 Hi, I'm Tom Bocchina with ST Mems and Sensors Product Marketing. Today, I'm going to show you a smart pipe demo created by our applications team. In this demo, we've constructed a model of an air handling pipe with a fan on one side, a filter in the middle, and pressure sensors on either side of the filter. The pressure sensors are connected to the cloud via Wi-Fi. And we're using ST's predictive maintenance AWS cloud dashboard to display the data. Using a simple algorithm offline, we can measure the back pressure in the system to determine the filter goodness. A filter becomes dirty over time and needs to be replaced periodically. Depending on the conditions, the filter may need to be changed more often in a dusty environment and less often in a clean environment. Wouldn't it be nice to receive an alarm when the filter is starting to become clogged? In our smart pipe demo, sensors report the condition of the filter in real time to a predictive maintenance dashboard, allowing us to detect the filter effectiveness and predict when to replace the filter based on thresholds that we control. Let me walk you through the live demo. I've downloaded and installed the predictive maintenance Wi-Fi 2.2.0 bin to my ST WIN kits. And I've provisioned my kits following the instructions in the user guide found on the ST WIN function pack, predictive maintenance website. I've installed the kits into the pipe mock-up on either side of the filter. I have a variable speed power supply set to approximately 12 volts, a fan, and a mock-up of an airflow pipe. In the center of the pipe, we have a slot, which we use to resemble a filter, sort of like an HVAC system. I've taken the ST WIN kits and mounted them inside the pipe. On the right is a video of the ST WIN working inside the tube with the fan running. As I mentioned, the ST WIN kits are broadcasting to the cloud and we can see their data in ST's predictive maintenance website. As I said, I've provisioned two kits and we can monitor them in the dashboard. This dashboard is free, by the way, on ST's website and you can use it to create your own configurations for asset monitoring. Here we can see the predictive maintenance dashboard, which is reporting the pressure in real-time on the right. When I install a semi-block filter, the status moves from green closer to the yellow. Now let's see what happens when we simulate a clogged and dirty filter using a piece of paper to block the flow. Here we can see that the airflow is reduced and the filter status in the predictive maintenance dashboard moves to the yellow or warning state. If we block the filter even further, the dashboard would move into the red state to indicate an alarm. The core electronics in this demo is an off-the-shelf evaluation kit called ST WIN, pictured here. I've also installed the ST WIN Wi-Fi expansion cord board for my cloud connection. These are fully available from all major distributors today. ST WIN has a large variety of sensors, including mem sensors dedicated to vibration, acceleration, temperature, sound, and it also has a built-in BLE connectivity and expansion capability for Wi-Fi and other add-in boards. In this demo, we're using only the pressure sensor, the LPS-22HH. This pressure sensor has a very low power consumption. It's a tiny size and high accuracy, which fits perfectly for the smart pipe application. The LPS-22HH is in production now and fully available from the distributor of your choice. In summary, the ST WIN fits very well into the Industry 4.0 Maintenance Strategy continuum. It's a great feasibility tool for level three condition monitoring and level four predictive maintenance. ST WIN is available now, and there are also many free firmware examples on the ST WIN website. Thanks for your valuable time. I'm Tom Bocchino. And please take a look at our many other demos at ST's Virtual Developers Conference.