Process Parameters Optimization of Laser Beam Welded Joints by Neural Network

Missori, S.; Sili, A.; Ucciardello, Nadia

doi:10.1080/10426910701774692

Cited by 18 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different variants of BPNN have been employed by the researchers in the field of laser and allied processes. Conventional gradient descent BPNN algorithm and faster algorithms like Levenberg Marquardt (LM) BPNN [8,9] has been already used for input/output modeling in the field of laser cutting [10] and laser welding [11][12][13]. But it has been observed that gradient descent BPNN is too slow for many practical problems [14] and the faster algorithms lack in generalization or prediction capability for small and noisy dataset.…”

Section: Work Piecementioning

confidence: 99%

“…But best optimization result can only be obtained if the SA-ANN model itself is optimized for its various controlling parameters. In earlier research works [10][11][12][13], ANN has tried to arrive at optimum ANN architecture by repetitive trial and error method which is very time-consuming and involves a high degree of uncertainty. Present work involves a unique feature of optimization for the operating parameters of SA and ANN using quasi-Newton search algorithm for determination of optimum ANN architecture and SA parameter (initial temperature).…”

Section: Work Piecementioning

confidence: 99%

See 1 more Smart Citation

Application of an optimized SA-ANN hybrid model for parametric modeling and optimization of LASOX cutting of mild steel

Chaki¹,

Ghosal

2011

Prod. Eng. Res. Devel.

View full text Add to dashboard Cite

Laser assisted oxygen cutting (LASOX) process is an efficient method for cutting thick mild steel plates compared to conventional laser cutting process. However, scanty information is available as to modeling of the process. The paper presents an optimized SA-ANN model of artificial neural network (ANN) and simulated annealing (SA) to predict and optimize cutting quality of LASOX cutting process of mild steel plates. Optimization of SA-ANN parameters is carried out first where the ANN architecture and initial temperature for SA are optimized. The optimized ANN architecture is further trained using single hidden layer back propagation neural network (BPNN) with Bayesian regularization (BR). The trained ANN is then used to evaluate the objective function during optimization with SA. Experimental dataset employed for the purpose consists of input cutting parameters comprising laser power, cutting speed, gas pressure and stand-off distance while the resulting cutting quality is represented by heat affected zone (HAZ) width, kerf width and surface roughness. Results indicate that the SA-ANN model can predict the optimized output with reasonably good accuracy (around 3%). The proposed approach can be extended for prediction and optimization of operational parameters with reasonable accuracy for any experimental dataset.

show abstract

Section: Work Piecementioning

confidence: 99%

Section: Work Piecementioning

confidence: 99%

Application of an optimized SA-ANN hybrid model for parametric modeling and optimization of LASOX cutting of mild steel

Chaki¹,

Ghosal

2011

Prod. Eng. Res. Devel.

View full text Add to dashboard Cite

show abstract

“…Single hidden layer back propagation neural network (BPNN) (Haykin, 2006), a popular variant of multilayer feed forward ANN has been already employed by the researchers for input/output modelling in the field of laser cutting (Yousef et al, 2003), laser micro machining (LMM) (Dhara et al, 2008) and laser welding (Olabi et al, 2006;Missori et al, 2008) processes. Recently, non-traditional optimisation algorithms like GA have also been used in laser cutting of quad flat non-lead (QFN) packages (a plastic encapsulated package with a copper lead frame substrate used in semiconductor devices) where a user defined objective function has been employed for optimisation of process parameters (Tsai et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

Kerf quality prediction and optimisation for pulsed Nd:YAG laser cutting of aluminium alloy sheets using GA-ANN hybrid model

Chaki

Ghosal

Bathe

2012

IJMMS

View full text Add to dashboard Cite

During precision cutting of thin sheet metals with pulsed Nd:YAG laser beam, best cut quality can obtained by uniform kerf with minimum kerf width. An integrated GA-ANN model has been developed and employed in the present work for prediction and optimisation of cut quality where trained ANN is used for computation of fitness value. A full factorial experiment on laser cutting of aluminium alloy using pulsed Nd:YAG laser has been accomplished for generation of dataset for the model. It is observed that, the ANN module can predict kerf width and kerf deviation with mean absolute % error of 0.42% and 1.05%. Optimised kerf width and kerf deviation determined by GA optimisation results in absolute % error of 1.87% and 2.00% only during comparison with results of validation experiment. By way of using this model a considerable improvement in kerf quality has been achieved with optimised parameter setting.

show abstract

“…The ANNs have been widely applied over years; particularly, they were applied in modelling, pattern classification and clustering tasks [22]. There are several application fields, including aid of decision-making processes [23,24,25,26], classification tasks [27,28,29], phenomena and processes prediction [30,31,32,33,34], design optimisation [35,36] and materials characterisation [37,38].…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network in Fibres Length Prediction for High Precision Control of Cellulose Refining

et al. 2019

View full text Add to dashboard Cite

Paper, a web of interconnected cellulose fibres, is widely used as a base substrate. It has been applied in several applications since it features interesting properties, such as renewability, biodegradability, recyclability, affordability and mechanical flexibility. Furthermore, it offers a broad possibility to modify its surface properties toward specifics additives. The fillers retention and the fibres bonding ability are heavily affected by the cellulose refining process that influences chemical and morphological features of the fibres. Several refining theories were developed in order to determine the best refining conditions. However, it is not trivial to control the cellulose refining as different phenomena occur simultaneously. Therefore, it is intuitively managed by experienced papermakers to improve paper structures and properties. An approach based on the machine learning aimed at estimating the effects of refining on the fibres morphology is proposed in this study. In particular, an artificial neural network (ANN) was implemented and trained with experimental data to predict the fibres length as a function of refining process variables. The prediction of this parameter is crucial to obtain a high-performance process in terms of effectiveness and the optimisation of the final product performance as a function of the process parameter. To achieve these results, data mining of the experimental patterns collected was exploited. It led to the achievement of excellent performance and high accuracy in fibres length prediction.

show abstract

Process Parameters Optimization of Laser Beam Welded Joints by Neural Network

Cited by 18 publications

References 3 publications

Application of an optimized SA-ANN hybrid model for parametric modeling and optimization of LASOX cutting of mild steel

Application of an optimized SA-ANN hybrid model for parametric modeling and optimization of LASOX cutting of mild steel

Kerf quality prediction and optimisation for pulsed Nd:YAG laser cutting of aluminium alloy sheets using GA-ANN hybrid model

Artificial Neural Network in Fibres Length Prediction for High Precision Control of Cellulose Refining

Contact Info

Product

Resources

About