| 基于自适应增强SVM集成算法的风机故障诊断 |
| |
| 引用本文： | 杨宏晖,陈兆基,戴键. 基于自适应增强SVM集成算法的风机故障诊断[J]. 测控技术, 2010, 29(7): 72-74 |
| |
| 作者姓名： | 杨宏晖 陈兆基 戴键 |
| |
| 作者单位： | 西北工业大学,航海学院,陕西,西安,710072;西北工业大学,航海学院,陕西,西安,710072;西北工业大学,航海学院,陕西,西安,710072 |
| |
| 基金项目： | 西北工业大学教育教学改革研究基金 |
| |
| 摘 要： | 提出了自适应增强支持向量机集成算法,并结合风机噪声信号的人耳听觉谱特征,对风机故障进行分类识别.现场实测数据的识别实验证明,该算法可正确识别99%的正常机器,并且对故障类型诊断的正确识别率比单个支持向量机分类器高1.88%～2.50%.
|
| 关 键 词： | 自适应增强支持向量机集成 人耳听觉谱特征 风机故障诊断 |
Fault Diagnosis for Fan Based on Serf-Adaptive Boosting SVM Ensemble |
| |
| YANG Hong-hui,CHEN Zhao-ji,DAI Jian. Fault Diagnosis for Fan Based on Serf-Adaptive Boosting SVM Ensemble[J]. Measurement & Control Technology, 2010, 29(7): 72-74 |
| |
| Authors: | YANG Hong-hui CHEN Zhao-ji DAI Jian |
| |
| Abstract: | A self-adaptive enhanced support vector machine ensemble method is proposed.The proposed novel method combined with auditory spectrum feature is applied to identify of fan fault.The identification experiments of field measurement data proved that the proposed method is effective for fan fault diagnosis.The classification accuracy of normal fans is about 99%,and the classification accuracy of the type of faulty fans of proposed SVM ensemble method is 1.88%~2.50% higher than single SVM classifier. |
| |
| Keywords: | self-adaptive support vector machine ensemble auditory spectrum feature fault diagnosis of fan |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《测控技术》浏览原始摘要信息 |
|
点击此处可从《测控技术》下载全文 |
|
