Snow melting control method and system for large-span roof

Abstract

The invention discloses a snow melting control method and system for a large-span roof, and relates to the technical field of disaster prevention and control, and the method comprises the steps: analyzing the relevance between the snow accumulation state of the roof and an environmental factor through computer vision, thereby obtaining the possible time of snow accumulation of the roof through analysis; the snow melting assembly is opened in advance according to the predicted possible time before the next accumulated snow arrives, the method can be applied to any roof with the snow melting assembly, data does not need to be prepared in advance, and the flow steps of the method can automatically learn and analyze the accumulated snow characteristics of the roof and prepare countermeasures in advance after first-time installation. Compared with the prior art, the method makes up the vacancy of roof accumulated snow prevention, has a self-learning function giving consideration to the environment, and guarantees the accuracy of roof accumulated snow prevention.

Description

Technical Field

[0001] The present application relates to the field of disaster prevention and control technology, and in particular to a snow melting control method and system for a large-span roof. Background Art

[0002] The hazards of snow accumulation on roofs primarily include: 1. Structural stress: The weight of accumulated snow increases the stress on the roof structure, especially on flat roofs and those with shallow slopes, potentially causing structural damage or even roof collapse. 2. Water leakage risk: Melting snow can cause water to seep through the roof, damaging internal facilities and equipment. 3. Heat loss: A snow-covered roof can affect the building's insulation, increasing internal heat loss and increasing energy consumption. 4. Safety hazards: Snow on the roof can fall, endangering people and facilities below. 5. Pressure on the building: If snow on the roof is not promptly removed, repeated freezing and thawing can transform the underlying snow into ice, which exerts a greater pressure than the snow. Furthermore, long-span roofs often experience uneven snow depth, and this uneven load has a far greater impact on the roof's steel structure than even snow accumulation. The weight of accumulated snow is far greater than one might imagine. A 100-square-meter roof with more than 40 centimeters of snow can bear a load of 3 to 5 tons.

[0003] From the above, we can see that it is necessary to clear the snow from the roof in time to protect the personal safety of surrounding users and the service life of the building. Usually, heating, flushing, shoveling, chemical snow removal, mechanical snow removal and other means are used to remove snow.

[0004] At present, the prevention of snow accumulation on roofs is still in its initial stage and experimental stage. Usually, the method of snow accumulation is adopted first and then management is adopted. When the snow reaches a certain thickness, it is removed by manual cleaning. There is no effective means to prevent snow accumulation. Some roofs may adopt the form of installing heating strips to prevent snow accumulation, but in practice, the heating strips are usually operated at full power throughout the day in cold weather. Although the effect of preventing snow accumulation is achieved, the power resources consumed are large and the operating cost is high. Summary of the Invention

[0005] The main purpose of this application is to provide a snow melting control method and system for a large-span roof, so as to solve the problem that there is no effective means to prevent snow accumulation in the prior art.

[0006] In order to achieve the above objectives, this application provides the following technical solutions: A snow melting control method for a large-span roof, the snow melting control method being applied to the top roof of a large-span building, the top roof being equipped with a snow melting assembly, the snow melting range of the snow melting assembly covering the top roof, the snow melting control method comprising: Step S1, acquiring a side view image and a top view image of the top roof based on a preset detection interval; Step S2, identifying the top surface boundary and the side surface boundary of the top roof from all the side view images and all the top view images respectively based on computer vision; Step S3: When the RGB value within the top surface boundary of the same preset detection interval approaches the maximum value and the perimeter of the side boundary increases, it is determined that snow accumulation has begun; Step S4, obtaining a starting timestamp of snow accumulation, and obtaining a real-time perimeter of the side boundary based on the preset detection interval; Step S5, obtaining environmental climate parameters of the area where the long-span building is located based on the preset detection interval; Step S6, analyzing the time linear regression relationship between all starting timestamps and all environmental climate parameters, and the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; Step S7, obtaining future environmental climate parameters and substituting them into the time linear regression relationship and the circumference linear regression relationship, respectively, to obtain a future starting timestamp and a future circumference; Step S8, when the future perimeter begins to exceed the perimeter of the side boundary, obtaining the previous future start timestamp closest to the exceeded future perimeter and defining it as the future snowmelt start timestamp; Step S9: When the future snow melting start timestamp arrives, start the snow melting component.

