Chirag

Exploring STM32N6

Chirag on March 10, 2025

A few months ago, I attended the 𝐒𝐓𝐌32 𝐒𝐮𝐦𝐦𝐢𝐭, a global event where they launched their latest microcontroller series – 𝐒𝐓𝐌32𝐍6. This microcontroller is geared towards AI-ML applications due to its integrated neural processing unit and high-performance core.

After the launch, I immediately got my hands on the STM32N6 discovery kit to dive into the world of Edge ML.

What started as an exploration of Edge ML has now expanded into a broader learning journey of

✅ Camera interfaces

✅ Displays, touchscreens, GUIs and TouchGFX

✅ Azure RTOS, ThreadX and advanced interfaces like USB and ethernet

✅ Audio processing

✅ Advanced microcontroller based hardware with external memories, displays and cameras

I’ve already built a few simple applications using TouchGFX and run multiple ML and computer vision based demo applications.

My current target is to learn camera and display interfacing and integration. Eventually I will work my way up to interfacing audio/visual signals with various ML models to build embedded AI applications.

Guest Seminar

Chirag on February 16, 2025

I was honored to be invited to BugBuster 2.0, hosted by Sardar Patel Institute of Technology, to deliver a 1.5-hour pre-event workshop on PCB design and debugging.

The event brings together 150+ students from across the country for a 24-hour hardware hackathon.
We explored the art and science of PCB design, its components, debugging techniques, and how to get started with embedded systems.A special thanks to Prof. P.V. Kasambe and @Woodrow of the I.E.T.E organizing team for their dedication and effort in creating such an outstanding event!

First Project using NanoEdge AI Studio

Chirag on January 8, 2025

Last week, I shared my excitement about exploring Edge Machine Learning with the X-NUCLEO-IKS4A1, NUCLEO-F401RE, and NanoEdgeAI Studio.

I’m excited to share the experience of my first EdgeML application!

MEMS sensor on IKS4A1 senses motor vibrations and F401RE runs an ML model which estimates the speed range based solely on vibration data.

NanoEdgeAI Studio is an intuitive tool designed by STM to easily implement ML models for microcontrollers.

Here’s what it enabled me to do:
1️⃣ Sensor Data Collection: NEAI Studio works with the microcontroller to log the data stream into a csv file which is used for training the ML model.

2️⃣ Model Training: Based on the data collected, NEAI Studio automatically evaluates multiple models, trains them, benchmarks them, and identifies the best fit for your data.

3️⃣ Model Validation and Deployment: You can test various models on your host PC before deploying it to the target microcontroller. The input data stream can be stored data or a stream of fresh data from your microcontroller. You can compare between different parameters like inference time, RAM size, flash size and accuracy.
NEAI Studio then generates a lightweight, ready-to-use model library that I could integrate directly into my application on resource-constrained microcontrollers.

My Application

My final application, running on the NUCLEO-F401RE, has two modes:

🔹 Data Logger Mode: Captures and logs vibration data for training and validating the model initially.

🔹 Inference Mode: Runs the ML model generated by NanoEdgeAI Studio to predict the speed range of the DC motor based on its vibrations.

This project shows how it is possible to bring ML to the edge, even on hardware with limited resources. The potential applications for predictive maintenance, anomaly detection, and more are immense!

Excited to Dive into Edge Machine Learning!

Chirag on January 1, 2025

I recently got my hands on the X-NUCLEO-IKS4A1, a powerful sensor evaluation board from STMicroelectronics that’s perfect for exploring Edge AI applications. 🌟

This incredible board is packed with sensors such as accelerometers, gyroscopes
magnetometer, barometer etc. Some of these sensors even have the capability to perform signal processing and run ML models directly!

Paired with a Nucleo board, this platform offers an excellent foundation for real-time data processing at the edge.

My goal? To deep-dive into Edge Machine Learning; harnessing this technology for low-power, highly intelligent systems. Over the coming weeks, I’ll be:
🔹 Learning how to integrate sensor data with AI/ML models on microcontrollers.
🔹 Exploring edge computing use cases like predictive maintenance and motion analysis.
🔹 Sharing my progress, challenges, and key takeaways.

The potential of Edge AI is massive, from IoT to industrial automation, and I’m thrilled to start this journey.

Troubleshooting competition

Chirag on January 30, 2019

The PCB that we designed

Every year the department of electronics engineering at SPIT organizes an electronics hardware and simulation competition for the 3rd year students. This year I was a part of the organizing team and in charge of the hardware aspects of the competition.

There were three phases to this competition

A quiz based on basic electronics concepts
Students debug a circuit in simulation
Students debug the same circuit in hardware

This year was a step up from the previous years as we involved the entire third-year class in the final phase that is the hardware phase.

Adithiya and I designed the PCBs and had 30 of them manufactured.

Due to some circumstances, we got the PCBs very late and were hard pressed for time to have them assembled and tested. With the help of our classmates, we were able to solder all the 28 boards in one day!

