基于改进SOM神经网络的农机液压系统故障诊断方法
|
摘要
随着农业机械液压系统复杂度的提升,其故障发生率也逐渐增加。液压系统是农业机械的核心,准确诊断农业机械液压系统的故障是十分重要的。针对目前农业机械液压系统故障诊断准确率低的问题,提出一种基于改进SOM神经网络的故障诊断方法。该方法利用SOM神经网络的自组织性实现输入数据的无监督聚类,然后基于BP网络进一步提升聚类性能。实验结果表明,该方法能够有效实现农业机械液压系统的故障诊断,对4种典型农业机械液压故障的综合诊断正确率达到93%。
With the increase of the complexity of the hydraulic system of agricultural machinery, its failure rate is gradually increasing. Hydraulic system is the core of agricultural machinery. It is very important to diagnose the fault of hydraulic system of agricultural machinery accurately. Aiming at the problem of low accuracy of fault diagnosis in hydraulic system of agricultural machinery, a fault diagnosis method based on improved SOM neural network was proposed in this paper. This method used the self-organization of SOM neural network to realize unsupervised clustering of input data, and then further improved the clustering performance based on BP network. The experimental results showed that the method could effectively realize the fault diagnosis of the hydraulic system of agricultural machinery, and the accuracy rate of the comprehensive diagnosis of four typical hydraulic faults of agricultural machinery reached 93%.
With the increase of the complexity of the hydraulic system of agricultural machinery, its failure rate is gradually increasing. Hydraulic system is the core of agricultural machinery. It is very important to diagnose the fault of hydraulic system of agricultural machinery accurately. Aiming at the problem of low accuracy of fault diagnosis in hydraulic system of agricultural machinery, a fault diagnosis method based on improved SOM neural network was proposed in this paper. This method used the self-organization of SOM neural network to realize unsupervised clustering of input data, and then further improved the clustering performance based on BP network. The experimental results showed that the method could effectively realize the fault diagnosis of the hydraulic system of agricultural machinery, and the accuracy rate of the comprehensive diagnosis of four typical hydraulic faults of agricultural machinery reached 93%.
引文
[1] 王光明, 张晓辉, 朱思洪, 等. 拖拉机液压机械无级变速箱换段过程液压故障诊断[J]. 农业工程学报, 2015, 31(6): 25-34.Wang Guangming, Zhang Xiaohui, Zhu Sihong, et al. Hydraulic failure diagnosis of tractor hydro-mechanical continuously variable transmission in shifting process [J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(6): 25-34.
[2] Belletti B, Rinaldi M, Bussettini M, et al. Characterising physical habitats and fluvial hydromorphology: A new system for the survey and classification of river geomorphic units [J]. Geomorphology, 2017, 283: 143-157.
[3] Zhang C, Yang M, Li J. Detailed modeling and parameters optimization analysis on governing system of hydro-turbine generator unit [J]. IET Generation Transmission & Distribution, 2018, 12(5): 1045-1051.
[4] 孙焕新, 边辉. 卷取卸卷小车液压升降故障分析与处理[J]. 机床与液压, 2018, 46(10): 141-142.Sun Huanxin, Bian Hui. Fault analysis and treatment for hydraulic lifting system of stripper car [J]. Machine Tool & Hydraulics, 2018, 46(10): 141-142.
[5] Zhou L, Kai S U, Zhou Y, et al. Hydro-mechanical coupling analysis of pervious lining in high pressure hydraulic tunnel [J]. Journal of Hydraulic Engineering, 2018, 49(3): 313-322.
[6] Vásquez S, Kinnaert M, Pintelon R. Active fault diagnosis on a hydraulic pitch system based on frequency-domain identification [J]. IEEE Transactions on Control Systems Technology, 2017, 27(3): 1-16.
[7] 贺湘宇, 何清华. 基于有源自回归模型与模糊C-均值聚类的挖掘机液压系统故障诊断[J]. 吉林大学学报(工学版), 2008, 38(1): 183-187.He Xiangyu, He Qinghua. Fault diagnosis for excavator hydraulic system based on auto-regressive with extra inputs model and fuzzy C-means clustering [J]. Journal of Jilin University (Engineering and Technology Edition), 2008, 38(1): 183-187.
[8] Wen L, Li X, Gao L, et al. A new convolutional neural network-based data-driven fault diagnosis method [J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998.
[9] 张浩, 王国伟, 苑超, 等. 基于AIGA-BP神经网络的粮食产量预测研究[J]. 中国农机化学报, 2016, 37(6): 205-209.Zhang Hao, Wang Guowei, Yuan Chao, et al. Research on forecast of grain production based on AIGA-BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2016, 37(6): 205-209.
[10] 王笑岩, 王石. 基于BP神经网络的辽宁省农机总动力预测[J]. 中国农机化学报, 2015, 36(2): 314-317.Wang Xiaoyan, Wang Shi. Prediction on total power of agricultural machinery in Liaoning Province based on BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2015, 36(2): 314-317.
