Related Experiment Video
Updated: Aug 5, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
Published on: October 14, 2017
Data-Driven Real-Time Rice Milling Optimisation via YOLO26 Machine Vision and Adaptive Closed-Loop Motor Control
Benjamin Ilo1, Yogang Singh2, Hongwei Zhang1
1Advanced Food Innovation Centre (AFIC), Sheffield Hallam University, Sheffield S9 2AA, UK.
This study introduces a cloud-based system using YOLOv26 machine vision and Arduino control to reduce rice breakage during milling. The closed-loop system significantly improved milling quality, achieving Grade A-equivalent standards.
Area of Science:
- Agricultural Engineering
- Computer Vision
- Machine Learning
- Process Control
Background:
- Conventional rice milling quality inspection occurs post-process, preventing real-time adjustments and leading to increased grain breakage.
- Lack of immediate feedback in traditional milling processes hinders optimization and results in suboptimal product quality.
Purpose of the Study:
- To develop and validate a cloud-mediated, closed-loop control system for real-time rice milling quality adjustment.
- To quantitatively assess the effectiveness of a YOLOv26 machine vision pipeline coupled with Arduino-based actuators in reducing rice breakage.
Main Methods:
- A cloud-mediated architecture was implemented, integrating a YOLOv26 machine vision pipeline for broken rice detection with Arduino microcontrollers for actuator control.
- Image data was acquired, uploaded to the cloud, and processed for broken rice fraction estimation using YOLOv26 and a hybrid classifier.
- Actuators (motor and vibrator) were controlled via Pulse Width Modulation (PWM) based on real-time quality feedback.
Main Results:
- The YOLOv26 detector achieved high performance with a mean Average Precision of 0.951 on a test set.
- Closed-loop operation significantly reduced the broken rice fraction from 21.04% to 6.19% compared to an open-loop baseline.
- Dynamic analysis revealed a near-linear plant gain, quantifying the relationship between PWM input and breakage percentage.
Conclusions:
- The developed closed-loop system effectively reduces rice breakage, moving laboratory prototype quality from non-compliant to Grade A-equivalent at constant throughput.
- The study provides a quantitative characterization of the actuator's transfer relationship under deep learning feedback, enabling future control system synthesis.
- A roadmap for scaling the technology from laboratory prototype to pilot-scale deployment is outlined.
Related Concept Videos
Open and closed-loop control systems
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal and...
Mechanical Efficiency of Real Machines
However, in reality, no machine can be truly ideal, and all of them experience some...
Sequence Networks of Rotating Machines
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Feedback control systems
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...
PID Controller
Rolling Resistance: Problem Solving