Title：An Intelligent Asset Management System Based on Big Data and Internet of Things in the Context of Wind Farms

Lecturer: Prof. Wenjuan Zhang, University of Warwick, UK

Time: April 2, 2024, 10:00-11:30

Venue: School of Business 218

Organizer: Department of Management Science and Engineering, School of Business, East China University of Science and Technology, China

Host: Prof. Prof. Jia Li

Synopsis:

  Fixed assets such as infrastructures and equipments require long-term and regular maintenance, and the operation and maintenance (O&M) costs are very expensive to ensure their continuous and safe operation. In the case of wind farms, for example, O&M costs account for 25%-30% of the total life cycle costs of a project. Controlling O&M costs is the key to ensure the operational efficiency of wind farms. Optimizing the maintenance strategy to control costs and ensure operational safety is a crucial task in wind farm operations.

  Maintenance strategies include after-the-fact maintenance, planned maintenance and condition-based maintenance. Currently, wind farms mainly use after-the-fact maintenance and planned maintenance. After-the-fact maintenance requires longer repair time, more maintenance resources and leads to longer downtime, which results in higher power loss, and its economy is much lower than other types of maintenance strategies. Planned maintenance is the main maintenance strategy used in wind farms today, but if the planned maintenance intervals are not properly selected, over-maintenance or under-maintenance can occur, resulting in high maintenance costs or low reliability. Conditional maintenance is the process of judging the operating status of the core components of the wind turbine and predicting their remaining life span through the status information of the wind turbine monitoring process, in order to detect and predict failures in a timely manner and formulate an effective maintenance program. Conditional maintenance can minimize unnecessary maintenance and downtime while maximizing the reliability of wind turbine equipment to achieve the purpose of cost reduction and efficiency. However, its realization requires the installation of complex condition monitoring equipment and the development of effective models and algorithms, and currently there are relatively few wind farms adopting condition maintenance.

  With the Internet of Things, big data and artificial intelligence technology becoming more and more mature, intelligent operation and maintenance of wind farms has become an inevitable trend. A smart asset management system based on big data and IoT in the context of wind farms uses artificial intelligence to analyze the massive data collected by IoT and predict the remaining life of assets, formulate plans and budgets for operation and maintenance, and manage the whole life cycle of wind farm assets to optimize the operation and maintenance of wind farms and provide support for asset operation and maintenance decisions. This report hopes to discuss the necessity, feasibility, current challenges, and future development of an intelligent asset management system for wind farms.

Introduction to the Lecturer:

  Wenjuan Zhang, Ph.D. in Applied Statistics and Operations Research, is currently an Associate Professor at the University of Warwick Business School, UK. Her main research interests include business analytics, big data analytics, machine learning, artificial intelligence, reliability, maintenance optimization and engineering asset management. He has led and participated in more than 20 research and industrial projects, and published dozens of academic papers and project reports. The projects involve the UK Department for Transport, UK Power Grid, UK Healthcare, electrical companies, wind farms, banks, supermarkets, and so on.