Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fruit quality detection method based on machine learning

A technology of quality inspection and machine learning, applied in the field of big data

Inactive Publication Date: 2020-02-28
南京所云人工智能科技有限公司
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for detecting fruit quality based on machine learning, which solves the technical problems of fruit quality detection based on machine learning and gas data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fruit quality detection method based on machine learning
  • Fruit quality detection method based on machine learning
  • Fruit quality detection method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Such as Figure 1-Figure 4 Shown a kind of fruit quality detection method based on machine learning, comprises the steps:

[0031] Step 1: Establish the sensor unit, acquisition unit 2 and host computer;

[0032] Step 2: The sensor unit includes a gas guide bottle, the left end of the gas guide bottle is provided with an exhaust gas outlet 1, and the right end is provided with an air inlet 8, and the gas guide bottle is provided with a collection unit 2, an array sensor 3 and an air suction pump 7;

[0033] Both the aspirating pump 7 and the array sensor 3 are electrically connected to the acquisition unit 2;

[0034] The present invention adopts a regular hexagonal sensor array and a steady flow plate, so that the collected gas does not appear turbulent flow, and the air flow received by each sensor 13 is uniform, so that the collected gas data is more authentic, and the detection efficiency is greatly improved. accuracy.

[0035] Step 3: The host computer screens t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fruit quality detection method based on machine learning, and belongs to the technical field of big data. A sensor establishing unit, an acquisition unit and an upper computer are included, the upper computer establishes a training set and a test set according to principal component sample gas data, the upper host carries out analysis and dimension reduction on the principal component sample gas data in the training set, a KNN algorithm is used to trim the training set, SVM is used for training to obtain a training model, and the principal component sample gas data inthe test set is classified according to the training model. The technical problem in fruit quality detection based on machine learning and gas data is solved, a flow guide plate is added to the sensor unit to solve the problem of airflow instability, a hardware object combining a machine learning method and embedded equipment is applied, fruit quality detection is conducted according to fruit gasdata, the detection steps are simple, installation is easy, and the fruit quality detection device is suitable for various fruit storage environments.

Description

technical field [0001] The invention belongs to the field of big data technology, in particular to a machine learning-based fruit quality detection method. Background technique [0002] At present, most of my country's near-infrared detection equipment comes from imports, and imported instruments include two types: [0003] (1) Large-scale testing equipment used in the laboratory. This kind of testing equipment is generally expensive, bulky, and the testing operation process is cumbersome, and the environmental requirements for the experiment are also relatively high. [0004] (2) When fruit processing enterprises process fruit, they need to carry out quality judgment and testing equipment for the fruit. Miniaturized testing equipment has only been invented in recent years, but it is rare, and most of them are also designed for use by researchers. Suitable for large-scale promotion at low prices. [0005] In recent years, in order to reduce the cost of the instrument, real...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01N33/00
CPCG01N33/0062G06F18/24147G06F18/2411G01N33/0068
Inventor 邹修国吴佳鸿张世凯罗漫漫任乔牧胡红兵姚和阳魏宇宁
Owner 南京所云人工智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products