Neural network-based methods of rapidly detecting heavy-metal content of soil on site

A neural network and heavy metal technology, applied in neural learning methods, biological neural network models, measuring devices, etc., can solve the problems of expensive, inconvenient, and time-consuming equipment, and achieve easy classification or prediction, improved accuracy, and accurate Detection effect

Active Publication Date: 2019-02-05
苏州市环境科学研究所 +3
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In the above-mentioned detection methods, the instruments and equipment used are relatively sophisticated, expensive, and large in size, and they need to be fixed and used after installation and debugging in the laboratory, and cannot be carried around for use when going out. When detecting the content of heavy metals in soil, on-site sampling is required. Finally, it is sent to the laboratory for complex pretreatment and heterotopic detection and analysis, which is time-consuming and inconvenient, and cannot be used for on-site rapid detection

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A method for rapidly detecting heavy metal content in soil on the spot, the steps of which are:

[0061] 1. Collect about 5g of soil sample on site; when collecting, remove dead branches and leaves, and gravel particles visible to the naked eye;

[0062] 2. Crush the collected soil samples, and then apply pressure to compact them into thin discs with a thickness of about 1mm;

[0063] 3. Place the compacted soil sample between a pair of parallel metal plates;

[0064] 4. Heat and dry the compacted soil sample in a compacted state, the heating temperature is 110°C, and the drying time is 3 minutes;

[0065] 5. At a constant temperature, use an alternating signal source to apply an alternating electric signal v with a frequency constantly changing on the above pair of parallel metal plates t Acting on the dried soil sample, the signal amplitude remains unchanged, and the output alternating electric signal v of the alternating signal source t The frequency f changes eve...

Embodiment 2

[0075] In the above step 5, the output alternating electric signal v of the alternating signal source t The frequency f changes every 200ms, the frequency increases from 100Hz, and the difference between every two frequencies is 1.1 times until it increases to about 1MHz. The specific frequency list is as follows:

[0076] 100Hz, 110Hz, 121Hz, 133.1Hz..., 777.88KHz, 855.67KHz, 941.23KHz, 1.035MHz, a total of 98 frequency points,

[0077] All the other are the same as the first embodiment.

[0078] The test of 98 frequency points is completed, and it takes a total of 49s.

Embodiment 3

[0080] Adjust steps 2-3 to: crush the collected soil sample, place the crushed soil sample directly between a pair of parallel metal plates and apply pressure to compact it, scrape off the leaked parallel metal plates with a scraper The excess part outside the parallel metal plate is made into a thin sheet sample with the same shape and size as the parallel metal plate;

[0081] All the other are identical with embodiment two.

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 provides a method of rapidly detecting the heavy-metal content of soil on site. The methods are completely different from principles of the prior art. One of the methods specifically includes: collecting a soil test sample on site; and compacting and drying the soil test sample, placing the same between a pair of parallel metal plates, applying an alternating electrical signal of continuously changed frequency thereto, detecting and recording electrical parameters, which are of passing through the pair of parallel metal plates and the soil test sample by the alternating electrical signal, in real time to use the same for normalization, obtaining features of a measurement curve through neural network-based machine learning, and obtaining the heavy-metal content of the collected soil test sample.

Description

technical field [0001] The invention relates to a method for quickly detecting soil heavy metal content on the spot based on a neural network. Background technique [0002] Soil heavy metal pollution is a very common phenomenon. Soil heavy metal pollution refers to the introduction of heavy metals into the soil due to natural reasons or human activities, causing the content of heavy metals in the soil to be significantly higher than the background value, and causing existing or potential soil pollution. Phenomena of quality degradation, ecological and environmental degradation. Soil heavy metals come from a wide range of sources, mainly including atmospheric dustfall, sewage irrigation, improper stacking of industrial solid waste, mining activities, pesticides and fertilizers, etc. All industries that use heavy metals and materials containing heavy metals as raw materials for production may discharge heavy metals during the production process. If they are not disposed of pr...

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): G01N27/00G01N1/28G01N1/44G01N21/33G01N21/31G01N21/64G01N27/62G01N23/223G06N3/08
CPCG01N1/286G01N1/44G01N21/31G01N21/33G01N21/64G01N23/223G01N27/00G01N27/62G06N3/08
Inventor 许伟施维林蔡慧陈洁贺志刚孟宪荣
Owner 苏州市环境科学研究所
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products