Innovative projects co-developed
Smart manufactory, academic project developed in cooperation with IBM Power AI. Product tracking and counting using Deep Learning, with IBMPowerAI and OpenCV.
R-CNN is slow because it performs a ConvNet forward pass for each object proposal, without sharing computation The Fast R-CNN method has several advantages:
Higher detection quality (mAP) than R-CNN, SPPnet
Training is single-stage, using a multi-task loss
Training can update all network layers
No disk storage is required for feature caching
Vibration monitoring using MEMS accelerometer and IBM Watson rules and actions
Cloud vibration monitoring is emerging as an application that includes two technologies. High performance instruments that monitor machine for maintenance and wireless communication which allows sending data to cloud for monitoring, analyzing and classification.
The vibrations signal measured with an 3-axis MEMS sensor, FFT (Fast Fourier Transform) analysis was performed on STM32 microcontroller then data will be sent to IBM Watson IoT for monitoring, analyzing and classification.
Thanks to the smart gateway IoT2040 from Siemens we are able to connect the S7-1500 to Cloud over LoRaWAN.
Monitoring and Analysis of Production Line using Siemens S7-1500 using IBM Cloud AI capabilities.
Smart Gateway is connected to Cloud over LoRaWAN
S7-1500 is connected to Cloud over Siemens IoT 2040Smart gateway
IoT2040 , first demo Gas detecting : nodered on the #IOT2040 which is equiped with Yocto Linux (open source) and Arduino compatible, the gas sensor is connected directly to #IOT2040 via integrated GPIOx
ARM sytem On chip Design
Cortex M0 based on system on chip With PWM.
Variable duty cycle with assembly code « keil ARM », Pwm module with verilog integrated with ARM M0 SoC
implementation on Nexys 3
Thanks to ARM university program