The objective of this paper is to examine the use and applications of reinforcement learning (RL) techniques in the production planning and control (PPC) field addressing the following PPC areas: facility resource planning, capacity planning, purchase and supply management, production scheduling and inventory management. The main RL characteristics, such as method, context, states, actions, reward and highlights, were analysed. The considered number of agents, applications and RL software tools, specifically, programming language, platforms, application programming interfaces and RL frameworks, among others, were identified, and 181 articles were sreviewed. The results showed that RL was applied mainly to production scheduling problems, followed by purchase and supply management. The most revised RL algorithms were model-free and single-agent and were applied to simplified PPC environments. Nevertheless, their results seem to be promising compared to traditional mathematical programming and heuristics/metaheuristics solution methods, and even more so when they incorporate uncertainty or non-linear properties. Finally, RL value-based approaches are the most widely used, specifically Q-learning and its variants and for deep RL, deep Q-networks. In recent years however, the most widely used approach has been the actor-critic method, such as the advantage actor critic, proximal policy optimisation, deep deterministic policy gradient and trust region policy optimisation.

A wide variety of methods and techniques with multiple characteristics are used in solving replenishment, production and distribution planning problems. Selecting a solution method (either a solver or an algorithm) when attempting to solve an optimization problem involves considerable difficulty. Identifying the best solution method among the many available ones is a complex activity that depends partly on human experts or a random trial-and-error procedure. This paper addresses the challenge of recommending a solution method for replenishment, production and distribution planning problems by proposing a decision-making tool for algorithm selection based on the fuzzy TOPSIS approach. This approach considers a collection of the different most commonly used solution methods in the literature, including distinct types of algorithms and solvers. To evaluate a solution method, 13 criteria were defined that all address several important dimensions when solving a planning problem, such as the computational difficulty, scheduling knowledge, mathematical knowledge, algorithm knowledge, mathematical modeling software knowledge and expected computational performance of the solution methods. An illustrative example is provided to demonstrate how planners apply the approach to select a solution method. A sensitivity analysis is also performed to examine the effect of decision maker biases on criteria ratings and how it may affect the final selection. The outcome of the approach provides planners with an effective and systematic decision support tool to follow the process of selecting a solution method.

The ambition of the EU Data Strategy can be summarized as a ‘federation of interoperable data spaces’. Currently, a multitude of architectures, frameworks and protocols is used by various data spaces. The Data Sharing Coalition has provided an architecture framework for interoperability between data spaces, making use of a harmonization domain and data space proxies as key architecture concepts. Complete interoperability between a wide variety of data spaces presents a challenge for the harmonization domain. To enable interoperability between a variety of data spaces, a set of harmonization profiles are required in the harmonization domain to provide the necessary functionalities. However, implementing each harmonization profile comes with additional complexity. Therefore, it is desirable to identify a minimal set of harmonization profiles to provide interoperability between an adequate variety of data spaces. This paper addresses the identification of harmonization profiles, presents a framework for structuring harmonization profiles and explores the impact of key trust aspects (policy management and trust ecosystem) on harmonization profiles.

This paper addresses the i4Q project vision, including stakeholders’ requirements and expectations, aiming to present the digital technologies, as well as a multi-dimensional benchmarking instrument that supports the i4Q design and development. It also sets clear specifications that drive the creation of i4Q. It analyses the current systems of the demonstration scenarios, to establish the starting point (Key Performance Indicators’ (KPIs)) for the implementation of their industrial use cases and to understand how, data reliability and manufacturing quality, are impacted by i4Q. Finally, it focuses on the most suitable KPIs and identifies the most relevant regulation and trustworthy systems for data management in the i4Q Solutions.

With the target of Zero-Defect Manufacturing, the European Project Industrial Data Services for Quality Control in Smart Manufacturing (i4Q) aims to develop 22 software solutions based on Artificial Intelligence (AI) to optimize manufacturing processes, ensuring quality, effectiveness and interoperability among manufacturing companies. The solutions will be implemented in real manufacturing scenarios, where the outcomes of the project will be tested and evaluated. One of the solutions, i4Q Line Reconfiguration Toolkit, will be deployed in FACTOR, a manufacturing company dedicated to metal machining and precision turning. This paper covers: (i) the introduction of the pilot case and the project solutions; (ii) the goal that FACTOR aims to achieve by the implementation of the solutions; (iii) the main features of the Line Reconfiguration Toolkit solution and their alignment with the requirements exposed by FACTOR, and (iv) the expected results when applying i4Q Line Reconfiguration Toolkit in FACTOR.

Nowadays, manufacturing companies are eager to access insights from advanced analytics, without requiring them to have specialized IT workforce or data science advanced skills. Most of current solutions lack of easy-to-use advanced data preparation, production reporting and advanced analytics and prediction. Thanks to the increase in the use of sensors, actuators and instruments, European manufacturing lines collect a huge amount of data during the manufacturing process, which is very valuable for the improvement of quality in manufacturing, but analyzing huge amounts of data on a daily basis, requires heavy statistical and technology training and support, making them not accessible for SMEs. The European i4Q Project, aims at providing an IoT-based Reliable Industrial Data Services (RIDS), a complete suite consisting of 22 i4Q Solutions, able to manage the huge amount of industrial data coming from cheap cost-effective, smart, and small size interconnected factory devices for supporting manufacturing online monitoring and control. This paper will present a set of i4Q services, for data integration and fusion, data analytics and data distribution. Such services, will be responsible for the execution of AI workloads (including at the edge), enabling the dynamic deployment industrial scenarios based on a cloud/edge architecture. Monitoring at various levels is provided in i4Q through scalable tools and the collected data, is used for a variety of activities including resource monitoring and management, workload assignment, smart alerting, predictive failure and model (re)training.

