CN104849231A - Plastic material on-line recognition method and device - Google Patents
Plastic material on-line recognition method and device Download PDFInfo
- Publication number
- CN104849231A CN104849231A CN201510242919.6A CN201510242919A CN104849231A CN 104849231 A CN104849231 A CN 104849231A CN 201510242919 A CN201510242919 A CN 201510242919A CN 104849231 A CN104849231 A CN 104849231A
- Authority
- CN
- China
- Prior art keywords
- sample
- wavelength
- matrix
- class
- waste
- 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.)
- Granted
Links
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a plastic material on-line recognition method and device. According to the method, an infrared spectrum recognition model with universality is established; the recognition model is established according to the types of raw materials to be recognized, thus the aim of recognizing a specific plastic material from waste plastic garbage is achieved, and environment pollution caused in the garbage treatment process is reduced. Meanwhile, by comprehensive analysis of infrared spectrum data of various materials, feature information is extracted, the volume of spectrum data needing to be measured in the recognition process is reduced, the data processing complexity is reduced, and the recognition speed is improved. The device is realized based on the method, and the device has the capability of dynamic regulation and measurement of wavelength extension, no special requirements on the material types of raw materials which can be treated exist, and the adaptability is wide.
Description
Technical field
The present invention relates to Material Identification technical field, particularly relate to a kind of method and device of plastic material ONLINE RECOGNITION.
Background technology
Along with the development of China's plastics industry and the raising of the level of consumption, plastic products are ubiquitous from industrial and agricultural production to clothing, food, lodging and transportion--basic necessities of life in the application of China.While bringing huge material progress, the generation of plastic refuse also brings a series of society and environmental problem.Waste or used plastics in domestic waste is made up of multi items plastic hybrid usually, and common type comprises: polyethylene terephthalate (PET), tygon (PE), polypropylene (PP), polystyrene (PS), acrylonitrile-butadiene-styrene copolymer (ABS), polyamide (PA), polycarbonate resin (PC), Polyvinylchloride (PVC) etc.
Wherein, PVC suitability for industrialized production is seven more than ten years, its abundant raw material is easy to get, can obtain after mixing with each analog assistant that form is enriched, the goods of different properties, there is superior cost performance, be widely used in industrial and agricultural production, building materials, daily life, the environmental pressure brought is also remarkable especially.Due to height chloride in PVC material, in pure PVC polymer resin, chlorine element accounts for 57% of gross mass, for improving thermal stability and the mechanical property of material, need in process of production to add the stabilizing agent of metalline (as lead, barium, calcium, cadmium or organo-tin compound) and the plastifier based on phthalic ester, multiple environmental problem can be caused to the improper process of PVC discarded object.
At present, the process means of the waste or used plastics that China is common comprise landfill disposal, burn and reclaim the approach such as heat energy, reclaiming process.Under landfill condition, stabilizing agent contained by PVC discarded object and plastifier decomposition can separate out heavy metallic salt and harmful gas, pollute soil and water source.When adopting burning means process waste or used plastics rubbish, not only containing a large amount of chloride in release gas, cause air and water acidification, also have greater risk to generate high toxicity carcinogen dioxin.In addition, the hydrochloric acid that PVC material pyrolytic process produces, to reclaim equiment also just larger harm.Because PVC discarded object brings a series of pollution problem, to identify and PVC material in separating waste, worn plastics is one of the gordian technique realizing garbage harmless, recycling treatment.
At present, identify that the method for waste or used plastics material comprises the means such as artificial cognition, electrostatic separation, gravity floatation, X-ray spectrum analysis, Infrared spectroscopy, wherein Infrared spectroscopy is comparatively advanced, uses technology widely.When infrared radiation and material occur to interact, with the frequency multiplication of molecular vibrational frequency or combine frequently close wavelength location and can there is stronger absorption, due to the difference of chemical analysis and functional group, notable difference is there is in variety classes plastics to the Absorption Characteristics near infrared range, by measuring material in the transmission of near infrared region or reflectance spectrum, can identify plastic type.
When carrying out plastic material identification based on method of infrared spectrophotometry analysis, widely used technology is divided into two classes.The two-dimension spectrum curve of first kind technology measurement of species near infrared region, is contrasted by the characteristic curve of the means such as principal component analysis and pattern-recognition and known materials, judges measured matter composition; Homogenous material intrinsic spectral signature is only depended on during this type of technology identification material, discriminator can be carried out to various material simultaneously, but due to the measurement that needs and the data volume of process large, system realizes more complicated, recognition speed is slow, the requirement to recognition speed when being difficult to meet process waste or used plastics rubbish.Equations of The Second Kind technology is by measuring the radiation intensity of the plastic sample transmission of different wave length position or reflection near infrared range, realize the identification to material, but, this type of technology is poor to the garbage raw material adaptability that complicated components is changeable, especially owing to comprising polytype plastic material in plastic garbage, the identification that this scheme cannot realize particular plastic material in plastic garbage raw material is adopted.
Summary of the invention
The object of this invention is to provide a kind of method and device of plastic material ONLINE RECOGNITION, simplify the complexity of data processing, the identification of particular plastic material can be realized fast and accurately.
The object of the invention is to be achieved through the following technical solutions:
A method for plastic material ONLINE RECOGNITION, the method comprises:
More than one sample selected respectively by steps A, the various material plastic products comprised from waste plastic raw material, and according to plastic material a to be detected, sample is divided into a class and non-a class; Spectral measurement is carried out to each sample, and pre-service is carried out to the results of spectral measurements data obtained;
Step B, within spectra collection scope, with certain sampling interval, the spectroscopic data sequence that resampling obtains one dimension is carried out to the pre-processed results of each sample, calculate the relative ratio of each data point in one dimension spectral sequence, obtain the dual wavelength relative ratio matrix of each sample, calculate the deviation of a class and non-a class sample relative ratio matrix again, obtain deviation matrix;
Step C, sample for non-a class, utilize a proportion threshold value preset and described deviation matrix to compare, obtain corresponding identity matrix; Again according to the identity matrix of each non-a class sample, respectively by element carry out with computing and and computing, obtain sample population identity matrix and statistical matrix; N is chosen to identifying wavelength and often identifying the wavelength ratio of a class sample corresponding to wavelength at this wavelength for a pair from overall recognition matrix and/or statistical matrix
i=1 ~ N;
Step D, waste or used plastics raw material to be measured be placed in two spectral coverage detector identified region and detector operation wavelength is set according to the result in step C, and measuring waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
i, then according to ratio k
iwith ratio
difference and the magnitude relationship of threshold value, judge that current waste or used plastics raw material to be measured is as a class or non-a class, thus realize plastic material ONLINE RECOGNITION.
