Determination of the Half-Beam cone angle for Pierce electron gun design using an artificial neural network

• Various electron gun design methods are utilized to determine the preliminary electron gun geometry. • The half-beam cone angle plays a vital role in determining the electron gun geometry. • In this study, a novel method is proposed for designing the electron gun geometry using an artificial neural network. • A comparison of ANN results with three well-known methods including Vaughan’s iterative method, Tiwary’s noniterative method, and Yang’s modified noniterative method, demonstrates that ANN has better performance than other methods. Various electron gun design methods, especially iterative and noniterative, are generally utilized for preliminary electron gun design based on the input design beam parameters. In the electron gun design methods, calculating the half-beam cone angle is crucial, as it significantly influences the determination of the electron gun’s geometry. In this paper, an Artificial Neural Network (ANN) model was proposed for predicting the half-beam cone angle. The ANN model was trained and tested using experimental data obtained from previously documented studies on electron guns. The predicted results of the proposed ANN model were compared with three well-known methods in the electron gun design: iterative method, noniterative method, and modified noniterative method. The comparison indicates that the proposed ANN model achieves better performance than the other methods, with a Main Relative Error (MRE) of less than 5%.