Teppo Pirttioja’s research while affiliated with VTT Technical Research Centre of Finland and other places

This paper presents a design of a process automation system extended with multi-agent systems (MAS) and experiments with its implementation. According to this design, MAS can be used to extend the functionality of ordinary process automation systems at higher levels of control. Anticipated benefits of this include enhanced reconfigurability, responsiveness and flexibility of the resulting automation system. The design also takes into account particular characteristics of process automation. An agent platform for process automation is presented as a basis for applying MAS. A FIPA-compliant agent platform is extended with process automation specific functionality. The platform utilizes a hierarchical agent organization and a BDI-agent model. Two applications are implemented using the platform. One of these shows how the techniques of distributed planning can be applied in discrete control. The other provides a model for supervisory continuous control using the techniques of distributed search. Experiments performed with a laboratory test environment using the applications are presented. They are able to demonstrate the feasibility of the approach in test scenarios.

This paper presents a design of a process automation system extended with multi-agent systems (MAS) and experiments with its implementation. According to this design, MAS can be used to extend the functionality of ordinary process automation systems at higher levels of control. Anticipated benefits of this include enhanced reconfigurability, responsiveness and flexibility of the resulting automation system. The design also takes into account particular characteristics of process automation. An agent platform for process automation is presented as a basis for applying MAS. A FIPA-compliant agent platform is extended with process automation specific functionality. The platform utilizes a hierarchical agent organization and a BDI-agent model. Two applications are implemented using the platform. One of these shows how the techniques of distributed planning can be applied in discrete control. The other provides a model for supervisory continuous control using the techniques of distributed search. Experiments performed with a laboratory test environment using the applications are presented. They are able to demonstrate the feasibility of the approach in test scenarios.

To determine the operational situation of a monitored industrial process, an operator needs efficient access to a wide range of information. Measurement data alone does not encapsulate the overall situation, but pieces of information have to be searched from different plant IT systems that unfortunately often have varying interfaces and data formats. Information agent and semantic Web techniques address similar challenges in the context of the Internet by annotating heterogeneous data with formal semantics provided by ontology languages like OWL, and by providing human users with autonomous assistants for information retrieval. This paper presents an agent based concept for process automation that provides operators with easily configured information retrieval and monitoring services, releasing them from tedious data harvesting tasks.

An approach to extend process monitoring with the help of information agents (IA) handling semantic data is presented in this paper. According to this approach, an operator of a process automation system can configure monitoring tasks that a group of IAs performs proactively. The monitoring tasks are assumed to be composites which refer to several process observations and their logical relations. The purpose of these composite monitoring tasks is to enhance the work of the operator by letting him to supervise process phenomena at a higher level of abstraction instead of following a large amount of simple measurement data. The monitoring agents operate as a multi-agent system consisting of agents with capabilities to combine both numerical and symbolic information from several data sources. The agents can setup and execute user configured monitoring tasks cooperatively. The approach is illustrated with test scenarios using data from an industrial paper making process.

While automation systems can track thousands of measurements it is still up to human process operators to determine the operational situation of the controlled process, particularly in abnormal situations. To fully exploit the computing power of embedded processors and to release humans from simple data harvesting activities, the concept of proactive computing tries to exploit the strengths of both man and machine. Proactive features can be implemented using intelligent agent technology, enabling humans to move from simple interaction with computers into supervisory tasks. Autonomous information agents can handle massive amounts of heterogeneous data. They perform tedious tasks of information retrieving, combining and monitoring on the behalf of their users. This paper presents a multi-agent-based architecture for process automation, which aims to support process operators in their monitoring activities. The approach is tested with a scenario inspired by a real-world industrial challenge.

An approach to indirect process monitoring based on a society of constraint handling agents is presented in this paper. According to this approach an operator of a process automation system can define monitoring tasks which a group of agents perform proactively. The monitoring tasks are assumed to be composites and refer to several process measurements. The purpose of the monitoring agents is to enhance the work of the operator by letting him to supervise the indirect monitoring tasks instead of following a large amount of measurement data. The monitoring agents operate as a multi-agent system consisting of agents with constraint handling capabilities. The agents can setup and execute user configured monitoring tasks cooperatively. Constraints are used as one method for modeling the monitoring logic of the agents. The approach is illustrated with a test scenario using measurement data from an industrial process.

2006 IEEE International Conference on Industrial Informatics, INDIN'06. Singapore, 16 - 18 Aug. 2006 Nr.Article number 4053586, 1323 - 1328 An approach to indirect process monitoring based on a society of constraint handling agents is presented in this paper. According to this approach an operator of a process automation system can define monitoring tasks which a group of agents perform proactively. The monitoring tasks are assumed to be composites and refer to several process measurements. The purpose of the monitoring agents is to enhance the work of the operator by letting him to supervise the indirect monitoring tasks instead of following a large amount of measurement data. The monitoring agents operate as a multi-agent system consisting of agents with constraint handling capabilities. The agents can setup and execute user configured monitoring tasks cooperatively. Constraints are used as one method for modeling the monitoring logic of the agents. The approach is illustrated with a test scenario using measurement data from an industrial process. An approach to indirect process monitoring based on a society of constraint handling agents is presented in this paper. According to this approach an operator of a process automation system can define monitoring tasks which a group of agents perform proactively. The monitoring tasks are assumed to be composites and refer to several process measurements. The purpose of the monitoring agents is to enhance the work of the operator by letting him to supervise the indirect monitoring tasks instead of following a large amount of measurement data. The monitoring agents operate as a multi-agent system consisting of agents with constraint handling capabilities. The agents can setup and execute user configured monitoring tasks cooperatively. Constraints are used as one method for modeling the monitoring logic of the agents. The approach is illustrated with a test scenario using measurement data from an industrial process.

This paper studies issues concerning the application of user configurable cooperative information agents for monitoring tasks in process automation. Within this application area the amount of information gathered from the processes has been growing vastly and the supervising personnel has been minimized in the production plants. As this trend seems to keep going further, the end users need more effective information handling tools. However, the information overflow problem has also shown up in other application domains, and it is useful to discuss the similarities and differences with solutions used in these areas. This paper proposes an agent-based architecture to support active monitoring of the changes in process related data situated in various heterogeneous information sources. This approach is based on a BDI agent model, where individual userconfigurable information processing modules are flexibly linked. The approach is demonstrated with an industrially inspired test scenario.

2006 International IEEE Workshop on Distributed Intelligent Systems, 151-156 IEEE Workshop on Distributed Intelligent Systems: Collective Intelligence and Its Applications (DIS'06). Praha, 15 - 16 June 2006.

IEEE Conference on Emerging Technologies and Factory Automation, ETFA. Praha, Czech Republic, 20 - 22 Sept. 2006, 153 - 158 While automation systems can track thousands of measurements it is still up to human process operators to determine the operational situation of the controlled process, particularly in abnormal situations. To fully exploit the computing power of embedded processors and to release humans from simple data harvesting activities, the concept of proactive computing tries to exploit the strengths of both man and machine. Proactive features can be implemented using intelligent agent technology, enabling humans to move from simple interaction with computers into supervisory tasks. Autonomous information agents can handle massive amounts of heterogeneous data. They perform tedious tasks of information retrieving, combining and monitoring on the behalf of their users. This paper presents a multi-agent-based architecture for process automation, which aims to support process operators in their monitoring activities. The approach is tested with a scenario inspired by a real-world industrial challenge. (24 refs.)