Described spectral measurement is carried out to each sample, and pre-service is carried out to the results of spectral measurements data obtained comprises:
With the spectral resolution preset and wavelength coverage, spectral measurement is carried out to each sample, gathers reflectance spectrum, obtain corresponding spectral absorption curve;
Spectral manipulation software is utilized to carry out the spectral absorption curve of each sample presetting the level and smooth and standard normalized of counting;
Wherein, the spectral resolution preset is 1 ~ 3nm, and default wavelength coverage is 1100nm ~ 2000nm, and default counting is 5 ~ 13 points.
Describedly within spectra collection scope, with certain sampling interval, the spectroscopic data sequence that resampling obtains one dimension is carried out to the pre-processed results of each sample, calculate the relative ratio of each data point in one dimension spectral sequence, obtain the dual wavelength relative ratio matrix of each sample, calculate the deviation of a class and non-a class sample relative ratio matrix again, obtain deviation matrix; Comprise:
The pre-processed results of each sample is designated as A (λ), and resampling result is designated as A'(k);
The relative ratio matrix K (m, n) of the result of resampling represent be expressed as K (m, n)=A'(m by the spectroscopic data ratio that each sample spectra curve is located at wavelength points m and n)/A'(n); Average by element to the relative ratio matrix of all a class samples, its result is designated as K
a, the relative ratio matrix of each non-a class sample is designated as K
s;
To each non-a class sample, calculate its relative ratio matrix K
swith a class sample relative ratio matrix K
abetween the absolute value of element difference, be designated as the deviation matrix D of this sample
s(m, n), is expressed as: D
s(m, n)=| K
s-K
a|.
The described sample for non-a class, utilizes a proportion threshold value preset and described deviation matrix to compare, obtains corresponding identity matrix; Again according to the identity matrix of each non-a class sample, respectively by element carry out with computing and and computing, obtain sample population identity matrix and statistical matrix and comprise:
For the sample of each non-a class, utilize a proportion threshold value T preset and deviation matrix D
s(m, n) compares, and obtains corresponding identity matrix M
s(m, n), is expressed as:
For the identity matrix M of each non-a class sample
s(m, n), respectively by element carry out with computing and and computing, obtain sample population identity matrix P
0(m, n) and statistical matrix Q
0(m, n), is expressed as:
P
0(m,n)＝∪M
S(m,n)；
Q
0(m,n)＝∑M
S(m,n)。
The described N that chooses from overall recognition matrix or statistical matrix is to identifying wavelength and often identifying the wavelength ratio of a class sample corresponding to wavelength at this wavelength for a pair
comprise:
If overall identity matrix P
0(m, n) is null matrix, then from statistical matrix Q
0search the index value (m, n) that greatest member is corresponding in (m, n), as the 1st to identification wavelength, be designated as
with
and record the wavelength ratio of a class sample at this wavelength place
then, from the sample steps A, removing meets M
sthe sample of (m, n)=1, and the overall identity matrix P recalculating remaining sample
1(m, n) and statistical matrix Q
1(m, n), if overall identity matrix P
1(m, n) is still null matrix, then repeat abovementioned steps, obtains the 2nd to identification wavelength
with
and the ratio of correspondence
and continue removing the selected the 2nd to identification wavelength
with
place meets M
sthe sample of (m, n)=1, to remaining sample calculated population identity matrix P again
2(m, n) and statistical matrix Q
2(m, n); Repeat above-mentioned steps, until obtain N-1 to identification wavelength;
If repeat the overall identity matrix P that above-mentioned steps calculates for the N time
n-1there is one or more nonzero element, then from all nonzero elements, select a pair wavelength
with
as last to identification wavelength, and record a class sample at this wavelength place ratio
Describedly waste or used plastics raw material to be measured to be placed in two spectral coverage detector identified region and detector operation wavelength is set according to the result in step C, and measuring waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
i, then according to ratio k
iwith ratio
difference and the magnitude relationship of threshold value, judge that current waste or used plastics raw material to be measured comprises as a class or non-a class:
Waste or used plastics raw material to be measured to be placed in two spectral coverage detector identified region and according to the operation wavelength that the result in step C arranges detector the 1st time to be
with
and measure waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
1, calculate
if d
1< T, wherein, T is threshold value, then the operation wavelength changing detector the 2nd time is
with
repeat said process;
In above process, if there is d
i> T then judges that this waste or used plastics raw material to be measured is as non-a class; If N is in identification wavelength, all d
iall meet d
i< T, then this waste or used plastics raw material to be measured is a class.
A device for plastic material ONLINE RECOGNITION, this device is arranged on above the conveying device of waste or used plastics raw material to be measured, and it comprises:
Broadband IR source, pre-objective, beam splitter, the optical processing structure that two covers are identical, and for performing the microprocessing unit of preceding method; Wherein, described optical processing structure comprises: the collimator objective set gradually, Tunable filters, collecting objective and infrared sensor;
The infrared light radiation that broadband IR source sends converges in waste or used plastics raw material to be measured surface, and the irreflexive infrared radiation of plastic sample is collected by pre-objective, and converges on the beam splitter plane of incidence; Infrared radiation is divided into two-way after beam splitter internal transmission, respectively from the outgoing of beam splitter two outgoing end faces to optical processing structure;
Incident Tunable filters after collimator objective collimation in optical processing structure; Tunable filters duty, by the control of microprocessing unit, possesses the function of dynamic conditioning through spectral coverage centre wavelength, filters out infrared arrowband monochromatic radiation from the optical radiation of incidence; Filtered monochromatic radiation is received by collecting objective, converges on the photosurface of infrared sensor, completes the conversion of radiation intensity to electric signal;
Microprocessing unit is according to identification wavelength pair, control two-way Tunable filters to adjust successively through centre wavelength, and gather the output signal of two-way infrared eye, calculate incident IR radiation in the intensity of each determined wavelength and relative scale, complete the identification to waste or used plastics raw material to be measured.
Described beam splitter is the single-core fiber beam splitter that two single core multimode optical fibers adopt fused biconical taper processes to make, and comprises an incidence channel and two exit channels, and form y-type structure, optical fiber fusion site is fixed with hardening agent.
Described Tunable filters is acousto-optic tunable filter or liquid crystal tunable harmonic wave device;
The center wavelength tuning scope of described Tunable filters is 1100nm ~ 2000nm, and bandwidth is 5nm ~ 30nm.
Described infrared sensor comprises: infrared photodiode and amplifying circuit, and incident IR radiation is converted to current signal by photodiode, and signal amplitude scope is 0.1nA ~ 1uA, exports after amplifying circuit process with voltage signal.
