Rapid and accurate prediction of temperature evolution in wire plus arc additive manufacturing using feedforward neural network

Le, Van Thao; Nguyen, Hai Dang; Bui, Manh Cuong; Pham, Thinh Quy Duc; Le-Hong, Thai; Tran, Xuan Van; Tran, Hoang Son

doi:10.1016/j.mfglet.2022.02.003

Cited by 10 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown that computational times can be reduced significantly for geometries produced by single-pass directed energy deposition (DED) techniques by using a semi-analytical method [11]. Recently, a neural network has been employed to predict temperature fields during WAAM much faster than what is possible using FE simulations [12]. The current article presents a physicsbased numerical method for determining temperature fields in thin-walled structures (i.e., where the thickness is small compared to other dimensions) during WAAM repair.…”

Section: Introductionmentioning

confidence: 99%

A fast simulation method for thermal management in wire arc additive manufacturing repair of a thin-walled structure

Qvale,

Njaastad,

Bræin

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Ensuring first-time-right on-site repair of critical structures is a key challenge for additive manufacturing (AM)–based repair solutions. Fast thermal simulations are thus needed to plan efficient and error-free AM processes. This paper addresses a fast thermal simulation method for a novel subsea wire arc additive manufacturing (SWAAM) repair procedure. Current commercial finite element (FE) codes for typical welding and AM are computationally expensive and slow. The presented 2D finite difference approach can be used to simulate SWAAM on a damaged plate with around 70 times acceleration compared to real welding times, without the use of parallelization. Although not being able to accurately represent the temperature in close vicinity of the welding torch, the approach shows excellent correspondence with FE simulations and experiments in regions of the plate where the temperature has assumed a distribution that is largely two-dimensional. Compared with FE simulations, the approach is experimentally verified to be accurate to 10 °C within 7 s after the welding torch has passed a point on the plate. Thus, the approach can provide a measure of the global temperature field in a thin-walled structure during repair. The thermal simulation is preceded by a welding path planner, which generates appropriate paths based on slicing of a 3D surface scan of the damage that is to be repaired. Damages to equipment or non-ideal welding conditions are prevented by automatically pausing the welding if the calculated temperature in the path ahead of the welding torch exceeds a predefined interpass temperature limit.

show abstract

Section: Introductionmentioning

confidence: 99%

A fast simulation method for thermal management in wire arc additive manufacturing repair of a thin-walled structure

Qvale,

Njaastad,

Bræin

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…However, its extensive computation time limits its further application. To address this challenge, predictive models based on machine learning have been developed, allowing us to rapidly predict the thermal history and the geometrical information of WAAM deposits for the given process parameters [14][15][16][17][18][19][20]. For instance, Van et al [18] built a prediction model for the WAAM thermal history via a feedforward neural network-based surrogate model (FFNN-SM).…”

Section: Introductionmentioning

confidence: 99%

“…To address this challenge, predictive models based on machine learning have been developed, allowing us to rapidly predict the thermal history and the geometrical information of WAAM deposits for the given process parameters [14][15][16][17][18][19][20]. For instance, Van et al [18] built a prediction model for the WAAM thermal history via a feedforward neural network-based surrogate model (FFNN-SM). The developed FFNN-SM model can accurately estimate the temperature evolutions at different sample positions, whilst saving 99.75% time compared to the finite element (FE) simulations.…”

Section: Introductionmentioning

confidence: 99%

An ANN Hardness Prediction Tool Based on a Finite Element Implementation of a Thermal–Metallurgical Model for Mild Steel Produced by WAAM

Cheng,

Ling,

De Waele

2024

Metals

View full text Add to dashboard Cite

WAAM has emerged as a promising technique for manufacturing medium- and large-scale metal parts due to its high material deposition efficiency and automation level. However, its high heat accumulation and complex thermal evolution strongly affect the resulting microstructures and mechanical properties. The heterogeneous and unpredictable nature of these properties hinder the widespread application of WAAM in the steel construction industry. In this study, an artificial neural network (ANN) hardness model is developed, based on a thermal–metallurgical model for mild steel. The objective is to establish non-linear relationships between the input process parameters and the desired output, i.e., hardness. The thermal–metallurgical model utilizes a well-distributed heat source model, a death-and-birth algorithm, and a metallurgical model to simulate the temperature field and to calculate the microstructure phase fraction. The temperature prediction errors at four thermocouple positions are mostly below 20%. Because of the limited experimental data, twenty-five simulation experiments are performed using the L25 orthogonal array based on the Taguchi method. The analysis of variance (ANOVA) reveals that the travel speed has the greatest impact on hardness. With the dataset from the thermal–metallurgical model, an ANN model to predict hardness is developed. A comparison to experimental data shows excellent performance and accuracy, with the Mean Absolute Percentage Error (MAPE) of ANN predictions within 10% of the targeted hardness.

show abstract

“…Hajializadeh et al [10] developed an ANN model integrated with the FE model for the computation of residual stresses in different deposited structures. The transient temperature evolution for multi-layer deposition with varying heat input levels for a WAAM process is analysed by ANN [13]. Mukherjee et al [7] predicted the maximum longitudinal residual stress of a deposit by ANN and RF models, and FE model.…”

Section: Introductionmentioning

confidence: 99%

Physics-informed machine learning models for the prediction of transient temperature distribution of ferritic steel in directed energy deposition by cold metal transfer

Kumar

Sarma

Bag

et al. 2023

Science and Technology of Welding and Joining

View full text Add to dashboard Cite

In-situ monitoring of the additive layer characteristics in the directed energy deposition (DED) process by any contact technology is cumbersome. A well-tested finite element (FE) model is often employed to extract transient temperature distribution during deposition. However, the numerical model pertaining to each deposition attribute is computationally expensive. In the present work, we have generated a dataset through an experimentally validated thermal model, and further multiple machine learning (ML) algorithms are applied to train datasets. Models with an accuracy of more than 99% are utilised for the prediction of transient temperature distribution. The validation of deposition attributes using experiments and numerical model suggests that the physics-informed machine learning models for cold metal transfer can be applied in the DED process.

show abstract

Rapid and accurate prediction of temperature evolution in wire plus arc additive manufacturing using feedforward neural network

Cited by 10 publications

References 7 publications

A fast simulation method for thermal management in wire arc additive manufacturing repair of a thin-walled structure

A fast simulation method for thermal management in wire arc additive manufacturing repair of a thin-walled structure

An ANN Hardness Prediction Tool Based on a Finite Element Implementation of a Thermal–Metallurgical Model for Mild Steel Produced by WAAM

Physics-informed machine learning models for the prediction of transient temperature distribution of ferritic steel in directed energy deposition by cold metal transfer

Contact Info

Product

Resources

About