Prediction of electric power performance of the exhaust waste heat recovery system of an automobile with thermoelectrical generator under real driving conditions by means of machine learning algorithms

被引:0
作者
Celik, Ahmet [1 ]
Kunt, M. Akif [2 ]
Gunes, Haluk [2 ]
机构
[1] Kutahya Dumlupinar Univ, Tavsanli Vocat Sch, Dept Comp Technol, Kutahya, Turkiye
[2] Kutahya Dumlupinar Univ, Tavsanli Vocat Sch, Dept Motor Vehicles & Transportat Technol, Kutahya, Turkiye
关键词
Thermoelectric generator; waste heat recovery; electricity generation; machine learning; prediction; smart car systems;
D O I
10.1177/09544089231218112
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
In internal combustion engines, approximately 40% of the thermal power obtained from fuel burning is thrown out to the environment from the exhaust system. Implementations of waste heat recovery systems with thermoelectrical generator over exhaust system have become widespread as it is the waste heat resource with the highest temperature in a vehicle. During literature research, experiments related to waste heat recovery under real road conditions are very few and no study on estimation of system performance by machine learning algorithms has been found; therefore, Toyota Corolla has designed an air-cooled waste heat recovery system using 3 thermoelectrical generators for the exhaust system of the automobile. During the road tests, temperature and electric power generation values obtained as per gear, vehicle speed and engine speed have been recorded. In the study, a dataset consisting of 10 attributes was created with each record as a result of the path test. Using this dataset, Random Forest, Support Vector Machine (SVM) and Naive Bayes machine learning algorithms estimated the electrical power to be generated from the thermoelectric generator recovery system. In the study, 7 electric power classification estimates were made. In the estimation process, 76% of the dataset was used for training and 24% was used for testing. In terms of estimation success; an estimation success of 96.6% has been achieved by Random Forest method; 94.6% by Support Vector Machine (SVM) method; and 76.7% by Naive Bayes method. The results show that prospective electricity generation estimation can be achieved with high level of accuracy.
引用
收藏
页码:1873 / 1883
页数:11
相关论文
共 48 条
[1]  
Akhtar Z, 2020, SN Computer Science, V1, DOI [10.1007/s42979-020-00145-8, 10.1007/s42979-020-00145-8, DOI 10.1007/S42979-020-00145-8]
[2]   Stock Market Prediction with Gaussian Naive Bayes Machine Learning Algorithm [J].
Ampomah, Ernest Kwame ;
Nyame, Gabriel ;
Qin, Zhiguang ;
Addo, Prince Clement ;
Gyamfi, Enoch Opanin ;
Gyan, Michael .
INFORMATICA-AN INTERNATIONAL JOURNAL OF COMPUTING AND INFORMATICS, 2021, 45 (02) :243-256
[3]  
Khripach NA, 2015, BIOSCI BIOTECH RES A, V12, P375, DOI 10.13005/bbra/2213
[4]   The linear random forest algorithm and its advantages in machine learning assisted logging regression modeling [J].
Ao, Yile ;
Li, Hongqi ;
Zhu, Liping ;
Ali, Sikandar ;
Yang, Zhongguo .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2019, 174 :776-789
[5]  
Balaban M.E., 2018, Veri Madenciligi ve Makine Ogrenmesi Temel Algoritmalari ve R Dili ile Uygulamalari, VSecond
[6]  
BELOVSKI I, 2018, INT SYMP ELECTR APP, P1
[7]  
Birkholz U., 1988, Proceedings of the 7th International Conference on Thermoelectric Energy Conversion, P124
[8]   Review of thermoelectric generation for internal combustion engine waste heat recovery [J].
Burnete, Nicolae Vlad ;
Mariasiu, Florin ;
Depcik, Christopher ;
Barabas, Istvan ;
Moldovanu, Dan .
PROGRESS IN ENERGY AND COMBUSTION SCIENCE, 2022, 91
[9]  
Çelik A, 2022, Mühendislik Bilimleri ve Tasarım Dergisi, V10, P1212, DOI 10.21923/jesd.976865
[10]   Improved naive Bayes classification algorithm for traffic risk management [J].
Chen, Hong ;
Hu, Songhua ;
Hua, Rui ;
Zhao, Xiuju .
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2021, 2021 (01)