Abstract This paper focuses on the machine-tool selection problem, which consists of choosing the most suitable machine to satisfy the needs of a manufacturing company. The final decision affects the performance of the production system. Selecting an inadequate machine can negatively affect the company's results. For this reason, this is an important process that may imply some difficulties for the decision-maker. The objective of this work was to develop a cost model for vertical high-speed machining (HSM) centres based on machine characteristics. It is important to determine the cost of the machine tool, which is based on the tool's characteristics and needs to satisfy both the buyer and the manufacturer. In order to determine the main machine specifications associated with machine cost, a preliminary analysis was conducted with entry-level vertical HSM centres. As a result, two models were developed: one from the buyer's point of view and the other from the manufacturer's point of view. The cost estimation models were developed using two different techniques: multiple regression analysis (MRA) and artificial neural networks (ANN). The paper then examines the performance of the models, and compares the models’ outputs to determine which model offers the best results. Cost estimation is important to determine the machine costs that adapt best to the characteristics of manufacturing factories. The correlation obtained by the multilayer ANN models is better than the one obtained by MRA. Applying the proposed cost models will help the user (engineers or machine manufacturers) to determine the approximate machine cost based on its characteristics when they select a vertical HSM centre.
[1]
Bülent Çatay,et al.
A decision support system for machine tool selection
,
2004
.
[2]
Sergio Cavalieri,et al.
Parametric vs. neural network models for the estimation of production costs: A case study in the automotive industry
,
2004
.
[3]
Jerry Y. H. Fuh,et al.
A neural network approach for early cost estimation of packaging products
,
1998
.
[4]
Kishan G. Mehrotra,et al.
Elements of artificial neural networks
,
1996
.
[5]
Avraham Shtub,et al.
Estimating the cost of steel pipe bending, a comparison between neural networks and regression analysis
,
1999
.
[6]
Tarek Hegazy,et al.
Developing Practical Neural Network Applications Using Back‐Propagation
,
1994
.
[7]
David J. Edwards,et al.
A comparative analysis between the multilayer perceptron “neural network” and multiple regression analysis for predicting construction plant maintenance costs
,
2000
.
[8]
W. Boettinger,et al.
Microstructural characterization of Al-7075-T651 chips and work pieces produced by high-speed machining
,
2006
.
[9]
Sung Hoon An,et al.
Comparison of construction cost estimating models based on regression analysis, neural networks, and case-based reasoning
,
2004
.