Detecting machine malfunctions at an early stage is crucial for reducing interruptions in operational processes within industrial settings. Recently, the deep learning approach has started to be preferred for the detection of failures in machines. Deep learning provides an effective solution in fault detection processes thanks to automatic feature extraction. In this study, a deep learning-based system was designed to analyze the sound signals produced by industrial machines. Acoustic sound signals were converted into Mel spectrograms. For the purpose of classifying spectrogram images, the DenseNet-169 model, a deep learning architecture recognized for its effectiveness in image classification tasks, was used. The model was trained using the transfer learning method on the MIMII dataset including sounds from four types of industrial machines. The results showed that the proposed method reached an accuracy rate varying between 97.17% and 99.87% at different Sound Noise Rate levels.
Generalized Out-of-distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning
Zhejiang University and the University of Illinois Urbana–Champaign Joint Institute（浙江大学与伊利诺伊大学厄巴纳-香槟分校联合研究院）；College of Computer Science and Technology in Zhejiang University（浙江大学计算机科学与技术学院）
Graph Neural Network-Based Semi-Supervised Open-Set Fault Diagnosis for Marine Machinery Systems
Intelligent Transportation School, Zhejiang Institute of Communications, China（浙江交通学院智能交通学院）；Center for Applied Intelligent Systems Research, Halmstad University, Sweden（哈马碧大学应用智能系统研究中心）
Advancing machine fault diagnosis: A detailed examination of convolutional neural networks
Wroclaw University of Science and Technology（弗罗茨瓦夫理工大学）；University of Ottawa（渥太华大学）；Sant Longowal Institute of Engineering and Technology（桑特隆戈瓦尔工程技术学院）
Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation
ZJU-UIUC Joint Institute at Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所）；ZJU-UoE Institute at Zhejiang University（浙江大学-爱丁堡大学联合研究所）；College of Biomedical Engineering and Instrument Science at Zhejiang University（浙江大学生物医学工程与仪器科学学院）；College of Computer Science and Technology in Zhejiang University（浙江大学计算机科学与技术学院）
Bearing fault diagnosis under varying working condition based on domain adaptation
China University of Mining and Technology（中国矿业大学）
传统的滚动轴承智能故障诊断方法都是基于一个共同的假设，即带标签的训练数据（源域）和未带标签的测试数据（目标域）来自同一个分布。当分布发生变化时，大多数故障诊断模型需要使用新收集的标记训练数据从头开始重建。然而，注释大量的训练数据来重建这样的新模型是昂贵的或不可能的。同时，大量的标记训练数据还没有被充分利用，这显然是一种资源浪费。领域自适应（DA）是迁移学习的重要研究方向之一，其目标是充分利用来自源域和目标域的信息，最大限度地减小不同领域分布之间的差异，从而最大限度地减小跨领域预测误差。在本文中，我们提出了一个第一次研究的无监督DA在滚动轴承故障诊断领域中的变化的工作条件和一种新的诊断策略，提出了基于无监督DA使用子空间对齐（SA）。经过带模拟退火的无监督DA处理后，训练数据和测试数据的分布趋于接近，用训练数据训练的分类器可以对测试数据进行分类。对Case Western Reserve基准数据中60个变工况下的领域自适应诊断问题和新数据中12个变工况下的领域自适应诊断问题的实验结果表明了该方法的有效性。该方法不仅能有效区分轴承故障类型，而且能有效区分故障严重程度。
Toward Multimodal Industrial Fault Analysis: A Single-Speed Chain Conveyor Dataset with Audio and Vibration Signals
Digital Innovation Research Center, Duke Kunshan University（杜克昆山大学数字创新研究中心）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）
AeroGPT: Leveraging Large-Scale Audio Model for Aero-Engine Bearing Fault Diagnosis
School of Physics and Astronomy, The University of Edinburgh（爱丁堡大学物理与天文学学院）；Glasgow College, University of Electronic Science and Technology of China（电子科技大学格拉斯哥学院）；Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（香港理工大学电子与电气工程系）；Department of Systems Engineering, City University of Hong Kong（香港城市大学系统工程系）；School of Mechanical Engineering, Northwestern Polytechnical University（西北工业大学机械工程学院）；Department of Industrial Engineering, Tsinghua University（清华大学工业工程系）；City University of Hong Kong Shenzhen Research Institute（香港城市大学深圳研究院）