As seen from the above technical solution provided by the invention, the program sets up infrared spectrum model of cognition based on Infrared Spectrum Technology, the spectroscopic data amount that compression identifying need gather, thus the complexity of reduced data process, realize the identification fast and accurately to particular plastic material.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
The process flow diagram of the method for a kind of plastic material ONLINE RECOGNITION that Fig. 1 provides for the embodiment of the present invention one;
The process flow diagram setting up model of cognition that Fig. 2 provides for the embodiment of the present invention one;
The process flow diagram of the plastic material ONLINE RECOGNITION that Fig. 3 provides for the embodiment of the present invention one;
The curve of spectrum schematic diagram of the PVC that Fig. 4 provides for the embodiment of the present invention one and non-PVC material sample;
The overall identity matrix schematic diagram that Fig. 5 provides for the embodiment of the present invention one;
The numeric distribution of the statistical matrix that Fig. 6 provides for the embodiment of the present invention one and maximal value element index wavelength schematic diagram;
The various samples that Fig. 7 provides for the embodiment of the present invention one are at the schematic diagram of selected wavelength points place reflectance spectrum ratio;
The schematic diagram to motion sample identification that Fig. 8 provides for the embodiment of the present invention two;
The schematic diagram of the device of a kind of plastic material ONLINE RECOGNITION that Fig. 9 provides for the embodiment of the present invention two;
The principle schematic of the beam splitter that Figure 10 provides for the embodiment of the present invention two;
The device of the plastic material ONLINE RECOGNITION that Figure 11 provides for the embodiment of the present invention two realizes the schematic diagram of ONLINE RECOGNITION and sorting waste or used plastics raw material.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on embodiments of the invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to protection scope of the present invention.
The object of the invention is to, for the demand of plastic garbage resource and harmless treatment, study a kind of method and related device of ONLINE RECOGNITION waste plastics material, from containing various common plastics, in waste or used plastics raw material as ethylene glycol terephthalate (PET), tygon (PE), Polyvinylchloride (PVC), polypropylene (PP), polystyrene (PS), acrylonitrile-butadiene-styrene copolymer (ABS), polyamide (PA), polycarbonate resin (PC) etc., identify the sheet or block object of specifying plastic material.Be described in detail below in conjunction with specific embodiment.
Embodiment one
The process flow diagram of the method for a kind of plastic material ONLINE RECOGNITION that Fig. 1 provides for the embodiment of the present invention one.As shown in Figure 1, the method mainly comprises the steps:
Step 11, set up model of cognition; As shown in Figure 2, it mainly comprises:
Steps A, sampling, collection spectroscopic data and spectroscopic data pre-service.
More than one sample selected respectively by the various material plastic products comprised from waste plastic raw material, and according to plastic material a to be detected, sample is divided into a class and non-a class; Spectral measurement is carried out to each sample, and pre-service is carried out to the results of spectral measurements data obtained; In real work, also can classify to sample more after pre-processing.
In the embodiment of the present invention, described spectral measurement is carried out to each sample, and the results of spectral measurements data obtained are carried out pre-service and comprised: with the spectral resolution preset and wavelength coverage, spectral measurement is carried out to each sample, gathers reflectance spectrum, obtain corresponding spectral absorption curve; Spectral manipulation software is utilized to carry out the spectral absorption curve of each sample presetting the level and smooth and standard normalized of counting; Wherein, the spectral resolution preset is 1 ~ 3nm, and default wavelength coverage is 1100nm ~ 2000nm, and default counting is 5 ~ 13 points.
Step B, spectroscopic data process.
1) within spectra collection scope, with certain sampling interval, the spectroscopic data sequence that resampling obtains one dimension is carried out to the pre-processed results of each sample, calculate the relative ratio of each data point in one dimension spectral sequence, obtain the dual wavelength relative ratio matrix of each sample, calculate the deviation of a class and non-a class sample relative ratio matrix again, obtain deviation matrix.
Wherein, the pre-processed results of each sample is designated as A (λ), and resampling result is designated as A'(k), resampling is spaced apart 2 ~ 30nm, is preferably 2nm.
The relative ratio matrix K (m, n) of the result of resampling represent be expressed as K (m, n)=A'(m by the spectroscopic data ratio that each sample spectra curve is located at wavelength points m and n)/A'(n), m, n ∈ k; Average by element to the relative ratio matrix of all a class samples, its result is designated as K
a, the relative ratio matrix of each non-a class sample is designated as K
s.
To each non-a class sample, calculate its relative ratio matrix K
swith a class sample relative ratio matrix K
abetween the absolute value of element difference, be designated as the deviation matrix D of this sample
s(m, n), is expressed as: D
s(m, n)=| K
s-K
a|.
2) for the sample of non-a class, utilize a proportion threshold value preset and described deviation matrix to compare, obtain corresponding identity matrix;
Specifically, for the sample of each non-a class, utilize a threshold value T preset and deviation matrix D
s(m, n) compares, and obtains corresponding identity matrix M
s(m, n), is expressed as:
Owing in the physical sense there is symmetry than value matrix, by the restriction of element index by identity matrix M
s(m, n) is treated to triangle battle array, to simplify subsequent calculations.Described threshold value T span is 0.1 ~ 1.0.Identity matrix intermediate value be 1 element illustrate under the condition of given threshold level T, adopt a pair characteristic wavelength corresponding with element index can distinguish this non-a class sample and a class sample.
Step C, extraction characteristic wavelength.
According to the difference of unlike material sample spectra feature, extract several characteristic wavelength points that can characterize material type, for the identification of plastic material.Wherein every two characteristic wavelengths are formed a pair, according to the result of aforementioned spectral data processing in the embodiment of the present invention, calculate the overall recognition matrix of non-a class sample and statistical matrix to choose N to identifying wavelength and often identifying the wavelength ratio of a class sample at this wavelength place that wavelength is corresponding for a pair
i=1 ~ N.Detailed process is as follows:
1) to the identity matrix of all non-a class samples, respectively by element carry out with computing and and computing, obtain sample population identity matrix P
0(m, n) and statistical matrix Q
0(m, n), is expressed as:
P
0(m,n)＝∪M
S(m,n)；
Q
0(m,n)＝∑M
S(m,n)。
2) if overall identity matrix P
0(m, n) is null matrix (i.e. P
0(m, n)=0), then from statistical matrix Q
0search the index value (m, n) that greatest member is corresponding in (m, n), as the 1st to identification wavelength, be designated as
with
and record the wavelength ratio of a class sample at this wavelength place
then, from the sample steps A, removing meets M
sthe sample of (m, n)=1, by aforementioned 1) in formula recalculate overall identity matrix and the statistical matrix of remaining sample, be designated as P respectively
1(m, n) and Q
1(m, n), if overall identity matrix P
1(m, n) is still null matrix, then repeat abovementioned steps, obtains the 2nd to identification wavelength
with
and the ratio of correspondence
and continue removing the selected the 2nd to identification wavelength
with
place meets M
sthe sample of (m, n)=1, to remaining sample calculated population identity matrix P again
2(m, n) and statistical matrix Q
2(m, n); Repeat above-mentioned steps, until obtain N-1 to identification wavelength (namely until overall identity matrix P
n-1there is one or more nonzero element).
