Software reliability prediction model based on grey Elman neural network
CAO Weidong1,2, ZHU Yuanzhi1,2, ZHAI Panpan1,2, WANG Jing1,2
1. College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China; 2. Information Technology Research Base of Civil Aviation Administration of China, Civil Aviation University of China, Tianjin 300300, China
Abstract：The current software reliability prediction model has big prediction accuracy fluctuation and poor adaptability in field data of reliability with strong randomness and dynamics. In order to solve the problems, a software reliability prediction model based on grey Elman neural network was proposed. First, the grey GM (1,1) model was used to predict the failure data and weaken its randomness. Then the Elman neural network was utilized to build the model for predicting the residual produced by GM (1,1), and catch the dynamic change rules. Finally, the prediction results of GM (1,1) and Elman neural network residual were combined to get the final prediction outcomes. The simulation experiment was conducted by using field failure data set produced by the flight inquiry system. The gray Elman neural network model was compared with Back-Propagation (BP) neural network model and Elman neural network model, the corresponding Mean Squared Error (MSE) and Mean Relative Error (MRE) of the three models were respectively 105.1, 270.9, 207.5 and 0.0011, 0.0021, 0.0016. The errors of gray Elman neural network prediction model were the minimum. The experimental results show that the proposed gray Elman neural network prediction model has higher prediction accuracy.
[1] 司冠南,任宇涵,许静,等.基于贝叶斯网络的网构软件可信性评估模型[J].计算机研究与发展,2012,49(5):1028-1038.(SI G N, REN Y H, XU J, et al. A dependability evaluation model for internetware based on Bayesian network[J]. Journal of Computer Research and Development, 2012, 49(5):1028-1038.) [2] 张婷婷,张德平,刘国强.软件可靠性预测的增强贝叶斯组合模型[J].计算机应用研究,2016,33(4):1096-1101.(ZHANG T T, ZHANG D P, LIU G Q. Enhanced Bayesian combinational model for software reliability prediction[J]. Application Research of Computers, 2016, 33(4):1096-1101.) [3] 郭平.软件可靠性工程中的计算智能方法[M].北京:科学出版社,2012:256-257.(GUO P. Computational Intelligence for Software Reliability Engineering[M]. Beijing:Science Press, 2012:256-257.) [4] 赵宇.可靠性数据分析[M].北京:国防工业出版社,2011:56-64.(ZHAO Y. Data Analysis of Reliability[M]. Beijing:National Defence Industry Press, 2011:56-64.) [5] MOURA M D C, ZIO E, LINS I D, et al. Failure and reliability prediction by support vector machines regression of time series data[J]. Reliability Engineering & System Safety, 2011, 96(11):1527-1534. [6] 靳昂,江建慧,楼俊刚,等.基于灰色模型的软件可靠性建模[J].计算机应用,2009,29(3):690-694.(JIN A, JIANG J H, LOU J G, et al. Software reliability modeling based on grey system theory[J]. Journal of Computer Applications, 2009, 29(3):690-694.) [7] LO J H. A data-driven model for software reliability prediction[C]//Proceedings of the 2012 IEEE International Conference on Granular Computing. Piscataway, NJ:IEEE, 2012:326-331. [8] XIAO X, DOHI T. Wavelet shrinkage estimation for non-homogeneous poisson process based software reliability models[J]. IEEE Transactions on Reliability, 2013, 62(1):211-225. [9] 韦大伟,崔正斌.基于神经网络集成的软件可靠性预测研究[J].计算机工程与设计,2010,31(19):4228-4231.(WEI D W, CUI Z B. Research on software reliability prediction based on neural network ensemble[J]. Computer Engineering and Design, 2010, 31(19):4228-4231.) [10] 乔辉,周雁舟,邵楠. 基于学习向量量化神经网络的软件可靠性预测[J].计算机应用,2012,32(5):1436-1438,1442.(QIAO H, ZHOU Y Z, SHAO N. Software reliability prediction based on learning vector quantization neutral network[J]. Journal Computer Applications, 2012, 32(5):1436-1438, 1442.) [11] KIRAN N R, RAVI V. Software reliability prediction using wavelet neural networks[C]//ICCIMA'07:Proceedings of the 2007 International Conference on Computational Intelligence and Multimedia Applications. Piscataway, NJ:IEEE, 2007:195-199. [12] ROY P, MAHAPATRA G S, RANI P, et al. Robust feedforward and recurrent neural network based dynamic weighted combination models for software reliability prediction[J]. Applied Soft Computing, 2014, 22(5):629-637. [13] LAKSHMANAN I, RAMASAMY S. An artificial neural-network approach to software reliability growth modeling[J]. Procedia Computer Science, 2015, 57:695-702. [14] 乔辉,周雁舟,邵楠,等.基于AGA-LVQ神经网络的软件可靠性预测模型研究[J].计算机科学,2013,40(1):179-182.(QIAO H, ZHOU Y Z, SHAO N, et al. Research of software reliability prediction model based on AGA-LVQ[J]. Computer Science, 2013, 40(1):179-182.) [15] 刘逻, 郭立红,肖辉,等. 基于参数动态调整的动态模糊神经网络的软件可靠性增长模型[J].计算机科学,2013,40(2):186-190.(LIU L, GUO L H, XIAO H, et al. Software reliability growth model based on dynamic fuzzy neural network with parameters dynamic adjustment[J]. Computer Science, 2013, 40(2):186-190.) [16] 刘逻,郭立红.基于结合自适应步长布谷鸟搜查算法的模糊神经网络的软件可靠性增长模型[J].计算机应用,2014,34(10):2908-2912.(LIU L, GUO L H. Software reliability growth model based on self-adaptive step cuckoo search algorithm-fuzzy neural network[J]. Journal of Computer Applications, 2014, 34(10):2908-2912.) [17] 邓聚龙.灰色系统基本方法[M].2版.武汉:华中科技大学出版社,2005:26-40.(DENG J L. The Primary Methods of Grey System Theory[M]. 2nd ed. Wuhan:Huazhong University of Science & Technology Press, 2005:26-40.) [18] JIE S, LI W, WEISONG Z, et al. Numerical analysis of modeling based on improved Elman neural network[J]. Scientific World Journal, 2014, 2014(1):271593.
2016, Vol. 36 
