Arnaldo Pereira

Specification of the PERFoRM architecture for the seamless production system reconfiguration

The world is assisting to the fourth industrial revolution, with several domains of science and technology being strongly developed and, specially, being integrated with each other, allowing to build evolvable complex systems. Data digitization, big-data analysis, distributed control, Industrial Internet of Things, Cyber-Physical Systems and self-organization, amongst others, are playing an important role in this journey. This paper considers the best practices from previous successful European projects addressing distributed control systems to develop an innovative architecture that can be industrially deployed. For this purpose, a particular design process has to be addressed in order to consider the requirements and functionalities from various use cases. To investigate the known practices, four use cases are enlighted in this paper, which cover a wide spectrum of the European industrial force, as well as industrial standards to support a smooth migration from traditional systems to the emergent distributed systems.

Adaptive Multi-Agent System for a Washing Machine Production Line

This paper describes the implementation of a multi-agent system in a real industrial washing machine production line aiming to integrate process and quality control, allowing the establishment of feedback control loops to support adaptation facing condition changes. For this purpose, the agent-based solution was implemented using the JADE framework, being the shared knowledge structured using a proper ontology, edited and validated in Protege and posteriorly integrated in the multi-agent system. The solution was intensively tested using historical real production data and it is now being installed in the real production line. The preliminary results confirm the initial expectations in terms of improvement of process performance and product quality.

Deployment of multi-agent systems for industrial applications

Multi-agent system (MAS) is being pointed out as a suitable technology to develop systems that demand flexibility, robustness and re-configurability. Consequently, a significant effort has been noticed to apply MAS to industrial domains exhibiting these characteristics, like manufacturing and smart grids. In spite of the adequacy of the MAS principles to solve the industrial requirements, the truly deployment of MAS for industrial applications is far to be solved. This paper discusses the current challenges for the deployment of MAS in the context of industrial applications, mainly focusing the integration of agents with physical equipment and the ability to run agents directly in industrial or low cost controllers. An experimental MAS solution for a smart grid case study was deployed aiming to support the discussion.

Integration of an agent-based strategic planner in an enterprise service bus ecosystem

The continuous change in the manufacturing world is demanding more flexible, responsive and accurate planning tools, which are able to assist the decision-makers to take tactical and strategic decisions on short notice with a high level of confidence. For this purpose, these tools should dynamically explore different operative scenarios in the planning procedure and produce information about key performance indicators. This paper describes the development of an agent-based strategic planner, combining the flexibility of multi-agent systems principles with the optimization capability of a Mixed Integral Programming technique. The tool is integrated in an ecosystem of heterogeneous decision-making systems through an Enterprise Service Bus that also provides access to legacy data.

Trust and risk management towards resilient large-scale Cyber-Physical Systems

Empowering distributed entities with decisional and adaptation capabilities is the current trend in control systems operating in highly changing environments. Cyber-Physical Systems (CPS) is a paradigm addressing this challenge as it allows the integration of both physical and decisional parts. By acting in highly changing environments, these complex control systems must be resilient. This paper proposes a trust and risk management mechanism to be deployed in CPS for resilience improvement. This mechanism, inspired by social and biological behaviour, is deployed in a smart-grid demonstrator. The preliminary results show that embedding this mechanism into distributed entities can lead to an increase of the system stability and efficiency dealing with system uncertainty and perturbations, and consequently improving the system resilience.

Data collection for global monitoring and trend analysis in the GRACE multi-agent system

Multi-agent systems (MAS) paradigm is a suitable approach to implement distributed manufacturing systems addressing the emergent requirements of flexibility, robustness and responsiveness. In such systems, the distributed agents have a local view of the system environment being the global data collection a complex and critical issue to provide the functionalities of the ISA-95 standard, such as dynamic scheduling, maintenance management and quality assurance. This paper describes the data collection mechanisms in a multi-agent system that supports the global monitoring over the time and the trend analysis to perform self-adaptation and self-optimization. The proposed approach was developed and tested in an industrial washing machines production line.

Dynamic monitoring of key-performance indicators in industrial environments

Manufacturing companies generate huge amounts of relevant data that, potentially, can help the decision makers to monitor and supervise the health status of the shop-floor. Many problems are present that prevent this monitoring, namely the identification of which data should be collected, how to execute this collection or how this data should be analysed and displayed to the user. This paper deals with the last issue, where a dynamic and responsive User Interface is developed enabling the decision maker, having an in-the-mesh intervention, to constantly monitor relevant Key-Performance Indicators (KPI). The paper describes the development of such tool, considering a web-based approach under a platform agnostic perspective. The user interface presents an dynamic view over the aggregated KPI, where data is annotated with relevant warning information.

Engineering an ADACOR based solution into a small-scale production system

On the verge of Cyber-Physical Systems (CPS), companies will need, sooner or later, to adapt their systems in order to follow the emergent visions of Industrie 4.0 and Industrial Internet demanding the digitalization of their processes, preventing the losing of their competiveness levels. The engineering of such innovative manufacturing control systems assumes a crucial challenge without which becomes hard to convince researchers and, primarily, practitioners of the proposed architecture potentials. This paper describes the engineering aspects of deploying an ADACOR (ADAptive holonic COntrol aRchitecture for distributed manufacturing systems) based CPS for a real small-scale production system. Since the solution is using agent technology, a special attention is devoted to the interface from the agent control layer to the physical resources using the industrially adopted OPC-UA (OPC Unified Architecture). At the end, some lessons learned in engineering this CPS are drawn.