Inverse Design + AI

  • Paper:
    Prognostics and Health Management(PHM) Asia Pacific 2021
Multidisciplinary Inverse Design using Deep Learning: a Case Study of Brake Systems

It is well known that braking performances are target performances which must be considered for vehicle development. Apparent piston travel (APT) which is the distance piston travels when the driver pushing on the pedal and drag torque which means unnecessary residual torque occurred by piston’s roll-back distance after braking are major brake performance evaluation factors. In this work, we propose deep learning-based inverse design model for APT and drag to reduce time and cost of iterative optimization methods. Especially, we can get the optimal design instantly, that satisfies both target drag performance and APT performance in Trade-off relationship for piston travel displacement through multidisciplinary inverse design model that optimizes multiple objective functions simultaneously. This work is the first study applying deep leaning-based inverse design to brake system design and will be extended to various vehicle systems in the future.