Loading...

Identification and Forecasting of Nuclear Power Plants Transients by Semi-Supervised Method with Change of Representation Technique

Mirzaei Dam-Abi, Ali | 2019

383 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52960 (46)
  4. University: Sharif University of Technology
  5. Department: Energy Engineering
  6. Advisor(s): Ghofrani, Mohamad Bagher; Moshkbar Bakhshayesh, Khalil
  7. Abstract:
  8. In this work, we aim to find a way to identify and forecast transients in nuclear power plants with the aid of semi-supervised machine learning algorithm. Forecasting and identifying transients in nuclear power plants at the early stages of formation are essential for safety considerations and precautionary measures. The use of machine learning algorithms provides an intelligent control mechanism that, along with the main operator of the power plant, raises the transient detection and identification rate. Our algorithm of choice is to change the way data is presented, which is a semi-supervised learning approach. The algorithm consists of two methods: quantum dynamics clustering (unsupervised learning) and neural network (supervised learning). Quantum dynamics clustering that based on physical intuition and rooted in quantum mechanics, clusters are formed using the potential function of the Schrodinger equation in the neighborhood of the data with the least potential (center of the cluster). Then the distribution of labeled data in the clusters is checked and, if adequately clustered (data with similar labels in the same cluster), the data will be labeled and will use for the train of neural network. In other words, the processes of cross-correlation and proximity measure between learning data are critical learning criteria. This algorithm makes the proper balance between memorization and generalization.With a small amount of labeled data, the learning operation will be satisfied. The task of proximity measurements done with quantum clustering and task of data correlation doneby neural network
  9. Keywords:
  10. Nuclear Power Plants ; Machine Learning ; Neural Network ; Nuclear Safety ; Semi-Supervised Learning ; Quantum Clustering

 Digital Object List

 Bookmark

No TOC