Advance Search
CHEN Xiangyuan,QIN Wei,LIU Yanchi,et al. Audio recognition method of belt conveyor roller fault based on convolutional neural network and linear regression[J]. Coal Science and Technology,2025,53(S1):389−398. DOI: 10.12438/cst.2024-0229
Citation: CHEN Xiangyuan,QIN Wei,LIU Yanchi,et al. Audio recognition method of belt conveyor roller fault based on convolutional neural network and linear regression[J]. Coal Science and Technology,2025,53(S1):389−398. DOI: 10.12438/cst.2024-0229

Audio recognition method of belt conveyor roller fault based on convolutional neural network and linear regression

More Information
  • Received Date: February 24, 2024
  • Available Online: May 25, 2025
  • Aiming at the problems of complex sound source and insignificant characteristics in the audio recognition of roller fault of belt conveyor in coal mine, an audio recognition method of roller fault based on convolution neural network and linear regression is proposed. Firstly, the audio signal along the roller is collected by the MEMS pickup carried by the inspection robot of the belt conveyor. Based on the wavelet autocorrelation denoising technology, the sound is preprocessed to suppress the background noise signal in the audio signal and optimize the data quality. Secondly, using the voiceprint spectrum separation technology, the HPSS (Harmonic Percussive Source Separation) method is used to separate the harmonic and shock wave components to enhance the sound signal characteristics of the roller fault. Based on MFCC (Mel Frequency Cepstrum Coefficient) voiceprint feature extraction method, the voiceprint feature information of the roller in the harmonic-shock wave is analyzed, the sound spectrum is generated, and the voiceprint representation ability of the roller fault is improved. Then, a harmonic-shock wave weak classifier is constructed based on multi-scale residual convolutional neural network, and a sound quality weak classifier is constructed based on multiple linear regression. Finally, based on two weak classifiers, using the spectrogram and sound quality features as data sources, fusion of multimodal faulty features and enrich data dimensions, based on the spectrogram and sound quality features, residual convolutional neural network computing image features, fast fitting of audio basic features using multiple linear regression, a roller fault voiceprint representation model combining convolutional neural network and linear regression is generated for joint training. The sample weight of the model training is optimized by the Focal Loss loss function to improve the accuracy of the model for roller fault recognition.The method in this paper is used to analyze and verify the audio information of the fault roller of the belt conveyor actually collected in Guojiawan Coal Mine of Yulin. The results show that the detection rate of roller fault reaches 95.79 %, and the detection accuracy reaches 95.60 %.

  • [1]
    刘澎,任文清. 煤矿无人值守带式输送机智能化系统设计[J]. 工矿自动化,2021,47(S2):75−77,96.

    LIU Peng,REN Wenqing. Intelligent system design of unattended belt conveyor in coal mine[J]. Industry and Mine Automation,2021,47(S2):75−77,96.
    [2]
    田元武. 煤矿带式输送机智能化关键技术的研究[J]. 自动化应用,2023(S1):112−114.

    TIAN Yuanwu. Research on key technologies of intelligent belt conveyor in coal mine[J]. Automation Application,2023(S1):112−114.
    [3]
    朱荣贵. 矿用皮带运输机常见故障分析及预防[J]. 机械工程师,2018(3):162−163,166. doi: 10.3969/j.issn.1002-2333.2018.03.057

    ZHU Ronggui. Analysis and prevention of common failure in mine belt conveyor[J]. Mechanical Engineer,2018(3):162−163,166. doi: 10.3969/j.issn.1002-2333.2018.03.057
    [4]
    李玮华,杨秦建. 在线带式输送机托辊工况动态监测系统的研发[J]. 西安科技大学学报,2008,28(1):100−104. doi: 10.3969/j.issn.1672-9315.2008.01.022

    LI Weihua,YANG Qinjian. Dynamic testing system of strap conveyer’s roll release online[J]. Journal of Xi’an University of Science and Technology,2008,28(1):100−104. doi: 10.3969/j.issn.1672-9315.2008.01.022
    [5]
    白宏磊,张明泽,王克成. 长距离带式输送机托辊的故障检测[J]. 辽宁科技大学学报,2015,38(1):41−45.

    BAI Honglei,ZHANG Mingze,WANG Kecheng. Fault detection of lon-distance belt conveyor idlers[J]. Journal of University of Science and Technology Liaoning,2015,38(1):41−45.
    [6]
    张俊. 基于红外热成像技术的托辊故障诊断系统研究[J]. 机械研究与应用,2023,36(4):174−178.

    ZHANG Jun. Research on idler fault diagnosis system based on infrared thermal imaging technology[J]. Mechanical Research & Application,2023,36(4):174−178.
    [7]
    彭程程. 基于二阶瞬态提取变换的滚动轴承故障特征提取方法研究[J]. 机电工程,2021,38(10):1246−1252. doi: 10.3969/j.issn.1001-4551.2021.10.004

    PENG Chengcheng. Fault feature extraction method for rolling bearing based on STET[J]. Journal of Mechanical & Electrical Engineering,2021,38(10):1246−1252. doi: 10.3969/j.issn.1001-4551.2021.10.004
    [8]
    郝洪涛,倪凡凡,陈亮,等. 远程带式输送机托辊故障巡检方法[J]. 煤矿机械,2018,39(11):133−135.

