Abdelkader Adla

A co-operative intelligent decision support system for boilers combustion management based on a distributed architecture

The management system of the boilers combustion is one of the most critical systems for the good functioning of GLZ-I oil plant. It has a high impact on the methods of cogitation and apprehension of various problems related to maintenance. It is a multiparticipant process with high level of interactivity. In this work we consider the paradigm of distributed decision-support systems where several decision-makers must reach a common decision. As a solution we propose an integrated framework based on a distributed architecture where each decision-maker uses a specific co-operative intelligent decision support system. The support system is viewed as a set of computer-based tools integrating expert knowledge and using collaboration technologies that help decision-makers and provide them with interactive capabilities to enhance their understanding and information base about options through use of models and data processing.

A Cooperative Intelligent Decision Support System

Traditional decision support systems give not enough possibilities of intervention to the user. In complex situations, decision is not structured and it becomes primordial to design intelligent and cooperative systems allowing a joint resolution of problem and dynamic sharing of the tasks between the user and the system according to problems to be solved and an appropriate cooperation mode. We propose, in this paper, a cooperative architecture for intelligent decision support system. The framework embeds expert knowledge within the DSS to provide intelligent decision support, and implements the intelligent DSS using collaboration technologies by putting the decision maker effectively in the loop of such DSS. To this end, besides the conceptual model of the domain, we used a structure based on task-method paradigm for task conceptual modelling. Applicability and relevance of this system are illustrated through a case study where the system and the user cooperate in decision problem solving which consists of identifying boiler defects, diagnosing and suggesting actions of cure

Agent-Based Group Decision Making

The multi-agent system paradigm represents one of the most promising approaches to address decision making problems. We have integrated agents into GDSS for the purpose of automating more tasks for the decision maker, enabling more indirect management, and requiring less direct manipulation of the DSS. Specifically, agents were used to collect information and generate alternatives that would allow the user to focus on solutions that were found to be significant. The decision making process, applied to the boilers defects in an oil plant, relies in MADS on a cycle that includes recognition of the causes of a defect (diagnosis), plan actions to solve the incidences and, execution of the selected actions.

A Hybrid Approach for Designing an Adaptive User Interface: IDSS and BDI Agents

Adaptive user interfaces (AUI) are designed to support users in performing their tasks by adapting to their individual characteristics. AUIs can facilitate user performance, make the interaction more efficient, improve ease of use and assist the user in overcoming information overflow and help them use complex systems. Utilizing these advancements, we present an approach for the design of complex adaptive interface. This latter uses Intelligent Agents based on a Belief, Desire, and Intention (BDI) architecture to achieve problem resolution in a typical boiler combustion management system (GLZ). The proposed architecture separates generic knowledge base about adaptive user interface from application specific knowledge in order to provide an IDSS. Integrating BDI agents into an IDSS can improve the ability of human operators and decision makers to perform their duties in a better way and provide useful enhancements to existing systems. The study reports the basic design principles of the user interface as well as details of the application.

Intelligent Ontology CBR System for Fault Diagnosis and Repair

Previous research in decision making has proposed the use of a case based reasoning approach to accumulate, organize, preserve, link and share diverse knowledge coming from past experiences. However, existing CBR systems lack semantic understanding, which is important for intelligent knowledge retrieval in decision support system. To develop an intelligent CBR system which can not only carry out data matching retrieval, but also perform semantic associated data access, and improve the traditional keyword-based search. .An effective case representation method as well as an appropriate case retrieval approach must be found. Ontology technology is an ideal selection for realizing our system because owing to the good semantic understanding offered by ontology. Thus, we adopt ontology approach as a means to acquire domain knowledge and construct a case-base and use ontological semantic retrieval as the case retrieval method. The resulting ontology based CBR tool is experimented in fault diagnosis and repairing domain, a semi-structured decision-making environment involving multiple attributes. The results showed the feasibility and the applicability of our approach, and the benefit of the ontology support.

COORDINATION IN MULTI-AGENT DECISION SUPPORT SYSTEM - Application to a Boiler Combustion Management System (GLZ)

In Multi-agents systems, the cognitive capability present in an agent can be deployed to realize effective problem-solving by the combined effort of the system and the user. It offers the potential to automate a far wider part of the problem solving task than was possible with classical DSS. In this paper, we propose to integrate agents in a group decision support system. The resulting system, MADS is designed to support operators during contingencies. We experiment our system on a case of boiler breakdown to detect a functioning defect of the boiler (GLZ: Gas Liquefying Zone) to diagnose the defect and to suggest one or several appropriate cure actions. In MADS the communication support enhances communication and coordination capabilities of participants. A simple scenario is given, to illustrate the feasibility of the

Proposal for an Adaptive User Interface Design: A Hybrid Approach: IDSS and BDI Agents, Application to the Boiler Combustion Management System (GLZ)

The interaction with humans is one of the critical components of modern Distributed Artificial Intelligence (DAI). Adaptive interfaces are a promising attempt to overcome contemporary problems due to the increasing complexity of human-computer interaction. They are designed to tailor a systems interactive behavior with consideration of both individual needs of human users and altering conditions within an application environment. Utilizing these advancements, we present an approach for the design of complex adaptive interface. This latter uses Intelligent Agents based on a Belief, Desire, and Intention (BDI) architecture to achieve problem resolution in a typical boiler combustion management system (GLZ). In our approach, MAS is used in order to coordinate an adaptive interface with a distributed decision and distributed information architecture. Agents can assist the users by executing actions such as anticipating the needed information, using the internet to collect data, and assisting the operator in analysis and treatment.