| 杨磊， 李郝林， 迟玉伦.基于自适应模糊神经网络的砂轮磨损评估[J].轻工机械,2020,38(6):72-76 |
| 基于自适应模糊神经网络的砂轮磨损评估 |
| Wear Evaluation of Grinding Wheel Based on Adaptive Fuzzy Neural Network |
| |
| DOI：10.3969/j.issn.1005 2895.2020.06.014 |
| 中文关键词: 砂轮磨损 自适应模糊神经网络 多特征信号样本 在线评估 |
| 英文关键词:grinding wheel wear adaptive fuzzy neural network multiple characteristic signal sample online evaluation |
| 基金项目: |
|
| 摘要点击次数: 845 |
| 全文下载次数: 950 |
| 中文摘要: |
| 为实现砂轮磨损状态的实时监测评估，课题组提出了使用自适应模糊神经网络模型对砂轮状态进行监测。通过对磨削过程的振动信号及声发射信号特征值的提取，获得了不同磨损程度砂轮的多特征信号样本；采用多特征信号样本对自适应模糊神经网络进行学习与训练，建立了砂轮磨损状态识别模型；实现了对砂轮磨损状态的准确识别与在线监测。实验表明：基于自适应模糊神经网络的砂轮磨损程度评估系统，测试样本的实际磨损程度和网络判别结果类别相符。该自适应模糊神经网络系统能够对砂轮磨损程度类型准确进行在线评估。 |
| 英文摘要: |
| In order to realize the real time monitoring and evaluation of the wear status of the grinding wheel, an adaptive fuzzy neural network model was proposed to monitor the status of the grinding wheel. By extracting the characteristic values of vibration signals and acoustic emission signals during the grinding process, multiple characteristic signal samples of grinding wheels with different degrees of wear were obtained. The adaptive fuzzy neural network was learned and trained by using the multiple characteristic signal samples to establish the grinding wheel wear status identification model. The accurate identification and online monitoring of the wear status of the grinding wheel were realized. The experiments show that the actual wear degree of the test sample is consistent with the classification of the result identified by the grinding wheel wear degree evaluation system based on adaptive fuzzy neural network. The adaptive fuzzy neural network system can accurately evaluate the type of grinding wheel wear degree online. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
