Unlock instant, AI-driven research and patent intelligence for your innovation.

Real-time prediction method of compost maturity based on deep learning network

A deep learning network, real-time prediction technology, applied in the field of agricultural informatics, to achieve the effect of efficient learning ability

Inactive Publication Date: 2021-06-29
NANJING AGRICULTURAL UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if it is directly used as an index for judging maturity, there are many limitations.

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
  • Real-time prediction method of compost maturity based on deep learning network
  • Real-time prediction method of compost maturity based on deep learning network
  • Real-time prediction method of compost maturity based on deep learning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with embodiment, but protection scope of the present invention is not limited to this:

[0033] combine figure 1 , a method for real-time prediction of compost maturity based on deep learning network, comprising the following steps:

[0034] S1. Extract the temperature and humidity data of the compost at time t and the grayscale image data of the compost surface at time t;

[0035] S2. Preprocessing, performing median filtering on the compost surface grayscale image data;

[0036] S3. Based on the data obtained in S2, construct a convolutional neural network (CNN) to extract compost image features, figure 2 It is the CNN structure diagram;

[0037] S4. Combine compost temperature, humidity data and compost image features to form compost real-time feature vectors, and compost real-time feature vectors are normalized and integrated by the minimum-maximum method;

[0038] S5, based on the data obtain...

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 real-time prediction method of compost maturity based on a deep learning network. The compost internal temperature, humidity, and surface image depth feature vectors are used as compost description features. real-time monitoring. The maturity prediction process starts with the real-time measurement and image acquisition of the temperature and humidity of the pile. The method first preprocesses the image, and extracts the depth features of the image by a convolutional neural network (CNN), and then combines it with the temperature and humidity of the pile as a judgment of maturity. The input of the process is sent to the recurrent neural network (RNN) to predict whether it is rotten at the current moment. The relatively complete, reasonable and accurate real-time monitoring method for compost maturity provided by the invention provides guidance for production.

Description

technical field [0001] The invention relates to a real-time prediction method of compost maturity realized by using information technology using compost temperature, humidity and image information through a deep learning network, belonging to the field of agricultural informatics. Background technique [0002] In agricultural production, in order to maintain and improve soil fertility, it is necessary to apply a certain amount of organic materials to the soil, and to use microorganisms to decompose these materials to a certain extent before application is called decomposing. The composting production mode is divided into static mode and dynamic mode, and the present invention takes the composting mode of linear fermenter as the research object. The width of the fermentation tank is generally 2.0-6.0m, the depth is 0.3-2.0m, and the length is 20-60m. The primary fermentation time of the compost is generally 15-25 days, and then the compost that has completed the primary ferm...

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 Patents(China)
IPC IPC(8): G01N33/00G06N3/04
CPCG01N33/00G06N3/045
Inventor 徐阳春薛卫韦中胡雪娇梅新兰陈行健
Owner NANJING AGRICULTURAL UNIVERSITY