Distributed Artificial Intelligence Technology Applications And Research, Comprehensive Logging System

Incepting in the mid to late 1970s, Distributed Artificial Intelligence (DAI) is an important branch of Artificial Intelligence (AI) research. The area of its research deals with cooperative problem solving using a federation of collaborating entities. The studies of DAI are divided into distributed problem solving (DPS) and multi-agent system (MAS). Recently, the studies of Agent and MAS have opened a new way for the capability of comprehensiveness, analysis, implementation and application of distributed systems. The DAI technology has been used in many areas like decision support, web search and information retrieval, information systems modeling, etc.These agents are intelligent in the sense that they are adaptive, independent, and posses reasoning capability. They can plan and execute tasks in cooperation with other agents in order to satisfy their goals. They also learn in the process and adapt to changes in the environment dynamically. These agents are often heterogeneous. A MAS is defined as a loosely coupled network of agents that work together to solve problems that are beyond the individual capabilities or knowledge of each agent. The increasing interest in MAS research is due to significant advantages inherent in such systems, including their ability to solve problems that may be too large for a centralized single agent, provide enhanced speed and reliability, and tolerate uncertain data and knowledge. Some of the key research issues in a MAS are in the areas of coordination, negotiation, and communication.The comprehensive logging or mud logging is an oil exploration technology while drilling. For the purpose of detecting the presence of oil and gas areas, it deals with both the information from the geological drilling engineering and that received while drilling, aided by analytical instruments, and using such technologies as electronics, computer, network communication and information analysis. Its main task is to obtain a variety of real-time data, and to provide a reliable first-hand information for the exploration and development of the oil and gas fields. It has many features such as plenty of collection data, high precision, continuous data, real-time information, fast estimate and less interference by the human factors, etc. A comprehensive logging system is made up of hardware (comprehensive logging instrumentation) and software (on-line and off-line system).The status quo for the domestic technical level of the comprehensive logging is that there is still a wide gap in general compared with the foreign developments. To enhance the decision-making at the scene, site information integrity, intelligence and miniaturization of the comprehensive logging system, and to make the system more open, we constructed a model of comprehensive logging system based on MAS technology at three levels, namely the hierarchical model, the structural model and the business model. We gave the definition of the function for the agents in these models, and conducted some studies on communication, negotiation and coordination among agents, and on knowledge representation, updating and sharing for the agent. In an application project, we implemented a new comprehensive logging software system based on the system model that we made, and it achieved favorable results in practice.