Intelligent manufacturing systems bring together data, models, automation, and decision support to address manufacturing challenges. A 2019 special issue call from the Journal of Intelligent Manufacturing captured the breadth of this field, inviting research on how Industry 4.0 approaches could support manufacturing processes and shop-floor decisions. Although the submission timetable has passed, its themes remain a useful map of the technical questions that connect automation, operations, and manufacturing research.
What intelligent manufacturing systems encompass
The call did not define intelligent manufacturing as a single technology. Instead, it grouped a range of approaches that can help manufacturing systems sense conditions, interpret information, and support decisions. These included artificial intelligence, big data analytics, sensor information fusion, simulation, and Internet of Things (IoT) methods for self-configuration and self-diagnosis.
For industrial automation teams, this breadth matters. A manufacturing challenge may involve equipment condition, product quality, process performance, or production scheduling. Addressing it can require information from multiple sensors, analytical or model-based methods, and a way to present useful outputs to decision-makers. The special issue’s scope reflects that the value lies not simply in collecting data, but in applying it to manufacturing processes and decisions.
Industry 4.0 research themes for the plant floor
Quality assurance and inspection
Smart quality assurance and intelligent inspection were among the listed topics. These areas focus research attention on how inspection and quality activities can be informed by intelligent methods. The call also included the fusion of sensor information for manufacturing processes, a related theme where multiple information sources can be considered together rather than treated in isolation.
Predictive maintenance and equipment health
Smart maintenance, predictive and prescriptive capabilities, and prognostics and health management (PHM) were prominent topics. The call also distinguished data-driven and model-based prognostics. Together, these themes point to research into assessing equipment health and using that assessment to inform maintenance decisions. For plant managers and reliability teams, the practical question is how condition-related information can support action, not just generate more alarms or reports.
Analytics, simulation, and digital twins
Big data analytics for manufacturing systems and processes, virtualization, simulation, and digital twins for decision-making were also included. These approaches offer different ways to work with manufacturing information: analytics can examine data, while simulation and digital representations can help consider system behavior in a virtual setting. The call positioned these methods in relation to manufacturing decision-making, rather than presenting them as isolated technologies.
Adaptive operations and emerging applications
Other topics addressed how manufacturing systems might respond to changing conditions. They included self-configuration and self-diagnosis IoT methods for shop floors, as well as self-optimization models for scheduling and sequencing. The scope also extended to blockchain technology, resource efficiency and circular-economy tracking, autonomy, autonomous vehicles, and drones. This range illustrates how the Industry 4.0 research agenda spans both production operations and related questions of resource use and movement.
Why the call connected manufacturing and PHM communities
The special issue was organized alongside the 13th IFAC Workshop on Intelligent Manufacturing Systems (IMS 2019) and the Asian Pacific Conference of Prognostics and Health Management 2019 (PHM AP 2019). The editors planned to invite selected papers from both events, while also opening the issue to other high-quality research papers within its stated scope.
For selected conference papers, submissions to the special issue had to be extended versions of the work presented at the relevant event. This arrangement connected broad intelligent-manufacturing research with the more focused PHM field, while retaining an open call for contributions across the listed topics.
Submission process and historical timeline
The announced process began with an extended abstract of no more than 1,000 words, submitted as a PDF by email to Ahmad Barari by October 31, 2019. The abstract was expected to state the tentative paper title, author list, corresponding author, main contribution, results, and methodology. Authors were to receive notification about whether an extended paper could be reviewed by November 30, 2019.
Accepted authors then had to submit full papers through the journal’s submission system and identify the special issue in the system menu; email submissions were not allowed. The full-paper deadline was March 21, 2020. The schedule anticipated first-round review results by the end of June 2020, possible revised submissions by the end of September, final decisions by the end of November, and online publication in early 2021. These dates describe a completed historical call, not an open submission opportunity.
Practical implications for automation teams
The call’s enduring value is its view of intelligent manufacturing as a connected set of capabilities and research problems. Quality, maintenance, analytics, simulation, decision support, and adaptive shop-floor operations all appear within the same agenda. For engineers, integrators, and operations leaders, that is a reminder to frame digitalization initiatives around the manufacturing decision or process they are intended to support.
Whether evaluating predictive maintenance, sensor fusion, or a digital twin, teams can usefully ask how the approach relates to available process information, operational decisions, and the wider production system. The special issue’s themes offer a structured lens for those discussions: intelligent manufacturing systems are not one tool or deployment, but a broad field connecting data and models to manufacturing needs.
Access Official Technical PDF