Predictive Maintenance and Fault Monitoring Enabled by Machine Learning: Experimental Analysis of a TA-48 Multistage Centrifugal Plant Compressor

被引:13
作者
Achouch, Mounia [1 ,2 ,3 ]
Dimitrova, Mariya [1 ]
Dhouib, Rizck [1 ]
Ibrahim, Hussein [1 ,3 ]
Adda, Mehdi [2 ]
Sattarpanah Karganroudi, Sasan [1 ,4 ]
Ziane, Khaled [3 ]
Aminzadeh, Ahmad [1 ]
机构
[1] Technol Inst Ind Maintenance ITMI, 175 Rue Verendrye, Sept Iles, PQ G4R 5B7, Canada
[2] Univ Quebec Rimouski, Dept Math Comp Sci & Engn, Rimouski, PQ G56 3A1, Canada
[3] Ctr Res Innovat Energy Intelligence CR2Ie, 175 Rue Verendrye, Sept Iles, PQ G4R 5B7, Canada
[4] Univ Quebec Trois Rivieres, Dept Mech Engn, Trois Rivieres, PQ G8Z 4M3, Canada
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 03期
关键词
industry; 4; 0; predictive maintenance; machine learning algorithms; fault prediction; Rotary equipment; LSTM neural networks;
D O I
10.3390/app13031790
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
In an increasingly competitive industrial world, the need to adapt to any change at any time has become a major necessity for every industry to remain competitive and survive in their environments. Industries are undergoing rapid and perpetual changes on several levels. Indeed, the latter requires companies to be more reactive and involved in their policies of continuous improvement in order to satisfy their customers and maximize the quantity and quality of production, while keeping the cost of production as low as possible. Reducing downtime is one of the major objectives of these industries of the future. This paper aimed to apply machine learning algorithms on a TA-48 multistage centrifugal compressor for failure prediction and remaining useful life (RUL), i.e., to reduce system downtime using a predictive maintenance (PdM) approach through the adoption of Industry 4.0 approaches. To achieve our goal, we followed the methodology of the predictive maintenance workflow that allows us to explore and process the data for the model training. Thus, a comparative study of different prediction algorithms was carried out to arrive at the final choice, which is based on the implementation of LSTM neural networks. In addition, its performance was improved as the data sets were fed and incremented. Finally, the model was deployed to allow operators to know the failure times of compressors and subsequently ensure minimum downtime rates by making decisions before failures occur.
引用
收藏
页数:19
相关论文
共 30 条
[1]  
Abdulqader D. M., 2020, MACH LEARN, V62, P233, DOI DOI 10.1109/ICSET53708.2021.9612526
[2]   On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges [J].
Achouch, Mounia ;
Dimitrova, Mariya ;
Ziane, Khaled ;
Karganroudi, Sasan Sattarpanah ;
Dhouib, Rizck ;
Ibrahim, Hussein ;
Adda, Mehdi .
APPLIED SCIENCES-BASEL, 2022, 12 (16)
[3]  
airrelief.com, AIR RELIEF AIR RELIE
[4]  
Ali J., 2012, INT J COMPUTER SCI I, V9, P272
[5]   Nonlinear inflation forecasting with recurrent neural networks [J].
Almosova, Anna ;
Andresen, Niek .
JOURNAL OF FORECASTING, 2023, 42 (02) :240-259
[6]   Industry 4.0 technologies assessment: A sustainability perspective [J].
Bai, Chunguang ;
Dallasega, Patrick ;
Orzes, Guido ;
Sarkis, Joseph .
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2020, 229
[7]  
Benedick P.-L, 2022, THESIS U LUXEMBOURG
[8]  
Bholowalia P., 2014, INT J COMPUT APPL, V105, P17, DOI DOI 10.5120/18405-9674
[9]   POINTS OF SIGNIFICANCE Machine learning: a primer [J].
Bzdok, Danilo ;
Krzywinski, Martin ;
Altman, Naomi .
NATURE METHODS, 2017, 14 (12) :1119-1120
[10]   Data mining in predictive maintenance systems: A taxonomy and systematic review [J].
Esteban, Aurora ;
Zafra, Amelia ;
Ventura, Sebastian .
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2022, 12 (05)