参数优化SAE方法及在轴承故障诊断的应用
|
摘要
稀疏自动编码(Sparse Auto Encoder, SAE)通过寻找一组"超完备"基向量用于挖掘输入数据的内在结构与模式,使得高层输出能够更好的表达输入样本的类别信息,其良好的降维性能受到广泛关注并逐渐应用在机械设备故障诊断中。然而,SAE模型中隐含层特征数直接影响高层输出对低层输入模式的表达效果,简单的设置隐含层特征数难以取得理想的识别效果,针对该问题,利用萤火虫寻优算法的优点,确定各个隐含层的最优特征数,从而确定最优的SAE模型。轴承仿真及故障状态识别实验证明,隐含层特征数确定之后的稀疏自动编码模型在不同测试样本数目下均能取得比浅层结构及随机参数SAE模型更好的识别效果,得到更高的识别正确率。
Sparse Auto Encoder(SAE) finds a set of "super-complete" base vectors to mine the intrinsic structure and pattern of input data, which enables high-level output to better express the category information of input samples. Its good performance of dimension reduction has been widely concerned and gradually applied in fault diagnosis of mechanical equipment. However, the feature number of hidden layer in SAE model directly affects the expression effect of high-level output on low-level input mode. Simply setting the feature number of hidden layer is difficult to achieve ideal recognition effect. Aiming at this problem, the optimal feature number of each hidden layer is determined by using the advantages of the firefly learning algorithm, and the optimal SAE model is determined. Bearing simulation and fault state recognition experiments show that sparse automatic coding model can achieve better recognition effect than shallow structure and random parameter SAE model under different test samples after the number of hidden layer features is determined, and the recognition accuracy is higher.
Sparse Auto Encoder(SAE) finds a set of "super-complete" base vectors to mine the intrinsic structure and pattern of input data, which enables high-level output to better express the category information of input samples. Its good performance of dimension reduction has been widely concerned and gradually applied in fault diagnosis of mechanical equipment. However, the feature number of hidden layer in SAE model directly affects the expression effect of high-level output on low-level input mode. Simply setting the feature number of hidden layer is difficult to achieve ideal recognition effect. Aiming at this problem, the optimal feature number of each hidden layer is determined by using the advantages of the firefly learning algorithm, and the optimal SAE model is determined. Bearing simulation and fault state recognition experiments show that sparse automatic coding model can achieve better recognition effect than shallow structure and random parameter SAE model under different test samples after the number of hidden layer features is determined, and the recognition accuracy is higher.
引文
[1]Hinton,G.E and Salakhutdinov,R.Reducing the Dimensionality of Data with Neural Networks.[J].Science,2006,313:504-507.
[2]Hinton,G.E,Osindero.S,Y.W.A Fast Learning Algorithm for Deep Belief Nets.[J].Neural Computation,2006,18(7):1527-1554.
[3]Yoshua Bengio.Learning Deep Architectures for AI.[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.
[4]Hugo Larochelle,Michael Mandel,Razvan Pascanu,et al.Learning Algorithms for the Classification Restricted Boltzman Machine.[J].The Journal of Machine Learning Research,2012,13:643-669.
[5]Yoshua Bengio,Pascal Lamblin,Dan Popovici,et al.Greedy Layer-Wise Training of Deep Networks.[C].Advances in Neural Information Processing Systems19(NIPS’06),2007:153-160.
[6]Honglak Lee,Roger Grosse,Rajesh Ranganath,et al.Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks.[J].Communications of The ACM,2011,54:95-103.
[7]Feng Li,Loc Tran,Kim-Han Thung,et al.Robust Deep Learning for Improved Classification of AD/MCIPatients[J].Machine Learning in Medical Imaging,Lecture Notes in Computer Science,2014,8679:240-247.
[8]Xiaonan Hu,Qihe Liu,Hongbin Cai,et al.Gas Recognition Under Sensor Drift by Using Deep Learning.[J].Practical Applications of Intelligent Systems Advances in Intelligent Systems and Computing,2014,279:23-33.
[9]深度学习:推进人工智能的梦想[EB/OL].http://www.csdn.net/article/2013-05-29/2815479,2013.Deep Learning:Advancing the Dream of Artificial Intelligence[EB/OL].http://www.csdn.net/article/2013-05-29/2815479,2013.
