Frost detection method, apparatus, device, and storage medium

Abstract

The application provides a frost detection method, device, equipment and storage medium. The frost detection method comprises the following steps: in response to a frost detection request for a target evaporator, driving an image acquisition module to acquire an image of the target evaporator to obtain a target detection image of the target evaporator; identifying frost of the target evaporator according to the target detection image and an image calibration ratio to obtain a frost detection parameter, wherein the image calibration ratio is a conversion ratio obtained by calibrating a target calibration plate provided in a chamber of the target evaporator with known calibration size data; and when the frost detection parameter meets a target defrosting condition, defrosting treatment is performed on the target evaporator. The method directly obtains a frost detection parameter representing a frost state in multiple dimensions during operation of the target evaporator, improves the frost evaluation accuracy in the frost measurement process, effectively reduces the frost measurement cost, and provides reliable data support for defrosting control of the refrigeration equipment.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a method, apparatus, device, and storage medium for detecting frost. Background Technology

[0002] Currently, with the rapid development of refrigeration technology, more and more users are using refrigeration equipment such as refrigerators, freezers, cold storage, and air conditioners for cooling operations. During the operation of these refrigeration devices, the evaporator surface gradually frosts due to the condensation of moisture in the air. The accumulation of frost increases heat exchange resistance, reduces refrigeration efficiency, increases energy consumption, and may even cause air duct blockage. To ensure refrigeration performance, refrigeration equipment needs to be defrosted periodically. However, existing frost detection methods can only indirectly reflect the degree of frost on the evaporator and cannot effectively obtain accurate data on the frost status. This low accuracy in frost detection affects subsequent defrosting decisions, thus impacting the refrigeration performance of the equipment. Summary of the Invention

[0003] This application provides a method, apparatus, device, and storage medium for frost detection, aiming to solve the technical problem of low frost detection accuracy in existing refrigeration equipment.

[0004] On one hand, embodiments of this application provide a frosting detection method, which includes the following steps: In response to a frost detection request for the target evaporator, the image acquisition module is driven to acquire an image of the target evaporator to obtain a target detection image of the target evaporator. Frost recognition is performed based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator. The image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with known calibration size data set in the target evaporator room. When the frost detection parameters meet the target defrosting conditions, the target evaporator is defrosted.

[0005] In one possible implementation of this application, before performing frost recognition based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator, the method further includes: The calibration image data of the target evaporator is acquired using the image acquisition module and the target calibration plate; The image calibration ratio corresponding to the target evaporator is determined based on the calibration size data and calibration image data of the target calibration plate; The image acquisition module and the target calibration plate are located in the target evaporator chamber, with the target calibration plate situated within the shooting range of the image acquisition module and forming an angle with the image acquisition module.

[0006] In one possible implementation of this application, determining the image calibration ratio corresponding to the target evaporator based on the calibration size data and calibration image data of the target calibration plate includes: Obtain the calibration pixels in the calibration image data, and calculate the calibration pixel distance between any of the calibration pixels; Obtain the calibration size data corresponding to the calibration pixel, calculate the ratio between the calibration size data and the calibration pixel distance, and obtain the image calibration ratio corresponding to the target evaporator.

[0007] In one possible implementation of this application, the step of performing frost recognition based on the target detection image and the image calibration ratio to obtain frost detection parameters of the target evaporator includes: The target detection image is segmented using an image segmentation model to determine the frosting region mask in the target detection image; The ratio between the number of frost pixels in the frost area mask and the total number of pixels in the target evaporator is calculated to obtain the frost coverage rate of the target evaporator. The frost thickness data of the target evaporator is determined based on the edge position information of the target evaporator and the image calibration ratio. The frost detection parameters of the target evaporator are determined based on the frost coverage rate and the frost thickness data.

[0008] In one possible implementation of this application, determining the frost thickness data of the target evaporator based on the edge position information of the target evaporator and the image calibration ratio includes: Edge detection is performed on the target detection image and / or calibration image data using an edge detection model to determine the edge position information of the target evaporator, wherein the edge position information is the fin edge position information of the evaporation fins in the target evaporator; The target frost layer region in the frost area mask is determined based on the edge location information and the frost area mask. The frost thickness data of the target evaporator is determined based on the frost edge pixels of the target frost region, the edge position information, and the image calibration ratio.

[0009] In one possible implementation of this application, determining the frost detection parameters of the target evaporator based on the frost coverage rate and the frost thickness data includes: The frost coverage rate is weighted using a first weighting coefficient to obtain a weighted coverage rate; the frost thickness data is weighted using a second weighting coefficient to obtain weighted thickness data. The sum of the weighted coverage rate and the weighted thickness data is calculated to obtain the comprehensive frosting index of the target evaporator; The difference between the comprehensive frost index and the historical frost index is calculated to obtain the frost rate data of the target evaporator; The comprehensive frost index and the frost rate data are determined as the frost detection parameters for the target evaporator.

[0010] In one possible implementation of this application, the step of defrosting the target evaporator when the frosting detection parameters meet the target defrosting conditions includes: Obtain the first defrost condition and / or the second defrost condition from the target defrost conditions; When the comprehensive frost index in the frost detection parameters meets the first defrosting condition, the target evaporator is defrosted. And / or, when the frost rate data in the frost detection parameters meets the second defrosting condition, the target evaporator is defrosted.

