| 摘要 |
A tire is easily designed. Design parameters of the shape, structure and pattern of a known tire and the performance of the tire are inputted to a nonlinear arithmetic unit (32) through an experimental data input unit (40) in an optimizer (30). The nonlinear arithmetic unit (32), which is a conversion system of a neural network, learns the relations between the design parameters of the shape, structure, and pattern of the tire and the performance of the tire. The ranges, etc. which restrict the performance of the tire and the design parameters of the tire which are to be optimized are inputted through an optimization item input unit (42). An optimization arithmetic unit (34) estimates the performance of the tire in accordance with the design parameters of the tire by using the optimization items and the model of the arithmetic unit (32) and optimizes until an object function which is the performance of the tire is converged. The optimized design parameters are outputted from an optimization result output unit (44),
|
