Prediction of welding residual stresses using machine learning: Comparison between neural networks and neuro-fuzzy systems

Mathew, Jino; Griffin, John; Alamaniotis, Miltiadis; Kanarachos, Stratis; Fitzpatrick, Michael E.

doi:10.1016/j.asoc.2018.05.017

Cited by 84 publications

(28 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eqs. (2)(3)(4) are then used to obtain regression equation predicted micro-pore attributes. The different MLAs are also utilized to obtain micro-pore attributes corresponding to the said 10000 input parameters.…”

Section: Performance Evaluation Of the Mlas Through Monte-carlo Reliability Analysismentioning

confidence: 99%

Study of Micro-porosity in Electron Beam Butt Welding

Das¹,

Dinda²,

Das³

et al. 2021

Preprint

View full text Add to dashboard Cite

As complete elimination of porosity from the weld is very difficult, the next option available is to minimize this weld porosity, which is crucial for the safe performance of the welded components. However, this investigation through experiments alone is very tedious and time consuming. Additionally, very limited models are available in the literature for accurate prediction of different porosity attributes. The present study, thus, addressees both the experimental as well as modelling aspect on the study of micro-porosity during Electron Beam Welding (EBW) of SS304 plates. Welding parameters are reported to have significant influence on the micro-porosity. Hence, the influences of these parameters on micro-porosity attributes, namely pores number, average diameter, and sphericity are extensively studied experimentally employing optical microscopy (OM), scanning electron microscopy (SEM), X-ray computed tomography (XCT), and Raman spectroscopy. This is followed by an elaborate modelling through seven popular and well-recognized Machine Learning Algorithms (MLAs) namely, Multi-Layer Perceptron (MLP), Support Vector Regression (SVR), M5P model trees regression, Reduced Error Pruning Tree (REPTree), Random Forest (RF), Instance-based k-nearest neighbor algorithm (IBk) and Locally Weighted Learning (LWL). These different techniques enhance the chance of obtaining the better predictions of the said micro-porosity attributes by overcoming the effect of data-dependence and other limitations of individual MLAs. The different model-predicted micro-porosity data are also validated through experimental data. Statistical tests and Monte-Carlo reliability analysis are additionally utilized to evaluate the performances of the employed algorithms. IBk and MLP are overall found to perform well.

show abstract

Section: Performance Evaluation Of the Mlas Through Monte-carlo Reliability Analysismentioning

confidence: 99%

Study of Micro-porosity in Electron Beam Butt Welding

Das¹,

Dinda²,

Das³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…were used extensively in several welding problems to predict weld geometries, cooling rate, stresses, UTS etc. 2,3,24 Lostado et al 25 combined ANN, genetic algorithm (GA), regression trees and FEM to study the influence of input parameters on the weld geometries, thermal cycle and distortion during GMAW for weld optimization. Escribano et al 26 combined finite element analysis and data mining techniques to develop models to predict the optimized force, pressure etc.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The welding process involves the occurrence of multiple simultaneous physical processes, namely heat transfer, fluid motion, stress formation etc., which makes the joints vulnerable to failure. 1 , 2 Among many, the electron beam welding (EBW) process is a popular high energy welding technique, accompanied by the higher cooling rate, strong influence of Marangoni forces, Lorentz and buoyant forces. 3 , 4 The integrity and quality of the joints under the influence of these complex conditions need to be assured through the proper inspection to prevent any monetary loss, unwanted failure, and loss of life.…”

Section: Introductionmentioning

confidence: 99%

Prediction of residual stress in electron beam welding of stainless steel from process parameters and natural frequency of vibrations using machine-learning algorithms

Das

Pratihar

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

In the present study, machine learning algorithms have been used to predict residual stress during electron beam welding of stainless steel using the information of input process parameters and natural frequency of vibrations. Accelerating voltage, beam current and welding speed have been considered as input process parameters. Both residual stress and natural frequencies of vibration of the weld obtained using each set of the input parameters are measured experimentally. A number of machine learning algorithms, namely M5 algorithm-based Model Trees Regression, Random forest, Support Vector Regression, Reduced Error Pruning Tree, Multi-layer perceptron, Instance-based k-nearest neighbor algorithm, and Locally weighted learning have been used for the said purpose. Support vector regression and Locally weighted learning are found to perform consistently good and bad, respectively. The predicted welding residual stresses have been validated experimentally through X-ray diffraction (XRD) and good agreements are obtained. In addition, statistical tests are conducted, and the estimated reliability values of the employed models are analyzed through Monte-Carlo simulations.

show abstract

“…Applicability of neutron diffractometers for residual strain and microstructure analysis could be a limiting factor for coating layers produced using nanostructured feedstock powders where small crystal size is still a bottleneck. There are other approaches and schemes for testing and predicting residual stresses in thermal spray coatings [68], however, issues regarding the accuracy, applicability, distribution analysis can be further investigated using principles of artificial intelligence (AI) and machine learning (ML) approaches [69][70].…”

Section: General Assessment Of Examplesmentioning

confidence: 99%

Measuring Residual Strain and Stress in Thermal Spray Coatings Using Neutron Diffractometers

et al. 2020

View full text Add to dashboard Cite

Background: During thermal spray coating, residual strain is formed within the coating and substrates due to thermo-mechanical processes and microstructural phase changes.Objective: This paper provides a comprehensive guide to researchers planning to use neutron diffraction technique for thermal spray coatings, and reviews some of these studies. Methods: ENGIN-X at the ISIS spallation source is a neutron diffractometer (time-of-flight) dedicated to materials science and engineering with high resolution testing. The focus is on the procedure of using ENGIN-X diffractometer for thermal spray coatings with a view that it can potentially be translated to other diffractometers.Results: Number of studies involving neutron diffraction analysis in thermal spray coatings remain limited, partly due to limited number of such strain measurement facilities globally, and partly due to difficulty is applying neutron diffraction analysis to measure residual strain in the thermal spray coating microstructure. Conclusions: This technique can provide a non-destructive through-thickness residual strain analysis in thermally sprayed components with a level of detail not normally achievable by other techniques. Neutron sources have been used to measure strains in thermal spray coatings, and here, we present examples where such coatings have been characterised at various neutron sources worldwide, to study residual strains and microstructures.

show abstract

Prediction of welding residual stresses using machine learning: Comparison between neural networks and neuro-fuzzy systems

Cited by 84 publications

References 31 publications

Study of Micro-porosity in Electron Beam Butt Welding

Study of Micro-porosity in Electron Beam Butt Welding

Prediction of residual stress in electron beam welding of stainless steel from process parameters and natural frequency of vibrations using machine-learning algorithms

Measuring Residual Strain and Stress in Thermal Spray Coatings Using Neutron Diffractometers

Contact Info

Product

Resources

About