[0011] On the other hand, this application provides a frosting detection device, the frosting detection device comprising: The image acquisition module is configured to respond to a frosting detection request for the target evaporator, drive the image acquisition module to acquire images of the target evaporator, and obtain a target detection image of the target evaporator. The frost detection module is configured to identify frost based on the target detection image and the image calibration ratio to obtain frost detection parameters of the target evaporator. The frost detection module is configured to perform defrosting treatment on the target evaporator when the frost detection parameters meet the target defrosting conditions.

[0012] On the other hand, this application also provides a frosting detection device, the frosting detection device comprising: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the frosting detection method.

[0013] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the frosting detection method.

[0014] In this application, in response to a frost detection request for a target evaporator, an image acquisition module is driven to acquire an image of the target evaporator to obtain a target detection image of the target evaporator; frost recognition is performed based on the target detection image and the image calibration ratio to obtain frost detection parameters of the target evaporator, wherein the image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with calibrated size data set in the target evaporator chamber; when the frost detection parameters meet the target defrosting conditions, defrosting processing is performed on the target evaporator. This invention implements an image acquisition module and a target calibration board installed in the target evaporator chamber of a refrigeration system. When a frost detection request is met, the image acquisition module is driven to acquire target detection images of the target evaporator during operation. After determining the image calibration ratio using the target calibration board, frost identification is performed on the target evaporator using the target detection images and the image calibration ratio. This determines frost detection parameters that characterize the frost state of the target evaporator from multiple dimensions. Adaptive defrosting processing is then performed using these frost detection parameters and target defrosting conditions. This allows for the direct acquisition of frost detection parameters that characterize the frost state of the target evaporator during operation, improving the accuracy of frost assessment during frost measurement, effectively reducing frost measurement costs, and providing reliable data support for defrosting control of refrigeration equipment. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram illustrating a scenario of the frost detection method according to an embodiment of this application; Figure 2 This is a flowchart illustrating one embodiment of the frosting detection method in this application. Figure 3a A top view of a scenario in an embodiment of the evaporator compartment in the frosting detection method provided in this application; Figure 3b This is a front view of a scene in an embodiment of the evaporator compartment in the frosting detection method provided in this application. Figure 4 This is a flowchart illustrating an embodiment of the frosting detection method for determining the frosting detection parameters of a target evaporator provided in this application. Figure 5 A schematic diagram of one embodiment of the frosting detection device provided in this application; Figure 6This is a schematic diagram of one embodiment of the frost detection device provided in this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0019] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0020] Currently, with the rapid development of refrigeration technology, more and more users are using refrigeration equipment such as refrigerators, freezers, cold storage, and air conditioners for cooling operations. During the operation of these refrigeration devices, the evaporator surface gradually frosts due to the condensation of moisture in the air. The accumulation of frost increases heat exchange resistance, reduces refrigeration efficiency, increases energy consumption, and may even cause air duct blockage. To ensure refrigeration performance, refrigeration equipment needs to be defrosted periodically. However, existing frost detection methods can only indirectly reflect the degree of frost on the evaporator and cannot effectively obtain accurate data on the frost status. This low accuracy in frost detection affects subsequent defrosting decisions, thus impacting the refrigeration performance of the equipment.

[0021] Based on this, this application proposes a frosting detection method, apparatus, device, and computer-readable storage medium to solve the technical problem of low frosting detection accuracy in existing refrigeration equipment.

[0022] The frost detection method in this embodiment of the invention is applied to a frost detection device, which is provided in a frost detection equipment. The frost detection equipment is provided with one or more processors, a memory, and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the frost detection method; wherein, the frost detection equipment can be any refrigeration equipment, such as a refrigerator, freezer, or air conditioner.

[0023] like Figure 1 As shown, Figure 1 This is a schematic diagram of a scenario for the frost detection method according to an embodiment of this application. The frost detection scenario in this embodiment includes a frost detection device 100 (the frost detection device 100 integrates a frost detection apparatus), and the frost detection device 100 is equipped with a computer-readable storage medium corresponding to the frost detection method to execute the steps of the frost detection method.

[0024] Understandable Figure 1 The frosting detection device in the frosting detection method scenario shown, or the device included in the frosting detection device, does not constitute a limitation on the embodiments of the present invention. That is, the number or type of frosting detection device included in the frosting detection method scenario, or the number or type of device included in each device, does not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of the present invention.

[0025] In this embodiment of the invention, the frosting detection device 100 is mainly used to: respond to a frosting detection request for a target evaporator, drive the image acquisition module to acquire an image of the target evaporator, and obtain a target detection image of the target evaporator; Frost recognition is performed based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator. The image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with known calibration size data set in the target evaporator room. When the frost detection parameters meet the target defrosting conditions, the target evaporator is defrosted.

[0026] This application provides a method, apparatus, device, and computer-readable storage medium for detecting frost, which will be described in detail below.

[0027] It will be understood by those skilled in the art that Figure 1 The application environment shown is only one application scenario related to the solution of this application and does not constitute a limitation on the application scenario of this application. Other application environments may include more than one application scenario. Figure 1 The number of more or fewer frost detection devices shown, or the frost detection network connections, for example Figure 1 Only one frost detection device is shown in the figure. It is understood that the scenario of this frost detection method may also include one or more frost detection devices, which are not limited here. The frost detection device 100 may also include a memory for storing target detection images, image calibration ratios, frost detection parameters and other data.

[0028] It should be noted that, Figure 1 The schematic diagram of the frost detection method shown is merely an example. The scenario of the frost detection method described in this embodiment of the invention is intended to more clearly illustrate the technical solution of this embodiment and does not constitute a limitation on the technical solution provided by this embodiment of the invention.

