Computer Network Fault Intelligent Diagnosis Base On Neural Network

Computer network is an most important facility in 21 century. With the development of its shapes, the management work of computer network become more and more complex. Computer network fault diagnosis became the focus of people attention. A good computer network connects to good network management. Any fault of network, even though the fault which happens in a short time, may bring to the huge loss in economy, society and construction of national defences.In the draught of fact demands, the application of fault diagnosis become more and more abroad, has filted into the Mechanics and Electronics system, Industry Automatization system, computer system, and all kinds of dynamic system in abroad way, including abjection identify system, combination navigation system and so on from traditional machine system and electron system. As the development of Physics, Mathematics and basic science, and the development of Control Theory, Information Science and application science, it provided many kinds of technology ways for faults diagnosis, became the impetus of the development of faults diagnosis technology.As the factor of faults is too much, information is too much, it makes the manager of network difficult to use the tools which exist today to resolve the user's service demands of faults diagnosis. How to use the intelligence technology import to network fault diagnosis area, using self-study, auto-adapted technology to create and maintenance the fault diagnosis repository, increase the efficiency of network management is a problem which is worth to lucubrate.As the development of artificial intelligence, it can bring the neural network technology into the network fault diagnosis area, it can greatly exert the advantage of neural network which used in fault diagnosis. This paper use the Self-Organizing Feature Map neural network and BP neural network to diagnosis the network fault, use the cluster in training sample, add the result to the sample and put some weights, it can increase the qualities. Parallel computing is used in the neural network compute. The computer network fault diagnosis is used as a example to analysis. the work has been emulated and analyzed by computers, and a computer network fault diagnosis system has been excogitated. The whole works have been summed up and the future researching directions have been discussed at the end of this paper.