Jungle AI - Wind

Generate more revenue with your
existing turbines

Predict failures to avoid downtime

It only takes one malfunctioning component to cause a turbine to stop. Service providers and OEMs have full calendars and therefore need to know in advance when to plan repairs and which spare parts to procure.

Canopy finds abnormal conditions in your turbines, helping you prevent downtime events before they occur.

Identify and resolve underperformance

Minor performance issues often go unnoticed, but the cost of lost production can easily reach hundreds of thousands of euros per month for large wind farms.

Canopy flags underperformance in real-time, and quantifies losses, telling you exactly what to do to get those turbines back on track.

Trusted alarms for focused teams

Wind asset managers and performance teams often still rely on SCADA alarms that miss out on operational conditions, leading to alarm fatigue and inefficiencies in problem-solving.

Canopy’s machine learning models provide fewer and contextual alarms so your team can focus on the issues that drive revenue.

Monitor everything, all the time

Keeping track of all the possible inefficiencies and components that can affect production and profitability is a task that should not be underestimated.

Canopy is designed to monitor all components on a 24/7 basis. When there’s anything happening to your farms, you’ll be the first to know about it.

Typical issues that Canopy is designed to tackle

We know, these snapshots don’t do justice to Canopy: open them in a new tab for sharp visualisation, or get the complete experience by booking a demo with our team.
‍

Curtailment

Bearing issues

Cooling system failures

Hydraulic system issues

Icing detection

Component overheating

Pitch system faults

Hardware/software upgrade

Detect self and grid curtailment with Canopy. Use impact quantification to calculate losses or visualise performance curves to get to the bottom of the issue.

Degraded bearings experience higher than normal temperature operational ranges. Canopy makes it easy to see this overheating.

Canopy monitors the temperature of the internal components, to easily identify issues with ventilation or cooling systems.

Identify abnormal pressures or temperatures which are often symptoms of hydraulics malfunctioning.

Detect underperformance caused by icing, and and quantify energy losses to calculate the ROI of de-icing equipment.

Oil, gearbox, generator and transformer phases can suffer overheating and cause degradation, underperformance or downtime.

Comparing the individual blade pitches and investigating hydraulic components can reveal a malfunctioning pitch system.

Compare the behaviour of the asset before and after the upgrade allow to precisely evaluate its return on investment.

October 17, 2023

Case: Canopy detection prevents gearbox failure

The gearbox is a complex component that is hard to monitor using conventional methods.
Learn how Canopy enabled a wind customer to identify a failing component in time and promptly replace it, preventing production loss.

Read case study

Just a few steps away from top-
notch wind farm performance

Data ingress

We start by connecting to your wind farm directly, or to where your data is centralised, and ingress data into our systems continuously. Our automated services then prepare your data to make it easily accessible for our machine learning models.

Model training

Next up, our team of electrical engineering and machine learning experts use your historical data to train and validate AI models that are fine-tuned to your application, learning your wind farm’s unique behaviour all the way down to the individual sensor level.

Live monitoring

Log in to Canopy to monitor your wind farms in real time, and get advanced analytics and data visualisation tools beyond your imagination. Leverage the domain expertise of our Service Delivery team during the regular support meetings to benefit from our experience with similar projects.

Learn more

April 11, 2024

Unlocking prescriptive maintenance with AI-based Detections

Prescriptive maintenance solutions are essencial for optimising renewable energy assets, but building such robust features comes with its challenges.

Read blog post

March 25, 2022

Solving predictive maintenance challenges with Time-Machine AI models

Today we will go on a journey to discover some of the key advantages our Time-Machine AI models bring to predictive maintenance pipelines.

Read blog post

March 8, 2022

Unlocking scalable predictive analytics with next-gen AI models

The need for AI-based predictive solutions for electromechanical assets is on the rise. However, building large scale AI-dependent online systems is by no means an easy feat.

Read blog post