Parametric Identification of the Inverted Pendulum System: a Differential Evolution Approach

https://doi.org/10.58571/CNCA.AMCA.2025.004

Resumen: This work proposes a straightforward methodology to address the problem of parametric identification of an inverted pendulum system using the Differential Evolution metaheuristic optimization algorithm. Five variants of the algorithm are evaluated to determine which one performs best for this specific application, the main difference between the variants is the mutation stage. To validate the results, 30 simulations were carried out for each variant using both noise-free and noise-contaminated signals. This approach enables the use of robust statistical metrics to support the reliability of the results. The experiments show that the rand/2/bin variant yields the best performance in terms of accuracy and consistency under both noisy and noise-free conditions. This conclusion is based on analyzing the average error values and the variability observed across the simulations.

¿Cómo citar?

Mejía-Delgadillo, M., Garrido Moctezuma, R. & Mezura Montes, E. (2025). Parametric Identification of the Inverted Pendulum System: a Differential Evolution Approach. Memorias del Congreso Nacional de Control Automático 2025, pp. 20-25. https://doi.org/10.58571/CNCA.AMCA.2025.004

Palabras clave

Parametric identification, Differential Evolution, Inverted pendulum.

• Bay, J. (1999). Fundamentals of linear state space systems. McGraw-Hill Higher Education.
• Belegundu, A.D. and Chandrupatla, T.R. (2019). Optimization concepts and applications in engineering. Cambridge University Press.
• Corriou, J.P. and Courriou, J.P. (2004). Process control. Springer.
• Das, S. and Suganthan, P.N. (2011). Differential evolution: A survey of the state-of-the-art. IEEE Transactions on Evolutionary Computation, 15(1), 4–31. doi:10.1109/TEVC.2010.2059031.
• Dyvak, M., Manzhula, V., and Dyvak, T. (2022). Identification of parameters of interval nonlinear models of static systems using multidimensional optimization. Computational Problems of Electrical Engineering, 12(2), 5–13.
• Fantoni, I. and Lozano, R. (2012). Non-linear control for underactuated mechanical systems. Springer Science & Business Media.
• Hafez, I. and Dhaouadi, R. (2023). Identification of mechanical parameters in flexible drive systems using hybrid particle swarm optimization based on the quasinewton method. Algorithms, 16(8), 371.
• Jaan, K. (2009). Numerical methods in engineering with matlab.
• Jumanov, I.I., Xolmonov, S.M., and Diumanov, I. (2024). Identification of non-stationary objects based on multiparameter optimization tools. In 2024 International Russian Automation Conference (RusAutoCon), 1146–1152. IEEE.
• Navidi, W.C. (2006). Statistics for engineers and scientists, volume 2. McGraw-Hill New York.
• Price, K., Storn, R.M., and Lampinen, J.A. (2006). Differential Evolution: A Practical Approach to Global Optimization. Springer Science & Business Media.
• Qian, J., Zhang, H., and Wang, S. (2025). Parameter identification of the pv systems based on an adapted version of human evolutionary optimizer. Scientific Reports, 15(1), 7375.
• Semenov, A., Volkov, A., and Schipakina, N. (2019). Parametric identification of nonlinear systems by aggregation of static and dynamic neural networks. In 2019 International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon), 1–6. IEEE.
• Storn, R. and Price, K. (1997). Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 11(4), 341–359.