Industrial waste material dynamic fractionation assessment system and method

Abstract

The application discloses an industrial waste material dynamic grading evaluation system and method, relates to the technical field of industrial waste treatment, and is used for solving the problem of significant deviation between the resource recovery rate and the predicted value in waste treatment experiments, which leads to low waste resource utilization efficiency, and through comprehensive acquisition of waste area environment data and component data, setting a threshold value to screen a to-be-determined grading position, analyzing component stability and predicting the recovery rate according to waste physical property data and historical treatment data. The real value of the recovery rate is obtained through experiments, the predicted value is compared with the real value to analyze the grading difference, and the high-quality grading position is screened or the screening standard is dynamically adjusted to meet the resource utilization demand. The method improves the component stability judgment and the recovery rate prediction accuracy and improves the resource utilization efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial waste treatment, more particularly, the present application relates to an industrial waste material dynamic grading evaluation system and method. BACKGROUND

[0002] The continuous growth of industrial waste treatment and resource utilization demand makes the grading evaluation of industrial waste materials an important link to improve waste treatment efficiency and resource recovery rate. However, the existing waste grading evaluation method has certain limitations in dynamic, real-time and intelligent aspects, and it is difficult to adapt to the complex and variable industrial waste treatment scene requirements.

[0003] The prior art has the following disadvantages:

[0004] At present, the industrial waste grading evaluation method generally relies on static or empirical threshold, lacks dynamic adjustment capability based on real-time environmental parameters and waste physical characteristics, and is difficult to respond to changes in waste accumulation density, pyrolysis increment and particle size, etc. Characteristics, resulting in a significant deviation between the resource recovery rate in the waste treatment experiment and the predicted value, thereby reducing the efficiency of waste resource utilization, therefore, an industrial waste material dynamic grading evaluation system and method are proposed.

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide an industrial waste material dynamic grading evaluation system and method, which realizes multi-dimensional dynamic analysis and grading adjustment of waste components by real-time collection of waste parameters and combination of intelligent analysis model, to solve the problems proposed in the above background.

[0007] To achieve the above purpose, the present application provides the following technical scheme, an industrial waste material dynamic grading evaluation method, comprising the following steps:

[0008] Step S1: Obtain waste area environmental data and waste component data, and set threshold value by comprehensively screening a plurality of pending grading positions from the waste area environmental data and waste component data;

[0009] Step S2: Collect waste physical property data and waste historical treatment data of each pending grading position for comparative analysis, judge the stability of waste components according to the analysis result, and predict the resource recovery rate after waste treatment of the pending grading position to obtain the recovery rate prediction value;

[0010] Step S3: performing waste treatment experimental work at the to-be-classified location and detecting the real waste treatment situation of the to-be-classified location to obtain a real value of the recovery rate, and analyzing the classification difference by comparing the predicted value of the recovery rate and the real value of the recovery rate;

[0011] Step S4: screening the to-be-classified location according to the classification difference and recording or reducing the screening standard to meet the waste resource utilization requirement.

[0012] In a preferred embodiment, in step S1, the waste area environment data is waste accumulation density, and the waste composition data is waste pyrolysis increment.

[0013] The waste accumulation density is obtained by detecting the height and unit area mass of the waste distribution in the waste area environment, taking the average height as the zero point of the waste area environment accumulation density, screening the positions higher than the average height in the waste area environment, and taking the unit area mass of the screened position and the average height as the waste accumulation density.

[0014] The waste pyrolysis increment is obtained by performing pyrolysis experiments on different waste under the same conditions, and analyzing and detecting the heat release amount difference between before and after waste pyrolysis in the same time period.

[0015] In a preferred embodiment, in step S1, the threshold is set to screen the to-be-classified location as follows:

[0016] Setting an initial accumulation density threshold: setting an initial accumulation density threshold by using quantile method;

[0017] Adjusting the initial accumulation density threshold: taking the product of the initial accumulation density threshold and the waste pyrolysis increment as the adjusted accumulation density threshold;

[0018] Screening the to-be-classified location: comparing the accumulation density of each position in the waste area environment with the accumulation density threshold, and screening the positions higher than the accumulation density threshold as the to-be-classified location.

[0019] In a preferred embodiment, in step S2, the waste physical property data of the to-be-classified location is the proportion of particle size distribution in the waste in the to-be-classified location, and the waste historical treatment data includes a waste adapted particle size proportion table and a treatment efficiency of the waste under the adapted particle size proportion.

[0020] In a preferred embodiment, in step S2, when judging the stability of the waste composition, the waste adapted particle size proportion is obtained by using the waste adapted particle size proportion table, the Euclidean distance is calculated by using the proportion of particle size distribution in the waste and the adapted particle size proportion of the waste, and the judgment rule is set according to the Euclidean distance to judge the stability of the waste composition as follows:

[0021] Rule 1: When the Euclidean distance calculated by the pending classification position is zero, the output result is 1;

[0022] Rule 2: When the Euclidean distance calculated by the pending classification position is not zero, mark it as e, and the output result is 1 / (1+e);

[0023] Determine the stability of the waste composition: when the output result is 1, determine that the stability of the waste composition is normal; otherwise, determine that the stability of the waste composition is abnormal, and record the output result.

[0024] In a preferred embodiment, in step S2, the system predicts the resource recovery rate of the waste after treatment in the pending classification position according to the stability of the waste composition, and the prediction process is as follows:

[0025] Process 1: Determine the treatment efficiency of the waste under the adaptive particle size ratio of the pending classification position, and record the average value of the resource recovery rate after waste treatment;

[0026] Process 2: Calculate the predicted value of the resource recovery rate of the waste according to the output result of the pending classification position, and take the product of the average value of the resource recovery rate after waste treatment and the output result as the predicted value of the resource recovery rate of the waste;

[0027] Process 3: Output the predicted value of the resource recovery rate of the waste.

[0028] In a preferred embodiment, in step S3, waste treatment experiments are carried out in the pending classification position, and the true value of the resource recovery rate of the waste is obtained. After the system receives the true value of the resource recovery rate of the waste, each pending classification position is numbered, and the true value of the resource recovery rate is combined into a true classification data set according to the number, and the predicted value of the resource recovery rate of the waste is combined into a predicted classification data set according to the number, and the classification difference is analyzed according to the combined data set, and the specific steps are as follows:

[0029] Step 1: Subtract the data with the same number in the predicted classification data set and the true classification data set to obtain the classification difference value of the corresponding number of the pending classification position;

[0030] Step 2: Set a screening rule, if the calculated classification difference value is positive or zero, it is determined that the classification difference of the pending classification position is small; if the calculated classification difference value is negative, it is determined that the classification difference of the pending classification position is large;

[0031] Step 3: Screening, when the classification difference of the pending classification position is large, mark it as a high-quality classification position; when the classification difference of the pending classification position is small, mark it as a backup classification position.

[0032] In a preferred embodiment, in step S4, the waste resource utilization demand quantity is converted into the required number of high-quality classification positions, and the specific process is as follows:

[0033] The resource recovery rate prediction values of all high-quality classification positions are added up and compared with the number of high-quality classification positions to obtain the average resource recovery rate prediction value of the high-quality classification positions.

[0034] The waste resource utilization demand quantity is compared with the average resource recovery rate prediction value of the high-quality classification positions to obtain the required number of high-quality classification positions.

[0035] In a preferred embodiment, in step S4, the number of high-quality classification positions is compared with the required number of high-quality classification positions, and if the number of high-quality classification positions is greater than or equal to the required number of high-quality classification positions, the demand is met, and there is no need to lower the screening standard to obtain more classification positions.

[0036] If the number of high-quality classification positions is less than the required number of high-quality classification positions, the demand is not met, and the screening standard is lowered to obtain more classification positions.

[0037] The industrial waste material dynamic classification evaluation system comprises a data acquisition unit, a classification position analysis unit, a classification position determination unit, and a resource remediation unit.

[0038] The data acquisition unit is used to collect waste area environmental data, waste composition data, waste physical property data, and waste historical treatment data, and transmit them to the subsequent units for analysis and processing.

[0039] The classification position analysis unit is used to receive waste area environmental data and waste composition data and screen out the to-be-determined classification positions, and transmit the to-be-determined classification positions to the classification position determination unit.

[0040] The classification position determination unit is used to receive waste physical property data and waste historical treatment data, and to predict and compare the to-be-determined classification positions, and classify the to-be-determined classification positions into high-quality classification positions and alternative classification positions.

[0041] The resource remediation unit is used to record the high-quality classification positions and count their number, compare it with the waste resource utilization demand, and use the alternative classification positions for remediation.

[0042] The technical effects and advantages of the present application are as follows:

[0043] The application obtains waste area environment data and waste component data, sets a threshold to screen a plurality of to-be-determined classification positions, compares and analyzes waste physical property data and waste historical processing data of each to-be-determined classification position, judges waste component stability according to the analysis result, and obtains a recovery rate prediction value by predicting resource recovery rate after waste processing of the to-be-determined classification position, performs waste processing experiment at the to-be-determined classification position and detects real waste processing condition of the to-be-determined classification position to obtain a real recovery rate value, analyzes classification difference by comparing the recovery rate prediction value and the real recovery rate value, screens the to-be-determined classification position and records or reduces screening standards to meet waste resource utilization requirements, and improves accuracy of waste component stability judgment and resource recovery rate prediction and resource utilization efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 It is a module structure diagram of the industrial waste material dynamic classification evaluation system of the application.

[0045] Figure 2 It is an implementation flow diagram of the industrial waste material dynamic classification evaluation method of the application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0047] Embodiment 1

[0048] The application provides an industrial waste material dynamic classification evaluation system and method, which combines Figure 1 and Figure 2 The specific embodiments of the application are described in detail with reference to the drawings and their descriptions.

[0049] As shown in Figure 1 , an industrial waste material dynamic classification evaluation system includes a data acquisition unit, a classification position analysis unit, a classification position determination unit, and a resource remediation unit.

[0050] The data acquisition unit is used to acquire waste area environment data, waste component data, waste physical property data, and waste historical processing data, and transmit them into the subsequent units for analysis and processing, respectively;

[0051] The classification position analysis unit is used to receive waste area environment data and waste component data and screen to-be-determined classification positions, and transmit the to-be-determined classification positions into the classification position determination unit;

[0052] The hierarchical position determination unit is used to receive waste physical property data and waste historical treatment data, predict and compare the pending hierarchical position, and classify the pending hierarchical position into a high-quality hierarchical position and an alternative hierarchical position;

[0053] The resource remediation unit is used to record the high-quality hierarchical position and compare the number of the high-quality hierarchical position with the waste resource utilization demand, and remediate the alternative hierarchical position.

[0054] The specific implementation process is as follows:

[0055] The data acquisition unit is responsible for collecting waste area environmental data, waste composition data, waste physical property data, and waste historical treatment data.

[0056] The waste area environmental data includes waste accumulation density, which is calculated by detecting the height of waste distribution and the mass per unit area. The specific calculation process is obtained by detecting the height of waste distribution area and the mass per unit area.

[0057] First, measure the vertical accumulation height of the waste in the area to obtain the actual height value of the waste accumulation per unit area.

[0058] Then, measure the total mass of the waste per unit area.

[0059] Finally, divide the mass of the waste per unit area by the corresponding accumulation height, and the result is the waste accumulation density of the area.

[0060] It should be noted that the waste accumulation density is obtained by combining three-dimensional laser scanning and ground load detection technology.

[0061] Three-dimensional laser scanning is to emit high-frequency pulsed laser beams to the surface of the waste through laser scanning equipment, receive the reflected signals and combine with spatial positioning information to construct a high-precision three-dimensional point cloud model of the waste accumulation area, thereby realizing non-contact and real-time acquisition of the waste accumulation height.

[0062] The ground load detection technology is to measure the actual mass data of the waste per unit area in real time by setting high-precision strain sensors, piezoelectric load sensors, or electronic weighing modules under the ground of the waste stacking area, which is not described here.

[0063] The waste composition data includes waste pyrolysis increment, which is obtained by measuring the change of heat release after pyrolysis experiments of different wastes under the same conditions. The change of heat release during the pyrolysis process of different types of waste is measured to obtain the waste pyrolysis increment.

[0064] The specific process is: under the conditions of uniform temperature control, heating rate and atmosphere, pyrolysis experiments are respectively conducted on different waste samples, and the heat values released by each waste sample are recorded.

[0065] Then, the heat release values between different wastes are compared and analyzed. The pyrolysis increment of the waste with higher heat release value relative to the waste with lower heat release value is the heat difference between the two.

[0066] It should be noted that the waste pyrolysis increment is obtained by applying the thermogravimetric analysis combined with differential scanning calorimetry method. Thermogravimetric analysis refers to real-time monitoring of the mass change of waste samples during the heating process under controlled atmosphere and temperature conditions, thereby obtaining the temperature range and mass change characteristics of the sample during the pyrolysis process.

[0067] Differential scanning calorimetry refers to measuring the heat flow difference between the sample and the reference under the same temperature control conditions to obtain the information of the heat absorption and release behavior of the waste during pyrolysis, thereby analyzing its thermal effect characteristics and heat release capacity, which will not be described here.

[0068] The waste physical property data is the particle size distribution ratio of the waste in the to-be-determined classification position. By sampling the waste sample in the to-be-determined classification position, the waste particles are classified according to particle size by sieving and laser particle size analyzer. Then, the number of particles in each particle size interval is counted and compared with the total amount of the sample to obtain the distribution ratio of each particle size interval.

[0069] It should be noted that the particle size distribution ratio is obtained by laser particle size analysis or multi-stage sieving image recognition. Laser particle size analysis is to emit a laser beam of a specific wavelength from a laser particle size analyzer to a waste particle sample, use the scattering effect of particles on laser, and calculate the number distribution and volume distribution of particles in the sample according to Mie scattering theory to obtain accurate particle size distribution ratio.

[0070] Multi-stage sieving image recognition is to perform step-by-step sieving on the waste sample by a group of pre-set sieves with decreasing mesh size, then collect and process the image of the retained particle sample after each stage of sieving, and finally calculate the complete particle size distribution ratio by combining edge recognition, morphological analysis and other image processing algorithms.

[0071] The waste historical treatment data includes a waste adapted particle size ratio table and a waste treatment efficiency under the adapted particle size ratio. The waste adapted particle size ratio table is used to record the best treatment ratio of each type of waste under different particle size distribution in history. The waste treatment efficiency under the adapted particle size ratio reflects the actual resource treatment effect of the waste under the corresponding ratio condition.

[0072] It should be noted that the waste adaptive particle size ratio table refers to an empirical or statistical reference data table constructed based on historical treatment data, which records the resource treatment effect, process matching degree or energy efficiency utilization of different types of waste under a specific particle size distribution ratio, and can provide quantitative reference for the classification assessment and resource allocation of the waste to be treated, which will not be described here;

[0073] These data are transmitted to the subsequent unit for analysis and processing respectively.

[0074] The classification position analysis unit receives the waste area environment data and waste composition data from the data acquisition unit, and screens a plurality of pending classification positions according to the set threshold value.

[0075] As shown in Figure 2 The initial bulk density threshold is set using the quantile method, and the product of the initial bulk density threshold and the waste pyrolysis increment is used as the adjusted bulk density threshold. The bulk density of each position in the waste area environment is compared with the bulk density threshold, and the positions higher than the bulk density threshold are screened as the pending classification positions.

[0076] The classification position determination unit receives the pending classification position information transmitted from the classification position analysis unit, and further receives the waste physical property data and waste historical treatment data provided by the data acquisition unit.

[0077] In this unit, the stability of the waste composition in the pending classification position is first judged. The waste adaptive particle size ratio table is used to obtain the waste adaptive particle size ratio, and the Euclidean distance is calculated using the particle size distribution ratio in the waste and the adaptive particle size ratio of the waste. The judgment rule is set according to the Euclidean distance.

[0078] When the calculated Euclidean distance of the pending classification position is zero, the output result is 1, and the stability of the waste composition is normal at this time;

[0079] When the calculated Euclidean distance is not zero, it is marked as e, and the output result is

[0080] At this time, if the output result is less than 1, it is judged that the stability of the waste composition is abnormal and the output result is recorded.

[0081] Based on the stability of the waste composition, the system predicts the resource recovery rate of the waste after treatment in the pending classification position.

[0082] The prediction process includes determining the treatment efficiency of the waste under the adaptive particle size ratio, and recording the average value of the resource recovery rate after treatment of the waste. The product of the average value of the resource recovery rate after treatment of the waste and the output result is used as the predicted value of the resource recovery rate of the waste.

[0083] The prediction result is then passed to the next step for verification.

[0084] The waste treatment experiment is carried out in the pending classification position to detect the real treatment condition and obtain the real value of resource recovery rate.

[0085] The real value of resource recovery rate is corresponded to each pending classification position by setting the number, and the data is merged into the real classification data set.

[0086] It should be noted that the number setting is the unique number set by the experiment personnel according to the data sampling specification number and the experiment data mapping rule, which is not described here;

[0087] At the same time, the predicted value of resource recovery rate of waste is merged into the predicted classification data set according to the number, and the classification difference is analyzed according to the merged data set, and the specific steps are as follows:

[0088] Step 1: The classification difference is calculated by subtracting the data of the same number in the predicted classification data set and the real classification data set.

[0089] Step 2: When the classification difference value is positive or zero, it is judged that the classification difference of the pending classification position is small, and when the classification difference value is negative, it is judged that the classification difference of the pending classification position is large.

[0090] Step 3: The position with small classification difference is marked as the selected classification position, and the position with large classification difference is marked as the high-quality classification position.

[0091] The resource remediation unit receives the high-quality classification position and the selected classification position information transmitted by the classification position determination unit, and counts the number of high-quality classification positions.

[0092] The waste resource utilization demand is converted into the number of required high-quality classification positions, and the specific process is as follows:

[0093] The predicted average value of resource recovery rate of high-quality classification position is obtained by accumulating the predicted value of resource recovery rate of all high-quality classification positions and calculating the ratio with the number of high-quality classification positions, and the ratio between the waste resource utilization demand and the predicted average value of resource recovery rate of high-quality classification position is calculated to obtain the number of required high-quality classification positions.

[0094] The number of high-quality classification positions is compared with the number of required high-quality classification positions, if the number of high-quality classification positions is greater than or equal to the number of required high-quality classification positions, the demand is reached, and there is no need to reduce the screening standard to obtain more classification positions.

[0095] If the number of high-quality classification positions is less than the number of required high-quality classification positions, the demand is not reached, and the screening standard is reduced to obtain more classification positions.

[0096] The process of lowering the screening standard includes readjusting the bulk density threshold or relaxing the judgment condition of waste composition stability, thereby expanding the range of the to-be-determined classification position and increasing the number of high-quality classification positions. The specific operation method of lowering the screening standard is not limited, and will not be described here.

[0097] The operation process of the system is as follows:

[0098] The data acquisition unit first acquires the waste area environmental data and waste composition data, and transmits these data to the classification position analysis unit.

[0099] The classification position analysis unit screens a plurality of to-be-determined classification positions according to the set threshold and transmits the information to the classification position determination unit.

[0100] The classification position determination unit further receives the waste physical property data and waste historical treatment data, and classifies each to-be-determined classification position by analyzing the waste composition stability and predicting the resource recovery rate.

[0101] Subsequently, waste treatment experiments are carried out at the to-be-determined classification positions and the real processing conditions are detected, and the real value is compared with the predicted value to analyze the classification difference.

[0102] Finally, the resource remediation unit records and statistics the high-quality classification positions and the alternative classification positions according to the classification difference results, and determines whether the screening standard needs to be lowered to obtain more classification positions according to the waste resource utilization demand.

[0103] In the above content, the high-quality classification position and the alternative classification position are taken as the classification standard. Optionally, the high-quality classification position is divided into the first grade, i.e., meeting the high resource utilization standard, and the alternative classification position is divided into the second grade, i.e., meeting the basic utilization condition.

[0104] Optionally, the third and fourth grade positions can also be set.

[0105] For example, the position that does not meet the utilization standard at present but has utilization potential is marked as the third grade position, and the position that does not meet the utilization standard at present and has no utilization potential is marked as the fourth grade position, and the like, which will not be described here.

[0106] In actual application, it is assumed that there are various industrial wastes in the waste accumulation area of a factory. The data acquisition unit acquires the waste bulk density and pyrolysis increment data through sensors and laboratory equipment.

[0107] The classification position analysis unit sets the initial bulk density threshold according to the quantile method and screens a plurality of to-be-determined classification positions through the adjusted bulk density threshold.

[0108] The hierarchical position determination unit receives these pending hierarchical position information and further analyzes the stability of the waste composition, for example, the proportion of the particle size distribution of the waste at a certain position is close to the value in the adaptive particle size proportion table, and the system determines that the composition stability is normal and predicts the resource recovery rate to be 80%.

[0109] Subsequently, waste treatment experiments are carried out at this position, and the detection shows that the true value of the resource recovery rate is 75%, and the hierarchical difference value is 5, so this position is marked as a candidate hierarchical position.

[0110] The particle size distribution proportion of the waste at another position deviates greatly from the adaptive particle size proportion, and the system determines that the composition stability is abnormal and predicts the resource recovery rate to be 60%, and the experimental detection shows that the true value of the resource recovery rate is 85%, and the hierarchical difference value is -25, so this position is marked as a high-quality hierarchical position.

[0111] The resource remediation unit counts the number of high-quality hierarchical positions and determines whether the waste resource utilization demand is met. If not, more hierarchical positions are obtained by lowering the screening standard.

[0112] As can be seen from the above embodiments, the system can effectively realize dynamic hierarchical evaluation of industrial waste materials and ensure that the waste resource utilization demand is met.

[0113] In order to better enable those skilled in the art to fully understand and implement the present application, the implementation principle of the present application is further described below in conjunction with a specific application scenario.

[0114] In the industrial waste treatment scene, it is assumed that the waste accumulation area of a factory is distributed with various types of industrial waste, including metal waste, plastic waste, and mixed waste. The data acquisition unit obtains waste area environment data and waste composition data through multi-source sensors and laboratory equipment.

[0115] For example, the sensor monitors the waste accumulation density in real time, which is calculated as the ratio of the height of the waste distribution to the mass per unit area.

[0116] At the same time, the laboratory equipment obtains the waste pyrolysis increment through pyrolysis experiments, that is, measures the change in heat release before and after pyrolysis of the waste under the same conditions. These data are transmitted to the hierarchical position analysis unit for preliminary screening.

[0117] The hierarchical position analysis unit sets an initial accumulation density threshold according to the quantile method, and takes the product of the initial accumulation density threshold and the waste pyrolysis increment as the adjusted accumulation density threshold.

[0118] Subsequently, the system compares the accumulation density of each position in the waste area environment with the adjusted accumulation density threshold, and selects the positions higher than the threshold as the pending hierarchical positions.

[0119] For example, in a certain waste accumulation area, if the accumulation density of a certain position is significantly higher than the adjusted accumulation density threshold, the position is marked as a pending classification position.

[0120] This step ensures that the screening process can dynamically adapt to the complexity of the waste accumulation area, avoiding errors that may be caused by static thresholds.

[0121] The classification position determination unit receives the pending classification position information from the classification position analysis unit and further obtains waste physical property data and waste historical processing data.

[0122] The waste physical property data includes the particle size distribution ratio in the waste at the pending classification position, while the waste historical processing data includes the waste adapted particle size ratio table and the processing efficiency of the waste at the adapted particle size ratio.

[0123] In this unit, the system first determines the stability of the waste composition. Specifically, the waste adapted particle size ratio is obtained from the waste adapted particle size ratio table, and the Euclidean distance is calculated using the particle size distribution ratio in the waste and the adapted particle size ratio.

[0124] When the Euclidean distance is zero, the output result is 1, and the stability of the waste composition is determined to be normal;

[0125] When the Euclidean distance is not zero, it is marked as e, and the output result is calculated as 1 divided by 1 plus e.

[0126] If the output result is less than 1, the stability of the waste composition is determined to be abnormal, and the output result is recorded.

[0127] Based on the stability of the waste composition, the system predicts the resource recovery rate after processing the waste at the pending classification position.

[0128] The prediction process includes determining the processing efficiency of the waste at the adapted particle size ratio, recording the average value of the resource recovery rate after processing the waste, and taking the product of the average value and the output result as the predicted value of the resource recovery rate of the waste.

[0129] Waste processing experiments are conducted at the pending classification positions to detect the actual processing conditions.

[0130] For example, at a certain pending classification position, the system obtains the actual value of the resource recovery rate through experiments, and corresponds this value to each pending classification position according to the number.

[0131] At the same time, the predicted value of the resource recovery rate of the waste is also merged according to the number to form a predicted classification data set.

[0132] The classification difference is calculated by subtracting the data with the same number in the predicted classification data set and the actual classification data set.

[0133] For example, if the predicted value of the resource recovery rate of a certain pending classification position is 80%, and the actual value is 75%, the classification difference value is 5.

[0134] According to the positive and negative of the classification difference value, the size of the classification difference is judged:

[0135] If the value is positive or zero, it is determined that the classification difference is small, and the position is marked as a candidate classification position.

[0136] If the value is negative, it is determined that the classification difference is large, and the position is marked as a high-quality classification position.

[0137] The resource remediation unit receives the high-quality classification position and candidate classification position information transmitted by the classification position determination unit, and counts the number of high-quality classification positions.

[0138] The system determines whether the number of high-quality classification positions meets the demand for waste resource utilization.

[0139] For example, if the number of high-quality classification positions does not meet the demand, more classification positions are obtained by lowering the screening standard.

[0140] The process of lowering the screening standard includes readjusting the bulk density threshold or relaxing the judgment condition of waste composition stability.

[0141] For example, the bulk density threshold is lowered by a certain percentage, or the Euclidean distance judgment rule is adjusted, thereby expanding the range of pending classification positions and increasing the number of high-quality classification positions.

[0142] Through the above steps, it can be seen that the present application realizes efficient and accurate classification evaluation of industrial waste materials by real-time collection of waste parameters through multi-source sensors, and multi-dimensional dynamic analysis and classification adjustment of waste composition through intelligent analysis model.

[0143] For example, in a certain practical application, the system successfully selects multiple high-quality classification positions by dynamically adjusting the bulk density threshold and the waste composition stability judgment condition, meeting the demand for waste resource utilization.

[0144] At the same time, by comparing the predicted value with the actual value, the system can continuously optimize the classification standard and improve the waste treatment efficiency and resource recovery rate.

[0145] Further, the industrial waste material dynamic classification evaluation system also includes its corresponding industrial waste material dynamic classification evaluation method, which includes the following steps:

[0146] Step S1: Obtain waste area environmental data and waste composition data, and set a threshold to screen out multiple pending classification positions based on the waste area environmental data and waste composition data;

[0147] Step S2: Collecting physical property data of waste at the to-be-determined classification position and waste historical treatment data for comparative analysis, judging waste component stability according to the analysis result and predicting resource recovery rate after waste treatment at the to-be-determined classification position to obtain a recovery rate prediction value;

[0148] Step S3: Performing waste treatment experiment at the to-be-determined classification position and detecting real waste treatment at the to-be-determined classification position to obtain a real recovery rate value, and analyzing classification difference by comparing the recovery rate prediction value and the real recovery rate value;

[0149] Step S4: Screening the to-be-determined classification position according to the classification difference and recording or reducing the screening standard to meet the waste resource utilization demand.

[0150] The above formulas are dimensionless values, and the formulas are obtained by collecting a large amount of data to simulate the most real situation, and the preset parameters in the formulas are set by a person skilled in the art according to the actual situation.

[0151] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium sets. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0152] It should be understood that the term "and / or" in this document is merely used to describe associated relationship, and it can mean three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " in this document generally means that the associated objects before and after the " / " are in an "or" relationship, but can also mean an "and / or" relationship, which can be understood according to the context before and after.