[0007] As a further improvement of the present application, step S9, when the future snow melting start timestamp arrives, starts the snow melting component, and then includes: Step S10, when the future snow melting start timestamp arrives, obtaining real-time environmental climate parameters of the area where the large-span building is located; Step S20, obtaining data similarity between the real-time environmental climate parameter and the future environmental climate parameter, and if the data similarity is less than a preset similarity threshold, executing step S30; Step S30, defining all future environmental climate parameters as distorted environmental climate parameters; Step S40 , substituting the real-time environmental climate parameters into step S6 to update the time linear regression relationship and the circumference linear regression relationship.

[0008] As a further improvement of the present application, step S9, when the future snow melting start timestamp arrives, starts the snow melting component, and then includes: Step S100, obtaining the RGB value of the top surface boundary in an uncovered state and defining it as a standard RGB value; Step S200, after the snow melting component is turned on, obtaining the real-time RGB value within the top surface boundary based on a preset detection interval; Step S300: when the real-time RGB value is equal to the standard RGB value, reducing the output power of the snow melting component according to a preset ratio; Step S400, repeatedly executing steps S200 to S300 several times until the real-time RGB value is not equal to the standard RGB value; Step S500, obtaining the output power corresponding to the previous step in which the real-time RGB value is not equal to the standard RGB value and defining it as the minimum output power; Step S600: adjusting the current output power of the snow melting component to the minimum output power through the PID control law.

[0009] As a further improvement of the present application, step S2, based on computer vision, identifies the top surface boundary and the side surface boundary of the top roof from all side view images and all top view images respectively, including: Step S21, obtaining the image position of the top roof in each side view image and each top view image respectively through a target detection algorithm; Step S22, converting each side view image and each top view image into a grayscale image using a color space conversion function of a cross-platform computer vision library; Step S23, extracting the edges of each grayscale image using an edge detection algorithm; Step S24, projecting the image position into a corresponding grayscale image; Step S25 : obtaining edges that match the image position based on the current grayscale image and marking them as the top surface boundary and the side surface boundary.

[0010] As a further improvement of the present application, step S6, parsing the time linear regression relationship between all starting timestamps and all environmental climate parameters, and the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters, includes: Step S61, defining all starting timestamps as known dependent variables and all environmental climate parameters as known independent variables; Step S62, defining the known dependent variables and the known independent variables of the same preset detection interval into a linear regression equation through multiple linear regression; Step S63, integrating the linear regression equations of all preset detection intervals into a linear regression equation group; Step S64, solving all unknown linear regression coefficients of the linear regression equations by the least square method; Step S65, substituting all the known linear regression coefficients obtained by solving into the linear regression equation group to obtain the time linear regression relationship; Step S66: Replace all known dependent variables with all real-time circumferences and repeat steps S62 to S65 to obtain the circumference linear regression relationship.

[0011] As a further improvement of the present application, step S9, when the future snow melting start timestamp arrives, starts the snow melting component, and then includes: Step S1000, obtaining the activation time of the snow melting component; Step S1000, determining whether the on time exceeds a preset time threshold, if so, executing step S3000; Step S3000: Turn off the snow melting component.

[0012] As a further improvement of the present application, step S3000, closing the snow melting component, then includes: Step S10000: sending the top surface boundary and the side surface boundary to an external visualization terminal; Step S20000: obtaining a start timestamp and a close timestamp of the snow melting component based on the start duration; Step S30000: Send the minimum output power, the start timestamp, and the shutdown timestamp to an external monitoring terminal.

