Search Results

This paper presents two closed-loop control methods for monitoring and improving the combustion behavior and the combustion noise on two 4-cylinder diesel engines, in which an in-cylinder pressure and an accelerometer transducer are used to monitor and control them. Combustion processes are developed to satisfy the stricter and stricter regulations on emissions and fuel consumption. These combustion processes are influenced by the factors such as engine durability, driving conditions, environmental influences and fuel properties. Combustion noise could be increased by these factors and is detrimental to interior sound quality. Therefore, it is necessary to develop robust combustion behaviors and combustion noise. For this situation, we have developed two closed-loop control methods. Firstly, a method using in-cylinder pressure data was developed for monitoring and improving the combustion noise of a 1.7L engine. A new index using the values calculated from the data was proposed.

The combustion noise of a diesel engine can be deteriorated by combustion characteristics such as the maximum rate of heat release and the start of combustion. These combustion characteristics in turn are influenced by the factors such as the engine NVH durability, driving conditions, environmental factors and fuel properties. Therefore, we need to develop the robust combustion noise that is insensitive to these factors. To achieve this aim, methods for predicting combustion characteristics has been developed by analyzing the vibration signal measured from the engine cylinder block. The closed-loop control of injection parameters through combustion characteristics prediction has been performed to produce the desired engine combustion performance. We constructed an ECU logic for the closed-loop control and verified the design in a diesel passenger car. We also evaluated the effect of combustion noise and fuel consumption by applying the closed-loop control.

The high-frequency whining noise produced by motors in modern electric vehicles causes a significant issue, leading to annoyance among passengers. This noise becomes even more noticeable due to the quiet nature of electric vehicles, which lack other noises to mask the high-frequency whining noise. To improve the noise caused by motors, it is essential to optimize various motor design parameters. However, this task requires expert knowledge and a considerable time investment. In this study, we explored the application of artificial intelligence to optimize the NVH performance of motors during the design phase. Firstly, we selected and modeled three benchmark motor types using Motor-CAD. Machine learning models were trained using Design of Experiment methods to simulate batch runs of Motor-CAD inputs and outputs.