A single-axis shredder based on garbage classification and recycling and a garbage identification method

Abstract

The present invention discloses a single-shaft shredder and a garbage identification method based on garbage classification and recycling. The method comprises: a material identification unit for capturing images of garbage materials input into an inlet, then intelligently identifying the captured images to obtain identification results, which include the type and attributes of the garbage materials; a parameter adjustment unit for automatically retrieving corresponding processing parameters from a processing parameter database based on the identification results of the garbage materials, and then adjusting the processing parameters of the single-shaft shredder based on the retrieved processing parameters; and a classification and recycling unit for intelligently classifying the shredded garbage materials according to their types and attributes, and then recycling the classified garbage materials. Automatic identification of garbage materials and automatic adjustment of processing parameters are achieved, improving processing efficiency and reducing manual intervention.

Description

Technical Field

[0001] The present invention relates to the technical field of garbage classification, and in particular to a single-shaft shredder based on garbage classification and recycling and a garbage identification method. Background Art

[0002] Current garbage sorting and recycling technology mainly relies on manual sorting and traditional shredder processing. In this technology, garbage materials first need to be sorted manually, and then the sorted garbage materials are input into the shredder for processing. During the processing process, the processing parameters of the shredder are usually fixed and cannot be dynamically adjusted according to the type and properties of the garbage materials, which may lead to poor processing effect and efficiency; in addition, due to the low efficiency and low accuracy of manual sorting, the sorting effect and recycling efficiency of this technology need to be improved. At the same time, manual sorting also has problems such as harsh working environment, high labor intensity, and high health risks; traditional shredders are usually unable to intelligently sort and recycle shredded garbage materials, which not only affects recycling efficiency, but may also lead to waste of resources; therefore, the current garbage sorting and recycling technology has problems such as low sorting effect and recycling efficiency, inability to dynamically adjust processing parameters, and inability to achieve intelligent sorting and recycling.

[0003] The invention with application number: CN201910725703 discloses a method for waste sorting and processing. Through a submersible pump, a solar panel, a floating plate, a drain pipe and a filter membrane, the waste treatment device can collect and process waste on the sea surface for a long time. At the same time, the cooperation between the submersible pump and the drain pipe allows the waste treatment device to move continuously. Through the cooperation of an interception plate, a storage box, high-pressure liquid nitrogen and a crushing wheel, the waste treatment device can embrittle the collected large plastic waste at low temperature, and then crush the embrittled plastic waste through the crushing wheel. The defects include: although large plastic waste can be processed by low-temperature embrittlement and crushing, this treatment method cannot completely solve the environmental problems of plastic waste. The treatment of plastic waste also needs to consider multiple methods such as recycling, incineration and landfill to achieve more comprehensive plastic waste treatment and resource utilization.

[0004] Therefore, there is an urgent need for a single-shaft shredder and a garbage identification method based on garbage classification and recycling. Summary of the Invention

[0005] The present invention provides a single-shaft shredder based on garbage classification and recycling and a garbage identification method to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A single-shaft shredder based on garbage classification and recycling, comprising:

[0008] The material identification unit is used to collect images of the garbage materials input into the entrance, and then perform intelligent recognition on the collected images to obtain recognition results, which include the type and attributes of the garbage materials;

[0009] A parameter adjustment unit is used to automatically retrieve corresponding processing parameters from a processing parameter database according to the identification result of the waste material, and then adjust the processing parameters of the single-shaft shredder according to the retrieved processing parameters;

[0010] The classification and recycling unit is used to intelligently classify the shredded garbage materials according to their types and properties, and then recycle the classified garbage materials.

[0011] Among them, the material identification unit includes: image acquisition module, image preprocessing module and identification module;

[0012] An image acquisition module is used to use a high-resolution image sensor to capture high-definition images of the garbage materials input into the entrance and obtain image information of the garbage materials;

[0013] The image preprocessing module is used to perform preprocessing operations on the collected image information. The preprocessing operations include image grayscale, binarization, noise removal and edge detection;

[0014] The recognition module is used to use a deep learning model based on image recognition to intelligently identify the pre-processed image information and obtain recognition results, which include the type and attributes of the garbage material.

[0015] The parameter adjustment unit includes: a processing parameter database, a database query module and a processing parameter adjustment module;

[0016] A processing parameter database, which uses a relational database to store processing parameters corresponding to different types and properties of garbage materials. The processing parameters for each type of garbage material include rotation speed, shredding blade angle, feed speed, and shredding time;

[0017] The database query module is used to retrieve the corresponding processing parameters from the processing parameter database according to the type and properties of the waste material through hash index query technology;

[0018] The processing parameter adjustment module is used to adopt an adaptive control strategy to dynamically adjust the processing parameters of the single-shaft shredder according to the retrieved processing parameters, including the rotation speed, the angle of the shredding blade, the feed speed and the shredding time.

[0019] Among them, the classification and recycling unit includes: material separation module, recycling processing module and material tracking module;

[0020] The material separation module uses a support vector machine machine learning algorithm to intelligently classify waste materials according to their types and attributes, and uses a clustering algorithm to group waste materials of the same type and attributes into one category;

[0021] The recycling module is used to automatically select the optimal recycling method for different waste materials according to different classifications using an intelligent decision-making system. The recycling method includes reuse, recycling or other environmentally friendly treatment methods;

[0022] The material tracking module is used to track and manage each type of waste material using RFID technology to ensure that each type of waste material receives corresponding recycling treatment.

[0023] Wherein, the database query module includes: a hash mapping submodule;

[0024] A hash function is used to map the types and attributes of garbage materials in the processing parameter database as keywords to unique hash values. The hash mapping submodule uses dynamic hash indexing technology to establish an index based on the hash value and the corresponding processing parameters to locate and retrieve the processing parameters. The query request from the processing parameter adjustment module is received, including the type and attribute of the garbage material, and the hash index query technology is used to locate the corresponding processing parameter through the hash value. Online learning technology is used to dynamically update the processing parameters in the processing parameter database according to the actual operation of the single-axis shredder.

