Weld-Quality Prediction Algorithm Based on Multiple Models Using Process Signals in Resistance Spot Welding
نویسندگان
چکیده
An efficient nondestructive testing method of resistance spot weld quality is essential in evaluating the all welded joints automotive components a car body production line. This study proposes prediction algorithm for welding that can predict geometrical and physical properties spot-welded joint evaluate based on acceptance criteria. To this end, four statistical models main joint, including tensile shear strength, indentation depth, expulsion occurrence, failure mode, were estimated material information, dynamic resistance, electrode displacement signals. The significance was then verified through an analysis variance. accuracies 94.3%, 93.4%, 97.5%, 85.0% modes, respectively. A evaluation methodology overall requirements authorized standards proposed using models.
منابع مشابه
Neural Network-Based Resistance Spot Welding Control and Quality Prediction
This paper describes the development and evaluation of neural network-based systems for industrial welding process control and weld quality assessment. The developed systems utilize recurrent neural networks for process control and both recurrent networks and static networks for quality prediction. The first section describes a system capable of both welding process control and real-time weld q...
متن کاملAnalysis of Resistance Spot Welding Process Parameters Effect on the Weld Quality of Three-steel Sheets Used in Automotive Industry: Experimental and Finite Element Simulation
In the present research, the effects of spot-welding process parameters on the nugget diameter and electrode penetration depth of spot-welded joints were investigated. To achieve this, a spot-welded joint of three-thin sheet low carbon steels (same thicknesses of 0.8 mm) was simulated as an electerical-thermal-mechanical coupling of 3D finite element model. After validating the finite element s...
متن کاملQuality Evaluation and Automatic Classification in Resistance Spot Welding by Analyzing the Weld Image on Metal Bands by Computer Vision
This paper introduces a novel method for the quality evaluation of resistance spot welds. The evaluation is based on computer vision methods, which allow nondestructive on-line real-time processing. The input of the system is the image of a weld imprint on a metal band which covers the electrodes against wear and soiling. In order to find the position of the resistance spot welds, we describe a...
متن کاملWelding challenges facing advanced automotive steels in resistance spot welding process: A review
Nowadays, the use of advanced high strength steels (AHSSs) in body-in-white is one of the hot applied strategies which is followed by the most of the automakers. The study of weldability and weld challenges facing these steels in resistance spot welding process as the most widely used process in the assembly lines of the automotive industry is essential to use the outstanding mechanical respons...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Metals
سال: 2021
ISSN: ['2075-4701']
DOI: https://doi.org/10.3390/met11091459