    HAO Hongtao,NI Fanfan,CHEN Liang,et al. Investigation of inspection method on roller of remote belt conveyor[J]. Coal Mine Machinery,2018,39(11):133−135.
    [9]
    邵晨. 基于噪声信号技术的皮带机托辊故障监测[J]. 仪表技术,2017(8):7−11,46.

    SHAO Chen. Fault detection of belt system based on noise signal technology[J]. Instrumentation Technology,2017(8):7−11,46.
    [10]
    刘芬. 基于大数据技术的带式输送机托辊故障诊断[J]. 煤矿机械,2020,41(8):177−179.

    LIU Fen. Fault diagnosis of roller of belt conveyor based on big data technology[J]. Coal Mine Machinery,2020,41(8):177−179.
    [11]
    方崇全. 煤矿带式输送机巡检机器人关键技术研究[J]. 煤炭科学技术,2022,50(5):263−270.

    FANG Chongquan. Research on key technology of inspection robot for coal mine belt conveyor[J]. Coal Science and Technology,2022,50(5):263−270.
    [12]
    宋天祥,杨明锦,杨林顺,等. 基于谱聚类分析的托辊故障诊断[J]. 电子测量技术,2019,42(5):144−150.

    SONG Tianxiang,YANG Mingjin,YANG Linshun,et al. Fault diagnosis for roller based on spectral clustering analysis[J]. Electronic Measurement Technology,2019,42(5):144−150.
    [13]
    吴文臻,程继明,李标. 矿用带式输送机托辊音频故障诊断方法[J]. 工矿自动化,2022,48(9):25−32.

    WU Wenzhen,CHENG Jiming,LI Biao. Audio fault diagnosis method of mine belt conveyor roller[J]. Journal of Mine Automation,2022,48(9):25−32.
    [14]
    曹贯强. 带式输送机托辊故障检测方法[J]. 工矿自动化,2020,46(6):81−86.

    CAO Guanqiang. Fault detection method for belt conveyor roller[J]. Industry and Mine Automation,2020,46(6):81−86.
    [15]
    贺志坚,欧阳毅,郑虎鸣,等. 驻极体电容振动拾音器(ECVP)[J]. 电声技术,2017,41(3):27−30.

    HE Zhijian,OUYANG Yi,ZHENG Huming,et al. Electret capacitive vibration pickup(ECVP)[J]. Audio Engineering,2017,41(3):27−30.
    [16]
    景会成,白世平,崔传金,等. 心电信号降噪及R波提取技术研究[J]. 电子测量技术,2022,45(24):67−75.

    JING Huicheng,BAI Shiping,CUI Chuanjin,et al. Research on ECG signal noise reduction and R-wave extraction technology[J]. Electronic Measurement Technology,2022,45(24):67−75.
    [17]
    余星辰,王云泉. 基于小波包能量的煤矿瓦斯和煤尘爆炸声音识别方法[J]. 工矿自动化,2023,49(1):131−139.

    YU Xingchen,WANG Yunquan. Coal mine gas and coal dust explosion sound recognition method based on wavelet packet energy[J]. Journal of Mine Automation,2023,49(1):131−139.
    [18]
    ONO N,MIYAMOTO K,LE ROUX J,et al. Separation of a monaural audio signal into harmonic/percussive components by complementary diffusion on spectrogram[C]//2008 16th European Signal Processing Conference. Piscataway,NJ:IEEE,2008:1‒4.
    [19]
    赵扬青,彭智才,蒋雨涵,等. 音频的梅尔频率倒谱系数特征抽取过程[J]. 信息技术与信息化,2023(1):104−111. doi: 10.3969/j.issn.1672-9528.2023.01.026

    ZHAO Yangqing,PENG Zhicai,JIANG Yuhan,et al. Mel-frequency cepstral coefficients feature extraction process of audio[J]. Information Technology and Informatization,2023(1):104−111. doi: 10.3969/j.issn.1672-9528.2023.01.026
    [20]
    韩鹏飞,陈晓. 基于MFCC-IMFCC和GA-SVM的鸟声识别[J]. 计算机系统应用,2022,31(11):393−399.

    HAN Pengfei,CHEN Xiao. Bird sound recognition based on MFCC-IMFCC and GA-SVM[J]. Computer Systems and Applications,2022,31(11):393−399.
    [21]
    金可心,卢海峰,杨亮,等. 融入时频能量特征的车内噪声声品质评价方法[J]. 电子测量与仪器学报,2022,36(5):96−103.

    JIN Kexin,LU Haifeng,YANG Liang,et al. Sound quality evaluation method of vehicle interior noise based on time-frequency energy characteristics[J]. Journal of Electronic Measurement and Instrumentation,2022,36(5):96−103.
    [22]
    陈建廷,向阳. 深度神经网络训练中梯度不稳定现象研究综述[J]. 软件学报,2018,29(7):2071−2091.

    CHEN Jianting,XIANG Yang. Survey of unstable gradients in deep neural network training[J]. Journal of Software,2018,29(7):2071−2091.
    [23]
    佟哲. 矿用带式输送机托辊远程故障诊断方法研究[D]. 徐州:中国矿业大学,2020.

    TONG Zhe. Research on remote fault diagnosis method of idler of mine belt conveyor[D]. Xuzhou:China University of Mining and Technology,2020.

Catalog

    Article views (33) PDF downloads (17) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return