[10]Adam项目展示微软研究院人工智能领域新突破[EB/OL].http://blog.sina.com.cn/s/blog_4caedc7a0102ux ma.html,2014.Adam Project Show Microsoft Research New Breakthroughs in Artificial Intelligence Field[EB/OL].http://blog.sina.com.cn/s/blog_4caedc7a0102uxma.html,2014.
[11]谷歌4亿美元收购人工智能公司Deep Mind[EB/OL].http://tech.sina.com.cn/i/2014-01-27/09259131393.shtml,2014.Google Takeover the Artificial Intelligence Company of Deep Mind for$400 Million[EB/OL].http://tech.sina.com.cn/i/2014-01-27/09259131393.shtml,2014.
[12]P Tamilselvan,P Wang.Failure Diagnosis Using Deep Belief Learning based Health State Classification.[J].Relia-bility Engineering and System Safety,2013,115:124-135.
[13]V.T Tran,F.AThobiani,A Ball.An Approach to Fault Diagnosis of Rciprocating Compressor Valves Using Teager-Kaiser Energy Operator and Deep Belief Networks.[J].Expert Systems with Applications,2014,41:4 113-4 122.
[14]Lei Y G,Jia F,Zhou X,et al.A Deep Learning-based Method for Machinery Health Monitoring with Big Data[J].Chinese Journal of Mechanical Engineering,2015,51(21),pp.49-56.
[15]Jia F.,Lei Y G,Lin J.,Zhou X,Lu N Deep Neural Networks:A Promising Tool for Fault Characteristic Mining and Intelligent Diagnosis of Rotating Machinery with Massive Data[J].Mechanical Systems and Signal Processing,2016,72-73:303-315
[16]谢吉朋.云平台下基于深度学习的高速列车走行部故障诊断技术研究[D].西南交通大学,2015.Xie J P.Research on Fault Diagnosis of High Speed Running Gear Based on Deep Learning under Cloud Platform[D].Xi’an:Southwest Jiaotong University,2015.
[17]Ren L,Cui J,Sun Y Q,et al.Multi-bearing Remaining Useful Life Collaborative Prediction:A Deep Learning approach[J].Journal of Manufacturing Systems,2017,43:248-256
[18]Jiateng Yin,Wentian Zhao,Fault Diagnosis Network Design for Vehicle on-board Equipments of High-speed Railway:A Deep Learning Approach[J].Engineering Appli-cations of Artificial Intelligence,2016,56:250-259
[19]王宪保,李洁,姚明海,等.基于深度学习的太阳能电池片表面缺陷检测方法[J].模式识别与人工智能,2014,27:517-523.Wang X B,Li J,Yao M H,et al.Solar Cells Surface Defects Detection Based on Deep Learning[J].Pattern Recognition and Artificial Intelligence,2014,27:517-523.
[20]COATES A,NG A Y,LEE H.An Analysis of Singlelayer Networks in Unsupervised Feature Learning[J].Journal of Machine Learning Research,2011,15:215-223.
[21]Yang X S.Firefly Algorithms for Multimodal Optimization[J].Stochastic Algorithms:Foundations and Applications,2009,5792:169-178.
[22]Y.F.WANG,P.J.KOOTSOOKOS.Modeling of Low Shaft Speed Bearing Faults for Condition Monitoring[J].Mechanical Systems and Signal Processing,1998,12(3):415-426.
[2]Hinton,G.E,Osindero.S,Y.W.A Fast Learning Algorithm for Deep Belief Nets.[J].Neural Computation,2006,18(7):1527-1554.
[3]Yoshua Bengio.Learning Deep Architectures for AI.[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.
[4]Hugo Larochelle,Michael Mandel,Razvan Pascanu,et al.Learning Algorithms for the Classification Restricted Boltzman Machine.[J].The Journal of Machine Learning Research,2012,13:643-669.
[5]Yoshua Bengio,Pascal Lamblin,Dan Popovici,et al.Greedy Layer-Wise Training of Deep Networks.[C].Advances in Neural Information Processing Systems19(NIPS’06),2007:153-160.
[6]Honglak Lee,Roger Grosse,Rajesh Ranganath,et al.Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks.[J].Communications of The ACM,2011,54:95-103.
