Construction waste separation system

Abstract

The invention discloses a construction waste separation system, which relates to the field of waste separation, and comprises a separator main body, an intelligent separation module, a temperature acquisition module and a light acquisition module; the construction waste separation system can ensure that the detected temperature of an object is consistent with the establishment temperature of an existing spectrum analysis model in the system through the temperature acquisition module and the temperature adjustment module, thereby avoiding data abnormalities due to changes in the detected temperature; the light acquisition module and the light adjustment module can ensure that the ambient light of the object and the output light power of an infrared laser transmitter are consistent with the establishment conditions of the existing spectrum analysis model in the system, thereby avoiding data abnormalities due to changes in the detection environment, thereby improving the accuracy and precision of waste detection, reducing or avoiding the need for subsequent manual re-sorting; different construction wastes are discharged through different discharge ports, thereby achieving fine classification of construction wastes and waste utilization, improving enterprise production efficiency, and increasing the utilization rate of construction wastes.

Description

Technical Field

[0001] The invention relates to waste separation technology, in particular to a construction waste separation system. Background Art

[0002] Construction waste refers to the slag, abandoned soil, abandoned materials, residual mud and other wastes generated during the construction, laying, demolition and repair of various buildings, structures, pipe networks, etc. by construction units or individuals. At present, the amount of construction waste in my country has accounted for 30%-40% of the total urban waste. Based on the standard of 500-600 tons / 10,000 square meters, by 2020, my country will have an additional construction area of ​​about 30 billion square meters, and the newly generated construction waste will be a shocking number. However, most of the construction waste is transported to the suburbs or villages by construction units without any treatment, and is piled up or landfilled in the open air, consuming a large amount of construction funds such as land acquisition fees and garbage removal fees. At the same time, the spillage and dust, ash and sand flying during the removal and stacking process have caused serious environmental pollution. At present, the main method of treating construction waste in my country is to bury it underground. Its harm lies in: first of all, it occupies a large amount of land. Take Beijing as an example. According to relevant data, due to the demolition of existing buildings before the construction of the Olympic project and the construction of new construction sites, Beijing has to set up 20 to 30 construction waste disposal sites every year, which has caused considerable land pressure. Secondly, it causes serious environmental pollution. The construction glue, coatings and paints in construction waste are not only high-molecular polymer materials that are difficult to biodegrade, but also contain harmful heavy metal elements. These wastes are buried underground, which will cause groundwater pollution and directly endanger the lives of surrounding residents. Thirdly, it destroys the soil structure and causes surface subsidence. The current landfill method is: after 8 meters of garbage is buried, a 2-meter soil layer is added, but it is basically difficult to grow vegetation on the soil layer. The surface of the landfill area will sink and sink, and it will take a long time to reach a stable state. Recycling technology can make construction waste zero waste.

[0003] At present, waste separation is done by human eyes to judge the types of construction waste, which has low accuracy and high cost. The existing waste separation system cannot refine the powder according to the different types of construction waste during use, which will cause the construction waste that could have been further utilized to be mistakenly screened out, and it is impossible to distinguish the mixed powder, resulting in the waste of pure powder and the incorrect recycling of mixed powder. Summary of the invention

[0004] The object of the present invention is to provide a construction waste separation system to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a construction waste separation system, comprising:

[0006] A separator body, wherein a feed port for putting in construction waste is provided on the top of the separator body, a power supply module for powering the separator body, a temperature acquisition module, a light acquisition module and an intelligent separation module is provided on the top of the separator body, a plurality of discharge ports are provided on the side wall of the separator body, the plurality of discharge ports are respectively a first discharge port for outlet of available waste and a second discharge port for outlet of unavailable waste, and a cover plate is connected to the top of the first discharge port by a hinge, a third discharge port for discharging powder is provided at the bottom of the separator body, and shock absorbing mechanisms are provided at the four corners of the bottom of the separator body, and the shock absorbing mechanism comprises a bottom plate and a shock absorbing spring for connecting the bottom plate and the separator body;

[0007] An intelligent separation module, wherein the intelligent separation module is used to realize intelligent separation of construction waste;

[0008] A temperature acquisition module, which is used to acquire the temperature of the object to be measured and the ambient temperature;

[0009] The light collection module is used to collect ambient light and the output light power of the infrared laser transmitter.

