...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Mechanical systems and signal processing >Condition classification of small reciprocating compressor for refrigerators using artificial neural networks and support vector machines
【24h】

Condition classification of small reciprocating compressor for refrigerators using artificial neural networks and support vector machines

机译：基于人工神经网络和支持向量机的小型冰箱往复式压缩机的状态分类。

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The need to increase machine reliability and decrease production loss due to faulty products in highly automated line requires accurate and reliable fault classification technique. Wavelet transform and statistical method are used to extract salient features from raw noise and vibration signals. The wavelet transform decomposes the raw time-waveform signals into two respective parts in the time space and frequency domain. With wavelet transform prominent features can be obtained easily than from time-waveform analysis. This paper focuses on the development of an advanced signal classifier for small reciprocating refrigerator compressors using noise and vibration signals. Three classifiers, self-organising feature map, learning vector quantisation and support vector machine (SVM) are applied in training and testing for feature extraction and the classification accuracies of the techniques are compared to determine the optimum fault classifier. The classification technique selected for detecting faulty reciprocating refrigerator compressors involves artificial neural networks and SVMs. The results confirm that the classification technique can differentiate faulty compressors from healthy ones and with high flexibility and reliability.
机译：由于高度自动化生产线中的故障产品，需要提高机器可靠性并减少生产损失，这需要准确而可靠的故障分类技术。小波变换和统计方法用于从原始噪声和振动信号中提取显着特征。小波变换将原始时间波形信号分解为时域和频域的两个部分。与时间波形分析相比，使用小波变换可以轻松获得显着特征。本文着重于开发一种用于小型往复式冰箱压缩机的，使用噪声和振动信号的高级信号分类器。自分类特征图，学习矢量量化和支持向量机（SVM）这三个分类器用于特征提取的训练和测试中，并比较了该技术的分类精度，以确定最佳的故障分类器。选择用于检测往复式冰箱压缩机故障的分类技术涉及人工神经网络和SVM。结果证实，该分类技术可以将故障压缩机与正常压缩机区分开，并且具有很高的灵活性和可靠性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号