An improved artificial neural network for laser welding parameter selection and prediction

Zhong, Yong; Xue, Kaiping; Shi, Dongyan

doi:10.1007/s00170-013-4796-1

Cited by 11 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In accordance with this purpose, various methods have been introduced in the literature based on finite element, experimental design, or artificial intelligence. 1,12–16…”

Section: Introductionmentioning

confidence: 99%

“…In accordance with this purpose, various methods have been introduced in the literature based on finite element, experimental design, or artificial intelligence. 1,[12][13][14][15][16] Design of experiments (DOE) based approaches have been one of the most widely used methods to optimize LTW parameters in literature because the effects of a number of input parameters on a desired response can be efficiently analyzed. Regarding the full or fractional factorial design in DEO, many studies used the response surface methodology (RSM) to optimize the LTW parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-response optimization for laser transmission welding of PMMA to ABS using Taguchi-based TOPSIS method

Kucukoglu,

Yuce,

Sozer

et al. 2023

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Recently, the usage of laser transmission welding (LTW) technology in the automotive industry has been rising for joining thermoplastic parts regarding its superior properties in comparison to other welding technologies. However, specifying the process parameters is a crucial step to obtain satisfactory welding quality for the vehicle parts. In this context, this paper addresses the LTW process of Polimetil metakrilat (PMMA) to Akrilonitril bütadien stiren (ABS) materials for the production of taillights in an automotive company and proposes a new multi-response Taguchi-Based TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) method to optimize machining parameters in the laser welding process. In the proposed solution methodology, the main effects of the parameters on different outputs are identified by using the [Formula: see text] orthogonal array of the Taguchi method. Regarding the best parameter set for each output, the best parameter set for multi-response is identified by using the TOPSIS method, in which alternatives are evaluated through the interrelated quality measures. To optimize welding process in taillight production, PMMA and ABS samples with the dimensions of [Formula: see text] in width, [Formula: see text] in length, and [Formula: see text] in thickness are used in the experiments. The samples are welded by using LPKF Twinweld 3D 6000® laser welding machine. For the welding process, laser power, welding speed, and pressure force are taken into account as the input parameters to optimize three responses: weld strength, breaking strain, and weld width. To identify the best process parameter values, the Taguchi Method is initially employed to calculate the main effects of LTW parameters for each output. Then, the TOPSIS method is carried out to evaluate a number of alternative parameter sets generated through the Taguchi results. As a consequence of the TOPSIS ranking scores, the best parameter set that jointly optimizes three outputs of the LTW process is identified for the taillight production as [Formula: see text] power, [Formula: see text] speed, and [Formula: see text] pressure force. Based on the conducted experiments, this parameter setting achieves the highest weld strength, breaking strain level, and above-average weld width. The results of the experiments show that the proposed methodology is capable of optimizing LTW parameters for a multi-response with fewer experiments in the joining of plastic vehicle parts.

show abstract

“…In accordance with this purpose, various methods have been introduced in the literature based on finite element, experimental design, or artificial intelligence. 1,12–16…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-response optimization for laser transmission welding of PMMA to ABS using Taguchi-based TOPSIS method

Kucukoglu,

Yuce,

Sozer

et al. 2023

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…However, the use of a CNN instead of traditional process-parameter tuning methods holds a certain reference value. Zhong Yuguang et al [ 23 ] proposed integrating the gray correlation model (GCM), genetic algorithm simulated annealing (GASA), and artificial neural network (ANN) algorithms to solve the prediction problem of process parameters. By using the weights and thresholds of the GASA neural network, global optimization can be achieved within a relatively short training time.…”

Section: Introductionmentioning

confidence: 99%

Variable-Structure Proportional–Integral–Derivative Laser Solder Joint Temperature Intelligent Control Method with Adjustable Power Upper Limit

Li,

Cao,

Zhang

et al. 2023

Micromachines

View full text Add to dashboard Cite

Laser soldering is a crucial soldering technique in the realm of electronic assembly. The temperature of the solder joint is intimately connected with the quality of the solder. This paper introduces an adjustable power upper limit variable-structure Proportional–Integral–Derivative (PID) intelligent control method for regulating the temperature of the solder joint during laser soldering. Distinct laser power limits are employed for workpieces with varying heat capacities. The solder joint temperature is monitored through an infrared thermometer, which enables closed-loop temperature control via a variable-structure PID algorithm. Residual neural network (ResNet) models are utilized to predict key soldering process parameters. This method has been executed and validated on a practical testing platform. Compared to other laser soldering control techniques, the proposed method demonstrates a low overshoot, rapid dynamic response, and swift adjustment capabilities, effectively enhancing the soldering quality and production efficiency.

show abstract

“…Yin [ 14 ] proposed a backpropagation (BP) ANN model to obtain the mathematical relationship between the optimization goals and process parameters and applied a genetic algorithm to optimize the parameters. In order to speed up the convergence and avoid local minimum of the conditional ANN, Zhong [ 15 ] inducted genetic algorithm simulated annealing (GASA) based on the random global optimization into the network training. Meanwhile, the gray correlation model (GCM) was used as a pre-processing tool to simplify the original networks based on obtaining the main influence elements of network inputs.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Geometric Characteristics of Melt Track Based on Direct Laser Deposition Using M-SVR Algorithm

et al. 2021

View full text Add to dashboard Cite

Geometric characteristics provide an important means for characterization of the quality of direct laser deposition. Therefore, improving the accuracy of a prediction model is helpful for improving deposition efficiency and quality. The three main input variables are laser power, scanning speed, and powder-feeding rate, while the width and height of the melt track are used as outputs. By applying a multi-output support vector regression (M-SVR) model based on a radial basis function (RBF), a non-linear model for predicting the geometric features of the melt track is developed. An orthogonal experimental design is used to conduct the experiments, the results of which are chosen randomly as training and testing data sets. On the one hand, compared with single-output support vector regression (S-SVR) modeling, this method reduces the root mean square error of height prediction by 22%, with faster training speed and higher prediction accuracy. On the other hand, compared with a backpropagation (BP) neural network, the average absolute error in width is reduced by 5.5%, with smaller average absolute error and better generalization performance. Therefore, the established model can provide a reference to select direct laser deposition parameters precisely and can improve the deposition efficiency and quality.

show abstract

An improved artificial neural network for laser welding parameter selection and prediction

Cited by 11 publications

References 21 publications

Multi-response optimization for laser transmission welding of PMMA to ABS using Taguchi-based TOPSIS method

Multi-response optimization for laser transmission welding of PMMA to ABS using Taguchi-based TOPSIS method

Variable-Structure Proportional–Integral–Derivative Laser Solder Joint Temperature Intelligent Control Method with Adjustable Power Upper Limit

Prediction of Geometric Characteristics of Melt Track Based on Direct Laser Deposition Using M-SVR Algorithm

Contact Info

Product

Resources

About