Search

CN-122007120-A - Environment-friendly treatment method and system based on waste metal recycling

CN122007120ACN 122007120 ACN122007120 ACN 122007120ACN-122007120-A

Abstract

The invention discloses an environment-friendly treatment method and system based on waste metal recycling, and relates to the technical field of waste metal recycling, wherein the method comprises the steps of obtaining multisource data of waste metal after primary screening; the method comprises the steps of carrying out pretreatment on multi-source data, carrying out evaluation on the pretreated multi-source data to obtain a preliminary screening accuracy evaluation value, judging the preliminary screening accuracy evaluation value, calibrating weighing equipment if the preliminary screening accuracy evaluation value is judged to be unqualified, gradually adjusting electric field intensity according to the conductive characteristics of waste metal, collecting residue data, carrying out evaluation on the pretreated residue data to obtain a residue value evaluation value, judging the residue value evaluation value, adjusting parameters of rotary drum equipment and changing electrode spacing of a current separator if the residue is judged to be valuable, and carrying out environment-friendly harmless treatment if the residue is judged to be non-valuable. The method solves the problem of low accuracy in the waste metal recovery process, improves the waste metal identification and treatment accuracy, and maximizes the resource recovery benefit by dynamically evaluating the residue value.

Inventors

  • CHEN HONGSEN
  • CAO WENBO
  • YANG CHUNXI
  • JIANG WEI

Assignees

  • 广东晟科环保科技有限公司

Dates

Publication Date
20260512
Application Date
20260120

Claims (10)

