Intelligent Global Sensitivity Analysis Based on Deep Learning

被引：0

作者：

Wu S. ^{[1
]}

Qi Z. ^{[2
]}

Li J. ^{[1
]}

机构：

[1] School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai

[2] State Key Laboratory of Complex Electromagnetic Environment Effects on Electronic Information System, Henan, Luoyang

来源：

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University | 2022年 / 56卷 / 07期

关键词：

convolutional neural network; deep learning; Inception module; nonlinear system analysis; sensitivity analysis; Sobol' method;

D O I：

10.16183/j.cnki.jsjtu.2021.191

中图分类号：

学科分类号：

摘要：

This paper proposes an end-to-end method that combines deep learning and sensitivity analysis, which can perform gradient back propagation calculation sensitivity on the saved weight information while training the model. The structure and activation function of the depth model are specially designed to adapt to the subsequent sensitivity calculation. The experimental results conducted on a Boston house prices dataset, a track information fusion dataset, and the G function show that the proposed method is more accurate than classical methods such as Sobol' method when the parameter distribution is uneven, and has a stronger robustness. Compared with the traditional neural network method, the accuracy of the proposed method is higher. The experiment proves that the sample parameter sensitivity obtained by the deep learning model can be used to optimize the model output. © 2022 Shanghai Jiao Tong University. All rights reserved.

引用

页码：840 / 849

页数：9

共 24 条

[1] SALTELLI A, ALEKSANKINA K, BECKER W, Et al., Why so many published sensitivity analyses are false: A systematic review of sensitivity analysis practices, Environmental Modelling and Software, 114, pp. 29-39, (2019)
[2] ZHANG X Y, TRAME M, LESKO L, Et al., Sobol sensitivity analysis: A tool to guide the development and evaluation of systems pharmacology models, CPT: Pharmacometrics and Systems Pharmacology, 4, 2, pp. 69-79, (2015)
[3] ZHOU Yunfeng, ZHOU Yongchao, ZHENG Chunhua, Et al., Sensitivity analysis of parameters of storm water management model with Sobol method, Journal of Zhejiang University (Engineering Science), 53, 2, pp. 347-354, (2019)
[4] WANG Fenghua, WANG Shaojing, SU Lei, Et al., Sensitivity analysis of substation grounding grid parameters based on Sobol' method, High Voltage Engineering, 43, 1, pp. 300-306, (2017)
[5] HE Kun, YAN Zheng, XU Xiaoyuan, Et al., Sobol' method based global sensitivity analysis of power flow in islanded microgrid, Automation of Electric Power Systems, 42, 14, pp. 99-106, (2018)
[6] TANG Y, REED P, WAGENER T, Et al., Comparing sensitivity analysis methods to advance lumped watershed model identification and evaluation, Hydrology and Earth System Sciences, 11, 2, pp. 793-817, (2007)
[7] ROSOLEM R, GUPTA H V, SHUTTLEWORTH W J, Et al., A fully multiple-criteria implementation of the Sobol' method for parameter sensitivity analysis, Journal of Geophysical Research: Atmospheres, 117, pp. 1-18, (2012)
[8] KHORASHADI ZADEH F, NOSSENT J, SARRAZIN F, Et al., Comparison of variance-based and moment-independent global sensitivity analysis approaches by application to the SWAT model, Environmental Modelling and Software, 91, pp. 210-222, (2017)
[9] CUKIER R I, LEVINE H B, SHULER K E., Nonlinear sensitivity analysis of multiparameter model systems, Journal of Computational Physics, 26, 1, pp. 1-42, (1978)
[10] TARANTOLA S, GATELLI D, MARA T A., Random balance designs for the estimation of first order global sensitivity indices, Reliability Engineering and System Safety, 91, 6, pp. 717-727, (2006)

← 1 2 3 →