Simulation Research of Automotive Magneto-rheological Semi-Active Suspension Based on Artificial Intelligence Technology
Abstract: In modern society, the rapid development of the economy in different regions has not only enabled multiple industries to achieve better development speed, but also enabled the material living standards of residents in these regions to be better improved in a relatively short period of time. This improvement has also led to a rapid increase in people's requirements for various aspects of life. With the improvement of people's economic level, the field of automotive research and development has begun to conduct more in-depth research on driving and riding comfort. How to make drivers or passengers feel no bumps on the road during the driving process has become an important content in automotive research and development. The degree of this adjustment and the service life of various materials in it have become a key issue limiting the long-term maintenance of a good driving experience for the car. A Magneto-rheological fluid (MRF) proposed in modern industry has become the key to the further development of automotive suspension. This MRF has many excellent characteristics, among which its durability and responsiveness make it a material that can play a significant role in the research and manufacture of automotive suspensions. Some researchers in current society have proposed a Magneto-rheological damper (MRD) through research on MRF. The integration of this shock absorber brings the performance of the vehicle's shock absorber suspension to a higher level. However, with the rapid development of artificial intelligence (AI) technology, more and more people begin to hope to further integrate some of the AI technologies with automotive shock suspension technology, making the existing automotive suspension systems have better performance in various aspects. After studying AI technology, this paper used AI technology to optimize the simulation model of Magneto-rheological (MR) semi-active suspension, so that the optimized MR semi-active suspension system model can maintain its state in a good range throughout a long service cycle. Finally, through simulation experiments, this paper studied the performance of this kind of MR semi-active suspension combined with AI technology and existing MR semi-active suspension in various aspects. This paper concluded that the performance of MR semi-active suspension integrated with AI technology has increased by an average of 15.8% compared to the existing MR semi-active suspension in various aspects.
Loading