Air conditioner purification unit filter assembly dust accumulation amount identification and replacement early warning system and method

Abstract

The invention discloses an air conditioner purification unit filter assembly dust accumulation amount recognition and replacement early warning system and method, and relates to the technical field of intelligent recognition and early warning. The system comprises an image acquisition module which at least comprises a 4K automatic focusing high-definition network camera, a high-resolution black and white camera and a CCD pinhole type high-definition network camera, and further comprises an image data transmission module, a data storage processing platform, a dust accumulation amount intelligent identification system, a dust accumulation data transmission module and an early warning control module. The early warning control module at least comprises three prompts in the early warning process, and the three prompts are short message notifications including display screen display alarm and indicator lamp alarm. On the basis of machine learning, the efficient, rapid and low-cost intelligent recognition method for the dust accumulation amount of the air conditioner filter assembly is established, the recognition efficiency of the dust accumulation amount of the air conditioner assembly is greatly improved, and the filter assembly replacement early warning system can set corresponding threshold values by itself so that early warning of the dust accumulation amount of different degrees can be conducted.

Description

Technical Field

[0001] The present invention relates to the field of intelligent identification and early warning technology, and in particular to a system and method for identifying the amount of dust accumulated in a filter assembly of an air-conditioning purification unit and providing an early warning for replacement. Background Art

[0002] At present, there is a system and method for intelligently identifying the amount of dust accumulated in the filter components of air conditioning purification units and replacing early warning systems.

[0003] It is mainly a real-time detection system for dust accumulation on the air conditioner filter, which includes the air conditioner indoor unit, outdoor unit, and filter dust accumulation detection control chip. By setting air, wind speed, temperature, humidity and usage time monitoring devices, multi-parameter detection can improve the accuracy of dust fullness detection results, and can provide users with a comfortable and safe air conditioner use experience. The heavy metal lead detector and the dust mite activity detector are both set on the air conditioner filter, and the air monitoring device includes a mounting plate, a vertical plate, a power supply component and an air monitor installed above the air conditioner outdoor unit. The air detector monitors the air quality parameters in the current installation environment of the air conditioner outdoor unit, and transmits the acquired air quality parameters back to the filter dust accumulation detection control chip. A wind speed monitoring device is provided on one side of the air conditioner indoor unit, and the wind speed sensor is used to monitor the average wind speed of the air conditioner indoor unit in the working state during the cycle time, and form a wind speed parameter to be transmitted back to the filter dust accumulation detection control chip. The air conditioning system operates in different environments, and the dust accumulation speed is different. Through various parameters, the various pollution levels (mild, moderate, and severe) of the filter dust can be accurately detected. The voice announcer on the air conditioner display screen will make announcements according to different pollution levels, reminding users to clean the filter in time.

[0004] The existing real-time detection system for dust accumulation on air conditioning filters has the disadvantages of limited detection accuracy, high cost, difficult maintenance, delayed data processing, low intelligence level, and poor environmental adaptability.

[0005] Therefore, a new solution to the above problems needs to be proposed. Summary of the invention

[0006] The purpose of the present invention is to provide an air conditioning purification unit filter component dust accumulation identification and replacement warning system and method to solve the technical problems raised in the background technology and achieve accurate, efficient and economical air conditioning filter component dust accumulation identification and replacement warning effect.

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an air-conditioning purification unit filter assembly dust accumulation amount identification and replacement warning system, including an image acquisition module, the image acquisition module at least includes a 4K auto-focus high-definition network camera, a high-resolution black and white camera and a CCD pinhole high-definition network camera, and also includes an image data transmission module, a data storage processing platform, a dust accumulation amount intelligent identification system, a dust accumulation data transmission module and a warning control module, the warning control module includes at least three prompts in the warning process, the three prompts are SMS notification alarm, display screen display alarm and indicator light alarm;

[0008] The image acquisition module transmits the acquired image to the data storage processing platform through the image data transmission module, and the dust accumulation intelligent recognition system in the data storage processing platform performs intelligent recognition of the dust accumulation, and transmits the specific recognition data to the early warning control module, and performs alarm processing according to whether the alarm threshold is reached.

