LogoLogo
HomeDocsAPI & SDKsProjectsForumStudio
  • Welcome
    • Featured Machine Learning Projects
      • Getting Started with the Edge Impulse Nvidia TAO Pipeline - Renesas EK-RA8D1
      • Smart City Traffic Analysis - NVIDIA TAO + Jetson Orin Nano
      • ROS 2 Pick and Place System - Arduino Braccio++ Robotic Arm and Luxonis OAK-D
      • Optimize a cloud-based Visual Anomaly Detection Model for Edge Deployments
      • Rooftop Ice Detection with Things Network Visualization - Nvidia Omniverse Replicator
      • Surgery Inventory Object Detection - Synthetic Data - Nvidia Omniverse Replicator
      • NVIDIA Omniverse - Synthetic Data Generation For Edge Impulse Projects
      • Community Guide – Using Edge Impulse with Nvidia DeepStream
      • Computer Vision Object Counting - Avnet RZBoard V2L
      • Gesture Appliances Control with Pose Detection - BrainChip AKD1000
      • Counting for Inspection and Quality Control - Nvidia Jetson Nano (TensorRT)
      • High-resolution, High-speed Object Counting - Nvidia Jetson Nano (TensorRT)
    • Prototype and Concept Projects
      • Renesas CK-RA6M5 Cloud Kit - Getting Started with Machine Learning
      • TI CC1352P Launchpad - Getting Started with Machine Learning
      • OpenMV Cam RT1062 - Getting Started with Machine Learning
      • Getting Started with Edge Impulse Experiments
  • Computer Vision Projects
    • Workplace Organizer - Nvidia Jetson Nano
    • Recyclable Materials Sorter - Nvidia Jetson Nano
    • Analog Meter Reading - Arduino Nicla Vision
    • Creating Synthetic Data with Nvidia Omniverse Replicator
    • SonicSight AR - Sound Classification with Feedback on an Augmented Reality Display
    • Traffic Monitoring - Brainchip Akida
    • Multi-camera Video Stream Inference - Brainchip Akida
    • Industrial Inspection Line - Brainchip Akida
    • X-Ray Classification and Analysis - Brainchip Akida
    • Inventory Stock Tracker - FOMO - BrainChip Akida
    • Container Counting - Arduino Nicla Vision
    • Smart Smoke Alarm - Arduino Nano 33
    • Shield Bot Autonomous Security Robot
    • Cyclist Blind Spot Detection - Himax WE-I Plus
    • IV Drip Fluid-Level Monitoring - Arduino Portenta H7
    • Worker PPE Safety Monitoring - Nvidia Jetson Nano
    • Delivered Package Detection - ESP-EYE
    • Bean Leaf Disease Classification - Sony Spresense
    • Oil Tank Measurement Using Computer Vision - Sony Spresense
    • Object Counting for Smart Industries - Raspberry Pi
    • Smart Cashier with FOMO - Raspberry Pi
    • PCB Defect Detection with Computer Vision - Raspberry Pi
    • Bicycle Counting - Sony Spresense
    • Counting Eggs with Computer Vision - OpenMV Cam H7
    • Elevator Passenger Counting - Arduino Nicla Vision
    • ESD Protection using Computer Vision - Seeed ReComputer
    • Solar Panel Defect Detection - Arduino Portenta H7
    • Label Defect Detection - Raspberry Pi
    • Dials and Knob Monitoring with Computer Vision - Raspberry Pi
    • Digital Character Recognition on Electric Meter System - OpenMV Cam H7
    • Corrosion Detection with Computer Vision - Seeed reTerminal
    • Inventory Management with Computer Vision - Raspberry Pi
    • Monitoring Retail Checkout Lines with Computer Vision - Renesas RZ/V2L
    • Counting Retail Inventory with Computer Vision - Renesas RZ/V2L
    • Pose Detection - Renesas RZ/V2L
    • Product Quality Inspection - Renesas RZ/V2L
    • Smart Grocery Cart Using Computer Vision - OpenMV Cam H7
    • Driver Drowsiness Detection With FOMO - Arduino Nicla Vision
    • Gastroscopic Image Processing - OpenMV Cam H7
    • Pharmaceutical Pill Quality Control and Defect Detection
    • Deter Shoplifting with Computer Vision - Texas Instruments TDA4VM
    • Smart Factory Prototype - Texas Instruments TDA4VM
    • Correct Posture Detection and Enforcement - Texas Instruments TDA4VM
    • Visual Anomaly Detection with FOMO-AD - Texas Instruments TDA4VM
    • Surface Crack Detection and Localization - Texas Instruments TDA4VM
    • Surface Crack Detection - Seeed reTerminal
    • Retail Image Classification - Nvidia Jetson Nano
    • SiLabs xG24 Plus Arducam - Sorting Objects with Computer Vision and Robotics - Part 1
    • SiLabs xG24 Plus Arducam - Sorting Objects with Computer Vision and Robotics - Part 2
    • Object Detection and Visualization - Seeed Grove Vision AI Module
    • Bike Rearview Radar - Raspberry Pi
    • Build a Self-Driving RC Vehicle - Arduino Portenta H7 and Computer Vision
    • "Bring Your Own Model" Image Classifier for Wound Identification
    • Acute Lymphoblastic Leukemia Classifier - Nvidia Jetson Nano
    • Hardhat Detection in Industrial Settings - Alif Ensemble E7
    • Motorcycle Helmet Identification and Traffic Light Control - Texas Instruments AM62A
    • Import a Pretrained Model with "Bring Your Own Model" - Texas Instruments AM62A
    • Product Inspection with Visual Anomaly Detection - FOMO-AD - Sony Spresense
    • Visual Anomaly Detection in Fabric using FOMO-AD - Raspberry Pi 5
    • Car Detection and Tracking System for Toll Plazas - Raspberry Pi AI Kit
    • Visual Anomaly Detection - Seeed Grove Vision AI Module V2
    • Object Counting with FOMO - OpenMV Cam RT1062
    • Visitor Heatmap with FOMO Object Detection - Jetson Orin Nano
    • Vehicle Security Camera - Arduino Portenta H7
  • Audio Projects
    • Occupancy Sensing - SiLabs xG24
    • Smart Appliance Control Using Voice Commands - Nordic Thingy:53
    • Glass Window Break Detection - Nordic Thingy:53
    • Illegal Logging Detection - Nordic Thingy:53
    • Illegal Logging Detection - Syntiant TinyML
    • Wearable Cough Sensor and Monitoring - Arduino Nano 33 BLE Sense
    • Collect Data for Keyword Spotting - Raspberry Pi Pico
    • Voice-Activated LED Strip - Raspberry Pi Pico
    • Snoring Detection on a Smart Phone
    • Gunshot Audio Classification - Arduino Nano 33 + Portenta H7
    • AI-Powered Patient Assistance - Arduino Nano 33 BLE Sense
    • Acoustic Pipe Leakage Detection - Arduino Portenta H7
    • Location Identification using Sound - Syntiant TinyML
    • Environmental Noise Classification - Nordic Thingy:53
    • Running Faucet Detection - Seeed XIAO Sense + Blues Cellular
    • Vandalism Detection via Audio Classification - Arduino Nano 33 BLE Sense
    • Predictive Maintenance Using Audio Classification - Arduino Nano 33 BLE Sense
    • Porting an Audio Project from the SiLabs Thunderboard Sense 2 to xG24
    • Environmental Audio Monitoring Wearable - Syntiant TinyML - Part 1
    • Environmental Audio Monitoring Wearable - Syntiant TinyML - Part 2
    • Keyword Spotting - Nordic Thingy:53
    • Detecting Worker Accidents with Audio Classification - Syntiant TinyML
    • Snoring Detection with Syntiant NDP120 Neural Decision Processor - Arduino Nicla Voice
    • Recognize Voice Commands with the Particle Photon 2
    • Voice Controlled Power Plug with Syntiant NDP120 (Nicla Voice)
    • Determining Compressor State with Audio Classification - Avnet RaSynBoard
    • Developing a Voice-Activated Product with Edge Impulse's Synthetic Data Pipeline
    • Enhancing Worker Safety using Synthetic Audio to Create a Dog Bark Classifier
  • Predictive Maintenance and Defect Detection Projects
    • Predictive Maintenance - Nordic Thingy:91
    • Brushless DC Motor Anomaly Detection
    • Industrial Compressor Predictive Maintenance - Nordic Thingy:53
    • Anticipate Power Outages with Machine Learning - Arduino Nano 33 BLE Sense
    • Faulty Lithium-Ion Cell Identification in Battery Packs - Seeed Wio Terminal
    • Weight Scale Predictive Maintenance - Arduino Nano 33 BLE Sense
    • Fluid Leak Detection With a Flowmeter and AI - Seeed Wio Terminal
    • Pipeline Clog Detection with a Flowmeter and AI - Seeed Wio Terminal
    • Refrigerator Predictive Maintenance - Arduino Nano 33 BLE Sense
    • Motor Pump Predictive Maintenance - Infineon PSoC 6 WiFi-BT Pioneer Kit + CN0549
    • BrickML Demo Project - 3D Printer Anomaly Detection
    • Condition Monitoring - Syntiant TinyML Board
    • Predictive Maintenance - Commercial Printer - Sony Spresense + CommonSense
    • Vibration Classification with BrainChip's Akida
    • AI-driven Audio and Thermal HVAC Monitoring - SeeedStudio XIAO ESP32
  • Accelerometer and Activity Projects
    • Arduino x K-Way - Outdoor Activity Tracker
    • Arduino x K-Way - Gesture Recognition for Hiking
    • Arduino x K-Way - TinyML Fall Detection
    • Posture Detection for Worker Safety - SiLabs Thunderboard Sense 2
    • Hand Gesture Recognition - OpenMV Cam H7
    • Arduin-Row, a TinyML Rowing Machine Coach - Arduino Nicla Sense ME
    • Fall Detection using a Transformer Model – Arduino Giga R1 WiFi
    • Bluetooth Fall Detection - Arduino Nano 33 BLE Sense
    • Monitor Packages During Transit with AI - Arduino Nano 33 BLE Sense
    • Smart Baby Swing - Arduino Portenta H7
    • Warehouse Shipment Monitoring - SiLabs Thunderboard Sense 2
    • Gesture Recognition - Bangle.js Smartwatch
    • Gesture Recognition for Patient Communication - SiLabs Thunderboard Sense 2
    • Hospital Bed Occupancy Detection - Arduino Nano 33 BLE Sense
    • Porting a Posture Detection Project from the SiLabs Thunderboard Sense 2 to xG24
    • Porting a Gesture Recognition Project from the SiLabs Thunderboard Sense 2 to xG24
    • Continuous Gait Monitor (Anomaly Detection) - Nordic Thingy:53
    • Classifying Exercise Activities on a BangleJS Smartwatch
  • Air Quality and Environmental Projects
    • Arduino x K-Way - Environmental Asthma Risk Assessment
    • Gas Detection in the Oil and Gas Industry - Nordic Thingy:91
    • Smart HVAC System with a Sony Spresense
    • Smart HVAC System with an Arduino Nicla Vision
    • Indoor CO2 Level Estimation - Arduino Portenta H7
    • Harmful Gases Detection - Arduino Nano 33 BLE Sense
    • Fire Detection Using Sensor Fusion and TinyML - Arduino Nano 33 BLE Sense
    • AI-Assisted Monitoring of Dairy Manufacturing Conditions - Seeed XIAO ESP32C3
    • AI-Assisted Air Quality Monitoring - DFRobot Firebeetle ESP32
    • Air Quality Monitoring with Sipeed Longan Nano - RISC-V Gigadevice
    • Methane Monitoring in Mines - Silabs xG24 Dev Kit
    • Smart Building Ventilation with Environmental Sensor Fusion
    • Sensor Data Fusion with Spresense and CommonSense
    • Water Pollution Detection - Arduino Nano ESP32 + Ultrasonic Scan
    • Fire Detection Using Sensor Fusion - Arduino Nano 33 BLE Sense
  • Novel Sensor Projects
    • 8x8 ToF Gesture Classification - Arduino RP2040 Connect
    • Food Irradiation Dose Detection - DFRobot Beetle ESP32C3
    • Applying EEG Data to Machine Learning, Part 1
    • Applying EEG Data to Machine Learning, Part 2
    • Applying EEG Data to Machine Learning, Part 3
    • Liquid Classification with TinyML - Seeed Wio Terminal + TDS Sensor
    • AI-Assisted Pipeline Diagnostics and Inspection with mmWave Radar
    • Soil Quality Detection Using AI and LoRaWAN - Seeed Sensecap A1101
    • Smart Diaper Prototype - Arduino Nicla Sense ME
    • DIY Smart Glove with Flex Sensors
    • EdgeML Energy Monitoring - Particle Photon 2
    • Wearable for Monitoring Worker Stress using HR/HRV DSP Block - Arduino Portenta
  • Software Integration Demos
    • Azure Machine Learning with Kubernetes Compute and Edge Impulse
    • ROS2 + Edge Impulse, Part 1: Pub/Sub Node in Python
    • ROS2 + Edge Impulse, Part 2: MicroROS
    • Using Hugging Face Datasets in Edge Impulse
    • Using Hugging Face Image Classification Datasets with Edge Impulse
    • Edge Impulse API Usage Sample Application - Jetson Nano Trainer
    • MLOps with Edge Impulse and Azure IoT Edge
    • A Federated Approach to Train and Deploy Machine Learning Models
    • DIY Model Weight Update for Continuous AI Deployments
    • Automate the CI/CD Pipeline of your Models with Edge Impulse and GitHub Actions
    • Deploying Edge Impulse Models on ZEDEDA Cloud Devices
Powered by GitBook
On this page
  • Problem Statement
  • Reasons for Solar Panel Damage
  • Challenges in Solar Panel Monitoring
  • Solution
  • Advantages over Manual Inspection
  • Hardware Required
  • Architecture
  • Data Acquisition
  • Create Impulse
  • Model Training
  • Training Output
  • Model Testing
  • Deployment
  • Summary

Was this helpful?

Edit on GitHub
Export as PDF
  1. Computer Vision Projects

Solar Panel Defect Detection - Arduino Portenta H7

Use an Arduino Portenta H7 and FOMO to identify cracks and defects in solar panel arrays.

PreviousESD Protection using Computer Vision - Seeed ReComputerNextLabel Defect Detection - Raspberry Pi

Last updated 1 year ago

Was this helpful?

Created By: Manivannan Sivan

Public Project Link:

Problem Statement

Reasons for Solar Panel Damage

  • Microscopic fractures, hot spots and cracks can appear on the surface of solar panel glass cells, and can grow in size over time. These cracks can reduce the effectiveness of solar cells. The lamination, panel frame and waterproofing of the solar system may remain in good condition despite the cracks, making it hard to identify the cause of the problem.

  • Storm, hail, snow pressure, lightning and other weather conditions can cause extensive damage to solar modules. External damage may also occur due to fire, animal activity, broken tree branches, icy conditions and excessive heat or cold.

  • The scratches from fallen debris can dramatically lower your panels’ energy output. Scratches can hinder sunlight from shining directly onto the cells, and that decreases the amount of solar energy each panel is able to absorb. That, in turn, can increase utility bills, which is one reason to install solar panels in the first place.

Challenges in Solar Panel Monitoring

  • To monitor solar panel and look for damage, manual inspection needs to be done every month or few months.

  • In larger areas, monitoring solar panels periodically needs more people, and the time between inspections might be reduced (more inspection needed).

  • Manual inspection is more time consuming and less efficient.

Solution

Advantages over Manual Inspection

  • It is efficient and less time consuming

  • Hourly monitoring is possible using automated inspection

  • This prototype, if combined with a drone or self driving robot, can inspect entire solar farms.

