Benchmarking Deep Neural Network Architectures for Machining Tool Anomaly Detection

被引:2
作者
Puranik, Tejas [1 ]
Gharbi, Aroua [1 ]
Bagdatli, Burak [1 ]
Fischer, Olivia Pinon [1 ]
Mavris, Dimitri N. [1 ]
机构
[1] Georgia Inst Technol, Daniel Guggenheim Sch Aerosp Engn, 620 Cherry St,ESM G-10, Atlanta, GA 30332 USA
来源
SMART AND SUSTAINABLE MANUFACTURING SYSTEMS | 2020年 / 4卷 / 02期
关键词
condition monitoring; deep learning; anomaly detection; fault detection; classification; architecture benchmarking; WEAR;
D O I
10.1520/SSMS20190039
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
With the democratization of cyber-physical systems, edge computing, and large-scale data infrastructure, the volume of operational data available is continuously increasing. One of the significant challenges in current industrial research is defining a robust and scalable approach for machine health monitoring and anomaly detection. The methods that exist for such purposes rely extensively on feature engineering and are strongly dependent on the expertise of the operator, hence limiting their generalization. Deep learning techniques, on the other hand, are known to automate feature engineering and allow complex abstractions to be learned, making them particularly suitable for machine health monitoring. This paper presents a benchmarking of deep neural network architectures for the identification of machining tool anomalies on a lathe machine. The features are generated using indirect metrics such as sensor data and process variables from the machine controller, but without direct metrics like surface roughness or finished part quality. The ability of different architectures to identify incipient anomalies in tool quality is compared. A detailed treatment of various subsets of features is provided along with their relative importance to identify the minimum required parameters for accurately identifying the tool anomaly for each architecture considered. Finally, a recommendation is provided based on the results obtained on the type of architecture that is appropriate for the identification of machining tool anomalies. It is expected that the embeddings of the training data learned by the chosen network can be used for other learning tasks, such as transfer learning to another machine or anomaly type. The methodology described in this paper lends itself well to continuous monitoring through the use of scalable robust models and appropriate units of analysis for each model.
引用
收藏
页码:121 / 145
页数:25
相关论文
共 27 条
[1]  
Aggarwal C.C., 2018, Neural networks and deep learning: A textbook, DOI [DOI 10.1007/978-3-319-94463-0, 10.1007/978-3-319-94463-0]
[2]  
Analog Devices, 2004, ADXL103 ADXL203
[3]  
[Anonymous], 2016, P ANN C PROGN HLTH M
[4]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[5]   Predicting tool wear with multi-sensor data using deep belief networks [J].
Chen, Yuxuan ;
Jin, Yi ;
Jiri, Galantu .
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2018, 99 (5-8) :1917-1926
[6]   Deep learning for time series classification: a review [J].
Fawaz, Hassan Ismail ;
Forestier, Germain ;
Weber, Jonathan ;
Idoumghar, Lhassane ;
Muller, Pierre-Alain .
DATA MINING AND KNOWLEDGE DISCOVERY, 2019, 33 (04) :917-963
[7]  
Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1
[8]   A survey on Deep Learning based bearing fault diagnosis [J].
Hoang, Duy-Tang ;
Kang, Hee-Jun .
NEUROCOMPUTING, 2019, 335 :327-335
[9]   Tool wear monitoring using naive Bayes classifiers [J].
Karandikar, Jaydeep ;
McLeay, Tom ;
Turner, Sam ;
Schmitz, Tony .
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2015, 77 (9-12) :1613-1626
[10]   A review on the application of deep learning in system health management [J].
Khan, Samir ;
Yairi, Takehisa .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2018, 107 :241-265