CN220271166U - Waste plastic identification system based on near infrared spectrum - Google Patents
Waste plastic identification system based on near infrared spectrum Download PDFInfo
- Publication number
- CN220271166U CN220271166U CN202321544228.8U CN202321544228U CN220271166U CN 220271166 U CN220271166 U CN 220271166U CN 202321544228 U CN202321544228 U CN 202321544228U CN 220271166 U CN220271166 U CN 220271166U
- Authority
- CN
- China
- Prior art keywords
- spectrum
- computer
- near infrared
- plastic
- identification system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 229920003023 plastic Polymers 0.000 title claims abstract description 41
- 239000004033 plastic Substances 0.000 title claims abstract description 41
- 239000002699 waste material Substances 0.000 title claims abstract description 25
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 18
- 239000000523 sample Substances 0.000 claims abstract description 63
- 238000001228 spectrum Methods 0.000 claims abstract description 53
- 230000009471 action Effects 0.000 claims abstract description 5
- 238000012546 transfer Methods 0.000 claims description 3
- 238000004497 NIR spectroscopy Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 8
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 206010063385 Intellectualisation Diseases 0.000 abstract 1
- 238000000926 separation method Methods 0.000 abstract 1
- 238000000034 method Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000007781 pre-processing Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000000701 chemical imaging Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The utility model discloses a waste plastic identification system based on near infrared spectrum; the device comprises a camera, a spectrum probe, a transmission platform, a computer and a mechanical arm; the plastic to be tested moves under the action of the conveying platform, the photo shot by the camera is transmitted to the computer in real time for processing, and the position information of the plastic is calculated; the mechanical arm drives the near infrared spectrum probe to move to the upper side of the plastic, the near infrared spectrum signal of the plastic is collected and transmitted back to the computer, and the computer analyzes and identifies the spectrum to obtain the type information of the plastic. Compared with the prior art, the plastic identification system based on the near infrared spectrum realizes automation and intellectualization of plastic identification, and has the characteristics of high separation efficiency, high speed and low cost.
Description
Technical Field
The utility model relates to the field of nondestructive testing equipment production, in particular to the field of waste recycling and production in the environment-friendly industry, in particular to a waste plastic identification system based on near infrared spectrum.
Background
The plastic is widely applied in production and life by virtue of a series of advantages of low cost, easy processing, strong durability and the like, and is an important base material. At present, the plastic industry in China develops rapidly, and the irregular recovery and disposal of a large amount of plastic wastes bring about great energy waste and serious pollution to the environment. At present, the plastic products in China are recovered mainly by manual recovery, and the recovery mode has low efficiency and great harm to human health.
Meanwhile, the existing technology for sorting and identifying the waste plastics is quite various, but the identification accuracy is low, the testing time is long, the precision is low, and the production capacity of plastics recycling enterprises is severely restricted.
The existing methods for identifying the types of the waste plastics by utilizing the spectrum signals comprise a near infrared hyperspectral imaging method and a single probe scanning imaging method. Although the detection method can basically meet the sorting requirement, at least the following disadvantages exist:
1. the detection cost is high: the near infrared hyperspectral imaging method is expensive in equipment, and the construction cost of the waste plastic identification system is higher than that of a single-probe system.
2. The detection efficiency is low: the single probe scanning imaging method is long in time consumption and low in detection speed due to the fact that the whole identification area needs to be scanned point by point, and is particularly not suitable for spectrum collection of waste plastics in the motion process.
Disclosure of Invention
The utility model aims to overcome the defects and shortcomings of the prior art and provide a real-time, rapid and low-cost waste plastic identification system based on near infrared spectrum.
The utility model is realized by the following technical scheme:
the waste plastic identification system based on the near infrared spectrum comprises a camera 1, a spectrum probe 2, a conveying platform 3, a computer 4 and a mechanical arm 5;
the spectrum probe 2 is arranged at the end part of the mechanical arm 5; the mechanical arm 5 is used for collecting the spectrum information of the sample to be tested on the transmission platform 3 and transmitting the spectrum information to the computer 4;
the camera 1 is used for collecting image information of a designated area and transmitting the image information to the computer 4.
The camera 1, the spectrum probe 2 and the mechanical arm 5 are respectively connected with the computer 4 through signals.
The mechanical arm 5 drives the spectrum probe 2 to move in a plane parallel to the conveying platform 3.
The camera 1 is located above the transfer platform 3.
The computer 4 analyzes the information transmitted by the camera 1 and identifies the position of the sample to be detected.
The computer 4 sends an action signal to the mechanical arm 5 to drive the spectrum probe 2 to move to a designated area.
