Mahi Ayman, Mariam Elaskary, Nour Elgarhy, Zeina Tamer
Supervised by: Eng. Yomna Hassan, Eng. Maha Sayed
March 7, 2022t
Institutions have been rapidly redirecting their investments away from fossil fuels, creating a favorable scenario for the generation of clean energy. The wind industry, especially, has seen an exponential increase in recent years. Early fault detection creates an alternative for operation and maintenance (O&M), helping forgo costs before they reach a catastrophic stage since preventive methods are used to stop malfunctions before their occurrence, improving turbine reliability and allowing for maximum utilization and better control of the wind farms. In this document, deep learning methods such as Autoencoders-LSTM (Long short-term memory) are used on time series data produced from SCADA to reach the optimal results.
This document intends to familiarize the software and renewable energy engineers with the system, including the system architecture, design viewpoints, data design and user interface. The proposed system will be utilized through a web application that allow renewable energy engineers located on wind farms to detect failures in the components of each wind turbine and receive logs on the behavior of said wind turbines.
The system described in this document is a deep learning-based prediction model that uses time series SCADA collected datasets from wind turbines to detect anomalies that foretell failures that would occur in one of the components of the wind turbine. Engineers will utilize this system to prevent these faults from occurring thus reducing the high costs usually spent on corrective maintenance. This document describes the system’s architecture and functionalities thoroughly to facilitate the process.
The Software design document will describe in details the architecture of the Fault Detection In Wind Turbines System. The first section is the introduction which will discuss the document’s purpose, scope, and overview. In the second section we will talk about the systems overview, scope, goals and timeline. In the third section the system’s design viewpoints are discussed. It includes the following (context, composition, logical, patterns use, algorithm, interaction, and interface viewpoint). The fourth section will discuss the data design and the datasets used for this system including data and dataset description and database design description. The fifth section will display the wireframes and details of the user interface of the web application designed to facilitate the access to the system. The sixth section will include the requirements matrix of this project.
1.4 Intended audience
- Renewable Energy Engineers
Engineers located on wind farms and Condition Monitoring specialists will be able to reference this document to get a better understanding of the system and its architecture and how to utilize it. Through this document they’ll identify the data this system works with and the expected outcome.
- Software Engineers
Any software engineer responsible for the maintenance and refactoring of this system will find this document essential for the process.