Hostname: page-component-cd9895bd7-7cvxr Total loading time: 0 Render date: 2024-12-27T06:05:21.942Z Has data issue: false hasContentIssue false
  • English
  • Français

An explicit methodology for manufacturing cost–tolerance modeling and optimization using the neural network integrated with the genetic algorithm

Published online by Cambridge University Press:  29 April 2020

A. Saravanan Open the ORCID record for A. Saravanan [Opens in a new window] ,
J. Jerald  and
A. Delphin Carolina Rani
A. Saravanan*
Affiliation:
Department of Production Engineering, National Institute of Technology, Tiruchirappalli620015, India
J. Jerald
Affiliation:
Department of Production Engineering, National Institute of Technology, Tiruchirappalli620015, India
A. Delphin Carolina Rani
Affiliation:
Department of Computer Science and Engineering, Bharathidasan University, Tiruchirappalli, India
*
Author for correspondence: A. Saravanan, E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

The objective of the paper is to develop a new method to model the manufacturing cost–tolerance and to optimize the tolerance values along with its manufacturing cost. A cost–tolerance relation has a complex nonlinear correlation among them. The property of a neural network makes it possible to model the complex correlation, and the genetic algorithm (GA) is integrated with the best neural network model to optimize the tolerance values. The proposed method used three types of neural network models (multilayer perceptron, backpropagation network, and radial basis function). These network models were developed separately for prismatic and rotational parts. For the construction of network models, part size and tolerance values were used as input neurons. The reference manufacturing cost was assigned as the output neuron. The qualitative production data set was gathered in a workshop and partitioned into three files for training, testing, and validation, respectively. The architecture of the network model was identified based on the best regression coefficient and the root-mean-square-error value. The best network model was integrated into the GA, and the role of genetic operators was also studied. Finally, two case studies from the literature were demonstrated in order to validate the proposed method. A new methodology based on the neural network model enables the design and process planning engineers to propose an intelligent decision irrespective of their experience.

Keywords

Artificial neural network (ANN)cost–tolerance modelinggenetic algorithm (GA)tolerance optimization
Type
Research Article
Information
AI EDAM , Volume 34 , Special Issue 3: Thematic Collection: Fablabs, Makerspaces, and Design Spaces , August 2020 , pp. 430 - 443
Check for updates
Copyright
Copyright © Cambridge University Press 2020

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Alex, G, Chavez, BP and Davy, M (2019) Methodology to design ontologies from organizational models: application to creativity workshops. AI EDAM 33, 148–159.Google Scholar
Ashiagbor, A, Liu, H-C and Nnaji, BO (1998) Tolerance control and propagation for the product assembly modeller. International Journal of Production Research 36, 75–94.CrossRefGoogle Scholar
ASME Y14.5-2009 (2009) Dimensioning and Tolerancing. American Society of Mechanical Engineers. https://www.asme.org/codes-standards/find-codes-standards/y14-5-dimensioning-tolerancing.Google Scholar
Babić, BR, Nešić, N and Miljković, Z (2011) Automatic feature recognition using artificial neural networks to integrate design and manufacturing: review of automatic feature recognition systems. AI EDAM 25, 289–304.Google Scholar
Balamurugan, C, Saravanan, A, Dinesh Babu, P, Jagan, S and Ranga Narasimman, S (2017) Concurrent optimal allocation of geometric and process tolerances based on the present worth of quality loss using evolutionary optimisation techniques. Research in Engineering Design 28, 185–202.CrossRefGoogle Scholar
Bukharov, OE and Bogolyubov, DP (2015) Development of a decision support system based on neural networks and a genetic algorithm. Expert Systems with Applications 42, 6177–6183.CrossRefGoogle Scholar
Carpenter, WC and Hoffman, ME (1997) Selecting the architecture of a class of back-propagation neural networks used as approximators. AI EDAM 11, 33–44.Google Scholar
Chandrasegaran, SK, Ramani, K, Sriram, RD, Horváth, I, Bernard, A, Harik, RF and Gao, W (2013) The evolution, challenges, and future of knowledge representation in product design systems. Computer-Aided Design 45, 204–228.CrossRefGoogle Scholar
Diplaris, SC and Sfantsikopoulos, MM (2000) Cost–tolerance function. A new approach for cost optimum machining accuracy. International Journal of Advanced Manufacturing Technology 16, 32–38.CrossRefGoogle Scholar
Geraci, G, De Tullio, MD and Iaccarino, G (2017) Polynomial chaos assessment of design tolerances for vortex-induced vibrations of two cylinders in tandem. AI EDAM 31, 185–198.Google Scholar
Hayes, CC and Sun, HC (1995) Using a manufacturing constraint network to identify cost-critical areas of designs. AI EDAM 9, 73.Google Scholar
Homann, BS and Thornton, AC (1998) Precision machine design assistant: a constraint-based tool for the design and evaluation of precision machine tool \nconcepts. AI EDAM 12, 419–429.Google Scholar
Hu, J, Xiong, G and Wu, Z (2004) A variational geometric constraints network for a tolerance types specification. The International Journal of Advanced Manufacturing Technology 24, 214–222.CrossRefGoogle Scholar
Huang, MF, Zhong, YR and Xu, ZG (2005) Concurrent process tolerance design based on minimum product manufacturing cost and quality loss. The International Journal of Advanced Manufacturing Technology 25, 714–722.CrossRefGoogle Scholar
Islam, MN (2009) A dimensioning and tolerancing methodology for concurrent engineering applications I: Problem representation. International Journal of Advanced Manufacturing Technology 42, 910–921.CrossRefGoogle Scholar
Janakiraman, V and Saravanan, R (2010) Concurrent optimization of machining process parameters and tolerance allocation. The International Journal of Advanced Manufacturing Technology 51, 357–369.CrossRefGoogle Scholar
Kontovourkis, O, Phocas, MC and Lamprou, I (2015) Adaptive kinetic structural behavior through machine learning: optimizing the process of kinematic transformation using artificial neural networks. AI EDAM 29, 371–391.Google Scholar
Kukolj, DD, Berko-pusic, MT and Atlagic, B (2001) Experimental design of supervisory control functions based on multilayer perceptrons. AI EDAM 15, 425–431.Google Scholar
Kumar, LR, Padmanaban, KP, Kumar, SG and Balamurugan, C (2016) Design and optimization of concurrent tolerance in mechanical assemblies using bat algorithm. Journal of Mechanical Science and Technology 30, 2601–2614.CrossRefGoogle Scholar
Lee, J and Kwon, YS (2013) Conservative multi-objective optimization considering design robustness and tolerance: a quality engineering design approach. Structural and Multidisciplinary Optimization 47, 259–272.CrossRefGoogle Scholar
Lin, Z-C and Chang, D-Y (2002) Cost-tolerance analysis model based on a neural networks method. International Journal of Production Research 40, 1429–1452.CrossRefGoogle Scholar
Liu, S-G, Jin, Q, Wang, P and Xie, R-J (2014) Closed-form solutions for multi-objective tolerance optimization. The International Journal of Advanced Manufacturing Technology 70, 1859–1866.CrossRefGoogle Scholar
Mörtl, M and Schmied, C (2015) Design for cost – a review of methods, tools and research directions. Journal of the Indian Institute of Science 95, 379–404.Google Scholar
Ngoi, BKA (1992) Applying linear programming to tolerance chart balancing. The International Journal of Advanced Manufacturing Technology 7, 187–192.CrossRefGoogle Scholar
Ngoi, BKA, Agarwal, M and Chua, CS (1998) Nonlinear optimisation in tolerance charts? A study of objective functions. The International Journal of Advanced Manufacturing Technology 14, 423–427.CrossRefGoogle Scholar
Pierre, L, Teissandier, D and Nadeau, JP (2009) Integration of thermomechanical strains into tolerancing analysis. International Journal on Interactive Design and Manufacturing 3, 247–263.CrossRefGoogle Scholar
Prabhaharan, G, Asokan, P, Ramesh, P and Rajendran, S (2004) Genetic-algorithm-based optimal tolerance allocation using a least-cost model. The International Journal of Advanced Manufacturing Technology 24, 647–660.CrossRefGoogle Scholar
Reed, K and Gillies, D (2016) Automatic derivation of design schemata and subsequent generation of designs. AI EDAM 30, 367–378.Google Scholar
Rojek, I (2017) Technological process planning by the use of neural networks. AI EDAM 31, 1–15.Google Scholar
Sanz-lobera, A, Sebastián, MA and Pérez, JM (2010) New cost–tolerance model for mechanical part design. The International Journal of Advanced Manufacturing Technology 51, 421–430.CrossRefGoogle Scholar
Saravanan, A and Jerald, J (2019) Ontological model-based optimal determination of geometric tolerances in an assembly using the hybridised neural network and Genetic algorithm. Journal of Engineering Design 30, 180–198.CrossRefGoogle Scholar
Saravanan, A, Balamurugan, C, Sivakumar, K and Ramabalan, S (2014) Optimal geometric tolerance design framework for rigid parts with assembly function requirements using evolutionary algorithms. The International Journal of Advanced Manufacturing Technology 73, 1219–1236.CrossRefGoogle Scholar
Saravanan, A, Jerald, J and Delphin Carolina Rani, A (2020) An intelligent constitutive and collaborative framework by integrating the design, inspection and testing activities using a cloud platform. International Journal of Computer Integrated Manufacturing. doi:10.1080/0951192X.2020.1736712CrossRefGoogle Scholar
Shen, Z, Shah, JJ and Davidson, JK (2008) Automatic generation of min/max tolerance charts for tolerance analysis from CAD models. International Journal of Computer Integrated Manufacturing 21, 869–884.CrossRefGoogle Scholar
Srinivasan, RS, Wood, KL and McAdams, DA (1996) Functional tolerancing: a design for manufacturing methodology. Research in Engineering Design – Theory, Applications, and Concurrent Engineering 8, 99–115.Google Scholar
Su, D and Wakelam, M (1999) Evolutionary optimization within an intelligent hybrid system for design integration. AI EDAM 13, 351–363.Google Scholar
Tsai, J-C and Cutkosky, MR (1997) Representation and reasoning of geometric tolerances in design. AI EDAM 11, 325–341.Google Scholar
Wang, Y and Huang, L (2009) Risk assessment of supply chain based on BP neural network. 2009 2nd International Symposium on Knowledge Acquisition and Modeling, pp. 186–188.CrossRefGoogle Scholar
Wolbrecht, E, D'Ambrosio, B, Paasch, R and Kirby, D (2000) Monitoring and diagnosis of a multistage manufacturing process using Bayesian networks. AI EDAM 14, 53–67.Google Scholar
Yang, CC, Marefat, MM and Ciarallo, FW (1997) Tolerance analysis and synthesis by interval constraint networks. Proceedings of International Conference on Robotics and Automation, Albuquerque, NM, USA, Vol. 3, pp. 2522–2527.CrossRefGoogle Scholar