Machine learning algorithms for prediction of penetration depth and geometrical analysis of weld in friction stir spot welding process

Bahedh, Abdulbaseer S.; Mishra, Akshansh; Al-Sabur, Raheem; Jassim, Ahmad K.

doi:10.1051/metal/2022032

Cited by 12 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It compares the actual values of a set of data with the predicted values produced by a machine learning algorithm. The confusion matrix is a fundamental tool in machine learning [29], and it is widely used in many applications, including computer vision, natural language processing, and fraud detection. The basic structure of a confusion matrix includes four different metrics: true positives (TP), false positives (FP), true negatives (TN), and false negatives (FN).…”

Section: Confusion Matrixmentioning

confidence: 99%

Enhancing Friction Stir Welding: Quality Machine Learning Based Friction Stir Welding Tool Condition Monitoring

2024

Int. Res. J. multidiscip. Technovation

View full text Add to dashboard Cite

Ensuring the quality and optimizing the tool in Friction Stir Welding (FSW) process is quite complex and the solution relies on implementing Condition Monitoring. The major impact of this process yields good quality welds and cuts down the non-operational timing and cost. Condition Monitoring is the key to find a solution to the challenging problem of ensuring quality and optimizing the tool in the FSW process. The creation of a graphical user interface (GUI) and the development and comparison of several models, including Decision Tree (DT), Random Forest (RF), Light Gradient Boosted Machine (LGBM), and Extreme Gradient Boosting (XGBoost), are the main objectives of this study. By offering an uniform interface for tracking and evaluating tool condition data, GUI can make it easier for operators and the maintenance crew to collaborate. Vibration analysis is the first step in tool condition monitoring. Al5083 and AZ31B are used as the workpiece and H13 as the tool in this investigation. The signals are obtained from the experimental setup via DAQ, and LabView processes them. A Python script converts the raw signals into statistical data. Following that, the data was loaded into ML models and optimized using Optuna. TKinter has been used to create the GUI. For prediction, the best models were included in the GUI. By the deployed models, LGBM generates 96% for 1000 rpm, 96.55% for 1200 rpm, and 95.90% for 1400 rpm for Al5083 93.22% for 1000 rpm, 99.29% for 1200 rpm, and 91.50% for 1000 rpm for AZ31B. For real-time prediction, these models are thus connected to a graphical user interface. In each case, the LGBM classifier topped the others. This work served as an initial basis for the creation of a semi-onboard diagnostic approach that requires minimal human input.

show abstract

Section: Confusion Matrixmentioning

confidence: 99%

Enhancing Friction Stir Welding: Quality Machine Learning Based Friction Stir Welding Tool Condition Monitoring

2024

Int. Res. J. multidiscip. Technovation

View full text Add to dashboard Cite

show abstract

“…21. Non-linear mathematical between frictional stress and input parameters was obtained by utilized FEM results and Taguchi method regression for the optimization as shown in equation (3).…”

Section: Frictional Stressmentioning

confidence: 99%

“…Plastic deformation also plays an important role in (FSW). In recent years, FSW has come to compete strongly with traditional welding methods and has expanded to include underwater welding [1] and polymer welding [2] in addition to the applications of machine learning [3] and online monitoring [4]. There are numerous researches investigated FSW experimentally and numerically.…”

Section: Introductionmentioning

confidence: 99%

Numerical Simulation and Optimization of Friction Stir Welding Parameters

Jasim¹,

Saleh²,

Jasim³

2023

BJES

View full text Add to dashboard Cite

In this paper friction stir welding process has been studied whereby utilized FEM method (Ansys software ver. 20). The main effective parameter in this process were rotational speed, linear speed, tool shoulder radius, heat transfer coefficient and clamping percentage to study their influence on represent temperature, von misses stress and frictional stress distribution. Because of the difficulty to obtained the number of the simulation cases in order to get the most important results, Taguchi L27 orthogonal array was apply to reduce the total number of the simulation cases. Pure copper (t = 3.18 mm) material type was applied as work plate material. ANOVA statistical tool was utilized to achieved the optimization process after the simulation cases done. Percentage of contribution of each parameter can be obtained by ANOVA table and mean of S/N ratio plot. Validation process was achieved between the Current study and experiment work in the temperature distribution field with percentage of error 2.7 %. From optimization result It is found that the optimum condition in order to obtained good results for temperature was rotational speed of (450 rpm), linear speed (2.75 mm/s), tool shoulder radius (7 mm), heat transfer coefficient (300 w/m2 K), clamping distance percentage (40 %). And for von misses stress was rotational speed of (550 rpm), linear speed (3 mm/s), tool shoulder radius (7 mm), heat transfer coefficient (300 w/m2 K), clamping distance percentage (20 %). While for frictional stress was rotational speed of (450 rpm), linear speed (2.5 mm/s), tool shoulder radius (7 mm), heat transfer coefficient (300 w/m2 K), clamping distance percentage (30 %).

show abstract

“…The efficiency of welding is enhanced using the technique by using a nonconsumable tool that was very useful to reduce the time and cost of the process. FSSW is widely used in many engineering applications in the industrial sections (e.g., Mazda Motor Corporation) [ 1 ]. FSSW is a solid-state joining technique known for its ability to create high-quality welds without the drawbacks associated with traditional fusion welding methods.…”

Section: Introductionmentioning

confidence: 99%

Numerical and Experimental Analyses of Developed Friction Stir Spot Welding (DFSSW) Based on Systematic Design Process Approach

Abd Al-Sahb,

Hussein,

Mohammed

et al. 2024

The Scientific World Journal

View full text Add to dashboard Cite

This research paper presents a developed technique for Friction Stir Spot Welding (FSSW) to join similar aluminum sheets (6061), and then this technique was analyzed critically based on numerical simulation and experimental work. The objective of this Developed Friction Stir Spot Welding (DFSSW) is to avoid or at least reduce the keyhole defects by optimizing the design parameters of the process. The coupling problem (thermomechanical) was solved numerically using the finite element method to find the variations of temperatures and stress distributions in addition to the applied forces by the tool. Different parameters were considered in the numerical analysis, such as rotational speed and plunge depth. The experimental results proved the success of the developed technique by comparing the available results of tensile shear force with the results of other researchers that applied the traditional FSSW. It was obtained the highest tensile shear force (2388 N) under the optimal working and design conditions, when the rotational speed, plunging depth, height, and diameter of the sliced disc were 2100 rpm, 0.3 mm, 3.5 mm, and 12 mm, respectively. It was found that both the diameter and height of the sliced disc are significant parameters that ensure the success of this new technique when selecting the suitable values for these parameters. Otherwise, selecting unsuitable values of these parameters leads to appearing defects (e.g., flash) or the sample will fail under a low level of tensile shear force. The other essential advantage outcome point of this new technique was reducing the defect of the keyhole significantly compared with the results of typical Friction Stir Spot Welding. According to the results of the promising developed welding procedure that can be automated, it can be used widely in the industrial sectors.

show abstract

Machine learning algorithms for prediction of penetration depth and geometrical analysis of weld in friction stir spot welding process

Cited by 12 publications

References 13 publications

Enhancing Friction Stir Welding: Quality Machine Learning Based Friction Stir Welding Tool Condition Monitoring

Enhancing Friction Stir Welding: Quality Machine Learning Based Friction Stir Welding Tool Condition Monitoring

Numerical Simulation and Optimization of Friction Stir Welding Parameters

Numerical and Experimental Analyses of Developed Friction Stir Spot Welding (DFSSW) Based on Systematic Design Process Approach

Contact Info

Product

Resources

About