Diagnosis tasks intelligent training based on a model tracing approach
Luíz Faria, Zita Vale, Carlos A. Ramos, Albino Marques · International journal of engineering intelligent systems for electrical engineering and communications · 2005
The new requirements of power systems operation demand experienced and well trained operators. However, the training is not often considered a priority task, due mostly to its high costs and medium/long term results.Usually, the training programs available in industrial environment do not consider the particular training needs of each trainee. The application of the Intelligent Tutoring technology has proved to be a feasible possibility to be used in the existing training approaches in the power systems area. This paper presents a Web-based Intelligent Tutoring System (ITS) to train Control Centre operators of the Portuguese electrical transmission network. One of the major advantages of the training based on the ITS technology is the ability to provide individualized training. The proposed system belongs to the model-tracing tutors' category, which tracks trainee's progress and keeps them within a specified tolerance of an acceptable solution. The individualized training requires a trainee's model. This is used to model the trainee's understanding of domain concepts. In this way, the paper describes a curriculum planning module used to choose the most appropriate problem to the trainee's knowledge status. This module includes a neural network to perform a classification of each type of incident according to the trainee's current knowledge.