学习迁移
一般化
计算机科学
人工智能
适应(眼睛)
机器学习
构造(python库)
断层(地质)
原始数据
领域(数学分析)
传输(计算)
卷积神经网络
领域(数学)
边际分布
模式识别(心理学)
数据挖掘
数学
并行计算
地震学
数学分析
程序设计语言
纯数学
地质学
物理
光学
统计
随机变量
作者
Zhijian Wang,Xinxin He,Bin Yang,Naipeng Li
出处
期刊:IEEE Transactions on Industrial Electronics
[Institute of Electrical and Electronics Engineers]
日期:2021-09-03
卷期号:69 (8): 8430-8439
被引量:164
标识
DOI:10.1109/tie.2021.3108726
摘要
Due to the data distribution discrepancy, fault diagnosis models, trained with labeled data in one scene, likely fails in classifying by unlabeled data acquired from the other scenes. Transfer learning is capable to generalize successful application trained in one scene to the fault diagnosis in the other scenes. However, the existing transfer methods do not pay much attention to reduce adaptively marginal and conditional distribution biases, and also ignore the degree of contribution between both biases and among network layers, which limit classification performance and generalization in reality. To overcome these weaknesses, we establish a new fault diagnosis model, called subdomain adaptation transfer learning network (SATLN). First, two convolutional building blocks were stacked to extract transferable features from raw data. Then, the pseudo label learning is amended to construct target subdomain of each class. Furthermore, a subdomain adaptation is combined with domain adaptation to reduce both marginal and conditional distribution biases simultaneously. Finally, a dynamic weight term is applied for adaptive adjustment of the contributions from both discrepancies and each network layers. The SATLN method is tested with six transfer tasks. The results demonstrate the effectiveness and superiority of the SATLN in the cross-domain fault diagnosis field.
科研通智能强力驱动
Strongly Powered by AbleSci AI