Method for treating rural household garbage

Abstract

The invention relates to the technical field of garbage treatment, in particular to a method for treating rural household garbage, which realizes automatic and intelligent classification of the rural household garbage by designing and constructing a garbage classification model based on image recognition and a machine learning algorithm, and has the advantages that compared with a traditional manual classification mode, the classification efficiency is greatly improved; according to the method, the garbage can be recognized and classified more quickly and accurately, the classification efficiency is greatly improved, meanwhile, classification errors caused by human factors are reduced, the classification accuracy is ensured, and the problem that in the prior art, in the treatment process of preparing the soil fertilizer from the rural household garbage, the soil fertilizer is not damaged is solved. The technical problems that due to the fact that manual classification is adopted for garbage classification, efficiency is low, accuracy is not high, non-degradable or harmful substances are likely to be mixed in the composting treatment process, and the composting quality and safety are affected are solved.

Description

Technical Field

[0001] The invention relates to the technical field of garbage disposal, and in particular to a method for treating rural domestic garbage. Background Art

[0002] Rural domestic waste refers to solid waste generated in daily life in rural areas, including kitchen waste, paper, plastic, metal, glass, fabric, ash and other types. With the development of rural economy and the improvement of living standards, the amount of rural domestic waste has increased year by year, and its composition has become increasingly complex. Traditional methods of rural domestic waste disposal are mostly landfill, incineration or simple stacking, but these methods not only occupy a large amount of land resources, but may also pollute the soil, water and air, affecting the rural ecological environment and residents' health.

[0003] In recent years, with the enhancement of environmental awareness and the popularization of the concept of resource recycling, the classification and resource utilization of rural domestic waste have gradually received attention. Among them, preparing rural domestic waste into soil fertilizer is a potential treatment method. By composting biodegradable waste, it can be converted into soil fertilizer rich in organic matter, which can be used to improve soil structure, increase soil fertility, promote crop growth, and realize resource recycling.

[0004] However, in the prior art, in the process of preparing soil fertilizer from rural domestic waste, manual sorting of waste is used, resulting in low efficiency and low accuracy. Non-degradable or harmful substances are easily mixed into the composting process, affecting the quality and safety of the compost. Summary of the invention

[0005] The purpose of the present invention is to provide a method for treating rural domestic waste, aiming to solve the technical problems in the prior art that, in the process of preparing soil fertilizer from rural domestic waste, manual classification of waste is used, resulting in low efficiency and low accuracy, and non-degradable or harmful substances are easily mixed into the composting process, affecting the quality and safety of the compost.

[0006] To achieve the above object, the present invention adopts a method for treating rural domestic waste, comprising the following steps:

[0007] Step 1: Design a garbage sorting and processing system;

[0008] Step 2: Build a garbage classification model based on image recognition and machine learning algorithms, and embed it into the garbage classification and processing system;

[0009] Step 3: Deploy image acquisition equipment and computer processing equipment at rural domestic waste classification sites to capture waste images and transmit them to the waste classification model;

[0010] Step 4: The garbage classification processing system processes and identifies the image data based on the garbage classification model, classifies the garbage into compostable garbage and non-compostable garbage, and feeds back to the classification execution system and operators;

[0011] Step 5: The classification execution system collects compostable waste and performs pre-processing;

[0012] Step 6: After the pretreatment is completed, the compost is stacked in layers, first laying a 20cm thick layer of hay or dead leaves as a base, and then adding compostable waste alternately;

[0013] Step 7: After stacking, turn the pile at least once a week and keep it ventilated until fermentation is complete;

[0014] Step 8: Remove impurities and incompletely decomposed substances from the fermented compost to obtain pure soil fertilizer.

[0015] Among them, in step one, the designed garbage classification and processing system includes a garbage classification module, a pretreatment module, a composting processing module and a quality control module.

[0016] The specific process of building a garbage classification model based on image recognition and machine learning algorithms is as follows:

[0017] Collect a large amount of image data of rural domestic waste and label it into compostable and non-compostable categories;

[0018] Use image processing techniques to extract features of garbage images, such as color, shape, and texture;

[0019] Based on the features of the extracted garbage images, a machine learning algorithm (such as convolutional neural network (CNN) or support vector machine (SVM)) is used to train the garbage classification model so that it can accurately identify the garbage category;

[0020] Optimize model performance by adjusting model parameters, adding data enhancement, etc.

[0021] Among them, the specific methods of deploying image acquisition equipment and computer processing equipment at rural domestic waste classification stations are as follows:

[0022] Select high-definition image acquisition devices (such as cameras) and computer processing devices (such as servers or embedded devices), and install the image acquisition devices (such as cameras) at the garbage sorting sites and ensure that they can capture clear images of the garbage;

[0023] The image acquisition device is then connected to a computer processing device to transmit the image data in real time.

[0024] Among them, the garbage classification processing system processes and identifies the image data based on the garbage classification model, classifies the garbage into compostable garbage and non-compostable garbage, and feeds back to the classification execution system and operators in the following specific ways:

[0025] The computer processing device receives the image data from the image acquisition device and performs preprocessing on the image data, such as denoising and normalization;

[0026] The trained garbage classification model is then used to infer the preprocessed image data to obtain the garbage category, and the classification results are fed back to the classification execution system and operators.

[0027] Mean filtering and Gaussian filtering are used for image preprocessing.

[0028] Among them, in step five, the compost waste is pre-treated by removing large impurities and breaking it up.

[0029] Among them, in step six, the layers are stacked, and the thickness of each layer does not exceed 30 cm; the carbon-nitrogen ratio is controlled to be 30:1, which is achieved by adjusting the proportion of animal and plant residues.

[0030] Among them, integrated automation equipment is used in the garbage classification, pretreatment and composting treatment, such as automatic sorting machines, crushers, mixers, etc. A remote control system is developed to realize remote monitoring and control of automation equipment, and mobile applications and Web platforms are developed to facilitate managers to check equipment status, receive warning information and perform remote operations anytime and anywhere.

[0031] Automation control is used to achieve precise control and optimized operation of automation equipment.

[0032] Network communication protocols: such as MQTT and HTTP, used to achieve data communication between devices and the cloud or mobile applications.

[0033] In the process of handling rural domestic waste, data from waste classification, composting treatment, and resource recovery are integrated, and machine learning algorithms are used to establish prediction models for key indicators such as waste classification accuracy, compost product quality, and resource recovery rate. Based on the results of the prediction model, decision support is provided to managers, such as adjusting waste classification strategies and optimizing composting treatment parameters.

[0034] After the composting is completed, the compost is crushed, mixed, and packaged as needed to prepare soil fertilizer for use in farmland.

[0035] A method for processing rural domestic waste of the present invention comprises the following steps: firstly designing a waste classification processing system; constructing a waste classification model based on image recognition and machine learning algorithms, and implanting the model into the waste classification processing system; deploying image acquisition equipment and computer processing equipment at rural domestic waste classification sites to capture waste images and transmit them to the waste classification model; the waste classification processing system processes and identifies image data based on the waste classification model, classifies waste into compostable waste and non-compostable waste, and feeds back the data to the classification execution system and operators; the classification execution system collects compostable waste and performs pre-processing; after the pre-processing is completed, the compostable waste is collected and pre-processed. After fermentation, the compost is stacked in layers, firstly a 20 cm thick layer of hay or dead leaves is laid as a base, and then compostable garbage is added alternately; after stacking, the compost is turned over at least once a week and ventilation is maintained until fermentation is completed; impurities and incompletely decomposed substances in the fermented compost are removed to obtain pure soil fertilizer, thereby solving the technical problems in the prior art of preparing soil fertilizer from rural domestic waste, the manual classification of garbage, resulting in low efficiency and low accuracy, and the easy mixing of non-degradable or harmful substances in the composting process, which affects the quality and safety of the compost.

[0036] The present invention realizes the automatic and intelligent classification of rural domestic waste by designing and constructing a garbage classification model based on image recognition and machine learning algorithms. Compared with the traditional manual classification method, the invention can identify and classify garbage more quickly and accurately, greatly improving the classification efficiency, while also reducing classification errors caused by human factors and ensuring the accuracy of classification.

[0037] At the same time, with the assistance of the classification execution system, the present invention can accurately collect compostable garbage and avoid the mixing of non-degradable or harmful substances, thereby optimizing the composting process. By adopting the stacking method, supplemented by regular turning and ventilation, the present invention ensures the full fermentation of the composting process and effectively improves the quality of the compost. In addition, the process of removing impurities and incompletely decomposed substances further ensures the purity and safety of the final soil fertilizer.

[0038] The present invention helps to reduce the pollution of rural domestic garbage to the environment and improve the rural ecological environment. At the same time, by providing high-quality soil fertilizer, it promotes the sustainable development of agricultural production and improves the quality of life of rural residents. In addition, the intelligent and automated characteristics of the method also enhance the awareness and participation of rural residents in environmental protection and garbage classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 It is a flow chart of the steps of the method for processing rural domestic garbage of the present invention. DETAILED DESCRIPTION

[0041] Embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0042] See also Figure 1 , Figure 1 It is a flow chart of the steps of the method for processing rural domestic garbage of the present invention.

[0043] The present invention provides a method for treating rural domestic garbage, comprising the following steps:

[0044] S1. Design a garbage sorting and processing system;

[0045] According to this specific implementation, the designed garbage classification and processing system includes a garbage classification module, a pretreatment module, a composting processing module and a quality control module.

[0046] S2. Build a garbage classification model based on image recognition and machine learning algorithms, and embed it into the garbage classification and processing system;

[0047] For this specific implementation, the specific process of building a garbage classification model based on image recognition and machine learning algorithms is as follows:

[0048] Collect a large amount of image data of rural domestic waste and label it into compostable and non-compostable categories;

[0049] Use image processing techniques to extract features of garbage images, such as color, shape, and texture;

[0050] Based on the features of the extracted garbage images, a machine learning algorithm (such as convolutional neural network (CNN) or support vector machine (SVM)) is used to train the garbage classification model so that it can accurately identify the garbage category;

[0051] Optimize model performance by adjusting model parameters, adding data enhancement, etc.

[0052] S3. Deploy image acquisition equipment and computer processing equipment at rural domestic waste sorting sites to capture waste images and transmit them to the waste sorting model;

[0053] For this specific implementation, a high-definition image acquisition device (such as a camera) and a computer processing device (such as a server or an embedded device) are selected, and the image acquisition device (such as a camera) is installed at the garbage classification site, and it is ensured that it can capture clear garbage images;

[0054] The image acquisition device is then connected to a computer processing device to transmit the image data in real time.

[0055] S4. The garbage classification processing system processes and identifies the image data based on the garbage classification model, classifies the garbage into compostable garbage and non-compostable garbage, and feeds back to the classification execution system and operators;

[0056] According to this specific implementation, the garbage classification processing system processes and identifies the image data based on the garbage classification model, classifies the garbage into compostable garbage and non-compostable garbage, and feeds back to the classification execution system and the operator in the following specific manner:

[0057] The computer processing device receives the image data from the image acquisition device and performs preprocessing on the image data, such as denoising and normalization;

[0058] The trained garbage classification model is then used to infer the preprocessed image data to obtain the garbage category, and the classification results are fed back to the classification execution system and operators.

[0059] Mean filtering and Gaussian filtering are used for image preprocessing.

[0060] The specific process includes the following:

[0061] Image data acquisition:

[0062] The system collects image data of the garbage to be sorted in real time through devices such as cameras or sensors.

[0063] These image data should contain different angles, lighting conditions, and background information of the garbage to ensure the generalization ability of the model.

[0064] Image preprocessing:

[0065] The collected image data is preprocessed, including denoising, enhancement, cropping and other operations, to improve image quality.

[0066] The preprocessed image data will be input into the garbage classification model.

[0067] Garbage classification model processing:

[0068] The garbage classification model is an image classification model based on deep learning, such as convolutional neural network (CNN).

[0069] The model has been trained with a large number of labeled data sets and can automatically identify and classify garbage.

[0070] During processing, the model extracts features from the image, such as color, shape, texture, etc., and matches them with features in the training set.

[0071] Classification result output:

[0072] Based on the processing results of the garbage classification model, the system divides the garbage into compostable garbage and non-compostable garbage.

[0073] The classification results are output in the form of labels or text and displayed on the system interface.

[0074] Feedback to the classification execution system and operators: Operators: The system will also feedback the classification results to the operator in the form of vision (such as screen display), hearing (such as voice broadcast or) touch (such as vibration reminder). The operator can confirm or adjust the classification results of the system based on this information.

[0075] S5, the classification execution system collects compostable waste and performs pre-processing work;

[0076] For this specific embodiment, the classification execution system: the system automatically sends the garbage to the corresponding processing equipment or container according to the classification results. For example, compostable garbage may be sent to a composting treatment facility, while non-compostable garbage may be sent to other treatment processes.

[0077] The compost waste is pre-processed by removing large impurities and breaking it up.

[0078] S6. After the pretreatment is completed, the compost is stacked in layers, first laying a 20 cm thick layer of hay or dead leaves as a base, and then adding compostable waste alternately;

[0079] According to this specific implementation method, the layers are stacked, and the thickness of each layer does not exceed 30 cm; the carbon-nitrogen ratio is controlled to be 30:1, which is achieved by adjusting the proportion of animal and plant residues.

[0080] S7. After stacking, turn the pile at least once a week and keep it ventilated until fermentation is complete;

[0081] S8. Remove impurities and incompletely decomposed substances from the fermented compost to obtain pure soil fertilizer.

[0082] According to this specific embodiment, after the composting is completed, the compost is crushed, mixed, and packaged as needed to prepare soil fertilizer for use in farmland.

[0083] Integrated automation equipment is used in garbage classification, pretreatment, and composting, such as automatic sorting machines, crushers, mixers, etc. A remote control system is developed to achieve remote monitoring and control of automated equipment, while mobile applications and Web platforms are developed to facilitate managers to check equipment status, receive warning information, and perform remote operations anytime and anywhere.

[0084] Automation control is used to achieve precise control and optimized operation of automation equipment.

[0085] Network communication protocols: such as MQTT and HTTP, used to achieve data communication between devices and the cloud or mobile applications.

[0086] In the process of handling rural domestic waste, the data of waste classification, composting treatment and resource recovery are integrated, and machine learning algorithms are used to establish prediction models for key indicators such as waste classification accuracy, compost product quality, and resource recovery rate. Based on the results of the prediction model, decision support is provided to managers, such as adjusting waste classification strategies and optimizing composting treatment parameters.

[0087] A method for processing rural domestic waste using the present embodiment comprises the following steps: firstly, designing a waste classification processing system; constructing a waste classification model based on image recognition and machine learning algorithms, and implanting it into the waste classification processing system; deploying image acquisition equipment and computer processing equipment at rural domestic waste classification sites to capture waste images and transmit them to the waste classification model; the waste classification processing system processes and identifies image data based on the waste classification model, classifies the waste into compostable waste and non-compostable waste, and feeds back the data to the classification execution system and operators; the classification execution system collects compostable waste and performs pre-processing; the pre-processing After the fermentation is completed, the compost is stacked in layers, firstly a 20 cm thick layer of hay or dead leaves is laid as a base, and then compostable garbage is added alternately; after stacking, the compost is turned over at least once a week and ventilation is maintained until the fermentation is completed; the impurities and incompletely decomposed substances in the fermented compost are removed to obtain pure soil fertilizer, thereby solving the technical problems in the prior art of preparing soil fertilizer from rural domestic waste, the manual classification of garbage classification leads to low efficiency and low accuracy, and non-degradable or harmful substances are easily mixed into the composting process, affecting the quality and safety of the compost.

[0088] The present invention realizes the automatic and intelligent classification of rural domestic waste by designing and constructing a garbage classification model based on image recognition and machine learning algorithms. Compared with the traditional manual classification method, the invention can identify and classify garbage more quickly and accurately, greatly improving the classification efficiency, while also reducing classification errors caused by human factors and ensuring the accuracy of classification.

[0089] At the same time, with the assistance of the classification execution system, the present invention can accurately collect compostable garbage and avoid the mixing of non-degradable or harmful substances, thereby optimizing the composting process. By adopting the stacking method, supplemented by regular turning and ventilation, the present invention ensures the full fermentation of the composting process and effectively improves the quality of the compost. In addition, the process of removing impurities and incompletely decomposed substances further ensures the purity and safety of the final soil fertilizer.

[0090] The present invention helps to reduce the pollution of rural domestic garbage to the environment and improve the rural ecological environment. At the same time, by providing high-quality soil fertilizer, it promotes the sustainable development of agricultural production and improves the quality of life of rural residents. In addition, the intelligent and automated characteristics of the method also enhance the awareness and participation of rural residents in environmental protection and garbage classification.

[0091] The present invention achieves harmlessness and high reduction rate, which is specifically embodied as follows:

[0092] Detoxification:

[0093] 1. Garbage classification:

[0094] By processing and identifying image data through the garbage classification model, garbage can be accurately divided into compostable garbage and non-compostable garbage, avoiding the mixing of hazardous waste into the composting process and reducing the risk of environmental pollution.

[0095] Hazardous waste such as pesticide bottles, batteries, etc. will be collected separately and disposed of safely, avoiding potential harm to the environment and human health.

[0096] 2. Composting process:

[0097] During the composting process, by controlling the composting conditions (such as temperature, humidity, ventilation, etc.), it is ensured that the organic matter is fully fermented and converted into stable soil fertilizer, avoiding the production of harmful gases and substances.

[0098] The soil fertilizer after composting does not contain harmful substances, is safe and harmless to the soil and plants, and can be used in agricultural production to improve soil fertility.

[0099] 3. Reduce secondary pollution:

[0100] The system reduces secondary pollution caused by landfill and incineration through precise classification and efficient processing.

[0101] It avoids the pollution of the environment and groundwater by leachate and harmful gases that may be produced during the landfill process.

[0102] High reduction rate:

[0103] 1. Garbage classification and reduction:

[0104] Through garbage sorting, recyclable garbage, hazardous waste and kitchen waste are collected and processed separately, reducing the amount of garbage entering landfills and incinerators.

[0105] Garbage classification improves the recycling rate of resources and reduces the amount of garbage generated.

[0106] 2. Composting treatment and reduction:

[0107] During the composting process, organic matter is converted into stable soil fertilizer, reducing the amount of waste.

[0108] The volume of soil fertilizer after composting treatment is much smaller than the original garbage volume, achieving a high garbage reduction rate.

[0109] 3. Resource recycling:

[0110] By recycling and reusing recyclable materials in garbage, such as metals, plastics, paper, etc., the recycling of resources is achieved.

[0111] Soil fertilizer after composting can be used in agricultural production, improving soil fertility and crop yields and realizing resource recycling.

[0112] What is disclosed above is only a preferred embodiment of the present invention, and it certainly cannot be used to limit the scope of rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. A method for treating rural domestic waste, characterized in that: The steps include: Step 1: Design a garbage sorting and processing system; Step 2: Build a garbage classification model based on image recognition and machine learning algorithms, and embed it into the garbage classification and processing system; Step 3: Deploy image acquisition equipment and computer processing equipment at rural domestic waste classification sites to capture waste images and transmit them to the waste classification model; Step 4: The garbage classification processing system processes and identifies the image data based on the garbage classification model, classifies the garbage into compostable garbage and non-compostable garbage, and feeds back to the classification execution system and operators; Step 5: The classification execution system collects compostable waste and performs pre-processing; Step 6: After the pretreatment is completed, the compost is stacked in layers, first laying a 20cm thick layer of hay or dead leaves as a base, and then adding compostable waste alternately; Step 7: After stacking, turn the pile at least once a week and keep it ventilated until fermentation is complete; Step 8: Remove impurities and incompletely decomposed substances from the fermented compost to obtain pure soil fertilizer.

2. The method for treating rural domestic waste according to claim 1, characterized in that: In step one, the designed garbage classification and processing system includes a garbage classification module, a pretreatment module, a composting processing module and a quality control module.

3. The method for treating rural domestic waste according to claim 2, characterized in that: The specific process of building a garbage classification model based on image recognition and machine learning algorithms is as follows: Collect a large amount of image data of rural domestic waste and label it into compostable and non-compostable categories; Use image processing techniques to extract features of garbage images, such as color, shape, and texture; Based on the features of the extracted garbage images, a machine learning algorithm is used to train the garbage classification model so that it can accurately identify the garbage category; Optimize model performance by adjusting model parameters, adding data enhancement, etc.

4. The method for treating rural domestic waste according to claim 3, characterized in that: The specific methods of deploying image acquisition equipment and computer processing equipment at rural domestic waste classification sites are as follows: Select high-definition image acquisition equipment and computer processing equipment, install the image acquisition equipment at the garbage sorting site, and ensure that it can capture clear garbage images; The image acquisition device is then connected to a computer processing device to transmit the image data in real time.

5. The method for treating rural domestic waste according to claim 4, characterized in that: The garbage classification system processes and identifies image data based on the garbage classification model, classifies garbage into compostable garbage and non-compostable garbage, and feeds back to the classification execution system and operators in the following specific ways: The computer processing device receives the image data from the image acquisition device and performs preprocessing on the image data, such as denoising and normalization; The trained garbage classification model is then used to infer the preprocessed image data to obtain the garbage category, and the classification results are fed back to the classification execution system and operators; Mean filtering and Gaussian filtering are used for image preprocessing.

6. The method for treating rural domestic waste according to claim 5, characterized in that: In step five, the compost waste is pre-processed by removing large impurities and breaking it up.

7. The method for treating rural domestic waste according to claim 6, characterized in that: In step six, the layers are stacked, with each layer not exceeding 30 cm thick; the carbon-nitrogen ratio is controlled to be 30:1 by adjusting the proportion of animal and plant residues.

8. The method for treating rural domestic waste according to claim 7, characterized in that: Integrated automation equipment is used in the garbage classification, pretreatment and composting processes, and a remote control system is developed to achieve remote monitoring and control of the automation equipment. At the same time, mobile applications and Web platforms are developed to facilitate managers to check equipment status, receive warning information and perform remote operations anytime and anywhere.

9. The method for treating rural domestic waste according to claim 8, characterized in that: In the process of handling rural domestic waste, the data of waste classification, composting treatment and resource recovery are integrated, and machine learning algorithms are used to establish a prediction model for waste classification accuracy, compost product quality and resource recovery rate; based on the results of the prediction model, decision support is provided to managers.

10. The method for treating rural domestic waste according to claim 9, characterized in that: After the composting is completed, the compost is crushed, mixed, and packaged as needed to prepare soil fertilizer for use in farmland.

Images