UDC 631.372: 004.8
DOI 10.36461/NP.2023.66.2.002
DETERMINATION OF AN EFFECTIVE MACHINE LEARNING ALGORITHM FOR PREDICTING OPERATING MODES OF DIESEL ENGINE
S.V. Kalachin1, Doctor of Engineering Sciences, Associate Professor; K.Z. Kukhmazov1, Doctor of Engineering Sciences, Professor; I.A. Murog2, Doctor of Engineering Sciences, Professor
1Federal State Budgetary Educational Institution of Higher Education "Penza State Agrarian University", Penza, Russia, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
2Federal State Budgetary Educational Institution of Higher Education “Ryazan State University named after S.A. Yesenin”, Ryazan, Russia
The presentday development of technological progress in agriculture is based on the widespread introduction of high-tech equipment, which is based on artificial intelligence technologies into production, in particular on the basis of machine learning, which is the most significant and exciting of its subsections. The purpose of the research presented in the article is to develop a method of investigation of the efficiency parameters of existing machine learning algorithms for solving a practical problem, which is prediction of the operating modes of a diesel engine. The solution of the problem was carried out on the basis of the developed computer research method based on the capabilities of the high-level programming language Python, which is a computer model for conducting a computational experiment. Any researcher with elementary knowledge in software development can use th is software to process their own data set. The result of the study showed that each machine learning algorithm for solving a specific practical problem has its own disadvantages and undeniable advantages. But the main efficiency criteria by which the work of any software product is evaluated are the accuracy of the result and the time (speed) of the program code execution. Therefore, to predict the operating modes of a diesel engine, the DecisionTreeRegressor (Decision Tree) is the most effective of the analyzed machine learning algorithms.
Keywords: machine learning, algorithm, operating mode, diesel engine, forecast accuracy, memory consumption, execution time, program code.
