The Digital Innovation and Wind Energy Data Forum aims to bring together industry leaders and experts to exchange and share their experiences in all aspects of Digital Innovation, Big Data and Artificial Intelligence. It also provides a unique interdisciplinary platform for researchers, scientists and opinion leaders to present and discuss the latest innovations, trends, technology and applications, as well as the practical challenges encountered and solutions adopted in the fields of Big Data, Machine Learning and Artificial Intelligence.
The Forum will critically examine the digitisation of the wind energy sector and data-driven operations, performance forecasting and new business models, optimising wind energy assets with artificial intelligence (AI) and automation, data-driven monitoring and inspection, predictive maintenance and using advanced analytics to reduce costs and drive performance.
Attendees will gather to discuss the importance of data-driven predictive maintenance and develop an optimised strategy for the performance of their wind farm. Advanced data analytics and integrated IoT-based Big Data platforms develop analytical opportunities for planning and forecasting, revealing the bright future of the wind industry.
Elliot RoT® Wind
Elliot Cloud and Reliability of Things have developed a series of standard solutions for any equipment in the industry, which allow the early detection of faults in industrial equipment through the use of Artificial Intelligence (AI) techniques under the name of Reliability of Things® (RoT). Under this concept, a SAAS solution called RoTWind has been developed to assess the state of health of wind turbines in a wind farm and provides a series of tools to evaluate maintenance interventions and analyse the root cause.
Elliot RoT® Edge
For the RoT Egde solution, a device (patent pending) has been developed that connects directly to the PLC of the control system of the equipment whose status is to be analysed and allows its health status to be analysed.
This Elliot RoT Egde device has been presented at the congress as it is unique in the market. The device can communicate with most industrial control systems (e.g. Siemens PLC) by simply connecting a cable. Through this direct connection and by making a simple modification to the code of the control system (PLC), the device collects the operating data of the equipment to which it is connected and makes a "Digital Clone" of the machine, i.e. it makes a model of it. Using Artificial Intelligence (AI) techniques, the normal behaviour of the machine is used to assess the health of the different components.
Reducing the risk of breakdowns and their impact
The vast majority of industrial machinery has rotating equipment such as motors, generators or gearboxes, as well as electrical equipment such as converters and transformers. All of these components are often critical in their respective processes, so reliability and availability are in high demand.
Premature failure can lead to significant economic losses, both in terms of material damage and production losses, and can even result in personal injury through accidents. In order to plan maintenance effectively, it is essential to have accurate information as far in advance as possible about the state of health of process components in order to know when repair or replacement will be necessary.
Elliot RoT® enables continuous monitoring and assessment of equipment health status under normal operating conditions for the vast majority of industrial equipment. Either with the equipment's own sensors or with additional IoT sensors, RoT provides simple but valuable information on the health status of the equipment and can be used to monitor the health of the equipment:
- Early detection of degradation and failures up to months in advance, depending on the failure mode.
- Evaluate maintenance actions, which helps staff to know if the equipment has been repaired correctly.
- Monitor the operating history and the evolution of the health of the equipment, which helps to find the root cause of failures, very useful to have a better knowledge of the equipment and to clarify responsibilities about the origin of the failure.