Using a Genetic Algorithm to Achieve Optimal Matching between PMEP and Diameter of Intake and Exhaust Throat of a High-Boost-Ratio Engine

Abstract

With the increasingly stringent CO2 emission regulations, the degree of strengthening of the engines is increasing. Under high-pressure conditions, the airway throat parts of the intake and exhaust systems have a great influence on the flow loss of the diesel engine. The reasonable distribution of the throat area of the intake and exhaust ports in the limited cylinder headspace is key to improving the performance of supercharged engines. This study took a large-bore, high-pressure ratio diesel engine as the research object. Firstly, the three-dimensional (3D) flow simulation method was used to reveal the influence law of different throat areas on the engine intake and exhaust flow under steady-state conditions, and a steady-flow test bench was built to verify the accuracy of the simulation model and law. Secondly, based on the 3D steady-state calculation and test results, a more accurate one-dimensional simulation model was constructed, and a joint optimization simulation platform was established based on the dynamic data link library. On this basis, the mathematical description of the multi-objective optimization of airway throat size was established using machine learning methods, such as a genetic algorithm, the design domain and boundary conditions of variable parameters were clarified, and the collaborative optimization objective of integrated flow coefficient and flow loss is proposed to achieve the fast and accurate optimization of intake and exhaust throat diameters.

Experimental Study on the Flow Characteristics of Two-Stage Variable Turbines in a Twin-VGT System

“…The power consumption of the two-stage compressor is related to the supercharge ratio distribution, the efficiency of the two-stage compressor and the inlet temperature of the two-stage compressor. When the inlet temperatures of high-and low-pressure compressors are different, the ideal supercharge ratio distribution of the two-stage compressor is not equal to 5:5 [29]. Next, the effects of high-and low-pressure VGT blade opening on the supercharge ratio distribution, compressed air temperature and isentropic efficiency of the secondary compressor will be further analyzed.…”

Preparation and Analysis of Experimental Findings on the Thermal and Mechanical Characteristics of Pulsating Gas Flows in the Intake System of a Piston Engine for Modelling and Machine Learning

“…In recent years, the development of high-precision engine control systems has been promoted, taking into account the peculiarities of the flow of gas exchange processes based on mathematical models, machine learning, and artificial intelligence methods. Machine learning algorithms are intensively used in various fields of science and technology to create optimisers, develop control systems for technical equipment, and address related issues [28][29][30]. Song Y. et al, created a mathematical description of a multicriteria optimisation of the gas dynamics of flows and the geometry of intake and exhaust channels in an engine head pack through machine learning methods, in which the design constraints and boundary conditions of variable flow parameters in the gas exchange system and the RICE cylinder were refined [28].…”

“…Machine learning algorithms are intensively used in various fields of science and technology to create optimisers, develop control systems for technical equipment, and address related issues [28][29][30]. Song Y. et al, created a mathematical description of a multicriteria optimisation of the gas dynamics of flows and the geometry of intake and exhaust channels in an engine head pack through machine learning methods, in which the design constraints and boundary conditions of variable flow parameters in the gas exchange system and the RICE cylinder were refined [28]. Moreover, researchers and specialists are increasingly turning to artificial neural networks to reduce the amount of harmful substances in engine exhaust gases [31,32], to optimise fuel injection into the cylinder for RICE operating modes [33], and to solve other technical problems.…”

Research on an Optimization Method for Injection-Production Parameters Based on an Improved Particle Swarm Optimization Algorithm

“…In recent years, many scholars have introduced mathematical and machine learning methods to optimize actual injection and extraction parameters. Common methods for determining injection-production parameters include numerical simulation [3][4][5] and various evolutionary algorithms, such as the genetic algorithm [6,7], the artificial bee colony algorithm [8], the particle swarm optimization (PSO) algorithm [9], etc., in order to obtain better injection-production parameters, and there is a certain reference significance. Zhang et al [10] used numerical simulation methods to optimize single-well production, injection volume and oil production rate in the gas injection stage in the depletion stage.…”