基于多特征融合分析的设备故障状态智能分类方法  

Intelligent Classification Method for Equipment Fault Status Based on Multi Feature Fusion Analysis

作　　者：赖治平 王旭 黄育尚 陈昌邦 LAI Zhi-ping;WANG Xu;HUANG Yu-shang;CHEN Chang-bang(Nanning rail transit operation Co.,LTD.,Nanning 530029;Nanning Rail Transit Co.,Ltd.,Nanning 530029;Baosight Software(Guangxi)Co.,LTD.,Nanning 530200)

机构地区：[1]南宁轨道交通运营有限公司,南宁530029 [2]南宁轨道交通集团有限责任公司,南宁530029 [3]宝信软件(广西)有限公司,南宁530200

出　　处：《环境技术》2024年第9期118-124,共7页Environmental Technology

摘　　要：设备复杂度的增加和自动化水平的提高,设备故障的发生频率和类型也日益增多,导致生产中断、产品质量下降,甚至引发安全事故。在此背景下,研究一种基于多特征融合分析的设备故障状态智能分类方法。通过集成多种传感器和数据采集设备,实现对设备运行状态的全面监控和实时数据采集。从采集数据中挖掘出对故障分类具有关键价值的特征向量并通过分配权重实现多特征融合。在此基础上,构建基于多分类支持向量机的分类模型,通过训练和优化模型参数,使其能够准确识别并分类各种复杂的设备故障。结果表明:所研究方法应用下,绝大部分测试样本与实际的故障类别重合,极少部分被错误分类,由此证明了所研究方法的准确性。The increase in equipment complexity and automation level has led to an increasing frequency and types of equipment failures,resulting in production interruptions,product quality degradation,and even safety accidents.In this context,a method for intelligent classification of equipment fault states based on multi feature fusion analysis is studied.By integrating multiple sensors and data acquisition devices,comprehensive monitoring and real-time data collection of device operating status can be achieved.Extract feature vectors with key value for fault classification from collected data and achieve multi feature fusion by assigning weights.On this basis,a classification model based on multi class support vector machine is constructed.By training and optimizing the model parameters,it can accurately identify and classify various complex equipment faults.The results showed that under the application of the research method,the vast majority of test samples overlapped with the actual fault categories,and a very small number were misclassified,thus proving the accuracy of the research method.

关 键 词：多特征融合分析 设备故障状态 多分类支持向量机 智能分类方法 运行状态 

分 类 号：TP20.88[自动化与计算机技术—检测技术与自动化装置]