[0025] Among them, the processing parameter adjustment module includes: a high-precision sensor;

[0026] The corresponding processing parameters are obtained from the database query module, including the rotational speed, the angle of the shredding blade, the feed speed and the shredding time. High-precision sensors are used to monitor the operating status and performance indicators of the single-shaft shredder in real time, including the rotational speed, current and temperature. A deep reinforcement learning algorithm is used to dynamically adjust the processing parameters based on the real-time monitored operating status and performance indicators to optimize the shredding effect and processing efficiency. A machine learning algorithm is used to evaluate the current shredding effect and processing efficiency based on the real-time monitored operating status and performance indicators, obtain the evaluation results, and dynamically adjust the processing parameters based on the evaluation results through an adaptive control strategy.

[0027] Among them, the material separation module includes: support vector machine classification model;

[0028] A deep learning algorithm is used to extract key features from garbage materials, including shape, color and texture; adaptive feature scaling and dimensionality reduction technology are used to preprocess the extracted key features; a support vector machine classification model is constructed based on the preprocessed key features, and the constructed support vector machine classification model is used to classify according to the preprocessed key features; a deep clustering algorithm is used to group garbage materials of the same type and attributes into one category.

[0029] Among them, the material tracking module includes: RFID reader;

[0030] High-frequency RFID technology is used to bind a unique RFID tag to each type of garbage material, and the RFID tag is associated with the type and properties of the garbage material; an RFID reader is used to scan the garbage material and read the information on the RFID tag, including the type and properties of the garbage material; based on the read RFID information, the garbage material is associated with the corresponding recycling treatment to ensure that each type of garbage material receives the corresponding recycling treatment; big data analysis technology is used to analyze the read RFID information to optimize the classification and recycling of garbage materials.

[0031] Among them, a garbage identification method based on garbage classification and recycling includes:

[0032] S101: Capture images of waste materials input into the entrance, then perform intelligent recognition on the captured images to obtain recognition results, which include the type and attributes of the waste materials;

[0033] S102: According to the identification result of the waste material, the corresponding processing parameters are automatically retrieved from the processing parameter database, and the processing parameters of the single-shaft shredder are adjusted according to the retrieved processing parameters;

[0034] S103: Intelligently classify the shredded garbage materials according to their types and properties, and then recycle the classified garbage materials.

[0035] Wherein, step S101 includes:

[0036] S1011: Using a high-resolution image sensor to capture high-definition images of the garbage materials input into the entrance to obtain image information of the garbage materials;

[0037] S1012: performing preprocessing operations on the collected image information, the preprocessing operations including grayscale conversion, binarization, noise removal, and edge detection of the image;

[0038] S1013: Using a deep learning model based on image recognition, perform intelligent recognition on the pre-processed image information to obtain recognition results, which include the type and attributes of the waste material.

[0039] Compared with the prior art, the present invention has the following advantages:

[0040] A single-shaft shredder for waste sorting and recycling includes: a material recognition unit for capturing images of waste materials input into an inlet, then intelligently identifying the captured images to obtain recognition results, including the type and properties of the waste materials; a parameter adjustment unit for automatically retrieving corresponding processing parameters from a processing parameter database based on the waste material recognition results, and then adjusting the processing parameters of the single-shaft shredder based on the retrieved processing parameters; and a classification recovery unit for intelligently classifying the shredded waste materials according to their type and properties, and then recycling the classified waste materials. This system achieves automatic identification of waste materials and automatic adjustment of processing parameters, improving processing efficiency and reducing manual intervention.

[0041] Other features and advantages of the present invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the present invention.

[0042] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0044] Figure 1 This is a structural diagram of a single-shaft shredder based on garbage classification and recycling in an embodiment of the present invention;

[0045] Figure 2 This is a structural diagram of a material identification unit in an embodiment of the present invention;

[0046] Figure 3 2 is a structural diagram of a parameter adjustment unit in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0048] An embodiment of the present invention provides a single-shaft shredder based on garbage classification and recycling, comprising:

[0049] The material identification unit is used to collect images of the garbage materials input into the entrance, and then perform intelligent recognition on the collected images to obtain recognition results, which include the type and attributes of the garbage materials;

[0050] A parameter adjustment unit is used to automatically retrieve corresponding processing parameters from a processing parameter database according to the identification result of the waste material, and then adjust the processing parameters of the single-shaft shredder according to the retrieved processing parameters;

[0051] The classification and recycling unit is used to intelligently classify the shredded garbage materials according to their types and properties, and then recycle the classified garbage materials.

[0052] The working principle of the above technical solution is as follows: the garbage recognition unit collects images of the garbage materials input to the entrance, and intelligently recognizes the collected images to obtain recognition results, including the type and attributes of the garbage materials. Then, the parameter adjustment unit automatically retrieves the corresponding processing parameters from the processing parameter database based on the recognition results of the garbage materials and adjusts the processing parameters of the single-shaft shredder. Finally, the garbage classification and recycling unit intelligently classifies the shredded garbage materials according to their types and attributes and carries out corresponding recycling processing;

[0053] Among them, the garbage identification unit collects images of garbage materials through a camera or other image acquisition equipment, and the collected images are pre-processed by an image processing algorithm to extract characteristic information of the garbage materials, which includes shape and color; the garbage identification unit uses an intelligent recognition algorithm to analyze and identify the pre-processed images to obtain the type and attributes of the garbage materials, and the parameter adjustment unit retrieves the corresponding processing parameters from the processing parameter database based on the identification results of the garbage materials. The parameter adjustment unit applies the retrieved processing parameters to the single-axis shredder, and automatically adjusts the shredder's speed, shredding blade angle, feed speed, shredding time and other processing parameters. The single-axis shredder shreds the garbage materials according to the adjusted processing parameters, and the shredded garbage materials enter the garbage classification and recycling unit. The garbage classification and recycling unit uses an intelligent classification algorithm to classify the shredded garbage materials, and sends them to corresponding recycling devices for recycling according to their types and attributes.