  1. 1. The environment-friendly treatment method based on the recycling of the waste metal is characterized by comprising the following specific steps of: firstly, multi-source data of waste metal after primary screening is obtained, and the multi-source data is preprocessed; evaluating the preprocessed multi-source data to obtain a preliminary screening accuracy evaluation value; Judging the primary screening accuracy evaluation value; If the primary screening accuracy rate is judged to be unqualified, calibrating the weighing equipment, gradually adjusting the electric field intensity according to the conductive characteristics of the waste metal, and returning to the step one to continuously acquire multi-source data; if the primary screening accuracy rate is judged to be qualified, executing the fourth step; step four, sorting by a rotary drum and collecting by a current separator to obtain residue data; preprocessing the residue data, and evaluating the preprocessed residue data to obtain a residue value evaluation value; fifthly, judging a residue value evaluation value; Step six, if the residue is valuable, adjusting parameters of the rotary drum equipment, changing the electrode spacing of the current separator, and returning to the step four to continuously acquire residue data; If the residue is judged to be worthless, the environment-friendly harmless treatment is carried out.
  2. 2. The environmentally friendly treatment method based on scrap metal recycling according to claim 1, wherein the multivariate data comprises propane tank identification data, glass identification data and heavy iron identification data.
  3. 3. The environmental protection treatment method based on the recycling of waste metal according to claim 2, wherein the primary screening accuracy evaluation value obtaining process is as follows: Respectively carrying out data processing on the propane tank identification data, the glass identification data and the heavy iron identification data to obtain a propane tank error coefficient, a glass error coefficient and a heavy iron error coefficient; The error coefficient of the propane tank, the error coefficient of the glass and the error coefficient of the heavy iron are comprehensively analyzed to obtain an evaluation value of the accuracy of the primary screening, and the specific calculation formula is as follows: ; Wherein, the Represents an evaluation value of the accuracy of the preliminary screening, Representing the error coefficient of the propane tank, The coefficient of error of the glass is indicated, Representing the heavy iron error coefficient.
  4. 4. The environmental protection treatment method based on the recycling of waste metal according to claim 3, wherein the specific acquisition mode of the error coefficient of the propane tank is as follows: the method comprises the steps of extracting local and global geometric features from propane tank identification data subjected to point cloud noise reduction by adopting a three-dimensional point cloud feature embedding technology and utilizing a PointNet ++ model, and mapping the point cloud data into feature vectors with fixed dimensions; Acquiring a real attribute value of a propane tank sample, constructing a multi-task learning model based on a transducer architecture, taking the mapped feature vector with fixed dimension as input, and outputting a predicted attribute value of the propane tank sample; the mean square error between the predicted attribute value and the real attribute value of the propane tank is calculated, and the error coefficient of the propane tank is calculated by combining the actual range of the attribute of the propane tank, wherein the specific calculation formula is as follows: ; In the formula, Is the propane tank error coefficient, n is the number of samples, For the predicted attribute value of the ith propane tank sample, For the true attribute value of the ith propane tank sample, The maximum value and the minimum value of the real attribute value of the propane tank are respectively.
  5. 5. The environment-friendly treatment method based on waste metal recycling as claimed in claim 4, wherein the specific acquisition mode of the glass error coefficient is as follows: The method comprises the steps of (1) encoding spectrum data and morphological characteristics into the same characteristic space through a self-encoder by using a spectrum-morphology joint embedding method for glass identification data after spectrum processing and morphological analysis, and generating a fusion characteristic vector; Constructing a multi-task learning model, taking the generated fusion feature vector as input, and outputting a spectrum feature and a morphological feature prediction attribute value; Acquiring the spectrum feature and the morphological feature true value, and calculating a spectrum feature prediction error and a morphological feature prediction error by combining the spectrum feature and the morphological feature prediction attribute value; according to the spectrum characteristic prediction error and the morphological characteristic prediction error, calculating a glass error coefficient in a weighted fusion mode, wherein the specific calculation formula is as follows: ; In the formula, Is the coefficient of error of the glass and, Is the prediction error of the spectral characteristics, Is the prediction error of the morphological feature, Is the maximum of the true values of the spectral features, Is the minimum of the true values of the spectral features, Is the maximum value of the true value of the morphological feature, Is the minimum of the true values of the morphological features, Is the weight of the spectral feature, Is a morphological feature weight.
  6. 6. The environment-friendly treatment method based on waste metal recycling as claimed in claim 5, wherein the specific acquisition mode of the heavy iron error coefficient is as follows: Aiming at the heavy iron identification data after pressure analysis and magnetic permeability calculation, constructing a pressure-magnetic permeability correlation network, modeling the relationship between pressure and magnetic permeability by adopting a graph neural network, constructing a joint error measure according to the pressure and magnetic permeability correlation of the heavy iron identification data, and calculating a pressure prediction error and a magnetic permeability prediction error; According to the pressure prediction error and the magnetic permeability prediction error, the correlation error between the pressure and the magnetic permeability is measured by using covariance, and the heavy iron error coefficient is calculated according to the following specific calculation formula: ; In the formula, 、 The covariance of the predicted pressure and the magnetic permeability, the true pressure and the magnetic permeability are respectively obtained, Standard deviation of pressure and magnetic permeability data respectively, the pressure prediction error is The magnetic permeability prediction error is , Is the heavy iron error coefficient.
  7. 7. The environmental protection treatment method based on the recycling of waste metal according to claim 6, wherein in the second step, the process of judging the primary screening accuracy evaluation value is as follows: Setting a threshold value of the primary screening accuracy evaluation value, and comparing the primary screening accuracy obtained by the calculation in the step one with the threshold value: If the primary screening accuracy evaluation value is smaller than the threshold value, judging that the primary screening accuracy is unqualified; and if the primary screening accuracy evaluation value is greater than or equal to the threshold value, judging that the primary screening accuracy is qualified.
  8. 8. The environmental protection treatment method based on the recycling of waste metal according to claim 7, wherein in the fifth step, the process of judging the residue value evaluation value is as follows: setting a residue value evaluation threshold value, and comparing the residue value evaluation value calculated in the fourth step with the threshold value: If the residue value evaluation value is smaller than the threshold value, determining that the residue is worthless; if the residue value evaluation value is greater than the threshold value, the residue is determined to be valuable.
  9. 9. The method for environmental protection based on scrap metal recycling as set forth in claim 8, wherein in the sixth step, if the residue is valuable, the process of adjusting parameters of the drum equipment and changing the electrode spacing of the current separator is as follows: Fine-tuning the rotating speed of the roller according to the particle size distribution and density difference of metal and impurities in the current residue; according to the effective separation condition of metal particles and the purity after separation, the electrode spacing of the current separator is adjusted, after each adjustment of the electrode spacing, a small batch test is carried out, the separated metal and impurities are collected, and the components and the weight of the separated metal and impurities are analyzed to determine the optimal electrode spacing; after adjusting the parameters of the drum apparatus and changing the electrode spacing of the current separator, step four is re-performed until the residue is judged to be worthless.
  10. 10. The environmental protection treatment system based on scrap metal recycling according to claim 9, comprising an acquisition module, a judgment module, a collection module, an evaluation module, the modules directly having connection: the acquisition module is used for acquiring multi-source data of the waste metal after the primary screening and preprocessing the multi-source data; evaluating the preprocessed multi-source data to obtain a preliminary screening accuracy evaluation value; The device comprises a judging module, a weighing device, a measuring module and a control module, wherein the judging module is used for judging the primary screening accuracy evaluation value, calibrating the weighing device if the primary screening accuracy evaluation value is judged to be unqualified, gradually adjusting the electric field intensity according to the conductive characteristic of waste metal, and continuously acquiring multi-source data; The collecting module is used for collecting the residue data through the rotary drum classification and the galvanic separator, preprocessing the residue data, and evaluating the preprocessed residue data to obtain a residue value evaluation value; The evaluation module is used for judging the residue value evaluation value, adjusting parameters of the rotary drum equipment and changing the electrode spacing of the current separator if the residue is judged to be valuable, continuously acquiring residue data, and carrying out environment-friendly harmless treatment if the residue is judged to be worthless.