[0013] In order to achieve the above objectives, this application also provides the following technical solutions: A snow melting control system for a large-span roof, the snow melting control system being applied to the above-mentioned snow melting control method, the snow melting control system comprising: A top roof view image acquisition module is used to acquire a side view image and a top view image of the top roof based on a preset detection interval; A top roof image boundary acquisition module is used to identify the top surface boundary and side boundary of the top roof from all side view images and all top view images based on computer vision; The module for determining whether snow accumulation has begun on the roof is used to determine whether snow accumulation has begun when the RGB values ​​within the top surface boundary of the same preset detection interval approach the maximum value and the perimeter of the side boundary increases; A top roof snow accumulation parameter acquisition module is used to obtain a starting timestamp of snow accumulation and obtain a real-time perimeter of the side boundary based on the preset detection interval; A building environmental climate parameter acquisition module, configured to acquire environmental climate parameters of an area where a large-span building is located based on the preset detection interval; Snow linear regression relationship analysis module, used to analyze the time linear regression relationship between all starting timestamps and all environmental climate parameters, as well as the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; A top roof snow parameter prediction module is used to obtain future environmental climate parameters and substitute them into the time linear regression relationship and the perimeter linear regression relationship respectively to obtain a future starting timestamp and a future perimeter respectively; A future snowmelt start time definition module is configured to obtain a previous future start timestamp closest to the exceeded future perimeter when the future perimeter begins to exceed the perimeter of the side boundary and define the previous future start timestamp as the future snowmelt start timestamp; The snow melting component activation module is configured to activate the snow melting component when the future snow melting activation timestamp arrives.

[0014] In order to achieve the above objectives, this application also provides the following technical solutions: An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the snow melting control method as described above is implemented.

[0015] In order to achieve the above objectives, this application also provides the following technical solutions: A storage medium stores program instructions, which, when executed by a processor, can implement the snow melting control method described above.

[0016] This application obtains side and top images of the top roof based on a preset detection interval; identifies the top surface boundary and side boundary of the top roof from all side images and all top images based on computer vision; determines that snow accumulation has begun when the RGB value within the top surface boundary of the same preset detection interval approaches the full value and the perimeter of the side boundary increases; obtains the starting timestamp of snow accumulation and obtains the real-time perimeter of the side boundary based on the preset detection interval; obtains the environmental climate parameters of the area where the large-span building is located based on the preset detection interval; analyzes the time linear regression relationship between all starting timestamps and all environmental climate parameters, as well as the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; obtains future environmental climate parameters and substitutes them into the time linear regression relationship and the perimeter linear regression relationship respectively to obtain the future starting timestamp and future perimeter respectively; when the future perimeter begins to exceed the perimeter of the side boundary, obtains the previous future starting timestamp closest to the exceeded future perimeter and defines it as the future snow melting start timestamp; when the future snow melting start timestamp arrives, turns on the snow melting component. This application uses computer vision to analyze the correlation between a roof's snow accumulation status and environmental factors, thereby determining the likely time when snow will begin to accumulate on the roof. It then activates the snowmelt component based on the predicted likely time before the next snowfall. This application is applicable to any roof with a snowmelt component and eliminates the need for advance data preparation. The application's process steps can automatically learn and analyze the roof's snow accumulation characteristics after initial installation, allowing for the preparation of countermeasures. Compared to existing technologies, this application addresses the gap in roof snow prevention while also providing environmentally friendly self-learning capabilities, ensuring the accuracy of roof snow prevention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic flow chart of the steps of an embodiment of a snow melting control method for a large-span roof according to the present application; Figure 2 This is a functional module diagram of an embodiment of a snow melting control system for a large-span roof according to the present application; Figure 3 This is a schematic structural diagram of an embodiment of the electronic device of the present application; Figure 4 This is a structural diagram of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features specified as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications in the embodiments of this application (such as up, down, left, right, front, back, etc.) are intended only to illustrate the relative positional relationships and movement of components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units and may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or device.

[0020] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] like Figure 1 As shown, this embodiment provides an embodiment of a snow melting control method for a large-span roof. In this embodiment, the snow melting control method is applied to the top roof of a large-span building. The top roof is installed with a snow melting component, and the snow melting range of the snow melting component covers the top roof.

[0022] Long-span roofs are preferably used on the roofs of large-span buildings, which generally refer to buildings with spans of 30 meters or more. Article 8.6.1 of the 2003 Code for Steel Structures defines structures with spans of 60 meters or more as long-span structures. These structures are primarily used in civil architecture such as theaters, stadiums, exhibition halls, conference halls, airports, and other large public buildings. In industrial architecture, they are primarily used in aircraft assembly plants, hangars, and other large-span factories.

