半监督学习用于工业故障检测和诊断:系统性审查
José Miguel Ramírez-Sanz1, Jose-Alberto Maestro-Prieto1, Álvar Arnaiz-González1
1Universidad de Burgos, Avda. Cantabria s/n, Burgos, 09006, Burgos, Spain.
ISA transactions
|October 1, 2023
概括
半监督学习 (SSL) 通过使用有限的标记数据来增强工业故障检测和诊断 (FDD) 的机器学习 (ML). 本综述整理了FDD的SSL方法,为现实应用提供了最佳实践.
科学领域:
- 工业自动化 工业自动化
- 机器学习 机器学习
- 数据科学数据科学数据科学
背景情况:
- 故障检测和诊断 (FDD) 对行业至关重要,机器学习 (ML) 方法是领先的竞争者.
- 传统的ML方法包括监督和无监督的学习,但在工业环境中经常与稀缺的标记数据作斗争.
研究的目的:
- 系统地审查和组织关于半监督学习 (SSL) 的现有文献,用于FDD应用.
- 为了识别FDD域内使用最多和最少的SSL算法.
- 为在工业FDD中实施SSL提供实际建议.
主要方法:
- 对FDD的SSL方法进行文献审查和系统组织.
- 基于van Engelen & Hoos.的分类法进行SSL算法的分类.
- 分析与故障检测任务和数据集结构相关的算法使用情况.
主要成果:
- 对于FDD来说,SSL是一个有前途的解决方案,特别是在标记数据稀缺的地方.
- 确定了不同SSL算法的普及程度及其适用于各种FDD任务的适用性.
- 突出了在FDD研究中遇到的常见数据集结构.
结论:
- 在工业环境中,SSL具有显著的潜力,可以提高基于ML的FDD系统的准确性.
- 为FDD实践实施SSL的最佳实践建议,以减轻常见的工业故障.
- 本综述为未来在FDD中进行SSL研究提供了基础的理解和路线图.
相关概念视频
01:25Distribution Reliability and Automation
123
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
123
01:21Power System Three-Phase Short Circuits
103
Determining the subtransient fault current in a power system involves representing transformers by their leakage reactances, transmission lines by their equivalent series reactances, and synchronous machines as constant voltage sources behind their subtransient reactances. In this analysis, certain elements are excluded, such as winding resistances, series resistances, shunt admittances, delta-Y phase shifts, armature resistance, saturation, saliency, non-rotating impedance loads, and small...
103