[11] 尤文坚, 叶雪英, 唐仕云. 基于径向基神经网络农机数量预测的研究[J]. 中国农机化学报, 2013, 34(2): 128-132.Jou Wenjian, Ye Xueying, Tang Shiyun. Research on forecast of the number of agricultural machinery based on RBF neural network [J]. Journal of Chinese Agricultural Mechanization, 2013, 34(2): 128-132.
[12] 王丽艳, 郭树国. 基于BP神经网络玉米蛋白粉吸水性的预测[J]. 中国农机化学报, 2013, 34(6): 125-128.Wang Liyan, Guo Shuguo. Water absorption index prediction for corn gluten meal based on BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2013, 34(6): 125-128.
[13] 鲁敏, 岑红蕾, 王洪坤. 基于LM-BP的新疆玛纳斯灌区用水量预测[J]. 中国农机化学报, 2014, 35(2): 75-77.Lu Min, Yan Honglei, Wang Hongkun.Prediction of Xinjiang manas irrigation area water consumption based on LM-BP [J]. Journal of Chinese Agricultural Mechanization, 2014, 35(2): 75-77.
[14] Jiang H, Wang R, Gao Z, et al. Classification of weld defects based on the analytical hierarchy process and Dempster-Shafer evidence theory [J]. Journal of Intelligent Manufacturing, 2017(6): 1-12.
[2] Belletti B, Rinaldi M, Bussettini M, et al. Characterising physical habitats and fluvial hydromorphology: A new system for the survey and classification of river geomorphic units [J]. Geomorphology, 2017, 283: 143-157.
[3] Zhang C, Yang M, Li J. Detailed modeling and parameters optimization analysis on governing system of hydro-turbine generator unit [J]. IET Generation Transmission & Distribution, 2018, 12(5): 1045-1051.
[4] 孙焕新, 边辉. 卷取卸卷小车液压升降故障分析与处理[J]. 机床与液压, 2018, 46(10): 141-142.Sun Huanxin, Bian Hui. Fault analysis and treatment for hydraulic lifting system of stripper car [J]. Machine Tool & Hydraulics, 2018, 46(10): 141-142.
[5] Zhou L, Kai S U, Zhou Y, et al. Hydro-mechanical coupling analysis of pervious lining in high pressure hydraulic tunnel [J]. Journal of Hydraulic Engineering, 2018, 49(3): 313-322.
[6] Vásquez S, Kinnaert M, Pintelon R. Active fault diagnosis on a hydraulic pitch system based on frequency-domain identification [J]. IEEE Transactions on Control Systems Technology, 2017, 27(3): 1-16.
[7] 贺湘宇, 何清华. 基于有源自回归模型与模糊C-均值聚类的挖掘机液压系统故障诊断[J]. 吉林大学学报(工学版), 2008, 38(1): 183-187.He Xiangyu, He Qinghua. Fault diagnosis for excavator hydraulic system based on auto-regressive with extra inputs model and fuzzy C-means clustering [J]. Journal of Jilin University (Engineering and Technology Edition), 2008, 38(1): 183-187.
[8] Wen L, Li X, Gao L, et al. A new convolutional neural network-based data-driven fault diagnosis method [J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998.
[9] 张浩, 王国伟, 苑超, 等. 基于AIGA-BP神经网络的粮食产量预测研究[J]. 中国农机化学报, 2016, 37(6): 205-209.Zhang Hao, Wang Guowei, Yuan Chao, et al. Research on forecast of grain production based on AIGA-BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2016, 37(6): 205-209.
[10] 王笑岩, 王石. 基于BP神经网络的辽宁省农机总动力预测[J]. 中国农机化学报, 2015, 36(2): 314-317.Wang Xiaoyan, Wang Shi. Prediction on total power of agricultural machinery in Liaoning Province based on BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2015, 36(2): 314-317.
[11] 尤文坚, 叶雪英, 唐仕云. 基于径向基神经网络农机数量预测的研究[J]. 中国农机化学报, 2013, 34(2): 128-132.Jou Wenjian, Ye Xueying, Tang Shiyun. Research on forecast of the number of agricultural machinery based on RBF neural network [J]. Journal of Chinese Agricultural Mechanization, 2013, 34(2): 128-132.
[12] 王丽艳, 郭树国. 基于BP神经网络玉米蛋白粉吸水性的预测[J]. 中国农机化学报, 2013, 34(6): 125-128.Wang Liyan, Guo Shuguo. Water absorption index prediction for corn gluten meal based on BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2013, 34(6): 125-128.
[13] 鲁敏, 岑红蕾, 王洪坤. 基于LM-BP的新疆玛纳斯灌区用水量预测[J]. 中国农机化学报, 2014, 35(2): 75-77.Lu Min, Yan Honglei, Wang Hongkun.Prediction of Xinjiang manas irrigation area water consumption based on LM-BP [J]. Journal of Chinese Agricultural Mechanization, 2014, 35(2): 75-77.
[14] Jiang H, Wang R, Gao Z, et al. Classification of weld defects based on the analytical hierarchy process and Dempster-Shafer evidence theory [J]. Journal of Intelligent Manufacturing, 2017(6): 1-12.