1 Department of Mechanical Engineering, North China Electric Power University, Baoding 071003, China
2 Yanzhao Electric Power Laboratory, North China Electric Power University, Baoding 071003, China
Show less
文章历史+
Received
Published
Revised
2025-10-10
2026-08-28
2026-01-19
Online Date
2026-09-04
PDF (10456K)
摘要
基于声音信号的螺栓松动检测方法具有便捷高效的特点,针对螺栓群松动问题现有方法检测精细程度不够,缺乏松动状态细粒度的描述。针对输电铁塔中典型螺栓连接节点,通过敲击采集获得了48类松动的649个音频,利用音调平移、时间拉伸及噪声添加等数据增强方法获得了6 087个增强样本。基于梅尔频率倒谱系数(Mel frequency cepstral coefficients,MFCC)提取了螺栓群敲击声信号的时频特征,结合SE(squeeze-and-excitation)注意力模块增强特征通道的判别性,利用Inception模块融合多尺度时频信息,搭建了多任务卷积神经网络-循环神经网络(convolutional neural network-recurrent neural network,CNN-RNN)架构,提出了基于MFCC特征的螺栓群松动状态检测方法,实现了螺栓群的松动区域、松动数量及松动位置的多维度精准识别。实验结果表明:所提方法在区域识别、松动个数识别任务中分别达到98.13%、92.20%的平均准确率,在松动位置判定任务中Top-3覆盖率达到91.86%,研究成果为输电线路运维提供了高效的螺栓松动检测手段。
Abstract
The bolt loosening detection method based on acoustic signals is characterized by convenience and high efficiency. However, existing methods for bolt group loosening problems suffer from insufficient detection precision and lack fine-grained descriptions of loosening states. Focusing on typical bolted connection nodes in transmission towers, 649 audio samples corresponding to 48 types of loosening states were collected through tapping. A total of 6 087 augmented samples were obtained by adopting data augmentation techniques such as pitch shifting, time stretching, and noise addition. The time-frequency features of the tapping acoustic signals of bolt groups were extracted based on Mel frequency cepstral coefficients (MFCC). The discriminability of feature channels was enhanced by integrating the squeeze-and-excitation (SE) attention module, and multi-scale time-frequency information was fused using the Inception module. A multi-task convolutional neural network-recurrent neural network (CNN-RNN) architecture was established, and a bolt group loosening state detection method based on MFCC features was proposed. This method achieved accurate multi-dimensional identification of the loosening area, the number of loose bolts, and the loosening positions of bolt groups. Experimental results show that the proposed method achieves average accuracies of 98.13% and 92.20% in the tasks of area identification and loose bolt count recognition, respectively. Meanwhile, the Top-3 coverage rate reaches 91.86% in the loosening position determination task. The research results provide an efficient bolt loosening detection approach for the operation and maintenance of transmission lines.
ZHANG Wei, CAI Ze-jiang, ZHANG Qiang, JIANG Wen-qiang.
Bolt Groups Loosening Detection Method of Transmission Tower Based on MFCC Feature[J].
Science Technology and Engineering, 2026, 26(24): 10404-10413 DOI:10.12404/j.issn.1671-1815.2507118
梅尔频率倒谱系数(Mel frequency cepstral coe-fficients,MFCC)最初用于语音识别,通过模拟人耳听觉特性,对短时频谱进行加权滤波和倒谱分析,提取音频信号的感知特征。近年来,其时频特征提取优势被引入损伤识别领域[24],如轴承故障检测、声发射监测[25]与部分放电缺陷识别[26]等,显著提升了在线监测的准确性和鲁棒性。基于以上现状,选用MFCC作为特征进行提取。
JiangWenqiang, MoZe, AnLiqiang. Computing method of bolted joint critical loosening load with flexible thread[J]. Journal of Mechanical Engineering, 2020, 56(15): 238-248.
[3]
JiangW Q, LiuY P, ChanS L, et al. Direct analysis of an ultrahigh-voltage lattice transmission tower considering joint effects[J]. Journal of Structural Engineering, 2017, 143: 04017009.
[4]
JiangW Q, MoZ, YangL Q, et al. Theoretical study on early stage self-loosening of bolted joint in lattice transmission tower under transverse load[J]. Advanced Steel Construction, 2022, 18: 574-584.
GaoGuangyi, ZhangXuesen, LiHuan, et al. Research on loosening diagnosis of flange bolts of wind turbine tower barrel based on strain monitoring theory[J]. Industrial Construction, 2024, 54(11): 15-23.
ZhaoWeiping, ChangHaotan, JiChunlei. Numerical simulation of loosening law of bolted joints under lateral vibration[J]. Journal of Vibration and Shock, 2024, 43(8): 61-69, 88.
[9]
ZhouY, YiH Z, YueX Y, et al. Method for loose bolt positioning and prediction of bolt axial force in bolt group[J]. Measurement, 2024, 227: 114316.
KangJingjie, ZhangLijun, SunYuandong, et al. A bolt loosening angle detection method based on color segmentation[J]. Journal of Mechanical Strength, 2025, 47(5): 102-109.
ZhangYifan, WangKang, SunTianxiang, et al. Finite element simulation analysis and strength check of bolted beams under diffe-rent working conditions[J]. Science Technology and Engineering, 2023, 23(36): 15473-15482.
LiuJie, WangXiangdong, JiaBoyan, et al. Detection method for complete loosening of iron towers bolts based on vibration characteristics[J]. Science Technology and Engineering, 2022, 22(32): 14213-14220.
ZhaoZhenbing, DingJietao. Weakly supervised detection method for pin-missing bolt of transmission line based on improved PCL model[J]. Science Technology and Engineering, 2022, 22(23): 10169-10178.
ZhangJunshu, LiDan, RenWeixin. Identification of bolt pre-tightening state based on cointegration analysis of vibro-acoustic modulation signals[J]. Journal of Vibration and Shock, 2022, 41(21): 1-6, 18.
[20]
WangS Y, ZhouY, KongQ Z. A force-adaptive percussion method for bolt looseness assessment[J]. Journal of Civil Structural Health Monitoring, 2024, 14: 831-841.
ZhangHong, LiuBinbin, LiYunfei. Flange bolted connection state recognition based on time series two dimensionalization and attention mechanism[J]. Journal of Vibration and Shock, 2022, 41(9): 181-188.
[25]
YuanC, ChenW S, HaoH, et al. Near real-time bolt-loosening detection using mask and region-based convolutional neural network[J]. Structural Control and Health Monitoring, 2021, 28: e2741.
[26]
NguyenT, TaQ, HoD, et al. A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning[J]. Developments in the Built Environment, 2023, 14: 100122.
[27]
PanX, YangT. 3D vision-based bolt loosening assessment using photogrammetry, deep neural networks, and 3D point-cloud processing[J]. Journal of Building Engineering, 2023, 70: 106326.
[28]
LuoP, WangB, WangH X, et al. An ultrasmall bolt defect detection method for transmission line inspection[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-12.
ChenRenxiang, XuPeiwen, HanKunlin. Intelligent looseness detection for bolts of a fan foundation based on a multi-scale one-dimensional convolutional neural network[J]. Journal of Vibration and Shock, 2022, 41(22): 301-307.
[31]
JiangZ P, ZhuZ W, ZhuoD B. Identification of bolt loosening damage of steel truss structure based on MFCC-WPES and optimized random forest[J]. Applied Sciences, 2024, 14: 6626.
[32]
DuC F, LiuJ H, GongH, et al. Percussion-based loosening detection method for multi-bolt structure using convolutional neural network DenseNet-CBAM[J]. Structural Health Monitoring, 2024, 23(4): 2183-2199.
[33]
YuanC, WangS Y, QiY Z, et al. Automated structural bolt looseness detection using deep learning-based prediction model[J]. Structural Control and Health Monitoring, 2022, 29(3): e2899.
[34]
KongQ Z, ZhuJ X, Ho SiuC, et al. Tapping and listening: a new approach to bolt looseness monitoring[J]. Smart Materials and Structures, 2018, 27(7): 07LT02.
[35]
ZhouY, WangS Y, ZhouM, et al. Percussion-based bolt looseness identification using vibration-guided sound reconstruction[J]. Structural Control and Health Monitoring, 2022, 29: e2876.
[36]
LiD, NieJ H, WangH, et al. Loading condition monitoring of high-strength bolt connections based on physics-guided deep learning of acoustic emission data[J]. Mechanical Systems and Signal Processing, 2024, 206: 110908.
[37]
MoharanaS, VishnuS. Piezo impedance-based monitoring of loosening of bolts: experimental and numerical study[J]. Journal of Intelligent Material Systems and Structures, 2022, 33: 1056-1071.