3) if repeat the overall identity matrix P that calculates for the N time of above-mentioned steps
n-1there is one or more nonzero element, then from all nonzero elements, select a pair wavelength
with
as last to identification wavelength, and record a class sample at this wavelength place ratio
Step 12, plastic material ONLINE RECOGNITION.As shown in Figure 3, main process is as follows:
Waste or used plastics raw material to be measured to be placed in two spectral coverage detector identified region and detector operation wavelength is set according to the result in step C, and measuring waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
i, then according to ratio k
iwith ratio
difference and the magnitude relationship of threshold value, judge that current waste or used plastics raw material to be measured is as a class or non-a class, thus realize plastic material ONLINE RECOGNITION; Specifically:
Waste or used plastics raw material to be measured to be placed in two spectral coverage detector identified region and according to the operation wavelength that the result in step C arranges detector the 1st time to be
with
and measure waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
1, calculate
if d
1< T, wherein, T is threshold value (consistent with aforesaid threshold values T), then the operation wavelength changing detector the 2nd time is
with
repeat said process;
In above process, if there is d
i> T then judges that this waste or used plastics raw material to be measured is as non-a class; If N is in identification wavelength, all d
iall meet d
i< T, then this waste or used plastics raw material to be measured is a class.
For the ease of understanding, below in conjunction with two concrete examples, the present invention is described further.
Example one
In this example for identify and sorting comprise PVC plastic in the waste or used plastics raw material of PVC and ABS two kinds of materials (namely appointment PVC material be aforesaid plastic material a), implementation process comprises following steps:
1) from waste or used plastics raw material, 26 samples are collected, adopt etalon spectrometers, to each sample with spectral resolution 3nm, wavelength coverage 1100nm ~ 2000nm, measures reflection spectrum curve respectively, then 5 level and smooth and standard normalizeds are carried out with spectral manipulation software, obtain the curve of spectrum of each sample, and according to PVC and non-PVC material, sample is classified, as shown in Figure 4, wherein with the curve of circles mark for PVC sample spectra, with square mark curve for ABS sample spectra.
2) to the spectroscopic data of collected specimens with after the resampling of 2nm interval, calculate the dual wavelength ratio matrix of PVC sample and average and obtain typical ratio matrix K
pVC.Dual wavelength ratio matrix K is calculated to each ABS sample
s, and difference calculation deviation matrix:
D
S(m,n)＝|K
S-K
PVC|
Get threshold value T=0.5 and calculate sample identification matrix M
s(m, n):
For the identity matrix M of each non-a class sample
s(m, n), respectively by element carry out with computing and and computing, obtain sample population identity matrix P
0(m, n) and statistical matrix Q
0(m, n), is expressed as:
P
0(m,n)＝∪M
S(m,n)；
Q
0(m,n)＝∑M
S(m,n)。
As shown in Figure 5, wherein black picture element corresponds to P to the overall identity matrix of gained
0(m, n) nonzeros, the index value determination determined wavelength according to non-zero entry vegetarian refreshments in the A of region is
with
and record a class sample at this wavelength place ratio.
The ONLINE RECOGNITION of PVC material then can be realized again according to the mode of abovementioned steps 12.
Example two
From multiple plastic material in this example, comprise PVC, ABS, PA, PE, PET, PP, PS, identify in the waste or used plastics raw material of formation and sub-elect the raw material of PVC material, implementation process comprises following steps:
From waste or used plastics raw material, choose 70 samples altogether, measure spectrum data, and classify, spectral measurement and process parameter consistent with precedent, repeat no more.
Based on sample spectral data, select threshold value T=0.25 calculated population identity matrix P
0(m, n) and statistical matrix Q
0(m, n).Overall identity matrix P in this example
0(m, n) is full null matrix, then Corpus--based Method matrix Q
0(m, n) choosing then first to measurement wavelength.Numeric distribution and the maximal value element index wavelength of statistical matrix are shown in Fig. 6, select first to identify wavelength pair accordingly:
with
typical ratio
employing first is identified that wavelength is to the sample that can not correctly identify, calculated population identity matrix P again
1(m, n), choosing second according to matrix non-zero element index to identification wavelength is
with
typical ratio
as shown in Figure 7, for various material sample, at selected wavelength points place, (Fig. 7 a is
With
Fig. 7 b is
With
Time) reflectance spectrum ratio, rectangle marked is PVC material sample ratio, spider lable is non-PVC material sample ratio, from data, adopts above-mentioned two can identify PVC material from the mixed material comprising ABS, PA, PA66, PET, PS, PE, PP and PVC component to measurement wavelength.
The main tool of such scheme of the embodiment of the present invention has the following advantages:
1) set up a kind of infrared spectrum model of cognition with versatility, according to the material kind identifying raw material, set up model of cognition, reach the object identifying particular plastic material from waste or used plastics rubbish, reduce the environmental pollution that garbage processing procedure causes.
2) by the comprehensive ir data analyzing various material, characteristic information extraction, reduces the spectroscopic data amount that identifying need be measured, and reduces data processing complexity, improves recognition speed.
Through the above description of the embodiments, those skilled in the art can be well understood to above-described embodiment can by software simulating, and the mode that also can add necessary general hardware platform by software realizes.Based on such understanding, the technical scheme of above-described embodiment can embody with the form of software product, it (can be CD-ROM that this software product can be stored in a non-volatile memory medium, USB flash disk, portable hard drive etc.) in, comprise some instructions and perform method described in each embodiment of the present invention in order to make a computer equipment (can be personal computer, server, or the network equipment etc.).
