Using Artificial Neural Network for Predicting and Evaluating Situation Awareness of Operator

The decrease of situation awareness (SA) is one of reasons leading to human factor accidents in nuclear power plants. The main purpose of this paper is to the evaluation and prediction the operators’ SA in digital main control room. Firstly, this paper used both the entropy weight method...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Shengyuan Yan, Kai Yao, Cong Chi Tran
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/99a3affd900946bda2f6f662834bf4dd
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:The decrease of situation awareness (SA) is one of reasons leading to human factor accidents in nuclear power plants. The main purpose of this paper is to the evaluation and prediction the operators&#x2019; SA in digital main control room. Firstly, this paper used both the entropy weight method and variation coefficient method to determine the relevant influencing factors. Secondly, principal component analysis (PCA) was used to concentrate the input variables into common component. Then, an artificial neural network (ANN) model was conducted based on influencing factors and SA data. The result showed that there are identified fifteen factors that have a greater impact on SA reliability, accounting for 65.2&#x0025; of the weight of all factors. The PCA result showed that the contribution rate of eight common factors reached 80.6&#x0025; for the total variance of variables and the cumulative variance. Therefore, these variables were explained by eight common components. The 8-14-1 network structure was can obtain the minimum of the MSE (0.0058) and the maximum of R<sup>2</sup> (0.9814). The predicted data can obtain the minimal MSE value (0.0035) and maximum R<sup>2</sup> (0.9886) when the &#x2018;Relu&#x2019; function was used as the activation function of both the hidden layer and output layer. The average prediction accuracy of the constructed ANN model is more than exceeded 92&#x0025; for the test data. This result indicated that the developed ANN model can accurately evaluate operator&#x2019;s SA.