Genetic Neural Network for Apparent Resistivity Solution of Transient Electromagnetic
Qin Shanqiang1, Fu Zhihong1, Zhu Xuegui1, Ji Yongliang2
1. State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing University Chongqing 400044 China; 2. Electric Power Research Institute Chongqing Electric Power Company Chongqing 401123 China
Abstract The genetic neural network is applied to compute the central-loop transient electromagnetic (TEM) apparent resistivity. According to the central loop TEM response, a relationship between inputs and outputs of an ANN as well as three-layer architecture with single input and single output for ANN is designed. The ANN sample sets are calculated, and the number of hidden layer neuron is determined through trial method. A genetic algorithm is introduced to optimize connection weights of the ANN and then a GABP neural network with the optimal connection weights. A nonlinear equation of the TEM response is fitted by GABP neural network, and transient parameter value is obtained. The transient parameter value and kernel value from measured data are corresponding one by one. Finally, the apparent resistivity is calculated. Two examples with GABP neural network are presented. The first one is a forward calculated model of high impedance abnormal body in uniform half space, the second one is the grounding grid with the structural shape ‘?’ in a substation of power system. Pseudo-section of apparent resistivity is obtained, and good effects to solve inverse problem is achieved. The comparisons between the theoretical models and the measured data show that the GABP is a usefulness algorithm, which can reduce much computing time of TEM apparent resistivity. This method provides the base technology for a real-time fault diagnosis platform of grounding grids using TEM.
[1] Ward S H, Hohmann G W. Electromagnetic theory for geophysical applications//electromagnetic methods in applied geophysics: voume 1, theory[M]. Australian Society of Exploration Geophysicists, 1988. [2] Spies B R, Raiche A P. Calculation of apparent conductivity for the transient electromagnetic (coincident loop) method using an HP-67 calculator[J]. Geophysics, 1980, 45(7): 1197-1204. [3] Raiche A P, Spies B R. Coincident loop transient electromagnetic master curves for interpretation of two-layer earths[J]. Geophysics, 1981, 46(1): 53-64. [4] Christensen N B. 1D imaging of central loop transient electromagnetic soundings[J]. Journal of Environ- mental & Engineering Geophysics, 1995, 2(1): 53-66. [5] 付志红,孙天财,陈清礼,等. 斜阶跃场源瞬变电磁法的全程视电阻率数值计算[J]. 电工技术学报, 2008, 23(11): 15-21. Fu Zhihong, Sun Tiancai, Chen Qingli, et al. Transient electromagnetic apparent resistivity imaging for break point diagnosis of grounding grids[J]. Transactions of China Electrotechnical Socity, 2008, 23(11): 15-21. [6] Rob Callan. Artificial intelligence[M]. Beijing: Publishing House of Electronics Industry, 2004. [7] Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. [8] Hecht-Nielsen R. Theory of the backpropagation neural network[J]. IEEE International Joint Con- ference on Neural Networks, 1988, 1(S1): 445-448. [9] Mirko van der Baan, Christian Jutten. Neural networks in geophysical applications[J]. Geophysics, 2000, 65(4): 1032-1047. [10] Smith J A. LA1 inversion using a back-propagation neural network trained with a multiple scattering model[J]. IEEE Transactions on Geoscience and Remote Sensing, 1993, 31(5): 1102-1106. [11] Russel