Browse Publications Technical Papers 2021-26-0415
2021-09-22

Steering Performance Calculator using Machine Learning Techniques 2021-26-0415

In the conceptualization phase of vehicle development, for achieving reasonable dynamics performance, proper selection of steering system meeting all the requirements is necessary. This requires accurate prediction of major steering performance attributes like steering effort, steering torque, Turning Circle Diameter (TCD), %Ackerman and steering returnability. However, currently available models majorly depend on Computer Aided Engineering (CAE)-analysis or physical trials which requires system detailing and the same cannot be used for early prediction of the steering performances in the concept phase. This paper aims to address this deficiency with the help of a new steering performance calculator. In the calculator, performance attributes namely steering effort, steering torque, TCD and %-Ackerman has been modelled with engineering calculations and other attributes namely steering returnability&precision has been modelled through machine learning techniques. The developed calculator has been validated for its correctness by correlating with the existing vehicle performance values. The predictions made by the calculator are encouraging and correlates with actual performance values by >90%. The different modules available in this calculator helps in the calculation of steering performances given vehicle and system specifications. Thus, this calculator helps in effective calculation of steering performance attributes and competent target setting in the advanced engineering concept phase of vehicle development without any CAE-analysis and physical trials, thus saving engineering development time.

SAE MOBILUS

Subscribers can view annotate, and download all of SAE's content. Learn More »

Access SAE MOBILUS »

Members save up to 16% off list price.
Login to see discount.
Special Offer: Download multiple Technical Papers each year? TechSelect is a cost-effective subscription option to select and download 12-100 full-text Technical Papers per year. Find more information here.
X