摘要
针对矿山皮带输送机滚动轴承故障振动信号噪声大、故障特征提取困难的问题,提出了一种结合信号优化预处理与深度学习的故障识别模型。该模型首先利用鲸鱼优化算法(Whale Optimization Algorithm,WOA)优化的变分模态分解(Variational Mode Decomposition,VMD)方法,对原始振动信号进行自适应降噪与重构以精准提取故障特征。然后,将重构后的信号转换为二维灰度图,作为模型的输入。最后,在识别分类阶段构建了一种改进的Extreme Inception(Xception)和卷积神经网络(Extreme Inception and Convolutional Neural Network,Xception-CNN)模型。该模型融合了Xception架构的深度可分离卷积优点以更高效地利用计算资源,同时引入了通道注意力机制以增强对关键故障特征的关注,并嵌入残差学习模块以缓解深层网络的梯度消失问题,最终实现端到端的故障状态智能分类。结果表明:Xception-CNN故障识别模型在测试集上实现了98.61%的最高识别准确率,F1分数达到0.985;在强噪声(信噪比为10 dB)干扰下,该模型准确率仍保持在98.61%,显著优于对比方法,具有较好的鲁棒性。同时,模型参数量仅为42.7 MB,单样本推理耗时仅12.3 ms,在保证高精度的同时具备良好的工程应用效率。
A fault recognition model combining signal optimization preprocessing and deep learning is proposed to address the problems of high noise in vibration signals and difficult feature extraction of rolling bearings in mining belt conveyors.The model first utilizes the Whale Optimization Algorithm(WOA)optimized Variational Mode Decomposition(VMD)method to adaptively denoise and reconstruct the original vibration signal to accurately extract fault features.Then,convert the reconstructed signal into a two-dimensional grayscale image as input to the model.Finally,an improved Extreme Inception(Xception)and Convolutional Neural Network(Xception-CNN)model was constructed during the recognition and classification stage.This network integrates the deep separable convolution advantages of Xception architecture to more efficiently utilize computing resources,while also introducing channel attention mechanism to enhance attention to key fault features,and embedding residual learning module to alleviate the gradient vanishing problem of deep networks,ultimately achieving end-to-end intelligent classification of fault states.The results showed that the proposed Xception-CNN fault recognition model achieved the highest recognition accuracy of 98.61%on the test set,with an F1 score of 0.985.Under strong noise,i.e.with a signal-tonoise ratio of 10 dB interference,the accuracy of the model still remains at 98.61%,significantly better than the comparison method,and has good robustness.At the same time,the model parameter size is only 42.7 MB,and the time-consumed for the single-sample inference is only 12.3 ms,which ensures high accuracy while having good engineering application efficiency.This provides new ideas and methods for fault diagnosis and predictive maintenance of mining equipment,which is of great significance for promoting the progress of mining equipment maintenance technology.
作者
权国辉
邰金华
张庆莉
薛春霞
QUAN Guohui;TAI Jinhua;ZHANG Qingli;XUE Chunxia(College of Advanced Materials Engineering,Zhengzhou Technical College,Zhengzhou 450121,China;School of Mechanical Engineering,North China University of Water Resources and Electric Power,Zhengzhou 450046,China;School of Information Engineering,Henan University of Animal Husbandry and Economy,Zhengzhou 450011,China)
出处
《金属矿山》
北大核心
2025年第10期149-158,共10页
Metal Mine
基金
2025年度河南省高等学校重点科研项目(编号:25B430045,25B430040)
2025年度河南省科技攻关项目(编号:252102230071)
2024年度河南省高等教育(高等职业教育类)教学改革研究与实践项目(编号:2024SJGLX0721)。
关键词
滚动轴承
故障识别
信号处理
鲸鱼优化算法
变模态分解
卷积神经网络
rolling bearing
fault recognition
signal processing
whale optimization algorithm
variational mode decomposition
convolutional neural network
作者简介
权国辉(1978-),女,副教授,硕士;通信作者:邰金华(1973-),女,副教授,硕士。