[0029] Based on the scenarios described above for frost detection methods, various embodiments of the frost detection method disclosed in this invention are proposed.

[0030] like Figure 2 As shown, Figure 2 This is a flowchart illustrating one embodiment of the frosting detection method in this application. The frosting detection method includes the following steps 201 to 203: 201. In response to the frost detection request for the target evaporator, drive the image acquisition module to acquire an image of the target evaporator and obtain a target detection image of the target evaporator; The frost detection method in this embodiment is applied to a frost detection device. The type and number of frost detection devices are not specifically limited. That is, the frost detection device can be one or more refrigeration devices that use an evaporator to achieve the refrigeration function. For example, in a specific embodiment, the frost detection device is a refrigeration device such as a refrigerator, freezer, or air conditioner, or a smart control terminal that is connected to the device for control.

[0031] Optionally, the target evaporator is a heat exchange device installed in the evaporator chamber of a frosting detection device or a designated refrigeration device, which absorbs heat to evaporate the liquid and achieve a cooling effect. Optionally, in one specific embodiment, the target evaporator is a finned evaporator. Optionally, in other embodiments, the target evaporator may also be other types of evaporator modules. This embodiment is not specifically limited here.

[0032] The surface of the target evaporator will gradually accumulate frost due to the condensation of moisture in the air. The frost layer will increase the heat exchange resistance, reduce the refrigeration efficiency, increase energy consumption, and cause air duct blockage. Therefore, during operation, the frost detection equipment will also respond to the frost detection request for the target evaporator. Through the frost detection request, the equipment will perform frost detection and defrosting control on the target evaporator to achieve a comprehensive assessment of the degree of frost on the target evaporator, thereby providing reliable data support for the defrosting control of the refrigeration equipment.

[0033] Optionally, the frost detection request is an operational request that drives the frost detection device to identify the frost status of the target evaporator through the image acquisition module and target calibration board to assess the degree of frost on the target evaporator. This frost detection request can be triggered actively by the user, for example, by clicking the frost control button on the frost detection device or the corresponding refrigeration equipment. Alternatively, the frost detection request can be automatically triggered by the frost detection device, for example, by automatically triggering the frost detection request when frost detection conditions are met. The frost detection conditions are the evaluation conditions for determining whether to perform frost detection on the target evaporator. In a specific embodiment, the frost detection conditions are an interval time greater than or equal to a preset interval threshold (e.g., 10 minutes) and / or the compressor of the refrigeration equipment being in a stopped state.

[0034] Optionally, the image acquisition module is a camera component fixedly installed at a preset position in the corresponding evaporator compartment of the target evaporator, used to acquire images of the target evaporator and the target calibration plate. Optionally, in one specific embodiment, the image acquisition module can be any camera component with low-temperature resistance, anti-condensation, and waterproof design. For example, the image acquisition module can be any one or more of a visible light camera, an infrared camera, and a multispectral camera.

[0035] Optionally, the preset position can be any location directly opposite the target evaporator, diagonally above the target evaporator, or to the side of the target evaporator. For example... Figure 3a As shown, Figure 3a A top view of a scenario in an embodiment of the evaporator compartment in the frosting detection method provided in this application; Figure 3bThis is a front view of a scene in an embodiment of the evaporator compartment in the frosting detection method provided in this application. Figure 3a and Figure 3b In the embodiment shown, the evaporator chamber is equipped with an image acquisition module and a light source module that can cover the entire frosting evaporation area, as well as a target calibration plate for calibration.

[0036] Optionally, the target calibration plate is a calibration plate with known color and size, located near the target evaporator, used to determine the corresponding image calibration ratio for pixel ratio conversion. Optionally, in one specific embodiment, the target calibration plate is designed to maintain a frost-free surface through methods such as an anti-frost coating, a transparent cover, or micro-heating. The target calibration plate forms an angle with the image acquisition module and is within the image acquisition range of the image acquisition module.

[0037] Optionally, the light source module is a light source fixture used to provide illumination for the image acquisition module. In one specific embodiment, the light source module is any one or more of an LED fill light and an infrared light source.

[0038] Optionally, the target detection image is image data obtained by the image acquisition module from the target evaporator, used to characterize the surface state of the target evaporator. The frosting detection device can evaluate the frosting state of the target evaporator through this target detection image.

[0039] Optionally, after receiving a frost detection request, the frost detection device, under the frost detection conditions corresponding to the request, drives the image acquisition module to acquire an image of the target evaporator to obtain a target detection image of the target evaporator. That is, the frost detection device activates the light source module and drives the image acquisition module to capture an image of the target evaporator, thereby obtaining a target detection image containing both the target evaporator image and the target calibration plate image.

[0040] Optionally, in one specific embodiment, the frost detection device performs illumination calibration on the image acquisition module before driving it to acquire images. Specifically, the frost detection device drives the image acquisition module to acquire at least one image of the target evaporator in a frost-free state (i.e., no frost on the evaporator surface) as a reference image. The reference brightness and contrast information of this reference image are recorded by a target calibration plate, and this information is used as illumination calibration parameters. Before acquiring the target detection image, these illumination calibration parameters are used to calibrate and compensate the acquired image to obtain a calibrated target detection image. This eliminates the influence of changes in the light source, ensuring that the evaporator fins of the target evaporator are aligned with the frost layer, thus avoiding misjudgments in subsequent detection and evaluation.