[0054] The beneficial effects of the above technical solution are: through the intelligent technology of the garbage identification unit and the parameter adjustment unit, automatic identification of garbage materials and automatic adjustment of processing parameters are realized, which improves processing efficiency and reduces manual intervention; through the intelligent identification and classification algorithm, the type and properties of garbage materials can be accurately identified, accurate classification can be achieved, and the efficiency and quality of garbage recycling are improved; through the intelligent classification and recycling processing of the garbage classification and recycling unit, garbage materials of different types and properties can be effectively recycled and utilized, realizing resource reuse and environmental protection, and through the shredding and classified recycling processing methods, the volume of garbage and the release of pollutants can be effectively reduced, reducing pollution and harm to the environment; through the effective processing of garbage classification and recycling, the value utilization of garbage resources can be realized, and economic benefits and sustainable development can be improved.

[0055] In another embodiment, the material identification unit includes: an image acquisition module, an image preprocessing module, and an identification module;

[0056] An image acquisition module is used to use a high-resolution image sensor to capture high-definition images of the garbage materials input into the entrance and obtain image information of the garbage materials;

[0057] The image preprocessing module is used to perform preprocessing operations on the collected image information. The preprocessing operations include image grayscale, binarization, noise removal and edge detection;

[0058] The recognition module is used to use a deep learning model based on image recognition to intelligently identify the pre-processed image information and obtain recognition results, which include the type and attributes of the garbage material.

[0059] The working principle of the above technical solution is as follows: the garbage identification unit adopts image recognition technology, including an image acquisition module, an image preprocessing module and a recognition module; first, the image acquisition module uses a high-resolution image sensor to collect high-definition images of the garbage materials input into the entrance to obtain image information of the garbage materials; then, the image preprocessing module performs preprocessing operations on the collected image information, including grayscale, binarization, noise removal and edge detection, etc., to extract the characteristic information of the garbage materials; finally, the recognition module uses a deep learning model based on image recognition to perform intelligent recognition of the preprocessed image information to obtain recognition results, including the type and attributes of the garbage materials.

[0060] Among them, the image acquisition module uses a high-resolution image sensor to capture high-definition images of garbage materials to ensure clear image information; the collected image information is processed by the image preprocessing module, first performing a grayscale operation to convert the color image into a grayscale image to simplify subsequent processing, and then performing a binarization operation to convert the grayscale image into a binary image to extract the outline of the object, followed by a noise removal operation to remove noise interference in the image through a filtering algorithm, and finally performing an edge detection operation to extract the edge information of the object; the preprocessed image information is input into the recognition module, and the recognition module uses a deep learning model based on image recognition to perform intelligent recognition of the image. The deep learning model can identify the characteristics of different garbage materials through training and learning, thereby judging the type and attributes of the garbage materials. The recognition module outputs the recognition results, including the type and attributes of the garbage materials. The recognition results can be used as the input of the parameter adjustment unit to automatically adjust the processing parameters and processing methods of the single-axis shredder.

[0061] The beneficial effects of the above technical solution are as follows: the use of image recognition technology can accurately identify garbage materials, thereby improving the accuracy of garbage classification; through image recognition technology and deep learning models, automatic identification of garbage materials is achieved, reducing manual intervention and improving processing efficiency; the deep learning model based on image recognition can learn and identify the characteristics of a variety of garbage materials, and is suitable for the identification of garbage materials of different types and attributes; through the training and updating of the deep learning model, the accuracy and adaptability of recognition can be continuously improved to adapt to the identification needs of different garbage materials; through accurate garbage material identification, accurate classification and recycling of garbage can be achieved, thereby improving the efficiency and quality of garbage recycling; through the effective treatment of garbage classification and recycling, the landfill and incineration of garbage can be reduced, the pollution and harm to the environment can be reduced, and the goal of environmental protection can be achieved.

[0062] In another embodiment, the parameter adjustment unit includes:

[0063] Processing parameter database, used to store processing parameters corresponding to different types and properties of waste materials;

[0064] The database query module is used to retrieve corresponding processing parameters from the processing parameter database according to the type and properties of the waste material through database query technology;

[0065] The processing parameter adjustment module is used to adjust the processing parameters of the single-shaft shredder according to the retrieved processing parameters, and the processing parameters include rotation speed, angle of the shredding blade, feed speed and shredding time.

[0066] The working principle of the above technical solution is as follows: a processing parameter database, a database query module and a processing parameter adjustment module are used to automatically adjust the processing parameters of the single-shaft shredder according to the identification results of the garbage material; first, the processing parameter database adopts a relational database to store the processing parameters corresponding to different types and properties of garbage materials, including rotation speed, shredding blade angle, feed speed and shredding time; then, the database query module adopts hash index query technology to retrieve the corresponding processing parameters from the processing parameter database according to the type and properties of the garbage material; finally, the processing parameter adjustment module adopts an adaptive control strategy to dynamically adjust the processing parameters of the single-shaft shredder according to the retrieved processing parameters.

[0067] Among them, the processing parameter database adopts a relational database, which stores the processing parameters corresponding to different types and attributes of garbage materials in the form of tables, including rotation speed, shredding blade angle, feed speed and shredding time; each type and attribute of garbage material corresponds to a row of records, and each processing parameter corresponds to a column of fields; the database query module adopts hash index query technology, and retrieves the corresponding processing parameters in the processing parameter database through query statements according to the type and attribute of garbage materials. The hash index can quickly locate the corresponding records, thereby improving query efficiency; the processing parameter adjustment module adopts an adaptive control strategy, and dynamically adjusts the processing parameters of the single-axis shredder according to the retrieved processing parameters. According to different types and attributes of garbage materials, the processing parameters such as rotation speed, shredding blade angle, feed speed and shredding time are adjusted to achieve the best shredding effect and processing efficiency.

[0068] The beneficial effects of the above technical solution are as follows: through the processing parameter database and database query module, the corresponding processing parameters can be accurately retrieved according to the type and properties of the garbage material, so as to realize the accurate adjustment of the processing parameters of the single-shaft shredder; the processing parameter adjustment module using the adaptive control strategy can dynamically adjust the processing parameters of the single-shaft shredder according to the processing parameters of different garbage materials to adapt to the processing requirements of different garbage materials; by accurately adjusting the processing parameters, the processing efficiency of the single-shaft shredder can be improved, and efficient garbage processing and recycling can be achieved; according to the adjustment of the processing parameters of different garbage materials, the parameters such as the angle of the shredding blade, the feed speed and the shredding time can be optimized to achieve better shredding effect; by accurately adjusting the processing parameters, unnecessary energy consumption and machine loss can be reduced, the service life of the equipment can be increased and energy can be saved; the automated operation of the parameter adjustment unit reduces manual intervention and improves work efficiency and accuracy.

[0069] In another embodiment, the classification and recycling unit includes: a material separation module, a recycling processing module, and a material tracking module;

[0070] The material separation module uses a support vector machine machine learning algorithm to intelligently classify waste materials according to their types and attributes, and uses a clustering algorithm to group waste materials of the same type and attributes into one category;

[0071] The recycling module is used to automatically select the optimal recycling method for different waste materials according to different classifications using an intelligent decision-making system. The recycling method includes reuse, recycling or other environmentally friendly treatment methods;

[0072] The material tracking module is used to track and manage each type of waste material using RFID technology to ensure that each type of waste material receives corresponding recycling treatment.

[0073] The working principle of the above technical solution is as follows: the material separation module uses the machine learning algorithm of the support vector machine to train the model to intelligently classify the waste materials according to their types and properties. First, a large number of waste material samples are collected and their features are extracted. Then, the support vector machine algorithm is used to train the samples and establish a classification model. In actual application, the image recognition module obtains images of the shredded waste materials, extracts their features, and uses the trained classification model to classify the waste materials, grouping waste materials of the same type and properties into the same category.

[0074] The recycling and processing module uses an intelligent decision-making system to automatically select the optimal recycling and processing method for different types of waste materials. Based on the classification results, the intelligent decision-making system automatically selects the most suitable recycling and processing method for that type of waste materials according to pre-set rules or algorithms. For example, for reusable waste materials, you can choose to reuse or recycle them; for recyclable waste materials, you can choose to recycle them; for waste materials that cannot be reused or recycled, you can choose to treat them in an environmentally friendly way.

[0075] The material tracking module uses RFID technology to track and manage each type of waste material. Each type of waste material is equipped with an RFID tag that contains the type and attribute information of the waste material. After the materials are separated, the RFID tag of each waste material is read by the RFID reader and associated with the corresponding recycling and treatment method. Through the material tracking module, the processing progress of each type of waste material can be monitored in real time to ensure that each type of waste material is properly recycled.

[0076] Among them, according to the different classifications of waste materials, the optimal recycling and treatment method is automatically selected for treatment, including: building a waste material classification-treatment method information database, the information database including: multiple waste material classifications and multiple recycling and treatment methods corresponding to the waste material classifications;

[0077] When receiving waste materials to be processed, the classification information of the waste materials is obtained through the intelligent decision-making system;

[0078] Based on the classification information, retrieving the recycling and processing method corresponding to the waste material classification from the waste material classification-processing method information database;

[0079] When multiple recycling and treatment methods are retrieved, the intelligent decision-making system evaluates the multiple recycling and treatment methods, and the evaluation criteria include: environmental benefits, economic benefits and treatment efficiency;

[0080] Based on the evaluation criteria, determine the best recycling method and associate it with the waste material;

[0081] When the classification information of waste materials changes or becomes unclear, the intelligent decision-making system will remind the processing personnel to conduct corresponding checks and updates;

[0082] Automatically guide or control the corresponding processing equipment to recycle waste materials according to the associated optimal recycling method;

[0083] Ensure that waste materials are processed according to the best recycling methods, thus achieving efficient and environmentally friendly waste material processing;

[0084] Through intelligent decision-making systems, we continuously optimize the waste material processing process to improve processing efficiency and environmental benefits;

[0085] Ensure the automation and intelligent operation of the entire processing system, meet the processing needs of different types of waste materials, and maximize the utilization of resources.

[0086] The beneficial effects of the above technical solution are: the machine learning algorithm of the support vector machine can be used to intelligently classify garbage materials according to their types and properties, thereby improving classification accuracy and efficiency; through the intelligent decision-making system, the optimal recycling and treatment method is automatically selected according to the different classifications of garbage materials, thereby improving recycling and treatment efficiency and resource utilization; through RFID technology, each type of garbage material is tracked and managed to ensure that each type of garbage material receives corresponding recycling and treatment, thereby improving the traceability and management effect of recycling and treatment; through the intelligent classification and recycling treatment of the classified recycling unit, the reuse, recycling or other environmentally friendly treatment methods of garbage materials can be realized, thereby promoting resource recovery and environmental protection; the automated operation of the classified recycling unit reduces manual intervention, improves work efficiency and accuracy, and reduces labor costs and error rates.

[0087] In another embodiment, the database query module includes: a hash mapping submodule;

[0088] A hash function is used to map the types and attributes of garbage materials in the processing parameter database as keywords to unique hash values. The hash mapping submodule uses dynamic hash indexing technology to establish an index based on the hash value and the corresponding processing parameters to locate and retrieve the processing parameters. The query request from the processing parameter adjustment module is received, including the type and attribute of the garbage material, and the hash index query technology is used to locate the corresponding processing parameter through the hash value. Online learning technology is used to dynamically update the processing parameters in the processing parameter database according to the actual operation of the single-axis shredder.

