Fault classification method and system for port crane transmission device

The invention discloses a fault classification method and system for a port crane transmission device. Real-time signals of a port crane transmission device are collected to serve as original data, the original data are subjected to denoising and dimensionality reduction processing, then features of the data subjected to dimensionality reduction are extracted, the extracted features are enhanced by using the idea of small sample learning enhancement, and the real-time signals of the port crane transmission device are obtained. And then the extracted depth feature vectors are input into the constructed depth learning model to divide the fault types of the transmission device, so that the accuracy of fault classification is effectively improved. 本发明公开了一种港口起重机传动装置的故障分类方法及系统。通过收集港口起重机传动装置的实时信号作为原始数据，对原始数据进行去噪和降维处理，然后对降维后的数据的特征进行提取，并利用小样本学习增强的思想，对提取到的特征进行增强，之后将提取的深度特征向量输入构建好的深度学习模型中对传动装置的故障类型进行划分，有效提高了故障分类的准确性。