The identification method of the waste plastic identification system based on the near infrared spectrum comprises the following steps:
the sample to be measured is conveyed to a conveying platform 3 along with a conveying belt, and a camera 1 positioned on the conveying platform 3 detects the image information of the sample to be measured and transmits the image information to a computer 4;
the computer 4 processes the image information of the sample to be measured, obtains the real-time position of the sample to be measured on the conveyor belt, and calculates the relative position of the sample to be measured and the spectrum probe 2;
the mechanical arm 5 drives the spectrum probe 2 to rapidly move to the position right above the sample to be detected, collects spectrum information of the sample to be detected and transmits the spectrum information to the computer 4;
the computer 4 compares the spectrum information of the collected sample to be tested with the pre-trained machine algorithm model data, and extracts the material type information of the sample to be tested.
The processing and analyzing flow of the image information is as follows:
converting the position information of the sample to be detected into position information in an actual world coordinate system;
calibrating internal and external parameters of the camera, and carrying out distortion correction and coordinate system matrix transformation to obtain the position of a pixel point in an absolute coordinate system;
preprocessing the acquired image, namely filtering and binarizing the acquired image;
and calculating the preprocessed image information to obtain the contour and centroid positions of the sample to be detected.
The comparison flow of the pre-trained machine algorithm model data is as follows:
preprocessing the collected spectrum data, and reserving spectrum effective information;
modeling the preprocessed spectrum data by a combined classification algorithm;
inputting the collected spectrum data into a machine algorithm model to obtain the predicted category of the spectrum data;
and controlling the lower computer to screen and sort the plastics according to the prediction type.
The preprocessing of the spectral data is derivative processing, smoothing processing or principal component analysis.
Compared with the prior art, the utility model has the following advantages and effects:
the system combines the single spectrum probe and the mechanical arm to form the plastic rapid identification system, overcomes the defects of long time spent by scanning imaging of the single spectrum probe and high equipment cost of near infrared hyperspectral imaging, and realizes rapid detection of a plastic sample to be detected in the motion process. Compared with the traditional spectrum recognition system, the system realizes rapid, low-cost and intelligent plastic recognition, improves recognition efficiency and reduces cost.
The precise identification of the sorted plastic products is realized by means of a machine learning algorithm, and the speed and accuracy of identifying the types of the waste plastic products are greatly improved. In the actual sorting and identifying process, a large amount of spectrum and image data of waste plastics are collected and captured, and the system built by the utility model can screen and retain the effective information which is actually obtained and is favorable for identifying and sorting, and continuously expand and enrich modeling data, thereby improving the sorting efficiency and precision.
Drawings
Fig. 1 is a schematic diagram of a waste plastic recognition system based on near infrared spectrum.
Detailed Description
The present utility model will be described in further detail with reference to specific examples.
The waste plastic identification system based on the near infrared spectrum comprises a camera 1, a spectrum probe 2, a conveying platform 3, a computer 4 and a mechanical arm 5;
the spectrum probe 2 is arranged at the end part of the mechanical arm 5; the mechanical arm 5 is used for collecting the spectrum information of the sample to be tested on the transmission platform 3 and transmitting the spectrum information to the computer 4;
the camera 1 is used for collecting image information of a designated area and transmitting the image information to the computer 4.
The camera 1, the spectrum probe 2 and the mechanical arm 5 are respectively connected with the computer 4 through signals.
The mechanical arm 5 drives the spectrum probe 2 to move in a plane parallel to the conveying platform 3.
The camera 1 is located above the transfer platform 3.
The computer 4 analyzes the information transmitted by the camera 1 and identifies the position of the sample to be detected.
The computer 4 sends an action signal to the mechanical arm 5 to drive the spectrum probe 2 to move to a designated area.
The plastic is conveyed forward by the conveying platform 3; the camera 1 collects and transmits platform image information; the computer 4 receives the image signal and analyzes the position information of the sample to be detected; the computer 4 sends an action signal to the mechanical arm 5, and the spectrum probe 2 is moved to the position above the sample to be detected; the spectrum probe 2 collects spectrum signals of a sample to be detected; the computer 4 analyzes the spectrum signals, extracts the type information of the sample material to be detected, compares the type information with the pre-trained machine algorithm model data, marks the possible type of the sample material to be detected and visually displays the possible type of the sample material to be detected.
The identification method of the waste plastic identification system based on the near infrared spectrum can be realized by the following steps:
the sample to be measured is conveyed to a conveying platform 3 along with a conveying belt, and a camera 1 positioned on the conveying platform 3 detects the image information of the sample to be measured and transmits the image information to a computer 4;
the computer 4 processes the image information of the sample to be measured, obtains the real-time position of the sample to be measured on the conveyor belt, and calculates the relative position of the sample to be measured and the spectrum probe 2;
the mechanical arm 5 drives the spectrum probe 2 to rapidly move to the position right above the sample to be detected, collects spectrum information of the sample to be detected and transmits the spectrum information to the computer 4;
the computer 4 compares the spectrum information of the collected sample to be tested with the pre-trained machine algorithm model data, and extracts the material type information of the sample to be tested.
