2014/11/10 by Ali Mesbah, Mesbah, Ali, Stefan Streif +1
Computer Science · Decision Sciences · #Advanced Multi-Objective Optimization Algorithms #FOS: Electrical engineering #FOS: Mathematics #Optimal Experimental Design Methods #Optimization and Control (math.OC) #Probabilistic and Robust Engineering Design #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1411.2683
openalex publication_date 2014/11/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Accurate estimation of parameters is paramount in developing high-fidelity\nmodels for complex dynamical systems. Model-based optimal experiment design\n(OED) approaches enable systematic design of dynamic experiments to generate\ninput-output data sets with high information content for parameter estimation.\nStandard OED approaches however face two challenges: (i) experiment design\nunder incomplete system information due to unknown true parameters, which\nusually requires many iterations of OED; (ii) incapability of systematically\naccounting for the inherent uncertainties of complex systems, which can lead to\ndiminished effectiveness of the designed optimal excitation signal as well as\nviolation of system constraints. This paper presents a robust OED approach for\nnonlinear systems with arbitrarily-shaped time-invariant probabilistic\nuncertainties. Polynomial chaos is used for efficient uncertainty propagation.\nThe distinct feature of the robust OED approach is the inclusion of chance\nconstraints to ensure constraint satisfaction in a stochastic setting. The\npresented approach is demonstrated by optimal experimental design for the\nJAK-STAT5 signaling pathway that regulates various cellular processes in a\nbiological cell.\n