Enabling Intelligence in Additive Manufacturing for First Time-Right Production

About the Project

Please note, there is no funding attached to this project. All tuition fees and any other associated costs (including bench fees) must be financed by the student. Please consider this before submitting your application.

PhD Research Topic

Additive Manufacturing (AM), commonly referred to as 3D printing, is transforming how high-performance and bespoke components are designed and produced. While AM offers significant advantages in terms of design freedom and material efficiency, one of its most pressing limitations is process unpredictability. In most cases, multiple trials are required before a high-quality component is achieved. This inefficiency results in unnecessary use of time, energy, and materials—especially detrimental when manufacturing high-value parts. This PhD project aims to overcome that limitation by embedding intelligence within AM systems through sensing, data analytics, and machine learning. The overarching goal is to make “first-time-right” production a standard outcome in AM.

The research will focus on polymer and/or metal AM technologies, depending on the student’s background and interests. The central vision is to move away from fixed parameter sets and towards intelligent, adaptive systems capable of real-time decision-making during the build. This project will integrate in-process monitoring with artificial intelligence (AI) and control algorithms that respond dynamically to defects or anomalies—leading to highly reliable, first-attempt successful builds.

The student will begin by developing a deep understanding of defect formation in AM processes, informed by both literature and experimental observations. Various sensing techniques will be explored—including infrared thermography, high-speed imaging, acoustic emission, and thermocouples—to detect critical indicators of quality such as overheating, inter-layer adhesion issues, void formation, or geometrical deviations. The project will identify an optimal combination of sensors appropriate for specific AM technologies and develop methods to integrate them into the process without disrupting the build environment.

The next stage of research will involve processing the sensor data to extract meaningful features. These data streams will be used to train AI and machine learning models—such as neural networks, decision trees, or support vector machines—to predict build quality and detect process deviations. Initial training will be based on a controlled set of builds with known defect types, and this dataset will grow over the course of the project. The developed models will not only classify issues but will also generate feedback for adaptive process control, increasing the level of autonomy in the AM system.

The third core component of the research involves developing a closed-loop feedback system. This system will act on the predictions made by the AI models and automatically adjust process parameters such as laser power, scanning speed, or extrusion temperature during the build. The aim is to stabilise conditions in real time and prevent minor anomalies from developing into critical defects. The feedback system will be trialled on a series of benchmark parts, increasing in complexity, to demonstrate its generalisability and reliability.

The project will be based in Sheffield Hallam University’s state-of-the-art manufacturing laboratories. Facilities include advanced polymer and metal 3D printers, thermal and acoustic imaging systems, sensor integration platforms, and analysis software such as Ansys, MATLAB, and Python-based machine learning libraries. The student will benefit from SHU’s multi-disciplinary expertise in materials science, mechanical engineering, computing, and automation, along with exposure to industrial collaborations and technology transfer pathways.

The originality of this project lies in its holistic integration of sensing, data analytics, and control logic to enable truly adaptive AM. While current systems rely heavily on pre-set parameters and post-build inspection, this project aspires to build a new generation of intelligent manufacturing platforms that continuously learn and optimise as they operate. The reduction in failed builds directly supports sustainability targets, reduces material and energy usage, and improves cost-efficiency in industrial settings.

In addition to academic outputs such as journal articles and conference presentations, this research will deliver broader impact. The work aligns with SHU’s research themes in Smart Manufacturing, AI and Robotics, and Sustainable Engineering. From a societal perspective, the research provides opportunities for engagement through school outreach activities, such as showcasing how digital twins operate during university open days. Economically, the technology could enhance productivity across industries that are increasingly relying on AM for rapid production of tooling, fixtures, and end-use components.

Ultimately, this PhD project will equip the successful candidate with cutting-edge skills in smart manufacturing, automation, and AI integration—positioning them for careers in advanced engineering, research, and industrial R&D. The developed framework may serve as a prototype for the next generation of intelligent, self-optimising manufacturing systems.

Eligibility

Applicants should hold a 1st or 2:1 Honours degree in a related discipline. A Master’s degree in a related area is desirable. We welcome applications from all candidates irrespective of age, pregnancy and maternity, disability, gender, gender identity, sexual orientation, race, religion or belief, or marital or civil partnership status.

International candidates are required to provide an IELTS certificate with a score of at least 6.5 overall , and a minimum of 6.0 in all components. For further information on English Language requirements, please click here.

How to apply

To apply, please use our online application form.

As part of your application, please upload:

• A research proposal (max. 1500 words) in your own words, briefly outlining the proposed research, the current knowledge and context referencing key background literature; a proposed methodology or approach to answer the key questions, and any potential significance or impact of the research
• Copy of your highest degree certificate
• Non-UK applicants must submit IELTS results (or equivalent) taken in the last two years and a copy of their passport.

Applicants must provide 2 references, with at least one to be academic. References must be received directly from the referees.

We strongly recommend you contact the lead academic, Dr Prveen Bidare p.bidare@shu.ac.uk, to discuss your application.

Information about our research degrees can be found here.

Funding Notes

There is no funding attached to this project. The applicant will need to fund their own tuition fees, as well as any associated bench fee and living expenses. The home tuition fee for 25/26 is £5,006 and the international tuition fee for 25/26 is £17,725 (not including any applicable bench fee). For further information on fees, visit View Website