Embodiment two
The embodiment of the present invention provides a kind of device of plastic material ONLINE RECOGNITION, this device is arranged on above the conveying device of waste or used plastics raw material to be measured, waste or used plastics raw material to be measured passes through the surveyed area of this device under the drive of conveying device, detector will not change to the observation area of sample in the same time, as shown in Figure 8.Because the reflectivity of raw material surface diverse location there are differences, the bulk strength of raw material reflectance spectrum will change with observation area change.The content analyzing previous embodiment one is known, during by the radiation intensity identification raw material material of measuring multiple characteristic wavelength point, need ensure that the measured zone of two wavelength points in often pair of characteristic wavelength is consistent, make dual wavelength radiation intensity rate correctly reflect the spectral signature of material.And due to the right ratio data of each wavelength that calculates independent in recognition methods, between each stack features wavelength, observation position changes, can not have an impact to identification accuracy.The device of a kind of plastic material ONLINE RECOGNITION provided in the embodiment of the present invention is infrared double-wave length pick-up unit, based on paired expansion and the dynamic conditioning of tunable filter part complete twin detector operation wavelength, and use beam splitter that incident radiation is divided into two-way by energy proportion, eliminate by sample motion the impact identifying accuracy.By the timesharing measurement capability of comprehensive utilization tunable filter part and the energy segmentation ability of beam splitter, reach the object of the mixed species plastics of rapid movement being carried out to ONLINE RECOGNITION.
As shown in Figure 9, this device mainly comprises:
The identical optical processing structure of broadband IR source 8, pre-objective 1, beam splitter 2, two cover, and for performing the microprocessing unit 7 of method described in embodiment one in previous existence; Wherein, described optical processing structure comprises: the collimator objective (3a, 3b) set gradually, Tunable filters (4a, 4b), collecting objective (5a, 5b) and infrared sensor (6a, 6b);
The infrared light radiation 9 that broadband IR source 8 sends converges in waste or used plastics raw material 11 to be measured surface, and the irreflexive infrared radiation 10 of plastic sample is collected by pre-objective 1, and converges on beam splitter 2 plane of incidence; Infrared radiation is divided into two-way after beam splitter internal transmission, respectively from the outgoing of beam splitter two outgoing end faces to optical processing structure;
Incident Tunable filters (4a, 4b) after collimator objective (3a, 3b) collimation in optical processing structure; Tunable filters (4a, 4b) duty, by the control of microprocessing unit 7, possesses the function of dynamic conditioning through spectral coverage centre wavelength, filters out infrared arrowband monochromatic radiation from the optical radiation of incidence; Filtered monochromatic radiation is received by collecting objective (5a, 5b), converges on the photosurface of infrared sensor (6a, 6b), completes the conversion of radiation intensity to electric signal;
Microprocessing unit 7 is according to identification wavelength pair, control two-way Tunable filters (4a, 4b) to adjust successively through centre wavelength, and gather the output signal of two-way infrared eye (6a, 6b), calculate incident IR radiation in the intensity of each determined wavelength and relative scale, complete the identification to waste or used plastics raw material to be measured.
In the embodiment of the present invention, the principle of described beam splitter 2 as shown in Figure 10, described beam splitter 2 is the single-core fiber beam splitter that two single core multimode optical fibers adopt fused biconical taper processes to make, comprise an incidence channel and two exit channels, form y-type structure, optical fiber fusion site is fixed with hardening agent, ensures that three passage relative position relations are fixed, to eliminate because External Force Acting causes beam splitter structure to change the splitting ratio fluctuation of generation, ensure to measure accurately.Described single core multimode optical fiber core diameter is 0.6mm ~ 1.0mm, and be preferably 1.0mm, numerical aperture is 0.39 ~ 0.6, is preferably 0.48.Owing to adopting single-core fiber, enter the infrared radiation of fibre core via the multiple total reflection in transmitting procedure, enter in two exit channels at random, therefore entered the equal equal proportion of infrared radiation of beam splitter by difference on incident end face be assigned to two outgoing end faces, thus ensure that infrared radiation that two-way infrared eye collects is from sample surfaces the same area, improve the accuracy that sample dual wavelength ratio is measured, simplify the resetting difficulty of dual wavelength detector.In addition, in the embodiment of the present invention, beam splitter prism or light splitting plain film also can be used as beam splitter member, as long as can above-mentioned functions be realized.
In the embodiment of the present invention, the center wavelength tuning scope of described Tunable filters (4a, 4b) is 1100nm ~ 2000nm, passband width is 5nm ~ 30nm, the centre wavelength of optical filter free transmission range can under the control of external electric signal dynamic conditioning, to filter out the monochromatic component of sample reflection radiation at specified wavelength place.Described Tunable filters can be acousto-optic tunable filter or liquid crystal tunable harmonic wave device; This two classes wave filter all has without sports apparatus, and the advantage that spectral coverage switch speed is fast can complete the adjustment through spectral coverage in 10ms, thus reaches the spectral scan speed of hundreds of times.
In the embodiment of the present invention, described infrared sensor (6a, 6b) comprising: infrared photodiode and amplifying circuit, incident IR radiation is converted to current signal by photodiode, and signal amplitude scope is 0.1nA ~ 1uA, exports after amplifying circuit process with voltage signal.Amplifying circuit adopts high-gain I-V conversion plan, and gain amplifier is 10
7-10
9v/A, fast response time, exports without time delay, realizes the Quick Measurement to faint radiation signal.
Microprocessing unit 7 in the embodiment of the present invention can adopt industrial computer or Implementation of Embedded System, as long as can realize the method for step 12 described in previous embodiment one.In addition, the specific implementation of the function that this microprocessing unit 7 realizes has a detailed description in embodiment one, therefore here repeats no more.
For the ease of understanding, below in conjunction with two concrete examples, the present invention is described further.Two examples are below corresponding with the example of two in embodiment one, and the process of establishing of model of cognition refers to the content of two examples in embodiment one, only describe herein and utilize this device to carry out the process identified.
Example one
The device (infrared double-wave length pick-up unit) that Figure 11 is the plastic material ONLINE RECOGNITION provided based on the embodiment of the present invention realizes the schematic diagram of ONLINE RECOGNITION and sorting waste or used plastics raw material.
Infrared double-wave length pick-up unit is arranged on top in the middle part of travelling belt, setting height(from bottom) 500mm.The pre-objective field angle of pick-up unit is 3 °, and viewing plane is positioned at travelling belt surface.The halogen tungsten lamp that broadband IR source (light source module) is 50W, the field of view of pre-objective is illuminated in the broadband radiation that light source sends after converging.According to the result (example one see in embodiment one) to the sampling of waste or used plastics raw material and modeling, the running parameter of infrared double-wave length pick-up unit is set to by computer for controlling: determined wavelength 1736nm, 1680nm, typical ratio k
pVC=0.7, recognition threshold T=0.5.