[7]Feng Li,Loc Tran,Kim-Han Thung,et al.Robust Deep Learning for Improved Classification of AD/MCIPatients[J].Machine Learning in Medical Imaging,Lecture Notes in Computer Science,2014,8679:240-247.
[8]Xiaonan Hu,Qihe Liu,Hongbin Cai,et al.Gas Recognition Under Sensor Drift by Using Deep Learning.[J].Practical Applications of Intelligent Systems Advances in Intelligent Systems and Computing,2014,279:23-33.
[9]深度学习:推进人工智能的梦想[EB/OL].http://www.csdn.net/article/2013-05-29/2815479,2013.Deep Learning:Advancing the Dream of Artificial Intelligence[EB/OL].http://www.csdn.net/article/2013-05-29/2815479,2013.
[10]Adam项目展示微软研究院人工智能领域新突破[EB/OL].http://blog.sina.com.cn/s/blog_4caedc7a0102ux ma.html,2014.Adam Project Show Microsoft Research New Breakthroughs in Artificial Intelligence Field[EB/OL].http://blog.sina.com.cn/s/blog_4caedc7a0102uxma.html,2014.
[11]谷歌4亿美元收购人工智能公司Deep Mind[EB/OL].http://tech.sina.com.cn/i/2014-01-27/09259131393.shtml,2014.Google Takeover the Artificial Intelligence Company of Deep Mind for$400 Million[EB/OL].http://tech.sina.com.cn/i/2014-01-27/09259131393.shtml,2014.
[12]P Tamilselvan,P Wang.Failure Diagnosis Using Deep Belief Learning based Health State Classification.[J].Relia-bility Engineering and System Safety,2013,115:124-135.
[13]V.T Tran,F.AThobiani,A Ball.An Approach to Fault Diagnosis of Rciprocating Compressor Valves Using Teager-Kaiser Energy Operator and Deep Belief Networks.[J].Expert Systems with Applications,2014,41:4 113-4 122.
[14]Lei Y G,Jia F,Zhou X,et al.A Deep Learning-based Method for Machinery Health Monitoring with Big Data[J].Chinese Journal of Mechanical Engineering,2015,51(21),pp.49-56.
[15]Jia F.,Lei Y G,Lin J.,Zhou X,Lu N Deep Neural Networks:A Promising Tool for Fault Characteristic Mining and Intelligent Diagnosis of Rotating Machinery with Massive Data[J].Mechanical Systems and Signal Processing,2016,72-73:303-315
[16]谢吉朋.云平台下基于深度学习的高速列车走行部故障诊断技术研究[D].西南交通大学,2015.Xie J P.Research on Fault Diagnosis of High Speed Running Gear Based on Deep Learning under Cloud Platform[D].Xi’an:Southwest Jiaotong University,2015.
[17]Ren L,Cui J,Sun Y Q,et al.Multi-bearing Remaining Useful Life Collaborative Prediction:A Deep Learning approach[J].Journal of Manufacturing Systems,2017,43:248-256
[18]Jiateng Yin,Wentian Zhao,Fault Diagnosis Network Design for Vehicle on-board Equipments of High-speed Railway:A Deep Learning Approach[J].Engineering Appli-cations of Artificial Intelligence,2016,56:250-259
[19]王宪保,李洁,姚明海,等.基于深度学习的太阳能电池片表面缺陷检测方法[J].模式识别与人工智能,2014,27:517-523.Wang X B,Li J,Yao M H,et al.Solar Cells Surface Defects Detection Based on Deep Learning[J].Pattern Recognition and Artificial Intelligence,2014,27:517-523.
[20]COATES A,NG A Y,LEE H.An Analysis of Singlelayer Networks in Unsupervised Feature Learning[J].Journal of Machine Learning Research,2011,15:215-223.
[21]Yang X S.Firefly Algorithms for Multimodal Optimization[J].Stochastic Algorithms:Foundations and Applications,2009,5792:169-178.
[22]Y.F.WANG,P.J.KOOTSOOKOS.Modeling of Low Shaft Speed Bearing Faults for Condition Monitoring[J].Mechanical Systems and Signal Processing,1998,12(3):415-426.