[0089] The working principle of the above technical solution is as follows: the hash mapping submodule uses the hash function to map the types and attributes of garbage materials in the processing parameter database as keywords to a unique hash value. The selection of the hash function should take into account the uniqueness and distribution uniformity of the hash value to improve the query efficiency. The hash value and the corresponding processing parameter are indexed so that the corresponding processing parameter can be quickly located in subsequent queries; the query request from the processing parameter adjustment module is received, including the type and attribute of the garbage material. The query request receiving and parsing module is responsible for receiving the query request and parsing the garbage material type and attribute information therein; the hash index query technology is used to locate the corresponding processing parameter by the hash value. The query module uses hash index query technology to quickly locate the corresponding hash value based on the type and attribute information of the received garbage materials. The corresponding processing parameters can be directly obtained through the index of the hash value and the processing parameters to complete the query operation. The online learning technology is used to dynamically update the processing parameters in the processing parameter database according to the actual operation of the single-axis shredder. By monitoring the operating status and performance indicators of the single-axis shredder, such as speed, current, temperature, etc., the actual situation of the shredding process can be obtained in real time. According to these actual conditions, the online learning technology is used to dynamically adjust and update the processing parameters to optimize the shredding effect and improve the processing efficiency.

[0090] The beneficial effects of the above technical solution are as follows: hash index query technology can quickly locate the corresponding processing parameters, improving query efficiency and accuracy; online learning technology can dynamically update processing parameters according to actual operating conditions, so that the processing parameters can adapt to the characteristics of different garbage materials and the actual situation of the shredder, improving processing effects and resource utilization; through the application of hash index query and online learning technology of the database query module, the positioning, retrieval and dynamic adjustment of processing parameters can be achieved, improving the intelligence and adaptability of the system; optimized processing parameters can improve the shredding effect, reduce energy consumption and environmental pollution, and achieve the goals of resource recovery and environmental protection.

[0091] In another embodiment, the processing parameter adjustment module includes: a high-precision sensor;

[0092] The corresponding processing parameters are obtained from the database query module, including the rotational speed, the angle of the shredding blade, the feed speed and the shredding time. High-precision sensors are used to monitor the operating status and performance indicators of the single-shaft shredder in real time, including the rotational speed, current and temperature. A deep reinforcement learning algorithm is used to dynamically adjust the processing parameters based on the real-time monitored operating status and performance indicators to optimize the shredding effect and processing efficiency. A machine learning algorithm is used to evaluate the current shredding effect and processing efficiency based on the real-time monitored operating status and performance indicators, obtain the evaluation results, and dynamically adjust the processing parameters based on the evaluation results through an adaptive control strategy.

[0093] The working principle of the above technical solution is as follows: the corresponding processing parameters, including rotation speed, shredding blade angle, feed speed and shredding time, are obtained from the database query module. These processing parameters are retrieved from the processing parameter database through hash index query technology according to the type and properties of the garbage material; high-precision sensors are used to monitor the operating status and performance indicators of the single-axis shredder in real time, such as rotation speed, current and temperature. The sensors transmit the data obtained in real time to the processing parameter adjustment module; the deep reinforcement learning algorithm is used to dynamically adjust the processing parameters according to the real-time monitored operating status and performance indicators. The deep reinforcement learning algorithm learns and explores according to the current status and performance indicators. Select appropriate processing parameters for adjustment. The algorithm will continuously optimize the strategy based on the feedback of shredding effect and processing efficiency to achieve the best shredding effect and processing efficiency. Use machine learning algorithm to evaluate the current shredding effect and processing efficiency. According to the real-time monitored operating status and performance indicators, the machine learning algorithm will evaluate the shredding effect and processing efficiency and generate evaluation results. According to the evaluation results, the processing parameters are dynamically adjusted through the adaptive control strategy. The adaptive control strategy adjusts the processing parameters according to the evaluation results to optimize the shredding effect and processing efficiency. The strategy is based on empirical rules, fuzzy logic, and neural network methods. The appropriate strategy is selected according to the specific situation.

[0094] The beneficial effects of the above technical solution are: using high-precision sensors to monitor the operating status and performance indicators of the single-axis shredder in real time, it can accurately obtain the actual situation of the shredding process and provide accurate data support for the subsequent adjustment of processing parameters; using deep reinforcement learning algorithms to dynamically adjust processing parameters, it can automatically learn and optimize processing strategies based on the real-time monitored operating status and performance indicators, thereby improving shredding effects and processing efficiency; using machine learning algorithms to evaluate shredding effects and processing efficiency, it can objectively evaluate the current processing effects and provide a reference basis for subsequent processing parameter adjustments; through adaptive control strategies to dynamically adjust processing parameters, it can flexibly adjust processing parameters according to real-time monitoring and evaluation results to adapt to the characteristics of different garbage materials and shredders, thereby improving processing effects and resource utilization; optimized processing parameters can improve shredding effects, reduce energy consumption and environmental pollution, and achieve the goals of resource recovery and environmental protection.

[0095] In another embodiment, the material separation module includes: a support vector machine classification model;

[0096] A deep learning algorithm is used to extract key features from garbage materials, including shape, color and texture; adaptive feature scaling and dimensionality reduction technology are used to preprocess the extracted key features; a support vector machine classification model is constructed based on the preprocessed key features, and the constructed support vector machine classification model is used to classify according to the preprocessed key features; a deep clustering algorithm is used to group garbage materials of the same type and attributes into one category.

[0097] The working principle of the above technical solution is as follows: key features, including shape, color, and texture, are extracted from waste materials. These features can be extracted through image processing technology and computer vision algorithms. For example, shape features of materials can be extracted using image processing algorithms, color features can be extracted using color analysis algorithms, and texture features can be extracted using texture analysis algorithms. The extracted key features are pre-processed using adaptive feature scaling and dimensionality reduction techniques. Adaptive feature scaling can be performed based on the distribution of features to maintain the relative proportions between features. Dimensionality reduction technology can convert high-dimensional feature space into low-dimensional feature space to reduce the dimensionality of features while retaining key information.

