A novel entropy-based sensitivity analysis approach for complex systems

The modern electronic systems have become very complex with a high number of potential factors that may affect the systems' behavior. Sensitivity analysis may be employed to simplify the analysis of such systems and identify the most important factors upfront. The paper introduces two new sensitivity analysis methods based on the measure of entropy, which overcome the limitation of several state-of-the-art methods imposing a specific design of experiments and a high computational cost, measured as the number of simulations (measurements) needed, for the sensitivity analysis. Their performance is compared to other methods based on variance decomposition and One-Factor-at-a-Time screening. The proposed methods named the Entropy Simple method and the Entropy Pair one are applied on a set of custom functions and an E-Bike application. They proved to have comparable accuracy to the state-of-the-art methods with the advantage of a lower computational cost and which does not increase with the number of factors.

[1]  D. Shahsavani,et al.  Variance-based sensitivity analysis of model outputs using surrogate models , 2011, Environ. Model. Softw..

[2]  Charles F. Hockett,et al.  A mathematical theory of communication , 1948, MOCO.

[3]  Andi Buzo,et al.  On the influence of angle sensor nonidealities on the torque ripple in PMSM systems — An analytical approach , 2016, 2016 13th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD).

[4]  Andi Buzo,et al.  COMPARISON OF SENSITIVITY ANALYSIS METHODS IN HIGH-DIMENSIONAL VERIFICATION SPACES , 2016 .

[5]  R. Pastorelli,et al.  Design of surface Brillouin scattering experiments by sensitivity analysis , 2000 .

[6]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[7]  D. Hamby.  A comparison of sensitivity analysis techniques. , 1995, Health physics.

[8]  D. Hamby.  A review of techniques for parameter sensitivity analysis of environmental models , 1994, Environmental monitoring and assessment.

[9]  W. J. Langford.  Statistical Methods , 1959, Nature.

[10]  Stefano Tarantola,et al.  Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models , 2004 .

[11]  Stefano Tarantola,et al.  Random balance designs for the estimation of first order global sensitivity indices , 2006, Reliab. Eng. Syst. Saf..

[12]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[13]  Stefano Tarantola,et al.  Uncertainty and global sensitivity analysis of road transport emission estimates , 2004 .

[14]  Veronica Czitrom,et al.  One-Factor-at-a-Time versus Designed Experiments , 1999 .

[15]  Liviu Goras,et al.  Simulation-based approach to application fitness for an E-Bike , 2016, 2016 IEEE Sensors Applications Symposium (SAS).

[16]  Paola Annoni,et al.  Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index , 2010, Comput. Phys. Commun..

[17]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.