Data Science in Manufacturing Processes

Dear Colleagues,

A manufacturing process transforms a given volume of material into a component with a prescribed geometry, dimensional accuracy, and functional performance. Within the manufacturing ecosystem, processes are commonly classified into several major categories. Subtractive manufacturing processes include turning, milling, drilling, and related machining operations. Formative manufacturing processes comprise bulk deformation methods such as extrusion and rolling, as well as casting processes including injection molding, sand casting, and investment casting. Joining processes encompass arc welding, friction welding, and related techniques. Surface engineering methods include chemical vapor deposition (CVD) and physical vapor deposition (PVD). Nonconventional machining processes involve electrical discharge machining (EDM), micro- and nano-machining, and other advanced material removal techniques. Additive manufacturing processes include laser sintering and fused deposition modeling, among others. This classification continues to evolve as new technologies emerge.

The physical phenomena associated with each manufacturing process are inherently complex and often involve coupled thermal, mechanical, chemical, and tribological interactions. Consequently, research in manufacturing has traditionally relied on empirical and experimental approaches to characterize process behavior and performance. Over time, these studies and industrial practices have generated a substantial body of process data.

With the advancement of smart manufacturing systems and digital infrastructure, including sensor integration, cyber–physical systems, and data analytics platforms, these accumulated datasets can now be systematically exploited. Data-driven methodologies enable improved process modeling, parameter optimization, predictive maintenance, and adaptive control. As a result, manufacturing data can support the development of robust research strategies and enhance operational efficiency, thereby contributing measurable value to manufacturing systems as an integrated whole.

Contributions to this Special Issue, titled “Data Science in Manufacturing Processes”, should address the development, validation, and application of data-driven methods that advance fundamental understanding or practical performance of manufacturing operations. Suitable topics include machine learning and deep learning models for process prediction and control, hybrid physics-informed and data-driven modeling frameworks, uncertainty quantification, digital twins, anomaly detection, quality prediction, tool wear estimation, and real-time decision support systems. Studies that integrate multi-source data, such as in situ sensor signals, image-based monitoring, simulation outputs, and production logs, are particularly encouraged.

Submissions should demonstrate methodological rigor, reproducibility, and clear industrial relevance. Preference will be given to contributions that establish generalizable frameworks rather than isolated case studies, provide comparative benchmarking against established methods, and articulate the physical interpretation of data-driven results. Papers that bridge manufacturing science and data science, including scalable architectures for smart factories, edge computing strategies, and knowledge representation models for manufacturing systems, are also within scope. The objective of the Special Issue is to define a systematic foundation for data science in manufacturing and to promote transferable methodologies that enhance robustness, productivity, and sustainability across diverse process domains.

Prof. Dr. Sharifu Ura
Guest Editor

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 250 words) can be sent to the Editorial Office for assessment.

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. Journal of Manufacturing and Materials Processing is an international peer-reviewed open access monthly 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 1800 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.

• data science
• open data
• big data
• manufacturing processes
• smart manufacturing
• machine learning
• deep learning
• physics-informed modeling
• hybrid modeling
• digital twin
• process monitoring
• process optimization
• predictive maintenance
• tool wear prediction
• quality prediction
• anomaly detection
• sensor fusion
• multimodal data analytics
• uncertainty quantification
• cyber–physical systems
• edge computing
• industrial artificial intelligence
• knowledge representation
• manufacturing informatics
• data-driven control
• real-time decision support
• sustainable manufacturing