Description

Environment-friendly treatment method and system based on waste metal recycling Technical Field The invention relates to the technical field of waste metal recycling, in particular to an environment-friendly treatment method and system based on waste metal recycling. Background The greatest advantage of metals is that they can be recovered an unlimited number of times and they have little loss in their properties. The recycling of waste metal refers to the process of converting scrapped metal materials into reusable raw materials by a certain means, and the core aim is to realize resource recycling and energy consumption saving. The steel in the old metal of the scraped car accounts for about 70% -80%, the steel scrap recycled in the world each year can meet 30% of steel requirements, the iron ore exploitation of 3 hundred million tons is reduced, and the recycling significance of the waste metal of the scraped car is great. The prior art has the following defects: In the environment-friendly treatment process of recycling waste metal of scraped car, accuracy in the recognition process of treating substances which cannot be crushed such as propane tank, glass, heavy iron and the like is to be improved. After the magnetic drum adsorbs the iron pieces, there is no further evaluation of the garbage obtained when other substances than iron (containing many precious metals (copper, brass)) are classified by the drum and the residue collected by the galvanic separator. The present invention proposes a solution to the above-mentioned problems. Disclosure of Invention In order to overcome the above-mentioned drawbacks of the prior art, an embodiment of the present invention provides an environmental protection treatment method and system based on recycling of waste metal, so as to solve the problems set forth in the above-mentioned background art. In order to achieve the above purpose, the present invention provides the following technical solutions: An environment-friendly treatment method based on waste metal recycling comprises the following steps: firstly, multi-source data of waste metal after primary screening is obtained, and the multi-source data is preprocessed; evaluating the preprocessed multi-source data to obtain a preliminary screening accuracy evaluation value; Judging the primary screening accuracy evaluation value; If the primary screening accuracy rate is judged to be unqualified, calibrating the weighing equipment, gradually adjusting the electric field intensity according to the conductive characteristics of the waste metal, and returning to the step one to continuously acquire multi-source data; if the primary screening accuracy rate is judged to be qualified, executing the fourth step; step four, sorting by a rotary drum and collecting by a current separator to obtain residue data; preprocessing the residue data, and evaluating the preprocessed residue data to obtain a residue value evaluation value; fifthly, judging a residue value evaluation value; Step six, if the residue is valuable, adjusting parameters of the rotary drum equipment, changing the electrode spacing of the current separator, and returning to the step four to continuously acquire residue data; If the residue is judged to be worthless, the environment-friendly harmless treatment is carried out. In a preferred embodiment, the multivariate data comprises propane tank identification data, glass identification data, and heavy iron identification data. In a preferred embodiment, the primary screening accuracy assessment value is obtained as follows: Respectively carrying out data processing on the propane tank identification data, the glass identification data and the heavy iron identification data to obtain a propane tank error coefficient, a glass error coefficient and a heavy iron error coefficient; The error coefficient of the propane tank, the error coefficient of the glass and the error coefficient of the heavy iron are comprehensively analyzed to obtain an evaluation value of the accuracy of the primary screening, and the specific calculation formula is as follows: ; Wherein, the Represents an evaluation value of the accuracy of the preliminary screening,Representing the error coefficient of the propane tank,The coefficient of error of the glass is indicated,Representing the heavy iron error coefficient. In a preferred embodiment, the propane tank error coefficient is obtained in the following manner: the method comprises the steps of extracting local and global geometric features from propane tank identification data subjected to point cloud noise reduction by adopting a three-dimensional point cloud feature embedding technology and utilizing a PointNet ++ model, and mapping the point cloud data into feature vectors with fixed dimensions; Acquiring a real attribute value of a propane tank sample, constructing a multi-task learning model based on a transducer architecture, taking the mapped feature vector with fixed dimensi