[0010] Furthermore, the intelligent separation module includes an infrared laser emitter for emitting infrared lasers, a spectrometer for decomposing light into spectral lines, a spectral analysis system, a sample placement platform, a sample to be tested and a standard sample piece, and the spectral analysis system includes:

[0011] Spectral model input module, used by staff to input existing spectral analysis models;

[0012] A spectrum acquisition module, used to acquire spectrum information of the object to be tested that is currently undergoing infrared laser induced breakdown;

[0013] A spectral information conversion module, used to convert spectral information at any temperature into its corresponding standard spectral model when the temperature cannot be adjusted to the standard temperature;

[0014] A spectral feature selection module is used to select useful spectral information collected in the spectral collection module;

[0015] The spectral model training module is used to place a standard sample on the inspection platform for testing, and output the model calibration performance parameters when the model training is terminated;

[0016] A feature matching module is used to perform feature matching between the useful spectral information selected in the spectral feature selection module and the existing spectral analysis model input by the spectral model input module;

[0017] A temperature regulating module is used to regulate the ambient temperature and the temperature of the object to be measured;

[0018] A light adjustment module, used to adjust the ambient light and the output optical power of the infrared laser transmitter;

[0019] The illumination calculation module is used to calculate the output optical power of the infrared laser transmitter at the current temperature.

[0020] Furthermore, the specific working method of the spectral model training module is:

[0021] S1, select data, randomly select a number of data from the spectral model input module as a sample data group;

[0022] S2, initializing each weight and bias, and setting adjustment parameters, accuracy requirement parameters and adjustment rate;

[0023] S3, for each sample in the training set, calculating the output of the measurement data of the standard sample piece and the sample data of the standard sample piece;

[0024] S4, comparing the elements in the prediction result with the elements in the sample result, and further calculating the error of the measurement data;

[0025] S5, calculating the increments of each weight and bias based on the result of step S4;

[0026] S6, update weights and biases;

[0027] S7, calculate the total error of the predicted data and compare it with the accuracy parameter to determine whether it is less than the accuracy control parameter. If not, return to step S3 to continue the operation;

[0028] S8, the adjustment is completed, and the current weights and biases are saved. At this point, it can be considered that all parameters have reached a stable state and the training is completed.

[0029] Furthermore, the temperature acquisition module includes:

[0030] An ambient temperature acquisition module, wherein the ambient temperature acquisition module is fixedly connected to the separator body;

[0031] The sample temperature acquisition module is embedded on the top of the sample placement platform, and the temperature measuring end of the sample temperature acquisition module is in contact with the sample to be tested.

[0032] Furthermore, the light collection module includes:

[0033] An ambient light collection module, wherein the ambient light collection module is fixedly connected to the separator body;

[0034] The sample illumination collection module is fixedly arranged at the end of the infrared laser emitter, and the collection end of the sample illumination collection module points to the emission end of the infrared laser emitter.

[0035] Furthermore, the working method of the spectrum information conversion module is:

[0036] A1, reads the spectrum data matrix A of different samples at room temperature, the sample concentration matrix B corresponding to A, the spectrum data matrix C of different samples at different temperatures, and the background intensity matrix D at different temperatures;

[0037] A2, through functional data analysis, the spectrum data C at different temperatures are fitted into a curve C(D) along the background radiation D direction, and the spectrum data A at normal temperature is fitted into a straight line A(D);

[0038] A3, establish M different temperature spectral curves C(D)1, C(D)2, ..., C(D) through function model regression M , and M normal temperature spectrum straight lines A(D)1, A(D)2,…, A(D) M The nonlinear relationship between them is calculated and the correction coefficient is obtained;

[0039] A4, arrange the cycle results of W analysis lines in a matrix to form a nonlinear transformation model;

[0040] A5, establish a least squares support vector machine regression model through the normal temperature data matrix A and its corresponding concentration matrix B;

[0041] A6, the near-infrared background of the test sample is used as the input of the conversion model to obtain the conversion coefficient; then, the spectral intensity is multiplied by the conversion coefficient to obtain the converted spectrum; finally, the converted spectrum is used as the input of the regression model to obtain the concentration of the test sample.

