Feature: IIOT
their adoption in industrial applications. When combined with AI modelling tools,
the Renesas RA MCU platform and its Flexible SW Package build a multi-neural network layer structure.
Renesas off erings T e fl exible Renesas Advanced (RA) microcontrollers are 32-bit and highly suitable for smart sensor networks. Renesas also off ers a reference design for a versatile Artifi cial Internet of T ings (AIoT) sensor board solution. It targets applications in industrial predictive maintenance, smart-home/IoT appliances with gesture recognition, wearables (activity tracking) and innovative HMIs like the FingerSense solution. Renesas provides the complete range of devices, including an IoT-specifi ed RA microcontroller, an array of sensors (air quality, light, temperature, humidity, etc.), a 6-axis inertial measurement unit and cellular or Bluetooth communication support. For example, the Renesas intelligent
condition-monitoring box (Figure 3) is designed for machine condition monitoring based on fusing data from vibration, sound, temperature and magnetic fi eld sensors. Additional sensor modalities for monitoring acceleration, rotational speeds and shock and vibration can also be included. T e system implements sensor fusion
through AI algorithms to classify abnormal operating conditions with better granularity, for better decision making. T is edge AI architecture can simplify the handling of big data provided by sensors, ensuring that only the most relevant data is sent to the edge AI processor or the cloud for further analysis and the training of ML algorithms. In summary, implementing AI-based
deep learning in industrial applications off ers several benefi ts: • T e AI algorithm can employ sensor fusion to use data from one sensor to compensate for weaknesses in data from another.
• T e AI algorithm can classify the relevance of each sensor to specifi c tasks, and minimise or ignore data from sensors found less important.
• T rough continuous training at the edge or in the cloud, AI/ML algorithms can learn to identify changes in system
Figure 1: An example of a sensor fusion network setup
Figure 2: From Industry 4.0 perspective, feedback from one sensor is usually not enough, particularly for the implementation of control algorithms
Figure 3: Example of an IIoT-enabled platform by Renesas
behaviour that were previously unrecognised.
• T e AI algorithm can predict possible sources of failures, enabling preventative maintenance and improving overall productivity. Sensor fusion combined with AI deep learning presents a powerful tool to
maximise the benefi ts of using a variety of sensor modalities. AI/ML-based enhanced sensor fusion can be employed at several levels in a system, including at the data, fusion or decision level. Basic functions in sensor fusion implementations include smoothing and fi ltering sensor data and predicting sensor and system states.
www.electronicsworld.co.uk March 2023 31
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44
