分类器(UML)
渐进式学习
计算机科学
人工智能
机器学习
涡轮机
遗忘
数据挖掘
故障检测与隔离
训练集
风力发电
特征提取
模式识别(心理学)
状态监测
过程(计算)
非参数统计
进化算法
特征(语言学)
迭代和增量开发
决策树
支持向量机
断层(地质)
数据采集
统计分类
作者
Zhiyi He,Ya Gao,Haidong Shao,Shen Yan,Ming Zeng
标识
DOI:10.1177/14759217261423448
摘要
In industrial settings, it is important to diagnose new faults from the updated data stream. The model that learns incrementally by taking in new data can meet this requirement. However, the problems of time-consuming iterative updates and catastrophic forgetting in traditional incremental learning methods greatly reduce the diagnostic efficiency. To solve these problems, this paper introduces a replay-free evolutionary classifier (RFEC) architecture. The core of this strategy is to optimize the classification decision process by reconstructing the association between classification weights and feature vectors, with effective constraints on the objective function. Also, a nonparametric prototype classifier is introduced to ensure timely online fault diagnosis. This classifier uses classification prototypes and initial weights to allow quick updates during later incremental phases. The experimental results of the wind turbine simulation experimental platform show that RFEC has better accuracy and real-time update efficiency than other popular incremental learning methods. Specifically, it achieves an average accuracy of 90.57% and a dramatically reduced total training time of approximately 0.06 seconds during the incremental update stage.
科研通智能强力驱动
Strongly Powered by AbleSci AI