top of page

Wind

seta_branca_edited.png

AQTech's wind farm solution remotely monitors vibration, temperature and process variables to diagnose failures before they occur, following the guidelines of ISO 16079-1, 16079-2 and ISO 10816-21.

 

The system reports potential problems through notifications, tracks the power generation history (correlated with data from the anemometer) and evaluates the power quality using a laptop or smartphone.

 

The advanced Machine Learning features used include clustering and correlation using the k-means algorithm and the k-Nearest Neighbors (KNN) algorithm for classification and regression functions.

aero_eolica_1-min.png

Absolute vibration of the bearings

Absolute vibration of gearbox

Axial vibration of the main shaft

Axial vibration of high speed shaft

Phase reference

Rotation speed

Active and reactive power

Wind speed and direction

Nacelle position

Temperatures (bearings, oil, generator ...)

VibraOne Wind

VibraOne Wind is a data acquisition equipment developed to meet the needs of the generation utilities.

The system consists of processing functions, analog inputs, digital inputs, digital outputs, communication interfaces, among others.

The VibraOne Wind continuously monitors and records the operating conditions of the generating units, detecting faults and disturbances and allowing constant validation of the operation and performance of the field systems.

vibraone_wind_render2_edit-min.png
vibraone_wind_render1_edit-min.png
Home - Status by parque.jpg
Park - Bons Ventos.png
Wind turbine - BVS15 – 5.jpg
Fault diagnosis.jpg

OneBreeze

The AQTech predictive maintenance interface for wind turbines is equipped with intuitive and powerful numeric indicators, which automatically provide which machines deserve greater attention from operators.

 

With tools that use artificial intelligence and specific knowledge of vibration analysis as a means of calculation, the AQTech software provides valuable information on the expected date for failure of specific components of the wind turbine.

 

And, due to the nature of the algorithms, the longer the system is installed on the machine, the more accurate these indicators become, allowing to predict not only what will be the defective component in the drivetrain, but when it will present an alert level for its maintenance.

 

All of these features provide the user with an effective means of optimizing the productivity and reliability of their fleet of wind turbines, allowing a great reduction in their maintenance costs.

bottom of page