A Predictive Maintenance Application for A Robot Cell using LSTM Model

被引：3

作者：

Joseph, Doyel ^{[1
]}

Gallege, Tilani ^{[1
]}

Bekar, Ebru Turanoglu ^{[1
]}

Dudas, Catarina ^{[2
]}

Skoogh, Anders ^{[1
]}

机构：

[1] Chalmers Univ Technol, Dept Ind & Mat Sci, S-41296 Gothenburg, Sweden

[2] Volvo Cars AB, Dept Adv Analyt & AI, Gothenburg, Sweden

来源：

IFAC PAPERSONLINE | 2022年 / 55卷 / 19期

关键词：

Smart Maintenance; Predictive Maintenance; Machine Learning; Long Short-Term Memory (LSTM); CRISP-DM; Industrial Robots; Manufacturing;

D O I：

10.1016/j.ifacol.2022.09.193

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Maintaining equipment is critical for increasing production capacity and decreasing production time. With the advent of digitalization, industries are able to access massive amounts of data that can be used to ensure their long-term viability and competitive advantage by implementing predictive maintenance. Therefore, this study aims to demonstrate a predictive maintenance application for a robot cell using real-world manufacturing big data coming from a company in the automotive industry. A hyperparameter tuned Long Short-Term Memory (LSTM) model is developed, and the results show that this model is capable of predicting the day of failure with good accuracy. The difficulties inherent in conducting real-world industrial initiatives are analyzed, and recommendations for improvement are presented. Copyright (C) 2022 The Authors.

引用

页码：115 / 120

页数：6

共 21 条

[1] Degradation curves integration in physics-based models: Towards the predictive maintenance of industrial robots [J].

Aivaliotis, P. ;

Arkouli, Z. ;

Georgoulias, K. ;

Makris, S. .

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2021, 71

[2] A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders [J].

Bampoula, Xanthi ;

Siaterlis, Georgios ;

Nikolakis, Nikolaos ;

Alexopoulos, Kosmas .

SENSORS, 2021, 21 (03) :1-14

[3] Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling [J].

Baptista, Marcia ;

Sankararaman, Shankar ;

de Medeiros, Ivo. P. ;

Nascimento, Cairo, Jr. ;

Prendinger, Helmut ;

Henriques, Elsa M. P. .

COMPUTERS & INDUSTRIAL ENGINEERING, 2018, 115 :41-53

[4]

Bilbao Imanol, 2017, 2017 Eighth International Conference on Intelligent Computing and Information Systems (ICICIS). Proceedings, P173, DOI 10.1109/INTELCIS.2017.8260032

[5]

Chollet F., 2015, Keras

[6] An ARIMA supply chain model [J].

Gilbert, K .

MANAGEMENT SCIENCE, 2005, 51 (02) :305-310

[7] A recurrent neural network based health indicator for remaining useful life prediction of bearings [J].

Guo, Liang ;

Li, Naipeng ;

Jia, Feng ;

Lei, Yaguo ;

Lin, Jing .

NEUROCOMPUTING, 2017, 240 :98-109

[8]

Johnson C. R., 2010, CAE WORKSHOP INSIDER

[9]

Joseph D., 2021, STUDY REMAINING USEF

[10] A Machine Learning Based Health Indicator Construction in Implementing Predictive Maintenance: A Real World Industrial Application from Manufacturing [J].

Kurrewar, Harshad ;

Bekar, Ebru Turanouglu ;

Skoogh, Anders ;

Nyqvist, Per .

ADVANCES IN PRODUCTION MANAGEMENT SYSTEMS: ARTIFICIAL INTELLIGENCE FOR SUSTAINABLE AND RESILIENT PRODUCTION SYSTEMS (APMS 2021), PT III, 2021, 632 :599-608

← 1 2 3 →