Application of factor neural network in multiexpert system for oil-gas reservoir protection

Knowledge representation and reasoning model play an important role in multi-expert system. In this paper, a new knowledge representation method, factor neural network theory(FNN), is used in multi-expert system for oil-gas reservoir protection. Firstly, by introducing factor and factor space theory, knowledge representation model based on factor state space is presented. Secondly, analog factor neural network structure is analyzed to solve reasoning problem of expert system. For illustration, fuzzy reasoning theory is utilized in factor neural network to verify the effectiveness of our proposed method. The application of the expert system shows that factor neural network theory is valid in knowledge representation and reasoning model and blackboard mechanism based on point-to point can solve the communication problem among sub-expert systems better. As a result, our proposed method based on FNN can effectively improve the accuracy of inference results.