基于CWT-TFA-ResNet的升降类游乐设施传动系统故障诊断

doi:10.16265/j.cnki.issn1003-3033.2026.S1.0023

中国安全科学学报 ›› 2026, Vol. 36 ›› Issue (S1): 153-159.doi: 10.16265/j.cnki.issn1003-3033.2026.S1.0023

基于CWT-TFA-ResNet的升降类游乐设施传动系统故障诊断

吴琪¹(), 王华杰²^,³, 宋伟科²^,³, 罗海风¹^,^**()

¹ 北京林业大学工学院, 北京 100083
² 国家市场监督管理总局技术创新中心大型游乐设施健康管控, 北京 100029
³ 中国特种设备检测研究院, 北京 100029

收稿日期:2026-02-11 修回日期:2026-04-12 出版日期:2026-06-30
通信作者:
** 罗海风(1984—),男,河北石家庄人,博士,副教授,主要从事机器人、机器视觉、人工智能及应用方面的研究。E-mail:luohaifeng@bjfu.edu.cn。
作者简介:
吴琪 (2001—),女,安徽铜陵人,硕士研究生,主要研究方向为深度学习、机械故障诊断、信号处理。E-mail:wuqi2332023@163.com。
王华杰高级工程师
宋伟科正高级工程师

Fault diagnosis of transmission system of lifting amusement rides based on CWT-TFA-ResNet

Wu Qi¹(), Wang Huajie²^,³, Song Weike²^,³, Luo Haifeng¹^,^**()

¹ School of Technology, Beijing Forestry University, Beijing 100083, China
² Technology Innovation Center of Health Management of Large-scale Amusement Device, State Administration for Market Regulation, Beijing 100029, China
³ China Special Equipment Inspection & Research Institute, Beijing 100029, China

Received:2026-02-11 Revised:2026-04-12 Published:2026-06-30

摘要/Abstract

摘要：

为解决传统故障诊断方法在特定工况下处理复杂信号特征存在局限性的问题,提出一种用于升降类游乐设施传动系统的故障诊断方法。首先,运用连续小波变换(CWT)将试验台振动信号转化为富含时频特征的图像,以此保留信号在时频域的详细信息;其次,利用残差网络(ResNet)提取多层次分布式故障特征;然后,引入时频注意力(TFA)模块针对性强化时频域的特征,增强模型对复杂时频特征关键信息的捕捉能力;最后,在升降类游乐设施传动系统试验台开展试验,针对3个部位的4种故障类型进行诊断。结果表明:该方法在3个位置的故障识别准确率分别达到95.35%、95.97%、99.15%;将模型与多种深度学习故障诊断模型进行对比,识别指标存在明显提升;通过t-分布随机邻域嵌入(t-SNE)降维对模型提取特征可视化,不同运行状态样本整体呈现分区聚类效果。

关键词: 连续小波变换(CWT), 时频注意力(TFA), 残差网络(ResNet), 游乐设施传动系统, 故障诊断

Abstract:

A fault diagnosis method for the transmission system of lifting amusement rides was proposed to overcome the limitations of traditional fault diagnosis methods in handling complex signal features under specific operating conditions. First, vibration signals collected from the test bench were converted into images rich in time-frequency features using CWT to preserve detailed information in the time-frequency domain. Second, multilevel distributed fault-related features were extracted using ResNet. Third, a TFA module was introduced to selectively enhance time-frequency features, thereby improving the model's ability to capture critical information from complex time-frequency features. Finally, experiments were conducted on the test bench for the transmission system of lifting amusement rides to diagnose four types of faults at three locations. The results demonstrate that the fault recognition accuracies of the proposed method at the three locations reach 95.35%, 95.97%, and 99.15%, respectively. Substantial improvements in recognition metrics are achieved by the proposed method compared with multiple deep learning-based fault diagnosis models. The features extracted by the model are visualized after dimensionality reduction using t-distributed stochastic neighbor embedding (t-SNE), revealing an overall clustered distribution of samples under different operating conditions.

Key words: continuous wavelet transform (CWT), time-frequency attention (TFA), residual network (ResNet), transmission system of amusement ride, fault diagnosis

中图分类号:

X948

吴琪, 王华杰, 宋伟科, 罗海风. 基于CWT-TFA-ResNet的升降类游乐设施传动系统故障诊断[J]. 中国安全科学学报, 2026, 36(S1): 153-159.

Wu Qi, Wang Huajie, Song Weike, Luo Haifeng. Fault diagnosis of transmission system of lifting amusement rides based on CWT-TFA-ResNet[J]. China Safety Science Journal, 2026, 36(S1): 153-159.

图/表 8

图1

图2

图3

图4

图5

图6

图7

表1

参考文献 19

[1]	黄玺宁. 大型单摆式游乐设施转轴故障诊断方法研究[D]. 杭州: 中国计量大学, 2021.
	Huang Xining. Research on fault diagnosis method of rotating shaft of large-scale single pendulum amusement facility[D]. Hangzhou: China Jiliang University, 2021.
[2]	GB/T 41106.4—2021 大型游乐设施检查、维护保养与修理第4部分:升降类[S].
	GB/T 41106.4-2021 Large-scale amusement devices-inspection,maintenance and repair:part 4:sort of lifting rides[S].
[3]	张勇, 秦平彦, 林伟明, 等. 大型游乐设施运行状态测试系统及关键技术研究[J]. 中国安全科学学报, 2008, 18(12): 166-171,26.
	Zhang Yong, Qin Pingyan, Lin Weiming, et al. Dynamic performance test system for large recreation facilities and its key technologies[J]. China Safety Science Journal, 2008, 18(12): 166-171, 26.
[4]	丁翔, 盛坚. 小波变换在电力设备故障诊断中的应用研究[J]. 光源与照明, 2024(10): 75-77.
[5]	Peng Peizhen, Song Yang, Lu Yang, et al. Seizure prediction in EEG signals using STFT and domain adaptation[J]. Frontiers in Neuroscience, 2022, 15: DOI: 10.3389/fnins.2021.825434.
[6]	Yi Lingzhi, Long Jiao, Wang Yahui, et al. Stator-rotor fault diagnosis of induction motor based on time-frequency domain feature extraction[J]. Metrology and Measurement Systems, 2023, 30(4): DOI: 10.24425/mms.2023.147949.
[7]	刘元坤, 曹塬琪, 于艾鑫, 等. 基于BP-ANN雨水中总磷在人工渗滤系统去除过程优化[J]. 中国环境科学, 2025, 45(6): 3 151-3 160.
	Liu Yuankun, Cao Yuanqi, Yu Aixin, et al. Optimization of total phosphorus removal process in artificial percolation system based on BP-ANN[J]. China Environmental Science, 2025, 45(6): 3 151-3 160.
[8]	Akram T, Khan M A, Sharif M, et al. Skin lesion segmentation and recognition using multichannel saliency estimation and M-SVM on selected serially fused features[J]. Journal of Ambient Intelligence and Humanized Computing, 2024, 15(1): DOI: 10.1007/s12652-018-1051-5.
[9]	胡啸峰, 黄玲. 基于机器学习的户外作业警务人员热应激预测模型[J]. 中国安全科学学报, 2024, 34(11): 220-228. doi: 10.16265/j.cnki.issn1003-3033.2024.11.0171
	Hu Xiaofeng, Huang Ling. Heat stress prediction model for outdoor policeman based on machine learning[J]. China Safety Science Journal, 2024, 34(11): 220-228. doi: 10.16265/j.cnki.issn1003-3033.2024.11.0171
[10]	杨余, 杨鑫, 王英, 等. 基于mini-1D-CNN模型的TE过程故障诊断[J]. 中国安全科学学报, 2023, 33(2): 173-178. doi: 10.16265/j.cnki.issn1003-3033.2023.02.0017
	Yang Yu, Yang Xin, Wang Ying, et al. Research on TE process fault diagnosis based on mini-1D-CNN model[J]. China Safety Science Journal, 2023, 33(2): 173-178. doi: 10.16265/j.cnki.issn1003-3033.2023.02.0017
[11]	Pan Honghu, He Xingxi, Tang Sai, et al. An improved bearing fault diagnosis method using one-dimensional CNN and LSTM[J]. Journal of Mechanical Engineering, 2018, 64(7/8): DOI: 10.5545/sv-jme.2018.5249.
[12]	Zhao Haitao, Sun Shaoyuan, Jin Bo. Sequential fault diagnosis based on LSTM neural network[J]. IEEE Access, 2018, 6: DOI: 10.1109/ACCESS.2018.2794765.
[13]	邵海东, 张笑阳, 程军圣, 等. 基于提升深度迁移自动编码器的轴承智能故障诊断[J]. 机械工程学报, 2020, 56(9): DOI: 10.3901/JME.2020.09.084.
	Shao Haidong, Zhang Xiaoyang, Cheng Junsheng, et al. Intelligent fault diagnosis of bearing using enhanced deep transfer auto-encoder[J]. Journal of Mechanical Engineering, 2020, 56(9): DOI: 10.3901/JME.2020.09.084.
[14]	Ruan D, Chen X, Gühmann C, et al. Improvement of generative adversarial network and its application in bearing fault diagnosis: a review[J]. Lubricants, 2023, 11(2): DOI: 10.3390/lubricants11020074.
[15]	Xu Peng, Zhu Xiatian, Clifton D A. Multimodal learning with transformers: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(10): DOI: 10.1109/TPAMI.2023.3275156.
[16]	Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics, 1980, 36(4): DOI: 10.1007/BF00344251.
[17]	Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): DOI: 10.1109/5.726791.
[18]	He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016: DOI: 10.1109/CVPR.2016.90.
[19]	Zhang Qiquan, Song Qi, Ni Zhaoheng, et al. Time-frequency attention for monaural speech enhancement[C]. 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022: 7 852-7 856.

