International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

Using the method of binary logistic regression, the dependence of dichotomous variables on one or more, quantitative or qualitative independent variables is studied. In order to solve problems with binary dependent variables, binary choice model estimation methodologies, such as logistic regression (logit) and probit regression (probit), can be implemented. The logistic model is based on the logistic distribution, while the probit model is based on the normal distribution. In this paper the binary logistic regression methodology is applied for obtaining defect-free welds by electron beam welding process, based on experimental data.

This paper considers the process electron beam welding of stainless steel type 1H18NT in vacuum. Based on experimental data, the influence of the variations of the following process parameters: electron beam power, welding velocity, the distances from the magnetic lens of the electron gun to the beam focus and to the surface of the treated sample is investigated.

Neural and regression models for the geometry characteristics of the welded joints: surface of the weld cross-sections, weld depths and mean weld widths of the samples are estimated, as well as models for defining the areas of the process parameters, where the appearance of defects is or is not expected. The obtained models are used for developing the graphical user interface aiming investigation and prediction of the electron beam welding characteristics and process parameter optimization. This software can be implemented for supporting the operator’s choice of appropriate work regimes, obtaining the required welds quality standards, for education and investigations.

This article discusses a modelling approach for the welded seam form obtained by electron beam welding based on experimental data and types of mathematical functions. The process of electron beam welding is carried out by dividing the electron beam into two parts, resulting in the formation of two liquid baths. The samples that are welded are made of stainless steel with a change in process parameters: the distance between the two electron beam parts and the ratio of the power distribution between the two beam parts, the frequency of the deflection signal, the beam current, and the welding speed. Focusing current is of constant value. The weld cross sections shown in different process parameters are used to evaluate their shape using standard mathematical function – Gaussian functions.

This paper considers the process electron beam welding in vacuum of stainless steel 1H18NT. Neural network based models are developed and used for the description of the defectiveness, depending on the process parameters – electron beam power, welding velocity, the distance between the main surface of the magnetic lens of the electron gun and the beam focusing plane and the distance between the main surface of the magnetic lens of the electron gun and the sample surface. Neural network (NN) models, based on a multi-layered feedforward neural network, trained with Levenberg-Marquardt error backpropagation algorithm are compared with NN models, based on Pattern recording neural network, trained with Conjugate Gradient Algorithm. The neural networks are trained, verified and tested using a set of experimental data. The obtained models are implemented to predict areas of process parameters, where the appearance of defects is most probable and the location of welding regimes that should be avoided.