Dear Colleagues,

The quest towards Industry 4.0 and the associated requirement to create virtual replicas of physical devices (known as digital twins) has engendered the exploration of numerous research directions. Predictive and prescriptive maintenance, data center automation, fault detection, and root cause identification are among some of the most tackled challenges in this area. A wide variety of approaches have been proposed to address these issues, including full testing and deployment on real systems.

The wealth of big data originating from multiple sensors installed at various levels of granularity on industrial systems and components, as well as data centers and related computing nodes, has offered the possibility to create and train powerful data-driven machine learning (ML) and deep learning (DL) models, aimed at a variety of tasks.

There are strong motivations for the interest of researchers in this area. Firstly, the digitalization of complex manufacturing systems and computing facilities, and the automation of their management processes are of paramount importance for the sake of improving performance and reliability, reducing operating costs, and decreasing energy consumption. Secondly, the task of extracting meaningful information from the massive amount of data generated by the monitoring systems of modern industrial machines and large-scale computing facilities is overwhelming.

In this scenario, the adoption of ML/DL approaches is paramount to assist human activities and alleviate the burden of daunting tasks. Prospective fields of application for these techniques include data center automation, fault detection, and predictive maintenance. Moreover, additional concerns stem from their deployment on a wide range of target systems, ranging from the scalability issues of distributed DL models in the cloud to the limited computing resources of IoT edge devices.

The purpose of this Special Issue is to make the scientific community aware of the most recent advances in this area, and to show the current state of these technologies by analyzing different approaches and methodologies, identifying trends and challenges, and learning lessons from already deployed solutions and success stories. This review of the current state-of-the-art is not intended to make an exhaustive exploration of all of the existing works, but rather aims at providing an overview of the research targeting Machine Learning applied to Industry 4.0, bringing out the high level of activity of this area.

Prof. Dr. Andrea Borghesi
Prof. Dr. Giuseppe Tagliavini
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.

• Digital twins for manufacturing
• ML/DL applications for predictive maintenance
• ML/DL applications for prescriptive maintenance
• ML/DL models for anomaly detection and fault detection in data centers and HPC systems
• On-edge inference of DL models for Industry 4.0
• ML/DL models for root cause analysis
• Explainable ML/DL models for Industry 4.0
• Combining data-driven models and domain knowledge for predictive maintenance
• Transfer learning approaches in Industry 4.0 and predictive maintenance
• ML model implementations, deployment, and validation on real industrial and HPC systems
• Deploying ML/DL models on IoT devices with severe power constraints
• Static and dynamic mapping of ML/DL components at different levels of the IoT