 Wind energy represents one quarter of renewable energy produced worldwide. Hundreds of thousands of wind turbines are installed onshore and offshore, often in locations that are difficult to access. How do you make sure that they will work reliably and provide energy to the grid continuously? In the next two minutes I will describe wind turbine monitoring and I will also show you how it is done, keeping focus on estimation MEMS sensors. Monitoring of wind turbines is essential. One goal is to optimize operation of the wind turbine and generate as much energy as possible. Another important aspect is predictive maintenance. To detect failure as early as possible, to reduce or even avoid downturns. All parts of the turbine, the tower, the drivetrain and the rotor are monitored using many different types of sensors. Motion sensors and especially accelerometers play a very important role because they can monitor vibrations, measure tilt or detect shocks while more and more new wind power plants are being built. Additional monitoring of existing installations is also taking place by retrofitting more and more sensor systems. Such systems are usually battery powered and therefore require intelligent systems to minimize current consumption. This is where ST6-axis IMU with machine learning core, the ISM330DHCX provides excellent performance, intelligence embedded inside the sensor and ultra low power consumption for predictive maintenance. ST is producing dedicated 3-axis vibrameter with ultra-wide bandwidth, the IIS3DWB. Let's have a look now how ISM330DHCX and IIS3DW sensors work in our demonstration of wind turbine monitoring. We have here a downsized wind turbine, roughly 2.5 meters high. On each blade of the rotor there is ST evaluation kit, STwindotbox. The STwindotbox kit has been introduced very recently and it is already a second generation of industrial wireless sensor-noted kits. It is equipped with 9 sensors, wireless connectivity like Wi-Fi, BLE and NFC, a slot for microSD card, a USB connector and rechargeable battery. Using ST's BLE sensor app, we connect from tablet to one of the STwindotbox boards on the blades. We are monitoring operation of the turbine by gathering following information in real time. Raw sensor data coming from ISM330DHCX 6-axis IMU, combining accelerometer and gyroscope and magnetic field data from IIS2MDC stand-alone magnetometer. On another screen, we can see the actual position or tilt of the blade represented by the green circle. This screen is showing the speed of rotation of the rotor in RPM, which is the number of rotations per minute, calculated by machine learning core embedded inside the ISM330DHCX. The last screen is showing the blade orientation, number of rotations and direction of rotation detected by a finite state machine, the internal motion detection engine of the ISM330DHCX. As you can see, our sensor measure all this data very precisely. In addition, it performs this job at a minimal power consumption of just 15 microamps. As mentioned already, the second aim of monitoring wind turbines is to perform predictive maintenance. With our Vibrameter IIS3DWB, that is also embedded in the STwindotbox kit, we can measure the vibrations of the blades from 0 Hz up to 6 kHz. We analyze the data in frequency domain by running FFT and also in time domain. This is exactly the data that is needed for predictive maintenance of wind turbines. So, if you would like to evaluate how to monitor wind turbines with ST-motion sensors with minimal effort using small form factor wireless board and wired or wireless connection, you can easily order the STwindotbox kit from our website or through common distributors. For more information, please visit our website or contact our local sales representatives. Thank you for staying with me and see you soon.