[0042] Furthermore, the working method of the illumination calculation module is:

[0043] B1, calculate the effect of temperature on threshold current, the relationship is:

[0044] ,

[0045] Where Tr is the room temperature, Jth (Te) is the threshold current density measured at a certain temperature Te, T0 is an important parameter to characterize the temperature stability of infrared lasers, called characteristic temperature, which is related to the materials and structures used in infrared lasers. From the above formula, we can see that the higher T0 is, the better the temperature stability of infrared lasers is. If T0→ , then the Jth of the infrared laser transmitter does not change with temperature; from the relationship between the threshold current density Jth (Te) and the threshold current Ith (Te), the relationship between the current and temperature can be obtained as follows:

[0046] ,

[0047] where Sj is the area of the PN junction of the infrared laser emitter, and Ith(Tr) is the threshold current of the infrared laser emitter at room temperature;

[0048] B2. Calculate the influence of temperature on the lasing wavelength. The active region material of the infrared laser emitter uses a direct bandgap material. The lasing wavelength is determined by the bandgap width, as shown in the following formula:

[0049] ,

[0050] where L represents the length of the resonant cavity, represents the refractive index of the gain medium, and m is an integer. Each value of m corresponds to an oscillation frequency of a photon;

[0051] B3. Calculate the influence of temperature on the light output efficiency. Another important parameter of the output characteristics of the infrared laser emitter is the slope efficiency n, which is used to describe the slope of the P-I curve in the linear region of the threshold current of the infrared laser:

[0052] ,

[0053] The external differential quantum efficiency of the infrared laser emitter is defined as:

[0054] ,

[0055] Pth is the output optical power at the threshold current Ith, e is the electron charge, hv is the photon energy, and P and I are the power and injection current when the infrared laser operates normally. From the above formula, when I = h:

[0056] ,

[0057] Combining the formulas, we can get:

[0058] ,

[0059] Since Pth << P, the relationship between the power and temperature when the infrared laser operates is:

[0060] .

[0061] Compared with the prior art, the construction waste separation system provided by the present invention can ensure that the detected temperature of the object is consistent with the establishment temperature of the existing spectral analysis model in the system through the temperature acquisition module and the temperature adjustment module, thereby avoiding data abnormalities due to changes in the detected temperature; the ambient light of the object and the output light power of the infrared laser transmitter are consistent with the establishment conditions of the existing spectral analysis model in the system through the illumination acquisition module and the illumination adjustment module, thereby avoiding data abnormalities due to changes in the detection environment; the output light power of the infrared laser transmitter at the current temperature is calculated by the illumination calculation module, so that the illumination adjustment module can adjust the light intensity of the detection environment; the working state of the infrared laser transmitter can also be monitored by obtaining the current output light power of the infrared laser transmitter; at the same time, by performing spectral analysis on the construction waste, the analyzed target material can be separated from the construction waste; the separation of construction waste can be achieved through multiple analyses; and finally different construction wastes are discharged through different discharge ports, thereby ensuring the fine division of construction waste and waste utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0063] Figure 1 A schematic diagram of the overall structure provided by an embodiment of the present invention;

[0064] Figure 2 A schematic diagram of the left and right diagonal axis structure provided by an embodiment of the present invention;

[0065] Figure 3 for Figure 1 A schematic diagram of the structure enlargement at the center A;

[0066] Figure 4 A schematic diagram of the structure of the intelligent separation method provided by an embodiment of the present invention;

[0067] Figure 5 A schematic diagram of the structure of an intelligent module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0069] See also Figure 1-5 , construction waste separation system, including:

