Graph Deviation Network for Anomaly Detection and Localization in Additive Manufacturing Systems

Design for additive manufacturing (DFAM) seeks to develop designs that take advantage of the unique capabilities of additive manufacturing (AM) processes to maximize benefits. In this paper, several issues at the frontier of DFAM research are highlighted. First, the need is described to include as-manufactured mechanical and other physical properties, such as topology and shape optimization and generative design, during computational design. AM processes rarely produce parts with homogeneous composition and isotropic properties, so design methods and tools should not assume them. Second, the topic of designing for the AM process chain is important since AM-fabricated parts typically need postprocessing operations, such as support removal, finish machining, heat treatments, etc. DFAM methods need to incorporate the entire process chain, not just the AM process, which is explored with an example from metal powder bed fusion. Third, potentially, the largest benefit of AM can be realized by radically rethinking product architectures. Examples of an electric motorcycle and an assistive exosuit illustrate the ideas and potential benefits. Finally, some thoughts on design for 4D printing are offered, specifically for 3D printed morphing and deployable systems that utilize the shape memory effect.

Digital twin (DT) and additive manufacturing (AM) technologies are key enablers for smart manufacturing systems. DTs of AM systems are proposed in recent literature to provide additional analysis and monitoring capabilities to the physical AM processes. This work proposes a DT framework for real-time performance monitoring and anomaly detection in fused deposition modeling (FDM) AM process. The proposed DT framework can accommodate AM process measurement data to model the AM process as a cyber-physical system with continuous and discrete event dynamics, and allow for the development of various applications. A new performance metric is proposed for performance monitoring and a formal specification based anomaly detection method is proposed for AM processes. Implementation of the proposed DT on an off-the-shelf FDM printer and experimental results of anomaly detection and process monitoring are presented at the end.

Although many cases of medical implants produced through additive manufacturing (AM) in Ti6Al4V have been reported in literature, most of these processes had not been qualified. To enable certification and commercialisation of medical implants and devices an ISO 13485:2016 quality management system was successfully implemented in the Centre for Rapid Prototyping and Manufacturing (CRPM) at the Central University of Technology, Free State in South Africa. This certification covers qualification of both design, development and production of patient specific custom made titanium implants, as well as preoperative models, jigs and cutting guides in nylon by means of AM and supports commercialisation. With this quality management system as framework for ensuring the reliability and repeatability of the AM performed at the CRPM, the generation of data to validate the individual processes in the AM process chain was pursued. Sufficient research data has been produced and published to prove that medical implants produced through AM can fully comply with the international standards for material, physical, chemical and mechanical properties. In this paper the research performed towards the qualification of AM of Ti6Al4V medical implants is discussed. Examples are given of internationally leading work on utilising these implants in maxillofacial and orthopaedic surgeries.

Additive manufacturing (AM) systems present tremendous advantages over the traditional manufacturing systems, particularly for realizing complex shapes and producing custom parts. These advantages, and the rapid growth in the availability of AM systems, have led to a widespread increase in the use of AM. Unfortunately, general design for additive manufacturing (DfAM) tools that predict the engineering performance of AM parts are largely unavailable, and this has forced engineers to rely on engineering judgment and/or data from physical experiments. The data sets reported in the literature that quantify the performance of the existing AM systems provide much needed insight, but the data produced by experiments conducted on specific AM systems are necessarily of limited applicability. Given the large number of AM systems currently in use today, a potentially vast amount of data are needed to fully understand them all, and new AM systems and materials are being developed almost daily. To mitigate this need for an ever-increasing amount of data, this paper proposes the use of an approximation-assisted multi-objective optimization technique to quantify the performance of an AM system for specific design application in a targeted fashion. This general approach uses a limited number of physical experiments to answer a specific DfAM question of interest, and the results can then be used to design functional parts without the need for additional data. The implementation of the proposed approach is demonstrated with a material extrusion case study.

