Interpretable PID parameter tuning for control engineering using general dynamic neural networks: An extensive comparison

An Intelligent Model-Based Effective Approach for Glycemic Control in Type-1 Diabetes

Type-1 diabetes mellitus (T1DM) is a challenging disorder which essentially involves regulation of the glucose levels to avoid hyperglycemia as well as hypoglycemia. For this purpose, this research paper proposes and develops control algorithms using an intelligent predictive control model, which is based on a UVA/Padova metabolic simulator. The primary objective of the designed control laws is to provide an automatic blood glucose control in insulin-dependent patients so as to improve their life quality and to reduce the need of an extremely demanding self-management plan. Various linear and nonlinear control algorithms have been explored and implemented on the estimated model. Linear techniques include the Proportional Integral Derivative (PID) and Linear Quadratic Regulator (LQR), and nonlinear control strategy includes the Sliding Mode Control (SMC), which are implemented in this research work for continuous monitoring of glucose levels. Performance comparison based on simulation results demonstrated that SMC proved to be most efficient in terms of regulating glucose profile to a reference level of 70 mg/dL compared to the classical linear techniques. A brief comparison is presented between the linear techniques (PID and LQR), and nonlinear technique (SMC) for analysis purposes proving the efficacy of the design.

Polynomial Recurrent Neural Network-Based Adaptive PID Controller With Stable Learning Algorithm

This paper introduces a novel structure of a polynomial weighted output recurrent neural network (PWORNN) for designing an adaptive proportional—integral—derivative (PID) controller. The proposed adaptive PID controller structure based on a polynomial weighted output recurrent neural network (APID-PWORNN) is introduced. In this structure, the number of tunable parameters for the PWORNN only depends on the number of hidden neurons and it is independent of the number of external inputs. The proposed structure of the PWORNN aims to reduce the number of tunable parameters, which reflects on the reduction of the computation time of the proposed algorithm. To guarantee the stability, the optimization, and speed up the convergence of the tunable parameters, i.e., output weights, the proposed network is trained using Lyapunov stability criterion based on an adaptive learning rate. Moreover, by applying the proposed scheme to a nonlinear mathematical system and the heat exchanger system, the robustness of the proposed APID-PWORNN controller has been investigated in this paper and proven its superiority to deal with the nonlinear dynamical systems considering the system parameters uncertainties, disturbances, set-point change, and sensor measurement uncertainty.