Parametric and neural methods for cost estimation of process vessels

In this paper, a comparison is made between artificial neural networks and parametric functions for estimating the manufacturing cost of large-sized and complex-shaped pressure vessels in engineer-to-order manufacturing systems. In the case of large equipment built to customer's design, in fact, it is hard to estimate the production cost owing to the wide variability of vessel's size and configuration and the often scarce previous experience with similar units. However, when cost estimates are to be used for bidding purposes, a poor accuracy may have detrimental financial consequences. A cost overestimation bears the risk of making the firm uncompetitive and losing a customer, while underestimating the cost leads to winning a contract but incurring a financial loss. Furthermore, a precise knowledge of prospective resources utilization is critical for project management purposes when passing to the actual manufacture phase. The developed methods were tested with reference to a world leading manufacturer in 68 case studies with very encouraging results. In fact both techniques greatly outperformed the manual estimation methods currently adopted which suffered from an average estimation error of 26%, with maximum values of +81% and -60%. The parametric function method, instead, enabled a reduction of the average estimation error to about 12%, with extreme values within the ±33% range, while the neural network approach allowed to further reduce the average error to less than 9% with a +33% to -22% variability range. In this application, therefore, the neural network proved to be better suited than the parametric model, presumably owing to the better mapping capabilities. Such results are quite satisfactory considering the kind of production context, the scarcity of historical data and the severity of the considered application. In this paper, the procedure used to develop the two estimating methods is described and the obtained performances are evaluated in comparison with the manual method, also discussing the merits and limitations of the analysed approaches.

[1]  Walter Eversheim,et al.  Design-to-Cost for Production Systems , 1998 .

[2]  Kwai-Sang Chin,et al.  Developing a knowledge-based injection mould cost estimation system by decision tables , 1996 .

[3]  B. Edwin.  Parametric Cost Deployment , 1995 .

[4]  Ong Nan Shing,et al.  Design for manufacture of a cost-based system for molded parts , 1999 .

[5]  Alice E. Smith,et al.  COST ESTIMATION PREDICTIVE MODELING: REGRESSION VERSUS NEURAL NETWORK , 1997 .

[6]  Kristiaan Schreve,et al.  Manufacturing cost estimation during design of fabricated parts , 1999 .

[7]  Y. Asiedu,et al.  Simulation-based cost estimation under economic uncertainty using kernel estimators , 2000 .

[8]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[9]  Michael French.  Function Costing: A Potential Aid to Designers , 1990 .

[10]  James S. Noble,et al.  Concurrent design and economic justification in developing a product , 1990 .

[11]  Jerry Y. H. Fuh,et al.  A neural network approach for early cost estimation of packaging products , 1998 .

[12]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[13]  Avraham Shtub,et al.  A neural-network-based approach for estimating the cost of assembly systems , 1993 .

[14]  Howard B. Demuth,et al.  Neutral network toolbox for use with Matlab , 1995 .

[15]  N. S. Ong,et al.  Manufacturing cost estimation for PCB assembly: An activity-based approach , 1995 .

[16]  Douglas C. Montgomery,et al.  Applied Statistics and Probability for Engineers, Third edition , 1994 .

[17]  Jürgen Bode,et al.  Neural networks for cost estimation: Simulations and pilot application , 2000 .

[18]  Walter Eversheim,et al.  Qualitative and quantitative cost analysis for sheet metal stamping , 2004, Int. J. Comput. Integr. Manuf..

[19]  Michael Chester,et al.  Neural networks - a tutorial , 1993 .

[20]  Yuh-Min Chen,et al.  Cost-effective design for injection molding , 1999 .

[21]  Herbert Pickel.  Kostenmodelle als Hilfsmittel zum Kostengünstigen Konstruieren , 1988 .

[22]  Fredrik Elgh,et al.  Concurrent cost estimation as a tool for enhanced producibility—System development and applicability for producibility studies , 2007 .

[23]  Halbert White,et al.  Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[24]  Jürgen Bode,et al.  Decision support with neural networks in the management of research and development: Concepts and application to cost estimation , 1998, Inf. Manag..

[25]  Sergio Cavalieri,et al.  Parametric vs. neural network models for the estimation of production costs: A case study in the automotive industry , 2004 .

[26]  David Wallace,et al.  Prediction of the life cycle cost using statistical and artificial neural network methods in conceptual product design , 2002, Int. J. Comput. Integr. Manuf..

[27]  W. T. Chan,et al.  Feature-based cost estimation for packaging products using neural networks , 1996 .

[28]  Chan S. Park,et al.  An Economic Evaluation Model for Product Design Decisions under Concurrent Engineering , 1993 .

[29]  Avraham Shtub,et al.  Estimating the cost of steel pipe bending, a comparison between neural networks and regression analysis , 1999 .

[30]  Qing Wang,et al.  Process cost modelling using neural networks , 2000 .

[31]  Dimitris Kiritsis,et al.  Petri net techniques for process planning cost estimation , 1999 .

[32]  C. Ou-Yang,et al.  Developing an integrated framework for feature-based early manufacturing cost estimation , 1997 .

[33]  Fatemeh Zahedi,et al.  An Introduction to Neural Networks and a Comparison with Artificial Intelligence and Expert Systems , 1991 .

[34]  Henry C. Co,et al.  Design of a model generator for simulation in SLAM , 1988 .

[35]  Essam Shehab,et al.  An Intelligent Knowledge-Based System for Product Cost Modelling , 2002 .

[36]  Essam Shehab,et al.  A design to cost system for innovative product development , 2002 .

[37]  C. Richard Liu,et al.  Design for Manufacturing , 2007 .

[38]  R. M. Wyskida,et al.  Cost Estimator's Reference Manual , 1987 .

[39]  Alexander Layer,et al.  Recent and future trends in cost estimation , 2002, Int. J. Comput. Integr. Manuf..

[40]  Leo S. Wierda.  Linking Design, Process Planning and Cost Information by Feature-based Modelling , 1991 .

[41]  M. Gutierrez,et al.  Estimating hidden unit number for two-layer perceptrons , 1989, International 1989 Joint Conference on Neural Networks.

[42]  Paul G. Maropoulos,et al.  Artificial neural networks as a cost engineering methods in collaborative manufacturing environment. , 2005 .

[43]  Dirk Cattrysse,et al.  Cost estimation for sheet metal parts using multiple regression and artificial neural networks: A case study , 2008 .

[44]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[45]  David A. Koonce,et al.  Identifying and removing error in hierarchical cost estimates , 2007 .

[46]  David M. Dilts,et al.  Automated design-to-cost: integrating costing into the design decision , 1996, Comput. Aided Des..

[47]  David M. Miller,et al.  A knowledge-based approach to design for manufacturability , 1993, J. Intell. Manuf..

[48]  Marcus O'Connor,et al.  Artificial neural network models for forecasting and decision making , 1994 .

[49]  Claus J. Meisl.  Cost Modeling for Concurrent Engineering , 1993 .

[50]  Brian G. Kingsman,et al.  Responding to customer enquiries in make-to-order companies Problems and solutions , 1996 .

[51]  Leo S. Wierda.  Product cost-estimation by the designer , 1988 .

[52]  G. Boothroyd,et al.  Early cost estimating in product design , 1988 .