Intelligent Designs and Processes in Additive Manufacturing

Additive manufacturing (AM) is a transformative manufacturing technology that, unlike subtractive manufacturing, allows for parts with complex geometry to be fabricated without the use of special tools or machines. The exact amount of material specified in the CAD model is used, resulting in minimized material usage, functional flexibility and simplicity. Artificial intelligence (AI) techniques, such as machine learning (ML), deep learning, fuzzy logic, genetic algorithms, explainable AI (XAI) and others, are currently employed in AM with a focus on improving the level of automation in each phase of the AM process. This includes design for additive manufacturing (DfAM), process optimization, material selection, performance prediction, in-process quality inspection and process monitoring and control.

One of the key objectives of DfAM is achieving optimum performance while meeting user-defined goals, such as improved strength, increased stiffness, weight reduction, minimum mass, etc. Topology optimization that uses iterative computational optimization algorithms and generative design that incorporates machine learning algorithms are efficient DfAM techniques that can improve design freedom, reduce geometric complexity, optimize material usage, and enable novel structures and design paradigms. Material selection and process modelling is also a critical and complex pre-processing phase since multiple criteria must be considered, such as application and performance requirements, part quality, economic feasibility, sustainability, etc. In addition, the performance and quality of the manufactured part depends on the properties of the feedstock and the parameters of the printing process, and there is a wide variety of experimental and simulation data generated in AM manufacturing.

During the AM processing phase, the integration of machine learning (ML) models with machine vision and sensor technology can be utilized in in-situ process monitoring and quality assessment for detecting defects in the manufactured parts, such as geometric deviations, surface roughness, cracks, etc. In addition, ML techniques can be used for in-the-loop process control through autonomous and dynamic adjustment of critical printing parameters and immediate error correction, enhancing the accuracy and reliability of AM processes and ensuring high-quality and repeatable manufactured parts. With the integration of big data analytics and AI algorithms, large data sets can be processed and analyzed efficiently, providing accurate performance predictions and allowing for effective decision-making through different AM phases. ML models can be trained to develop relationships between input data (e.g., design domain, process parameters and experimental results) and output targets (e.g., mechanical properties, thermal behavior, energy efficiency, surface roughness and dimensional and geometric accuracy), providing optimal process parameters according to product requirements in various scenarios.

This Special Issue aims to highlight recent advances and provide novel insights into the challenges, approaches and state-of-the-art solutions regarding the application of Artificial Intelligent techniques in the field of additive manufacturing. This Special Issue welcomes original research articles, reviews and case studies focused on but not limited to the following topics:

• AI-assisted additive manufacturing (topology optimization, generative design, etc.);
• Autonomous decision-making methods and tools;
• The prediction of mechanical properties and the performance of additively manufactured parts;
• AM process modelling (predicting performance and optimizing process parameters, the development of process–property relationships, etc.);
• Quality inspection (the detection of defects and geometrical deviations in additively manufactured parts);
• In-situ process monitoring and process control;
• Data-driven design, material and process optimization using big data analytics and cloud computing;
• Applications in the automotive, aerospace, maritime, energy and biomedical industries.

Dr. Sotiria Dimitrellou
Prof. Dr. Dimitrios-Nikolaos Pagonis
Dr. Nicholas Sgouros
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• additive manufacturing
• artificial intelligence
• machine learning
• design optimization
• decision-making
• DfAM
• process planning
• AM data analytics
• real-time monitoring
• defect detection
• quality inspection
• AI/ML algorithms