Diagnosis of Diesel Engine Based on Oil Analysis Using Convolutional Neural Network and Visualization

Document Type : Dynamics, Vibrations, and Control

Authors

1 Corresponding author: Assistant Professor, Department of Industrial Engineering, Imam Hossein University, Tehran, Iran

2 Assistant Professor, Department of Industrial Engineering, University of Applied Science & Technology, Karaj, Iran

3 M.Sc., Department of Industrial Engineering, Imam Hossein University, Tehran, Iran

Abstract

Oil condition monitoring is an effective method for detecting abnormal erosions or defects in mechanical equipment and systems. One of the issues in the field of condition monitoring with the help of oil analysis is the cost and time required to inspect all samples by an expert. However, not all oil analysis samples need to be reviewed by an expert, and less than 10% of this data indicates a critical situation that requires rapid planning and action. The goal of this article is to turn the oil status into an image so that you can quickly identify the oil status by looking at the image. Also, by processing these images by software, the state of failure can be extracted through artificial intelligence. In this research, the data are taken from the sample test of motor oils of road construction rollers. First, the data were converted to gray scale images using baseline for diesel engines and through MATLAB software. In the next step, these images are processed using the convolutional neural network method to determine the oil status. Comparison of the obtained results showed that the visualization of the oil analysis results helps to understand the general condition of the oil for the user and the critical samples and the need for action are identified more quickly among the mass of oil samples.

Highlights

  • Providing a model for equipment health monitoring using oil analysis results
  • Visualization of equipment status based on oil analysis results
  • Image processing with convolutional neural network to identify critical samples 

Keywords

Smiley face

References

[1] Akl SY, Abd El-Ghafar S, Mosleh H, editors. An Experimental Investigation of Industrial Gearbox Condition Using Wear Particle Analysis Technique. ASME International Mechanical Engineering Congress and Exposition; 2016: American Society of Mechanical Engineers.##
[2] Ramezani S, Masoudi A, Memariani A. Application of data mining in determining the baseline lines of engine erosion behavior. Iranian Journal Of Supply Chain Management 2011;13(31).##
[3] Alizadeh D, Ahmadi H. Condition Monitoring of Diesel Engine via Oil Analysis Using Fuzzy Logic. Engine Research. 2022;19(19):9-18.##
[4] Bekana D, Antoniev A, Zach M, Mareček J. Monitoring of agricultural machines with used engine oil analysis. Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis. 2015;63(1):15-22.##
[5] Chaharsooghi SK, Nabavi A, Teimourpour B. Prediction model of remaining operating time until critical state based on engine oil analysis records with data mining solution. Logistics Thought. 2020;18(70):77-96.##
[6] Dowling NE. Mechanical Behavior of Materials eBook: International Edition: Pearson Higher Ed; 2013.##
[7] Haghparast A, Momeni A, Gord A, Mansoori F. Imaged financial Ratios and Bankruptcy Prediction using Convolutional Neural Networks. Financial Engineering and Portfolio Management. 2021;12(46):558-75.##
[8] Hirri A, Tagourmate S, Benamar A, Kzaiber F, Oussama A. Prediction of kinematic viscosity in motor oil using ftir coupled with partial least squares regression. Int J Chem Mater Environ Res. 2017;4(1):102-7.##
[9] Isa MC, Yusoff N, Nain H, Yati MSD, Muhammad M, Nor IM. Ferrographic analysis of wear particles of various machinery systems of a commercial marine ship. Procedia Engineering. 2013;68:345-51.##
[10] Król A, Gocman K, Giemza B. Neural networks as a tool to characterise oil state after porous bearings prolonged tests. Materials Science. 2015;21(3):466-72.##
[11] Kumar A, Ghosh SK. Oil condition monitoring for HEMM–a case study. Industrial Lubrication and Tribology. 2016.##
[12] Li L, Chang W, Zhou S, Xiao Y, editors. An identification and prediction model of wear-out fault based on oil monitoring data using PSO-SVM method. 2017 Annual Reliability and Maintainability Symposium (RAMS); 2017: IEEE.##
[13] Raposo H, Farinha JT, Fonseca I, Galar D. Predicting condition based on oil analysis–A case study. Tribology International. 2019;135:65-74.##
[14] Rauscher MS, Tremmel AJ, Schardt M, Koch AW. Non-dispersive infrared sensor for online condition monitoring of gearbox oil. Sensors. 2017;17(2):399.##
[15] RodRigues J, Costa I, Farinha JT, Mendes M, Margalho L. Predicting motor oil condition using artificial neural networks and principal component analysis. Eksploatacja i Niezawodność. 2020;22(3).##
[16] Sejkorová M, Glos J. Analysis of degradation of motor oils used in Zetor tractors. Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, volume 65, issue: 1. 2017.##
[17] Sidorov O. Artificial color constancy via GoogleNet with angular loss function. Applied Artificial Intelligence. 2020;34(9):643-55.##
[18] Yu S, Zhao D, Chen W, Hou H. Oil-immersed power transformer internal fault diagnosis research based on probabilistic neural network. Procedia Computer Science. 2016;83:1327-31.##
[19] Castresana J, Gabiña G, Martin L, Basterretxea A, Uriondo Z. Marine diesel engine ANN modelling with multiple output for complete engine performance map. Fuel. 2022;319:123873.##
[20] Karatuğ Ç, Arslanoğlu Y. Development of condition-based maintenance strategy for fault diagnosis for ship engine systems. Ocean Engineering. 2022;256:111515.##
[21] Chaki S, Biswas TK. An ANN-entropy-FA model for prediction and optimization of biodiesel-based engine performance. Applied Soft Computing. 2023;133:109929.##
[22] Wang J, Li T, Sun C, Yan R, Chen X. Improved spiking neural network for intershaft bearing fault diagnosis. Journal of Manufacturing Systems. 2022;65:208-19.##
[23] Kang H, Ma H. Fault detection and isolation of actuator failures in jet engines using adaptive dynamic programming. Applied Mathematics and Computation. 2022;414:126664.##
[24] Calvo-Bascones P, Sanz-Bobi MA. Advanced Prognosis methodology based on behavioral indicators and Chained Sequential Memory Neural Networks with a diesel engine application. Computers in Industry. 2023;144:103771.##
Aerospace Mechanics
Volume 19, Issue 3 - Serial Number 73
Serial No. 73, Autumn Quarterly
December 2023
Pages 123-136

Files

History

  • Receive Date: 06 December 2022
  • Revise Date: 12 February 2023
  • Accept Date: 16 March 2023
  • Publish Date: 21 April 2023

Share

How to cite

Statistics