Family cars’ life cycle cost(LCC) estimation model based on CBR

Design for cost (DFC) is a method that reduces life cycle cost (LCC) at design stage. From the angle of DFC, the design features of family cars were obtained, such as all dimensions, engine power and displacement. At conceptual design stage, cars’ LCC were estimated using case-based reasoning (CBR) method. An example was given. Hamming space and grey weighting algorithm were used to measure the similarity among those cases. Finally, the differences of LCC estimation model between CBR and artificial neural networks (ANN) were given: CBR model’s the estimation scope of LCC gets the restriction of sample value, it can not outside push; but its feature parameter quantities and sample quantities are unconcerned; ANN method has some outside push ability and self study ability, but it is instability, maybe convergence. Its sample feature parameter quantities and sample quantities are related to each other. Two methods have certain complementary; it is meaningful for raising estimation accuracy to combine two methods to carry out LCC estimation.