基于差异检测算法的重载机车关键部件故障识别研究

Research on fault identification of key components of heavy-duty locomotive via difference detection algorithm

针对重载机车牵引吨位重、运行速度快、运行环境恶劣、故障识别困难等,设计了一种基于机器视觉和深度学习的差异检测算法,利用卷积神经网络(CNNs)进行特征提取和分类识别,实现对机车关键部件潜在故障的快速准确识别,并针对螺栓检测等小目标检测进行优化。实验表明,与传统检测手段相比,该算法在检测速度、准确率和鲁棒性上展现出显著优势,能够有效提升重载机车检测的自动化水平,降低人为因素导致的误判风险。

A difference detection algorithm based on machine vision and deep learning is designed for heavy haul tonnage,high running speed,bad operating environment and difficulty in fault identification.The algorithm employs Convolutional Neural Networks(CNNs)for feature extraction and classification recognition to enable rapid and accurate identification of potential faults in key components.Additionally,it includes optimizations for the detection of small targets such as bolts.Experimental validation demonstrates that the algorithm proposed in this study exhibits significant advantages over traditional detection methods in terms of detection speed,accuracy,and robustness.It effectively enhances the level of automation in heavy-duty locomotive inspection while reducing the risk of misjudgment caused by human factors.