Waste or used plastics raw material is controlled by feeding mechanism, fall to conveyor belt surface one by one, conveying belt moves with the speed of 3m/s, drive raw material through field of illumination, its surface reflection is detected device and collects, by measuring the radiation intensity of two selected characteristic wavelength points, ratio calculated k, and according to selected typical ratio k
pVCidentify whether as PVC plastic with threshold value T.During dual wavelength ratio 0.2≤k≤1.2 of sample, be identified as PVC material, otherwise be then identified as non-PVC material (ABS), recognition result is sent to computer for controlling.The jet execution module of control module and then control conveying belt end, release pressure-air, kicks down the PVC raw material arriving point favored area in PVC collecting box.
Example two
The structure adopted and aforementioned exemplary one similar, does not repeat them here.According to the result (example two of previous embodiment one) to the sampling of waste or used plastics raw material and modeling, the running parameter of double UV check device is set to
T＝0.25。
After raw material to be measured enters measured zone, dual wavelength detector is first to measure wavelength
calculate spectral ratio k
1, and and standard value
relatively, exceed threshold interval and be then identified as non-PVC material; Otherwise be switched to measurement wavelength
calculate spectral ratio k
2, and and standard value
relatively, exceed threshold interval and be identified as non-PVC material; As twice threshold judges all to pass through, then sample is PVC material.After identification completes, recognition result is sent to control module to complete point selection operation to PVC by pick-up unit.
Embodiment of the present invention such scheme is except having the advantage described in previous embodiment one, and also tool has the following advantages:
1) this device possesses the ability of dynamic conditioning and expansion measurement wavelength, to processing the material type of raw material without particular/special requirement, wide adaptability.
2) adopt single-core fiber beam splitter segmentation incident radiation, realize dual-wavelength measurement, ensure that two-way infrared sensor viewing area is completely the same, improve the accuracy of spectral measurement.
3) infrared sensor adopts infrared photodiode and high-gain I-V amplifying circuit, realizes the real-time measurement to faint radiation signal, and spectral measurement speed is fast, reaches the object of quick ONLINE RECOGNITION.
The above; be only the present invention's preferably embodiment, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.
Claims (10)
1. a method for plastic material ONLINE RECOGNITION, is characterized in that, the method comprises:
More than one sample selected respectively by steps A, the various material plastic products comprised from waste plastic raw material, and according to plastic material a to be detected, sample is divided into a class and non-a class; Spectral measurement is carried out to each sample, and pre-service is carried out to the results of spectral measurements data obtained;
Step B, within spectra collection scope, with certain sampling interval, the spectroscopic data sequence that resampling obtains one dimension is carried out to the pre-processed results of each sample, calculate the relative ratio of each data point in one dimension spectral sequence, obtain the dual wavelength relative ratio matrix of each sample, calculate the deviation of a class and non-a class sample relative ratio matrix again, obtain deviation matrix;
Step C, sample for non-a class, utilize a proportion threshold value preset and described deviation matrix to compare, obtain corresponding identity matrix; Again according to the identity matrix of each non-a class sample, respectively by element carry out with computing and and computing, obtain sample population identity matrix and statistical matrix; N is chosen to identifying wavelength and often identifying the wavelength ratio of a class sample corresponding to wavelength at this wavelength for a pair from overall recognition matrix and/or statistical matrix
i=1 ~ N;
Step D, waste or used plastics raw material to be measured be placed in two spectral coverage detector identified region and detector operation wavelength is set according to the result in step C, and measuring waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
i, then according to ratio k
iwith ratio
difference and the magnitude relationship of threshold value, judge that current waste or used plastics raw material to be measured is as a class or non-a class, thus realize plastic material ONLINE RECOGNITION.
2. method according to claim 1, is characterized in that, describedly carries out spectral measurement to each sample, and carries out pre-service to the results of spectral measurements data obtained and comprise:
With the spectral resolution preset and wavelength coverage, spectral measurement is carried out to each sample, gathers reflectance spectrum, obtain corresponding spectral absorption curve;
Spectral manipulation software is utilized to carry out the spectral absorption curve of each sample presetting the level and smooth and standard normalized of counting;
Wherein, the spectral resolution preset is 1 ~ 3nm, and default wavelength coverage is 1100nm ~ 2000nm, and default counting is 5 ~ 13 points.
3. method according to claim 1, it is characterized in that, describedly within spectra collection scope, with certain sampling interval, the spectroscopic data sequence that resampling obtains one dimension is carried out to the pre-processed results of each sample, calculate the relative ratio of each data point in one dimension spectral sequence, obtain the dual wavelength relative ratio matrix of each sample, calculate the deviation of a class and non-a class sample relative ratio matrix again, obtain deviation matrix; Comprise:
The pre-processed results of each sample is designated as A (λ), and resampling result is designated as A'(k);
The relative ratio matrix K (m, n) of the result of resampling represent be expressed as K (m, n)=A'(m by the spectroscopic data ratio that each sample spectra curve is located at wavelength points m and n)/A'(n); Average by element to the relative ratio matrix of all a class samples, its result is designated as K
a, the relative ratio matrix of each non-a class sample is designated as K
s;
To each non-a class sample, calculate its relative ratio matrix K
swith a class sample relative ratio matrix K
abetween the absolute value of element difference, be designated as the deviation matrix D of this sample
s(m, n), is expressed as: D
s(m, n)=| K
s-K
a|.
