Ko, Hanseok .
IEEE ACCESS, 2021, 9 :85874-85884
[50]   HDNet: Hybrid Distance Network for semantic segmentation [J].
Li, Chunpeng ;
Kang, Xuejing ;
Zhu, Lei ;
Ye, Lizhu ;
Feng, Panhe ;
Ming, Anlong .
NEUROCOMPUTING, 2021, 447 :129-144