Reasoning and forecasting of regional fire data based on adaptive fuzzy generalized regression neural network
JIN Shan1,2, JIN Zhigang1
1. School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China;
2. Communication Department, Hexi District Fire Detachment, Tianjin 300222, China
While BP neural network,classical theory of probability and its derivative on algorithm were used to fire loss prediction,the system structure is complex,the detection data is not stable,and the result is easy to fall into local minimum, etc. To resolve these troubles, a method of reasoning and forecasting the regional fire data was proposed based on adaptive fuzzy Generalized Regression Neural Network (GRNN). The improved fuzzy C-clustering algorithm was used to correct weight for the initial data in network input layer, and it reduced the influence of noise and isolated points on the algorithm, improved the approximation accuracy of the predicted value. The adaptive function optimization of GRNN algorithm was introducd to adjust the expansion speed of the iterative convergence, change the step, and found the global optimal solution. The method was used to resolve the premature convergence problem and improved the search efficiency. While the identified fire loss data is put into the algorithm, the experimental results show that the method can overcome the problem of instable detection data, and has good ability of nonlinear approximation and generalization capability.
金杉, 金志刚. 基于自适应模糊广义回归神经网络的区域火灾数据推理预测[J]. 计算机应用, 2015, 35(5): 1499-1504.
JIN Shan, JIN Zhigang. Reasoning and forecasting of regional fire data based on adaptive fuzzy generalized regression neural network. Journal of Computer Applications, 2015, 35(5): 1499-1504.
[1] ZHOU P, BAI G. Robust design of turbine-blade low cycle fatigue life based on neural networks and fruit fly optimization algorithm[J].Journal of Aerospace Power,2013,28(5):1013-1017.(周平,白广忱.基于神经网络与果蝇优化算法的涡轮叶片低循环疲劳寿命强壮性设计[J].航空动力学报,2013,28(5):1013-1017.) [2] LI S,JI Y,LIU W, et al. Application of wavelet transform and neural network in the near-infrared spectrum analysis of oil shale[J].Spectroscopy and Spectral Analysis,2013,33(4):968-971.(李素义,嵇艳鞠,刘伟宇,等. 小波变换与神经网络融合法在油页岩近红外光谱分析中的应用[J].光谱学与光谱分析,2013,33(4):968-971.) [3] QIAN K,SONG A,ZHANG H,et al. Path planning for mobile robot based on adaptive fuzzy neural network[J]. Journal of Southeast University: Natural Science Edition, 2012,42(7):637-642.(钱夔,宋爱国,章华涛,等.基于自适应模糊神经网络的机器人路径规划方法[J].东南大学学报: 自然科学版,2012,42(7):637-642.) [4] MALAMUD B D, MOREIN G, TURCOTTE D L. Forest fires: an example of self-organized critical behavior[J].Science,1998,281(9):1840-1842. [5] RICOTTA C, AVENA G, MARCHETTI M. The flaming sadpile: self-organized criticality and wildfires[J].Eeological Modelling,1999,119(1):73-77. [6] TELESCA L.Time-clustering of natural hazards[J]. Natural Hazards, 2007,40(3):593-601. [7] WANG J.S patial-temporal distribution and correlation analysis of fire system[D]. Hefei: University of Science and Technology of China, 2009.(王健.火灾系统时空分布规律及相关性分析[D].合肥: 中国科学技术大学, 2009.) [8] WANG D. Correlation analysis and emergency decision model research on fire rescue time based on fires data[D].Hefei:University of Science and Technology of China,2013:31-63. (王德勇.基于火灾数据的消防时间关联分析与应急决策模型研究[D].合肥:中国科学技术大学,2013:31-63.) [9] ZHANG H. Analysis and forecast of city fire in guangdong province[D].Guangzhou: South China University of Technology,2013:31-63. (张宏. 广东省城市火灾趋势分析与预测[D].广州:华南理工大学,2013:31-63.) [10] LING Z. Information processing of fire detecting based on fuzzy neutral network[D].Chengdu:Sichuan University,2004. (凌智辉. 基于模糊神经网络的火灾探测信息处理[D].成都: 四川大学,2004.) [11] TANG Q. The research of fire data processing methods based on fuzzy neural network[D].Changsha: Hunan University,2010. (汤群芳.基于模糊神经网络的火灾数据处理方法的研究[D].长沙:湖南大学, 2010.) [12] ZHAO T,LI P,CAO J. Study of interval type-2 fuzzy controller for the twin-tank water level system [J].Chinese Journal of Chemical Engineering,2012,20(6):1102-1106. [13] ZHANG J,LI X,YANG H. A soft discretization method of celestial spectrum characteristic line based on fuzzy C-means clustering[J].Spectroscopy and Spectral Analysis,2012,32(5):1435-1438.(张继福,李鑫,杨海峰.基于模糊C-均值聚类的天文光谱特征线软离散化[J].光谱学与光谱分析,2012,32(5):1435-1438.) [14] SUN Y,ZENG W,ZHAO Y, et al. Intelligent method to develop constitutive relationship of Ti-6Al-2Zr-1Mo-1V alloy [J].Transactions of Nonferrous Metals Society of China,2012,22(6):1457-1461. [15] SURESH P, MARIMUTHU K, RANGANATHAN S, et al. Optimization of machining parameters in turning of Al-SiC-Gr hybrid metal matrix composites using grey-fuzzy algorithm [J].Transactions of Nonferrous Metals Society of China,2014,24(9):2805-2814. [16] YU F, ZHAO Y, LI H. Soil moisture retrieval based on GA-BP neural networks algorithm[J]. Journal of Infrared and Millimeter Waves,2012,31(6):283-288.(余凡,赵英时,李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报,2012,31(6):283-288.) [17] LIU X, HU X, WANG T. Rapid assessment of flood loss based on neural network ensemble[J].Transactions of Nonferrous Metals Society of China,2014,24(8):2636-2641. [18] CHEN T,JIANG R. New hybrid stream cipher based on chaos and neural networks[J]. Acta Physica Sinica,2013,62(4):040301.(陈铁明,蒋融融.混沌映射和神经网络互扰的新型复合流密码[J].物理学报,2013,62(4):040301.) [19] LIN Y, ZHENG Z, ZHANG H, et al. Effect of heat treatment process on tensile properties of 2A97 Al-Li alloy: experiment and BP neural network simulation[J].Transactions of Nonferrous Metals Society of China,2013,23(6):1728-1736. [20] LI M,HUANG X,LIU H, et al. Solubility prediction of gases in polymers based on chaotic self-adaptive particle swarm optimization artificial neural networks[J].Acta Chimica Sinica,2013,71(7):1053-1058.(李孟山,黄兴元,柳和生,等.基于混沌自适应粒子群人工神经网络的气体在聚合物中的溶解模型[J].化学学报,2013,71(7):1053-1058.)