[0153] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0154] It should be understood that the order of the above processes in various embodiments of the present application does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0155] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0157] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be realized by other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0158] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0159] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0160] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0161] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A dynamic grading and evaluation method for industrial waste materials, characterized in that: Includes the following steps: Step S1: Obtain environmental data and waste composition data of the waste area, and set thresholds based on the combined environmental data and waste composition data to filter out multiple undetermined grading locations; In step S1, the environmental data of the waste area is the waste bulk density; the waste composition data is the waste pyrolysis increment. The initial bulk density threshold is set using the quantile method. Then, the product of the initial bulk density threshold and the waste pyrolysis increment is used as the adjusted bulk density threshold. The bulk density of each location in the waste area environment is compared with the bulk density threshold, and the locations that are higher than the bulk density threshold are selected as the locations to be classified. Step S2: Collect physical property data of waste at each undetermined grading location and historical waste treatment data for comparative analysis. Based on the analysis results, determine the stability of waste composition and predict the resource recovery rate after waste treatment at the undetermined grading location to obtain the predicted recovery rate value. In step S2, the physical property data of the waste at the undetermined grading location is the particle size distribution ratio in the waste at the undetermined grading location, and the historical processing data of the waste includes the waste-suitable particle size ratio table and the processing efficiency of the waste under the suitable particle size ratio. First, the stability of the waste composition at the desired grading location is judged. The waste suitable particle size ratio table is used to obtain the waste suitable particle size ratio. The Euclidean distance is calculated using the particle size distribution ratio in the waste and the suitable particle size ratio of the waste. Judgment rules are set based on the Euclidean distance. When the Euclidean distance calculated from the undetermined grading position is zero, the output result is 1, indicating that the stability of the waste composition is normal. When the Euclidean distance calculated from the undetermined grade position is not zero, mark it as e, and the output result is 1 / (1+e); If the output result is less than 1, then the stability of the waste composition is determined to be abnormal and the output result is recorded. Based on the stability results of waste composition, the system predicts the resource recovery rate after waste treatment at the undetermined grading location; The prediction process includes determining the waste treatment efficiency under the appropriate particle size ratio, recording the average resource recovery rate after waste treatment, and multiplying the average resource recovery rate after waste treatment with the output result as the predicted value of the waste resource recovery rate. Step S3: Conduct waste treatment experiments at the undetermined grading locations and detect the actual waste treatment at the undetermined grading locations to obtain the true recovery rate value. Analyze the grading differences by comparing the predicted recovery rate value and the true recovery rate value. The locations to be classified are numbered, and the predicted resource recovery rates of the waste are merged into a predicted classification dataset according to the numbers. The classification differences are then analyzed based on the merged dataset. The specific steps are as follows: Step 1: The grading difference is calculated by subtracting the data with the same index in the predicted grading dataset and the actual grading dataset; Step 2: When the grading difference value is positive or zero, the grading difference of the position to be determined is small; when the grading difference value is negative, the grading difference of the position to be determined is large. Step 3: Locations with small grading differences are marked as candidate grading locations, while locations with large grading differences are marked as high-quality grading locations; Step S4: Based on the differences in grading, screen and record the determined grading positions or lower the screening criteria to meet the needs of waste resource utilization; Receive information on high-quality and alternative grading locations from the grading location determination unit, and count the number of high-quality grading locations. The demand for waste resource utilization is converted into the required number of high-quality grading locations. The specific process is as follows: The predicted resource recovery rates of all high-quality grading locations are summed up and the ratio is calculated with the number of high-quality grading locations to obtain the average predicted resource recovery rate of high-quality grading locations. The required number of high-quality grading locations is then calculated by comparing the demand for waste resource utilization with the average predicted resource recovery rate of high-quality grading locations. Compare the number of high-quality grading positions with the required number of high-quality grading positions. If the number of high-quality grading positions is greater than or equal to the required number of high-quality grading positions, then the requirement is met, and there is no need to lower the screening criteria to obtain more grading positions. If the number of high-quality graded positions is less than the required number of high-quality graded positions, the requirement is not met, and the screening criteria are lowered to obtain more graded positions.

2. The method for dynamic classification and evaluation of industrial waste materials according to claim 1, characterized in that: Waste bulk density is determined by detecting the height and mass per unit area of ​​waste distribution in the waste area environment. The average height is taken as the zero point of the bulk density of the waste area environment. Locations in the waste area environment that are higher than the average height are screened out, and the mass per unit area of ​​the screened location is compared with the average height to obtain the waste bulk density. The incremental heat release from waste pyrolysis is obtained by conducting pyrolysis experiments on different wastes under the same conditions and analyzing the difference in heat release before and after pyrolysis within the same time period.

3. The method for dynamic classification and evaluation of industrial waste materials according to claim 1, characterized in that: In step S3, waste treatment experiments are conducted at the undetermined grading locations to obtain the true value of the waste resource recovery rate. After receiving the true value of the waste resource recovery rate, the system assigns a number to each undetermined grading location, merges the true value of the resource recovery rate according to the number to form a true grading dataset, and merges the output predicted value of the waste resource recovery rate according to the number to form a predicted grading dataset. The grading differences are analyzed based on the merged dataset.

4. A dynamic classification and evaluation system for industrial waste materials, used to implement the dynamic classification and evaluation method for industrial waste materials as described in any one of claims 1-3, characterized in that: It includes a data acquisition unit, a hierarchical location analysis unit, a hierarchical location determination unit, and a resource recovery unit; The data acquisition unit is used to collect environmental data of the waste area, waste composition data, waste physical property data and waste historical treatment data, and transmit them to subsequent units for analysis and processing. The classification location analysis unit is used to receive environmental data and waste composition data of the waste area and filter out the undetermined classification locations, and then pass the undetermined classification locations to the classification location determination unit. The grading location determination unit is used to receive waste physical property data and waste historical processing data, predict and compare the grading locations to be determined, and classify the grading locations to be determined into high-quality grading locations and alternative grading locations. The resource recovery unit is used to record the high-quality grading locations and count their quantities, compare them with the waste resource utilization needs, and carry out remedial treatment using alternative grading locations.

Images