A Novel Adaptive PID Controller Design for a PEM Fuel Cell Using Stochastic Gradient Descent with Momentum Enhanced by Whale Optimizer

Abstract

This paper presents an adaptive PID using stochastic gradient descent with momentum (SGDM) for a proton exchange membrane fuel cell (PEMFC) power system. PEMFC is a nonlinear system that encounters external disturbances such as inlet gas pressures and temperature variations, for which an adaptive control law should be designed. The SGDM algorithm is employed to minimize the cost function and adapt the PID parameters according to the perturbation changes. The whale optimization algorithm (WOA) was chosen to enhance the adaptive rates in the offline mode. The proposed controller is compared with PID stochastic gradient descent (PIDSGD) and PID Ziegler Nichols tuning (PID-ZN). The control strategies’ robustnesses are tested under a variety of temperatures and loads. Unlike the PIDSGD and PID-ZN controllers, the PIDSGDM controller can attain the required control performance, such as fast convergence and high robustness. Simulation results using Matlab/Simulink have been studied and illustrate the effectiveness of the proposed controller.

Temperature Control of Fuel Cell Based on PEI-DDPG

“…Experience playback comprises two components: storage sampling and experience We define µ s θ µ and Q s, a θ Q to represent the policy network function and value network function, respectively, where θ µ and θ ′ µ denote the neural network parameters of Main-PolicyNet and Target-PolicyNet, respectively, and θ Q and θ ′ Q denote the neural network parameters of Main-QNet and Target-QNet, respectively. θ µ is updated by the gradient method, as in Equation ( 13), θ Q is updated by minimizing the loss function, as in Equation ( 14), and θ ′ µ and θ ′ Q are updated using a soft method as shown in Equation (15).…”

“…Some fuzzy-based control algorithms, including fuzzy control [13], incremental fuzzy control [14], and fuzzy incremental PID [15], are employed for PEMFC temperature regulation. Additionally, multi-input, multi-output fuzzy control is utilized [16].…”

PEMFC Current Control Using a Novel Compound Controller Enhanced by the Black Widow Algorithm: A Comprehensive Simulation Study

“…Simulation results exhibit that the PI shows good performance in terms of rising time, overshoot, undershoot, and steady-state error. Silaa et al [15] implemented an adaptive PID control strategy using stochastic gradient descent with momentum (SGDM) to control a DC/DC boost converter in order to achieve and obtain the required performance under a variety of disturbances. Simulation results show that the PIDSGDM controller can attain fast convergence and high robustness under extreme changes in temperature and load.…”

“…The previous equations can yield (15), which is the state-space equation that represents the boost converter dynamics [38]: The parameters of the DC/DC boost converter used in the simulation are presented in Table 2.…”

An Amplified Salp Swarm Optimization Algorithm for Maximum Power Point Tracking Control of Proton Exchange Membrane Fuel Cells

“…The working duty cycle of the DC/DC converter used for FC interface is set by the MPPT controllers during MPP operation. [18][19][20] In the base works, [21][22][23] several MPPT techniques such as perturb & observe (P&O), incremental conductance (INC), fuzzy logic control (FLC), adaptive neurofuzzy inference system (ANFIS), etc, for obtaining maximum power extraction from FCs are used. However, the baseline models [24][25][26] have the major drawbacks of high tracking time, reduced steady-state performance, high cost, and system complexity.…”