A food waste treatment system and method based on image recognition
By using an image recognition-based food waste treatment system and intelligent control through data acquisition, parameter optimization, and compensation modules, the problems of low efficiency and poor accuracy in food waste treatment have been solved, achieving efficient and accurate waste treatment and resource utilization.
Patent Information
- Application Number
- CN202510348861.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-24
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2045-03-24
AI Technical Summary
Current methods for handling kitchen waste suffer from low processing efficiency and difficulty in ensuring accurate sorting.
An image recognition-based food waste treatment system is adopted. Through the cooperation of data acquisition, parameter determination, parameter optimization and parameter compensation modules, intelligent control of the food waste treatment process is achieved, including target detection, feature fusion, equipment status monitoring and response time adjustment.
It has improved the accuracy and efficiency of waste disposal, providing strong support for urban waste sorting and resource utilization.
Smart Images

Figure CN120394504B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image recognition technology, and more specifically, to a food waste treatment system and method based on image recognition. Background Technology
[0002] In dealing with the current problem of food waste, we typically employ two main methods: manual sorting and mechanical shredding. However, these methods face a series of problems and challenges. First, manual sorting is relatively inefficient, consuming significant human resources and being particularly slow when processing large volumes of waste. Second, due to the subjectivity and instability of manual sorting, accuracy is often difficult to guarantee, potentially leading to the incorrect disposal of materials that should be recycled.
[0003] Therefore, it is necessary to design an image recognition-based food waste treatment system and method to solve the problems existing in the current technology. Summary of the Invention
[0004] In view of this, the present invention proposes a food waste treatment system and method based on image recognition, aiming to solve the problem of low processing efficiency in the current technology for food waste treatment.
[0005] In one aspect, the present invention proposes an image recognition-based food waste treatment system, comprising:
[0006] The data acquisition module is configured to collect video image data and quality data of the waste to be processed inside the kitchen waste processor.
[0007] The parameter determination module is configured to parse the video image data, determine whether there is waste to be processed in the video image data based on the parsing result; if so, calculate the comprehensive feature value of the waste to be processed in the video image data with qualified clarity, and determine the initial crushing parameters of the waste to be processed based on the comprehensive feature value and quality data.
[0008] The parameter optimization module is configured to collect the equipment status information of the food waste processor, parse the equipment status information to obtain equipment status feature values, calculate equipment deviation values based on the equipment status feature values, determine whether to optimize the initial crushing parameters based on the equipment deviation values, and if so, determine the optimization coefficient of the initial crushing parameters based on the equipment deviation values and obtain optimized crushing parameters.
[0009] The parameter compensation module is configured to collect the actual response time of the kitchen waste processor, and determine whether to compensate the optimized crushing parameters based on the actual response time; if so, calculate the difference between the actual response time and the standard response time, and record it as the response time difference, determine the compensation coefficient of the optimized crushing parameters based on the response time difference, and obtain the compensated crushing parameters.
[0010] The execution module is configured to receive the compensation crushing parameters and control the kitchen waste processor to perform waste processing operations based on the compensation crushing parameters.
[0011] Furthermore, when the parameter determination module determines whether there is unprocessed garbage in the video image data based on the parsing results, it includes:
[0012] The video image data is processed using a target detection algorithm to identify garbage targets in the video image data and determine whether the garbage targets are garbage to be processed.
[0013] When the target waste matches the preset target, the target waste is determined to be the waste to be processed.
[0014] When the target waste does not match the preset target, it is determined that the target waste is not the waste to be processed.
[0015] Furthermore, when the parameter determination module calculates the comprehensive feature value of the waste to be processed in the video image data with acceptable clarity, it includes:
[0016] The video image data with acceptable clarity is preprocessed to extract the shape, color, and texture features of the waste to be processed;
[0017] The shape features, color features, and texture features are fused using a feature fusion algorithm to obtain the comprehensive feature value of the waste to be processed.
[0018] Furthermore, when the parameter determination module determines the initial crushing parameters of the waste to be processed based on the comprehensive characteristic values and quality data, it includes:
[0019] Feature extraction is performed on the quality data to obtain quality feature values;
[0020] Based on the comprehensive characteristic value and the comprehensive characteristic threshold, the quality characteristic value is compared with the quality standard value, and the initial crushing parameters of the waste to be processed are determined based on the comparison result.
[0021] When the comprehensive characteristic value is greater than or equal to the comprehensive characteristic threshold, and the quality characteristic value is greater than or equal to the quality standard value, the initial crushing parameter is determined to be the first crushing parameter;
[0022] When the comprehensive characteristic value is greater than or equal to the comprehensive characteristic threshold and the quality characteristic value is less than the quality standard value, the initial crushing parameter is determined to be the second crushing parameter;
[0023] When the comprehensive characteristic value is less than the comprehensive characteristic threshold and the quality characteristic value is greater than or equal to the quality standard value, the initial crushing parameter is determined to be the third crushing parameter;
[0024] When the comprehensive characteristic value is less than the comprehensive characteristic threshold and the quality characteristic value is less than the quality standard value, the initial crushing parameter is determined to be the fourth crushing parameter.
