Research on Method of Anti-Fuzzy for Qualitative Evaluation Index of Materiel Support Plan

Abstract:

To solve the problem of difficulty to get accurate value of qualitative evaluation index of materiel support plan in work phase, and it is difficult to get expertise of experts which full of subjective in weight ascertaining sometimes, the paper introduce fuzzy theory to the process of materiel support plan evaluation, give membership function of qualitative evaluation index, on the base of membership function, remove fuzzy of the index by the method of barycenter, calculate the offset with genetic algorithm. By using the data of materiel support plan to train and predict, the value of the index get by this method are accurately. The result can be a useful consult for evaluate materiel support plan.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 3220-3224
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.3220
• Online since: September 2013
• Authors: Wei Zhu Zhou, Jing Huan
• Keywords: Anti-Fuzzy, Evaluation, Fuzzy Theory, Genetic Algorithm (GA), Neural Network (NN), Support Concept

References

[1] Shikai Shen, Yumei She．Approach to Information Systems Security Risk Assessment Based on Fuzzy－BP Neural Network, ．Computer Simulation，2011，10(28)：91-94.

[2] Xueqiang Yang, Jun Huang．Introduction of Equipment support Information Construction, ．Beijing：National Defense Industry Press，2011.

[3] TingxueXu, Renbo Yu． Research on Evaluation of Winged Missile Support Concept, ．Missiles and Space Vehicles，2010，6：18-22.

[4] S. Mitra, S. K. Pal. Fuzzy sets in pattern recognition and machine intelligence,. Fuzzy Sets and Systems, 2005, 156(3): 381-386.

DOI: 10.1016/j.fss.2005.05.035

[5] Rafael Ferrari．Unsupervised channel equalization using fuzzy prediction-error filters, ．IEEE XIII Workshop on Neural Network for signal processing，2003：869-878.

DOI: 10.1109/nnsp.2003.1318086

[6] Heng Song，Chen Wang，Yin He，ect．Decision feedback equalizer based on non-singleton fuzzy regular neural networks, ．Journal of systems engineering and electronics，2006，17 (4) ：896-900.

DOI: 10.1016/s1004-4132(07)60034-6

[7] Parag C. Pendharkar．Genetic algorithm based neural net-work approaches for predicting churn in cellular wireless network services, ．Expert Systems with Applications，2009，36(3)：6714-6720.

DOI: 10.1016/j.eswa.2008.08.050

[8] ZHAO D M, LIU H F, ZHANG J P．Mode of risk assessment of information security based on fuzzy neural network,. Computer Engineering and Applications, 2009, 45 (17) : 116-118.

[9] N Amjady．Day-ahead price forecasting of electricity markets by a new fuzzy neural network, ．IEEE transaction on power systems，2006，21(2)：887-896.

DOI: 10.1109/tpwrs.2006.873409