A knowledge based system has been developed to support designers in control rod programming of BWRs. The programming searches through optimal control rod patterns to realize safe and effective burning of nuclear fuel. Knowledge of experienced designers plays the main role in minimizing the number of calculations by the core performance evaluation code. This code predicts power distribution and thermal margins of the nuclear fuel.This knowledge is transformed into 'if-then' type rules and subroutines, and is stored in a knowledge base of the knowledge based system. The system consists of working area, an inference engine and the knowledge base. The inference engine can detect those data which have to be regenerated, call those subroutine which control the user's interface and numerical computations, and store competitive sets of data in different parts of the working area.Using this system, control rod programming of a BWR plant was traced with about 500 rules and 150 subroutines. Both the generation of control rod patterns for the first calculation of the code and the modification of a control rod pattern to reflect the calculation were completed more effectively than in a conventional method.

No abstract

An event identification method using a neural network has been evaluated in an on-line environment during the plant startup test at Unit No.4 Plant in the Kashiwazaki Kariwa Nuclear Power Station. In the method, the neural network identifies the event from the change pattern of analog data, such as reactor pressure signals, and then the result is confirmed or similar events are discriminated using digital data, such as valve open signals. Before the test the neural network is trained for the events causing a reactor scram by using analysis results.For the test the method is incorporated into a prototype of the alarm handling system which is connected to the plant facilities. Five kinds of analog data are acquired and eight sampled data from each, namely a total of 40 data, are input to the neural network after normalization. The results show that the load rejection, the turbine trip and the main steam isolation valve closure events are correctly identified from 9 kinds of subject events, regardless of the difference between the trained analysis results and the recognized plant data. This is owing to the data sampling and normalization methods as well as the robustness of the neural network.

No abstract

No abstract