We held our next tinyML Talks webcast. Manivannan Sivan from Valeo presented Industry 4.0: Predictive Maintenance using Arduino Portenta H7 and Edge Impulse on May 6, 2022.
The proposed method explains the potential of TinyML in Industrial 4.0. This TinyML model uses Arduino Portenta H7 and Edge Impulse to predict the anomalous operation in Industrial machineries like Pump, valves & fans. For Industrial machineries audio datasets, the proposed method uses open source datasets - MIMII. This dataset contains an audio of malfunctioning industrial machines. It contains the sounds generated from four types of industrial machines, i.e. valves, pumps, fans, and slide rails. Each type of machine includes seven individual product models*1, and the data for each model contains normal sounds (from 5000 seconds to 10000 seconds) and anomalous sounds (about 1000 seconds).The model is trained using Edge Impulse with 1-D Convolution layer and followed by neural network layers.
Manivannan has been working as a lead engineer on the computer vision platform at Valeo. He is pursuing his Ph.D. in “computational prediction methods on vehicle control stability” at VIT University. He passionately created many TinyML-based applications, from elephant conservation to the automotive field. His research work in 2015 holds one Indian patent, “An Ohmic heater for food preservation by the flash process through a low voltage IGBT based single phase inverter module.” One of his TinyML models won as the “Top 5 machine learning model” in the Elephant Edge contest conducted by hackster.
Watch on YouTube:
Download presentation slides:
Feel free to ask your questions on this thread and keep the conversation going!