[0025] Further, when the parameter optimization module calculates the equipment deviation value based on the equipment state characteristic value, and determines whether to optimize the initial crushing parameters based on the equipment deviation value, it includes:
[0026] Obtain the standard value of the device state corresponding to each of the device state feature values;
[0027] Calculate the number of device status characteristic values that are greater than the device status standard value, and record it as the first number;
[0028] Calculate the number of device status characteristic values that are less than or equal to the device status standard value, and record them as the second quantity;
[0029] The equipment deviation value is calculated based on the equipment status characteristic value, the equipment status standard value, the first quantity, and the second quantity.
[0030] The equipment deviation value is compared with the equipment deviation threshold, and the initial crushing parameters are optimized based on the comparison result.
[0031] When the deviation value of the equipment is less than the deviation threshold of the equipment, it is determined that the initial crushing parameters will not be optimized.
[0032] When the deviation value of the equipment is greater than or equal to the deviation threshold of the equipment, it is determined that the initial crushing parameters should be optimized.
[0033] Further, when the parameter optimization module determines the optimization coefficient of the initial crushing parameters based on the equipment deviation value and obtains the optimized crushing parameters, it includes:
[0034] The equipment deviation value is compared with the first equipment deviation value and the second equipment deviation value, and the optimization coefficient of the initial crushing parameter is determined based on the comparison result; wherein the first equipment deviation value is less than the second equipment deviation value;
[0035] An optimization coefficient range is defined, wherein the optimization coefficient range includes a first optimization coefficient, a second optimization coefficient, and a third optimization coefficient;
[0036] When the deviation value of the equipment is less than or equal to the first deviation value of the equipment, the optimization coefficient is determined as the first optimization coefficient, and the product of the first optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter;
[0037] When the deviation value of the equipment is greater than the first equipment deviation value and less than or equal to the second equipment deviation value, the optimization coefficient is determined as the second optimization coefficient, and the product of the second optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter;
[0038] When the deviation value of the equipment is greater than the deviation value of the second equipment, the optimization coefficient is determined as the third optimization coefficient, and the product of the third optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter.
[0039] Furthermore, when the parameter compensation module determines whether to compensate the optimized crushing parameters based on the actual response time, it includes:
[0040] The actual response time is compared with the standard response time, and the result of the comparison determines whether to compensate for the optimized crushing parameters.
[0041] When the actual response time is greater than the standard response time, it is determined that the optimized crushing parameters should be compensated.
[0042] When the actual response time is less than or equal to the standard response time, it is determined that no compensation will be made for the optimized crushing parameters.
[0043] Further, when the parameter compensation module determines the compensation coefficient of the optimized crushing parameters based on the response time difference and obtains the compensated crushing parameters, it includes:
[0044] The response time difference is compared with historical data, and the compensation coefficient of the optimized crushing parameters is determined based on the comparison results.
[0045] When there is a historical response time difference in the historical data that is the same as the response time difference, the historical compensation coefficient corresponding to the historical response time difference is used as the compensation coefficient of the optimized crushing parameter, and the product of the historical compensation coefficient and the optimized crushing parameter is used as the compensated crushing parameter.
[0046] When there is no historical response time difference in the historical data that is the same as the response time difference, calculate the difference between the response time difference and the historical data one by one, and record it as the difference response time. Extract the minimum value of the difference response time and record it as the minimum difference response time. Determine the compensation coefficient of the optimized crushing parameters based on the minimum difference response time, and obtain the compensated crushing parameters.
[0047] Further, when the parameter compensation module determines the compensation coefficient of the optimized crushing parameters based on the minimum difference response time and obtains the compensated crushing parameters, it includes:
[0048] The minimum difference response time is compared with the first minimum difference response time and the second minimum difference response time, and the compensation coefficient of the optimized crushing parameter is determined based on the comparison result; wherein, the first minimum difference response time is less than the second minimum difference response time;
[0049] When the minimum difference response time is less than or equal to the first minimum difference response time, the compensation coefficient is determined as the first compensation coefficient, and the product of the first compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter.
[0050] When the minimum difference response time is greater than the first minimum difference response time and less than or equal to the second minimum difference response time, the compensation coefficient is determined to be the second compensation coefficient, and the product of the second compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter.
[0051] When the minimum difference response time is greater than the second minimum difference response time, the compensation coefficient is determined to be the third compensation coefficient, and the product of the third compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter.
