Evolutionary prediction of manufacturing costs in tool manufacturing

One of the most important factors in the offer for tool manufacture is the total manufacturing cost. Although the total manufacturing costs can be rather precisely determined by the cost analysis, this approach is not well applicable in tool-making due to cost and, particularly, time demand. Therefore, the authors propose a new approach to prediction of total manufacturing costs, which is based on case based-reasoning method and imitates the human expert. The system first abstracts from CAD-models the geometrical features, and then it calculates the similarities between the source cases and target case. The most similar cases are used for preparation of prediction by genetic programming. The genetic programming method provides the model connecting the individual geometrical features with the costs searched for. Regarding to the connections between geometrical features and tool cost of source cases the formula for calculation of tool cost of target case is being made. The experimental results show that the quality of predictions made by the intelligent system is comparable to the quality assured by the experienced expert.