基于CNN-LSTM混合深度学习模型的轴承故障检测方法
Detection Method of Bearing Faults Based on CNN-LSTM Hybrid Deep Learning Model

随着近年来工业的快速发展，对机械设备稳定运行的要求也不断提高。因此，如何确保机械设备高效且平稳地运行成为了一个重要课题。对于传统的机械设备故障检测方法，其过于依赖人的经验，效率低下和检测结果出入过大的情况，本文提出一种基于混合深度学习模型的轴承故障检测方法。该方法能够准确捕捉到轴承信号中的空间特征和时间特征，通过美国凯斯西储大学的轴承数据集实验验证，显著提升了模型的效率和准确性，相比于传统的检测方法提高了检测效率和检测准确率。
With the rapid development of industry in recent years, the requirements for the stable operation of mechanical equipment have continuously increased. As a result, ensuring the efficient and smooth operation of machinery has become an important issue. Traditional fault detection methods for mechanical equipment heavily rely on human experience, leading to inefficiency and significant discrepancies in detection results. This paper proposes a bearing fault detection method based on a hybrid deep learning model. The method effectively captures both spatial and temporal features of the bearing signals. Experimental validation using the bearing dataset from Case Western Reserve University in the United States demonstrates a significant improvement in model efficiency and accuracy, enhancing both detection efficiency and accuracy compared to traditional methods.