Combining Supervised and Semi-Supervised Learning in the Design of a New Identifier for NPPs Transients

This study introduces a new identifier for nuclear power plants (NPPs) transients. The proposed identifier performs its function in two steps. First, the transient is identified by the previously developed supervised classifier combining ARIMA model and EBP algorithm. In the second step, the patterns of unknown transients are fed to the identifier based on the semi-supervised learning (SSL). The transductive support vector machine (TSVM) as a semi-supervised algorithm is trained by the labeled data of transients to predict some unlabeled data. The labeled and newly predicted data is then used to train the TSVM for another portion of unlabeled data. Training and prediction is continued until the change of targets is less than a desired value. The last targets (i.e., the final predicted for unlabeled data) identify the type of unknown transient. To analyze the ability of the proposed identifier, Bushehr nuclear power plant (BNPP) transients are examined. Results show good performance of the proposed identifier. Noticeable advantages are: clustering of unknown transients by labeled and unlabeled data, transductive approach of identifier without need to cluster all data, and sole dependency of identifier on sign of output signal due to the modular networks. Recognition of transient based on similarity of its statistical properties to the reference one, more robustness against noisy data, and improvement balance between memorization and generalization are other advantages of the identifier.