Nuclear power plants transient diagnostics using LVQ or some networks don't know that they don't know

摘要: A nuclear power plant's (NPP) status is monitored by a human operator. Any classifier system used to enhance the operator's capability diagnose NPP should classify novel transient as "don't know" if it not contained within its accumulated knowledge. In particular, neural network needs some kind of proximity measure between new data and training set. Multilayered perceptron (MLP) networks do have that measure, while Kohonen self-organizing maps (SOM) learning vector quantization (LVQ) do. This may also serve an explanation network's decision way case-based reasoning expert systems Applying "evidence accumulation" technique using transient's classification history can accuracy well consistency. >