Optimization of input parameters of ANN–driven plasma source through nature-inspired evolutionary algorithms

Abstract

The plasma sources are a device that produces energetic ion streams for applications in diversified fields. However, operating the ion sources with repeatable performance remains challenging and time-consuming due to its nonlinear nature and the complex relation between the input and output parameters. This maiden study examines the efficacy of nature-inspired evolutionary algorithms (NIEAs) for optimizing the input parameters of an ion source model based on an artificial neural network (ANN) that generates high-density negative hydrogen ions. Hence, it requires the development of a predictive ion source model based on ANNs and further optimized using NIEA. This work optimizes the magnetic field and gas pressure as input parameters using the particle swarm optimization (PSO) technique, simulated annealing (SA), and genetic algorithm (GA). The input parameters for different plasma densities and ion saturation currents are adjusted for a constant Radio Frequency (RF) power (900 watts) at 6 mTorr, 7.5 mTorr, 30 mTorr gas pressures and magnetic fields of 40G, 55G, and 86G. The number of iterations, the computation time, and the Root Mean Squared Error (RMSE) defines the performance of the algorithms. SA, GA, and PSO optimized the input parameters by averaging 569, 63, and 32 iterations, while the average computation time remained at 54 seconds, 27 seconds, and 4 seconds, respectively. The RMSEs for SA, GA, and PSO are 1.57, 1.56, and 0.54. The comparison shows that the PSO approach is the most efficient regarding the number of iterations, computation time and RMSE.