4. method according to claim 1, is characterized in that, the described sample for non-a class, utilizes a proportion threshold value preset and described deviation matrix to compare, obtains corresponding identity matrix; Again according to the identity matrix of each non-a class sample, respectively by element carry out with computing and and computing, obtain sample population identity matrix and statistical matrix and comprise:
For the sample of each non-a class, utilize a proportion threshold value T preset and deviation matrix D
s(m, n) compares, and obtains corresponding identity matrix M
s(m, n), is expressed as:
For the identity matrix M of each non-a class sample
s(m, n), respectively by element carry out with computing and and computing, obtain sample population identity matrix P
0(m, n) and statistical matrix Q
0(m, n), is expressed as:
P
0(m,n)＝∪M
S(m,n)；
Q
0(m,n)＝ΣM
S(m,n)。
5. method according to claim 1, is characterized in that, the described N that chooses from overall recognition matrix or statistical matrix is to identifying wavelength and often identifying the wavelength ratio of a class sample corresponding to wavelength at this wavelength for a pair
comprise:
If overall identity matrix P
0(m, n) is null matrix, then from statistical matrix Q
0search the index value (m, n) that greatest member is corresponding in (m, n), as the 1st to identification wavelength, be designated as
with
and record the wavelength ratio of a class sample at this wavelength place
then, from the sample steps A, removing meets M
sthe sample of (m, n)=1, and the overall identity matrix P recalculating remaining sample
1(m, n) and statistical matrix Q
1(m, n), if overall identity matrix P
1(m, n) is still null matrix, then repeat abovementioned steps, obtains the 2nd to identification wavelength
with
and the ratio of correspondence
and continue removing the selected the 2nd to identification wavelength
with
place meets M
sthe sample of (m, n)=1, to remaining sample calculated population identity matrix P again
2(m, n) and statistical matrix Q
2(m, n); Repeat above-mentioned steps, until obtain N-1 to identification wavelength;
If repeat the overall identity matrix P that above-mentioned steps calculates for the N time
n-1there is one or more nonzero element, then from all nonzero elements, select a pair wavelength
with
as last to identification wavelength, and record a class sample at this wavelength place ratio
6. method according to claim 5, it is characterized in that, describedly waste or used plastics raw material to be measured to be placed in two spectral coverage detector identified region and detector operation wavelength is set according to the result in step C, and measuring waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
i, then according to ratio k
iwith ratio
difference and the magnitude relationship of threshold value, judge that current waste or used plastics raw material to be measured comprises as a class or non-a class:
Waste or used plastics raw material to be measured to be placed in two spectral coverage detector identified region and according to the operation wavelength that the result in step C arranges detector the 1st time to be
with
and measure waste or used plastics raw material diffuse reflection radiation to be measured first to the intensity rate k identifying wavelength place
1, calculate
if d
1< T, wherein, T is threshold value, then the operation wavelength changing detector the 2nd time is
with
repeat said process;
In above process, if there is d
i> T then judges that this waste or used plastics raw material to be measured is as non-a class; If N is in identification wavelength, all d
iall meet d
i< T, then this waste or used plastics raw material to be measured is a class.
7. a device for plastic material ONLINE RECOGNITION, is characterized in that, this device is arranged on above the conveying device of waste or used plastics raw material to be measured, and it comprises:
Broadband IR source, pre-objective, beam splitter, the optical processing structure that two covers are identical, and the microprocessing unit of method described in any one of 1-6 is required for enforcement of rights; Wherein, described optical processing structure comprises: the collimator objective set gradually, Tunable filters, collecting objective and infrared sensor;
The infrared light radiation that broadband IR source sends converges in waste or used plastics raw material to be measured surface, and the irreflexive infrared radiation of plastic sample is collected by pre-objective, and converges on the beam splitter plane of incidence; Infrared radiation is divided into two-way after beam splitter internal transmission, respectively from the outgoing of beam splitter two outgoing end faces to optical processing structure;
Incident Tunable filters after collimator objective collimation in optical processing structure; Tunable filters duty, by the control of microprocessing unit, possesses the function of dynamic conditioning through spectral coverage centre wavelength, filters out infrared arrowband monochromatic radiation from the optical radiation of incidence; Filtered monochromatic radiation is received by collecting objective, converges on the photosurface of infrared sensor, completes the conversion of radiation intensity to electric signal;
Microprocessing unit is according to identification wavelength pair, control two-way Tunable filters to adjust successively through centre wavelength, and gather the output signal of two-way infrared eye, calculate incident IR radiation in the intensity of each determined wavelength and relative scale, complete the identification to waste or used plastics raw material to be measured.
8. device according to claim 7, it is characterized in that, described beam splitter is the single-core fiber beam splitter that two single core multimode optical fibers adopt fused biconical taper processes to make, and comprises an incidence channel and two exit channels, form y-type structure, optical fiber fusion site is fixed with hardening agent.
9. device according to claim 7, is characterized in that, described Tunable filters is acousto-optic tunable filter or liquid crystal tunable harmonic wave device;
The center wavelength tuning scope of described Tunable filters is 1100nm ~ 2000nm, and bandwidth is 5nm ~ 30nm.
10. device according to claim 7, it is characterized in that, described infrared sensor comprises: infrared photodiode and amplifying circuit, and incident IR radiation is converted to current signal by photodiode, signal amplitude scope is 0.1nA ~ 1uA, exports after amplifying circuit process with voltage signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510242919.6A CN104849231B (en) | 2015-05-13 | 2015-05-13 | A kind of method and device of plastic material ONLINE RECOGNITION |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510242919.6A CN104849231B (en) | 2015-05-13 | 2015-05-13 | A kind of method and device of plastic material ONLINE RECOGNITION |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104849231A true CN104849231A (en) | 2015-08-19 |
| CN104849231B CN104849231B (en) | 2017-11-07 |
Family
ID=53849039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510242919.6A Expired - Fee Related CN104849231B (en) | 2015-05-13 | 2015-05-13 | A kind of method and device of plastic material ONLINE RECOGNITION |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104849231B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105775502A (en) * | 2016-03-15 | 2016-07-20 | 上海理工大学 | Dustbin distinguishing objects |
| CN106872393A (en) * | 2017-04-14 | 2017-06-20 | 北京国科虹谱光电技术有限公司 | Target materials recognition methods and device in a kind of plastic refuse |
| CN108181258A (en) * | 2017-12-19 | 2018-06-19 | 东风汽车集团有限公司 | The identification method of plastics trademarks |
