Smart factories are complex environments equipped with both production machinery and computing devices that collect, share, and analyze data. For this reason, the modeling of today's factories can no longer rely on traditional methods, and computer engineering tools, such as SysML, must be employed. At the same time, the current SysML v1. * standard does not provide the rigorousness required to model the complexity and the criticalities of a smart factory. Recently, SysML v2 has been proposed and is about to be released as the new version of the standard. Its release candidate version shows the new version aims at providing a more rigorous and complete modeling language, able to fulfill the requirements of the smart factory domain. In this paper, we explore the capabilities of the new SysML v2 standard by building a rigorous modeling strategy, able to capture the aspects of a smart factory related to the production process, the computation and the communication. We apply the proposed strategy to model a fully-fledged smart factory, and we rely on models to automatically configure the different pieces of equipment and software components in the factory.

This paper presents an architecture for automated fault recovery in special-purpose machinery using standard IEC 61131-3 PLC control software. Building upon the MAPE-K paradigm (Monitor, Analyze, Plan, Execute with Knowledge), the proposed three-level architecture integrates runtime control via a previously presented modularization concept called Control Primitives, high-level reasoning using Regionalized Resource Process Dependence Graphs (RRPDGs), and an intermediate Resource Agent that bridges field-level execution and recovery planning. The architecture supports fully automated dynamic recovery and seamless resumption of productive operations while maintaining real-time reliability. Experimental evaluation demonstrates the scalability and low resource demands of the planning system across simulated scenarios and validates the concept on a lab-sized real-world demonstrator. The architecture and interfaces build a modular foundation for future research and industrial applications.

The complexity of current manufacturing systems is growing, increasing the complexity of testing and validating control software. Manufacturing software must be extensively tested to minimize errors that may lead to production stops or machine breakdowns. However, testing on real manufacturing systems is often impractical or limited to small portions of the real systems. This paper presents Frost, an open-source platform supporting early manufacturing software validation and testing. Frost is built on top of the Lingua Franca framework, which ensures deterministic execution, enhancing the reliability of software prototyping and testing. The proposed platform implements a set of reactors and classes designed to model the different parts of a manufacturing system, such as sensors, machines, control software, and communication infrastructure. The effectiveness and capabilities of the Frost platform are validated by comparing the overhead introduced and by implementing a digital twin of a real manufacturing system.

Detecting complex anomalies on massive amounts of data is a crucial task in Industry 4.0, best addressed by deep learning. However, available solutions are computationally demanding, requiring cloud architectures prone to latency and bandwidth issues. This work presents VARADE, a novel solution implementing a light autoregressive framework based on variational inference, which is best suited for real-time execution on the edge. The proposed approach was validated on a robotic arm, part of a pilot production line, and compared with several state-of-the-art algorithms, obtaining the best trade-off between anomaly detection accuracy, power consumption and inference frequency on two different edge platforms.

With the rise of Machine Learning (ML) and Artificial Intelligence (AI), the semiconductor industry is undergoing a revolution in how it approaches manufacturing. The SMART-IC project (DATE'24 MPP category: initial stage) works in this direction, by proposing an AI-enabled framework to support the smart monitoring and optimization of the semiconductor manufacturing process. An AI-powered engine examines sensor data recording physical parameters during production (like gas flow, temperature, voltage, etc.) as well as test data, with different goals: (1) the identification of anomalies in the production chain, either offline from collected data-traces or online from a continuous stream of sensed data; (2) the forecasting of new data of the future production; and (3) the automatic generation of synthetic traces, to strengthen the data-based algorithms. All such tasks provide valuable information to an advanced Manufacturing Execution System (MES), which reacts by optimizing the production process and management of the equipment maintenance policies. SMART-IC is a 300k€ academic project funded by the Italian Ministry of University and supported by STMicroelectronics and Technoprobe with industrial expertise and real-world applications. This paper shares the view of SMART-IC on the future of semiconductor manufacturing, the preliminary efforts, and the future results that will be reached by the end of the project, in 2025.

The DeFacto project, supported by the European Commission via a Marie Skłodowska-Curie Global Individual Fellowship, tackles the complexity arising from the transformation of industrial manufacturing systems into intricate cyber-physical systems. This evolution offers unprecedented opportunities but also poses intellectual and engineering challenges. DeFacto aims to advance the design automation of cyber-physical production systems by developing innovative modeling paradigms, scalable algorithms, software architectures, and tools. In the DeFacto approach, production systems are managed through service-oriented manufacturing software architectures. System-level models capture the features and the requirements of production systems, representing both production and computational processes as services provided by the infrastructure. Methodologies for system analysis and optimization rely on compositional abstractions of system behaviors grounded in assume-guarantee contracts. This paper outlines key research endeavors, findings, and lessons learned from the DeFacto project.

