Self-Adaptive Alarm Method for Equipment Condition Based on One-Class Support Vector Machine

您当前的位置：

首页 >

文章列表页 >

Self-Adaptive Alarm Method for Equipment Condition Based on One-Class Support Vector Machine

更新时间：2025-07-09

- Self-Adaptive Alarm Method for Equipment Condition Based on One-Class Support Vector Machine
- Vol. 43, Issue 11, Pages: 61-65(2009)
- 作者机构：
  
  1. 西安交通大学机械工程学院,西安,710049
  2. 西安交通大学机械制造系统工程国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：
  CLC： TH165.3
- Online First：10 November 2009，
  
  Published：2009
- 稿件说明：
移动端阅览
Self-Adaptive Alarm Method for Equipment Condition Based on One-Class Support Vector Machine[J]. 2009, 43(11): 61-65.
DOI：

Self-Adaptive Alarm Method for Equipment Condition Based on One-Class Support Vector Machine[J]. 2009, 43(11): 61-65. DOI：

摘要

为了提高对异常状态识别的适应性和有效性

提出了一种基于一类支持向量机的设备状态自适应报警方法.该方法使用一类支持向量机的在线算法

动态估计监测参数在高维特征空间中的最优分布区域

将新数据与上一时刻分布区域的相对距离作为异常指标

描述监测参数的统计特征变化

辨识出设备的异常状态.通过对仿真数据的报警效果分析

以及将该方法应用于对加热炉风机的振动监测中

得到的异常报警结果能够满足实际监测的需要

证明该方法具有异常的识别敏感性、缓慢劣化包容性和状态迁移适应性的特点.

Abstract

To improve the adaptability and effectiveness of recognition on abnormal condition

a self-adaptive alarm method for equipment condition based on one-class support vector machine(OC-SVM)is proposed. The optimum distribution area of monitoring parameters in high-dimensional feature space is dynamically estimated with on-line algorithm of OC-SVM. The abnormal index

determined by the relative distance between the new data and the distribution area at the previous moment

describes the statistical feature variation of monitoring parameters and identifies the abnormal condition of the equipments. The characteristics

such as the sensitivity in abnormal condition recognition

the toleration in slow deterioration and the adaptability in condition alternation

are verified by simulation data. The present method is further applied to the vibration monitoring of heating furnace fan. The alarms under the actual abnormal condition meet the demand of equipment monitoring.

关键词

Keywords

references

徐敏.设备故障诊断手册 [M].西安:西安交通大学出版社,1998:1045-1060.

FRANK P M. Residual evaluation for fault diagnosis based on adaptive fuzzy thresholds [C]∥IEE Colloquium on Qualitative and Quantitative Modeling Methods for Fault Diagnosis. London, UK: IEE Press, 1995:1-11.

BERNHARD S, JOHN C P, JOHN S T, et al. Estimating the support of a high-dimensional distribution [J]. Neural Computation, 2001, 13(7): 1443-1471.

DELPJINE P, PHILIPPE V, EMMANUEL D, et al. An abrupt change detection algorithm for buried landmines localization [J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(2):260-272.

胡桥,何正嘉,訾艳阳,等.基于模糊支持矢量数据描述的早期故障智能监测诊断 [J]. 机械工程学报,2005,41(12):145-150.

HU Qiao, HE Zhengjia, ZI Yanyang, et al. Incipient fault intelligent monitoring and diagnosis based on fuzzy support vector data description[J]. Chinese Journal of Mechanical Engineering, 2005, 41(12): 145-150.

钟清流,蔡自兴.基于OCSVM-CPSO的自适应故障诊断 [J]. 计算机工程与应用,2007,43(8):18-20.

ZHONG Qinliu, CAI Zixing. Self-adaptive fault-diagnoses based on OCSVM-CPSO [J]. Computer Engineering and Applications, 2007, 43(8): 18-20.

GERT C, TOMASO P. Incremental and decremental support vector machine learning [M]. Cambridge, MA,UK: MIT Press, 2001:409-415.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Effects of Steam Addition on the Swirl Combustion and Emission Characteristics of Cracked Ammonia

A Structure-Semantics-Residual Collaborative Image Compression Framework：Towards Privacy Protection and High-Fidelity Reconstruction

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

I/O Performance Modeling and Prediction Method for Large-Scale Parallel Applications Using Machine Learning

Diffusion Characteristics and Influencing Factors in Case of Hydrogen Leakage from Fuel Cell Vehicles Running in Tunnels

Related Author

No data

Related Institution

No data

⁰