VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1765
Title: | Remaining useful life assessment of bypass and blocking diodes in photovoltaic arrays using different CNN-based prediction models | Authors: | Nguyen Thuan Phat | Keywords: | Long short-term memory;Wavelet transform;Gated recurrent unit | Issue Date: | 2022 | Abstract: | This thesis examines the strength of various CNN-based deep learning models for assessing the remaining useful life (RUL) of photovoltaic (PV) arrays. Performed on a dataset containing RUL data obtained from multiple different calculation models, the project aims to find the best CNN-based models for the tasks of forecasting RUL using external factors, such as temperature, current, voltage, etc. as well as forecasting using previous RUL values. The ultimate goal of the thesis is to predict the day in which the PV system would fail. To this end, multiple CNN-based models, including ones incorporating gated recurrent unit (GRU), long short-term memory (LSTM), and wavelet transform (WT), were compared based on various metrics. The thesis also provides an overview on various related topics, such as the machine learning techniques mentioned, the wavelet transform, and PV systems diodes. While not all failure dates from were predicted, a majority of them were successfully forecasted |
URI(1): | https://epub.vgu.edu.vn/handle/dlibvgu/1765 | Rights: | Attribution-ShareAlike 3.0 United States |
Appears in Collections: | Computer Science (CS) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
Remaining useful life assessment of bypass and blocking diodes in photovoltaic arrays using different CNN-based prediction models.pdf | 4.44 MB | Adobe PDF |
This item is licensed under a Creative Commons License