|
|
Fault Diagnosis System of Numerical Control Machine Based on Incremental Learning |
ZHANG Yu-ying1,LU Yi1,ZHAO Jing2 |
1. College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou, Zhejang 310018, China
2. Hangzhou Wolei Intelligent Technology Co.Ltd, Hangzhou, Zhejang 310018, China |
|
|
Abstract In order to solve the problem of fault diagnosis when the spindle bearing and tool in numerical control machine malfunction at the same time or working conditions of numerical control machine are changed, a fault diagnosis model named deep convolutional neural network based on incremental learning was proposed. First, the vibration data sets of spindle bearings and tools at common speeds were input into a one-dimensional convolutional neural network, which combined a batch normalization algorithm. Secondly, manually judged the unknown fault type during cross-speed diagnosis, tagged it and re-entered the network. Incremental learning was used to retain old knowledge and learn the characteristics of new data to improve model performance. The fault diagnosis accuracy rate of the model at different speeds is between 76.49% and 86.09%. Compared with the two classic cross-domain algorithms of fine tuning and joint training, deep convolutional neural network based on incremental learning improves accuracy and shortens training time.
|
Received: 09 July 2021
Published: 14 November 2022
|
|
|
|
|
[1]辛梅. 神经网络训练算法在数控机床故障诊断中的应用 [J]. 自动化技术与应用, 2020, 39 (2):13-17.
Xin M. Application of neural network training algorithm in fault diaognosis of NC machine tool[J]. Techniques of Automation and Applications, 2020, 39(2):13-17.
[2]文妍, 谭继文, 李善. 基于多分类器融合与模糊综合评判的滚动轴承故障诊断[J]. 中国科技论文, 2016, 11(4):464-469.
Wen Y, Tan J W, Li S. Fault diagnosis for rolling bearing based on multiple classifiers fusion and fuzzy[J]. China Sciencepaper, 2016, 11(4):464-469.
[3]李正官, 韩天杰, 王超群, 等. 基于VGG-19卷积神经网络的刀具磨损监测方法[J]. 机械设计与制造工程, 2020, 49(6):93-97.
Li Z G, Han T J, Wang C Q, et al. Tool wear monitoring method based on VGG-19 convolution neural network[J]. Machine Design and Manufacturing Engineering, 2020, 49(06):93-97.
[4]时培明, 苏翠娇, 赵娜, 等. 基于AMD和自适应随机共振的旋转机械故障诊断方法研究[J]. 计量学报, 2017, 38(1):112-116.
Shi P M, Su C J, Zhao N, et al. Study on Fault Diagnosis Method for Rotating Machinery Based on Adaptive Stochastic Resonance and AMD[J]. Acta Metrologica Sinica, 2017, 38(1):112-116.
[5]Chen X L, Zhang B Z, Feng F Z, et al. Optimal Resonant Band Demodulation Based on an Improved Correlated Kurtosis and Its Application in Bearing Fault Diagnosis [J]. Sensors, 2017, 17(2):360.
[6]邢婷婷,关阳,孙登云, 等. 基于FSDPC_Otsu算法的滚动轴承故障研究[J]. 计量学报, 2021 42(11):1466-1471.
Xing T T, Guan Y, Sun D Y, et al. Rolling Bearing Fault Diagnosis Based on Clustering by Fast Search and Find of Density Peaks Combined Otsu Method[J]. Acta Metrologica Sinica, 2021 42(11):1466-1471.
[7]戴稳, 张超勇, 孟磊磊,等. 采用深度学习的铣刀磨损状态预测模型 [J]. 中国机械工程, 2020, 31(17):2071-2078.
Dai W, Zhang C Y, Meng L L, et al. Prediction model of milling cutter wear status based on deep learning[J]. China Mechanical Engineering, 2020, 31(17):2071-2078.
[8]陈炳旭. 基于深度卷积循环神经网络的刀具状态监测技术研究[D]. 武汉:华中科技大学, 2019.
[9]鄢小安, 贾民平. 基于改进奇异谱分解的形态学解调方法及其在滚动轴承故障诊断中的应用[J]. 机械工程学报, 2017, 53(7):104-112.
Yan X A, Jia M P. Morphological demodulation method based on improved singular spectrum decomposition and its application in rolling bearing fault diagnosis [J]. Journal of Mechanical Engineering, 2017, 53 (7):104-112.
[10]Zhang W, Li C H, Peng G L, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018, 100:439-453.
[11]陈维兴, 崔朝臣, 李小菁, 等. 基于多种小波变换的一维卷积循环神经网络的风电机组轴承故障诊断[J]. 计量学报, 2021, 42(5):615-622.
Chen W X, Cui C C, Li X J, et al. Bearing Fault Diagnosis of Wind Turbine Based on Multiwavelet-1D Convolutional LSTM [J]. Acta Metrologica Sinica, 2021, 42 (5):615-622.
[12]倪建功, 李娟, 邓立苗, 等. 基于知识蒸馏的胡萝卜外观品质等级智能检测[J]. 农业工程学报, 2020, 36 (18):181-187.
Ni J G, Li J, Deng L M, et al. Intelligent detection of appearance quality of carrot grade using knowledge distillation[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36 (18):181-187.
[13]Chao F, Qing L, Lin H C, et al. Development of Deep Convolutional Neural Network with Adaptive Batch Normalization Algorithm for Bearing Fault Diagnosis[J]. Shock and Vibration, 2020(3):1-10.
[14]Han B K, Ji S S, Wang J R, et al. An intelligent diagnosis framework for roller bearing fault under speed fluctuation condition [J]. Neurocomputing, 2021, 420.
[15]谢胜龙, 张为民, 鲁玉军, 等. 基于一维卷积神经网络的房颤智能诊断方法研究[J]. 计量学报, 2020, 41 (5):620-626.
Xie S L, Zhang W M, Lu Y J, et al. Research on Intelligent Diagnosis of Atrial Fibrillation Based on One-dimensional Convolution Neural Network [J].Acta Metrologica Sinica, 2020, 41 (5):620-626.
[16]孙红, 黄瓯严. 基于知识蒸馏的短文本分类方法[J]. 软件导刊, 2021, 20 (6):23-27.
Sun H, Huang O Y. Short Text Classification Method Based on Knowledge Distillation[J]. Software Guide, 2021, 20 (6):23-27.
[17]邓晓云. 振动诊断技术在数控机床状态监测与故障诊断中应用的研究[D]. 大连:大连交通大学, 2010.
[18]李善, 谭继文, 俞昆, 等. KPCA-GRNN网络在数控机床复合故障诊断中的应用[J]. 煤矿机械, 2016,37 (3):152-154.
Li S, Tan J W, Yu K, et al. Application of KPCA-GRNN Network in Complex Fault of CNC Machine[J]. Coal Mine Machinery, 2016, 37 (3):152-154. |
|
|
|