Then began the task of verifying that all the boards were functioning as expected. Here we faced a lot of issues regarding noise induced in the power rails due to the digital logic ICs. This took us some time to figure out which was solved by adding filtering capacitors at the appropriate places in the circuit.

Due to various issues, we had to major problems with the procurement of the 8051 ICs. We learnt the importance of planning in the procurement of the components.

In the end, we managed to overcome all the issues and the competition was a success.

Here are some of the photos.

The Team

Workshop on Introduction to Embedded Systems Design

Chirag on June 7, 2018

The final board

You can view the detailed plan of our workshop here

After our last workshop on “Introduction to Microcontrollers, Sensors and Arduino“, we wanted to go further by taking a workshop on embedded systems. In March 2018, we (Srijal and myself) in collaboration with Electronics Students Association and IR cell of our college we conducted another hands-on workshop on introduction to embedded systems design.

The aim was to demonstrate the complete end to end process of designing and building an embedded system from scratch; right from hardware design, board assembly, board configuration and then writing the respective embedded C code to get the experiments to life without using any Arduino libraries.

For this purpose, I designed a custom board using the ATmega328p microcontroller. The board had an onboard LCD display, 3.3V & 5V regulators, ISP as well as serial programming interfaces.

The ATmega board documentation can be viewed here.
The example codes for both embedded C and Arduino can be found here.

We started the workshop with concepts of PCB designing and manufacturing. We went through the design process and the design considerations for the board.

On the second day, the participants completed the assembly of their boards by soldering through hole and SMD components. Along the way, we showed them tips and tricks of soldering. After testing all the boards, we had LED and LCD interfacing experiments. We ended the day with an example of ADC (Analog to Digital Converter) interfacing using a potentiometer.

Workshop on Introduction to Microcontrollers, Sensors and Arduino

Chirag on February 11, 2018

Some of the photos from the workshop

You can see our detailed plan here.

The IEEE Student branch at our college invited Srijal and me to conduct a workshop on Arduino for the first year students. We decided to conduct an 8 hours workshop spanning over two days.

Our aim was to make the workshop completely hands on one and explain the theory through practicals. We did this because it is our firm belief that no concept can be understood by reading/listening alone; the only way to understand anything completely is by practically doing things and experiencing it. We wanted to start from scratch so that their base/foundation becomes strong and thus give them a platform to build their knowledge.

The first step for the hands-on workshop was to give them their own kits. For this, we assembled a kit containing all the required components.

Kit assembly

We started the workshop with simple examples such as blinking an LED, PWM (pulse-width modulation) then slowly moved up-to interfacing buttons, potentiometers, transistors, motors and ended the workshop with interfacing an ultrasonic distance sensor.

We first explained the concepts, circuit diagram and code to everyone and then using the kits they wrote the code and executed the project on their own.

Along the way, we showed them our projects to make them understand the application of what they were learning. This gave them a practical application understanding of the concepts that they had learned.

Feedback from all the participants

Some of the feedback from participants

It was funny how he articulated technology, didn’t bore us at all!

Excellent workshop and hats off to the hardwork done by Srijal and Chirag

We would like to enroll for future workshops as our practical knowledge is weak… I want more workshops

Liked the fact that we were given a lot of practical experience

It really motivated me to make projects myself

Journey of PCB designing

Chirag on December 25, 2017

Fixed DC supply

All my PCBs

I’ve designed PCBs for projects like the constant current load, real-time room occupancy system, PCBs to solve my own needs like making ac-dc power supplies, microcontroller boards etc. For conducting a workshop at my college; I designed an ATmega microcontroller board.

It all started with the RoboCon PCB designing workshop in my first year of engineering. We designed a blinky board which blinked 2 LEDs in sequence. It gave me a basic idea of PCB designing and I was on my way to designing more complex PCB’s.

Using this newly learned technique I went on to design and build my own DC power supplies which I still use to this day.

Next, I designed a micro-controller board very similar to an Arduino. I did this as it was more cost effective and I’d have another board that I could use in my projects.

Next, I designed the constant current load board which would be the most challenging design to date. The PCB was too complex and impractical to build by hand so I decided it was worth to get it professionally manufactured. I designed the board in Eagle and got it manufactured from PCBway (PCB prototyping company based out of China).

Constant Current Load

Next, I designed the ATmega board for the “Introduction to Embedded Systems Design, Embedded C Programming, PCB Designing and Soldering” workshop that we conducted in college. We assembled and distributed 10 boards for the workshop.

The last board that I have designed so far is for the real-time room occupancy system. It is the smallest board I have ever designed with the most component density. I have used small SMD packages like TQFP and SOT which have a very small lead spacing are quite challenging to solder by hand.

Prototype on breadboards

Room Occupancy Sensor

Needless to say, I still have a lot to learn in the domain of PCB designing and I am only just getting started and the journey has been satisfying so far…..