Abstract: In recent years, deep learning has been widely applied and has made remarkable progress in many fields because of its unique advantages and potential in feature extraction and pattern recognition. Its application in fault diagnosis and prognosis of complex industrial systems is an emerging field. This paper starts with an overview of deep learning, including deep learning methods-based application, platforms and useful tools. Five frequently-used deep learning models are introduced in this work, including Auto-Encoder（AE）, Deep Belief Networks（DBN）, Convolutional neural networks（CNN）, Recurrent Neural Network（RNN） and Generative Adversarial Network（GAN）. The application research based on deep learning in fault diagnosis and prognosis are systematically discussed in three aspects, research background, implementation process and research dynamics, and the current related literatures published in this field in recent years are reviewed. Problems, challenges and solutions of deep learning in the application of fault diagnosis and prognosis are discussed from the point view of research practice. The future research directions are also prospected at the end of this work.

Key words: deep learning, feature extraction, fault diagnosis, fault prognosis

摘要： 近年来，深度学习以其在特征提取与模式识别方面独特优势与潜力被广泛应用于众多领域，已取得显著进展，其在复杂工业系统故障诊断与预测中的研究属于新兴领域。对近年来深度学习及其在各领域发展的优秀综述文献以及主流的开源仿真工具平台进行了整理，同时介绍了五种典型的深度学习模型，包括自动编码器（Auto-Encoder，AE）、 深度置信网络（Deep Belief Networks，DBN）、 卷积神经网络（Convolutional Neural Networks，CNN）、 循环神经网络（Recurrent Neural Network，RNN）、生成对抗网络（Generative Adversarial Network，GAN）；从研究背景、实现流程及研究动态等三个方面就深度学习在故障诊断与预测中的应用研究进行了归纳总结，对近年来这一领域发表的相关论文进行了系统的综述；从研究实际出发探讨了深度学习在故障诊断与预测领域应用中存在的问题、挑战及解决方法，并对未来值得继续研究的方向进行了展望。

关键词: 深度学习, 特征提取, 故障诊断, 故障预测