[0070] A separator body 1, a feed port 2 for building waste is provided on the top of the separator body 1, a power supply module 3 for powering the separator body 1, a temperature acquisition module 11, a light acquisition module 12 and an intelligent separation module 4 is provided on the top of the separator body 1, a plurality of discharge ports are provided on the side wall of the separator body 1, the plurality of discharge ports are respectively a first discharge port 10 for outlet of available waste and a second discharge port 6 for outlet of unavailable waste, and a cover plate 5 is connected to the top of the first discharge port 10 by a hinge, a third discharge port 9 for discharging powder is provided at the bottom of the separator body 1, and shock absorbing mechanisms are provided at the four corners of the bottom of the separator body 1, and the shock absorbing mechanism includes a bottom plate 7 and a shock absorbing spring 8 for connecting the bottom plate 7 and the separator body 1;

[0071] Intelligent separation module 4, which is used to realize intelligent separation of construction waste;

[0072] The temperature acquisition module 11 is used to acquire the temperature of the object to be measured and the ambient temperature;

[0073] The light collection module 12 is used to collect the ambient light and the output light power of the infrared laser transmitter.

[0074] The intelligent separation module 4 includes an infrared laser emitter for emitting infrared lasers, a spectrometer for decomposing light into spectral lines, a spectral analysis system, a sample placement platform, a sample to be tested and a standard sample piece, and the spectral analysis system includes:

[0075] Spectral model input module, used by staff to input existing spectral analysis models;

[0076] A spectrum acquisition module, used to acquire spectrum information of the object to be tested that is currently undergoing infrared laser induced breakdown;

[0077] A spectral information conversion module, used to convert spectral information at any temperature into its corresponding standard spectral model when the temperature cannot be adjusted to the standard temperature;

[0078] A spectral feature selection module is used to select useful spectral information collected in the spectral collection module;

[0079] The spectral model training module is used to place a standard sample on the inspection platform for testing, and output the model calibration performance parameters when the model training is terminated;

[0080] A feature matching module is used to perform feature matching between the useful spectral information selected in the spectral feature selection module and the existing spectral analysis model input by the spectral model input module;

[0081] A temperature regulating module is used to regulate the ambient temperature and the temperature of the object to be measured;

[0082] A light adjustment module, used to adjust the ambient light and the output optical power of the infrared laser transmitter;

[0083] The illumination calculation module is used to calculate the output optical power of the infrared laser transmitter at the current temperature.

[0084] In this way, the staff inputs the existing spectral analysis model through the spectral model input module, the staff places the sample to be tested on the sample placement platform, starts the infrared laser transmitter to perform infrared laser induced breakdown on the sample to be tested, collects the spectral information of the object to be tested that is currently undergoing infrared laser induced breakdown through the spectral acquisition module, selects the useful spectral information collected in the spectral acquisition module through the spectral feature selection module, and performs feature matching between the useful spectral information selected in the spectral feature selection module and the existing spectral analysis model input by the spectral model input module through the feature matching module. For spectral models with the same feature matching, it is possible to know which element the corresponding element is, thereby realizing element analysis. At the same time, since there may be a mixture of multiple elements, the common identification of multiple elements can be achieved through feature matching at this time. The temperature of the object to be tested and the ambient temperature are collected through the temperature acquisition module, and the ambient temperature and the temperature of the object to be tested are adjusted through the temperature adjustment module. This setting can ensure that the detection temperature of the object is consistent with the establishment temperature of the existing spectral analysis model in the system, avoiding data abnormalities due to changes in the detection temperature; the ambient light and the output light power of the infrared laser transmitter are collected through the light acquisition module, and the ambient light and the output light power of the infrared laser transmitter are adjusted through the light adjustment module. In this way, It can ensure that the ambient illumination of the object and the output optical power of the infrared laser transmitter are consistent with the establishment conditions of the existing spectrum analysis model in the system, avoiding data abnormalities due to changes in the detection environment. However, as the temperature of the infrared laser transmitter increases, the threshold current of the infrared laser increases and the output power decreases. Therefore, it is necessary to calculate the output optical power of the infrared laser transmitter at the current temperature through the illumination calculation module, so that the illumination adjustment module can adjust the illumination intensity of the detection environment. By obtaining the output optical power of the current infrared laser transmitter, the working state of the infrared laser transmitter can also be monitored; when the temperature adjustment module cannot adjust the ambient temperature to be consistent with the establishment temperature of the existing spectrum analysis model in the system, the spectrum information conversion module can be used to convert the spectrum information at any temperature to its corresponding standard spectrum model when the temperature cannot be adjusted to the standard temperature; in order to ensure the working accuracy of the detection and analysis system, the spectrum model training module can be used to place standard sample pieces on the inspection platform for detection, and when the model training is terminated, the model calibration performance parameters are output to realize system training, and the separation of construction waste is realized by spectral analysis of construction waste. By discharging different construction waste through different discharge ports, the fine division of construction waste and waste utilization can be guaranteed.