机器学习方法	F₁值/%
1DCNN	83.24
LSTM	53.84
CWT-ResNet	93.50
MTF-ResNet	73.02
CWT-VGG	86.54
GAF-ResNet	76.93
CWT-TFA-ResNet	95.35

基于CWT-TFA-ResNet的升降类游乐设施传动系统故障诊断

Fault diagnosis of transmission system of lifting amusement rides based on CWT-TFA-ResNet

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价

[1]	何亚东, 徐伟, 王金江, 苟成冬, 王春利. 融合浅层与深度学习的化工过程故障诊断方法[J]. 中国安全科学学报, 2026, 36(7): 118-126.
[2]	盛武, 储小渝, 吴敏玮. 基于BO-XGBoost-SHAP架构的矿井主提升机故障诊断模型[J]. 中国安全科学学报, 2026, 36(5): 89-97.
[3]	王岩韬, 高艺, 时统宇. 基于QAR数据的飞行控制系统故障研究综述[J]. 中国安全科学学报, 2024, 34(4): 1-9.
[4]	樊晓萱, 段礼祥, 张娜, 李兴涛, 蒋璐朦. 基于联合定位密集网络的变载齿轮箱故障特征提取[J]. 中国安全科学学报, 2024, 34(10): 166-173.
[5]	尚书宏, 曹亮, 鲁伟. 基于小波变换特征提取的脱介筛故障诊断算法[J]. 中国安全科学学报, 2023, 33(S2): 233-237.
[6]	张斌, 张辛忻, 杨海涛. 基于神经网络的振动给料机故障诊断算法[J]. 中国安全科学学报, 2023, 33(S2): 55-59.
[7]	刘鑫, 王亚军, 姚美常, 苏磊, 王鹏. 基于LabVIEW的矿井提升机液压制动在线监测[J]. 中国安全科学学报, 2023, 33(S1): 145-149.
[8]	杨余, 杨鑫, 王英, 翟持, 张浩. 基于mini-1D-CNN模型的TE过程故障诊断[J]. 中国安全科学学报, 2023, 33(2): 173-178.
[9]	李刚, 卢佩玲, 杨勇. ZPW-2000轨道电路故障诊断算法应用研究[J]. 中国安全科学学报, 2022, 32(6): 53-59.
[10]	林海香, 卢冉, 陆人杰, 李新琴, 赵正祥, 白万胜. 融合BiLSTM-CBA组合模型的高铁车载设备故障诊断[J]. 中国安全科学学报, 2022, 32(6): 79-86.
[11]	余伟, 王志鹏, 刘硕, 何刚. 多级精细模型下的电机匝间短路故障诊断[J]. 中国安全科学学报, 2022, 32(6): 95-102.
[12]	邢玉龙, 王剑, 上官伟, 彭聪, 朱林富. 面向海量不平衡数据的轨道电路故障诊断方法[J]. 中国安全科学学报, 2022, 32(5): 112-118.
[13]	赵丹, 沈志远, 刘晓青. 基于OCISVM的矿井通风系统在线故障诊断[J]. 中国安全科学学报, 2022, 32(10): 76-82.
[14]	古莹奎, 刘平, 林忠海, 邱光琦. 基于Kurtogram与DSCN的滚动轴承故障诊断方法[J]. 中国安全科学学报, 2021, 31(6): 99-105.
[15]	陈志煌, 刘国恒, 王莹莹, 朱春丽, 单荐, 翟小东. 基于动态贝叶斯网络的水下连接器故障诊断[J]. 中国安全科学学报, 2020, 30(5): 81-87.