[0009] The method for identifying the amount of dust accumulated in the filter assembly of an air conditioning purification unit and for early warning of replacement includes at least the following steps:

[0010] S1: Based on experiments or related methods, image information of dust accumulation on the filter component and morphological feature information of dust accumulation on the filter component are obtained, and the information is combined and processed to establish a typical feature database of dust accumulation on the air conditioner filter component;

[0011] S2: by introducing integrated machine vision and learning algorithms, a basic image recognition model is established, the parameters of the basic image recognition model are set according to the device configuration and the image size, and the basic image recognition model is used to process the image information of the air conditioning filter component, and the image information at least includes preliminary recognition and classification of the amount and shape of dust accumulation in the image;

[0012] S3: The processed morphological feature information and image information of the dust accumulation on the filter component are input into the basic image recognition model for targeted training, so as to form a basic automatic recognition model of dust accumulation on the filter component that can accurately recognize images in the typical feature database of dust accumulation on the filter component, and has a certain recognition ability for new images. The basic automatic recognition model of dust accumulation on the filter component is used to perform image recognition tasks and generate recognition results;

[0013] S4: Building a filter component dust accumulation automatic recognition model, and when the training results of the filter component dust accumulation automatic recognition basic model and the machine vision learning algorithm reach a sufficient confidence level, obtaining a filter component dust accumulation amount image to be processed and inputting it into the filter component dust accumulation automatic recognition model for recognition, and obtaining a filter component dust accumulation amount image recognition result to be processed;

[0014] S5: While obtaining the results, randomly select the identification results for verification analysis to eliminate the influence of uncertain factors, improve the accuracy of the automatic identification results of component dust accumulation, verify the reliability of the model, and complete the iteration;

[0015] S6: The automatic identification model for dust accumulation in the filter component is combined with a deep learning algorithm convolutional neural network to model the changing characteristics of dust accumulation pollution in the component; a random forest ensemble learning method is used to construct a component dust pollution risk prediction model to further improve the accuracy and stability of the automatic identification model for dust accumulation in the filter component;

[0016] S7: An intelligent replacement warning system is built based on the component dust pollution risk prediction model and warning control module to monitor and analyze the component dust pollution risk in real time. When the dust pollution condition of the air-conditioning system components reaches a certain threshold, an early warning is issued through indicator lights or SMS notifications to remind users that they should take measures to clean the air-conditioning filter components.

[0017] Furthermore, in said S4, the image to be processed is obtained and input into the filter component dust accumulation automatic recognition model for basic recognition model training before recognition, that is, before the image to be processed is input into the established filter component dust accumulation automatic recognition model, it is ensured that the model has the ability to correctly extract, understand and recognize dust accumulation related features from the image;

[0018] The basic recognition model training includes at least the following steps:

[0019] Acquire image information of dust accumulation of filter components and combine to form training of dust accumulation of filter components;

[0020] Classifying the morphological features of the dust accumulation of the filter components in the training images to obtain multiple groups of training images of the dust accumulation of the filter components;

[0021] Based on the morphological features of the dust accumulation of the filter components in the training images, the basic image recognition model is trained in a targeted manner to form an automatic recognition system for the dust accumulation of the filter components;

[0022] Based on the method for constructing a typical feature database of dust accumulation of a filter component, the dust accumulation range and morphological features of the filter component are associated with the image in the form of electronic tags to form a training image of dust accumulation of the filter component;

[0023] The dust accumulation amount of the filter component is divided into a training set, a test set and a validation set in a ratio of 5:4:1, which is used for automatic identification model training of the dust accumulation amount of the filter component.

[0024] Furthermore, the construction of the filter component dust accumulation automatic identification model includes at least the following steps:

[0025] Based on the Backbone network structure in the machine vision learning algorithm, the dust accumulation image of the filter component is cut, the Neck network structure extracts and fuses the features of the dust accumulation image of the filter component, and the Predicton network structure predicts and outputs the dust accumulation image of the filter component.

[0026] The introduction of the basic training model that needs to be pre-configured for the machine vision learning algorithm, the pre-configuration at least includes the preset model selection, test data type, prediction result saving path, input image size, confidence threshold and result display settings;

[0027] The test was conducted. The data type of the test was picture. According to the computer parameter settings, the input picture resolution was 640×640, and the confidence threshold was 0.80 by default.

[0028] The number of training rounds is set to 200, and the pre-configured basic training model is trained to ensure that the training results reach a sufficient confidence level, thereby forming a reliable automatic identification model for the dust accumulation of the filter component.

[0029] Furthermore, using a machine vision learning algorithm to construct a filter component dust automatic recognition model includes at least the following steps:

[0030] Use labelme to create labels for the training images of dust accumulation of the filter components to form a json file, and then convert the json file to a txt file;

[0031] The basic training model is trained on the json file and the txt file through train to form an automatic recognition model for the dust accumulation of the filter component, and the dust accumulation recognition of the filter component is realized through detect.

[0032] Furthermore, after the automatic recognition model of dust accumulation amount of the filter component is constructed by using the machine vision learning algorithm, it is necessary to obtain the dust accumulation amount image of the filter component to be processed, and the method for obtaining the dust accumulation amount image of the filter component to be processed includes at least the following steps:

[0033] Using an image acquisition module to record an image of dust accumulation on a filter component;

[0034] The size of the filter component dust accumulation image is adjusted to the resolution of the input image to form a filter component dust accumulation image to be processed for recognition by the filter component dust accumulation automatic recognition model.

[0035] Furthermore, the recognition result of the image to be processed includes a picture result with confidence information, and an EXCEL table result with a dust accumulation range of the filter component and morphological feature information.

[0036] Furthermore, randomly selecting recognition results for verification analysis while obtaining the results at least includes the following steps:

[0037] The dust accumulation of the filter components was analyzed by optical microscopy;

[0038] Comparing the optical microscope analysis result with the recognition result of the image to be processed

[0039] Verify the reliability of the automatic recognition model and improve the model;

[0040] The model was improved and added to the database of typical characteristics of dust accumulation in filter components.

[0041] Furthermore, the size of the input image of the machine vision learning algorithm refers to the computer configuration parameters to improve the basic model training speed and the recognition speed of the automatic recognition model of the dust accumulation of the filtering component.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention is based on machine learning to establish an efficient, fast and low-cost method for intelligently identifying the amount of dust accumulated in air-conditioning filter components, which greatly improves the efficiency of identifying the amount of dust accumulated in air-conditioning components. The filter component replacement warning system can set corresponding thresholds by itself, thereby issuing warnings for different degrees of dust accumulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0045] Figure 1 This is a basic flow chart of intelligent identification of dust accumulation in a filter unit based on machine vision learning of the present invention;

[0046] Figure 2 This is a schematic diagram of the intelligent identification process of dust accumulation in the filter assembly of the present invention;

[0047] Figure 3 It is a schematic diagram of the risk prediction process of dust accumulation amount of the filter assembly of the present invention;

[0048] Figure 4 A schematic diagram of the dust accumulation amount replacement warning process of the filter assembly of the present invention;

[0049] Figure 5 Schematic diagram of the hardware system of the present invention. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0051] Embodiment 1:

[0052] See also Figure 5 , an air conditioning purification unit filter component dust accumulation identification and replacement warning system and method, including.

[0053] The dust accumulation amount identification and replacement warning system of the filter assembly of the air-conditioning purification unit includes an image acquisition module, which includes at least a 4K auto-focus high-definition network camera, a high-resolution black-and-white camera, and a CCD pinhole high-definition network camera, and also includes an image data transmission module, a data storage processing platform, an intelligent dust accumulation amount identification system, a dust accumulation data transmission module, and a warning control module. The warning control module includes at least three prompts during the warning process, and the three prompts are SMS notification alarm, display screen display alarm, and indicator light alarm;

[0054] The image acquisition module transmits the collected images to the data storage and processing platform through the image data transmission module, and the dust accumulation intelligent identification system in the data storage and processing platform performs intelligent identification of the dust accumulation, and transmits the specific identification data to the early warning control module, and performs alarm processing according to whether the alarm threshold is reached.

[0055] Embodiment 2:

[0056] Based on the above-mentioned embodiment 1, a method for identifying the amount of dust accumulated in the filter assembly of an air conditioning purification unit and an early warning method for replacement is further proposed;

[0057] See also Figure 1 - Figure 4 The method for identifying the dust accumulation amount of the filter component of the air conditioning purification unit and the early warning method for replacement at least comprises the following steps:

[0058] S1: Based on experiments or related methods, image information of dust accumulation on the filter component and morphological feature information of dust accumulation on the filter component are obtained, and the information is combined and processed to establish a typical feature database of dust accumulation on the air conditioner filter component;

[0059] S2: By introducing integrated machine vision and learning algorithms, a basic image recognition model is established. The parameters of the basic image recognition model are set according to the device configuration and the image size. The basic image recognition model is used to process the image information of the air conditioning filter component. The image information at least includes preliminary recognition and classification of the amount and shape of dust accumulation in the image;

[0060] S3: The processed morphological feature information and image information of the dust accumulation on the filter component are input into the basic image recognition model for targeted training, so as to form a basic automatic recognition model of dust accumulation on the filter component that can accurately recognize images in the typical feature database of dust accumulation on the filter component, and has a certain recognition ability for new images. The basic automatic recognition model of dust accumulation on the filter component is used to perform image recognition tasks and generate recognition results;

[0061] S4: Building a filter component dust accumulation automatic recognition model, and when the training results of the filter component dust accumulation automatic recognition basic model and the machine vision learning algorithm reach a sufficient confidence level, obtaining a filter component dust accumulation amount image to be processed and inputting it into the filter component dust accumulation automatic recognition model for recognition, and obtaining a filter component dust accumulation amount image recognition result to be processed;

[0062] In S4, the image to be processed is obtained and input into the filter component dust accumulation automatic recognition model for basic recognition model training before recognition, that is, before the image to be processed is input into the established filter component dust accumulation automatic recognition model, it is ensured that the model has the ability to correctly extract, understand and recognize dust accumulation related features from the image;

[0063] Basic recognition model training includes at least the following steps:

[0064] Acquire image information of dust accumulation of filter components and combine to form training of dust accumulation of filter components;

[0065] Classifying the morphological features of the dust accumulation amount of the filter components in the training images to obtain multiple groups of training images of the dust accumulation amount of the filter components;

[0066] Based on the morphological features of the dust accumulation of the filter components in the training images, the basic image recognition model is trained in a targeted manner to form an automatic recognition system for the dust accumulation of the filter components;

[0067] Based on the typical feature database construction method of filter component dust accumulation, the dust accumulation range and morphological features of the filter component are associated with the image in the form of electronic tags to form a training image of the dust accumulation of the filter component;

[0068] The dust accumulation of the filter components is divided into training set, test set and validation set in a ratio of 5:4:1, which is used for the training of the automatic recognition model of the dust accumulation of the filter components.

[0069] Building a filter component dust accumulation automatic recognition model includes at least the following steps:

[0070] Based on the Backbone network structure in the machine vision learning algorithm, the dust accumulation image of the filter component is cut, the Neck network structure extracts and fuses the features of the dust accumulation image of the filter component, and the Predicton network structure predicts and outputs the dust accumulation image of the filter component.

[0071] The basic training model that needs to be pre-configured when introducing the machine vision learning algorithm includes at least the preset model selection, test data type, prediction result save path, input image size, confidence threshold, and result display settings;

[0072] The test data type is picture. According to the computer parameter settings, the input picture resolution is 640×640, and the confidence threshold is 0.80 by default.

[0073] The number of training rounds is set to 200, and the pre-configured basic training model is trained to ensure that the training results reach a sufficient confidence level, thereby forming a reliable automatic identification model for the dust accumulation of the filter component.

[0074] The construction of a filter component dust automatic recognition model using a machine vision learning algorithm includes at least the following steps:

[0075] Use labelme to create labels for the training images of dust accumulation of the filter components to form a json file, and then convert the json file to a txt file;

[0076] The basic training model is trained by training json files and txt files to form an automatic recognition model for the dust accumulation of the filter component, and the recognition of the dust accumulation of the filter component is realized through detect.

[0077] The model used by the machine vision learning algorithm and the size of the input image are all based on the computer configuration parameters to improve the basic model training speed and the automatic recognition model recognition speed of the filter component dust accumulation.

[0078] After the automatic recognition model of dust accumulation amount of the filter component is constructed by using the machine vision learning algorithm, it is necessary to obtain the dust accumulation amount image of the filter component to be processed. The method for obtaining the dust accumulation amount image of the filter component to be processed includes at least the following steps:

[0079] Using an image acquisition module to record an image of dust accumulation on a filter component;

[0080] The size of the filter component dust accumulation image is adjusted to the resolution of the input image to form a filter component dust accumulation image to be processed for recognition by the filter component dust accumulation automatic recognition model.

[0081] The recognition results of the image to be processed include picture results with confidence information, EXCEL table results with the dust accumulation range of the filter component and morphological feature information.

[0082] S5: While obtaining the results, randomly select the identification results for verification analysis to eliminate the influence of uncertain factors, improve the accuracy of the automatic identification results of component dust accumulation, verify the reliability of the model, and complete the iteration;

[0083] While obtaining the results, randomly selecting the recognition results for verification analysis includes at least the following steps:

[0084] The dust accumulation of the filter components was analyzed by optical microscopy;

[0085] Comparison of optical microscope analysis results with recognition results of the image to be processed

[0086] Verify the reliability of the automatic recognition model and improve the model;

[0087] The model was improved and added to the database of typical characteristics of dust accumulation in filter components.

[0088] S6: The automatic dust recognition model for filter components is combined with the deep learning algorithm convolutional neural network to model the changing characteristics of component dust pollution; the random forest ensemble learning method is used to build a component dust pollution risk prediction model to further improve the accuracy and stability of the automatic dust recognition model for filter components;

[0089] S7: An intelligent replacement warning system is built based on the component dust pollution risk prediction model and warning control module to monitor and analyze the component dust pollution risk in real time. When the dust pollution condition of the air-conditioning system components reaches a certain threshold, an early warning is issued through indicator lights or SMS notifications to remind users that they should take measures to clean the air-conditioning filter components.

[0090] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. The dust accumulation identification and replacement warning system for the filter components of the air conditioning purification unit is characterized by: It includes an image acquisition module, which includes at least a 4K auto-focus high-definition network camera, a high-resolution black and white camera, and a CCD pinhole high-definition network camera, and also includes an image data transmission module, a data storage processing platform, an intelligent dust accumulation identification system, a dust accumulation data transmission module, and an early warning control module. The early warning control module includes at least three prompts during the early warning process, and the three prompts are SMS notification alarm, display screen alarm, and indicator light alarm; The image acquisition module transmits the acquired image to the data storage processing platform through the image data transmission module, and the dust accumulation intelligent recognition system in the data storage processing platform performs intelligent recognition of the dust accumulation, and transmits the specific recognition data to the early warning control module, and performs alarm processing according to whether the alarm threshold is reached.

2. A method for identifying the amount of dust accumulated in a filter assembly of an air conditioning purification unit and providing an early warning for replacement, which is used in the system for identifying the amount of dust accumulated in a filter assembly of an air conditioning purification unit as claimed in claim 1, and is characterized in that: At least the following steps are included: S1: Based on experiments or related methods, image information of dust accumulation on the filter component and morphological feature information of dust accumulation on the filter component are obtained, and the information is combined and processed to establish a typical feature database of dust accumulation on the air conditioner filter component; S2: by introducing integrated machine vision and learning algorithms, a basic image recognition model is established, the parameters of the basic image recognition model are set according to the device configuration and the image size, and the basic image recognition model is used to process the image information of the air conditioning filter component, and the image information at least includes preliminary recognition and classification of the amount and shape of dust accumulation in the image; S3: The processed morphological feature information and image information of the dust accumulation on the filter component are input into the basic image recognition model for targeted training, so as to form a basic automatic recognition model of dust accumulation on the filter component that can accurately recognize images in the typical feature database of dust accumulation on the filter component, and has a certain recognition ability for new images. The basic automatic recognition model of dust accumulation on the filter component is used to perform image recognition tasks and generate recognition results; S4: Building a filter component dust accumulation automatic recognition model, and when the training results of the filter component dust accumulation automatic recognition basic model and the machine vision learning algorithm reach a sufficient confidence level, obtaining a filter component dust accumulation amount image to be processed and inputting it into the filter component dust accumulation automatic recognition model for recognition, and obtaining a filter component dust accumulation amount image recognition result to be processed; S5: While obtaining the results, randomly select the identification results for verification analysis to eliminate the influence of uncertain factors, improve the accuracy of the automatic identification results of component dust accumulation, verify the reliability of the model, and complete the iteration; S6: The automatic identification model for dust accumulation in the filter component is combined with a deep learning algorithm convolutional neural network to model the changing characteristics of dust accumulation pollution in the component; Use the random forest ensemble learning method to build a component dust pollution risk prediction model to further improve the accuracy and stability of the automatic dust recognition model for filter components; S7: An intelligent replacement warning system is built based on the component dust pollution risk prediction model and warning control module to monitor and analyze the component dust pollution risk in real time. When the dust pollution condition of the air-conditioning system components reaches a certain threshold, an early warning is issued through indicator lights or SMS notifications to remind users that they should take measures to clean the air-conditioning filter components.

3. The method for identifying dust accumulation in filter components of an air conditioning purification unit and for early warning of replacement according to claim 2, characterized in that: In said S4, the image to be processed is obtained and input into the filter component dust accumulation automatic recognition model for basic recognition model training before recognition, that is, before the image to be processed is input into the established filter component dust accumulation automatic recognition model, it is ensured that the model has the ability to correctly extract, understand and recognize dust accumulation related features from the image; The basic recognition model training includes at least the following steps: Acquire image information of dust accumulation of filter components and combine to form training of dust accumulation of filter components; Classifying the morphological features of the dust accumulation of the filter components in the training images to obtain multiple groups of training images of the dust accumulation of the filter components; Based on the morphological features of the dust accumulation of the filter components in the training images, the basic image recognition model is trained in a targeted manner to form an automatic recognition system for the dust accumulation of the filter components; Based on the method for constructing a typical feature database of dust accumulation of a filter component, the dust accumulation range and morphological features of the filter component are associated with the image in the form of electronic tags to form a training image of dust accumulation of the filter component; The dust accumulation amount of the filter component is divided into a training set, a test set and a validation set in a ratio of 5:4:1, which is used for automatic identification model training of the dust accumulation amount of the filter component.

4. The method for identifying dust accumulation in filter components of an air conditioning purification unit and providing early warning for replacement according to claim 2, characterized in that: The construction of the automatic identification model for dust accumulation in the filter assembly comprises at least the following steps: Based on the Backbone network structure in the machine vision learning algorithm, the dust accumulation image of the filter component is cut, the Neck network structure extracts and fuses the features of the dust accumulation image of the filter component, and the Predicton network structure predicts and outputs the dust accumulation image of the filter component. The introduction of the basic training model that needs to be pre-configured for the machine vision learning algorithm, the pre-configuration at least includes the preset model selection, test data type, prediction result saving path, input image size, confidence threshold and result display settings; The test was conducted. The data type of the test was picture. According to the computer parameter settings, the input picture resolution was 640×640, and the confidence threshold was 0.80 by default. The number of training rounds is set to 200, and the pre-configured basic training model is trained to ensure that the training results reach a sufficient confidence level, thereby forming a reliable automatic identification model for the dust accumulation of the filter component.

5. The method for identifying dust accumulation and replacing early warning of filter components of an air conditioning purification unit according to claim 4, characterized in that: The construction of a filter component dust automatic recognition model using a machine vision learning algorithm includes at least the following steps: Use labelme to create labels for the training images of dust accumulation of the filter components to form a json file, and then convert the json file to a txt file; The basic training model is trained on the json file and the txt file through train to form an automatic recognition model for the dust accumulation of the filter component, and the dust accumulation recognition of the filter component is realized through detect.

6. The method for identifying dust accumulation in filter components of an air conditioning purification unit and providing early warning for replacement according to claim 5, characterized in that: After the automatic recognition model of dust accumulation amount of the filter component is constructed by using the machine vision learning algorithm, it is necessary to obtain the dust accumulation amount image of the filter component to be processed. The method for obtaining the dust accumulation amount image of the filter component to be processed includes at least the following steps: Using an image acquisition module to record an image of dust accumulation on a filter component; The size of the filter component dust accumulation image is adjusted to the resolution of the input image to form a filter component dust accumulation image to be processed for recognition by the filter component dust accumulation automatic recognition model.

7. The method for identifying dust accumulation in filter components of an air conditioning purification unit and providing early warning for replacement according to claim 2, characterized in that: The recognition result of the image to be processed includes a picture result with confidence information, and an EXCEL table result with the dust accumulation range of the filter component and morphological feature information.

8. The system and method for identifying dust accumulation and replacing early warning of filter components of an air conditioning purification unit according to claim 2, characterized in that: The step of randomly selecting the recognition results for verification analysis while obtaining the results includes at least the following steps: The dust accumulation of the filter components was analyzed by optical microscopy; Comparing the optical microscope analysis result with the recognition result of the image to be processed Verify the reliability of the automatic recognition model and improve the model; The model was improved and added to the database of typical characteristics of dust accumulation in filter components.

9. The method for identifying dust accumulation in filter components of an air conditioning purification unit and providing early warning for replacement according to claim 6, characterized in that: The size of the image input to the machine vision learning algorithm refers to the computer configuration parameters to improve the basic model training speed and the automatic recognition model recognition speed of the dust accumulation of the filtering component.

Images