[0085] The specific operation steps of separating construction waste are as follows: after spectral analysis of mixed construction waste such as slag, waste concrete, waste bricks and stones, etc., the usable waste is discharged from the first discharge port 10, wherein the usable waste includes but is not limited to bricks, wood boards, waste stones and other construction wastes that will not deform and can be artificially adjusted in shape later, wherein the usable waste also includes powder of a single component, which can not only avoid the secondary utilization of powder mixed with impurities, but also can reuse the powder of a single component, and the staff only needs to discharge the waste from the first discharge port 10. The materials can be collected for secondary utilization, and the construction waste that is unusable waste according to the spectral analysis result is discharged from the second discharge port 6, wherein the unusable waste includes but is not limited to flexible wood and other construction waste that is difficult to be identified from usable construction waste by the naked eye. In this way, the intelligent separation module set up can accurately screen according to the different spectral information of different materials, and the mixed powder that is a mixed powder of waste concrete and soil according to the spectral analysis result is directly discharged through the third discharge port 9, so as to avoid the problem of low accuracy of judging the type of construction waste and whether it is usable by the naked eye.

[0086] The specific working method of the spectral model training module is:

[0087] S1, select data, randomly select a number of data from the spectral model input module as a sample data group;

[0088] S2, initializing each weight and bias, and setting adjustment parameters, accuracy requirement parameters and adjustment rate;

[0089] S3, for each sample in the training set, calculating the output of the measurement data of the standard sample piece and the sample data of the standard sample piece;

[0090] S4, comparing the elements in the prediction result with the elements in the sample result, and further calculating the error of the measurement data;

[0091] S5, calculating the increments of each weight and bias based on the result of step S4;

[0092] S6, update weights and biases;

[0093] S7, calculate the total error of the predicted data and compare it with the accuracy parameter to determine whether it is less than the accuracy control parameter. If not, return to step S3 to continue the operation;

[0094] S8, the adjustment is completed, and the current weights and biases are saved. At this point, it can be considered that all parameters have reached a stable state and the training is completed.

[0095] The temperature acquisition module includes:

[0096] An ambient temperature acquisition module, which is fixedly connected to the separator body 1;

[0097] The sample temperature acquisition module is embedded on the top of the sample placement platform, and the temperature measuring end of the sample temperature acquisition module is in contact with the sample to be tested.

[0098] The light collection module includes:

[0099] An ambient light collection module, which is fixedly connected to the separator body 1;

[0100] The sample illumination collection module is fixedly arranged at the end of the infrared laser emitter, and the collection end of the sample illumination collection module points to the emission end of the infrared laser emitter.