[0041] 202. Based on the target detection image and the image calibration ratio, perform frost recognition to obtain the frost detection parameters of the target evaporator; Optionally, after acquiring a target detection image containing the corresponding image content of the target evaporator and the target calibration plate, the frost detection device also identifies the frost on the target evaporator based on the target detection image and the image calibration ratio, thereby obtaining frost detection parameters that characterize the frost state of the target evaporator in multiple dimensions.

[0042] Optionally, the image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with known calibration size data set in the target evaporator room, used to characterize the pixel size conversion ratio between image pixels and actual size in the target detection image.

[0043] Optionally, the frosting detection parameters are evaluation parameters that characterize the degree and state of frosting on the surface of the target evaporator in multiple dimensions. Optionally, in a specific embodiment, the frosting detection parameters include any one or more of frosting coverage, frosting thickness data, comprehensive frosting index, and frosting rate data.

[0044] Optionally, the frost coverage rate is a parameter characterizing the degree to which the target evaporator surface is covered by the target frost layer area, used to characterize the ratio of the frost layer area to the target evaporator surface area.

[0045] Optionally, the frost thickness data are parameter data characterizing the average frost thickness on the target evaporator surface.

[0046] Optionally, the comprehensive frost index is a quantitative parameter characterizing the degree of frost on the surface of the target evaporator. Optionally, this comprehensive frost index is calculated from frost coverage and frost thickness data, and can reflect the degree of influence of the frost on the surface of the target evaporator on the heat exchange performance of the target evaporator.

[0047] Optionally, the frosting rate data is a quantitative parameter characterizing the frosting rate of the target evaporator.

[0048] Optionally, the frost detection equipment can identify frost on the target detection image by using a target calibration ratio and an image segmentation model, thereby determining the degree of frost on the target evaporator and the impact of frost on the heat exchange efficiency from multiple dimensions.

[0049] Optionally, before acquiring the target detection image for frost detection, the frost detection device pre-calculates the target calibration ratio for pixel-to-size conversion of the image pixels. That is, the frost detection device acquires calibration image data of the target evaporator through the image acquisition module and the target calibration plate, and determines the image calibration ratio corresponding to the target evaporator based on the calibration size data and calibration image data of the target calibration data. Optionally, the calibration image data is image data acquired by the image acquisition module that includes the unfrostted target evaporator and the corresponding target calibration plate, used to establish the proportional relationship between pixels and actual sizes. Optionally, the calibration size data is the pre-measured calibration plate size data in the target calibration plate, used to provide actual size data support for the calibration process.

[0050] Optionally, after acquiring the calibration image data, the frosting detection device also acquires the calibration pixels of the calibration image data and calculates the calibration pixel distance between any of these calibration pixels. Here, the calibration pixels are the image pixels in the calibration image data selected for pixel distance-to-actual-size ratio conversion. The calibration pixel distance is the pixel distance between any two calibration pixels.

[0051] Optionally, after determining the calibration pixel distance between calibration pixels, the frosting detection device also acquires the calibration size data corresponding to the calibration pixel, calculates the ratio between the calibration size data and the calibration pixel distance, and obtains the image calibration ratio corresponding to the target evaporator. Here, the calibration size distance is the calibrated actual size data corresponding to the calibration pixel. The image calibration ratio characterizes the conversion ratio between the image pixels acquired by the image acquisition module and the actual size.

[0052] Optionally, after determining the image calibration ratio, the frost detection equipment also performs frost identification based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator.

[0053] Optionally, in one specific embodiment, after acquiring the target detection image, the frost detection device further preprocesses the acquired target detection image to improve the accuracy of subsequent frost recognition, thereby obtaining a preprocessed target detection image. This preprocessing operation includes any one or more of image denoising, illumination compensation, white balance adjustment, and normalization.

[0054] Optionally, the frost detection device uses an image segmentation model to segment the target detection image and determine the frost region mask in the target detection image. That is, the frost detection device uses a pre-trained image segmentation model to segment the target detection image, thereby determining the frost region mask corresponding to the target frost layer region in the target detection image. Here, the frost region mask is binary mask data representing the frost-covered areas in the target detection image. In this frost region mask, pixel 1 represents the frost layer, and 0 represents the background data corresponding to the non-frost layer.

[0055] Optionally, the image segmentation model is an artificial intelligence model used for frost detection and image segmentation of the target detection image, used to identify frost regions in the target detection image. Optionally, in a specific embodiment, the image segmentation model can be any one or more of image segmentation algorithms such as U-Net, DeepLab, and Mask R-CNN.

[0056] Optionally, in one specific embodiment, before using the image segmentation model for frost recognition, the frost detection device also performs supervised learning training on the initial segmentation model to obtain an image segmentation model capable of recognizing frost regions in the image. Specifically, the frost detection device acquires evaporator images from the target evaporator or other evaporators during the process from frost-free to severely frosted conditions, performs normalization processing, and manually labels the frost regions on the normalized evaporator images to generate training samples and segmentation mask labels. The segmentation mask labels are pixel category matrices with the same pixel size as the original image, used to identify frost regions and non-frost regions in the evaporator image, serving as reference labels for supervised learning during the training phase.