Additive manufacturing (AM) has recently been accorded considerable interest by manufacturers. Many manufacturing industries, amongst others in the aerospace sector, are already using AM parts or are investing in such manufacturing methods. Important material properties, such as microstructures, residual stress, and surface topography, can be affected by AM processes. In addition, a subtractive manufacturing (SM) process, such as machining, is required for finishing certain parts when accurate tolerances are required. This finish machining will subsequently affect the surface integrity and topography of the material. In this research work, we focused on the surface integrity of Ti-6Al-4V parts manufactured using three different types of AM and finished using an SM step. The aim of this study was to gain an understanding on how each process affects the resulting surface integrity of the material. It was found that each AM process affects the materials’ properties differently and that clear differences exist compared to a reference material manufactured using conventional methods. The newly generated surface was investigated after the SM step and each combination of AM/SM resulted in differences in surface integrity. It was found that different AM processes result in different microstructures which in turn affect surface integrity after the SM process.

Enhancement in the capabilities of additive manufacturing (AM) methods has led to development of many high-value components for aerospace, automotive and medical fields. Security concerns, such as (a) a predominantly cloud based process chain of AM may be breached and stolen files can be used for unauthorized reproduction of parts and (b) legitimately acquired parts can be reverse engineered, need to be addressed for this field to protect intellectual property and deter counterfeiting or unauthorized production. In the present work, a method of embedding an identification code inside the parts manufactured by AM methods is presented, which takes advantage of the layer-by-layer manufacturing process. The code is obfuscated by segmenting it into a specific number of parts, which are distributed throughout a large number of printed layers. In this case, viewing the code only from a specific direction is provides the correct visualization. A further obfuscation scheme is demonstrated that embeds multiple identification codes in the interpenetrating format. Only a specific set of processing conditions can lead to printing of the authentic code inside the part correctly. Numerous other conditions lead to printing of wrong code inside the part, which will lead to positive identification of counterfeit or unauthorized parts. Securing the AM process chain can help in accelerating the industrial applications of this versatile method.

The performance characterization of the manufacturing processes for additive manufacturing (AM) systems is a significant task for their standardization and implementation in the industry. Also, there is a large diversity of materials used in different AM processes. In the present paper, a methodology is proposed to evaluate, in different directions, the performance of an AM process and material characterization in terms of surface quality. This methodology consists of eight steps, based on a new surface inspection artifact and basic artifact orientations. The proposed artifact with several design configurations fits different AM systems sizes and meets the needs of customers. The effects of main factors on the surface roughness of up-facing platens of the artifacts are investigated using the statistical design of experiments. The proposed methodology is validated by a case study focused on PolyJet material jetting technology. Samples are manufactured of photopolymer resins and post-processed. Three factors (i.e., artifact orientation, platen orientation, and finish type) are considered for the investigation. The case study results show that the platen orientation, finish type, and their interaction have a significant influence on the surface roughness (Ra). The best Ra roughness results were obtained for the glossy finish type in the range of 0.5–4 μm.

Additive manufacturing (AM) processes have revolutionized manufacturing industries by enabling the production of complex geometries with reduced material waste and lead times. However, ensuring the quality of AM parts remains a significant challenge due to the complexity of the process and inherent variability in material properties. This review investigates the use of artificial intelligence (AI) to enhance quality assurance in AM processes, focusing on specific machine learning techniques such as convolutional neural networks for defect detection, support vector machines for classification of material properties, and reinforcement learning for real-time process optimization. The AI-driven methodologies are applied to predict defects, optimize process parameters, and monitor real-time production quality, utilizing large datasets generated from sensors and in-situ monitoring systems. The study demonstrates significant improvements in the accuracy of defect detection, the reliability of material property classification, and the efficiency of process optimization. In addition, it addresses challenges such as data pre-processing, model interpretability, and integration with existing AM systems. The findings highlight the potential of AI to transform quality assurance in AM and outline future research directions for further integration and enhancement of AI techniques in AM.