[0098] A support vector machine classification model is constructed based on the key features after preprocessing. Support vector machine is a supervised learning algorithm that achieves classification by constructing an optimal hyperplane. Here, the support vector machine learns the classification rules of different garbage materials based on the key features after preprocessing. Using the constructed support vector machine classification model, unknown garbage materials are classified according to the key features after preprocessing. By inputting the key features of the unknown materials into the support vector machine model, a prediction result of which category the material belongs to can be obtained. A deep clustering algorithm is used to classify garbage materials of the same type and attributes into one category. The deep clustering algorithm can group the materials according to the similarity of their features to form different clusters. Materials in the same cluster have similar features, that is, garbage materials of the same type and attributes.

[0099] The extracted key features are preprocessed, including:

[0100] Construct a garbage material feature information database corresponding to specific treatment sites;

[0101] When the processing site receives new waste materials, obtain basic information about the waste materials;

[0102] Using deep learning algorithms to extract key features from waste materials, including shape, color, and texture;

[0103] Based on the key features, adaptive feature scaling and dimensionality reduction techniques are used to preprocess the extracted key features;

[0104] Obtaining garbage material classification information that matches the pre-processed key features from a garbage material feature information database;

[0105] Determine the treatment method of waste materials based on classification information;

[0106] If the disposal method is recycling, the waste material is allocated to the recycling area;

[0107] If the disposal method is disposal, the waste material is allocated to the disposal area;

[0108] During the entire processing process, real-time images of the processing process are tracked and acquired by at least one image acquisition device disposed in the processing location;

[0109] Based on image recognition technology, it can identify abnormal behaviors during the processing according to real-time images;

[0110] If abnormal behavior is identified, the processing personnel will be immediately notified to make appropriate interventions and adjustments;

[0111] When the waste material processing is completed, the waste material feature information database is updated to facilitate subsequent waste material processing.

[0112] The beneficial effects of the above technical solution are: the use of deep learning algorithms to extract key features can accurately capture important information such as the shape, color and texture of garbage materials, thereby improving the accuracy of classification; the use of adaptive feature scaling and dimensionality reduction technology can reasonably preprocess the extracted key features, reduce feature redundancy and noise, and improve the classification effect; the use of support vector machine classification models can learn the classification rules of different garbage materials and achieve accurate classification; the use of deep clustering algorithms can group garbage materials of the same type and attributes into one category, facilitating subsequent processing and classification statistics; the application of material separation modules can realize the intelligent classification of garbage materials, improve the efficiency of garbage treatment and reduce resource waste, and have a positive impact on environmental protection and resource recycling.

[0113] In another embodiment, the material tracking module includes: an RFID reader;

[0114] High-frequency RFID technology is used to bind a unique RFID tag to each type of garbage material, and the RFID tag is associated with the type and properties of the garbage material; an RFID reader is used to scan the garbage material and read the information on the RFID tag, including the type and properties of the garbage material; based on the read RFID information, the garbage material is associated with the corresponding recycling treatment to ensure that each type of garbage material receives the corresponding recycling treatment; big data analysis technology is used to analyze the read RFID information to optimize the classification and recycling of garbage materials.

[0115] The working principle of the above technical solution is as follows: bind a unique RFID tag to each type of garbage material, and associate the RFID tag with the type and attribute of the garbage material; in the process of garbage material production or classification, paste or embed RFID tags for each type of garbage material, and bind the RFID tags with the type and attribute information of the garbage material; use an RFID reader to scan the garbage material and read the information on the RFID tag, including the type and attribute of the garbage material. When the garbage material passes through the sensing range of the RFID reader, the RFID reader will automatically read the information on the RFID tag and transmit it to the background system for processing; according to the read RFID tag, the garbage material will be scanned and the information on the RFID tag will be read. The FID information is used to associate the waste materials with the corresponding recycling treatment. The background system determines the type and properties of the waste materials based on the read RFID information, and associates them with the corresponding recycling treatment method. For example, for recyclable materials, the system will associate them with recycling stations or recycling centers to ensure that they are properly recycled. Big data analysis technology is used to analyze the read RFID information to optimize the classification and recycling treatment of waste materials. By analyzing a large amount of RFID information, the system can obtain statistical data on the classification and recycling treatment of waste materials, and then optimize the classification and recycling treatment strategy of waste materials, thereby improving recycling efficiency and resource utilization.

[0116] The RFID tags are associated with the types and properties of waste materials, including:

[0117] When the processing site receives new garbage materials, the RFID tag information on the garbage materials is obtained through high-frequency RFID reading equipment;

[0118] Based on the RFID tag information, the type and attribute information of the garbage material corresponding to the RFID tag is retrieved from the garbage material RFID tag information library;

[0119] Associating RFID tags with the types and attributes of the retrieved waste materials to ensure that each type of waste material is bound to a unique RFID tag and that the information on the RFID tag accurately reflects the type and attributes of the waste material;

[0120] During the entire processing process, the RFID tag information of the waste material is continuously tracked and obtained through at least one RFID reading device set up in the processing site;

[0121] Based on RFID technology, the location and status information of the waste material is updated in real time according to the RFID tag information;

[0122] If the RFID tag information of the waste material changes or is lost, the processing personnel will be immediately reminded to conduct corresponding inspections and updates;

[0123] When the waste material processing is completed, the waste material RFID tag information database is updated to ensure that the information in the database is accurate and complete, so as to facilitate the subsequent waste material processing and tracking;

[0124] Through the RFID tag information database, a reliable data support is provided, providing accurate information reference for the classification, tracking and processing of waste materials;

[0125] Ensure the efficient operation of the entire processing system and improve the accuracy and efficiency of waste material processing.

[0126] The beneficial effects of the above technical solution are as follows: the use of RFID technology for material tracking and management can achieve accurate identification and management of each type of waste material, avoiding confusion and mishandling; the binding and reading process of RFID tags is fast and efficient, which can improve the efficiency and accuracy of waste material processing; by associating waste materials with corresponding recycling treatments, it can ensure that each type of waste material is correctly recycled and treated, promoting resource recovery and reuse; the use of big data analysis technology to analyze RFID information can optimize the classification and recycling treatment strategies of waste materials, improve recycling efficiency and resource utilization, and have a positive impact on environmental protection and sustainable development.