[0057] Optionally, after acquiring training samples and segmentation mask labels, the frost detection device uses these training samples and segmentation mask labels to train an initial segmentation model, obtaining an image segmentation model capable of frost recognition and segmentation. This model includes a network structure description containing encoding paths, decoding paths, and skip connection configurations, as well as a parameter weight file containing segmentation capabilities. This network structure description containing encoding paths, decoding paths, and skip connection configurations, along with the parameter weight file containing segmentation capabilities, can be ported to any frost detection device, enabling the image segmentation model to be deployed in any hardware environment for real-time segmentation of the detected image.

[0058] Optionally, after acquiring the frosting area mask, the frosting detection device obtains the number of frost pixels corresponding to the frosting area mask, calculates the ratio between the number of frost pixels in the frosting area mask and the total number of pixels in the target evaporator, and obtains the frosting coverage rate of the target evaporator. Here, the number of frost pixels is the sum of the number of pixels representing the frost layer in the frosting area mask. The total number of pixels is the sum of the number of pixels representing the corresponding evaporator area of ​​the target evaporator.

[0059] Optionally, the frosting detection device further determines the frosting thickness data of the target evaporator based on the edge position information of the target evaporator and the image calibration ratio. That is, the frosting detection device uses an edge detection model to perform edge detection on the target detection image to determine the edge position information of the target evaporator, which is the fin edge position information of the evaporation fins in the target evaporator. The edge detection model is an artificial intelligence model used to identify the edge position of the evaporator in the target detection image. Optionally, the edge detection model can be any edge detection algorithm.

[0060] Optionally, after acquiring the edge location information, the frost detection device determines the target frost layer region within the frost region mask based on the edge location information and the frost region mask. The target frost layer region refers to the area division information characterizing the frost-covered area in the target evaporator.

[0061] Optionally, after determining the target frost region, the frost detection device further acquires frost edge pixels representing the edge of the frost layer in the target frost region, and determines the frost thickness data of the target evaporator based on the frost edge pixels of the target frost region, the edge position information, and the image calibration scale. Specifically, the frost detection area locates the frost edge of the target frost region, acquires the corresponding frost edge pixels, acquires the position information of the frost edge pixels, calculates the difference between the position information of the frost edge pixels and the corresponding edge position information of the target evaporator, obtains the edge position offset between the frost edge and the fin edge of the target evaporator, and calculates the product between the edge position offset and the image calibration scale to obtain the frost thickness data of the target evaporator. In other words, the frost detection device calculates the difference between the position information of the frost edge pixels and the edge position information to obtain the edge position offset, and converts the edge position offset using the image calibration scale, i.e., calculates the product between the image calibration scale and the edge position offset to obtain the frost thickness data, thereby determining the frost thickness information of the target evaporator. The frost layer edge data can be edge pixel data and corresponding position information measured on multiple vertical cross-sections.

[0062] Optionally, after acquiring the frost coverage rate and frost thickness data, the frost detection equipment determines the frost detection parameters for the target evaporator based on the frost coverage rate and frost thickness data. That is, the frost detection equipment further determines the comprehensive frost index and frost rate data based on the frost coverage rate and frost thickness data to obtain frost detection parameters for multi-dimensional evaluation of the degree of frost on the target evaporator.

[0063] 203. When the frost detection parameters meet the target defrosting conditions, the target evaporator is defrosted.

[0064] Optionally, after acquiring the frost detection parameters, the frost detection equipment can evaluate the degree of frost on the target evaporator from multiple dimensions using these parameters. Then, when the frost detection parameters meet the target defrosting conditions, the equipment can perform defrosting on the target evaporator, thereby achieving timely and accurate defrosting and avoiding impact on heat exchange efficiency.

[0065] The target defrosting condition is an evaluation condition used to determine whether defrosting is required based on frost detection parameters. Optionally, in one specific embodiment, the target defrosting condition includes a first defrosting condition and / or a second defrosting condition. The first defrosting condition is an evaluation condition that assesses whether defrosting is required based on the comprehensive frost index in the frost detection parameters. The second defrosting condition is an evaluation condition that assesses whether defrosting is required based on the frost rate data in the frost detection parameters.

[0066] Optionally, in one specific embodiment, after acquiring the frost detection parameters, the frost detection device performs defrosting treatment on the target evaporator when the comprehensive frost index in the frost detection parameters meets the first defrosting condition. Optionally, in one specific embodiment, the first defrosting condition is that the comprehensive frost index is greater than a preset frost index threshold. That is, when the comprehensive frost index is greater than the preset frost index threshold, the frost detection device performs defrosting treatment on the target evaporator.

[0067] Optionally, in one specific embodiment, after acquiring the frost detection parameters, the frost detection device performs defrosting treatment on the target evaporator when the frost rate data in the frost detection parameters meets the second defrosting condition. Optionally, in one specific embodiment, the second defrosting condition is that the frost rate data is greater than a preset frost rate threshold. That is, when the frost rate data is greater than the preset frost rate threshold, the frost detection device performs defrosting treatment on the target evaporator.

[0068] Optionally, in other embodiments, when performing frost detection and determining frost detection parameters, the frost detection device also collects the current operating parameters of the refrigeration equipment and stores the frost detection parameters and the current operating parameters in a corresponding database. Optionally, the current operating parameters include any one or more of the following: ambient temperature, compartment temperature, and evaporator fin temperature.

[0069] Optionally, in other embodiments, the frost detection device can also determine whether to perform defrosting based on the current operating parameters and the frost detection parameters.

[0070] In this embodiment, the frost detection device responds to a frost detection request for a target evaporator by driving an image acquisition module to acquire an image of the target evaporator, thereby obtaining a target detection image of the target evaporator. Frost is identified based on the target detection image and the image calibration ratio to obtain frost detection parameters for the target evaporator. The image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with pre-calibrated dimensions set in the target evaporator chamber. When the frost detection parameters meet the target defrosting conditions, defrosting is performed on the target evaporator. This invention implements an image acquisition module and a target calibration board installed in the target evaporator chamber of a refrigeration system. When a frost detection request is met, the image acquisition module is driven to acquire target detection images of the target evaporator during operation. After determining the image calibration ratio using the target calibration board, frost identification is performed on the target evaporator using the target detection images and the image calibration ratio. This determines frost detection parameters that characterize the frost state of the target evaporator from multiple dimensions. Adaptive defrosting processing is then performed using these frost detection parameters and target defrosting conditions. This allows for the direct acquisition of frost detection parameters that characterize the frost state of the target evaporator during operation, improving the accuracy of frost assessment during frost measurement, effectively reducing frost measurement costs, and providing reliable data support for defrosting control of refrigeration equipment.

[0071] like Figure 4 As shown, Figure 4 This is a schematic flowchart of an embodiment of the frosting detection method for determining frosting detection parameters of a target evaporator provided in this application. Figure 4 In the illustrated embodiment, the frosting detection method further includes steps 301 to 304: 301. The frost coverage rate is weighted using the first weighting coefficient corresponding to the frost coverage rate to obtain the weighted coverage rate; the frost thickness data is weighted using the second weighting coefficient corresponding to the frost thickness data to obtain the weighted thickness data. 302. Calculate the sum of the weighted coverage rate and the weighted thickness data to obtain the comprehensive frosting index of the target evaporator; 303. Calculate the difference between the comprehensive frost index and the historical frost index to obtain the frost rate data of the target evaporator; 304. The comprehensive frost index and the frost rate data are determined as the frost detection parameters of the target evaporator.

[0072] Based on the above embodiments, in this embodiment, after acquiring the frost coverage rate and frost thickness data, the frost detection device determines the frost detection parameters of the target evaporator based on the frost coverage rate and frost thickness data. That is, the frost detection device further determines the comprehensive frost index and frost rate data based on the frost coverage rate and frost thickness data to obtain frost detection parameters for multi-dimensional evaluation of the degree of frost on the target evaporator.

[0073] Optionally, the frost detection device pre-sets corresponding weighting coefficients for frost coverage and frost thickness data, and uses these weighting coefficients to weight the frost coverage and frost thickness data respectively. Specifically, the frost detection device uses a first weighting coefficient corresponding to the frost coverage to weight the frost coverage, obtaining a weighted coverage; and uses a second weighting coefficient corresponding to the frost thickness data to weight the frost thickness, obtaining weighted thickness data. The first weighting coefficient is used to weight the frost coverage. The second weighting coefficient is used to weight the frost thickness data. The weighted coverage is the weighted frost coverage. The weighted thickness data is the weighted frost thickness. Optionally, the first and second weighting coefficients can be configured according to the actual application scenario.

[0074] Optionally, after acquiring the weighted coverage and weighted thickness data, the frost detection equipment calculates the sum of the weighted coverage and weighted thickness data to obtain the comprehensive frost index of the target evaporator.

[0075] Optionally, after obtaining the comprehensive frost index, the frost detection device also obtains the historical frost index obtained from the previous measurement, calculates the difference between the comprehensive frost index and the historical frost index, and obtains frost rate data characterizing the frost rate of the target evaporator. The historical frost index is the comprehensive frost index obtained from the previous frost detection measurement of the target evaporator.

[0076] Optionally, after acquiring the comprehensive frost index and frost rate data, the frost detection equipment determines the comprehensive frost index and frost rate data as the frost detection parameters for the target evaporator.

[0077] In this embodiment, the frosting detection device weights the frosting coverage rate using a first weighting coefficient to obtain a weighted coverage rate; it weights the frosting thickness data using a second weighting coefficient to obtain weighted thickness data; it calculates the sum of the weighted coverage rate and the weighted thickness data to obtain the comprehensive frosting index of the target evaporator; it calculates the difference between the comprehensive frosting index and the historical frosting index to obtain the frosting rate data of the target evaporator; and it determines the comprehensive frosting index and the frosting rate data as the frosting detection parameters of the target evaporator. This achieves a multi-dimensional and comprehensive assessment of the frosting degree of the target evaporator, obtaining assessment parameters that directly characterize the frosting degree of the evaporator, improving the accuracy of frosting assessment during the frosting measurement process, effectively reducing the cost of frosting measurement, and providing reliable data support for defrosting control of refrigeration equipment.

[0078] To better implement the frost detection method in the embodiments of this application, based on the frost detection method, the embodiments of this application also provide a frost detection device, such as... Figure 5 As shown, Figure 5 This is a schematic diagram of one embodiment of the frost detection device provided in this application. Specifically, the frost detection device 400 includes: The image acquisition module 401 is configured to respond to a frosting detection request for the target evaporator, drive the image acquisition module to acquire an image of the target evaporator, and obtain a target detection image of the target evaporator. The frost detection module 402 is configured to perform frost recognition based on the target detection image and the image calibration ratio to obtain frost detection parameters of the target evaporator. The frost detection module 403 is configured to perform defrosting treatment on the target evaporator when the frost detection parameters meet the target defrosting conditions.

[0079] In one possible implementation of this embodiment, before the frost detection device identifies frost based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator, it further includes: The calibration image data of the target evaporator is acquired using the image acquisition module and the target calibration plate; The image calibration ratio corresponding to the target evaporator is determined based on the calibration size data and calibration image data of the target calibration plate; The image acquisition module and the target calibration plate are located in the target evaporator chamber, with the target calibration plate situated within the shooting range of the image acquisition module and forming an angle with the image acquisition module.

[0080] In one possible implementation of this embodiment, the frosting detection device determines the image calibration ratio corresponding to the target evaporator based on the calibration size data and calibration image data of the target calibration plate, including: Obtain the calibration pixels in the calibration image data, and calculate the calibration pixel distance between any of the calibration pixels; Obtain the calibration size data corresponding to the calibration pixel, calculate the ratio between the calibration size data and the calibration pixel distance, and obtain the image calibration ratio corresponding to the target evaporator.

[0081] In one possible implementation of this embodiment, the frost detection device identifies frost based on the target detection image and the image calibration ratio to obtain frost detection parameters for the target evaporator, including: The target detection image is segmented using an image segmentation model to determine the frosting region mask in the target detection image; The ratio between the number of frost pixels in the frost area mask and the total number of pixels in the target evaporator is calculated to obtain the frost coverage rate of the target evaporator. The frost thickness data of the target evaporator is determined based on the edge position information of the target evaporator and the image calibration ratio. The frost detection parameters of the target evaporator are determined based on the frost coverage rate and the frost thickness data.

[0082] In one possible implementation of this embodiment, the frosting detection device determines the frosting thickness data of the target evaporator based on the edge position information of the target evaporator and the image calibration ratio, including: Edge detection is performed on the target detection image and / or calibration image data using an edge detection model to determine the edge position information of the target evaporator, wherein the edge position information is the fin edge position information of the evaporation fins in the target evaporator; The target frost layer region in the frost area mask is determined based on the edge location information and the frost area mask. Calculate the distance between the first and second frost pixels in the target frost region; The frost thickness data of the target evaporator is calculated based on the frost layer pixel distance and the image calibration ratio.

[0083] In one possible implementation of this embodiment, the frost detection device determines the frost detection parameters of the target evaporator based on the frost coverage rate and the frost thickness data, including: The frost coverage rate is weighted using a first weighting coefficient to obtain a weighted coverage rate; the frost thickness data is weighted using a second weighting coefficient to obtain weighted thickness data. The sum of the weighted coverage rate and the weighted thickness data is calculated to obtain the comprehensive frosting index of the target evaporator; The difference between the comprehensive frost index and the historical frost index is calculated to obtain the frost rate data of the target evaporator; The comprehensive frost index and the frost rate data are determined as the frost detection parameters for the target evaporator.

[0084] In one possible implementation of this embodiment, the frost detection device performs defrosting treatment on the target evaporator when the frost detection parameters meet the target defrosting conditions, including: Obtain the first defrost condition and / or the second defrost condition from the target defrost conditions; When the comprehensive frost index in the frost detection parameters meets the first defrosting condition, the target evaporator is defrosted. And / or, when the frost rate data in the frost detection parameters meets the second defrosting condition, the target evaporator is defrosted.

[0085] In this embodiment, the frost detection device responds to a frost detection request for the target evaporator by driving the image acquisition module to acquire an image of the target evaporator, thereby obtaining a target detection image of the target evaporator. Frost is identified based on the target detection image and the image calibration ratio to obtain frost detection parameters for the target evaporator. The image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with pre-calibrated dimensions set in the target evaporator chamber. When the frost detection parameters meet the target defrosting conditions, defrosting is performed on the target evaporator. This invention implements an image acquisition module and a target calibration board installed in the target evaporator chamber of a refrigeration system. When a frost detection request is met, the image acquisition module is driven to acquire target detection images of the target evaporator during operation. After determining the image calibration ratio using the target calibration board, frost identification is performed on the target evaporator using the target detection images and the image calibration ratio. This determines frost detection parameters that characterize the frost state of the target evaporator from multiple dimensions. Adaptive defrosting processing is then performed using these frost detection parameters and target defrosting conditions. This allows for the direct acquisition of frost detection parameters that characterize the frost state of the target evaporator during operation, improving the accuracy of frost assessment during frost measurement, effectively reducing frost measurement costs, and providing reliable data support for defrosting control of refrigeration equipment.

[0086] This invention also provides a frosting detection device, such as... Figure 6 As shown, Figure 6 This is a schematic diagram of one embodiment of the frost detection device provided in this application.

[0087] The frost detection device integrates any of the frost detection devices provided in the embodiments of the present invention, and the frost detection device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured by the processor to perform the steps of the frost detection method described in any of the embodiments of the above-described frost detection method.

[0088] Specifically, the frost detection device may include components such as a processor 501 with one or more processing cores, a memory 502 with one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will understand that... Figure 6 The frost detection device structure shown does not constitute a limitation on the frost detection device. It may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 501 is the control center of the frosting detection device. It connects various parts of the device via interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 502, and by calling data stored in the memory 502, thereby providing overall monitoring of the frosting detection device. Optionally, the processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 501.

[0089] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and frosting detection by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the frosting detection device, etc. In addition, the memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0090] The frosting detection device also includes a power supply 503 that supplies power to the various components. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 503 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0091] The frosting detection device may also include an input unit 504, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0092] Although not shown, the frosting detection device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 501 in the frosting detection device loads the executable files corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 501 runs the application programs stored in the memory 502 to realize various functions, as follows: In response to a frost detection request for the target evaporator, the image acquisition module is driven to acquire an image of the target evaporator to obtain a target detection image of the target evaporator. Frost recognition is performed based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator. The image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with known calibration size data set in the target evaporator room. When the frost detection parameters meet the target defrosting conditions, the target evaporator is defrosted.

[0093] Therefore, embodiments of the present invention provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a disk, or an optical disk, etc. A computer program is stored thereon, which is loaded by a processor to execute the steps in any of the frosting detection methods provided in the embodiments of the present invention. For example, the computer program loaded by the processor can execute the following steps: In response to a frost detection request for the target evaporator, the image acquisition module is driven to acquire an image of the target evaporator to obtain a target detection image of the target evaporator. Frost recognition is performed based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator. The image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with known calibration size data set in the target evaporator room. When the frost detection parameters meet the target defrosting conditions, the target evaporator is defrosted.

[0094] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0095] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0096] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0097] The above provides a detailed description of a frosting detection method provided by the embodiments of this application. Specific embodiments have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and its core ideas. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for detecting frost formation, characterized in that, The frosting detection method includes: In response to a frost detection request for the target evaporator, the image acquisition module is driven to acquire an image of the target evaporator to obtain a target detection image of the target evaporator. Frost recognition is performed based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator. The image calibration ratio is a conversion ratio obtained by calibration using a target calibration plate with known calibration size data set in the target evaporator room. When the frost detection parameters meet the target defrosting conditions, the target evaporator is defrosted.

2. The frosting detection method according to claim 1, characterized in that, Before performing frost recognition based on the target detection image and the image calibration ratio to obtain the frost detection parameters of the target evaporator, the method further includes: The calibration image data of the target evaporator is acquired using the image acquisition module and the target calibration plate; The image calibration ratio corresponding to the target evaporator is determined based on the calibration size data and calibration image data of the target calibration plate; The image acquisition module and the target calibration plate are located in the target evaporator chamber, with the target calibration plate situated within the shooting range of the image acquisition module and forming an angle with the image acquisition module.

3. The frosting detection method according to claim 2, characterized in that, Determining the image calibration ratio corresponding to the target evaporator based on the calibration size data and calibration image data of the target calibration plate includes: Obtain the calibration pixels in the calibration image data, and calculate the calibration pixel distance between any of the calibration pixels; Obtain the calibration size data corresponding to the calibration pixel, calculate the ratio between the calibration size data and the calibration pixel distance, and obtain the image calibration ratio corresponding to the target evaporator.

4. The frosting detection method according to claim 1, characterized in that, The step of identifying frost based on the target detection image and the image calibration ratio to obtain frost detection parameters for the target evaporator includes: The target detection image is segmented using an image segmentation model to determine the frosting region mask in the target detection image; The ratio between the number of frost pixels in the frost area mask and the total number of pixels in the target evaporator is calculated to obtain the frost coverage rate of the target evaporator. The frost thickness data of the target evaporator is determined based on the edge position information of the target evaporator and the image calibration ratio. The frost detection parameters of the target evaporator are determined based on the frost coverage rate and the frost thickness data.

5. The frosting detection method according to claim 4, characterized in that, The step of determining the frost thickness data of the target evaporator based on the edge position information of the target evaporator and the image calibration ratio includes: Edge detection is performed on the target detection image and / or calibration image data using an edge detection model to determine the edge position information of the target evaporator, wherein the edge position information is the fin edge position information of the evaporation fins in the target evaporator; The target frost layer region in the frost area mask is determined based on the edge location information and the frost area mask. The frost thickness data of the target evaporator is determined based on the frost edge pixels of the target frost region, the edge position information, and the image calibration ratio.

6. The frosting detection method according to claim 4, characterized in that, The step of determining the frost detection parameters of the target evaporator based on the frost coverage rate and the frost thickness data includes: The frost coverage rate is weighted using a first weighting coefficient to obtain a weighted coverage rate; the frost thickness data is weighted using a second weighting coefficient to obtain weighted thickness data. The sum of the weighted coverage rate and the weighted thickness data is calculated to obtain the comprehensive frosting index of the target evaporator; The difference between the comprehensive frost index and the historical frost index is calculated to obtain the frost rate data of the target evaporator; The comprehensive frost index and the frost rate data are determined as the frost detection parameters for the target evaporator.

7. The frosting detection method according to any one of claims 1-6, characterized in that, When the frost detection parameters meet the target defrosting conditions, the target evaporator is defrosted, including: Obtain the first defrost condition and / or the second defrost condition from the target defrost conditions; When the comprehensive frost index in the frost detection parameters meets the first defrosting condition, the target evaporator is defrosted. And / or, when the frost rate data in the frost detection parameters meets the second defrosting condition, the target evaporator is defrosted.

8. A frosting detection device, characterized in that, The frost detection device includes: The image acquisition module is configured to respond to a frosting detection request for the target evaporator, drive the image acquisition module to acquire images of the target evaporator, and obtain a target detection image of the target evaporator. The frost detection module is configured to identify frost based on the target detection image and the image calibration ratio to obtain frost detection parameters of the target evaporator. The frost detection module is configured to perform defrosting treatment on the target evaporator when the frost detection parameters meet the target defrosting conditions.

9. A frosting detection device, characterized in that, The frost detection device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the frosting detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to execute the steps of the frosting detection method according to any one of claims 1 to 7.

Images