CN112101149B - Building waste classification method and system - Google Patents
Building waste classification method and system Download PDFInfo
- Publication number
- CN112101149B CN112101149B CN202010899036.3A CN202010899036A CN112101149B CN 112101149 B CN112101149 B CN 112101149B CN 202010899036 A CN202010899036 A CN 202010899036A CN 112101149 B CN112101149 B CN 112101149B
- Authority
- CN
- China
- Prior art keywords
- information
- output result
- construction waste
- output
- waste
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The invention discloses a building rubbish classification method and a system, which are used for obtaining first image information, inputting the first image information into a first classification model and obtaining first output information: including a first output result and a second output result; obtaining volatile gas component information of the construction waste; inputting the first output result and the volatile gas component information into a second classification model to obtain second output information: the first output result and the second output result are included, and a fifth output result is obtained according to the second output result and the fourth output result; constructing a training data set according to the fifth output result and the volatile gas component information; inputting a training data set into a first training model to obtain third output information, wherein the third output information comprises pollution level information of harmful garbage; and treating the construction waste according to the pollution level information of the harmful waste. The technical effects of effectively recycling the recyclable construction waste and protecting the environment are achieved.
Description
Technical Field
The invention relates to the field of garbage classification, in particular to a building garbage classification method and system.
Background
While the building industry in China is rapidly developed and grown, the quantity of building garbage throwing points and landfill sites in China is also increased rapidly. The construction waste refers to the general name of dregs, waste concrete, waste bricks and stones and other wastes generated in the production activities of the construction industry such as demolition, construction, decoration and repair, and mainly comprises recoverable resources such as concrete, reinforcing steel bars and building blocks and other harmful substances.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
in the existing building construction technology, because of the imperfect building garbage recycling system in China, the building garbage is directly buried or stacked, and serious environmental pollution is caused.
Disclosure of Invention
The embodiment of the application provides a construction waste classification method and a system, solves the problem of serious environmental pollution caused by direct landfill or stacking treatment of construction waste in the prior art, achieves classification treatment of the construction waste, and achieves the technical effects of effectively recycling the recyclable construction waste and protecting the environment.
In view of the above problems, the present application provides a method and a system for classifying construction waste.
In a first aspect, an embodiment of the present application provides a method for classifying construction waste, where the method includes: obtaining first image information, wherein the first image information comprises image information of construction waste; inputting the first image information into a first classification model to obtain first output information, wherein the first output information comprises a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste; obtaining volatile gas component information of the construction waste; inputting the first output result and the volatile gas component information into a second classification model to obtain second output information, wherein the second output information comprises a third output result and a fourth output result, the third output result is the result that the construction waste is harmless waste, and the fourth output result is the result that the construction waste is harmful waste; obtaining a fifth output result according to the second output result and the fourth output result; constructing a training data set according to the fifth output result and the volatile gas component information; inputting the training data set into a first training model to obtain third output information, wherein the third output information comprises pollution level information of harmful garbage; and treating the construction waste according to the pollution level information of the harmful waste.
In another aspect, the present application further provides a construction waste classification system, wherein the system includes: a first obtaining unit configured to obtain first image information including image information of construction waste; a first input unit, configured to input the first image information into a first classification model to obtain first output information, where the first output information includes a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste; a second obtaining unit, configured to obtain volatile gas component information of the construction waste; a second input unit, configured to input the first output result and the volatile gas component information into a second classification model to obtain second output information, where the second output information includes a third output result and a fourth output result, the third output result is a result that the construction waste is harmless waste, and the fourth output result is a result that the construction waste is harmful waste; a third obtaining unit, configured to obtain a fifth output result according to the second output result and the fourth output result; a fourth obtaining unit, configured to construct a training data set according to the fifth output result and the volatile gas component information. A third input unit, configured to input the training data set into a first training model to obtain third output information, where the third output information includes pollution level information of harmful garbage; the first treatment unit is used for treating the construction waste according to the pollution level information of the harmful waste.
In a third aspect, the present invention provides a construction waste classification system, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the method comprises the steps of obtaining first image information of the construction waste, inputting the first image information into a first classification model to preliminarily judge whether the construction waste is harmful waste or harmless waste, inputting a result of the harmless waste and construction waste volatile gas component information into a second classification model, and training the first training model according to the result of the harmful waste output, the result of the harmful waste judged by the first classification model and the volatile gas component information construction data training set, so that the training model can accurately judge the pollution level grade of the construction waste, the construction waste can be accurately and effectively classified, and the technical effects of effectively recycling the recyclable construction waste and protecting the environment are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flow chart of a construction waste classification method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of obtaining a first classification model in a construction waste classification method according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating a process of obtaining a second classification model in the construction waste classification method according to the embodiment of the present application;
FIG. 4 is a schematic flow chart illustrating a process of obtaining an accurate second classification model in the construction waste classification method according to the embodiment of the present application;
FIG. 5 is a schematic flowchart illustrating a training data set processing method in the building garbage classification method according to the embodiment of the present application;
FIG. 6 is a schematic flow chart illustrating a process of obtaining a more accurate training data set in a method for classifying construction waste according to an embodiment of the present application;
fig. 7 is a schematic flowchart of a method for classifying construction waste according to an embodiment of the present application, further determining pollution level information of the harmful waste;
fig. 8 is a schematic flow chart illustrating further determination of the pollution level information of the harmful garbage in the construction garbage classification method according to the embodiment of the present application;
fig. 9 is a schematic structural diagram of a construction waste classification system according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a first input unit 12, a second obtaining unit 13, a second input unit 14, a third obtaining unit 15, a fourth obtaining unit 16, a third input unit 17, a first processing unit 18, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, a bus interface 306.
Detailed Description
The embodiment of the application provides a construction waste classification method and a system, solves the problem of serious environmental pollution caused by direct landfill or stacking treatment of construction waste in the prior art, achieves classification treatment of the construction waste, and achieves the technical effects of effectively recycling the recyclable construction waste and protecting the environment. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
The technical scheme provided by the application has the following general idea:
the embodiment of the application provides a building rubbish classification method, which comprises the following steps: obtaining first image information, wherein the first image information comprises image information of construction waste; inputting the first image information into a first classification model to obtain first output information, wherein the first output information comprises a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste; obtaining volatile gas component information of the construction waste; inputting the first output result and the volatile gas component information into a second classification model to obtain second output information, wherein the second output information comprises a third output result and a fourth output result, the third output result is the result that the construction waste is harmless waste, and the fourth output result is the result that the construction waste is harmful waste; obtaining a fifth output result according to the second output result and the fourth output result; constructing a training data set according to the fifth output result and the volatile gas component information; inputting the training data set into a first training model to obtain third output information, wherein the third output information comprises pollution level information of harmful garbage; and treating the construction waste according to the pollution level information of the harmful waste.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides a building waste classification method, where the method includes:
step S100: obtaining first image information, wherein the first image information comprises image information of construction waste;
in particular, the image is a kind of similarity, vividness description or portrayal of an objective object, which is the most commonly used information carrier in human social activities, and the first image information is information of a clear image of construction waste automatically obtained by the image capturing device. The image capturing apparatus is an image pickup device having a clear image pickup unit, and is not particularly limited herein.
Step S200: inputting the first image information into a first classification model to obtain first output information, wherein the first output information comprises a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste;
specifically, the first classification model is a machine learning model obtained by training a plurality of sets of data, each set of training data in the plurality of sets including: image information of construction waste and identification information for identifying whether the construction waste is harmful. Through the training of a large amount of training data, and then obtain more accurate machine learning model and handle first image information, and then reach right first image information carries out the effect of accurate processing, and then accurate right construction waste judges, obtains the classification effect of accurate harmful rubbish and harmless rubbish, and then reaches effectively to recoverable construction waste recycle, environmental protection's technological effect.
Step S300: obtaining volatile gas component information of the construction waste;
specifically speaking, the volatile gas is the gas composition information that building rubbish volatilizees, through right the gas composition information that volatilizees is judged, can effectively distinguish the building rubbish information that can't be distinguished through picture information, and then reach the effect to whether building rubbish carries out more accurate judgement for harmful rubbish.
Step S400: inputting the first output result and the volatile gas component information into a second classification model to obtain second output information, wherein the second output information comprises a third output result and a fourth output result, the third output result is the result that the construction waste is harmless waste, and the fourth output result is the result that the construction waste is harmful waste;
specifically, the second classification model is constructed based on a logistic regression model, and specifically, a coordinate system is established with the first output result as an abscissa and the volatile gas component information as an ordinate, and a logistic regression line is obtained based on the logistic regression model through the coordinate system. One side of the logistic regression line represents a third output result, and the third output result is a result that the construction waste is harmless waste; the other side of the logistic regression line represents a fourth output result, and the fourth output result is a result that the construction waste is harmful waste. The construction waste judged by the first classification model is further judged according to the result that the construction waste is harmless waste, so that the effect of accurately judging whether the construction waste is harmful waste is achieved, and the technical effects of effectively recycling the recyclable construction waste and protecting the environment are achieved.
Step S500: obtaining a fifth output result according to the second output result and the fourth output result;
specifically, the second output result is a result of judging that the construction waste is harmful waste according to the image information of the construction waste by the first classification model, the fourth output result is a result of judging that the construction waste is harmful waste according to the volatile gas component of the construction waste by the second classification model, and a fifth output result is obtained by combining the image information and the volatile gas component information of the construction waste.
Step S600: and constructing a training data set according to the fifth output result and the volatile gas component information.
Specifically, a fifth output result and the volatile gas component information are used as a set of training data, a plurality of sets of training data of a combination of a large number of fifth output results and the volatile gas component information form a training data set, the training data set is used for training of a first training model, the training model is enabled to have enough experience to process the input construction waste information, accurate pollution level information of harmful waste is obtained to reasonably and accurately classify the construction waste, and therefore the technical effects of effectively recycling the recyclable construction waste and protecting the environment are achieved.
Step S700: inputting the training data set into a first training model to obtain third output information, wherein the third output information comprises pollution level information of harmful garbage;
specifically, the first training model is a Neural network model, which is a Neural network model in machine learning, and a Neural Network (NN) is a complex Neural network system formed by widely connecting a large number of simple processing units (called neurons), which reflects many basic features of human brain functions, and is a highly complex nonlinear dynamical learning system. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (Artificial Neural Networks) are a description of the first-order properties of the human brain system. Briefly, it is a mathematical model. And inputting the fifth output result and the volatile gas component information into a neural network model through training of a large number of training data sets, and outputting the pollution level information of the harmful garbage. More specifically, the training process is a supervised learning process, each set of supervised data includes the fifth output result, the volatile gas component information and identification information for identifying the pollution level of the construction waste, the fifth output result and the volatile gas component information are input into a neural network model, the neural network model outputs pollution level information of harmful waste, and whether the output information is consistent with the identification information for identifying the pollution level of the construction waste is judged, if so, supervised learning of the next set of data is performed; if the output information is inconsistent with the identification information for identifying the pollution level of the building rubbish, the neural network model carries out self correction and adjustment until the obtained output information is consistent with the identification information for identifying the pollution level of the building rubbish, the group of data supervised learning is ended, and the next group of data supervised learning is carried out; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through the supervised learning of the neural network model, the neural network model can process the input data more accurately, the output information of the pollution level of the construction waste is more accurate, the accurate pollution level information of the harmful waste is obtained to reasonably and accurately classify the construction waste, and the technical effects of effectively recycling the recyclable construction waste and protecting the environment are achieved.
Step S800: and treating the construction waste according to the pollution level information of the harmful waste.
Specifically, the method comprises the following steps: according to the difference of the pollution levels of the construction waste, the construction waste is treated, and the method specifically comprises the following steps: carrying out harmless treatment on the construction waste with low pollution level, and further converting the construction waste into harmless waste for recycling; the construction waste with high pollution level is treated in a centralized way, the harm of the construction waste is minimized, and the construction waste with different pollution levels is classified and treated according to the practical teaching, so that the technical effect of protecting the environment is achieved.
As shown in fig. 2, in order to obtain the first classification model, an embodiment S200 of the present application further includes:
step S210: inputting first image information into the first classification model, wherein the first classification model is obtained by training multiple groups of training data, and each group of training data in the multiple groups comprises: image information of construction waste and identification information for identifying whether the construction waste is harmful;
step S220: obtaining first output information of the first classification model, wherein the first output information comprises a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste;
specifically, the first classification model is a machine learning model obtained by training a plurality of sets of training data, each set of training data in the plurality of sets including: image information of construction waste and identification information for identifying whether the construction waste is harmful. The first output information of the training model comprises a first output result and a second output result, the first output result is the result that the construction waste is harmless waste, and the second output result is the result that the construction waste is harmful waste; through the training of a large amount of training data, and then obtain more accurate machine learning model and handle first image information, and then reach right first image information carries out the effect of accurate processing, and then accurate right construction waste judges, obtains the classification effect of accurate harmful rubbish and harmless rubbish, and then reaches effectively to recoverable construction waste recycle, environmental protection's technological effect.
As shown in fig. 3, in order to obtain the second classification model, step S400 in this embodiment of the present application further includes:
step S410: taking the first output result as an abscissa;
step S420: taking the volatile gas component information as a vertical coordinate;
step S430: obtaining a logistic regression line according to the abscissa and the ordinate by adopting a logistic regression model, wherein the logistic regression line comprises a first position and a first angle, and the first position and the first angle are located in a coordinate system constructed by the abscissa and the ordinate; wherein one side of the logistic regression line represents a first output result and the other side of the logistic regression line represents a second output result, wherein the first output result and the second output result are different.
Specifically, the second classification model is constructed based on a logistic regression model, and specifically, a coordinate system is established with the first output result as an abscissa and the volatile gas component information as an ordinate, and a logistic regression line is obtained based on the logistic regression model through the coordinate system. One side of the logistic regression line represents a third output result, and the third output result is a result that the construction waste is harmless waste; the other side of the logistic regression line represents a fourth output result, and the fourth output result is a result that the construction waste is harmful waste. The logistic regression line comprises a first position and a first angle, the first position and the first angle are located in a coordinate system formed by the abscissa and the ordinate, the logistic regression line is controlled by the first position and the first angle, and further judgment is carried out on a result that the construction waste judged by the first classification model is harmless waste, so that the effect of accurately judging whether the construction waste is harmful waste is achieved, and the technical effects of effectively recycling the recyclable construction waste and protecting the environment are achieved.
As shown in fig. 4, in order to obtain an accurate second classification model, step S430 in this embodiment of the present application further includes:
step S431: obtaining content information of sulfate ions in the volatile gas component information;
step S432: obtaining a threshold value of a predetermined sulfate ion content;
step S433: judging whether the content of sulfate ions in the volatile gas component information exceeds a threshold value of the preset sulfate ion content;
step S434: when the content of sulfate ions in the volatile gas component information exceeds the threshold value of the preset sulfate ion content, obtaining a first influence parameter;
step S435: the first influencing parameter is used for correcting a first angle of the logistic regression line.
Specifically, when the sulfate ion content of the building waste exceeds the threshold value, the building waste needs to be carefully treated, because the sulfate ion can be converted into hydrogen sulfide with a smelly egg flavor under an anaerobic condition, and serious threat is caused to the life of people, when the sulfate ion content of volatile gas component information of the building waste exceeds the predetermined threshold value, a first influence parameter is generated, and the first influence parameter is used for adjusting a first angle of the logistic regression line, so that the further accurate treatment of the logistic regression line is achieved, the effect of accurately judging whether the building waste is harmful waste is achieved, and the technical effects of effectively recycling the recyclable building waste and protecting the environment are achieved.
As shown in fig. 5, before inputting the training data set into the training model, step S600 in the embodiment of the present application further includes:
step S610: obtaining first training data, and generating a first verification code according to the first training data, wherein the first verification code corresponds to the first training data one to one;
step S620: acquiring second training data, and generating a second verification code according to the second training data and the first verification code; by analogy, obtaining Nth training data, and generating an Nth verification code according to the Nth training data and the Nth-1 verification code, wherein N is a natural number greater than 1, and the first training data, the second training data and the Nth training data are all data information in the training data set;
step S630: and copying and storing all training data and verification codes which form the training data set on M devices respectively, wherein M is a natural number greater than 1.
Specifically, the first training data includes the fifth output result and the volatile gas component information, and first training data and first verification codes which are generated according to the first training data and correspond to the first training data one by one are obtained; acquiring second training data, and acquiring a second verification code generated according to the second training data and the first verification code; by analogy, obtaining the Nth training data, and obtaining the Nth verification code generated according to the Nth training data and the Nth-1 verification code, wherein N is a natural number greater than 1, and each group of training data comprises: the fifth output result and the volatile gas component information. Respectively copying and storing all training data and verification codes which form the training data set on M devices, wherein the first training data and the first verification code are stored on one device as a first block, the second training data and the second verification code are stored on one device as a second block, the Nth training data and the Nth verification code are stored on one device as an Nth block, when the training data needs to be called, after each subsequent node receives data stored by a previous node, the data are checked through a common identification mechanism and stored, and each storage unit is connected in series through a Hash technology, so that the training data are not easy to lose and be damaged, and the training data are encrypted through logic of a block chain, so that the safety of the training data is ensured and the training data are stored on a plurality of devices, the data stored on the multiple devices are processed through a consensus mechanism, namely, a small number of the data are subject to majority, when one or more devices are tampered, the obtained training data are still correct as long as the number of the devices storing correct data is larger than the number of the devices being tampered, and the safety of the training data is further guaranteed. Therefore, the training model obtained through training of the training data is more accurate, the pollution level information of the construction waste output by the training model is more accurate, and the technical effects of recycling the recyclable construction waste and protecting the environment are achieved.
As shown in fig. 6, in order to obtain a more accurate training data set, the step S620 further includes:
step S621: taking the Nth training data and the Nth-1 verification code as an Nth block;
step S622: obtaining the recording time of the Nth block, wherein the recording time of the Nth block represents the time required to be recorded by the Nth block;
step S623: obtaining the first equipment with the fastest transport capacity in the M pieces of equipment according to the recording time of the Nth block;
and step S624, sending the recording right of the nth block to the first device.
Specifically, the Nth training data and the (N-1) th verification code are used as an Nth block, the Nth block is sent to M devices for recording, the device with the highest recording speed in the M devices is obtained as a first device, the mode that the device with the highest calculation and storage speed in the M devices stores the block is obtained through the relation of workload competition in the M devices, the storage speed recorded by the block is guaranteed, the safety of the block is further guaranteed, the safety of the training data is further guaranteed, the foundation is tamped for obtaining an accurate training model, the accurate pollution level information of harmful garbage can be further obtained, and the technical effects of effectively recycling the recyclable construction garbage and protecting the environment are further achieved.
As shown in fig. 7, in order to further determine the pollution level information of the harmful garbage, the step S800 further includes:
step S810: obtaining component information of the harmful garbage;
step S820: according to the component information of the harmful garbage, obtaining fermentation index information of the harmful garbage;
step S830: obtaining a predetermined fermentation index threshold;
step S840: judging whether the fermentation index of the harmful garbage exceeds the preset fermentation index threshold value or not;
step S850: and if the fermentation index of the harmful garbage exceeds the preset fermentation index threshold value, obtaining a first landfill standard.
Specifically, the construction waste is leached and washed by rainwater and soaked in surface water and underground water during stacking and landfill, and then the sewage seeped by fermentation is called percolate or leachate, which can cause serious pollution to the surrounding surface water and underground water. Obtaining component information of the harmful garbage, obtaining a fermentation index of the harmful garbage according to the component information of the harmful garbage, obtaining a first landfill standard by judging whether the fermentation index of the harmful garbage exceeds a preset fermentation index threshold value, and landfill the harmful garbage exceeding the preset fermentation index threshold value according to the first landfill standard if the fermentation index of the harmful garbage exceeds the preset fermentation index threshold value. Through further limiting the fermentation index of the harmful garbage, the harmful garbage is reasonably classified, so that a more reasonable treatment mode of the harmful garbage is obtained, and the technical effect of protecting the environment is achieved.
As shown in fig. 8, in order to further determine the pollution level information of the harmful garbage, the step S800 further includes:
step S860: obtaining component information of the harmful garbage;
step S870: according to the component information of the harmful garbage, acquiring anaerobic index information of the harmful garbage;
step S880: obtaining a predetermined anaerobic index threshold;
step S890: judging whether the anaerobic index of the harmful garbage exceeds the preset anaerobic index threshold value or not;
step S900: and if the anaerobic index of the harmful garbage exceeds the preset anaerobic index threshold value, first early warning information is obtained and used for reminding the harmful garbage of forbidding landfill treatment.
Specifically, when the anaerobic index of the construction waste exceeds a certain range, some organic substances are decomposed by the action of temperature, moisture, etc. Harmful gases are generated, such as construction waste gypsum contains a large amount of sulfate ions, and the sulfate ions can be converted into hydrogen sulfide with a smelly egg flavor under anaerobic conditions. Therefore, when the anaerobic index of the harmful garbage exceeds the preset anaerobic index threshold, harmful gas is possibly generated after landfill treatment, and therefore when the anaerobic index of the harmful garbage exceeds the preset anaerobic index threshold, first early warning information is generated and used for reminding the harmful garbage to prohibit landfill treatment.
To sum up, the construction waste classification method and the system provided by the embodiment of the application have the following technical effects:
1. the method comprises the steps of obtaining first image information of the construction waste, inputting the first image information into a first classification model to preliminarily judge whether the construction waste is harmful waste or harmless waste, inputting a result of the harmless waste and construction waste volatile gas component information into a second classification model, and training the first training model according to the result of the harmful waste output, the result of the harmful waste judged by the first classification model and the volatile gas component information construction data training set, so that the training model can accurately judge the pollution level grade of the construction waste, the construction waste can be accurately and effectively classified, and the technical effects of effectively recycling the recyclable construction waste and protecting the environment are achieved.
2. Due to the fact that the mode that the first classification model and the second classification model are subjected to multi-group training data supervised learning is adopted, the obtained first classification model and the obtained second classification model have more perfect experience to process the input data, and the technical effect of more accurately judging whether the construction waste is harmful waste or harmless waste is obtained.
3. The encryption processing based on block chain logic is carried out on the training data set, the Nth block is sent to the M devices for recording, the device with the highest recording speed in the M devices is obtained as the first device, the mode that the device with the highest calculation and storage speed in the M devices stores the block is obtained through the relation of workload competition in the M devices, the storage speed recorded by the block is guaranteed, the safety of the block is further guaranteed, the safety of the training data is further guaranteed, the foundation is tamped for obtaining an accurate training model, the accurate pollution level information of harmful garbage can be further obtained, and the technical effects of effectively recycling the recyclable construction garbage and protecting the environment are further achieved.
4. The method for further analyzing the component information of the harmful garbage is adopted, so that the fermentation index and the anaerobic index of the harmful garbage are further limited, the harmful garbage is reasonably classified, a more reasonable treatment method of the harmful garbage is obtained, and the technical effect of protecting the environment is achieved.
Example two
Based on the same inventive concept as the construction waste classification method in the foregoing embodiment, the present invention further provides a construction waste classification system, as shown in fig. 9, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first image information, where the first image information includes image information of construction waste;
a first input unit 12, where the first input unit 12 is configured to input the first image information into a first classification model to obtain first output information, where the first output information includes a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste;
a second obtaining unit 13, wherein the second obtaining unit 13 is used for obtaining volatile gas component information of the construction waste;
a second input unit 14, where the second input unit 14 is configured to input the first output result and the volatile gas component information into a second classification model to obtain second output information, where the second output information includes a third output result and a fourth output result, the third output result is a result that the construction waste is harmless waste, and the fourth output result is a result that the construction waste is harmful waste;
a third obtaining unit 15, where the third obtaining unit 15 is configured to obtain a fifth output result according to the second output result and the fourth output result;
a fourth obtaining unit 16, where the fourth obtaining unit 16 is configured to construct a training data set according to the fifth output result and the volatile gas component information;
a third input unit 17, where the third input unit 17 is configured to input the training data set into a first training model to obtain third output information, where the third output information includes pollution level information of harmful garbage;
a first processing unit 18, wherein the first processing unit 18 is used for processing the construction waste according to the pollution level information of the harmful waste.
Further, the system further comprises:
a fourth input unit, configured to input first image information into the first classification model, where the first classification model is obtained by training multiple sets of training data, and each set of training data in the multiple sets includes: image information of construction waste and identification information for identifying whether the construction waste is harmful;
a fifth obtaining unit, configured to obtain first output information of the first classification model, where the first output information includes a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste.
Further, the system further comprises:
a sixth obtaining unit configured to take the first output result as an abscissa;
a seventh obtaining unit configured to take the volatile gas component information as an ordinate;
an eighth obtaining unit, configured to obtain a logistic regression line according to the abscissa and the ordinate by using a logistic regression model, where the logistic regression line includes a first position and a first angle, and the first position and the first angle are located in a coordinate system constructed by the abscissa and the ordinate; wherein one side of the logistic regression line represents a first output result and the other side of the logistic regression line represents a second output result, wherein the first output result and the second output result are different.
Further, the system further comprises:
a ninth obtaining unit, configured to obtain first training data and generate a first verification code according to the first training data, where the first verification code corresponds to the first training data one to one;
a tenth obtaining unit, configured to obtain second training data, and generate a second verification code according to the second training data and the first verification code; by analogy, obtaining Nth training data, and generating an Nth verification code according to the Nth training data and the Nth-1 verification code, wherein N is a natural number greater than 1, and the first training data, the second training data and the Nth training data are all data information in the training data set;
an eleventh obtaining unit, configured to copy and store all training data and verification codes constituting the training data set on M devices, respectively, where M is a natural number greater than 1.
Further, the system further comprises:
a twelfth obtaining unit, configured to use the nth training data and the nth-1 verification code as an nth block;
a thirteenth obtaining unit, configured to obtain the nth block recording time, where the nth block recording time represents a time that an nth block needs to be recorded;
a fourteenth obtaining unit, configured to obtain, according to the nth block recording time, a first device with the fastest transport capacity from among the M devices;
a fifteenth obtaining unit, configured to send the recording right of the nth block to the first device.
Further, the system further comprises:
a sixteenth obtaining unit configured to obtain component information of the harmful garbage;
a seventeenth obtaining unit configured to obtain fermentation index information of the harmful garbage according to component information of the harmful garbage;
an eighteenth obtaining unit for obtaining a predetermined fermentation index threshold;
the first judgment unit is used for judging whether the fermentation index of the harmful garbage exceeds the preset fermentation index threshold value or not;
a nineteenth obtaining unit for obtaining a first landfill standard if a fermentation index of the harmful garbage exceeds the predetermined fermentation index threshold;
a twentieth obtaining unit for landfill-burying the harmful garbage according to the first landfill standard.
Further, the system further comprises:
a twenty-first obtaining unit for obtaining component information of the harmful garbage;
a twenty-second obtaining unit configured to obtain anaerobic index information of the harmful garbage according to the composition information of the harmful garbage;
a twenty-third obtaining unit for obtaining a predetermined anaerobic index threshold;
a second judging unit for judging whether the anaerobic index of the harmful garbage exceeds the predetermined anaerobic index threshold;
a twenty-fourth obtaining unit, configured to obtain first warning information if an anaerobic index of the harmful garbage exceeds the predetermined anaerobic index threshold, where the first warning information is used to remind the harmful garbage of prohibiting landfill treatment.
Various changes and specific examples of the construction waste classification method in the first embodiment of fig. 1 are also applicable to the construction waste classification system of this embodiment, and a person skilled in the art can clearly know the implementation method of the construction waste classification system in this embodiment through the foregoing detailed description of the construction waste classification method, so that the detailed description is omitted here for the sake of brevity of the description.
Exemplary electronic device
An electronic apparatus of an embodiment of the present application is described below with reference to fig. 10.
Fig. 10 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of a construction waste classification method as in the previous embodiment, the invention further provides a construction waste classification system, on which a computer program is stored, which when executed by a processor implements the steps of any one of the aforementioned construction waste classification methods.
Where in fig. 10 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the invention provides a building rubbish classification method, which comprises the following steps: obtaining first image information, wherein the first image information comprises image information of construction waste; inputting the first image information into a first classification model to obtain first output information, wherein the first output information comprises a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste; obtaining volatile gas component information of the construction waste; inputting the first output result and the volatile gas component information into a second classification model to obtain second output information, wherein the second output information comprises a third output result and a fourth output result, the third output result is the result that the construction waste is harmless waste, and the fourth output result is the result that the construction waste is harmful waste; obtaining a fifth output result according to the second output result and the fourth output result; constructing a training data set according to the fifth output result and the volatile gas component information; inputting the training data set into a first training model to obtain third output information, wherein the third output information comprises pollution level information of harmful garbage; and treating the construction waste according to the pollution level information of the harmful waste. The problem of among the prior art construction waste directly carry out landfill or stack processing, cause serious environmental pollution is solved, reach and carry out classification to construction waste, reach the technical effect of effective recoverable construction waste recycle, environmental protection.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are to be construed to include preferred embodiments and all such variations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention also encompasses these modifications and variations.
Claims (8)
1. A construction waste classification method, wherein the method comprises:
obtaining first image information, wherein the first image information comprises image information of construction waste;
inputting the first image information into a first classification model to obtain first output information, wherein the first output information comprises a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste;
obtaining volatile gas component information of the construction waste;
inputting the first output result and the volatile gas component information into a second classification model to obtain second output information, wherein the second output information comprises a third output result and a fourth output result, the third output result is the result that the construction waste is harmless waste, and the fourth output result is the result that the construction waste is harmful waste;
obtaining a fifth output result according to the second output result and the fourth output result; the fifth output result is a set of a second output result determined by the image information of the construction waste and a fourth output result determined by the component information of the construction waste volatile gas;
constructing a training data set according to the fifth output result and the volatile gas component information;
inputting the training data set into a first training model to obtain third output information, wherein the third output information comprises pollution level information of harmful garbage;
and treating the construction waste according to the pollution level information of the harmful waste.
2. The method of claim 1, wherein said inputting the first image information into a first classification model, obtaining first output information, comprises:
inputting first image information into the first classification model, wherein the first classification model is obtained by training multiple groups of training data, and each group of training data in the multiple groups comprises: image information of construction waste and identification information for identifying whether the construction waste is harmful;
obtaining first output information of the first classification model, wherein the first output information comprises a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste.
3. The method of claim 1, wherein said inputting said training data set into a first training model comprises:
obtaining first training data, and generating a first verification code according to the first training data, wherein the first verification code corresponds to the first training data one to one;
acquiring second training data, and generating a second verification code according to the second training data and the first verification code; by analogy, obtaining Nth training data, and generating an Nth verification code according to the Nth training data and the Nth-1 verification code, wherein N is a natural number greater than 1, and the first training data, the second training data and the Nth training data are all data information in the training data set;
and copying and storing all training data and verification codes which form the training data set on M devices respectively, wherein M is a natural number greater than 1.
4. The method of claim 3, wherein the method comprises:
taking the Nth training data and the Nth-1 verification code as an Nth block;
obtaining the recording time of the Nth block, wherein the recording time of the Nth block represents the time required to be recorded by the Nth block;
obtaining the first equipment with the fastest transport capacity in the M pieces of equipment according to the recording time of the Nth block;
and sending the recording right of the Nth block to the first equipment.
5. The method of claim 1, wherein the method comprises:
obtaining component information of the harmful garbage;
according to the component information of the harmful garbage, obtaining fermentation index information of the harmful garbage;
obtaining a predetermined fermentation index threshold;
judging whether the fermentation index of the harmful garbage exceeds the preset fermentation index threshold value or not;
if the fermentation index of the harmful garbage exceeds the preset fermentation index threshold value, obtaining a first landfill standard;
and according to the first landfill standard, landfill is carried out on the harmful garbage.
6. The method of claim 1, wherein the method comprises:
obtaining component information of the harmful garbage;
according to the component information of the harmful garbage, acquiring anaerobic index information of the harmful garbage;
obtaining a predetermined anaerobic index threshold;
judging whether the anaerobic index of the harmful garbage exceeds the preset anaerobic index threshold value or not;
and if the anaerobic index of the harmful garbage exceeds the preset anaerobic index threshold value, first early warning information is obtained and used for reminding the harmful garbage of forbidding landfill treatment.
7. A construction waste classification system, wherein the system comprises:
a first obtaining unit configured to obtain first image information including image information of construction waste;
a first input unit, configured to input the first image information into a first classification model to obtain first output information, where the first output information includes a first output result and a second output result, the first output result is a result that the construction waste is harmless waste, and the second output result is a result that the construction waste is harmful waste;
a second obtaining unit, configured to obtain volatile gas component information of the construction waste;
a second input unit, configured to input the first output result and the volatile gas component information into a second classification model to obtain second output information, where the second output information includes a third output result and a fourth output result, the third output result is a result that the construction waste is harmless waste, and the fourth output result is a result that the construction waste is harmful waste;
a third obtaining unit, configured to obtain a fifth output result according to the second output result and the fourth output result; the fifth output result is a set of a second output result determined by the image information of the construction waste and a fourth output result determined by the component information of the construction waste volatile gas;
a fourth obtaining unit, configured to construct a training data set according to the fifth output result and the volatile gas component information;
a third input unit, configured to input the training data set into a first training model to obtain third output information, where the third output information includes pollution level information of harmful garbage;
the first treatment unit is used for treating the construction waste according to the pollution level information of the harmful waste.
8. A construction waste classification system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010899036.3A CN112101149B (en) | 2020-08-31 | 2020-08-31 | Building waste classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010899036.3A CN112101149B (en) | 2020-08-31 | 2020-08-31 | Building waste classification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112101149A CN112101149A (en) | 2020-12-18 |
| CN112101149B true CN112101149B (en) | 2022-01-18 |
Family
ID=73756623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010899036.3A Active CN112101149B (en) | 2020-08-31 | 2020-08-31 | Building waste classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101149B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818810A (en) * | 2021-01-27 | 2021-05-18 | 广西融安蚂蚁农业发展有限公司 | Kumquat intelligent sorting method and device based on big data |
| CN115436374B (en) * | 2022-11-07 | 2023-03-24 | 湖南迪亚环境工程股份有限公司 | Leachate sewage monitoring system based on Internet of things |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000305354A (en) * | 1999-04-19 | 2000-11-02 | Ricoh Co Ltd | Image forming device |
| CN110598784A (en) * | 2019-09-11 | 2019-12-20 | 北京建筑大学 | Machine learning-based construction waste classification method and device |
| CN111573039A (en) * | 2020-05-22 | 2020-08-25 | 倪慧珍 | Intelligent garbage classification processing system based on big data |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101036916A (en) * | 2007-04-24 | 2007-09-19 | 大连理工大学 | Domestic waste comprehensive treatment technology based on the pre-processing |
| CN210730508U (en) * | 2019-08-05 | 2020-06-12 | 湖北金福阳科技股份有限公司 | Automatic domestic waste treatment device |
-
2020
- 2020-08-31 CN CN202010899036.3A patent/CN112101149B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000305354A (en) * | 1999-04-19 | 2000-11-02 | Ricoh Co Ltd | Image forming device |
| CN110598784A (en) * | 2019-09-11 | 2019-12-20 | 北京建筑大学 | Machine learning-based construction waste classification method and device |
| CN111573039A (en) * | 2020-05-22 | 2020-08-25 | 倪慧珍 | Intelligent garbage classification processing system based on big data |
Non-Patent Citations (2)
| Title |
|---|
| X-DenseNet: Deep Learning for Garbage Classification Based on Visual Images;Sha Meng 等;《Journal of Physics: Conference Series》;20200523;第1-5页 * |
| 基于NB-IoT的智能垃圾分类系统;杨皓文 等;《物联网技术》;20200819;第47-51页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112101149A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hacker et al. | Regulating ChatGPT and other large generative AI models | |
| CN112101149B (en) | Building waste classification method and system | |
| Chandy et al. | Cyberattack detection using deep generative models with variational inference | |
| CN110991568B (en) | Target identification method, device, equipment and storage medium | |
| WO2009141631A3 (en) | An improved neuro type-2 fuzzy based method for decision making | |
| CN111950068A (en) | Method and device for maintaining building equipment based on Bim | |
| CN115018348B (en) | Environment analysis method, system, equipment and storage medium based on artificial intelligence | |
| Tam et al. | ELECTRE III in evaluating performance of construction plants: case study on concrete vibrators | |
| Abba et al. | Modelling of uncertain system: a comparison study of linear and non-linear approaches | |
| El-Khoja et al. | Prediction of rubberised concrete strength by using artificial neural networks | |
| CN113255941B (en) | Bridge construction waste treatment method and device | |
| Benedetti et al. | A new rule generation method to develop a decision support system for integrated management at river basin scale | |
| CN114203262A (en) | Sewage utilization method and system based on recyclable clean fracturing fluid system | |
| Bukovics et al. | FUZZY SIGNATURE BASED MODEL FOR QUALIFICATION AND RANKING OF RESIDENTIAL BUILDINGS. | |
| CN112215421A (en) | Deep learning water quality index prediction method based on generation countermeasure network | |
| Zashcholkin et al. | Formation of the Interval Stego Key for the Digital Watermark Used in Integrity Monitoring of FPGA-based Systems. | |
| Gribkova et al. | Detecting intrusions in control systems: A rule of thumb, its justification and illustrations | |
| Lee et al. | A Study on the Influence of a Sewage Treatment Plant's Operational Parameters using the Multiple Regression Analysis Model | |
| CN107066824B (en) | Active fault detection method based on wet end of paper machine | |
| Rahbari et al. | Evaluating the process efficiency of industrial wastewater treatment plants using data envelopment analysis approach case study: Khuzestan steel company treatment plant | |
| CN111369352B (en) | Joint modeling method, apparatus, and medium | |
| Comas et al. | Demonstration of a tool for automatic learning and re-use of knowledge in the activated sludge process | |
| Durnyak et al. | Protection of the Information System of the Printing Enterprise from Cyber Threats. | |
| Huybrechts et al. | How Much of Biodiversity is Represented in Collections: A big data workflow of aggregated occurrence data | |
| Than et al. | Water quality classification by artificial neural network-a case study of dong Nai river, Vietnam |
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 |