B. Neural network applications in geophysics[C]// Evolving Geophysics through Innovation, CESG National Convention, Calgary, Canada, 2005: 339-341. [12] Srinivas Y, Raj A S, Oliver D H, et al. A robust behavior of feed forward back propagation algorithm of artificial neural networks in the application of vertical electrical sounding data inversion[J]. Geoscience Frontiers, 2012, 3: 729-736. [13] Calderón-Macías C, Sen M K, Stoffa P L. Artificial neural networks for parameter estimation in geophy- sics[J]. Geophysical Prospecting, 2000, 48(1): 21- 47. [14] 谷鑫, 胡升, 史婷娜, 等. 基于神经网络的永磁同步电机多参数解耦在线辨识[J]. 电工技术学报, 2015, 30(6): 114-121. Gu Xin, Hu Sheng, Shi Tingna, et al. Muti-parameter decoupling online identification of permanent magnet synchronous motor based on neural network[J]. Transactions of China Electrotechnical Socity, 2015, 30(6): 114-121. [15] 罗新, 牛海清, 来立永, 等. 粒子群优化自适应小波神经网络在带电局放信号识别中的应用[J]. 电工技术学报, 2014, 29(10): 326-333. Luo Xin, Niu Haiqing, Lai Liyong, et al. Application of adaptive wavelet neural network based on particle swarm optimization algorithm in online PD pattern recognition[J]. Transactions of China Electro- technical Socity, 2014, 29(10): 326-333. [16] 刘毅, 谭国俊, 何凤有, 等. 基于NNs-MRAS无速度传感器双馈电机LQR控制[J]. 电工技术学报, 2014, 29(7): 140-146. Liu Yi, Tan Guojun, He Fengyou, et al. LQR controller for doubly fed induction motor with speed sensorless control based on NNs-MRAS method[J]. Transactions of China Electrotechnical Socity, 2014, 29(7): 140-146. [17] 李龙, 魏靖, 黎灿兵, 等. 基于人工神经网络的负荷模型预测[J]. 电工技术学报, 2015, 30(8): 225- 230. Li Long, Wei Jing, Li Canbing, et al. Prediction of load model based on artificial neural network[J]. Transactions of China Electrotechnical Socity, 2015, 30(8): 225-230. [18] 汪先兵, 费树岷, 徐清扬, 等. BP神经网络PID控制磁真空开关储能电容恒流充电特性分析[J]. 电工技术学报, 2015, 30(10): 212-218. Wang Xianbing, Fei Shumin, Xu Qingyang, et al. Constant current charging characteristic analysis of storage capacitor based on BP neural network PID control for permanent magnet vacuum switch[J]. Transactions of China Electrotechnical Socity, 2015, 30(10): 212-218. [19] 陈伟根, 滕黎, 刘军, 等. 基于遗传优化支持向量机的变压器绕组热点温度预测模型[J]. 电工技术学报, 2014, 29(1): 44-51. Chen Weigen, Teng Li, Liu Jun, et al. Transformer winding hot-spot temperature prediction model of support vector machine optimized by genetic algorithm[J]. Transactions of China Electrotechnical Socity, 2014, 29(1): 44-51. [20] 付志红, 余慈拱, 侯兴哲, 等. 瞬变电磁法视电阻率成像的接地网断点诊断方法[J]. 电工技术学报, 2014, 29(9): 253-259. Fu Zhihong, Yu Cigong, Hou Xingzhe, et al. Transient electromagnetic apparent resistivity imaging for break point diagnosis of grounding grids[J]. Transactions of China Electrotechnical Socity, 2014, 29(9): 253-259. [21] Nabighian M N. Quasi-static transient response of a conducting half-space-an approximate repre- sentation[J]. Geophysics, 1979, 44(10): 1700-1705. [22] 姚仲敏, 潘飞, 沈玉会, 等. 基于GA-BP和POS- BP神经网络的光伏电站出力短期预测[J]. 电力系统保护与控制, 2015, 43(20): 83-89. Yao Zhongmin, Pan Fei, Shen Yuhui, et al. Short- term prediction of photovoltaic power generation output based on GA-BP and POS-BP neural network[J]. Power System Protection and Control, 2015, 43(20): 83-89. [23] 许童羽, 马艺铭, 曹英丽, 等. 基于主成分分析和遗传优化BP神经网络的光伏输出功率短期预测[J]. 电力系统保护与控制, 2016, 44(22): 90-95. Xu Tongyu, Ma Yiming, Cao Yingli, et al. Short term forecasting of photovoltaic output power based on principal component analysis and genetic optimi- zation of BP neural network[J]. Power System Protection and Control, 2016, 44(22): 90-95.
2017, Vol. 32 