Data sovereignty is the right that individuals and organizations own to control the access to and the disclosure of their private and sensitive data. In Europe, the International Data Spaces Association (IDSA) aims to promote this right by proposing technical and organizational guidelines to help companies build trusted data exchange ecosystems. The IDSA suggests the IDS Connectors as software components necessary to enforce data sovereignty on the technical level. Among many possible functionalities, an IDS Connector could enable (1) data exchange between data owners' and data user's Enterprise systems in a standardized communication protocol; (2) data access policy enforcement; and (3) internal data transformation operations, e.g., integration, mapping, or merging. However, software and service providers may start soon offering IDS Connectors with different configurations through multiple platforms on the Web, making the practical adoption of the IDS architectural guidelines more difficult, especially for small and medium enterprises. We propose developing an IDS Connector Store to discover and select IDS Connectors in IDS ecosystems to cope with this issue. The store will operate as a metadata repository to describe the connectors according to contextual information, e.g., the business domain, pricing model, and data access policies enforced. This paper reports on the current state of this research endeavor by providing a threefold contribution. First, it elaborates on research questions, methods, and goals to address the design problem on hand. Second, it presents an ontology requirements specification document highlighting competency questions related to discovering and selecting IDS Connectors in an IDS ecosystem. Last, it provides the first conceptual draft of an ontology for IDS Connectors described in OntoUML posed for discussion among the conceptual modeling community and to guide meaningful and further specification in Web Ontology Language (OWL).

Increased consumerism and the competitiveness of the global market have led to more stringent requirements in terms of product quality and manufacturing lines. The i4Q European project’s Rapid Manufacturing Line Qualification and Reconfiguration set of solutions aims to develop new and improved strategies and methods for process qualification, process reconfiguration and optimization using existing manufacturing data and intelligent algorithms. The set of solutions provides manufacturing lines’ diagnosis and prescription, process capacity forecasting, manufacturing line reconfiguration propositions, and data quality certifications and audit procedures. With this information, plant managers can make the required changes to the plant to improve manufacturing products’ quality, machines’ life cycle, plants’ productivity and so on.

The i4Q Project aims to provide a complete set of solutions consisting of IoT-based Reliable Industrial Data Services (RIDS), the so-called 22 i4Q Solutions, able to manage the huge amount of industrial data coming from cheap cost-effective, smart, and small size interconnected factory devices for supporting manufacturing online monitoring and control. This papers presents the reference architecture used to guide the development of IoT-based Reliable Industrial Data Services for Manufacturing Quality Control. Based on industry standards and known best practices, the reference architecture adopts a three-tiered architectural model to represent the main system architectural components, and provides four different architectural viewpoints to address business, usage, functional, and implementation concerns.

European manufacturing companies collect a large amount of data during their manufacturing processes thanks to the increasing use of sensors, actuators and instruments. This amount of data is very valuable for improving manufacturing quality, with a view to the Zero Defects objective. In order to take full advantage of the vast amount of accumulated data, quality must be targeted, and its Security, Trustiness and Traceability must be preserved. Data quality is influenced by several factors: including human errors, communication problems or inaccuracies, so any system used must be sufficiently reliable. This paper describes the technical approach to develop solutions to control manufacturing Data Security, Trustiness and Traceability with a zero-defect approach and provided by the i4Q project. The approach is exemplified with the industrial production line of injected plastic spare parts for the automotive sector.

An International Data Space (IDS) aims to support sharing sensitive data among trusted actors, enabling data owners to control how other agents could use their data, a property commonly denoted as data sovereignty. Data sharing with autonomy is increasingly essential for modern businesses to form ecosystems providing complex services to demanding clients. An IDS ecosystem requires the formation of data-sharing agreements involving different business roles. A data usage contract constitutes a central artifact to formalize this type of agreement. It can also guide actors in implementing or selecting the software components required to enforce data sovereignty. However, there are at least two critical challenges to overcome before forming data-sharing agreements in IDS. First, actors may interpret or represent data usage contracts differently, resulting in a semantic interoperability problem. Second, even assuming semantic mismatches as resolved, contract formation, in this case, would require business process alignment, which leads to an organizational interoperability problem. To address these issues, we envision a digital twin to simulate the formation of data-sharing agreements in IDS, which could support companies exploring semantic and organizational mismatches in this kind of environment. It could also help them assess the risks of adopting and implementing IDS technology. The contribution of this paper is threefold: (1) a research design based on the problem-solving perspective of Design Science; (2) a preliminary architectural model of the digital twin; and (3) a capability assessment of tools for modeling the digital twins envisioned by this research.

Based on a scientific literature review in the conceptual domain defined by smart manufacturing scheduling
(SMS), this article identifies the benefits and limitations of the reviewed contributions, establishes and discusses a
set of criteria with which to collect and structure its main synergistic attributes, and devises a conceptual
framework that models SMS around three axes: a semantic ontology context, a hierarchical agent structure, and
the deep reinforcement learning (DRL) method. The main purpose of such a modelling research is to establish a
conceptual and structured relationship framework to improve the efficiency of the job shop scheduling process
using the approach defined by SMS. The presented model orients the job shop scheduling process towards greater
flexibility, through enhanced rescheduling capability, and towards autonomous operation, mainly supported by
the use of machine learning technology. To the best of our knowledge, there are no other similar conceptual
models in the literature that synergistically combine the potential of the specific set of Industry 4.0 principles and
technologies that model SMS. This research can provide guidance for practitioners and researchers’ efforts to
move toward the digital transformation of job shops.