Smart manufacturing systems often use data to optimize production processes. Artificial intelligence algorithms can be used to tune the parameters of production recipes to achieve the desired results. Indeed, such algorithms will require to be trained by using data collected while executing manufacturing operations. However, the required sets of data are rarely available to most production companies. This work-in-progress paper introduces the Print+Mill dataset: a collection of data related to additive and subtractive manufac-turing operations. The data are collected during the execution of various production recipes, utilizing different materials and process parameters. For each recipe, the dataset includes data on the materials and parameters used, sensor readings from the machinery, such as power consumption and temperature, and information on the quality of the resulting product. The data are collected in a complex research facility; in the future, we plan to extend the dataset by considering other manufacturing operations, materials, and types of field data.

The design of manufacturing systems requires exploring diverse component configurations for one that best satisfies the requirements of the target system. At the same time, manufacturing systems evolve continuously, increasing their complexity and that of the production line in which they are installed. Model-based System Engineering (MBSE) methodologies and modeling languages like System Modeling Language (SysML) are used to assist system engineers during the entire design process. Yet, MBSE methodologies mainly rely on manually composed models for requirements verification, incurring enormous cost and effort especially in larger, more complex systems. This paper proposes a methodology exploiting the knowledge enclosed in a SysML model to automate the execution of a set of analyses defined over the represented manufacturing system. The proposed approach relies on Lingua Franca (LF) to simulate the specified analysis and analyze the results. Moreover, the methodology supports chains of analyses to represent dependent requirements and tradeoffs imposed upon a manufacturing system. The proposed methodology has been evaluated on a manufacturing system demonstrator. Results show the proposed methodology's applicability and scalability on diverse configurations of the manufacturing system.

The continuous evolution of Industry 4.0 demands advanced solutions for optimizing production processes, reducing energy consumption, and enhancing the capabilities of both human operators and production devices in smart factories. As factory automation software becomes increasingly complex, ensuring its robustness through extensive testing is critical. However, testing on actual production systems is often impractical due to the critical nature of the software.This paper explores the use of digital twins to simulate factory environments, enabling thorough validation of automation software. We propose leveraging Lingua Franca and the Functional Mock-up Interface (FMI) standard to create comprehensive digital twins. Lingua Franca ensures deterministic execution in simulations, while FMI facilitates the integration of diverse simulators for accurate modeling of heterogeneous systems. We introduce an interfacing method to integrate FMI components within Lingua Franca and present a strategy for modeling software-machinery interactions using the OPC Unified Architecture (OPC UA) protocol. The methodology is applied to develop a digital twin of a logistics subsystem in a manufacturing system, demonstrating the effectiveness of the simulation environment through various scenarios.

This article introduces the regionalized resource process dependence graphs (RRPDGs): a manufacturing processes representation inspired by the regionalized value state dependence graphs traditionally used in software compilers. An RRPDG is an ordered sequence of nodes, each characterized by stereotyped input and output parameters, encapsulating a transformation of the process state (e.g., a manufacturing operation). RRPDG allow defining complex transformations by composing a set of nodes (i.e., regions), hiding the internal details. Then, RRPDGs are used to automatically reasoning over dynamic reconfiguration and process optimization: an instance of the A-star search algorithm is used to search for possible transformations while pursuing an optimization function. The rules defined in this article over RRPDG models enforce the transformations' correctness. We use RRPDGs to model a real production system while the transformation rules are applied to optimize the system's processes. The proposed representation reduced the search complexity in each experiment, allowing to reach an optimal solution also in the case for which classical approaches were unable to complete before reaching the timeout. In all the experiments, the cost of the solution produced by using the regionalized representation is minor than the the solution produced by using the classical representation.

Industry 4.0 involves the integration of digital technologies, such as IoT, Big Data, and AI, into manufacturing and industrial processes to increase efficiency and productivity. As these technologies become more interconnected and interdependent, Industry 4.0 systems become more complex, which brings the difficulty of identifying and stopping anomalies that may cause disturbances in the manufacturing process. This paper aims to propose a diffusion-based model for real-time anomaly prediction in Industry 4.0 processes. Using a neuro-symbolic approach, we integrate industrial ontologies in the model, thereby adding formal knowledge on smart manufacturing. Finally, we propose a simple yet effective way of distilling diffusion models through Random Fourier Features for deployment on an embedded system for direct integration into the manufacturing process. To the best of our knowledge, this approach has never been explored before.

