A dynamic neural network based accident diagnosis advisory system for nuclear power plants

In this work, an accident diagnosis advisory system (ADAS) using neural networks is developed. In order to help the plant operators quickly identify the problem, perform diagnosis and initiate recovery actions ensuring the safety of the plant, many operator support systems and accident diagnosis systems have been developed. The ADAS is a kind of such accident diagnosis system, which makes the task of accident diagnosis easier, reduces errors, and eases the workload of operators by quickly suggesting likely accidents based on the highest probability of their occurrence. In order to perform better than other accident diagnosis systems, the ADAS has three main objectives. To satisfy these three objectives, two kinds of neural networks that consider time factors are used in this work. A simple accident diagnosis system is implemented in order to validate the ADAS. After training the prototype, several accident diagnoses were performed. The results show that the prototype can detect the accidents correctly with good performance.