Robotic welding and additive manufacturing (AM) processes have an intricate design space influenced by numerous configurable process parameters. Currently, the precise impact of each parameter or a combination of them on the variability and dimensions of deposited material is unclear due to the stochastic nature of the process, which is affected by factors like arc stability, temperature gradients and other in-process changes. In AM and various cases of welding like cladding, quantifying these variations is necessary for developing path planning strategies that produce components without defects. This study presents a framework that automates process data collection and scanning of the weld bead and analysis of the point cloud, based on the design of experiments principals towards building representative machine learning models. In comparison to alternative approaches, this framework incorporates spatial variation along the deposited length by utilising location-based binning of measurements, thereby enabling more detailed analysis of various deposition stages including arc ignition and extinction regions. The framework is tested with single pass bead-on-plate weld beads deposited with different process parameters followed by spatial–temporal matching. Variations were noted in relation to travel speed and welding current when subjected to identical heat input values. Machine learning models for prediction of height and width account for non-linearities and are validated with additional experimental data. These models have demonstrated a high degree of accuracy in predicting in-process variations within the deposited material.

Purpose: Additive manufacturing (AM) is a rapidly evolving manufacturing process, which refers to a set of technologies that add materials layer-by-layer to create functional components. AM technologies have received an enormous attention from both academia and industry, and they are being successfully used in various applications, such as rapid prototyping, tooling, direct manufacturing and repair, among others. AM does not necessarily imply building parts, as it also refers to innovation in materials, system and part designs, novel combination of properties and interplay between systems and materials. The most exciting features of AM are related to the development of radically new systems and materials that can be used in advanced products with the aim of reducing costs, manufacturing difficulties, weight, waste and energy consumption. It is essential to develop an advanced production system that assists the user through the process, from the computer-aided design model to functional components. The challenges faced in the research and development and operational phase of producing those parts include requiring the capacity to simulate and observe the building process and, more importantly, being able to introduce the production changes in a real-time fashion. This paper aims to review the role of robotics in various AM technologies to underline its importance, followed by an introduction of a novel and intelligent system for directed energy deposition (DED) technology. Design/methodology/approach: AM presents intrinsic advantages when compared to the conventional processes. Nevertheless, its industrial integration remains as a challenge due to equipment and process complexities. DED technologies are among the most sophisticated concepts that have the potential of transforming the current material processing practices. Findings: The objective of this paper is identifying the fundamental features of an intelligent DED platform, capable of handling the science and operational aspects of the advanced AM applications. Consequently, we introduce and discuss a novel robotic AM system, designed for processing metals and alloys such as aluminium alloys, high-strength steels, stainless steels, titanium alloys, magnesium alloys, nickel-based superalloys and other metallic alloys for various applications. A few demonstrators are presented and briefly discussed, to present the usefulness of the introduced system and underlying concept. The main design objective of the presented intelligent robotic AM system is to implement a design-and-produce strategy. This means that the system should allow the user to focus on the knowledge-based tasks, e.g. the tasks of designing the part, material selection, simulating the deposition process and anticipating the metallurgical properties of the final part, as the rest would be handled automatically. Research limitations/implications: This paper reviews a few AM technologies, where robotics is a central part of the process, such as vat photopolymerization, material jetting, binder jetting, material extrusion, powder bed fusion, DED and sheet lamination. This paper aims to influence the development of robot-based AM systems for industrial applications such as part production, automotive, medical, aerospace and defence sectors. Originality/value: The presented intelligent system is an original development that is designed and built by the co-authors J. Norberto Pires, Amin S. Azar and Trayana Tankova.