基于遗传算法改进的OVO TWSVM的机械密封状态研究
|
摘要
针对传统测试方法对实际工况下的密封端面状态识别准确率较低,且识别速度较慢的问题,提出了一种基于遗传算法改进的OVO TWSVM模型对密封状态进行识别。设计了2种工况,针对密封端面的声发射信号,先使用广义S变换对其进行滤波,提取典型时频域特征向量,合理划分训练和测试用例;构建了OVO TWSVM模型,并用遗传算法对其参数进行优化;对比优化前后的模型对样本的识别准确率,结果证明该方法具有更高的识别率,可应用于机械密封的状态识别。
In order to solve the problem of low accuracy and slow recognition speed of traditional test methods in the actual working condition, a novel novel OVO TWSVM model based on genetic algorithm was proposed to identify the sealing state. Two kinds of working conditions were designed. For the acoustic emission signal of the seal end face, generalized S transform was used to filter it, and the typical time-frequency domain feature vectors were extracted, and the training and test cases were divided reasonably. OVO TWSVM model was constructed and its parameters were optimized by genetic algorithm. Comparing the recognition accuracy of the model before and after optimization, the result proves that this method has a higher recognition rate and can be applied to the state recognition of mechanical seals.
In order to solve the problem of low accuracy and slow recognition speed of traditional test methods in the actual working condition, a novel novel OVO TWSVM model based on genetic algorithm was proposed to identify the sealing state. Two kinds of working conditions were designed. For the acoustic emission signal of the seal end face, generalized S transform was used to filter it, and the typical time-frequency domain feature vectors were extracted, and the training and test cases were divided reasonably. OVO TWSVM model was constructed and its parameters were optimized by genetic algorithm. Comparing the recognition accuracy of the model before and after optimization, the result proves that this method has a higher recognition rate and can be applied to the state recognition of mechanical seals.
引文
[1]Fan Y E,Gu F S,Ball A.A review of the condition monitoring of mechanical seals[C]//Proceedings of the 7th Biennial Conference on Engineering Systems Design and Analysis,ESDA 2004,v3:179-184.
[2]孙鑫晖,董翔文,张腾飞,等.声发射在密封监测领域的研究进展[J].润滑与密封,2018,43(6):136-140.
[3]张思聪.基于随机过程的机械密封剩余使用寿命预测[D].成都:西南交通大学,2018.
[4]Huang W F,Li Y B,Gao Z,et al.An acoustic emission study on the starting and stopping processes of a dry gas seal for pumps[J].Tribology Letters,2012,49(2):379-384.
[5]蒋恩超,傅攀,张思聪,等.基于声发射的机械密封状态识别[J].计算机测量与控制,2018,26(8):233-237.
[6]蒋恩超.基于声发射的机械密封端面摩擦状态研究[D].成都:西南交通大学,2018.
[7]朱奥辉,傅攀,陈官林.声发射机械密封端面摩擦状态识别[J].中国测试,2016,42(9):101-104.
[8]刘方园,王水花,张煜东.孪生支持向量机数学模型与应用综述[J].测控技术,2018,37(8):10-15.
[9]业巧林,闫贺.基于最小二乘的孪生有界支持向量机分类算法[J].华中科技大学学报(自然科学版),2018,46(3):30-35.
[10]李晓晖,傅攀,曹伟青,等.机械密封端面接触状态的声发射监测研究[J].振动与冲击,2016,35(8):83-89.
[11]齐韶维.快速孪生支持向量机理论及算法研究[D].西安:西安邮电大学,2018.
[12]邱建坤.基于孪生支持向量机的特征选择与多类分类算法研究[D].秦皇岛:燕山大学,2015.
[13]丁世飞,张健,张谢锴,等.多分类孪生支持向量机研究进展[J].软件学报,2018,29(1):89-108.
[14]Jayadeva,Khemchandani R,Chandra S.Twin support vector machines for pattern classification[J].IEEEtransactions on pattern analysis and machine intelligence,2007,29(5):905-910.
[15]雷德明,严新平.多目标智能优化算法及其应用[M].北京:科学出版社,2009.
[16]蒋恩超,傅攀,张思聪.小波包与GA-SVM在轴承故障诊断中的应用[J].计算机测量与控制,2017,25(10):7-10.
[2]孙鑫晖,董翔文,张腾飞,等.声发射在密封监测领域的研究进展[J].润滑与密封,2018,43(6):136-140.
[3]张思聪.基于随机过程的机械密封剩余使用寿命预测[D].成都:西南交通大学,2018.
[4]Huang W F,Li Y B,Gao Z,et al.An acoustic emission study on the starting and stopping processes of a dry gas seal for pumps[J].Tribology Letters,2012,49(2):379-384.
[5]蒋恩超,傅攀,张思聪,等.基于声发射的机械密封状态识别[J].计算机测量与控制,2018,26(8):233-237.
[6]蒋恩超.基于声发射的机械密封端面摩擦状态研究[D].成都:西南交通大学,2018.
[7]朱奥辉,傅攀,陈官林.声发射机械密封端面摩擦状态识别[J].中国测试,2016,42(9):101-104.
[8]刘方园,王水花,张煜东.孪生支持向量机数学模型与应用综述[J].测控技术,2018,37(8):10-15.
[9]业巧林,闫贺.基于最小二乘的孪生有界支持向量机分类算法[J].华中科技大学学报(自然科学版),2018,46(3):30-35.
[10]李晓晖,傅攀,曹伟青,等.机械密封端面接触状态的声发射监测研究[J].振动与冲击,2016,35(8):83-89.
[11]齐韶维.快速孪生支持向量机理论及算法研究[D].西安:西安邮电大学,2018.
[12]邱建坤.基于孪生支持向量机的特征选择与多类分类算法研究[D].秦皇岛:燕山大学,2015.
[13]丁世飞,张健,张谢锴,等.多分类孪生支持向量机研究进展[J].软件学报,2018,29(1):89-108.
[14]Jayadeva,Khemchandani R,Chandra S.Twin support vector machines for pattern classification[J].IEEEtransactions on pattern analysis and machine intelligence,2007,29(5):905-910.
[15]雷德明,严新平.多目标智能优化算法及其应用[M].北京:科学出版社,2009.
[16]蒋恩超,傅攀,张思聪.小波包与GA-SVM在轴承故障诊断中的应用[J].计算机测量与控制,2017,25(10):7-10.