Digital Twins enabling IIoT Machines
While the pace of technology development in the heavy machinery industry accelerates, manufacturers continue to face demands for increased productivity and design complexity to meet global requirements and the emergence of smart, connected products.
In order to create more intelligent machines that react interactively to their environment, an array of sensors is required. From GPS receivers and antennas, inclination sensors, Inertial Measurement Unit (IMU) and position sensors to RADAR, LiDAR and camera-based sensors for machine automation, these devices collect an enormous amount of data. As an illustration: Cisco estimates that by the end of 2019, the IoT will generate more than 500 zettabytes per year in data—and in the years beyond, that number is expected to grow exponentially, not linearly.
Collecting and storing the data will be a challenge, but how can OEMs analyze this amount of data and ultimately use the results to predict machine behavior and optimize operational efficiency? This is where the flexibility and predictive capability of the physics-based Digital Twin can help. Currently, most Digital Twin implementations run as a stand-alone instance as a lifelike copy of the real-life machine. This approach is especially useful in for example the product design and training stages of the product lifecycle. For data analysis purposes during machine operation, Digital Twins can be run in two further configurations that seamlessly bridge the physical and virtual domains: Digital Twin Online and Digital Twin On-board.
Digital Twin Online with Product Data
By implementing a Digital Twin in the cloud and combining it with real-time product data, a comparison can be made between real-life product data and Digital Twin generated data.
As the Digital Twin connects to the real control software the input from operators or algorithms can be used to operate both the digital and the physical instances of the machine. At the same time, the sensor data from the real-machine can be compared with the simulated sensors in the virtual environment, which allows for the analysis of the deltas between the two values. This analysis can be used to prevent critical failures in the field or recognize when key components need to be serviced or replaced as part of a preventive maintenance program.
Digital Twin On-Board with the Product
By running an instance of the Digital Twin on board with a machine, the comparison between the physical and virtual instance can be done in real-time. The main benefit of the on-board Digital Twin is the fact that analytics can be calculated at the edge which means that only the results get communicated to the cloud. This vastly reduces the amount of telematics that needs to be transmitted in real-time, reducing the need for bandwidth and central processing capacity. The on-board Digital Twin approach also allows calculated data to be used as an input to aid and evaluate operator inputs, creating a machine-in-the-loop approach.
Whether it is online or on-board, the physics-based Digital Twin can make an immense impact on how machines are and will be designed.
For more information about digital twin technology and its uses in product development, download the ebook below!