Distributed parameter system identification using finite element differential neural networks

• Published in: Applied soft computing Vol. 43; pp. 633 - 642
• Main Authors: Aguilar-Leal, O., Fuentes-Aguilar, R.Q., Chairez, I., García-González, A., Huegel, J.C.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2016
• Subjects: CUDA/C; Differential neural network; Distributed parameter systems; Finite element method; Non-parametric identification; Parallel numerical solutions; Finite element method; CUDA/C; Parallel numerical solutions; Differential neural network; Distributed parameter systems; Non-parametric identification
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2016.01.004

[Display omitted] •We proposed a method to solve the identification of uncertain distributed parameter systems.•We developed a novel DNN structure based on the finite element method.•We derived adaptive learning laws using Lyapunov's second method.•The identification algorithm is developed in Nvidia's CUDA/C to reduce the execution time.•The FEM-DNN algorithm that we present was compared with a neural network trained using group search optimization or GPO-NN, and showed a superior performance.•The algorithm was validated with a 3D simulated DPS and tested on a physical 2D experiment. Most of the previous work on identification involves systems described by ordinary differential equations (ODEs). Many industrial processes and physical phenomena, however, should be modeled using partial differential equations (PDEs) which offer both spatial and temporal distributions that are simply not available with ODE models. Systems described by a PDE belong to a class of system called distributed parameter system (DPS). This article presents a method for solving the problem of identification of uncertain DPSs using a differential neural network (DNN). The DPS, assumed to be described by a PDE, is approximated using the finite element method (FEM). The FEM discretizes the domain into a set of distributed and connected nodes, thereby, allowing a representation of the DPS in a finite number of ODEs. The proposed DNN follows the same interconnection structure of the FEM, thus allowing the DNN to identify the FEM approximation of the DPS in both 2D and 3D domains. Lyapunov's second method was used to derive adaptive learning laws for the proposed DNN structure. The identification algorithm, here developed in Nvidia's CUDA/C to reduce the execution time, runs mostly on the graphics processing unit (GPU). A physical experiment served to validate the 2D case. In the experiment, the DNN followed the trajectory of 57 markers that were placed on an undulating square piece of silk. The proposed DNN is compared against a method based on principal component analysis and an artificial neural network trained with group search optimization. In addition to the 2D case, a simulation validated the 3D case, where input data for the DNN was generated by solving a PDE with appropriate initial and boundary conditions over an unitary domain. Results show that the proposed FEM-based DNN approximates the dynamic behavior of both a real 2D and a simulated 3D system.