The processing and analyzing flow of the image information is as follows:
converting the position information of the sample to be detected into position information in an actual world coordinate system;
calibrating internal and external parameters of the camera, and carrying out distortion correction and coordinate system matrix transformation to obtain the position of a pixel point in an absolute coordinate system;
preprocessing the acquired image, namely filtering and binarizing the acquired image;
and calculating the preprocessed image information to obtain the contour and centroid positions of the sample to be detected.
The comparison flow of the pre-trained machine algorithm model data is as follows:
preprocessing the collected spectrum data, and reserving spectrum effective information;
modeling the preprocessed spectrum data by a combined classification algorithm;
inputting the collected spectrum data into a machine algorithm model to obtain the predicted category of the spectrum data;
and controlling the lower computer to screen and sort the plastics according to the prediction type.
The preprocessing of the spectral data is derivative processing, smoothing processing or principal component analysis.
As described above, the present utility model can be preferably realized.
The embodiments of the present utility model are not limited to the above examples, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principles of the utility model should be made and equivalents should be construed as falling within the scope of the utility model.
Claims (6)
1. The waste plastic identification system based on the near infrared spectrum is characterized by comprising a camera (1), a spectrum probe (2), a conveying platform (3), a computer (4) and a mechanical arm (5);
the spectrum probe (2) is arranged at the end part of the mechanical arm (5); the mechanical arm (5) is used for collecting spectrum information of a sample to be detected on the conveying platform (3) and transmitting the spectrum information to the computer (4);
the camera (1) is used for collecting image information of a designated area and transmitting the image information to the computer (4).
2. The near infrared spectrum-based waste plastic identification system according to claim 1, wherein the camera (1), the spectrum probe (2) and the mechanical arm (5) are respectively connected with a computer (4) in a signal manner.
3. The near infrared spectrum-based waste plastic identification system according to claim 2, wherein the mechanical arm (5) drives the spectrum probe (2) to move in a plane parallel to the conveying platform (3).
4. Waste plastic identification system based on near infrared spectroscopy according to claim 2, characterized in that the camera (1) is located above the transfer platform (3).
5. The near infrared spectrum-based waste plastic identification system according to claim 2, wherein the computer (4) analyzes the information transmitted from the camera (1) and identifies the position of the sample to be measured.
6. The near infrared spectrum based waste plastic identification system of claim 2, wherein the computer (4) sends an action signal to the mechanical arm (5) to drive the spectrum probe (2) to move to a designated area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202321544228.8U CN220271166U (en) | 2023-06-16 | 2023-06-16 | Waste plastic identification system based on near infrared spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202321544228.8U CN220271166U (en) | 2023-06-16 | 2023-06-16 | Waste plastic identification system based on near infrared spectrum |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN220271166U true CN220271166U (en) | 2023-12-29 |
Family
ID=89311466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202321544228.8U Active CN220271166U (en) | 2023-06-16 | 2023-06-16 | Waste plastic identification system based on near infrared spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN220271166U (en) |
-
2023
- 2023-06-16 CN CN202321544228.8U patent/CN220271166U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106733701B (en) | Potato multi-stage combination dysnusia detecting system and detection method | |
| CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
| CN110806736B (en) | Method for detecting quality information of forge pieces of die forging forming intelligent manufacturing production line | |
| CN206139527U (en) | Panoramic vision potato is selected separately and defect detecting device | |
| CN109261539B (en) | Garbage sorting system and method based on visual identification and convolutional neural network | |
| CN110779937A (en) | Casting product internal defect intelligent detection device | |
| CN110458807A (en) | A kind of railroad track defect Machine Vision Inspecting System | |
| CN106238342A (en) | The sorting of panoramic vision Rhizoma Solani tuber osi and defect detecting device and sorting detection method thereof | |
| CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
| CN101949686A (en) | Online nondestructive testing (NDT) method and device for comprehensive internal/external qualities of fruits | |
| CN105651782A (en) | Engine cylinder cover defect automatic detection equipment based on machine vision | |
| CN110302981B (en) | Solid waste sorting online grabbing method and system | |
| CN1485616A (en) | Fowl eggs quality non-destruction automatic detection grading apparatus and process | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN113145492A (en) | Visual grading method and grading production line for pear appearance quality | |
| CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
| CN103785622A (en) | Machine-vision-based part sorting device and method | |
| CN111784688A (en) | Flower automatic grading method based on deep learning | |
| CN207222383U (en) | Plank sorting system | |
| CN115060742A (en) | Printed circuit board defect detection system and method based on visual edge calculation | |
| CN220271166U (en) | Waste plastic identification system based on near infrared spectrum | |
| CN113245222B (en) | Visual real-time detection and sorting system and sorting method for foreign matters in panax notoginseng | |
| CN206139529U (en) | Transparent roller bearing mechanism |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |