CN116597239B - Processing method and system for recycled steel pipe for building - Google Patents
Processing method and system for recycled steel pipe for building Download PDFInfo
- Publication number
- CN116597239B CN116597239B CN202310880990.1A CN202310880990A CN116597239B CN 116597239 B CN116597239 B CN 116597239B CN 202310880990 A CN202310880990 A CN 202310880990A CN 116597239 B CN116597239 B CN 116597239B
- Authority
- CN
- China
- Prior art keywords
- processing
- steel pipe
- determining
- processed
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 277
- 239000010959 steel Substances 0.000 title claims abstract description 277
- 238000003672 processing method Methods 0.000 title abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 257
- 238000000034 method Methods 0.000 claims abstract description 135
- 230000008569 process Effects 0.000 claims description 117
- 230000032683 aging Effects 0.000 claims description 45
- 238000005457 optimization Methods 0.000 claims description 39
- 238000011084 recovery Methods 0.000 claims description 32
- 238000010276 construction Methods 0.000 claims description 29
- 238000013507 mapping Methods 0.000 claims description 28
- 239000000463 material Substances 0.000 claims description 28
- 238000010219 correlation analysis Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000004064 recycling Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 17
- 239000002994 raw material Substances 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 9
- 239000003086 colorant Substances 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000010365 information processing Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 4
- 229910000975 Carbon steel Inorganic materials 0.000 description 3
- 239000010962 carbon steel Substances 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000010008 shearing Methods 0.000 description 3
- 239000010935 stainless steel Substances 0.000 description 3
- 229910001220 stainless steel Inorganic materials 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012958 reprocessing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 229910000851 Alloy steel Inorganic materials 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/30—Administration of product recycling or disposal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Sustainable Development (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention provides a processing method and a processing system for a recycled steel pipe for a building, which relate to the technical field of data processing, and the method comprises the following steps: the method solves the technical problem of low efficiency in processing the recycled steel pipes in the prior art, realizes reasonable and accurate classification of the steel pipes, and further improves the processing efficiency of the recycled steel pipes.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a processing method and system of a recycled steel pipe for a building.
Background
Along with the continuous improvement of living standard, people demand better life more and more, except daily temperature people pursue life with higher quality and more comfortable, so the development of society is accelerated continuously, various buildings are obviously increased, the building materials used in the buildings are quite various, the building steel pipes are quite common, the new buildings replace old buildings, a plurality of waste steel pipe materials are produced, the existing recovery of the steel pipe materials is basically to transport the waste steel pipes to steel processing factories for reprocessing and utilizing, but the space area of the steel pipes is quite large under the condition of no treatment, so the transportation efficiency is reduced, and the direct reprocessing of the steel pipes is inconvenient.
In the prior art, the classification of the steel pipes is inaccurate, so that the technical problem of low efficiency in processing the recovered steel pipes is caused.
Disclosure of Invention
The application provides a processing method and a processing system for a recycled steel pipe for a building, which are used for solving the technical problem of low efficiency when the recycled steel pipe is processed due to inaccurate classification of the steel pipe in the prior art.
In view of the above problems, the present application provides a method and a system for processing recycled steel pipes for construction.
In a first aspect, the present application provides a method for processing recycled steel pipes for construction, the method comprising: performing multi-angle image acquisition on the steel pipe to be processed through image acquisition equipment to obtain multi-angle image information; extracting features of the multi-angle image information, and roughly classifying the steel pipes to be processed based on the image features; obtaining the number of steel pipes to be processed and local processing parameter information; analyzing the processing capacity according to the number of the steel pipes to be processed, the image characteristics and the local processing parameter information, and determining a processing batch strategy; determining a classification parameter threshold according to the processing batch strategy; reclassifying the coarse classification result based on the classification parameter threshold value to obtain a treatment classification result of the steel pipe to be treated; and matching the processing classification result with a preset processing flow list, determining processing flow parameters, and recycling the steel pipes according to the processing flow parameters.
In a second aspect, the present application provides a processing system for a recycled steel pipe for construction, the system comprising: the multi-angle image acquisition module is used for acquiring multi-angle images of the steel pipe to be processed through the image acquisition equipment to obtain multi-angle image information; the characteristic extraction module is used for extracting characteristics of the multi-angle image information and performing rough classification on the steel pipe to be processed based on the image characteristics; the information acquisition module is used for acquiring the number of the steel pipes to be processed and the local processing parameter information; the processing amount analysis module is used for carrying out processing amount analysis according to the number of the steel pipes to be processed, the image characteristics and the local processing parameter information and determining a processing batch strategy; the threshold determining module is used for determining a classification parameter threshold according to the processing batch strategy; the reclassifying module is used for reclassifying the coarse classification result based on the classification parameter threshold value to obtain a treatment classification result of the steel pipe to be treated; and the matching module is used for matching the processing classification result with a preset processing flow list, determining processing flow parameters and recycling the steel pipes according to the processing flow parameters.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the application provides a processing method and a processing system for a recycled steel pipe for a building, relates to the technical field of data processing, and solves the technical problem that in the prior art, the efficiency is low when the recycled steel pipe is processed due to inaccurate classification of the steel pipe, so that the reasonable and accurate classification of the steel pipe is realized, and the processing efficiency of the recycled steel pipe is further improved.
Drawings
FIG. 1 is a schematic flow chart of a processing method of a recycled steel pipe for construction;
FIG. 2 is a schematic flow chart of a rough classification result obtained in a processing method of a recycled steel pipe for a building;
FIG. 3 is a schematic diagram showing a process flow of determining a batch strategy in a processing method of a recycled steel pipe for construction;
FIG. 4 is a schematic flow chart of determining classification parameter threshold values corresponding to each classification number in the processing method of the recycled steel pipe for the building;
fig. 5 is a schematic flow diagram of a preset treatment flow list constructed in the processing method of the recycled steel pipe for construction;
Fig. 6 is a schematic structural view of a processing system for recycling steel pipes for construction.
Reference numerals illustrate: the device comprises a multi-angle image acquisition module 1, a feature extraction module 2, an information acquisition module 3, a throughput analysis module 4, a threshold determination module 5, a reclassification module 6 and a matching module 7.
Detailed Description
The application provides a processing method and a processing system for a recycled steel pipe for a building, which are used for solving the technical problem of low efficiency when the recycled steel pipe is processed due to inaccurate classification of the steel pipe in the prior art.
Example 1
As shown in fig. 1, an embodiment of the present application provides a processing method for a recycled steel pipe for construction, including:
step S100: performing multi-angle image acquisition on the steel pipe to be processed through image acquisition equipment to obtain multi-angle image information;
specifically, the processing method of the recycled steel pipe for the building, provided by the embodiment of the application, is applied to a processing system of the recycled steel pipe for the building, and the processing system of the recycled steel pipe for the building is in communication connection with an image acquisition device, and the image acquisition device is used for acquiring image parameters of the steel pipe to be processed currently.
For the later stage to the more accurate processing of handling of retrieving steel pipe for building, consequently at first need carry out the image acquisition of a plurality of angles to the retrieving steel pipe for building that does not carry out processing through the image acquisition equipment that is connected at present, carry out 360 full angles to the steel pipe that waits to handle at present and carry out image acquisition to 360 image information to the steel pipe that waits to handle at present to take it as multi-angle image information, for later stage realization carry out the retrieval to the steel pipe for building and handle as important reference basis.
Step S200: extracting features of the multi-angle image information, and roughly classifying the steel pipes to be processed based on the image features;
specifically, the image characteristic is extracted based on the collected multi-angle image information, the multi-angle image information is firstly input into a characteristic extraction convolution model, the color of the steel pipe, the thickness of the steel pipe and the size of the steel pipe are marked, the marked data are trained and converged based on a convolution neural network, so that the image characteristic information corresponding to the steel pipe is output, the image characteristic information comprises the color characteristic of the steel pipe, the thickness characteristic of the steel pipe and the size characteristic of the steel pipe, different types of clustering processing is carried out on all the current steel pipes to be processed according to the color characteristic of the steel pipe, the thickness characteristic of the steel pipe and the size characteristic of the steel pipe in the obtained image characteristic, and further, the steel pipes to be processed are primarily classified, namely, the rough classification is carried out according to the clustering result of the steel pipes to be processed, so that the rough classification result is obtained, and the recovery processing of the steel pipes for construction is guaranteed.
Step S300: obtaining the number of steel pipes to be processed and local processing parameter information;
specifically, after the steel pipes to be processed are roughly classified based on the obtained image features, in order to ensure the efficiency of processing the steel pipes in the later period, the number of the steel pipes to be processed currently and the local processing parameter information are required to be acquired, wherein the number of the steel pipes to be processed refers to the number of the steel pipes which are not processed, the local processing parameter information refers to the processing technological parameters, the processing capacity parameters, the adjustment range of the corresponding parameters and the like of equipment contained in a recovery steel pipe processing factory, and the basis is tamped for the recovery processing of the steel pipes for the subsequent realization.
Step S400: analyzing the processing capacity according to the number of the steel pipes to be processed, the image characteristics and the local processing parameter information, and determining a processing batch strategy;
specifically, since the processing methods corresponding to the different types of steel pipes are different, different processing batches are required to be divided for the steel pipes to be processed, further, based on the number of the obtained steel pipes to be processed, the local processing parameter information and the image characteristics of the steel pipes to be processed, analysis of the processing amounts of the steel pipes is performed on the three, that is, firstly, constraint conditions when the steel pipes are processed are determined according to the processing requirements in the local processing parameter information, in the range of the constraint conditions, the local processing process parameters, the processing capacity orders of magnitude, the image characteristics, the number of the steel pipes to be processed and the construction processing efficiency optimizing space contained in the local processing parameter information are utilized, the maximum value of the processing efficiency value is set as a target value to be optimized in the constructed processing efficiency optimizing space, a processing batch combination with the highest processing efficiency is obtained through the target value in the processing efficiency optimizing space, and the currently obtained processing batch combination is recorded as a processing batch strategy to be determined, so that the recovery processing of the steel pipes for construction is realized.
Step S500: determining a classification parameter threshold according to the processing batch strategy;
specifically, the steel pipes to be processed after coarse classification are subdivided, so that classification threshold values are required to be set for the subdivision of the steel pipes to be processed, in the determined processing batch strategy, the number of batches of the steel pipes to be processed, which correspond to the processing batch flow, are classified and then the characteristics of raw materials of the processing batch are classified, after the characteristics of color characteristics, thickness characteristics and size characteristics are classified in the coarse classification result of the steel pipes to be processed, the characteristic information of the color characteristics, thickness characteristics and size characteristics is determined from the image characteristic information in the coarse classification result, classification parameter threshold values are determined, steel pipe classification threshold values are determined according to the differences of the number of times of classification and the spans of different characteristics, namely, the more the number of times of classification is regarded as high in accuracy, the corresponding threshold value range is small, and finally the classification parameter threshold values are acquired, the classification parameter threshold values are correspondingly set according to different screening conditions of the steel pipes, so that classification with different accuracy can be achieved.
Step S600: reclassifying the coarse classification result based on the classification parameter threshold value to obtain a treatment classification result of the steel pipe to be treated;
specifically, the above-determined classification parameter threshold is taken as a limiting range, the to-be-treated steel pipe after coarse classification is reclassified, namely, the to-be-treated steel pipe after classification according to the color characteristics, the thickness characteristics and the size characteristics of the steel pipe is classified, in the classification parameter threshold, the steel pipe which is already classified into the same class in the coarse classification result is classified into finer different levels according to different levels in the classification parameter threshold by classifying the steel pipe with finer colors, and if the color of the to-be-treated steel pipe is classified into dark brown and light brown by the color number in the coarse classification, the to-be-treated steel pipe can be classified into dark brown, dark brown of reddish color, light brown of reddish color and the like by classifying the color of the steel pipe in the classification parameter threshold, so that the accuracy of the color of the to-be-treated steel pipe is finer, the treatment classification result of the to-be-treated steel pipe is finally obtained, and the accuracy of distinguishing the to-be-treated steel pipe when the construction steel pipe is treated is realized in the later stage is improved.
Step S700: and matching the processing classification result with a preset processing flow list, determining processing flow parameters, and recycling the steel pipes according to the processing flow parameters.
Specifically, the classification result of the steel pipe to be processed obtained after the subdivision is correspondingly matched with a preset processing flow list, and the construction process of the preset processing flow list can be as follows: performing correlation analysis of color characteristics, thickness characteristics and material characteristics on the recycled steel pipe data for construction in big data, correspondingly establishing a mutual mapping relation among colors, thickness and materials in the steel pipe data, further performing correlation analysis of color characteristics, thickness characteristics and aging characteristics of the steel pipe on the recycled steel pipe data for construction in big data, correspondingly establishing a mutual mapping relation among colors, thickness and aging degrees in the steel pipe data, summarizing and integrating processing information of the recycled steel pipe for history treatment, performing correlation analysis of relations among materials of the steel pipe, the aging degrees of the steel pipe and the process flow and process parameters for recycling the steel pipe in the processing information of the recycled steel pipe for history treatment, the method comprises the steps of establishing a mapping relation among materials of the steel pipe, ageing degree of the steel pipe, process flow of the steel pipe and process parameters of the steel pipe, finally establishing a mapping relation among colors, thicknesses and materials in steel pipe data, a mapping relation among colors, thicknesses and ageing degree in steel pipe data, a mapping relation among materials of the steel pipe, ageing degree of the steel pipe, process flow of the steel pipe and process parameters of the steel pipe, constructing a preset process flow list by performing influence and involvement generated by the three mapping relations, extracting and summarizing the parameters when the mapping relation in the obtained preset process flow list exists in a processing classification result, recording the parameters as the process flow parameters of the steel pipe to be processed, finally recycling the recovery steel pipe for the current building according to the determined process flow parameters, realizing reasonable and accurate classification of the steel pipe, thereby improving the processing efficiency of the recycled steel pipe.
Further, as shown in fig. 2, step S200 of the present application further includes:
step S210: inputting the multi-angle image information into a feature extraction convolution model to obtain image feature information, wherein the feature extraction convolution model is obtained by training and converging a convolution neural network through identification data of colors, thicknesses and sizes, and the image feature information comprises color features, thickness features and size features;
step S220: and clustering based on the color features, the thickness features and the size features, and performing steel pipe rough classification according to a clustering result to obtain the rough classification result.
Specifically, multi-angle image information acquired by an image acquisition device is input into a characteristic extraction coiler model, the characteristic extraction coiler model is obtained by training and converging a convolutional neural network through identification data obtained by identifying the color of a steel pipe, the thickness of the steel pipe and the size of the steel pipe contained in the multi-angle image information, the acquired multi-angle image information is equally divided in the characteristic extraction coiler model, traversing, identifying and screening are carried out according to the color data of the identified steel pipe, the thickness data of the steel pipe and the size data of the steel pipe captured by each equal block, namely, the multi-angle image information with the color data of the identified steel pipe, the thickness data of the steel pipe and the size data of the steel pipe is equally divided according to the multi-angle image information acquired by the image acquisition device, and meanwhile, the first area in the image equally divided is set as a starting point, namely, the obtained first area is marked as a zero area, then traversing is carried out from the first area, the color data, the thickness data and the size data of the steel pipe obtained in each area are matched with the color data, the thickness data and the size data of the steel pipe in the big data, so that image characteristic information containing color characteristics, thickness characteristics and size characteristics is generated, further, the color characteristics, the thickness characteristics and the size characteristics contained in the output image characteristic information are taken as classification references, different kinds of clustering processing is carried out on the steel pipe to be processed according to different color characteristics, different thickness characteristics and different size characteristics, and finally, the current steel pipe to be processed is roughly classified according to clustering results, namely, classification is carried out according to the color characteristics, the thickness characteristics and the size characteristics, and after classification is finished, the rough classification result of the steel pipe to be treated is obtained, so that the technical effect of providing important basis for recycling the steel pipe for the building in the later stage is achieved.
Further, as shown in fig. 3, step S400 of the present application further includes:
step S410: obtaining a to-be-processed requirement, local processing technological parameters and processing capacity orders according to the local processing parameter information;
step S420: determining constraint conditions according to the requirements to be processed;
step S430: based on the constraint condition, constructing a processing efficiency optimizing space by utilizing the local processing process parameters, the image characteristics, the processing capacity orders and the number of steel pipes to be processed;
step S440: and performing iterative optimization based on the maximum processing efficiency as a target value through the processing efficiency optimizing space to obtain an optimal combination of processing batches, and determining the optimal combination as the processing batch strategy.
Specifically, the local processing parameter information obtained above is used as the basis to obtain the processing requirement, the local processing process parameter and the processing capacity order, wherein the processing requirement refers to the requirement when the steel pipe is recycled, the local processing process parameter refers to the control range of the precision of the recycling equipment when the steel pipe is recycled, the processing capacity order refers to the number of the recycling steel pipes recycled by the recycling equipment when the steel pipe is recycled, further, the processing process parameter is used as the constraint condition according to the requirement when the steel pipe is recycled in the processing requirement, and the analysis is carried out on different steel pipe characteristics corresponding to different processes with relevance and the obtained image characteristics on the basis of the processing process flow of the steel pipe and the process parameter of the flow in the local processing process parameter, the method comprises the steps of measuring the correlation degree of steel pipe characteristics and image characteristics, recording the correlation degree as characteristic-parameter correlation, constructing a corresponding fitness function for a recovery processing result, local processing technological parameters and image characteristics, further adding constraint conditions into the constructed fitness function, establishing an optimization space corresponding to the fitness function with the constraint conditions, extracting the recovery technological parameter optimizing result, constructing a corresponding fitness function for the processing efficiency and the processing capacity order, the number of steel pipes to be processed and the image characteristics, constructing an optimization space corresponding to the fitness function, and adding the optimization space corresponding to the fitness function with the constraint conditions, the processing efficiency and the processing capacity order, the number of steel pipes to be processed, and reconstructing an optimization space corresponding to the fitness function by image features to perform space connection, thereby completing the construction of the optimization space of the processing efficiency.
Further, the current maximum treatment efficiency is used as a target value to carry out iterative optimization in a constructed treatment efficiency optimizing space, in the equivalent steel pipe recovery treatment process, the treatment batches capable of recovering and treating the maximum number of steel pipes are recorded as the maximum treatment efficiency, so that the comparison and extraction of the maximum value are continuously carried out in the constructed treatment efficiency optimizing space, the iteration is carried out, and finally, the optimal combination of the treatment batches selected by the iteration is set as a treatment batch strategy to be output, so that the recovery treatment of the steel pipes for the building is better in the later period.
Further, as shown in fig. 4, step S500 of the present application further includes:
step S510: determining batch dividing quantity, batch processing flow and batch raw material processing characteristics according to the batch processing strategy;
step S520: determining the dividing number of each process according to the batch dividing number and the batch processing process;
step S530: according to the dividing number of each flow and the characteristics of the raw materials of the processing batch, carrying out characteristic division on the rough classification result, and determining dividing number of each characteristic;
step S540: and determining a classification parameter threshold corresponding to each division amount based on the image characteristic information in the coarse classification result and the division amount of each characteristic.
Specifically, the above-mentioned determined process batch strategy is used to determine the batch dividing number, process batch flow and process batch raw material characteristics, the batch dividing number refers to the number of types of steel pipes to be processed, namely dividing times, the process batch flow refers to the flow of recovery processing corresponding to the steel pipes to be processed when recovery processing is performed, the recovery processing flow can include the processes of cleaning the steel pipes, crushing the steel pipes, compacting the steel pipes and shearing the steel pipes, the process batch raw material characteristics refer to the raw material characteristics corresponding to each process batch, the raw material characteristics corresponding to the cleaning process batch can be the surface stains and/or rust of the steel pipes, the raw material characteristics corresponding to the crushing process batch can be the grinding of the steel pipes to be processed with small size, the raw material characteristics corresponding to the shearing process batch can be the cutting of the steel pipes to be processed with large size, the raw material characteristics corresponding to the compacting process batch can be the grinding of the steel pipes to be processed with serious aging according to the color characteristics, the determined dividing number and the process flow can be based on the determined dividing number and the process batch, the raw material characteristics corresponding to each process batch can be further determined, the characteristic is roughly classified according to the determined characteristic of the dividing number, the raw material characteristics is further determined in the rough processing batch, the rough processing characteristic is determined in the rough processing batch component, the rough processing characteristic is determined according to the characteristic of the quality of the obtained characteristic is obtained in the rough processing batch, the rough processing batch is determined characteristic, and the rough processing characteristic is obtained in the classification characteristic is obtained, and the rough processing is obtained, and the characteristic is obtained according to the characteristic is obtained in the characteristic classification characteristic is obtained by the classification characteristic and the rough processing characteristic is obtained and the characteristic is obtained according to the characteristic is obtained and the characteristic is compared to the characteristic and the characteristic is obtained and the characteristic and is obtained according to the characteristic and the characteristic, the classification parameter threshold value corresponding to each classification number is determined according to the number of times of classification and the span between image features, namely the more the number of times of classification is, the higher the precision is, the smaller the threshold value range is, if the color of the steel pipe to be processed is classified into dark brown and light brown by the color number in coarse classification, the classification parameter threshold value can also comprise reddish dark brown, yellowish dark brown, reddish light brown, yellowish light brown and the like in the color level of the steel pipe, and four-time classification is performed, so that the precision of the color of the steel pipe to be processed is more finely classified, the subtle difference between the current steel pipes to be processed can be distinguished, and the more precise recovery processing of the building steel pipe based on the classification parameter threshold value corresponding to each classification number is achieved.
Further, as shown in fig. 5, step S700 of the present application further includes:
step S710: obtaining an experimental data set of the recycled steel pipe for the building through big data;
step S720: performing correlation analysis on the color characteristics, the thickness characteristics and the material characteristics of the experimental data set, and establishing a mapping relation between the color, the thickness and the material;
step S730: performing correlation analysis on the color characteristics, the thickness characteristics and the aging characteristics of the steel pipe on the experimental data set, and establishing a mapping relation of the color, the thickness and the aging degree;
step S740: and according to the historical recovery processing database, carrying out relation analysis on materials, ageing degrees, recovery process flows and process parameters, establishing mapping relations between the materials, ageing degrees, the process flows and the process parameters, and carrying out association on all the mapping relations to construct the preset processing flow list.
Specifically, the data of the recovered steel pipes for construction contained in the big data are extracted and summarized, thereby obtaining an experimental data set of the recovered steel pipes for construction, further, characteristic correlation analysis is carried out on the basis of the experimental data set of the big data according to the color characteristics and thickness characteristics of the steel pipes to be treated at present, the material characteristics of the steel pipes to be treated are judged according to the color characteristics and thickness characteristics of the steel pipes to be treated at present, the steel pipes for construction can be carbon steel, stainless steel, alloy steel, the exemplary carbon steel color is dark gray, the stainless steel color is silver, the thickness of the stainless steel is lower than that of the carbon steel, thereby establishing a mapping relation between the color, the thickness and the materials, namely a relation between the color, the thickness and the materials, further, carrying out correlation analysis on the basis of the experimental data set of the big data according to the color characteristics, the thickness characteristics and the aging characteristics of the steel pipes to be treated, judging the aging degree of the steel pipes to be treated according to the color characteristics and the thickness characteristics of the steel pipes to be treated at present, because the aging steel pipes to different degrees exist corresponding to the color and the thickness, namely, the thickness of the steel pipes to be treated are more than 40 percent, the history state of the aging state is more than the normal aging state is established, the ageing state is less than the normal state is established, and the ageing state is high, the ageing state is reduced, the ageing state is compared with the history state is reduced, and the normal state is formed by the information is obtained by establishing the mapping relation between the color and the ageing state is more than the normal state is high, the normal state is compared with the normal state after the ageing state is compared with the normal state, and carrying out relation analysis on the material and the ageing degree and the recovery process flow and the process parameters, so as to establish a mapping relation between the material and the ageing degree and the recovery process flow and the process parameters, namely the mutual corresponding relation between the material and the ageing degree and the recovery process flow and the process parameters.
And finally, correlating the mapping relation of the color, the thickness and the material, the mapping relation of the color, the thickness and the aging degree, and the mapping relation of the material, the aging degree and the technological process and technological parameters, and mutually connecting the overlapped parts in the three mapping relations, thereby completing the construction of a preset processing flow list.
Further, step S200 of the present application includes:
step S230: respectively collecting the external characteristics and the internal characteristics of the recycled steel pipe;
step S240: performing difference degree analysis on the external features and the internal features to determine internal and external difference degrees;
step S250: when the internal and external difference exceeds a preset threshold, determining a correction coefficient according to the external characteristic and the internal characteristic;
step S260: and correcting the image characteristics based on the correction coefficient.
Specifically, because the inside and outside of the steel pipe are different in sometimes contact environment, the aging degree and the stain existing inside and outside the steel pipe are different, therefore, the external characteristics of the recovered steel pipe, namely the aging degree and the stain existing on the outer surface of the steel pipe and the internal characteristics of the recovered steel pipe, namely the aging degree and the stain existing on the inner surface of the steel pipe are respectively collected, further, the external characteristics of the steel pipe are compared with the internal characteristics of the steel pipe, the inside and outside aging degree and the stain are compared, so that the difference between the two is compared, the inside and outside difference degree is determined, namely the aging degree of the inner surface of the steel pipe, the aging degree of the stain and the outer surface, the difference between the stain and the stain is preset when the time is used, the preset threshold is preset by a related technician according to the data quantity of the inside and the outside degree of the steel pipe and the stain in big data, if the current difference between the inside and the outside of the steel pipe to be treated exceeds the preset threshold, the correction coefficient is determined according to the external characteristics and the internal characteristics of the current steel pipe to be treated, namely the aging degree and the stain of the external characteristics and the internal characteristics are compared, the inside and the aging degree of the steel pipe are selected, the aging degree and the highest external characteristics of the stain are compared, so that the inside and outside characteristics of the steel pipe and the stain are completely corrected according to the aging degree and the largest, and the quality of the steel pipe is not completely treated, and the quality is completely corrected.
Further, step S430 of the present application includes:
step S431: determining a treatment process flow and flow process parameters according to the local treatment process parameters;
step S432: obtaining the corresponding steel pipe characteristics of each process according to the treatment process flow and the process parameters of the flow;
step S433: performing correlation analysis by utilizing the steel pipe characteristics corresponding to each process and the image characteristics to determine characteristic-parameter correlation;
step S434: based on the characteristic-parameter correlation, a first fitness function of a recovery processing result, local processing process parameters and image characteristics is established;
step S435: adding the constraint condition into the first fitness function, establishing a first-level optimization space, and obtaining a process parameter optimization result;
step S436: based on the optimizing result of the technological parameter, a second fitness function of the processing efficiency, the processing capacity order of magnitude, the number of steel pipes to be processed and the image characteristics is established, and a second-level optimizing space is established;
step S437: and connecting the primary optimization space with the secondary optimization space to construct the processing efficiency optimizing space.
Specifically, the processing technological process and the flow technological parameters are determined on the basis of local processing technological parameters, the processing technological process can comprise the processes of cleaning, crushing, shearing, compacting and the like of the steel pipes, the flow technological parameters refer to all parameters contained in the processing technological process, in the process of recycling the steel pipes, the steel pipe characteristics contained in the processing technological process and the flow technological parameters are respectively and correspondingly extracted, the steel pipe characteristics corresponding to all the processes are obtained, the correlation analysis is carried out on the steel pipe characteristics corresponding to all the processes contained in the recycling steel pipe processes and the extracted steel pipe image characteristics, the extraction integration is carried out on the steel pipes which accord with the steel pipe characteristics existing in the processes and accord with the image characteristics, the characteristic-parameter correlation is determined according to the extracted steel pipe information, and on the basis of the characteristic-parameter correlation, establishing a first fitness function of the recovery processing result of the steel pipe and the local processing process parameters and image characteristics, wherein the first fitness function represents a function of the local processing process parameters and the characteristic scores of the image characteristics so as to allow the recovery processing result to adapt to the function environment where the recovery processing result is positioned, further, adding constraint conditions into the first fitness function to establish a first-level optimization space, wherein the first-level optimization space is used for optimizing the effect of the recovery processing steel pipe, namely, finding out the process combination result meeting the processing requirements based on the current characteristics, extracting the process combination result meeting the processing requirements, and establishing a second fitness function of the processing efficiency and the processing capacity order, the number of the steel pipes to be processed and the image characteristics according to the process parameter optimization result extracted in the optimization space, wherein the second fitness function represents the processing capacity order, the number of the steel pipes to be processed and the feature score of the image features are functions, so that the processing efficiency is allowed to adapt to the function environment where the steel pipes are located, namely the recycling efficiency is optimized, the image features are subjected to batch processing for multiple times to improve the efficiency, the construction of the secondary optimization space is completed, and finally the constructed primary optimization space is connected with the secondary optimization space, namely the primary optimization space is analyzed with the secondary optimization space, so that the primary optimization space and the secondary optimization space are matched and connected according to the relevant degree of closeness of the primary optimization space and the secondary optimization space, the effect requirement of the recycling of the steel pipes is met, and the efficiency requirement of the recycling of the steel pipes is met.
Example 2
Based on the same inventive concept as the processing method of a recycled steel pipe for construction in the foregoing embodiments, as shown in fig. 6, the present application provides a processing system of a recycled steel pipe for construction, the system comprising:
the multi-angle image acquisition module 1 is used for acquiring multi-angle images of the steel pipe to be processed through the image acquisition equipment to obtain multi-angle image information;
the characteristic extraction module 2 is used for extracting characteristics of the multi-angle image information and performing rough classification on the steel pipe to be processed based on the image characteristics;
the information acquisition module 3 is used for acquiring the number of the steel pipes to be processed and the local processing parameter information;
the processing amount analysis module 4 is used for carrying out processing amount analysis according to the number of the steel pipes to be processed, the image characteristics and the local processing parameter information, and determining a processing batch strategy;
a threshold determining module 5, where the threshold determining module 5 is configured to determine a classification parameter threshold according to the processing batch policy;
the reclassifying module 6 is used for reclassifying the coarse classification result based on the classification parameter threshold value to obtain a treatment classification result of the steel pipe to be treated;
The matching module 7 is used for matching the processing classification result with a preset processing flow list, determining processing flow parameters and recycling the steel pipes according to the processing flow parameters.
Further, the system further comprises:
the input module is used for inputting the multi-angle image information into a feature extraction convolution model to obtain image feature information, wherein the feature extraction convolution model is obtained by training and converging a convolution neural network through identification data of colors, thicknesses and sizes, and the image feature information comprises color features, thickness features and size features;
and the steel pipe coarse classification module is used for clustering based on the color characteristics, the thickness characteristics and the size characteristics, and performing coarse classification on the steel pipes according to the clustering result to obtain the coarse classification result.
Further, the system further comprises:
the information processing module is used for obtaining a to-be-processed requirement, local processing technological parameters and processing capacity orders according to the local processing parameter information;
the constraint module is used for determining constraint conditions according to the requirements to be processed;
The optimizing module is used for constructing a processing efficiency optimizing space by utilizing the local processing process parameters, the image characteristics, the processing capacity orders and the number of the steel pipes to be processed based on the constraint conditions;
and the strategy determining module is used for carrying out iterative optimization based on the maximum target value of the processing efficiency through the processing efficiency optimizing space to obtain the optimal combination of the processing batches and determining the optimal combination as the processing batch strategy.
Further, the system further comprises:
the processing module is used for determining batch dividing quantity, batch processing flow and batch raw material processing characteristics according to the batch processing strategy;
the dividing module is used for determining the dividing number of each process according to the batch dividing number and the batch processing flow;
the characteristic dividing module is used for carrying out characteristic division on the coarse classification result according to the dividing quantity of each flow and the characteristics of the raw materials of the processing batch, and determining dividing quantity of each characteristic;
and the classification parameter threshold determining module is used for determining classification parameter thresholds corresponding to the division amount times based on the image characteristic information in the coarse classification result and the division amount times of the characteristics.
Further, the system further comprises:
the experimental data set module is used for obtaining an experimental data set of the recovery steel pipe for the building through big data;
the first correlation analysis module is used for performing correlation analysis on the color characteristics, the thickness characteristics and the material characteristics of the experimental data set and establishing a mapping relation between the color, the thickness and the material;
the second correlation analysis module is used for performing correlation analysis on the color characteristics, the thickness characteristics and the aging characteristics of the steel pipe on the experimental data set, and establishing a mapping relation between the color, the thickness and the aging degree;
and the mapping relation module is used for carrying out relation analysis on materials and ageing degrees, a recovery process flow and process parameters according to the historical recovery processing database, establishing mapping relations between the materials and ageing degrees, the process flow and the process parameters, and carrying out association on all the mapping relations to construct the preset processing flow list.
Further, the system further comprises:
the characteristic acquisition module is used for respectively acquiring the external characteristics and the internal characteristics of the recycled steel pipe;
The difference degree analysis module is used for carrying out difference degree analysis on the external characteristics and the internal characteristics and determining internal and external difference degrees;
the correction coefficient module is used for determining a correction coefficient according to the external characteristics and the internal characteristics when the internal and external difference exceeds a preset threshold;
and the correction module is used for correcting the image characteristics based on the correction coefficient.
Further, the system further comprises:
the parameter determining module is used for determining a processing process flow and flow process parameters according to the local processing process parameters;
the process characteristic module is used for obtaining the steel pipe characteristics corresponding to each process according to the treatment process flow and the process parameters of the flow;
the third correlation analysis module is used for carrying out correlation analysis on the steel pipe characteristics corresponding to each process and the image characteristics to determine characteristic-parameter correlation;
the first fitness function module is used for establishing a first fitness function of the recovery processing result, the local processing process parameters and the image characteristics based on the characteristic-parameter correlation;
The first-level optimization space module is used for adding the constraint conditions into the first fitness function, establishing a first-level optimization space and obtaining a process parameter optimizing result;
the secondary optimization space module is used for establishing a second fitness function of the processing efficiency, the processing capacity order of magnitude, the number of steel pipes to be processed and the image characteristics based on the process parameter optimizing result, and constructing a secondary optimization space;
and the optimizing space construction module is used for connecting the primary optimizing space with the secondary optimizing space to construct the processing efficiency optimizing space.
From the foregoing detailed description of a processing method of a recycled steel pipe for construction, it will be apparent to those skilled in the art that a processing system of a recycled steel pipe for construction in this embodiment is relatively simple in description, and the relevant points are referred to in the description of the method section, since the apparatus disclosed in the embodiments corresponds to the method disclosed in the embodiments.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A method of processing a recycled steel pipe for construction, the method comprising:
performing multi-angle image acquisition on the steel pipe to be processed through image acquisition equipment to obtain multi-angle image information;
extracting features of the multi-angle image information, and roughly classifying the steel pipes to be processed based on the image features;
obtaining the number of steel pipes to be processed and local processing parameter information;
analyzing the processing capacity according to the number of the steel pipes to be processed, the image characteristics and the local processing parameter information, and determining a processing batch strategy;
determining a classification parameter threshold according to the processing batch strategy;
reclassifying the coarse classification result based on the classification parameter threshold value to obtain a treatment classification result of the steel pipe to be treated;
matching the processing classification result with a preset processing flow list, determining processing flow parameters, and recycling the steel pipes according to the processing flow parameters;
the method for determining the processing batch strategy comprises the following steps of:
obtaining a to-be-processed requirement, local processing technological parameters and processing capacity orders according to the local processing parameter information;
Determining constraint conditions according to the requirements to be processed;
based on the constraint condition, constructing a processing efficiency optimizing space by utilizing the local processing process parameters, the image characteristics, the processing capacity orders and the number of steel pipes to be processed;
performing iterative optimization based on the maximum processing efficiency as a target value through the processing efficiency optimizing space to obtain an optimal combination of processing batches, and determining the optimal combination as the processing batch strategy;
based on the constraint condition, the local processing process parameters, image characteristics, processing capacity orders of magnitude and the number of steel pipes to be processed are utilized to construct a processing efficiency optimizing space, and the method comprises the following steps:
determining a treatment process flow and flow process parameters according to the local treatment process parameters;
obtaining the corresponding steel pipe characteristics of each process according to the treatment process flow and the process parameters of the flow;
performing correlation analysis by utilizing the steel pipe characteristics corresponding to each process and the image characteristics to determine characteristic-parameter correlation;
based on the characteristic-parameter correlation, a first fitness function of a recovery processing result, local processing process parameters and image characteristics is established;
adding the constraint condition into the first fitness function, establishing a first-level optimization space, and obtaining a process parameter optimization result;
Based on the optimizing result of the technological parameter, a second fitness function of the processing efficiency, the processing capacity order of magnitude, the number of steel pipes to be processed and the image characteristics is established, and a second-level optimizing space is established;
and connecting the primary optimization space with the secondary optimization space to construct the processing efficiency optimizing space.
2. The method of claim 1, wherein the feature extraction of the multi-angle image information and the coarse classification of the steel pipe to be processed based on the image features comprises:
inputting the multi-angle image information into a feature extraction convolution model to obtain image feature information, wherein the feature extraction convolution model is obtained by training and converging a convolution neural network through identification data of colors, thicknesses and sizes, and the image feature information comprises color features, thickness features and size features;
and clustering based on the color features, the thickness features and the size features, and performing steel pipe rough classification according to a clustering result to obtain the rough classification result.
3. The method of claim 1, wherein determining a classification parameter threshold according to the process batch policy comprises:
determining batch dividing quantity, batch processing flow and batch raw material processing characteristics according to the batch processing strategy;
Determining the dividing number of each process according to the batch dividing number and the batch processing process;
according to the dividing number of each flow and the characteristics of the raw materials of the processing batch, carrying out characteristic division on the rough classification result, and determining dividing number of each characteristic;
and determining a classification parameter threshold corresponding to each division amount based on the image characteristic information in the coarse classification result and the division amount of each characteristic.
4. The method of claim 1, wherein matching the process classification result with a predetermined process flow list, prior to determining the process flow parameters, comprises:
obtaining an experimental data set of the recycled steel pipe for the building through big data;
performing correlation analysis on the color characteristics, the thickness characteristics and the material characteristics of the experimental data set, and establishing a mapping relation between the color, the thickness and the material;
performing correlation analysis on the color characteristics, the thickness characteristics and the aging characteristics of the steel pipe on the experimental data set, and establishing a mapping relation of the color, the thickness and the aging degree;
and according to the historical recovery processing database, carrying out relation analysis on materials, ageing degrees, recovery process flows and process parameters, establishing mapping relations between the materials, ageing degrees, the process flows and the process parameters, and carrying out association on all the mapping relations to construct the preset processing flow list.
5. The method of claim 1, wherein the method further comprises:
respectively collecting the external characteristics and the internal characteristics of the recycled steel pipe;
performing difference degree analysis on the external features and the internal features to determine internal and external difference degrees;
when the internal and external difference exceeds a preset threshold, determining a correction coefficient according to the external characteristic and the internal characteristic;
and correcting the image characteristics based on the correction coefficient.
