计算机科学
人工智能
机器学习
稳健性(进化)
遗忘
断层(地质)
数据挖掘
生物化学
化学
语言学
哲学
基因
地震学
地质学
作者
Jun Zhu,Y. Wang,Cheng‐Geng Huang,Changqing Shen,Bojian Chen
出处
期刊:IEEE Transactions on Instrumentation and Measurement
[Institute of Electrical and Electronics Engineers]
日期:2024-01-01
卷期号:73: 1-14
标识
DOI:10.1109/tim.2023.3330177
摘要
Deep learning has been widely used for fault diagnosis of complex mechanical equipment in recent years. However, fault types keep increasing with the change in the working state of mechanical equipment in practical scenarios, which causes the performance of traditional machine learning models to degrade rapidly. Incremental learning can continuously learn new knowledge from incremental information while retaining previously learned knowledge, effectively enhancing the generalization performance of the model to meet the needs of fault diagnosis in actual industrial scenarios. Moreover, the noise environment will have a certain effect on the performance of the model. Therefore, this paper proposes a new incremental learning method using classification and feature level information, which aims to improve the robustness of the model under noisy condition. First, an adaptive dual-branch residual network is constructed, and weights are assigned through an adaptive algorithm to enable the model to retain old knowledge while learning new knowledge. Then, an adversarial network is used to reduce the differences at the feature level after the samples pass through the model of different phases, which ensures the sustainable learning ability of the model and promotes knowledge transfer between different phases. Meanwhile, catastrophic forgetting is overcome through the knowledge distillation loss. The comparative experimental results show that the proposed method in this paper outperforms the current popular incremental learning method.
科研通智能强力驱动
Strongly Powered by AbleSci AI