Quality Prediction and Control in Wire Arc Additive Manufacturing via Novel Machine Learning Framework

Abstract

Wire arc additive manufacturing (WAAM) is capable of rapidly depositing metal materials thus facilitating the fabrication of large-shape metal components. However, due to the multi-process-variability in the WAAM process, the deposited shape (bead width, height, depth of penetration) is difficult to predict and control within the desired level. Ultimately, the overall build will not achieve a near-net shape and will further hinder the part from performing its functionality without post-processing. Previous research primarily utilizes data analytical models (e.g., regression model, artificial neural network (ANN)) to forwardly predict the deposition width and height variation based on single or cross-linked process variables. However, these methods cannot effectively determine the optimal printable zone based on the desired deposition shape due to the inability to inversely deduce from these data analytical models. Additionally, the process variables are intercorrelated, and the bead width, height, and depth of penetration are highly codependent. Therefore, existing analysis cannot grant a reliable prediction model that allows the deposition (bead width, height, and penetration height) to remain within the desired level. This paper presents a novel machine learning framework for quantitatively analyzing the correlated relationship between the process parameters and deposition shape, thus providing an optimal process parameter selection to control the final deposition geometry. The proposed machine learning framework can systematically and quantitatively predict the deposition shape rather than just qualitatively as with other existing machine learning methods. The prediction model can also present the complex process-quality relations, and the determination of the deposition quality can guide the WAAM to be more prognostic and reliable. The correctness and effectiveness of the proposed quantitative process-quality analysis will be validated through experiments.

Effect of Process Parameters on Distortions Based on the Quantitative Model in the SLM Process

“…(1) Step 1. When the first layer is deposited and cooled down, the residual stress in the substrate σ (1) s can be expressed as:…”

“…s_e is the elastic strain of the substrate, u (1) is the displacement of the component, and ε (1) s_th is the thermal strain of the substrate. The residual stress in the first layer σ (1) f 1 is defined as:…”

“…where A s is the equivalent sectional area of the substrate, and A f 1 is the sectional area of the first layer. Therefore, the displacement of the first layer u (1) can be expressed as:…”

“…Additive manufacturing (AM) is a promising approach for rapid prototyping [1]. As a precision AM technology, selective laser melting (SLM) is widely employed in medical instruments, aerospace, and auto industries [2][3][4].…”

Unit Integration Method Solution and Experimental Research on Mechanism Characteristics for Flat Digging of Grab Dredgers

“…In the normal digging state, the digging curve is steep, while, in the flat digging state, the digging curve is smooth. In order to achieve the effect of flat digging, it is necessary to control the movement of the closing wires and the hoist wires [8][9][10][11]. When lifting the closing wires, while automatically controlling the hoist wires of the grab, the digging plane formed is flat, as shown in Figure 1b.…”