6. A system for processing recycled steel pipes for construction, the system comprising:
the multi-angle image acquisition module is used for acquiring multi-angle images of the steel pipe to be processed through the image acquisition equipment to obtain multi-angle image information;
the characteristic extraction module is used for extracting characteristics of the multi-angle image information and performing rough classification on the steel pipe to be processed based on the image characteristics;
the information acquisition module is used for acquiring the number of the steel pipes to be processed and the local processing parameter information;
the processing amount analysis module is used for carrying out processing amount analysis according to the number of the steel pipes to be processed, the image characteristics and the local processing parameter information and determining a processing batch strategy;
The threshold determining module is used for determining a classification parameter threshold according to the processing batch strategy;
the reclassifying module is used for reclassifying the coarse classification result based on the classification parameter threshold value to obtain a treatment classification result of the steel pipe to be treated;
the matching module is used for matching the processing classification result with a preset processing flow list, determining processing flow parameters and recycling the steel pipes according to the processing flow parameters;
wherein the throughput analysis module comprises:
the information processing module is used for obtaining a to-be-processed requirement, local processing technological parameters and processing capacity orders according to the local processing parameter information;
the constraint module is used for determining constraint conditions according to the requirements to be processed;
the optimizing module is used for constructing a processing efficiency optimizing space by utilizing the local processing process parameters, the image characteristics, the processing capacity orders and the number of the steel pipes to be processed based on the constraint conditions;
the strategy determining module is used for carrying out iterative optimization based on a target value of the maximum processing efficiency through the processing efficiency optimizing space to obtain an optimal combination of processing batches and determining the optimal combination as the processing batch strategy;
The parameter determining module is used for determining a processing process flow and flow process parameters according to the local processing process parameters;
the process characteristic module is used for obtaining the steel pipe characteristics corresponding to each process according to the treatment process flow and the process parameters of the flow;
the third correlation analysis module is used for carrying out correlation analysis on the steel pipe characteristics corresponding to each process and the image characteristics to determine characteristic-parameter correlation;
the first fitness function module is used for establishing a first fitness function of the recovery processing result, the local processing process parameters and the image characteristics based on the characteristic-parameter correlation;
the first-level optimization space module is used for adding the constraint conditions into the first fitness function, establishing a first-level optimization space and obtaining a process parameter optimizing result;
the secondary optimization space module is used for establishing a second fitness function of the processing efficiency, the processing capacity order of magnitude, the number of steel pipes to be processed and the image characteristics based on the process parameter optimizing result, and constructing a secondary optimization space;
And the optimizing space construction module is used for connecting the primary optimizing space with the secondary optimizing space to construct the processing efficiency optimizing space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310880990.1A CN116597239B (en) | 2023-07-18 | 2023-07-18 | Processing method and system for recycled steel pipe for building |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310880990.1A CN116597239B (en) | 2023-07-18 | 2023-07-18 | Processing method and system for recycled steel pipe for building |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116597239A CN116597239A (en) | 2023-08-15 |
| CN116597239B true CN116597239B (en) | 2023-10-27 |
Family
ID=87606651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310880990.1A Active CN116597239B (en) | 2023-07-18 | 2023-07-18 | Processing method and system for recycled steel pipe for building |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116597239B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132828B (en) * | 2023-08-30 | 2024-03-19 | 常州润来科技有限公司 | Automatic classification method and system for solid waste in copper pipe machining process |
| CN117218424A (en) * | 2023-09-12 | 2023-12-12 | 陕西丝路创城建设有限公司 | Material management method and system in photovoltaic power station construction |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318421A (en) * | 2014-11-20 | 2015-01-28 | 北京盈创高科新技术发展有限公司 | System and method for realizing reverse logistics in field of recycling of renewable resources |
| CN111047387A (en) * | 2019-10-29 | 2020-04-21 | 深圳市爱博绿环保科技有限公司 | Recovery management method and device |
| CN111598833A (en) * | 2020-04-01 | 2020-08-28 | 江汉大学 | Method and device for detecting defects of target sample and electronic equipment |
| CN114925756A (en) * | 2022-05-07 | 2022-08-19 | 上海燕龙基再生资源利用有限公司 | Waste glass classified recovery method and device based on fine management |
| CN116174342A (en) * | 2023-04-25 | 2023-05-30 | 广州赛志系统科技有限公司 | Board sorting and packaging method, terminal and board production line |
-
2023
- 2023-07-18 CN CN202310880990.1A patent/CN116597239B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318421A (en) * | 2014-11-20 | 2015-01-28 | 北京盈创高科新技术发展有限公司 | System and method for realizing reverse logistics in field of recycling of renewable resources |
| CN111047387A (en) * | 2019-10-29 | 2020-04-21 | 深圳市爱博绿环保科技有限公司 | Recovery management method and device |
| CN111598833A (en) * | 2020-04-01 | 2020-08-28 | 江汉大学 | Method and device for detecting defects of target sample and electronic equipment |
| CN114925756A (en) * | 2022-05-07 | 2022-08-19 | 上海燕龙基再生资源利用有限公司 | Waste glass classified recovery method and device based on fine management |
| CN116174342A (en) * | 2023-04-25 | 2023-05-30 | 广州赛志系统科技有限公司 | Board sorting and packaging method, terminal and board production line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116597239A (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116597239B (en) | Processing method and system for recycled steel pipe for building | |
| CN110245802B (en) | Cigarette empty-head rate prediction method and system based on improved gradient lifting decision tree | |
| CN101710235B (en) | Method for automatically identifying and monitoring on-line machined workpieces of numerical control machine tool | |
| CN113989279A (en) | Plastic film quality detection method based on artificial intelligence and image processing | |
| CN107179310B (en) | Raman spectrum characteristic peak recognition methods based on robust noise variance evaluation | |
| CN105630743A (en) | Spectrum wave number selection method | |
| CN114997608A (en) | Production efficiency assessment method and system based on industrial chain data analysis | |
| CN113177313B (en) | Intelligent classifying and disassembling method for multi-type mobile phone | |
| CN111898637B (en) | Feature selection algorithm based on Relieff-DDC | |
| CN114596061A (en) | Project data management method and system based on big data | |
| CN116843955A (en) | Microorganism classification and identification method and system based on computer vision | |
| CN112906738A (en) | Water quality detection and treatment method | |
| CN111461513A (en) | Government open data evaluation method and data analysis platform | |
| CN115169453A (en) | Hot continuous rolling width prediction method based on density clustering and depth residual error network | |
| CN116740044B (en) | Copper pipe milling surface processing method and system based on visual detection and control | |
| CN117095247B (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| CN114519651A (en) | Intelligent power distribution method based on electric power big data | |
| CN112418522B (en) | Industrial heating furnace steel temperature prediction method based on three-branch integrated prediction model | |
| CN115933534B (en) | Numerical control intelligent detection system and method based on Internet of things | |
| CN110427019B (en) | Industrial process fault classification method and control device based on multivariate discriminant analysis | |
| CN116883184A (en) | Financial tax intelligent analysis method based on big data | |
| CN116152709A (en) | Intelligent grading pretreatment method and system for decoration garbage | |
| CN115883182A (en) | Method and system for improving network security situation element identification efficiency | |
| CN112735532A (en) | Metabolite identification system based on molecular fingerprint prediction and application method thereof | |
| CN113298148A (en) | Ecological environment evaluation-oriented unbalanced data resampling method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |