基于深度学习的锂电池褶皱检测方法的研究
|
摘要
为了解决锂电池褶皱检测问题,提出基于深度学习的褶皱检测方法。CNN是在实际应用中最成功的深度神经网络,能够很好地实现分类。提出CNN来解决锂电池褶皱检测的方法:收集锂电池X光照片;人工把锂电池X光照片分为无褶皱和有褶皱两种,并标注;将数据集放入构建的CNN模型中训练学习。在数据集充足的情况下,通过大量实验表明:该方法的准确率能够达到99%,相对于原始的凭借经验、人工观察检测的方法有很大提升。
In order to solve the problem of lithium battery wrinkle detection,we proposed a wrinkle detection method based on deep learning. CNN is the most successful deep neural network in practical applications. It can achieve good classification. CNN was put forward to solve the problem of lithium battery wrinkle detection. We collected the X-ray photo of the lithium battery. The X-ray photo of the lithium battery was manually divided into two types: no wrinkles and wrinkles,and we marked them. The data set was put into the constructed CNN model for training and learning. With sufficient data sets,a large number of experiments have shown that the accuracy of the CNN-based lithium battery wrinkle detection method can reach 99%. Compared with the original experience,and manual observation and detection methods,it has been a big improvement.
In order to solve the problem of lithium battery wrinkle detection,we proposed a wrinkle detection method based on deep learning. CNN is the most successful deep neural network in practical applications. It can achieve good classification. CNN was put forward to solve the problem of lithium battery wrinkle detection. We collected the X-ray photo of the lithium battery. The X-ray photo of the lithium battery was manually divided into two types: no wrinkles and wrinkles,and we marked them. The data set was put into the constructed CNN model for training and learning. With sufficient data sets,a large number of experiments have shown that the accuracy of the CNN-based lithium battery wrinkle detection method can reach 99%. Compared with the original experience,and manual observation and detection methods,it has been a big improvement.
引文
[1]詹茵茵,邓积微,王太宏.属性约简的气胀锂电池在线检测方法[J].电源技术,2015,39(4):736-748.
[2]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[3]Krizhevsky A,Sutskever I,Hinton G E.Image Net classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems.Curran Associates Inc.2012:1097-1105.
[4]Sermanet P,Eigen D,Zhang X,et al.Over Feat:Integrated Recognition,Localization and Detection using Convolutional Networks[C]//Image Net Large Scale Visual Recognition Challenge 2013(ILSVRC2013),2013.
[5]Simonyan K,Zisserman A.Very Deep Convolutional Networks for Large-Scale Image Recognition[EB].ar Xiv:1409.1556,2014.
[6]Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2015.
[7]He K,Zhang X,Ren S,et al.Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2016:770-778.
[8]杨云,杜飞.深度学习实战[M].北京:清华大学出版社,2018.
[9]郑群花,段慧芳,沈尧,等.基于卷积神经网络和迁移学习的乳腺癌症病理图像分类[J].计算机应用与软件,2018,35(7):237-242.
[10]Bergstra J,Breuleux O,Bastien F,et al.Theano:a CPUand GPU math expression compiler[C]//Proceedings of the Python for Scientific Computing Conference(Sci Py),2010.
[11]张良均,杨海宏,何子健,等.Python与数据挖掘[M].北京:机械工业出版社,2016.
[12]孙正军.基于图像边缘提取的电池极片瑕疵检测研究[D].湖南:中南大学,2009.
[13]肖安邦.基于机器视觉的锂电池检测系统开发[D].哈尔滨:哈尔滨工业大学,2007.
[14]Sato M,Horie K,Hara A,et al.Application of deep learning to the classification of images from colposcopy:[J].Oncology Letters,2018,15(3):3518-3523.
[15]Li B,Hu X.Effective vehicle logo recognition in real-world application using mapreduce based convolutional neural networks with a pre-training strategy[J].Journal of Intelligent&Fuzzy Systems,2018,34(3):1985-1994.
[16]邓红莉,杨韬.一种基于深度学习的异常检测方法[J].信息通信,2015(3):3-4.
[17]韩洪伟,赵晓云.基于机器视觉的高速切片机锂电池极片在线检测系统设计[J].电源世界,2017(5):34-36.
[18]杨保亮,杨守良.基于STM32和PWM的锂离子电池检测系统设计和研究[J].现代电子技术,2018,41(12):120-123.
[2]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[3]Krizhevsky A,Sutskever I,Hinton G E.Image Net classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems.Curran Associates Inc.2012:1097-1105.
[4]Sermanet P,Eigen D,Zhang X,et al.Over Feat:Integrated Recognition,Localization and Detection using Convolutional Networks[C]//Image Net Large Scale Visual Recognition Challenge 2013(ILSVRC2013),2013.
[5]Simonyan K,Zisserman A.Very Deep Convolutional Networks for Large-Scale Image Recognition[EB].ar Xiv:1409.1556,2014.
[6]Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2015.
[7]He K,Zhang X,Ren S,et al.Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2016:770-778.
[8]杨云,杜飞.深度学习实战[M].北京:清华大学出版社,2018.
[9]郑群花,段慧芳,沈尧,等.基于卷积神经网络和迁移学习的乳腺癌症病理图像分类[J].计算机应用与软件,2018,35(7):237-242.
[10]Bergstra J,Breuleux O,Bastien F,et al.Theano:a CPUand GPU math expression compiler[C]//Proceedings of the Python for Scientific Computing Conference(Sci Py),2010.
[11]张良均,杨海宏,何子健,等.Python与数据挖掘[M].北京:机械工业出版社,2016.
[12]孙正军.基于图像边缘提取的电池极片瑕疵检测研究[D].湖南:中南大学,2009.
[13]肖安邦.基于机器视觉的锂电池检测系统开发[D].哈尔滨:哈尔滨工业大学,2007.
[14]Sato M,Horie K,Hara A,et al.Application of deep learning to the classification of images from colposcopy:[J].Oncology Letters,2018,15(3):3518-3523.
[15]Li B,Hu X.Effective vehicle logo recognition in real-world application using mapreduce based convolutional neural networks with a pre-training strategy[J].Journal of Intelligent&Fuzzy Systems,2018,34(3):1985-1994.
[16]邓红莉,杨韬.一种基于深度学习的异常检测方法[J].信息通信,2015(3):3-4.
[17]韩洪伟,赵晓云.基于机器视觉的高速切片机锂电池极片在线检测系统设计[J].电源世界,2017(5):34-36.
[18]杨保亮,杨守良.基于STM32和PWM的锂离子电池检测系统设计和研究[J].现代电子技术,2018,41(12):120-123.