The early detection of anomalous behaviors from a production line is a fundamental aspect of Industry 4.0, facilitated by the collection of massive amounts of data enabled by the Industrial Internet of Things. Nonetheless, the design and validation of anomaly detection algorithms, mostly based on sophisticated Machine Learning models, heavily rely on the availability of annotated datasets of realistic anomalies, which is very difficult to obtain in a real production line. To address this problem, we introduce the Robotic Arm Dataset (RoAD), specifically designed to support the development and validation of Multivariate Time Series Anomaly Detection (MTSAD) algorithms. We collect and annotate a large number of data and metadata to characterize the motion and energy consumption of a collaborative robotic arm in a full-fledged production line and annotate a comprehensive set of healthy as well as realistic anomalies scenarios. To prove the significance of RoAD and encourage future developments, we benchmark several state-of-the-art anomaly detection algorithms on our newly introduced dataset, and we freely release it to the scientific community.

This paper presents a software architecture extending the classical automation pyramid to control and reconfigure flexible, service-oriented manufacturing systems. At the Planning level, the architecture requires a Manufacturing Execution System (MES) consistent with the International Society of Automation (ISA) standard. Then, the Supervisory level is automated by introducing a novel component, called Automation Manager. The new component interacts upward with the MES, and downward with a set of servers providing access to the manufacturing machines. The communication with machines relies on the OPC Unified Architecture (OPC UA) standard protocol, which allows exposing production tasks as “services”. The proposed software architecture has been prototyped to control a real production line, originally controlled by a commercial MES, unable to fully exploit the flexibility provided by the case study manufacturing system. Meanwhile, the proposed architecture is fully exploiting the production line's flexibility.

Manufacturing systems require a careful scheduling of the resource usage to maximize the production efficiency. In a completely automated environment, the transport system should be orchestrated to work smoothly with the other resources. While the impact of job characteristics, such as fixed or variable processing times of the tasks composing the jobs, or task dependencies, has been extensively studied, the role of the transport system has received less attention.In this paper we consider a conveyor belt as a mean of transportation among a set of production machines. In this scenario, there is no input or output buffer at the machines, and the transport times depend on the availability of the machines. We propose a heuristic based on randomization, called SCHED-T, which is able to find a near optimal joint schedule for job processing and transfer in few seconds. We test our solution on known benchmarks, along with real-world instances, showing that our scheduler is able to predict accurately the overall processing time of a production line.

Products and materials traceability is essential in modern manufacturing, where the production must meet certain standards that range from Quality Control (QC) to the quality of the used materials. In this environment, blockchain applications allow certifying data provenience and subsequent modification, offering trust and security along the entire supply chain. Nonetheless, the design and the development of such applications are usually performed manually and, thus, subject to errors.In this paper, we propose a methodology allowing to automatically generate smart contracts starting from a SysML model. This approach allows easing the integration of blockchain applications in a production system: by abstracting the implementations with models, it is possible to generate smart contracts for different blockchains, connecting to multiple production environments.We applied the proposed methodology on a real manufacturing system, assessing the quality of a case-study production.

Manufacturing lines are evolving into complex cyber-physical production systems. However, their growth in complexity is not matched by the development of structured modeling and design methodologies. In particular, approaches exploiting both models typical of the manufacturing domain and models used by computer engineers are still missing. In this work, we outline a design flow contemplating the reuse of already existing manufacturing lines' models, while designing novel advanced production systems. To enable such a flow, we propose a methodology extracting System Modeling Language (SysML) structural diagrams from AutomationML descriptions. Then, we propose to design the system functionalities on top of the produced diagrams. The paper shows the application of the methodology to a concrete manufacturing line, the structure of which was originally modeled using AutomationML. To exemplify the advantages of the methodology, we exploit the models being generated to automatically extract a digital twin for the production system transportation line. The resulting digital twin is compliant with a well-known plant simulation tool.

The Industry 4.0 trend speeds up the adoption of a variety of technologies. In modern manufacturing, system data are collected both from the field through sensors and by exploiting complex simulations. Data analysis techniques became crucial to build and maintain any efficient production line, while autonomous systems and robots are the main focus of researchers and practitioners. This pervasive use of artificial intelligence derived technologies pushed humans to the border of production systems. Industry 5.0 aims at bringing the attention back to humans in production lines while magnifying their interactions with intelligent systems. This new trend will impact the design of future manufacturing infrastructures, increasing their complexity. Engineers will need modeling and developing tools able to capture this complexity. In this paper, we analyze the modeling languages and tools being used, identifying their strengths and weaknesses. Then, we propose some possible directions to provide engineers with the expressive power needed to tackle the challenges posed by Industry 5.0.