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.

The fused filament fabrication (FFF) process deposits thermoplastic material in a layer-by-layer manner, expanding the design space and manufacturing capability compared with traditional manufacturing. However, the FFF process is inherently directional as the material is deposited in a layer-wise manner. Therefore, the in-plane material cannot reach the isotropy character when performing the tensile test. This would cause the strength of the print components to vary based on the different process planning selections (building orientation, toolpath pattern). The existing toolpaths, primarily used in the FFF process, are linear, zigzag, and contour toolpaths, which always accumulate long filaments and are unidirectional. Thus, this would create difficulties in improving the mechanical strength from the existing toolpath strategies due to the material in-plane anisotropy. In this paper, an in-plane isotropy toolpath pattern is generated to enhance the mechanical strength in the FFF process. The in-plane isotropy can be achieved through continuous deposition while maintaining randomized distribution within a layer. By analyzing the tensile strength on the specimens made by traditional in-plane anisotropy toolpath and the proposed in-plane isotropy toolpath, our results suggest that the mechanical strength can be reinforced by at least 20% using our proposed toolpath strategy in extrusion-based additive manufacturing.

Additive manufacturing (AM), also known as 3D printing, was introduced to design complicated structures/geometries that overcome the manufacturability limitations of traditional manufacturing processes. However, like any other manufacturing technique, AM also has its limitations, such as the need of support structures for overhangs, long build time etc. To overcome these limitations of 3D printing, 4D printing was introduced, which utilizes smart materials and processes to create shapeshifting structures with the external stimuli, such as temperature, humidity, magnetism, etc. The state-of-the-art 4D printing technology focuses on the “form” of the 4D prints through the multi-material variability. However, the quantitative morphing analysis is largely absent in the existing literature on 4D printing. In this research, the inherited material anisotropic behaviors from the AM processes are utilized to drive the morphing behaviors. In addition, the quantitative morphing analysis is performed for designing and controlling the shapeshifting. A material–process–performance 4D printing prediction framework has been developed through a novel dual-way multi-dimensional machine learning model. The morphing evaluation metrics, bending angle and curvature, are obtained and archived at 99% and 93.5% R², respectively. Based on the proposed method, the material and production time consumption can be reduced by around 65–90%, which justifies that the proposed method can re-imagine the digital–physical production cycle.

The selective laser melting (SLM) process provides a more extensive design space and manufacturability. However, it is still hindered by its inaccuracy in dimension and functionality. The distortion in the SLM process affects the dimensional accuracy of the component and may even hinder the SLM process. Still, the distortion mechanism has not been well explained; specifically, the effects from the process parameters and scan strategies on the distortion have not been sufficiently investigated. In this study, a quantitative model that considers displacements, plastic strains, and thermal strains on each layer is developed to analyze the distortion mechanism. The distortion is found to be induced by a residual stress gradient among the layers. Then, a transient numerical method calculates residual stress, plastic strain, and distortion in the SLM process. Different simulations with various layers, scanning speeds, stiffness of support structures, and scan strategies are performed to study the relationship between process parameters and distortion. It can be found that the distortion decreases as the height increases. The distortion increases with the scanning speed, reaching the maximum at 700 mm/s and then dropping. We concluded that increasing the stiffness of the support structures is beneficial to reduce the distortion and changing the scanning direction among layers is useless to reduce the distortion. This study gives a theoretical model to analyze the distortion and provides guidance for reducing distortions in the SLM process.

Robotic additive manufacturing (AM) has gained much attention for its continuous material deposition capability with continuously changeable building orientations, reducing support structure volume and post-processing complexity. However, the current robotic additive process heavily relies on manual geometric reasoning that identifies additive features, related building orientations, tool approach direction, trajectory generation, and sequencing all features in a non-collision manner. In addition, multi-directional material accumulation cannot ensure the nozzle always stays above the building geometry. Thus, the collision between these two becomes a significant issue that needs to be solved. Hence, the common use of a robotic additive is hindered by the lack of fully autonomous tools based on the abovementioned issues. We present a systematic approach to the robotic AM process that can automate the abovementioned planning procedures in the aspect of collision-free. Typically, input models to robotic AM have diverse information contents and data formats, hindering the feature recognition, extraction, and relations to the robotic motion. Our proposed method integrates the collision-avoidance condition to the model decomposition step. Therefore, the decomposed volumes can be associated with additional constraints, such as accessibility, connectivity, and trajectory planning. This generates an entire workspace for the robotic additive building platform, rotatability, and additive features to determine the entire sequence and avoid potential collisions. This approach classifies the uniqueness of autonomous manufacturing on the robotic AM system to build large and complex metal components that are non-achievable through traditional one-directional AM in a computationally effective manner. This approach also paves the path in constructing an in situ monitoring and closed-loop control on robotic AM to control and enhance the build quality of the robotic metal AM process.