| CN108335295A (en) * | 2018-02-08 | 2018-07-27 | 吴永慧 | Hospital ward brightness self-adaptive regulating |
| CN110898890A (en) * | 2019-11-28 | 2020-03-24 | 广州广电计量检测股份有限公司 | Grinding and crushing device and grinding method |
| CN111163873A (en) * | 2017-09-01 | 2020-05-15 | 陶朗分选有限责任公司 | Classification method and device |
| CN112265753A (en) * | 2020-09-02 | 2021-01-26 | 北京致感致联科技有限公司 | Intelligent residential district rubbish discernment classification system |
| CN117169141A (en) * | 2023-11-03 | 2023-12-05 | 中国电力科学研究院有限公司 | Cable insulation material type identification and performance deduction method and device thereof |
| CN117688466A (en) * | 2024-02-02 | 2024-03-12 | 佛山市绿能环保有限公司 | Garbage class grabbing, classifying and identifying method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0493239A1 (en) * | 1990-12-20 | 1992-07-01 | Microfilm Archimed Inc. | Machine for sorting plastic bottles as a function of their plastic composition in order to recycle the same |
| US20010045518A1 (en) * | 2000-04-27 | 2001-11-29 | Sommer Edward J. | Method and apparatus for near-infrared sorting of recycled plastic waste |
| JP2002267599A (en) * | 2001-03-07 | 2002-09-18 | Mitsubishi Heavy Ind Ltd | Quality of material identification system for plastic and quality of material identification/assortment system for plastic |
| CN1463359A (en) * | 2001-03-27 | 2003-12-24 | 松下电器产业株式会社 | Method and appts. for identifying plastic |
| CN1524178A (en) * | 2001-11-28 | 2004-08-25 | ��ʽ�������»����������� | Plastic identifying method |
| CN1826517A (en) * | 2003-07-18 | 2006-08-30 | 松下电器产业株式会社 | Device and method of discrimating plastic |
| CN103480586A (en) * | 2013-10-08 | 2014-01-01 | 合肥美亚光电技术股份有限公司 | Dual infrared online plastic material sorting device |
-
2015
- 2015-05-13 CN CN201510242919.6A patent/CN104849231B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0493239A1 (en) * | 1990-12-20 | 1992-07-01 | Microfilm Archimed Inc. | Machine for sorting plastic bottles as a function of their plastic composition in order to recycle the same |
| US20010045518A1 (en) * | 2000-04-27 | 2001-11-29 | Sommer Edward J. | Method and apparatus for near-infrared sorting of recycled plastic waste |
| JP2002267599A (en) * | 2001-03-07 | 2002-09-18 | Mitsubishi Heavy Ind Ltd | Quality of material identification system for plastic and quality of material identification/assortment system for plastic |
| CN1463359A (en) * | 2001-03-27 | 2003-12-24 | 松下电器产业株式会社 | Method and appts. for identifying plastic |
| CN1524178A (en) * | 2001-11-28 | 2004-08-25 | ��ʽ�������»����������� | Plastic identifying method |
| CN1826517A (en) * | 2003-07-18 | 2006-08-30 | 松下电器产业株式会社 | Device and method of discrimating plastic |
| CN103480586A (en) * | 2013-10-08 | 2014-01-01 | 合肥美亚光电技术股份有限公司 | Dual infrared online plastic material sorting device |
Non-Patent Citations (4)
| Title |
|---|
| 孟玲 等: "红外光谱仪在鉴定塑料材质的应用", 《广东化工》 * |
| 张毅民 等: "基于近红外特征波长反射率比值法鉴别塑料", 《现代化工》 * |
| 欧育湘 等: "鉴别废旧塑料的先进近红外技术", 《化工进展》 * |
| 郭慧玲 等: "基于近红外光谱技术的常见塑料快速分类方法研究", 《现代科学仪器》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105775502A (en) * | 2016-03-15 | 2016-07-20 | 上海理工大学 | Dustbin distinguishing objects |
| CN106872393A (en) * | 2017-04-14 | 2017-06-20 | 北京国科虹谱光电技术有限公司 | Target materials recognition methods and device in a kind of plastic refuse |
| CN106872393B (en) * | 2017-04-14 | 2019-08-06 | 北京国科虹谱光电技术有限公司 | Target materials recognition methods and device in a kind of plastic refuse |
| CN111163873A (en) * | 2017-09-01 | 2020-05-15 | 陶朗分选有限责任公司 | Classification method and device |
| CN111163873B (en) * | 2017-09-01 | 2022-06-28 | 陶朗分选有限责任公司 | Classification method and device |
| CN108181258A (en) * | 2017-12-19 | 2018-06-19 | 东风汽车集团有限公司 | The identification method of plastics trademarks |
| CN108335295A (en) * | 2018-02-08 | 2018-07-27 | 吴永慧 | Hospital ward brightness self-adaptive regulating |
| CN110898890A (en) * | 2019-11-28 | 2020-03-24 | 广州广电计量检测股份有限公司 | Grinding and crushing device and grinding method |
| CN112265753A (en) * | 2020-09-02 | 2021-01-26 | 北京致感致联科技有限公司 | Intelligent residential district rubbish discernment classification system |
| CN117169141A (en) * | 2023-11-03 | 2023-12-05 | 中国电力科学研究院有限公司 | Cable insulation material type identification and performance deduction method and device thereof |
| CN117169141B (en) * | 2023-11-03 | 2024-02-23 | 中国电力科学研究院有限公司 | Cable insulation material type identification and performance deduction method and device thereof |
| CN117688466A (en) * | 2024-02-02 | 2024-03-12 | 佛山市绿能环保有限公司 | Garbage class grabbing, classifying and identifying method and system |
| CN117688466B (en) * | 2024-02-02 | 2024-04-30 | 佛山市绿能环保有限公司 | Garbage class grabbing, classifying and identifying method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104849231B (en) | 2017-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104849231A (en) | Plastic material on-line recognition method and device | |
| WO1998019800A1 (en) | Application of raman spectroscopy to identification and sorting of post-consumer plastics for recycling | |
| JP5265632B2 (en) | Plastic identification device and plastic identification method | |
| Safavi et al. | Sorting of polypropylene resins by color in MSW using visible reflectance spectroscopy | |
| Ahmad | A new technology for automatic identification and sorting of plastics for recycling | |
| JP5290466B2 (en) | Brominated flame retardant determining method, brominated flame retardant determining device, recycling method, and recycling device | |
| Xiao et al. | Development of an automatic sorting robot for construction and demolition waste | |
| CN106872393B (en) | Target materials recognition methods and device in a kind of plastic refuse | |
| CN103376251A (en) | Portable Raman spectrum measuring device and system for quickly detecting article | |
| US6433338B1 (en) | Method and device for identification of a type of material in an object and utilization therefor | |
| CN101281122A (en) | Apparatus for measuring optical parameter spectrum and quantitative method for eliminating diffuse transmission influence | |
| CN1221799C (en) | Identifying recycable carpet materials using hand-held infrared spectrometer | |
| Gülcan et al. | Evaluation of complex copper ore sorting: Effect of optical filtering on particle recognition | |
| JP2011226821A (en) | Identification device and identification method | |
| JPH08300354A (en) | Plastic classifying apparatus | |
| JP4932053B1 (en) | Raman scattering signal acquisition device, Raman scattering identification device, Raman scattering signal acquisition method, and Raman scattering identification method | |
| CN106778815A (en) | Wheat quality THz spectral classification methods based on DS evidence theories | |
| CN108582580B (en) | Plastic online sorting device based on near-infrared technology and sorting method thereof | |
| Kawazumi et al. | High-performance recycling system for waste plastics using Raman identification | |
| Cesetti et al. | Waste processing: new near infrared technologies for material identification and selection | |
| Palmieri et al. | Automatic detection and classification of EOL-concrete and resulting recovered products by hyperspectral imaging | |
| KR20130019818A (en) | Apparatus for color discrimination in visible light band and plastic classification system using thereof | |
| JP5143175B2 (en) | Identification method and identification device based on Raman scattering, and Raman scattering spectrum measurement method and measurement device | |
| CN203241352U (en) | Near-infrared grain sorting device | |
| CA2319315C (en) | Method and device for identification of a type of material in an object and utilization therefor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171107 Termination date: 20190513 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |