![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/IMG20250529123436-2-min.jpg\")
<\/p>\n![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/Screenshot-2025-06-18-211911.png\")
<\/p>\n\n
System Workflow<\/h3>\n\n\n- System Initialization<\/strong>
The ESP32-WROOM-32 and ESP32-CAM are powered on. The system displays the status “Ready” on the OLED and stands by to start the inference process.<\/li>\n- Image Capture<\/strong>
When a product passes in front of the camera, the ESP32-CAM automatically captures an image.<\/li>\n- AI Inference<\/strong>
The captured image is sent to the ESP32-WROOM-32 or processed directly on the ESP32-CAM (if the model is lightweight enough). The AI model classifies the image as:\n\n- Intact<\/strong> \u2192 the product is passed through<\/li>\n
- Damaged<\/strong> \u2192 the product is diverted to the reject path<\/li>\n<\/ul>\n<\/li>\n
- Decision Making and Action<\/strong>
Based on the classification result:\n\n- A servo or actuator directs the product to the appropriate path (accepted or rejected)<\/li>\n
- The OLED display shows the classification result and the count of passed vs. rejected products<\/li>\n<\/ul>\n<\/li>\n
- Monitoring and Redundancy<\/strong>
The system can be remotely monitored via a dashboard (web\/mobile app).
If the main ESP32 fails, the backup ESP32 is activated through a watchdog system and takes over the process.<\/li>\n<\/ol>\n
\n<\/article>\nSchematic<\/h3>\n
![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/proses.drawio-1.png\")
<\/p>\n
This diagram illustrates the flow of data and control in the proposed quality control system using ESP32 microcontrollers. The system is divided into three main stages: Input<\/strong>, Process<\/strong>, and Output<\/strong>.<\/p>\n\n- Input Stage<\/strong>:
The ESP32-CAM module functions as both a sensor<\/strong> and AI inference engine<\/strong>, capturing images of product packaging and classifying them as either intact<\/em> or damaged<\/em> using an embedded neural network model.<\/li>\n- Processing Stage<\/strong>:
A secondary ESP32 microcontroller receives the classification results for decision-making. It handles:\n\n- Communication with the cloud or mobile interface via Wi-Fi<\/strong>.<\/li>\n
- Logic control to determine actuator behavior.<\/li>\n
- Optional redundancy management in case of system faults.<\/li>\n<\/ul>\n<\/li>\n
- Output Stage<\/strong>:
The results are:\n\n- Sent to the User Interface<\/strong> (e.g., Blynk) for real-time notifications and system monitoring.<\/li>\n
- Used to control actuators<\/strong> (e.g., servo motors) to separate defective products automatically.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n
This architecture ensures efficient, real-time decision-making and system feedback in a compact, low-power embedded setup, suitable for industrial quality control applications.<\/p>\n
\n\ud83c\udfac\u00a0Demo and Evaluation<\/strong><\/h3>\n\n- \n
\ud83d\udee0\ufe0f\u00a0Setup<\/strong>: Assemble all hardware components, including the ESP32-CAM, dual ESP32 boards (MAIN & BACKUP), Arduino Nano, L298N motor driver, DC motor for the conveyor belt, and MG996R servo motor. Upload the developed firmware to each microcontroller using the Arduino IDE. Ensure required libraries such as Blynk, Servo, and WiFi are installed.<\/p>\nThis project operates in a Wi-Fi-based IoT environment, where the ESP32 connects to a network to send real-time notifications to the Blynk<\/strong> application. Additionally, the AI model for defect detection is deployed on the ESP32-CAM via the Edge Impulse<\/strong> platform, enabling local inference (Embedded AI) without cloud processing.<\/p>\n<\/li>\n<\/ul>\n![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/IMG20250529123628-min.jpg\")
![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/IMG20250529123617-min.jpg\")
![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/WhatsApp-Image-2025-05-18-at-21.13.53_77030941-min.jpg\")
![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/IMG20250529123608-min.jpg\")
<\/p>\n
\n- \n
\ud83d\udc15\u00a0Demo<\/strong>: This section demonstrates the full operation of the automated inspection system. The ESP32-CAM captures real-time images of products on a conveyor belt and classifies them using an embedded AI model. Based on the classification result, the main ESP32 controls a servo motor to sort the product into the appropriate lane \u2014 either \u201cpass\u201d or \u201creject.\u201d All decisions and system status updates are also sent to the Blynk app for real-time remote monitoring.<\/p>\n<\/li>\n- \n
- \n
- System Initialization<\/strong>
The ESP32-WROOM-32 and ESP32-CAM are powered on. The system displays the status “Ready” on the OLED and stands by to start the inference process.<\/li>\n- Image Capture<\/strong>
When a product passes in front of the camera, the ESP32-CAM automatically captures an image.<\/li>\n- AI Inference<\/strong>
The captured image is sent to the ESP32-WROOM-32 or processed directly on the ESP32-CAM (if the model is lightweight enough). The AI model classifies the image as:\n- \n
- Intact<\/strong> \u2192 the product is passed through<\/li>\n
- Damaged<\/strong> \u2192 the product is diverted to the reject path<\/li>\n<\/ul>\n<\/li>\n
- Decision Making and Action<\/strong>
Based on the classification result:\n- \n
- A servo or actuator directs the product to the appropriate path (accepted or rejected)<\/li>\n
- The OLED display shows the classification result and the count of passed vs. rejected products<\/li>\n<\/ul>\n<\/li>\n
- Monitoring and Redundancy<\/strong>
The system can be remotely monitored via a dashboard (web\/mobile app).
If the main ESP32 fails, the backup ESP32 is activated through a watchdog system and takes over the process.<\/li>\n<\/ol>\n
\n<\/article>\nSchematic<\/h3>\n
<\/p>\nThis diagram illustrates the flow of data and control in the proposed quality control system using ESP32 microcontrollers. The system is divided into three main stages: Input<\/strong>, Process<\/strong>, and Output<\/strong>.<\/p>\n
- \n
- Input Stage<\/strong>:
The ESP32-CAM module functions as both a sensor<\/strong> and AI inference engine<\/strong>, capturing images of product packaging and classifying them as either intact<\/em> or damaged<\/em> using an embedded neural network model.<\/li>\n- Processing Stage<\/strong>:
A secondary ESP32 microcontroller receives the classification results for decision-making. It handles:\n- \n
- Communication with the cloud or mobile interface via Wi-Fi<\/strong>.<\/li>\n
- Logic control to determine actuator behavior.<\/li>\n
- Optional redundancy management in case of system faults.<\/li>\n<\/ul>\n<\/li>\n
- Output Stage<\/strong>:
The results are:\n- \n
- Sent to the User Interface<\/strong> (e.g., Blynk) for real-time notifications and system monitoring.<\/li>\n
- Used to control actuators<\/strong> (e.g., servo motors) to separate defective products automatically.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n
This architecture ensures efficient, real-time decision-making and system feedback in a compact, low-power embedded setup, suitable for industrial quality control applications.<\/p>\n
\n\ud83c\udfac\u00a0Demo and Evaluation<\/strong><\/h3>\n
- \n
- \n
\ud83d\udee0\ufe0f\u00a0Setup<\/strong>: Assemble all hardware components, including the ESP32-CAM, dual ESP32 boards (MAIN & BACKUP), Arduino Nano, L298N motor driver, DC motor for the conveyor belt, and MG996R servo motor. Upload the developed firmware to each microcontroller using the Arduino IDE. Ensure required libraries such as Blynk, Servo, and WiFi are installed.<\/p>\n
This project operates in a Wi-Fi-based IoT environment, where the ESP32 connects to a network to send real-time notifications to the Blynk<\/strong> application. Additionally, the AI model for defect detection is deployed on the ESP32-CAM via the Edge Impulse<\/strong> platform, enabling local inference (Embedded AI) without cloud processing.<\/p>\n<\/li>\n<\/ul>\n
<\/p>\n- \n
- \n
\ud83d\udc15\u00a0Demo<\/strong>: This section demonstrates the full operation of the automated inspection system. The ESP32-CAM captures real-time images of products on a conveyor belt and classifies them using an embedded AI model. Based on the classification result, the main ESP32 controls a servo motor to sort the product into the appropriate lane \u2014 either \u201cpass\u201d or \u201creject.\u201d All decisions and system status updates are also sent to the Blynk app for real-time remote monitoring.<\/p>\n<\/li>\n
- \n
- \n
- Used to control actuators<\/strong> (e.g., servo motors) to separate defective products automatically.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n
- Processing Stage<\/strong>:
- Input Stage<\/strong>:
- Damaged<\/strong> \u2192 the product is diverted to the reject path<\/li>\n<\/ul>\n<\/li>\n
- Image Capture<\/strong>
![\"\"](\"https:\/\/filkom.ub.ac.id\/project\/wp-content\/uploads\/sites\/3\/2025\/06\/WhatsApp-Image-2025-06-02-at-11.54.02_c845a1b6-scaled.jpg\")
<\/p>\n