Hardware Required

  • Arduino Portenta H7

  • Portenta Vision Shield

  • Solar panel

Architecture

For this prototype development, I have used a FOMO-based object detection model to detect the cracks in the solar panel. The below diagram explains the overview of the model development.

The major steps that need to be followed for the model development are:

  • Data Acquisition

  • Model Training

  • Model Testing

  • Deployment

Data Acquisition

For data acquisition, I have collected the real images of solar panels with cracks using the Arduino Portenta H7 and Vision Shield.

To connect the Portenta for the first time, follow the below steps:

  1. Press the Reset button twice to put the device into "boot loader" mode

  2. Flash the downloaded firmware by opening the included script (flash_windows.bat, flash_mac.command or flash_linux.sh)

  3. After flashing, press the Reset button once.

  4. Open a command prompt and run the command edge-impulse-daemon

Now the Portenta is connected to the Edge Impulse account. I have placed the solar panel with cracks in front of the Arduino Portenta plus Vision shield. The distance between solar panel and Portenta is adjusted so that it captures the entire solar panel region.

Then go to Labeling queue in the Data acquisition section to draw bounding boxes around the cracks in the collected images.

In the Labelling queue, all the raw images are shown, and we need to drag and drop the markings and label the cracks.

So ideally, we add all the cracks as objects in the image.

Once labeling is completed for all images in the dataset, split the dataset into 80:20 ratios for training and testing data.

You can click any dataset and move it to the test data.

So I made the ratios close to 80:20.

Create Impulse

In the Create Impulse section, I have selected Object detection and set a Pixel size of 96x96.

Then in the Image section, I have selected the color depth as “ Grayscale”.

Model Training

In the Object detection section, I have selected the FOMO model -- FOMO (Faster Objects, More Objects) MobileNetV2 0.35

In Training settings, I have selected 200 training cycles and a Learning rate as 0.005

The Neural network architecture is FOMO model.

Training Output

In the training output, the model achieved 85.7% accuracy. Around 23.7% of cracks were identified as background, so, there is room for improvement.

The reason for the misclassification is that cracks and PV cells boundary lines look similar in some cases. In those situations, the model predicts the cracks as background.

To improve the accuracy, data augmentation is selected and data acquisition is done with different camera angles to better predict the cracks in the solar panel.

Model Testing

In Model testing, the model is able to identify cracks in solar panel images. In two of the testing data, it did miss identifying some cracks in the panels. This is normally due to lighting differences and camera angle, but it performs decently with 77.8% accuracy in Model testing.

Deployment

Go to the Deployment section and select Build firmware with Arduino Portenta H7 and download the firmware. Then press the Reset button twice to get into the boot loader mode again and open the downloaded script to flash it, similar to earlier.

On my Windows system, I opened the .bat file to flash it to the Portenta.

When complete, press the Reset button once. Finally, open a terminal and run the following command: edge-impulse-run-impulse

Summary

This TinyML model based on FOMO is able to identify cracks in solar panels. One of the key advantages is that it can run on constrained devices like microcontrollers, due to the use of Edge Impulse FOMO. This model can also be ported to other devices such as Sony Spresense, ESP–EYE, or larger systems like an Nvidia Jetson Nano.

I have developed a TinyML model using Edge Impulse and deployed the model onto an Arduino Portenta H7. This model is trained with solar panel images with cracks on them. In Edge Impulse, I have labeled the cracks in the images and trained using a based model.

Download the zip file

Go to the Data Acquisition section in Edge Impulse and .

You can read more about the Labeling queue at this link:

This FOMO model can run Object Detection on resource constrained microcontrollers. For more details about FOMO, refer to the following link:

FOMO
https://cdn.edgeimpulse.com/firmware/arduino-portenta-h7.zip
capture images
https://docs.edgeimpulse.com/docs/edge-impulse-studio/data-acquisition/labeling-queue
https://docs.edgeimpulse.com/docs/edge-impulse-studio/learning-blocks/object-detection/fomo-object-detection-for-constrained-devices
https://studio.edgeimpulse.com/public/126645/latest