Bead Geometry Prediction in Laser-Wire Additive Manufacturing Process Using Machine Learning: Case of Study

Abstract

In Laser Wire Additive Manufacturing (LWAM), the final geometry is produced using the layer-by-layer deposition (beads principle). To achieve good geometrical accuracy in the final product, proper implementation of the bead geometry is essential. For this reason, the paper focuses on this process and proposes a layer geometry (width and height) prediction model to improve deposition accuracy. More specifically, a machine learning regression algorithm is applied on several experimental data to predict the bead geometry across layers. Furthermore, a neural network-based approach was used to study the influence of different deposition parameters, namely laser power, wire-feed rate and travel speed on bead geometry. To validate the effectiveness of the proposed approach, a test split validation strategy was applied to train and validate the machine learning models. The results show a particular evolutionary trend and confirm that the process parameters have a direct influence on the bead geometry, and so, too, on the final part. Several deposition parameters have been found to obtain an accurate prediction model with low errors and good layer deposition. Finally, this study indicates that the machine learning approach can efficiently be used to predict the bead geometry and could help later in designing a proper controller in the LWAM process.

Parametric modeling approach in laser wire additive manufacturing process

“…Noting that, after placing the points on the first layer, the generated toolpath is then copied to the other layers with fixed or variable thicknesses using a Python script. A layer thickness algorithm (see, e.g., [13]) is run in the script to create the toolpath patterns for each layer.…”

“…Despite the advances in AM, there are still many challenges related to the process applicability, cost, and deposition process parameters [5,8,[10][11][12][13]. However, one of the main challenges in AM, especially in LWAM, is the understanding and knowledge of the combination of the system's software and hardware.…”

Investigation on the Cause-Effect Relationships between the Process Parameters and the Resulting Geometric Properties for Wire-Based Coaxial Laser Metal Deposition

“…It was concluded that the laser spot size, the laser power, the wire speed, and the traverse speed have the strongest influence on the geometry of the deposition [19,25]. Further works studied the correlation between several of the mentioned process parameters and the dimensions of the bead through empirical or numerical models [26][27][28][29][30][31][32]. Although the identified correlations show similarities, comparisons and general conclusions are difficult to draw since different systems and parameter ranges were used.…”

Modeling and Control of Layer Height in Laser Wire Additive Manufacturing

“…Further, for simplicity, the ratio between the melt-pool width and height will be fixed. Also, the melt-pool width and length are assumed to be equal in the derivation of the equations; in this work, some deposition trials allowed to obtain this ratio for different process parameters, as presented in [9].…”

“…To obtain a stable deposition process, reliable sensing, modeling and control approaches are needed. In Mbodj et al [9], a model to predict bead geometry and improve deposition accuracy was proposed. More specifically, a regression algorithm is applied to fit bead geometry with the main deposition process parameters (laser power, wire feed rate and advanced speed) and a neural network-based approach was used to study the influence of the parameters on the bead geometry.…”