粒子群优化算法是一种启发式的全局优化算法，将其与 BP 神经网络结合，能够有效地改善 BP 神经网络在进行电阻率层析反演中的收敛速度和求解质量。提出一种基于混沌振荡的粒子群算法，使用混沌振荡曲线来自适应调整惯性权重w以提高PSO算法的全局寻优能力，并使用其训练和优化BP神经网络的权值和阈值。比较不同隐含层节点数目和惯性权重w值对反演结果的影响，并给出混沌振荡PSO-BP算法非线性反演的具体实现方案。对均匀半空间中异常体理论模型进行反演，实验结果表明：混沌振荡PSO-BP不依赖初始模型，在稳定性和准确性上优于BP反演和标准PSO-BP反演，成像质量优于最小二乘法反演的。
The particle swarm optimization (PSO) is a heuristic global optimization method, which can effectively improve the convergence speed and the results quality with the BP neural network in resistivity tomography 2-D nonlinear inversion. A chaotic oscillation PSO algorithm was presented, and the chaos oscillation curve was used to adjust the inertia weight adaptively and improve the global optimum capability of PSO. And this algorithm was used to train and optimize the weights and threshold values of the BP neural network. The impacts of different numbers of the hidden layer nodes and types of the inertia weight to the inversion result were compared, and an implementation of chaotic oscillation PSO-BP algorithm was given. The half space abnormity synthetic model was inversed. The results show that the chaotic oscillation PSO-BP algorithm that is independent of the initial model has better performance than BP and standard PSO-BP algorithm in stability and accuracy, and has higher imaging quality than least square inversion.
参考文献
| [1] | SHIMA H;SAKAYAMA T.Resistivity tomography：An approach to 2-D resistivity inverse problem[A].New Orleans:Society of Exploration Geophysicists,1987:59-61. |
| [2] | 卢元林;王兴泰;王若;孙仁国 王劲松 .电阻率成像反演中的模拟退火方法[J].地球物理学报,1999,42(z1):225-233. |
| [3] | SHIMA H .2-D and 3-D resistivity image reconstruction using crosshole data[J].GEOPHYSICS,1992,57(10):1270-1281. |
| [4] | M. H. Loke;R. D. Barker .Least-squares deconvolution of apparent resistivity pseudosections[J].Geophysics,1995(6):1682-1690. |
| [5] | ZOHDY A A R .A new method for the automatic interpretation of Schlumbeger and Wenner sounding curves[J].GEOPHYSICS,1989,54(02):245-253. |
| [6] | Vincent Lesur;Michel Cuer;Andre Straub;Andre Straub;Andre Straub .2-D and 3-D interpretation of electrical tomography measurements, Part 2: The inverse problem[J].Geophysics,1999(2):396-402. |
| [7] | 徐海浪,吴小平.电阻率二维神经网络反演[J].地球物理学报,2006(02):584-589. |
| [8] | Jha, MK;Kumar, S;Chowdhury, A .Vertical electrical sounding survey and resistivity inversion using genetic algorithm optimization technique[J].Journal of Hydrology,2008(1/2):71-87. |
| [9] | J.P. Fernandez Alvarez;J.L. Fernandez Martinez;C.O. Menendez Perez .Feasibility Analysis of the Use of Binary Genetic Algorithms as Importance Samplers Application to a 1-D DC Resistivity Inverse Problem[J].Mathematical geology,2008(4):375-408. |
| [10] | Liu, B.;Li, S.C.;Nie, L.C.;Wang, J.;L, X.;Zhang, Q.S..3D resistivity inversion using an improved Genetic Algorithm based on control method of mutation direction[J].Journal of Applied Geophysics,2012:1-8. |
| [11] | FERNáNDEZ M J L;ESPERANZA G G .PSO:A powerful algorithm to solve geophysical inverse problems application to a 1D-DC resistivity case[J].Journal of Applied Geophysics,2012,71(01):13-25. |
| [12] | GAD E Q;KEISUKE U .Inversion of DC resistivity data usingneural network[J].GEOPHYSICAL PROSPECTING,2001,49(04):417-430. |
| [13] | Maiti, S.;Erram, V.C.;Gupta, G.;Tiwari, R.K..ANN based inversion of DC resistivity data for groundwater exploration in hard rock terrain of western Maharashtra (India)[J].Journal of Hydrology,2012:294-308. |
| [14] | Using artificial neural networks to invert 2D DC resistivity imaging data for high resistivity contrast regions: A MATLAB application[J].Computers & geosciences,2009(11):2268. |
| [15] | KENNEDY J;EBERHART R.Particle swarm optimization[A].Washington DC:IEEE Computer Society,1995:1942-1948. |
| [16] | 史峰;王小川;郁磊.Matlab 神经网络案例分析[M].北京:北京航空航天大学出版社,2010 |
| [17] | 师学明,肖敏,范建柯,杨国世,张旭辉.大地电磁阻尼粒子群优化反演法研究[J].地球物理学报,2009(04):1114-1120. |
| [18] | 闫永利,陈本池,赵永贵,陈谮,马晓冰,孔祥儒.电阻率层析成像非线性反演[J].地球物理学报,2009(03):758-764. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%