A Predictive Maintenance Model Using Recurrent Neural Networks

One of the main goals of Industry 4.0 is to anticipate machine breakdowns. Being able to prevent failures is important because downtime implies high cost and production loss. For this reason, the calculation of the number of remaining cycles or Remaining Useful Life (RUL) until a breakdown occurs is essential for machine maintenance. The calculation of the RUL should be based on previous observations, if possible under the same conditions. Research on RUL estimation has become central to the development of systems that monitor the current state of machines. Although this field has been studied in-depth, there is no single universal method. The lack of a universal method is the motivation behind this proposal in which the designed system uses recurrent neural networks (RNN) in a predictive maintenance problem.

[1]  Seyed Abbas Taher,et al.  Estimation of magnitude and time duration of temporary overvoltages using ANN in transmission lines during power system restoration , 2010, Simul. Model. Pract. Theory.

[2]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[3]  Juan M. Corchado,et al.  Use of Gamification Techniques to Encourage Garbage Recycling. A Smart City Approach , 2018, KMO.

[4]  Juan M. Corchado,et al.  Energy Optimization Using a Case-Based Reasoning Strategy , 2018, Sensors.

[5]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[6]  Lindley R. Higgins,et al.  Maintenance Engineering Handbook , 1967 .

[7]  Inés Sittón-Candanedo,et al.  Machine Learning Predictive Model for Industry 4.0 , 2018, KMO.

[8]  L. Swanson.  Linking maintenance strategies to performance , 2001 .

[9]  Hung-Cuong Trinh,et al.  An Empirical Investigation on a Multiple Filters-Based Approach for Remaining Useful Life Prediction , 2018 .

[10]  Huisheng Zhang,et al.  A novel prognostic model of performance degradation trend for power machinery maintenance , 2014 .

[11]  Javier Prieto,et al.  Semantic Analysis System for Industry 4.0 , 2018, KMO.

[12]  K. R. Krishnanand,et al.  Detection, classification, and location of faults in power transmission lines , 2015 .

[13]  Juan M. Corchado,et al.  Social computing in currency exchange , 2019, Knowledge and Information Systems.

[14]  Juan M. Corchado,et al.  Case-Based Reasoning and Agent Based Job Offer Recommender System , 2018, SOCO-CISIS-ICEUTE.

[15]  Benoît Iung,et al.  A proactive condition-based maintenance strategy with both perfect and imperfect maintenance actions , 2015, Reliab. Eng. Syst. Saf..

[16]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[17]  Man Gyun Na,et al.  Auto-tuned PID controller using a model predictive control method for the steam generator water level , 2001 .

[18]  Fernando de la Prieta,et al.  Human-Computer Interaction in Currency Exchange , 2018, KMO.