The first step towards intelligent wire arc additive manufacturing: An automatic bead modelling system using machine learning through industrial information integration

Ding, Donghong; He, Fengyang; Yuan, Lei; Pan, Zengxi; Wang, Lei; Ros, Montserrat

doi:10.1016/j.jii.2021.100218

Cited by 46 publications

(21 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Xia et al, (2020aXia et al, ( , 2020b achieve bead width control by adjusting wire feed rates via a real-time modelbased controller with the feedback of bead width. Ding et al (2021) developed an automatic system based on machine learning technologies to control multiple welding parameters to improve geometric accuracy of deposited components. Although many approaches have improved the accuracy of deposited bead geometry in simple deposition tasks, they provide limited control performance in practical applications.…”

Section: Introductionmentioning

confidence: 99%

“…Although many approaches have improved the accuracy of deposited bead geometry in simple deposition tasks, they provide limited control performance in practical applications. For example, although control of bead geometry has been demonstrated through mathematical modelling, this often comes at the expense of relatively long processing times and a requirement for large sets of training data to set up the model properly (Ding et al, 2021). In comparison, a real-time control strategy can feature reduced training costs, however, the control accuracy is then limited by reaction speeds and system latency (Abe et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Layer-by-layer model-based adaptive control for wire arc additive manufacturing of thin-wall structures

Polden

et al. 2022

J Intell Manuf

Self Cite

View full text Add to dashboard Cite

Improving the geometric accuracy of the deposited component is essential for the wider adoption of wire arc additive manufacturing (WAAM) in industries. This paper introduces an online layer-by-layer controller that operates robustly under various welding conditions to improve the deposition accuracy of the WAAM process. Two control strategies are proposed and evaluated in this work: A PID algorithm and a multi-input multi-output model-predictive control (MPC) algorithm. After each layer of deposition, the deposited geometry is measured using a laser scanner. These measurements are compared against the CAD model, and geometric errors are then compensated by the controller, which generates a new set of welding parameters for the next layer. The MPC algorithm, combined with a linear autoregressive (ARX) modelling process, updates welding parameters between successive layers by minimizing a cost function based on sequences of input variables and predicted responses. Weighting coefficients of the ARX model are trained iteratively throughout the manufacturing process. The performance of the designed control architecture is investigated through both simulation and experiments. Results show that the real-time control performance is improved by increasing the complexity of implemented control algorithm: controlled geometric fluctuations in the test component were reduced by 200% whilst maintaining fluctuations within a 3 mm limit under various welding conditions. In addition, the adaptiveness of designed control strategy is verified by accurately controlling the fabrication of a part with complex geometry.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Layer-by-layer model-based adaptive control for wire arc additive manufacturing of thin-wall structures

Polden

et al. 2022

J Intell Manuf

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then, the best candidates are selected following regression analysis of the experimentally determined quality parameters [3], [4]. Alternatively, datadriven modeling using neural networks [5], [6] or support vector machines [7] has been proposed to relate process inputs to quality parameters. All these approaches require a large number of samples, to either achieve good predictive capabilities, or to reliably cover all possible process variations.…”

Section: Introductionmentioning

confidence: 99%

Advanced Manufacturing Configuration by Sample-efficient Batch Bayesian Optimization

Guidetti¹,

Rupenyan²,

Fassl³

et al. 2022

Preprint

View full text Add to dashboard Cite

We propose a framework for the configuration and operation of expensive-to-evaluate advanced manufacturing methods, based on Bayesian optimization. The framework unifies a tailored acquisition function, a parallel acquisition procedure, and the integration of process information providing context to the optimization procedure. The novel acquisition function is demonstrated and analyzed on benchmark illustrative problems. We apply the optimization approach to atmospheric plasma spraying in simulation and experiments. Our results demonstrate that the proposed framework can efficiently find input parameters that produce the desired outcome and minimize the process cost.

show abstract

“…16 An automated bead modeling tool was proposed using a Support vector regression model algorithm using Machine learning. 17 Layer-wise weld pool conditions are predicted using hybrid deep learning models with convolutional neural networks (CNN) and recurrent neural networks (RNN). 18,19 Layer-wise computed tomography (CT) with a high-resolution camera such as digital-single-lens-reflex (DSLR) is used to detect the defects like voids, cracks, discontinuities, porosity, and incomplete fusion.…”

Section: Introductionmentioning

confidence: 99%

Inclusion of IoT technology in additive manufacturing: Machine learning-based adaptive bead modeling and path planning for sustainable wire arc additive manufacturing and process optimization

Reddy

Suresh

Anilkumar

2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Industrial civilization transforms current cutting edge technologies and the evolution of Industry 5.0 is more aggressive with the use of IoT-enabled smart machines and robots in the manufacturing sector today. IoT technology deals with digital data as in additive manufacturing (AM). The potential and progressive aspects of AM embarks for functional part development instead of initial prototyping. AM is one of large-scale production with less buy-to-fly (BTF) ratio. In the present work, a novel framework has been proposed and utilized to attain adaptive bead modeling and an appropriate path plan for enhanced deposition and surface quality of weld beads. Further, the influence of input process parameters toward sustainable wire arc additive manufacturing (WAAM) is also focused. Machine learning-based hybrid-TLBO (h-TLBO) and support vector machine (SVM) is deployed for the optimization process. With the aid of graph theory, weights are estimated for h-TLBO. The overall process parameters and entire data module is handled with IoT technology and can be accessed for processing. The simulated post-processing results are validated experimental test results and found to be in good concurrence.

show abstract

The first step towards intelligent wire arc additive manufacturing: An automatic bead modelling system using machine learning through industrial information integration

Cited by 46 publications

References 26 publications

Layer-by-layer model-based adaptive control for wire arc additive manufacturing of thin-wall structures

Layer-by-layer model-based adaptive control for wire arc additive manufacturing of thin-wall structures

Advanced Manufacturing Configuration by Sample-efficient Batch Bayesian Optimization

Inclusion of IoT technology in additive manufacturing: Machine learning-based adaptive bead modeling and path planning for sustainable wire arc additive manufacturing and process optimization

Contact Info

Product

Resources

About