[0127] In another embodiment, a method for identifying garbage based on garbage classification and recycling includes:

[0128] S101: Capture images of waste materials input into the entrance, then perform intelligent recognition on the captured images to obtain recognition results, which include the type and attributes of the waste materials;

[0129] S102: According to the identification result of the waste material, the corresponding processing parameters are automatically retrieved from the processing parameter database, and the processing parameters of the single-shaft shredder are adjusted according to the retrieved processing parameters;

[0130] S103: Intelligently classify the shredded garbage materials according to their types and properties, and then recycle the classified garbage materials.

[0131] The working principle of the above technical solution is as follows: the image of the waste material is captured by a camera or other image acquisition device; then, intelligent recognition technology such as deep learning or machine learning is used to process and analyze the captured image, extract the characteristics of the waste material, and compare them with a pre-trained model to obtain the type and attribute of the waste material.

[0132] Based on the identification results of the waste material, the system automatically retrieves the corresponding processing parameters from the processing parameter database; the processing parameter database stores the processing parameters of various waste materials, including the shredder's speed, blade angle, etc. Based on the identification results, the system automatically selects the corresponding processing parameters and applies them to the single-shaft shredder to achieve effective processing of the waste material;

[0133] The shredded waste materials are intelligently classified according to their types and properties. Based on the identification results of the waste materials, the system classifies them into corresponding classification containers or processing equipment; for example, recyclable materials are classified into recycling containers, and hazardous materials are classified into special processing equipment; in this way, the effective classification and recycling of waste materials can be achieved, and the recycling rate of resources can be improved.

[0134] The beneficial effects of the above technical solution are: the use of image recognition technology can automatically identify the type and properties of garbage materials, improving the accuracy and efficiency of recognition; automatic adjustment of processing parameters can realize intelligent adjustment of shredder processing parameters according to the type and properties of garbage materials, improving processing effect and resource utilization; intelligent classification and recycling processing can accurately classify and recycle garbage materials according to their types and properties, realize effective recycling and reuse of resources, and promote environmental protection and sustainable development.

[0135] In another embodiment, step S101 includes:

[0136] S1011: Using a high-resolution image sensor to capture high-definition images of the garbage materials input into the entrance to obtain image information of the garbage materials;

[0137] S1012: performing preprocessing operations on the collected image information, the preprocessing operations including grayscale conversion, binarization, noise removal, and edge detection of the image;

[0138] S1013: Using a deep learning model based on image recognition, perform intelligent recognition on the pre-processed image information to obtain recognition results, which include the type and attributes of the waste material.

[0139] Step S102 includes:

[0140] S1021: Using a relational database to store processing parameters corresponding to different types and properties of waste materials, the processing parameters for each type of waste material include rotation speed, shredding blade angle, feed speed, and shredding time;

[0141] S1022: Retrieving corresponding processing parameters from a processing parameter database based on the type and attributes of the waste material using a hash index query technology;

[0142] S1023: Adopting an adaptive control strategy, dynamically adjusting the processing parameters of the single-shaft shredder according to the retrieved processing parameters, including the rotation speed, the angle of the shredding blade, the feed speed, and the shredding time.

[0143] Step S103 includes:

[0144] S1031: Using a support vector machine (SVM) machine learning algorithm, intelligently classify waste materials based on their types and attributes, and using a clustering algorithm to group waste materials of the same type and attributes into one category;

[0145] S1032: Using an intelligent decision-making system, the optimal recycling method is automatically selected based on the different categories of waste materials. The recycling method includes reuse, recycling, or other environmentally friendly treatment methods;

[0146] S1033: Use RFID technology to track and manage each type of waste material to ensure that each type of waste material is recycled and processed accordingly.

[0147] The working principle of the above technical solution is as follows: using high-resolution image sensors for high-definition image acquisition can obtain detailed image information of waste materials and improve the accuracy and reliability of image recognition; performing image preprocessing operations, including grayscale, binarization, noise removal, and edge detection, can improve image quality, reduce noise interference, and provide clear image data for subsequent image recognition; using a deep learning model based on image recognition, it can intelligently identify the preprocessed image information. The deep learning model has powerful learning and recognition capabilities and can accurately identify the type and attributes of waste materials, improving the accuracy and efficiency of recognition; through intelligent recognition, it can achieve automated classification and management of waste materials, improving the degree of automation and efficiency of processing; intelligent recognition technology based on image recognition can reduce manual intervention, reduce labor costs, and improve work efficiency and production benefits.

[0148] The beneficial effects of the above technical solution are: through accurate identification of garbage materials, accurate classification and recycling of garbage can be achieved, thereby improving the efficiency and quality of garbage recycling; through effective treatment of garbage classification and recycling, landfill and incineration of garbage can be reduced, pollution and harm to the environment can be reduced, and the goal of environmental protection can be achieved.

[0149] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A single-shaft shredder based on garbage classification and recycling, characterized in that: include: The material identification unit is used to collect images of the garbage materials input into the entrance, and then perform intelligent recognition on the collected images to obtain recognition results, which include the type and attributes of the garbage materials; A parameter adjustment unit is used to automatically retrieve corresponding processing parameters from a processing parameter database according to the identification result of the waste material, and then adjust the processing parameters of the single-shaft shredder according to the retrieved processing parameters; The classification and recycling unit is used to intelligently classify the shredded waste materials according to their types and properties, and then recycle the classified waste materials; The parameter adjustment unit includes: a processing parameter database, a database query module and a processing parameter adjustment module; A processing parameter database, which uses a relational database to store processing parameters corresponding to different types and properties of garbage materials. The processing parameters for each type of garbage material include rotation speed, shredding blade angle, feed speed, and shredding time; The database query module is used to retrieve the corresponding processing parameters from the processing parameter database according to the type and properties of the waste material through hash index query technology; The database query module includes: a hash mapping submodule; A hash function is used to map the types and attributes of waste materials in the processing parameter database as keywords to unique hash values. The hash mapping submodule uses dynamic hash indexing technology to establish an index based on the hash value and the corresponding processing parameter to locate and retrieve the processing parameter. The module receives query requests from the processing parameter adjustment module, including the types and attributes of waste materials, and uses hash index query technology to locate the corresponding processing parameter based on the hash value. Online learning technology is used to dynamically update the processing parameters in the processing parameter database based on the actual operation of the single-shaft shredder. a processing parameter adjustment module for dynamically adjusting the processing parameters of the single-shaft shredder, including the rotational speed, the angle of the shredding blade, the feed speed, and the shredding time, based on the retrieved processing parameters using an adaptive control strategy; The processing parameter adjustment module includes: high-precision sensor; The corresponding processing parameters are obtained from the database query module, including the rotational speed, the angle of the shredding blade, the feed speed and the shredding time. High-precision sensors are used to monitor the operating status and performance indicators of the single-shaft shredder in real time, including the rotational speed, current and temperature. A deep reinforcement learning algorithm is used to dynamically adjust the processing parameters based on the real-time monitored operating status and performance indicators to optimize the shredding effect and processing efficiency. A machine learning algorithm is used to evaluate the current shredding effect and processing efficiency based on the real-time monitored operating status and performance indicators, obtain the evaluation results, and dynamically adjust the processing parameters based on the evaluation results through an adaptive control strategy.

2. A single-shaft shredder based on garbage classification and recycling according to claim 1, characterized in that: The material identification unit includes: image acquisition module, image preprocessing module and identification module; An image acquisition module is used to use a high-resolution image sensor to capture high-definition images of the garbage materials input into the entrance and obtain image information of the garbage materials; The image preprocessing module is used to perform preprocessing operations on the collected image information. The preprocessing operations include image grayscale, binarization, noise removal and edge detection; The recognition module is used to use a deep learning model based on image recognition to intelligently identify the pre-processed image information and obtain recognition results, which include the type and attributes of the garbage material.

3. The single-shaft shredder based on garbage classification and recycling according to claim 2 is characterized in that: The classification and recycling unit includes: material separation module, recycling processing module and material tracking module; The material separation module uses a support vector machine machine learning algorithm to intelligently classify waste materials according to their types and attributes, and uses a clustering algorithm to group waste materials of the same type and attributes into one category; The recycling module is used to automatically select the optimal recycling method for different waste materials according to different classifications using an intelligent decision-making system. The recycling method includes reuse, recycling or other environmentally friendly treatment methods; The material tracking module is used to track and manage each type of waste material using RFID technology to ensure that each type of waste material receives corresponding recycling treatment.

4. The single-shaft shredder based on garbage classification and recycling according to claim 3 is characterized in that: The material separation module includes: support vector machine classification model; A deep learning algorithm is used to extract key features from garbage materials, including shape, color and texture; adaptive feature scaling and dimensionality reduction technology are used to preprocess the extracted key features; a support vector machine classification model is constructed based on the preprocessed key features, and the constructed support vector machine classification model is used to classify according to the preprocessed key features; a deep clustering algorithm is used to group garbage materials of the same type and attributes into one category.

5. The single-shaft shredder based on garbage classification and recycling according to claim 4 is characterized in that: The material tracking module includes: RFID reader; High-frequency RFID technology is used to bind a unique RFID tag to each type of garbage material, and the RFID tag is associated with the type and properties of the garbage material; an RFID reader is used to scan the garbage material and read the information on the RFID tag, including the type and properties of the garbage material; based on the read RFID information, the garbage material is associated with the corresponding recycling treatment to ensure that each type of garbage material receives the corresponding recycling treatment; big data analysis technology is used to analyze the read RFID information to optimize the classification and recycling of garbage materials.

6. A garbage identification method based on garbage classification and recycling, characterized in that: The method uses the single-shaft shredder based on garbage classification and recycling as claimed in claim 5, and the method comprises: S101: Capture images of waste materials input into the entrance, then perform intelligent recognition on the captured images to obtain recognition results, which include the type and attributes of the waste materials; S102: According to the identification result of the waste material, the corresponding processing parameters are automatically retrieved from the processing parameter database, and the processing parameters of the single-shaft shredder are adjusted according to the retrieved processing parameters; S103: Intelligently classify the shredded waste materials according to their types and attributes, and then recycle the classified waste materials; Step S102 includes: S1021: Using a relational database to store processing parameters corresponding to different types and properties of waste materials, the processing parameters for each type of waste material include rotation speed, shredding blade angle, feed speed, and shredding time; S1022: Retrieving corresponding processing parameters from a processing parameter database based on the type and attributes of the waste material using a hash index query technology; The system further includes: using a hash function to map the types and attributes of waste materials in the processing parameter database as keywords to a unique hash value; a hash mapping submodule using dynamic hash indexing technology to establish an index based on the hash value and the corresponding processing parameter to achieve positioning and retrieval of the processing parameter; receiving a query request from the processing parameter adjustment module, including the type and attribute of the waste material, and using the hash index query technology to locate the corresponding processing parameter through the hash value; and using online learning technology to dynamically update the processing parameters in the processing parameter database based on the actual operation of the single-shaft shredder. S1023: Adopting an adaptive control strategy, dynamically adjusting the processing parameters of the single-shaft shredder according to the retrieved processing parameters, including the rotation speed, the angle of the shredding blade, the feed speed, and the shredding time.

7. The method for identifying garbage based on garbage classification and recycling according to claim 6, characterized in that: Step S101 includes: S1011: Using a high-resolution image sensor to capture high-definition images of the garbage materials input into the entrance to obtain image information of the garbage materials; S1012: performing preprocessing operations on the collected image information, the preprocessing operations including grayscale conversion, binarization, noise removal, and edge detection of the image; S1013: Using a deep learning model based on image recognition, perform intelligent recognition on the pre-processed image information to obtain recognition results, which include the type and attributes of the waste material.

Images