[0101] The working method of the spectrum information conversion module is:

[0102] A1, reads the spectrum data matrix A of different samples at room temperature, the sample concentration matrix B corresponding to A, the spectrum data matrix C of different samples at different temperatures, and the background intensity matrix D at different temperatures;

[0103] A2, through functional data analysis, the spectrum data C at different temperatures are fitted into a curve C(D) along the background radiation D direction, and the spectrum data A at normal temperature is fitted into a straight line A(D);

[0104] A3, establish M different temperature spectral curves C(D)1, C(D)2, ..., C(D) through function model regression M , and M normal temperature spectrum straight lines A(D)1, A(D)2,…, A(D) M The nonlinear relationship between them is calculated and the correction coefficient is obtained;

[0105] A4, arrange the cycle results of W analysis lines in a matrix to form a nonlinear transformation model;

[0106] A5, establish a least squares support vector machine regression model through the normal temperature data matrix A and its corresponding concentration matrix B;

[0107] A6, the near-infrared background of the test sample is used as the input of the conversion model to obtain the conversion coefficient; then, the spectral intensity is multiplied by the conversion coefficient to obtain the converted spectrum; finally, the converted spectrum is used as the input of the regression model to obtain the concentration of the test sample.

[0108] The working method of the lighting calculation module is:

[0109] B1, calculate the effect of temperature on threshold current, the relationship is:

[0110] ,

[0111] Where Tr is the room temperature, Jth (Te) is the threshold current density measured at a certain temperature Te, T0 is an important parameter to characterize the temperature stability of infrared lasers, called characteristic temperature, which is related to the materials and structures used in infrared lasers. From the above formula, we can see that the higher T0 is, the better the temperature stability of infrared lasers is. If T0→ , then the Jth of the infrared laser transmitter does not change with temperature; from the relationship between the threshold current density Jth (Te) and the threshold current Ith (Te), the relationship between the current and temperature can be obtained as follows:

[0112] ,

[0113] Where Sj is the area of ​​the PN junction of the infrared laser emitter, and Ith (Tr) is the threshold current of the infrared laser emitter at room temperature;

[0114] B2, calculate the effect of temperature on the lasing wavelength. The active area material of the infrared laser transmitter adopts direct bandgap material. The lasing wavelength is determined by the shelf band width, as shown in the following formula:

[0115] ,

[0116] Where L represents the length of the resonant cavity, represents the refractive index of the gain medium, and m is an integer, where each m value corresponds to an oscillation frequency of the photon;

[0117] B3, calculate the effect of temperature on light output efficiency. Another important parameter of the output characteristics of infrared laser transmitters is slope efficiency, which is used to describe the slope of the PI curve in the linear region of infrared laser current value:

[0118] ,

[0119] The external differential quantum efficiency of an infrared laser transmitter is defined as:

[0120] ,

[0121] Pth is the output optical power under the threshold current Ith, e is the electron charge, hv is the photon energy, P and I are the power and injection current of the infrared laser when it is working normally, respectively. From the above formula, it can be concluded that when I= h:

[0122] ,

[0123] Combining the formulas we get:

[0124] ,

[0125] Since Pth << P, the relationship between the power and temperature during the operation of the infrared laser is as follows:

[0126] .

[0127] Only some exemplary embodiments of the present invention have been described above by way of illustration. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. Construction waste separation system, characterized in that: include: A separator body (1), wherein a feed port (2) for feeding construction waste is provided at the top of the separator body (1), and shock absorbing mechanisms are provided at four corners of the bottom of the separator body (1), wherein the shock absorbing mechanisms include a bottom plate (7) and shock absorbing springs (8) for connecting the bottom plate (7) and the separator body (1); An intelligent separation module (4), the intelligent separation module (4) being used to realize intelligent separation of construction waste, the intelligent separation module (4) comprising an infrared laser emitter for emitting infrared lasers, a spectrometer for decomposing light into spectral lines, a spectral analysis system, a sample placement platform, a sample to be tested and a standard sample piece, the spectral analysis system comprising: Spectral model input module, used by staff to input existing spectral analysis models; A spectrum acquisition module, used to acquire spectrum information of the object to be tested that is currently undergoing infrared laser induced breakdown; A spectral information conversion module, used to convert spectral information at any temperature into its corresponding standard spectral model when the temperature cannot be adjusted to the standard temperature; A spectral feature selection module is used to select useful spectral information collected in the spectral collection module; The spectral model training module is used to place a standard sample on the inspection platform for testing, and output the model calibration performance parameters when the model training is terminated; A feature matching module is used to perform feature matching between the useful spectral information selected in the spectral feature selection module and the existing spectral analysis model input by the spectral model input module; A temperature regulating module is used to regulate the ambient temperature and the temperature of the object to be measured; A light adjustment module, used to adjust the ambient light and the output optical power of the infrared laser transmitter; Light calculation module, used to calculate the output optical power of the infrared laser transmitter at the current temperature; A temperature acquisition module (11), the temperature acquisition module (11) being used to acquire the temperature of an object to be measured and the ambient temperature; A light collection module (12) is used to collect ambient light and output light power of an infrared laser transmitter.

2. The construction waste separation system according to claim 1, characterized in that: A power supply module (3) for supplying power to the separator body (1), the temperature collection module (11), the light collection module (12) and the intelligent separation module (4) is arranged at the top of the separator body (1); a plurality of discharge ports are provided on the side wall of the separator body (1); the plurality of discharge ports are respectively a first discharge port (10) for discharging available waste and a second discharge port (6) for discharging unavailable waste; the top of the first discharge port (10) is connected to a cover plate (5) via a hinge; and a third discharge port (9) for discharging powder is provided at the bottom of the separator body (1).

3. The construction waste separation system according to claim 2, characterized in that: The specific working method of the spectral model training module is: S1, select data, randomly select a number of data from the spectral model input module as a sample data group; S2, initializing each weight and bias, and setting adjustment parameters, accuracy requirement parameters and adjustment rate; S3, for each sample in the training set, calculating the output of the measurement data of the standard sample piece and the sample data of the standard sample piece; S4, comparing the elements in the prediction result with the elements in the sample result, and further calculating the error of the measurement data; S5, calculating the increments of each weight and bias based on the result of step S4; S6, update weights and biases; S7, calculate the total error of the predicted data and compare it with the accuracy parameter to determine whether it is less than the accuracy control parameter. If not, return to step S3 to continue the operation; S8, the adjustment is completed, and the current weights and biases are saved. At this point, it can be considered that all parameters have reached a stable state and the training is completed.

4. The construction waste separation system according to claim 3, characterized in that: The temperature acquisition module comprises: An ambient temperature acquisition module, the ambient temperature acquisition module being fixedly connected to the separator body (1); The sample temperature acquisition module is embedded on the top of the sample placement platform, and the temperature measuring end of the sample temperature acquisition module is in contact with the sample to be tested.

5. The construction waste separation system according to claim 4, characterized in that: The light collection module comprises: An ambient light collection module, the ambient light collection module being fixedly connected to the separator body (1); The sample illumination collection module is fixedly arranged at the end of the infrared laser emitter, and the collection end of the sample illumination collection module points to the emission end of the infrared laser emitter.

6. The construction waste separation system according to claim 5, characterized in that: The working method of the spectrum information conversion module is: A1, reads the spectrum data matrix A of different samples at room temperature, the sample concentration matrix B corresponding to A, the spectrum data matrix C of different samples at different temperatures, and the background intensity matrix D at different temperatures; A2, through functional data analysis, the spectrum data C at different temperatures are fitted into a curve C (D) along the background radiation direction, and the spectrum data matrix A at room temperature is fitted into a straight line A (D); A3, establish M different temperature spectral curves C(D)1, C(D)2, ..., C(D) through function model regression M , and M normal temperature spectrum straight lines A(D)1, A(D)2,…, A(D) M The nonlinear relationship between them is calculated and the correction coefficient is obtained; A4, placing the cycle results of the analysis line in a matrix in sequence to form a nonlinear transformation model; A5, establishing a least squares support vector machine regression model through the normal temperature spectrum data matrix A and its corresponding concentration matrix B; A6, the near-infrared background of the test sample is used as the input of the conversion model to obtain the conversion coefficient; then, the spectral intensity is multiplied by the conversion coefficient to obtain the converted spectrum; finally, the converted spectrum is used as the input of the regression model to obtain the concentration of the test sample.

Images