Abstract
The assessment on hardware design defects plays an important role in the product development process. In order to improve the design quality through mitigating design defects, a model for assessing hardware product design defects is developed in this paper based on the design defects formation mechanism of product. A novel assessment method by applying fuzzy theory, genetic algorithm and neural network is proposed to construct assessment model. Assessment index is quantified by fuzzy language description. Fuzzy BP neural network tuned by genetic algorithm with the purpose of optimizing the connection weights and avoiding local minimum is used to evaluate probability of product design defects occurrence. The results obtained in this study demonstrated that the assessment model had excellent capabilities with a high accuracy and good training speed, thus provides an effective tool for assessing design defects of hardware product.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Carbone TA, Tippett DD (2004) Project risk management using the project risk FMEA. Eng Manage J 16(4):28–35
Chin KS, Tang DW et al (2009) Assessing new product development project risk by Bayesian network with a systematic probability generation methodology. Expert Syst Appl 36(6):9879–9890
Das SK, Gami S (2004) Expert rules for manufacturability analysis of misalignment defects during product design. Int J Comput Integr Manuf 17(1):58–68
Fang C, Marle F (2012) A simulation-based risk network model for decision support in project risk management. Decis Support Syst 52(3):635–644
Fan CF, Yu YC (2004) BBN-based software project risk management. J Syst Softw 73(2): 193–203
Frank MV (1995) Choosing among safety improvement strategies: a discussion with example of risk assessment and multi-criteria decision approaches for NASA. Reliab Eng Syst Saf 49(3):311–324
Garvey PR, Lansdowne ZF (1998) Risk matrix: an approach for identifying, assessing, and ranking program risks. Air Force J Logistics 22(1):18–21
Hu Y, Zhang X et al (2012) Software project risk analysis using Bayesian networks with causality constraints. Decis Support Syst 56:439–449
Jardine IJA, Jackson D (1989) Risk assessment and optimization of a safety system using the MAROS simulation package. Qual Reliab Eng Int 5(2):131–141
Khashman A (2010) Neural networks for credit risk evaluation: investigation of different neural models and learning schemes. Expert Syst Appl 37(9):6233–6239
Kurihara K, Nishiuchi N (2002) Efficient Monte Carlo simulation method of GERT-type network for project management. Comput Ind Eng 42(2):521–531
Lee E, Park Y, Shin JG (2009) Large engineering project risk management using a Bayesian belief network. Expert Syst Appl 36(3):5880–5887
Liu W, Xiao C, Zhu M (2012) The classification research on design defect of hardware based on Gray clustering assessment. Mach Des Manuf 12:65–67 (in Chinese)
Lyneis JM, Ford DN (2007) System dynamics applied to project management: a survey, assessment, and directions for future research. Syst Dyn Rev 23(2–3):157–189
Moll JV, Jacobs J, Kusters R, Trienekens J (2004) Defect detection oriented lifecycle modeling in complex product development. Inf Softw Technol 46(10):665–675
Park BJ, Oh SK, Pedrycz W (2013) The design of polynomial function-based neural network predictors for detection of software defects. Inf Sci 229:40–57
Sen P, Tan JK, Spencer D (1999) An integrated probabilistic risk analysis decision support methodology for systems with multiple state variables. Reliab Eng Syst Saf 64(1):73–87
Su XY, Deng Y et al (2012) An improved method for risk evaluation in failure modes and effects analysis of aircraft engine rotor blades. Eng Fail Anal 26:164–174
Wang J, Lin W, Huang YH (2010) A performance-oriented risk management framework for innovative R&D projects. Technovation 30(11):601–611
Wang Z, Li H, Jia Y (2013) A neural network model for expressway investment risk evaluation and its application. J Transp Syst Eng Inf Technol 13(4):94–99
Xu Z, Li H (2012) Assessing performance risk for complex product development: a simulation-based model. Qual Reliab Eng Int 29(2):267–275
Acknowledgments
The authors gratefully acknowledge the enterprises that provide data and design experts who participate in works of data fuzzy processing. We also thank M.S. Li and Yang Liu for their suggestions and providing language help on the earlier version of this article. This research is supported by the National Natural Science Foundation of China (Grant No. 71161018).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, H., Liu, W., Xiao, C., Hu, W. (2014). Assessment of Hardware Product Design Defects by Fuzzy Neural Network Based on Genetic Algorithm. In: Xu, J., Cruz-Machado, V., Lev, B., Nickel, S. (eds) Proceedings of the Eighth International Conference on Management Science and Engineering Management. Advances in Intelligent Systems and Computing, vol 280. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55182-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-55182-6_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-55181-9
Online ISBN: 978-3-642-55182-6
eBook Packages: EngineeringEngineering (R0)