Continuous–Discrete Time Neural Network Observer for Nonlinear Dynamic Systems Application to Vehicle Systems

Hasan Abdl Ghani (1) , Quang Truc Dam (1) , Hind Laghmara (2) , Sofiane Ahmed Ali (3) , Samia Ainouz (2) , Xing Gao (1)

1 IRSEEM - Institut de Recherche en Systèmes Electroniques Embarqués
2 LITIS - Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes
3 IBISC - Informatique, BioInformatique, Systèmes Complexes

This paper proposes a novel continuous-discrete (sampled data) time neural network (NSNN) observer for nonlinear systems. It can therefore be applied to systems with a high degree of non-linearity with no prior knowledge of the system dynamics. The proposed observer is a three-layer feedforward neural network that has been intensively trained using the error backpropagation learning algorithm, which includes an e-modification term to ensure robustness of the observer. A structure of the output predictor with a corrective term is added in the structure of the NN observer to overcome the problem of discrete time measurement. Simulations using MATLAB and CarSim are illustrated to demonstrate the performance of the proposed state observer strategy to reconstruct the state variables and parameters of a vehicle system.

Keywords: Sampled data neural network; Nonlinear observer; Backpropagation algorithm; Vehicle systems

Domains: Automatic; Machine Learning [cs.LG]

Hasan Abdl Ghani, Quang Truc Dam, Hind Laghmara, Sofiane Ahmed Ali, Samia Ainouz, et al.. Continuous–Discrete Time Neural Network Observer for Nonlinear Dynamic Systems Application to Vehicle Systems. 22nd World Congress of the International Federation of Automatic Control (World Congress IFAC 2023), Jul 2023, Yokohama, Japan. pp.5685--5690, ⟨10.1016/j.ifacol.2023.10.501⟩. ⟨hal-04015423⟩