Cooperative Rice Hulling and Polishing Control via Neural Network Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The rice processing industry faces challenges with excessive processing leading to decreased milled rice rate, nutrient loss, and increased energy consumption, and existing equipment lacks the ability to accurately control rice processing precision, stability, and efficiency due to independent control of rice hullers and polishers.
Innovation Solution
A method and device for cooperative control of rice hulling and polishing using neural networks and machine learning algorithms to acquire and optimize process parameters, predicting energy consumption and broken rice rate, and adjusting parameters in real-time to minimize losses and energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If independent control of rice hullers and polishers is used, then equipment operation simplicity is improved, but rice processing precision and stability deteriorate
Solution Approach 1:
The patent merges the independent control systems of the rice huller and rice polisher into a unified cooperative control system. The controller integrates process parameters from both devices and coordinates their operation based on real-time detection data, enabling synchronized adjustment of hulling and polishing processes to achieve precise control while maintaining operational simplicity.
2Adaptability or versatility
If manual parameter adjustment every 1-2 hours is performed, then processing adaptability is improved, but productivity and reliability deteriorate
Solution Approach 1:
The patent implements a real-time feedback control system where detection devices continuously monitor rice processing quality parameters. The controller receives this detection data and automatically adjusts process parameters of the huller and polisher without manual intervention, achieving continuous adaptability while eliminating the need for periodic manual adjustments and thereby improving productivity and reliability.
3Manufacturing precision
If excessive processing is applied to make rice fine and white, then product appearance quality is improved, but milled rice rate and nutrient content deteriorate
Solution Approach 1:
The patent employs dynamic parameter adjustment where the controller continuously optimizes hulling and polishing parameters based on real-time detection data. This dynamic control enables the system to achieve the desired rice appearance quality while automatically preventing excessive processing that would lead to nutrient loss and reduced milled rice rate, adapting the processing intensity to maintain optimal balance.
4Stability of the object's composition
If traditional process design is used, then processing stability is improved, but energy consumption and processing loss increase
Solution Approach 1:
The patent changes the operational parameters of the rice processing system through intelligent optimization. The controller adjusts parameters such as rolling speed, pressure, and temperature based on real-time detection data and process models, enabling the system to maintain stable processing while optimizing energy consumption and reducing processing losses compared to traditional fixed parameter designs.
Data Source
AI summary
The present disclosure provides a method and device for cooperative control of rice hulling and rice polishing, and a storage medium. The method includes: acquiring operation data of a rice huller during a rice hulling process; acquiring operation data of a rice polisher during a rice polishing process; acquiring real-time detection data of rice samples after rice hulling and rice polishing; establishing, an energy consumption prediction model and a broken rice rate prediction model via a neural network and in combination with the operation data of a rice huller and the operation data of a rice polisher; based on a machine learning algorithm, and in combination with the energy consumption prediction model, the broken rice rate prediction model and the real-time detection data, acquiring an optimized process parameter set; and controlling rice processing in real time according to the optimized process parameter set.