Exploration of Pattern Recognition of Automobile Anti-Lock Braking System
Abstract
Data management systems have had a significant impact on society and the economy as they are an important means of storing information derived from big data by means of computer technology. Data management systems enable pattern recognition, which plays a significant role in information recognition and gradually extends to other areas. Due to the gradual popularization of automobiles, the requirements for safe automobile braking performance are increasing. In this regard, an ABS (Anti-lock Braking System) can adequately meet the current requirements for automobile braking performance. At present, the research on ABSs focuses mainly on its control strategy. In actual production, many ABSs use logic threshold control. However, the pattern recognition of ABS is rare. In order to promote the application of ABS, this paper proposes the idea of pattern recognition through theoretical analysis. By means of the pattern recognition of the initial speed, the overall situation of the road surface and the braking force when braking, the ABS system can effectively improve the driving safety of the automobile. The braking distance of the car with ABS system was reduced by 2 meters on the road with a high coefficient of adhesion, and 7 meters on the road with low coefficient of adhesion compared to the car without the system. This would help improve the safety of braking when the car is in emergency braking, and provide more driving security for the driver. Pattern recognition can also provide a more theoretical basis for the extensive use of ABS in cars. At the same time, the innovative application of pattern recognition can also enrich the information storage of the data management system and further its development.
Keywords: Anti-lock braking system (ABS); pattern recognition; PID control algorithm; automobile system
Cite As
G. Yue, Y. Pan, "Exploration of Pattern Recognition of Automobile Anti-Lock Braking System",
Engineering Intelligent Systems, vol. 31 no. 6, pp. 429-437, 2023.