Cyber coordinated simulation for distributed multi-stage additive manufacturing systems

PurposeThis paper aims to present a systematic approach in the literature survey related to metal additive manufacturing (AM) processes and its multi-physics continuum modelling approach for its better understanding.Design/methodology/approachA systematic review of the literature available in the area of continuum modelling practices adopted for the powder bed fusion (PBF) AM processes for the deposition of powder layer over the substrate along with quantification of residual stress and distortion. Discrete element method (DEM) and finite element method (FEM) approaches have been reviewed for the deposition of powder layer and thermo-mechanical modelling, respectively. Further, thermo-mechanical modelling adopted for the PBF AM process have been discussed in detail with its constituents. Finally, on the basis of prediction through thermo-mechanical models and experimental validation, distortion mitigation/minimisation techniques applied in PBF AM processes have been reviewed to provide a future direction in the field.FindingsThe findings of this paper are the future directions for the implementation and modification of the continuum modelling approaches applied to PBF AM processes. On the basis of the extensive review in the domain, gaps are recommended for future work for the betterment of modelling approach.Research limitations/implicationsThis paper is limited to review only the modelling approach adopted by the PBF AM processes, i.e. modelling techniques (DEM approach) used for the deposition of powder layer and macro-models at process scale for the prediction of residual stress and distortion in the component. Modelling of microstructure and grain growth has not been included in this paper.Originality/valueThis paper presents an extensive review of the FEM approach adopted for the prediction of residual stress and distortion in the PBF AM processes which sets the platform for the development of distortion mitigation techniques. An extensive review of distortion mitigation techniques has been presented in the last section of the paper, which has not been reviewed yet.

Designing efficient closed-loop control algorithms is a key issue in Additive Manufacturing (AM), as various aspects of the AM process require continuous monitoring and regulation, with temperature being a particularly significant factor. Here we study closed-loop control for the temperatures in the extruder of a Material Extrusion AM system, specifically a Big Area Additive Manufacturing (BAAM) system. Previous approaches for temperature control in AM either require the knowledge of exact model parameters, or involve discretisation of the state and action spaces to employ traditional data-driven control techniques. On the other hand, modern algorithms that can handle continuous state and action space problems require a large number of hyperparameter tuning to ensure good performance. In this work, we circumvent the above limitations by making use of a state space temperature model while focusing on both model-based and data-driven methods. We adopt the Linear Quadratic Tracking (LQT) framework and utilise the quadratic structure of the value function in the model-based analytical solution to produce a data-driven approximation formula for the optimal controller. We demonstrate these approaches using a simulator of the temperature evolution in the extruder of a BAAM system and perform an in-depth comparison of the performance of these methods. We find that we can learn an effective controller using solely simulated input–output process data. Our approach achieves parity in performance compared to model-based controllers and so lessens the need for estimating a large number of parameters of the often intricate and complicated process model. We believe this result is an important step towards achieving autonomous intelligent manufacturing.

Additive manufacturing (AM) has gained notoriety for offering advantages over traditional manufacturing methods, such as increased design complexity and flexibility. However, it has not found widespread use beyond rapid prototyping. One hindrance to the acceptance of AM processes in industry is the time and cost of fabrication per component. While metal AM by itself can be inexpensive, extra manufacturing steps in the form of subtractive manufacturing (SM) may need to be performed to reach final part tolerances, leading to hybrid additive-subtractive manufacturing (HASM) of a part, which increases time and cost. A potential area to reduce cost is through increasing the efficiency of the HASM process by conducting additive and subtractive manufacturing simultaneously. Usually, HASM is performed in a process where AM is completed in one machine or cell and transferred to another machine or cell for SM in a sequential assembly line process. This efficiency decreases part cost, but high aspect ratio parts or parts with internal geometry that require interleaved additive deposition and machining cannot be produced. One unexplored solution to simultaneous HASM that allows for interleaved operations is to operate the deposition head and machining spindle concurrently within the same machine envelope, known as concurrent HASM (CHASM). In this type of process, both AM and SM occur simultaneously on a batch of small parts or a single large part, maintaining a high efficiency without sacrificing the full range of complex geometries that AM allows for. A potential approach to the single-machine method could be to combine a robot and mill within the same envelope. A challenge to this approach, however, is control of both systems. Most machine controllers have limited external communication or, if a robot has been integrated, only offer movement of either the robot or mill at any given time. As a result, systems must pause either the AM or SM process to switch between them rather than working simultaneously. The present work investigates the positional accuracy of such a CHASM system comprised of a robotic arm and a 3-axis mill. Open-loop tests with limited communication between machines are performed on the system to verify positional error during concurrent robot-mill movements. Under certain conditions, it is demonstrated that position error can stay within 2 mm for the duration of a single layer; however, these tests show that, generally, the open-loop positioning performance of the system is inadequate for CHASM without part-specific hand-tuning of parameters. Based on these results, a set of requirements for successful robot-CNC CHASM is proposed for future integrations.

PurposeMaterial extrusion (MEX) is a class of additive manufacturing (AM) process based on MEX principle. In the viewpoint of Industry 4.0 and sustainable manufacturing, AM technologies are gaining importance than conventional manufacturing route (subtractive manufacturing). Because of the ease of use and lesser operation skills, MEX had wide popularity in industry for product and prototype development. This study aims to analyze energy consumption of MEX-based AM process and its influencing factors.Design/methodology/approachA group of factors were identified pertaining to MEX-based AM process. In this viewpoint, this study presents the configuration of a structural model using interpretive structural modeling (ISM) to depict dominant factors in MEX-based AM process. A total of 18 influencing factors are identified and ranked using ISM methodology for MEX process. The Impact Matrix Cross-reference Multiplication Applied to a Classification analysis was done to categorize influencing factors into four groups for MEX-based AM process.FindingsThe derivation of structural model would enable AM practitioners to systematically analyze the factors and to derive key factors which enable comprehensive energy modeling and energy assessment studies. Also, it facilitates the development of energy efficient AM system.Originality/valueThe development of structural model for analysis of factors influencing energy consumption of MEX-based AM is the original contribution of the authors.

PurposeDue to the complexity of and variations in additive manufacturing (AM) processes, there is a level of uncertainty that creates critical issues in quality assurance (QA), which must be addressed by time-consuming and cost-intensive tasks. This deteriorates the process repeatability, reliability and part reproducibility. So far, many AM efforts have been performed in an isolated and scattered way over several decades. In this paper, a systematically integrated holistic view is proposed to achieve QA for AM.Design/methodology/approachA systematically integrated view is presented to ensure the predefined part properties before/during/after the AM process. It consists of four stages, namely, QA plan, prospective validation, concurrent validation and retrospective validation. As a foundation for QA planning, a functional workflow and the required information flows are proposed by using functional design models: Icam DEFinition for Function Modeling.FindingsThe functional design model of the QA plan provides the systematically integrated view that can be the basis for inspection of AM processes for the repeatability and qualification of AM parts for reproducibility.Research limitations/implicationsA powder bed fusion process was used to validate the feasibility of this QA plan. Feasibility was demonstrated under many assumptions; real validation is not included in this study.Social implicationsThis study provides an innovative and transformative methodology that can lead to greater productivity and improved quality of AM parts across industries. Furthermore, the QA guidelines and functional design models provide the foundation for the development of a QA architecture and management system.Originality/valueThis systematically integrated view and the corresponding QA plan can pose fundamental questions to the AM community and initiate new research efforts in the in-situ digital inspection of AM processes and parts.

Comparative study on life cycle assessment of components produced by additive and conventional manufacturing process