[0052] Compared with the prior art, the beneficial effects of the present invention are as follows: The image recognition-based kitchen waste treatment system provided by the present invention achieves intelligent control of the kitchen waste treatment process through the cooperation of data acquisition module, parameter determination module, parameter optimization module, parameter compensation module and execution module, thereby improving the accuracy and efficiency of waste treatment and providing strong support for urban waste classification and resource utilization.
[0053] In another aspect, the present invention also proposes a method for treating kitchen waste based on image recognition, comprising the following steps:
[0054] S100: Collects video image data and quality data of the waste to be processed from inside the kitchen waste processor;
[0055] S200: Analyze the video image data, and determine whether there is waste to be processed in the video image data based on the analysis result; if so, calculate the comprehensive feature value of the waste to be processed in the video image data with qualified clarity, and determine the initial crushing parameters of the waste to be processed based on the comprehensive feature value and quality data.
[0056] S300: Collect the equipment status information of the kitchen waste processor, parse the equipment status information to obtain equipment status feature values, calculate the equipment deviation value based on the equipment status feature values, and determine whether to optimize the initial crushing parameters based on the equipment deviation value; if so, determine the optimization coefficient of the initial crushing parameters based on the equipment deviation value, and obtain the optimized crushing parameters.
[0057] S400: Collect the actual response time of the kitchen waste processor, and determine whether to compensate the optimized crushing parameters based on the actual response time; if so, calculate the difference between the actual response time and the standard response time, and record it as the response time difference; determine the compensation coefficient of the optimized crushing parameters based on the response time difference, and obtain the compensated crushing parameters.
[0058] S500: Receive the compensation crushing parameters and control the kitchen waste processor to perform waste processing operations according to the compensation crushing parameters.
[0059] It is understandable that the above-mentioned image recognition-based kitchen waste treatment system and method have the same beneficial effects, and will not be elaborated further here. Attached Figure Description
[0060] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:
[0061] Figure 1 This is a structural block diagram of a food waste treatment system based on image recognition provided in an embodiment of the present invention;
[0062] Figure 2 A flowchart illustrating a kitchen waste treatment method based on image recognition provided in an embodiment of the present invention. Detailed Implementation
[0063] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.
[0064] See Figure 1 As shown in some embodiments of this application, this embodiment provides a food waste treatment system based on image recognition, including:
[0065] The data acquisition module is configured to collect video image data and quality data of the waste to be processed inside the kitchen waste processor.
[0066] The parameter determination module is configured to parse the video image data, determine whether there is waste to be processed in the video image data based on the parsing result; if so, calculate the comprehensive feature value of the waste to be processed in the video image data with qualified clarity, and determine the initial crushing parameters of the waste to be processed based on the comprehensive feature value and quality data.
[0067] The parameter optimization module is configured to collect the equipment status information of the food waste processor, parse the equipment status information to obtain equipment status feature values, calculate equipment deviation values based on the equipment status feature values, determine whether to optimize the initial crushing parameters based on the equipment deviation values, and if so, determine the optimization coefficient of the initial crushing parameters based on the equipment deviation values and obtain optimized crushing parameters.
[0068] The parameter compensation module is configured to collect the actual response time of the kitchen waste processor, and determine whether to compensate the optimized crushing parameters based on the actual response time; if so, calculate the difference between the actual response time and the standard response time, and record it as the response time difference, determine the compensation coefficient of the optimized crushing parameters based on the response time difference, and obtain the compensated crushing parameters.
[0069] The execution module is configured to receive the compensation crushing parameters and control the kitchen waste processor to perform waste processing operations based on the compensation crushing parameters.
[0070] It is understood that the image recognition-based food waste treatment system provided in this embodiment, through the cooperation of a data acquisition module, a parameter determination module, a parameter optimization module, a parameter compensation module, and an execution module, achieves intelligent control of the food waste treatment process, improves the accuracy and efficiency of waste treatment, and provides strong support for urban waste classification and resource utilization. Specifically: First, the data acquisition module is responsible for collecting video image data and quality data of the waste to be treated inside the food waste processor. This data is the basis for subsequent processing and analysis, and is crucial to ensuring the accuracy and targeting of waste treatment. Next, the parameter determination module analyzes the video image data to determine whether the waste to be treated appears in the video image data. Once the waste to be treated appears, the module calculates the comprehensive feature value of the waste to be treated in the video image data with acceptable clarity, and determines the initial crushing parameters of the waste to be treated based on the comprehensive feature value and the quality data. This process makes full use of image recognition technology, improving the level of intelligence in waste treatment. Then, the parameter optimization module collects the equipment status information of the food waste processor, analyzes the equipment status information, and obtains the equipment status feature value. Based on the equipment's state characteristic values, the module calculates the equipment deviation value and determines whether to optimize the initial crushing parameters based on this value. If optimization is needed, the module determines the optimization coefficient of the initial crushing parameters based on the equipment deviation value and obtains the optimized crushing parameters. This process ensures that the waste processor operates in optimal condition, improving the efficiency and effectiveness of waste treatment. In the parameter compensation stage, the parameter compensation module collects the actual response time of the food waste processor and determines whether to compensate for the optimized crushing parameters based on the actual response time. If compensation is needed, the module calculates the difference between the actual response time and the standard response time and records it as the response time difference. Based on the response time difference, the module determines the compensation coefficient of the optimized crushing parameters and obtains the compensated crushing parameters. This process further improves the accuracy and stability of waste treatment. Finally, the execution module receives the compensated crushing parameters and controls the food waste processor to perform waste treatment operations based on these parameters. This process achieves precise control of the waste treatment process, ensuring its smooth operation.
[0071] Specifically, when the parameter determination module determines whether there is garbage to be processed in the video image data based on the parsing results, it includes:
[0072] The video image data is processed using a target detection algorithm to identify garbage targets in the video image data and determine whether the garbage targets are garbage to be processed.
[0073] When the target waste matches the preset target, the target waste is determined to be the waste to be processed.
[0074] When the target waste does not match the preset target, it is determined that the target waste is not the waste to be processed.
[0075] Understandably, preset targets refer to the types of kitchen waste that are pre-defined in the system and require processing. For example, preset targets may include common kitchen waste such as vegetable scraps, fruit peels, and leftover food. By processing video image data through target detection algorithms, the system can automatically identify waste targets in the video and compare them with preset targets to determine whether the waste targets are the waste to be processed. This process greatly improves the accuracy and efficiency of waste identification.
[0076] Specifically, when the parameter determination module calculates the comprehensive feature value of the garbage to be processed in the video image data with acceptable clarity, it includes:
[0077] The video image data with acceptable clarity is preprocessed to extract the shape, color, and texture features of the waste to be processed;
[0078] The shape features, color features, and texture features are fused using a feature fusion algorithm to obtain the comprehensive feature value of the waste to be processed.
[0079] It is understandable that video image data with acceptable clarity refers to video image data whose image quality meets the system's set standards, and this data can accurately reflect the characteristic information of the waste to be processed.
[0080] Understandably, the specific process of fusion processing involves weighted summation or weighted averaging of shape, color, and texture features to obtain a more accurate and comprehensive integrated feature value of the waste to be processed. This process fully considers the feature information of the waste in different aspects, improving the accuracy and completeness of feature extraction.
[0081] Specifically, when the parameter determination module determines the initial crushing parameters of the waste to be processed based on the comprehensive characteristic values and quality data, it includes:
[0082] Feature extraction is performed on the quality data to obtain quality feature values;
[0083] Based on the comprehensive characteristic value and the comprehensive characteristic threshold, the quality characteristic value is compared with the quality standard value, and the initial crushing parameters of the waste to be processed are determined based on the comparison result.
[0084] When the comprehensive characteristic value is greater than or equal to the comprehensive characteristic threshold, and the quality characteristic value is greater than or equal to the quality standard value, the initial crushing parameter is determined to be the first crushing parameter;
[0085] When the comprehensive characteristic value is greater than or equal to the comprehensive characteristic threshold and the quality characteristic value is less than the quality standard value, the initial crushing parameter is determined to be the second crushing parameter;
[0086] When the comprehensive characteristic value is less than the comprehensive characteristic threshold and the quality characteristic value is greater than or equal to the quality standard value, the initial crushing parameter is determined to be the third crushing parameter;
[0087] When the comprehensive characteristic value is less than the comprehensive characteristic threshold and the quality characteristic value is less than the quality standard value, the initial crushing parameter is determined to be the fourth crushing parameter.
[0088] Understandably, quality characteristic values refer to the specific numerical values of the quality attributes of the waste to be treated after quantification. These values reflect the physical characteristics of the waste and its treatment requirements. The comprehensive characteristic threshold is derived from statistical analysis of historical processing data and waste type characteristics, serving as a critical value to distinguish different waste types and treatment needs. Quality standard values are set according to environmental protection requirements and resource utilization goals for waste treatment, used to assess whether the waste to be treated meets the treatment standards. By comparing the comprehensive characteristic values, quality characteristic values, and corresponding thresholds and standard values, the system can intelligently select the most suitable initial crushing parameters, ensuring the targeted and efficient nature of waste treatment.
[0089] In this embodiment, the order of crushing parameters is: first crushing parameter > second crushing parameter > third crushing parameter > fourth crushing parameter. This means that when the comprehensive characteristic value and quality characteristic value of the waste to be processed are both high, the system will select a more intense crushing parameter to ensure that the waste is fully crushed and processed. Conversely, when the comprehensive characteristic value and quality characteristic value of the waste to be processed are both low, the system will select a gentler crushing parameter to avoid unnecessary energy consumption and equipment wear. This intelligent parameter selection method not only improves the efficiency of waste treatment but also extends the service life of the equipment and reduces operating costs.
[0090] Specifically, when the parameter optimization module calculates the equipment deviation value based on the equipment state characteristic value, and determines whether to optimize the initial crushing parameters based on the equipment deviation value, it includes:
[0091] Obtain the standard value of the device state corresponding to each of the device state feature values;
[0092] Calculate the number of device status characteristic values that are greater than the device status standard value, and record it as the first number;
[0093] Calculate the number of device status characteristic values that are less than or equal to the device status standard value, and record them as the second quantity;
[0094] The equipment deviation value is calculated based on the equipment status characteristic value, the equipment status standard value, the first quantity, and the second quantity.
[0095] The equipment deviation value is compared with the equipment deviation threshold, and the initial crushing parameters are optimized based on the comparison result.
[0096] When the deviation value of the equipment is less than the deviation threshold of the equipment, it is determined that the initial crushing parameters will not be optimized.
[0097] When the deviation value of the equipment is greater than or equal to the deviation threshold of the equipment, it is determined that the initial crushing parameters should be optimized.
[0098] In this embodiment, equipment status characteristic values refer to various performance indicators and status parameters exhibited by the equipment during operation. These characteristic values reflect the current working state and performance of the equipment. For example, equipment status characteristic values may include the equipment's rotational speed, temperature, vibration, and degree of wear. Equipment status standard values refer to the standard values that various performance indicators and status parameters should reach under normal operating conditions. These standard values are determined comprehensively based on factors such as the equipment's design specifications, operating experience, and maintenance requirements, and are used to assess whether the equipment's operating status is normal.
[0099] In this embodiment, the calculation process for equipment deviation values involves calculating the difference between each equipment state characteristic value and its corresponding equipment state standard value to obtain the degree of deviation for each characteristic value. Then, a weighted average of these deviation degrees is applied based on a first quantity and a second quantity to obtain the overall deviation value for the equipment. The equipment deviation threshold is derived from statistical analysis of historical equipment state data and waste treatment results, used to determine whether the equipment state deviates from the normal range, thereby deciding whether to optimize the initial crushing parameters. This process ensures that the waste processor operates in optimal condition, avoiding poor treatment results and increased energy consumption due to inadequate equipment condition.
[0100] Specifically, when the parameter optimization module determines the optimization coefficient of the initial crushing parameters based on the equipment deviation value and obtains the optimized crushing parameters, it includes:
[0101] The equipment deviation value is compared with the first equipment deviation value and the second equipment deviation value, and the optimization coefficient of the initial crushing parameter is determined based on the comparison result; wherein the first equipment deviation value is less than the second equipment deviation value;
[0102] An optimization coefficient range is defined, wherein the optimization coefficient range includes a first optimization coefficient, a second optimization coefficient, and a third optimization coefficient;
[0103] When the deviation value of the equipment is less than or equal to the first deviation value of the equipment, the optimization coefficient is determined as the first optimization coefficient, and the product of the first optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter;
[0104] When the deviation value of the equipment is greater than the first equipment deviation value and less than or equal to the second equipment deviation value, the optimization coefficient is determined as the second optimization coefficient, and the product of the second optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter;
[0105] When the deviation value of the equipment is greater than the deviation value of the second equipment, the optimization coefficient is determined as the third optimization coefficient, and the product of the third optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter.
[0106] Understandably, the first optimization coefficient < the second optimization coefficient < the third optimization coefficient. This means that when the equipment deviation is small, the system will choose a smaller optimization coefficient, making smaller adjustments to the initial crushing parameters to maintain stable equipment operation. Conversely, when the equipment deviation is large, the system will choose a larger optimization coefficient, making larger adjustments to the initial crushing parameters to quickly restore the equipment to its optimal state. This intelligent optimization method not only improves the stability and reliability of waste treatment but also further enhances the equipment's operating efficiency and processing effect.
[0107] Specifically, when the parameter compensation module determines whether to compensate the optimized crushing parameters based on the actual response time, it includes:
[0108] The actual response time is compared with the standard response time, and the result of the comparison determines whether to compensate for the optimized crushing parameters.
[0109] When the actual response time is greater than the standard response time, it is determined that the optimized crushing parameters should be compensated.
[0110] When the actual response time is less than or equal to the standard response time, it is determined that no compensation will be made for the optimized crushing parameters.
[0111] Understandably, standard response time refers to the time required for the system to start executing a processing operation from receiving a processing instruction under ideal conditions. Actual response time, however, can be affected by various factors such as equipment status and network latency, leading to differences from the standard response time. When the actual response time exceeds the standard response time, it means the system response speed is slower, potentially causing delays in waste processing. To compensate for this delay, the parameter compensation module adjusts the optimized crushing parameters to ensure the timeliness and accuracy of waste processing. The compensation coefficient is directly proportional to the difference in response time; that is, the larger the difference, the larger the compensation coefficient, and the greater the adjustment range of the optimized crushing parameters. This further improves the stability and accuracy of waste processing, ensuring the reliable operation of the waste processing system.
[0112] Specifically, when the parameter compensation module determines the compensation coefficient of the optimized crushing parameters based on the response time difference and obtains the compensated crushing parameters, it includes:
[0113] The response time difference is compared with historical data, and the compensation coefficient of the optimized crushing parameters is determined based on the comparison results.
[0114] When there is a historical response time difference in the historical data that is the same as the response time difference, the historical compensation coefficient corresponding to the historical response time difference is used as the compensation coefficient of the optimized crushing parameter, and the product of the historical compensation coefficient and the optimized crushing parameter is used as the compensated crushing parameter.
[0115] When there is no historical response time difference in the historical data that is the same as the response time difference, calculate the difference between the response time difference and the historical data one by one, and record it as the difference response time. Extract the minimum value of the difference response time and record it as the minimum difference response time. Determine the compensation coefficient of the optimized crushing parameters based on the minimum difference response time, and obtain the compensated crushing parameters.
[0116] Understandably, historical data includes several historical response time differences and their corresponding historical compensation coefficients. By comparing the response time differences in historical data with the current response time difference, the system can intelligently select an appropriate compensation coefficient. When there are cases in the historical data where the response time difference is the same as the current one, the system can directly use the historical compensation coefficient, which greatly improves the accuracy and efficiency of compensation. When there are no completely identical cases in the historical data, the system calculates the difference response time and selects the minimum difference response time to determine the compensation coefficient. This process ensures the refinement and intelligence of the compensation.
[0117] Specifically, when the parameter compensation module determines the compensation coefficient of the optimized crushing parameters based on the minimum difference response time and obtains the compensated crushing parameters, it includes:
[0118] The minimum difference response time is compared with the first minimum difference response time and the second minimum difference response time, and the compensation coefficient of the optimized crushing parameter is determined based on the comparison result; wherein, the first minimum difference response time is less than the second minimum difference response time;
[0119] When the minimum difference response time is less than or equal to the first minimum difference response time, the compensation coefficient is determined as the first compensation coefficient, and the product of the first compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter.
[0120] When the minimum difference response time is greater than the first minimum difference response time and less than or equal to the second minimum difference response time, the compensation coefficient is determined to be the second compensation coefficient, and the product of the second compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter.
[0121] When the minimum difference response time is greater than the second minimum difference response time, the compensation coefficient is determined to be the third compensation coefficient, and the product of the third compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter.
[0122] Understandably, the first compensation coefficient < the second compensation coefficient < the third compensation coefficient. This means that when the minimum difference response time is small, the system will choose a smaller compensation coefficient, resulting in a smaller adjustment to the optimized crushing parameters, to avoid over-compensation leading to instability in equipment operation. Conversely, when the minimum difference response time is large, the system will choose a larger compensation coefficient, making larger adjustments to the optimized crushing parameters to quickly compensate for the response time delay, ensuring the timeliness and accuracy of waste treatment. This intelligent compensation mechanism not only improves the stability and efficiency of waste treatment but also further enhances the system's adaptability and robustness, enabling it to maintain excellent processing performance in various complex environments.
[0123] In this embodiment, the first minimum difference response time and the second minimum difference response time are derived from the statistical analysis of the historical response time differences and compensation effects by the system, and are used to distinguish the degree of influence of different response time differences on the selection of compensation coefficients.
[0124] See Figure 2 As shown in some embodiments of this application, this embodiment provides a method for treating kitchen waste based on image recognition, including the following steps:
[0125] S100: Collects video image data and quality data of the waste to be processed from inside the kitchen waste processor;
[0126] S200: Analyze the video image data, and determine whether there is waste to be processed in the video image data based on the analysis result; if so, calculate the comprehensive feature value of the waste to be processed in the video image data with qualified clarity, and determine the initial crushing parameters of the waste to be processed based on the comprehensive feature value and quality data.
[0127] S300: Collect the equipment status information of the kitchen waste processor, parse the equipment status information to obtain equipment status feature values, calculate the equipment deviation value based on the equipment status feature values, and determine whether to optimize the initial crushing parameters based on the equipment deviation value; if so, determine the optimization coefficient of the initial crushing parameters based on the equipment deviation value, and obtain the optimized crushing parameters.
[0128] S400: Collect the actual response time of the kitchen waste processor, and determine whether to compensate the optimized crushing parameters based on the actual response time; if so, calculate the difference between the actual response time and the standard response time, and record it as the response time difference; determine the compensation coefficient of the optimized crushing parameters based on the response time difference, and obtain the compensated crushing parameters.
[0129] S500: Receive the compensation crushing parameters and control the kitchen waste processor to perform waste processing operations according to the compensation crushing parameters.
[0130] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0131] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.
[0132] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0133] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A kitchen waste treatment system based on image recognition, characterized in that, include: The data acquisition module is configured to collect video image data and quality data of the waste to be processed inside the kitchen waste processor. The parameter determination module is configured to parse the video image data and determine whether there is garbage to be processed in the video image data based on the parsing results; If so, calculate the comprehensive feature value of the waste to be processed in the video image data with qualified clarity, and determine the initial crushing parameters of the waste to be processed based on the comprehensive feature value and quality data; The parameter optimization module is configured to collect the equipment status information of the kitchen waste processor, parse the equipment status information to obtain equipment status feature values, calculate the equipment deviation value based on the equipment status feature values, and determine whether to optimize the initial crushing parameters based on the equipment deviation value. If so, determine the optimization coefficient of the initial crushing parameters based on the equipment deviation value, and obtain the optimized crushing parameters; The parameter compensation module is configured to collect the actual response time of the kitchen waste processor, and determine whether to compensate the optimized crushing parameters based on the actual response time; if so, calculate the difference between the actual response time and the standard response time, and record it as the response time difference, determine the compensation coefficient of the optimized crushing parameters based on the response time difference, and obtain the compensated crushing parameters. The execution module is configured to receive the compensation pulverization parameters and control the kitchen waste processor to perform waste processing operations according to the compensation pulverization parameters; The parameter compensation module determines the compensation coefficient of the optimized crushing parameters based on the response time difference, and when obtaining the compensated crushing parameters, it includes: The response time difference is compared with historical data, and the compensation coefficient of the optimized crushing parameters is determined based on the comparison results. When there is a historical response time difference in the historical data that is the same as the response time difference, the historical compensation coefficient corresponding to the historical response time difference is used as the compensation coefficient of the optimized crushing parameter, and the product of the historical compensation coefficient and the optimized crushing parameter is used as the compensated crushing parameter. When there is no historical response time difference in the historical data that is the same as the response time difference, calculate the difference between the response time difference and the historical data one by one, and record it as the difference response time. Extract the minimum value of the difference response time and record it as the minimum difference response time. Determine the compensation coefficient of the optimized crushing parameters based on the minimum difference response time and obtain the compensation crushing parameters. The parameter compensation module determines the compensation coefficient of the optimized crushing parameters based on the minimum difference response time, and when obtaining the compensated crushing parameters, it includes: The minimum difference response time is compared with the first minimum difference response time and the second minimum difference response time, and the compensation coefficient of the optimized crushing parameter is determined based on the comparison result; wherein, the first minimum difference response time is less than the second minimum difference response time; When the minimum difference response time is less than or equal to the first minimum difference response time, the compensation coefficient is determined as the first compensation coefficient, and the product of the first compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter. When the minimum difference response time is greater than the first minimum difference response time and less than or equal to the second minimum difference response time, the compensation coefficient is determined to be the second compensation coefficient, and the product of the second compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter. When the minimum difference response time is greater than the second minimum difference response time, the compensation coefficient is determined to be the third compensation coefficient, and the product of the third compensation coefficient and the optimized crushing parameter is used as the compensation crushing parameter.
2. The food waste treatment system based on image recognition according to claim 1, characterized in that, When the parameter determination module determines whether there is unprocessed garbage in the video image data based on the parsing results, it includes: The video image data is processed using a target detection algorithm to identify garbage targets in the video image data and determine whether the garbage targets are garbage to be processed. When the target waste matches the preset target, the target waste is determined to be the waste to be processed. When the target waste does not match the preset target, it is determined that the target waste is not the waste to be processed.
3. The food waste treatment system based on image recognition according to claim 2, characterized in that, When the parameter determination module calculates the comprehensive feature value of the waste to be processed in the video image data with acceptable clarity, it includes: The video image data with acceptable clarity is preprocessed to extract the shape, color, and texture features of the waste to be processed; The shape features, color features, and texture features are fused using a feature fusion algorithm to obtain the comprehensive feature value of the waste to be processed.
4. The image recognition-based kitchen waste treatment system according to claim 3, characterized in that, When the parameter determination module determines the initial crushing parameters of the waste to be processed based on the comprehensive characteristic values and quality data, it includes: Feature extraction is performed on the quality data to obtain quality feature values; Based on the comprehensive characteristic value and the comprehensive characteristic threshold, the quality characteristic value is compared with the quality standard value, and the initial crushing parameters of the waste to be processed are determined based on the comparison result. When the comprehensive characteristic value is greater than or equal to the comprehensive characteristic threshold, and the quality characteristic value is greater than or equal to the quality standard value, the initial crushing parameter is determined to be the first crushing parameter; When the comprehensive characteristic value is greater than or equal to the comprehensive characteristic threshold, and the quality characteristic value is less than or equal to the quality standard value, the initial crushing parameter is determined to be the second crushing parameter; When the comprehensive characteristic value is less than the comprehensive characteristic threshold and the quality characteristic value is greater than or equal to the quality standard value, the initial crushing parameter is determined to be the third crushing parameter; When the comprehensive characteristic value is less than the comprehensive characteristic threshold and the quality characteristic value is less than the quality standard value, the initial crushing parameter is determined to be the fourth crushing parameter.
5. The food waste treatment system based on image recognition according to claim 4, characterized in that, The parameter optimization module calculates the equipment deviation value based on the equipment state characteristic value, and determines whether to optimize the initial crushing parameters based on the equipment deviation value, including: Obtain the standard value of the device state corresponding to each of the device state feature values; Calculate the number of device status characteristic values that are greater than the device status standard value, and record it as the first number; Calculate the number of device status characteristic values that are less than or equal to the device status standard value, and record them as the second quantity; The equipment deviation value is calculated based on the equipment status characteristic value, the equipment status standard value, the first quantity, and the second quantity. The equipment deviation value is compared with the equipment deviation threshold, and the initial crushing parameters are optimized based on the comparison result. When the deviation value of the equipment is less than the deviation threshold of the equipment, it is determined that the initial crushing parameters will not be optimized. When the deviation value of the equipment is greater than or equal to the deviation threshold of the equipment, it is determined that the initial crushing parameters should be optimized.
6. The image recognition-based kitchen waste treatment system according to claim 5, characterized in that, The parameter optimization module determines the optimization coefficient of the initial crushing parameters based on the equipment deviation value, and when obtaining the optimized crushing parameters, it includes: The equipment deviation value is compared with the first equipment deviation value and the second equipment deviation value, and the optimization coefficient of the initial crushing parameter is determined based on the comparison result; wherein the first equipment deviation value is less than the second equipment deviation value; An optimization coefficient range is defined, wherein the optimization coefficient range includes a first optimization coefficient, a second optimization coefficient, and a third optimization coefficient; When the deviation value of the equipment is less than or equal to the first deviation value of the equipment, the optimization coefficient is determined as the first optimization coefficient, and the product of the first optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter; When the deviation value of the equipment is greater than the first equipment deviation value and less than or equal to the second equipment deviation value, the optimization coefficient is determined as the second optimization coefficient, and the product of the second optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter; When the deviation value of the equipment is greater than the deviation value of the second equipment, the optimization coefficient is determined as the third optimization coefficient, and the product of the third optimization coefficient and the initial crushing parameter is used as the optimized crushing parameter.
7. The food waste treatment system based on image recognition according to claim 6, characterized in that, When the parameter compensation module determines whether to compensate the optimized crushing parameters based on the actual response time, it includes: The actual response time is compared with the standard response time, and the result of the comparison determines whether to compensate for the optimized crushing parameters. When the actual response time is greater than the standard response time, it is determined that the optimized crushing parameters should be compensated. When the actual response time is less than or equal to the standard response time, it is determined that no compensation will be made for the optimized crushing parameters.
8. A method for treating kitchen waste based on image recognition, applied to the kitchen waste treatment system based on image recognition as described in any one of claims 1-7, characterized in that, include: Collect video image data and quality data of the waste to be processed from inside the kitchen waste processor; The video image data is parsed, and the parsing results are used to determine whether there is any unprocessed garbage in the video image data; If so, calculate the comprehensive feature value of the waste to be processed in the video image data with qualified clarity, and determine the initial crushing parameters of the waste to be processed based on the comprehensive feature value and quality data; The equipment status information of the kitchen waste processor is collected, the equipment status information is parsed to obtain equipment status feature values, the equipment deviation value is calculated based on the equipment status feature values, and it is determined whether the initial crushing parameters should be optimized based on the equipment deviation value. If so, determine the optimization coefficient of the initial crushing parameters based on the equipment deviation value, and obtain the optimized crushing parameters; The actual response time of the kitchen waste processor is collected, and it is determined whether the optimized grinding parameters should be compensated based on the actual response time. If so, the difference between the actual response time and the standard response time is calculated and recorded as the response time difference. The compensation coefficient of the optimized grinding parameters is determined based on the response time difference, and the compensated grinding parameters are obtained. The device receives the compensation pulverization parameters and controls the food waste processor to perform waste processing operations based on the compensation pulverization parameters.
Citation Information
Patent Citations
Single-shaft shredding machine based on garbage classification and recovery and garbage identification method
CN117380374A
Real-time monitoring and optimizing method and system for resource utilization of construction waste
CN119443420A
Crushing method and system for kitchen garbage treatment equipment
CN119559571A
