Knowledge-based methods for cost estimation of metal casts

Abstract

The aim of the research presented in this paper was to verify the hypothesis that the problem of estimating the variable costs of metal casts can be solved by using knowledge-based systems. The estimation of variable costs determines the adequate pricing of products, which is a crucial marketing problem in enterprises. The problem of estimating the direct costs is especially important in companies whose participation in the market is defined as versatile manufacturing. This problem was the target of many studies presented in this paper. The assumptions that the direct costs of a metal cast are dependent on the physical features of the cast and the most effective method of cost estimation is an intuitive qualitative technique based on a rule-based system were considered. The nature of the relationships between the casts' features and the direct costs of production could be effectively formed by experts as reasoning rules. In this paper, the results of experiments conducted on the basis of the example of the production program of a foundry that manufactures water-system fittings is presented. Three methods of knowledge-definition and reasoning techniques were examined: the classical method of crisp reasoning, fuzzy reasoning with the Mamdani's method, and fuzzy reasoning with the Takagi-Sugeno model. Proper experiments were conducted. The results of the experiments confirmed the hypothesis, which allows the assessment of different reasoning methods.A. Maciol

Design of Takagi–Sugeno fuzzy systems by learning from examples in case a number of available data is not sufficient

“…The concept of Takagi and Sugeno may improve an expressiveness/computational efficiency relation both for tasks and classification tasks. Here we can also refer to the results of our research (Maciol 2017), which for a specific case showed an increase of the inference effectiveness expressed as the mean absolute percentage error by about 19% comparing to the results of the Mamdani's method (by 29% in a relation to the classical method) and by 20% comparing to the Mamdani's method (26% in a relation to the classical method) if expressed with the maximal relative deviation. Such a significant increase in the expressiveness is a result of a fact that relations between antecedents and conclusions are not described explicitly but with an arbitrary function.…”

“…Considering the inability of using of sufficiently large training sets in our earlier studies (Maciol 2017), we used the set of equations described with the defined above support points. The solution of the set of equations gave coefficients in the line function sought.…”

An Analytical Cost Model for Investment Casting

“…The method works well in mass production foundries making castings of similar characteristics, but it is not suitable for job shop or batch type foundries that have a wide range of products. To alleviate these problems, more elaborate cost models have been proposed by identifying and calculating the detailed cost elements (Sajid et al, 2018;Maciol, 2017). However, very few works have been reported on cost estimation of investment casting.…”