Investigation of the Extrapolation Capability of an Artificial Neural Network Algorithm in Combination with Process Signals in Resistance Spot Welding of Advanced High-Strength Steels

Abstract

Resistance spot welding is an established joining process for the production of safety-relevant components in the automotive industry. Therefore, consecutive process monitoring is essential to meet the high quality requirements. Artificial neural networks can be used to evaluate the process parameters and signals, to ensure individual spot weld quality. The predictive accuracy of such algorithms depends on the provided training data set, and the prediction of untrained data is challenging. The aim of this paper was to investigate the extrapolation capability of a multi-layer perceptron model. That means, the predictive performance of the model was tested with data that clearly differed from the training data in terms of material and coating composition. Therefore, three multi-layer perceptron regression models were implemented to predict the nugget diameter from process data. The three models were able to predict the training datasets very well. The models, which were provided with features from the dynamic resistance curve predicted the new dataset better than the model with only process parameters. This study shows the beneficial influence of process signals on the predictive accuracy and robustness of artificial neural network algorithms. Especially, when predicting a data set from outside of the training space.

Effects of Substrate Microstructure and Chemical Composition on Liquid Metal Embrittlement in Galvanized 3rd Generation AHSS

“…Intermetallic formation, especially at the coating-substrate interface is considered to be especially important in the context of LME, as iron enrichment of the liquid (e.g., due to substrate dissolution a continuous reaction layer creates a physical separation between liquid zinc and the steel substrate, and the growth of zinc-containing intermetallics consumes Zn-rich liquid). Dissolved iron in the liquid coating should also reduce the Zn activity and influence Zn penetration of grain boundaries, consistent with the reduced LME encountered in galvannealed AHSS (having a Fe-Zn alloyed coating) in comparison to hot-dip galvanized AHSS [14][15][16] having a relatively unalloyed Zn coating. With this context, it is insightful to consider the influence of alloy elements on intermetallic formation.…”

Feasibility Analysis and Countermeasures of Psychological Health Training Methods for Volleyball Players Based on Artificial Intelligence Technology

“…Artificial neural network, or short-form neural network, is a mathematical model that simulates the structural operation characteristics of animal neural network [ 17 , 18 ]. Neural network algorithm is an adaptive non-linear dynamic system composed of a large number of simple basic components.…”