[0023] Preferably, the snow melting assembly includes existing snow melting facilities that can be controlled to open and close, such as heating strips and salt water spraying.

[0024] Specifically, the snow melting control method includes the following steps: Step S1: Acquire a side view image and a top view image of the top roof based on a preset detection interval.

[0025] Preferably, the preset detection interval can be set to one of 5 minutes, 10 minutes, 30 minutes, and 60 minutes.

[0026] Step S2: Based on computer vision, the top surface boundary and the side surface boundary of the top roof are respectively identified from all the side view images and all the top view images.

[0027] Preferably, the side of the top roof is photographed based on a level viewing angle. Usually, the shooting unit needs to be located flush with the top of the large-span building, while the top surface of the top roof can be photographed in an adjacent higher-rise building, or by separately setting up a shooting unit through a pole, or by using a drone.

[0028] Step S3: When the RGB value within the top surface boundary of the same preset detection interval approaches the maximum value and the perimeter of the side boundary increases, it is determined that snow accumulation has begun.

[0029] Preferably, the full value of the RGB value is (255, 255, 255), that is, white. Due to the lighting factor of shooting, this embodiment adopts approximation, and the approximation can be set to 90% to 95% of the full value of the RGB value.

[0030] Preferably, for pure white roofs (rarely, most roofs are dark in color), the top surface monitoring is canceled, and the side thickness change is used as the main analysis object.

[0031] Step S4: Obtain the starting timestamp of snow accumulation, and obtain the real-time perimeter of the side boundary based on a preset detection interval.

[0032] Preferably, the real-time perimeter can directly adopt the boundary perimeter in the image, and the boundary perimeter can be directly identified and obtained by a computer.

[0033] Step S5: Acquire environmental climate parameters of the area where the long-span building is located based on a preset detection interval.

[0034] Preferably, the environmental climate parameters include sunshine intensity, sunshine duration, wind speed, ambient temperature, and ambient humidity.

[0035] Step S6: analyzing the time linear regression relationship between all starting timestamps and all environmental climate parameters, and the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters.

[0036] Preferably, steps S4 to S6 are a preliminary learning process for first installation.

[0037] Step S7: Obtain future environmental climate parameters and substitute them into the time linear regression relationship and the circumference linear regression relationship respectively to obtain the future starting timestamp and the future circumference respectively.

[0038] Preferably, future environmental climate parameters can be obtained directly from the local meteorological bureau.

[0039] Step S8: When the future perimeter begins to exceed the perimeter of the side boundary, the previous future start timestamp closest to the exceeded future perimeter is obtained and defined as the future snowmelt start timestamp.

[0040] Step S9: When the future snow melting start timestamp arrives, start the snow melting component.

[0041] Furthermore, in step S9, when the future snow melting start time stamp arrives, the snow melting component is started, and then the following steps are also included: Step S10: When the future snow melting start timestamp arrives, obtain the real-time environmental climate parameters of the area where the large-span building is located.

[0042] Step S20 , obtaining data similarity between the real-time environmental climate parameter and the future environmental climate parameter. If the data similarity is less than a preset similarity threshold, step S30 is executed.

[0043] Preferably, commonly used algorithms for determining data similarity include Euclidean distance, Manhattan distance, cosine similarity, Pearson correlation coefficient, etc., and the preset similarity threshold can be set to 90%.

[0044] Step S30: defining all future environmental climate parameters as distorted environmental climate parameters.

[0045] In step S40 , the real-time environmental climate parameters are substituted into step S6 to update the time linear regression relationship and the circumference linear regression relationship.

[0046] Preferably, the design of steps S10 to S40 is intended to prevent behaviors such as sudden climate changes that increase errors.

[0047] Furthermore, in step S9, when the future snow melting start time stamp arrives, the snow melting component is started, and then the following steps are also included: Step S100 , obtaining the RGB value of the top surface boundary in an uncovered state and defining it as a standard RGB value.

[0048] Preferably, the RGB values ​​should be collected in the same environment parameters as much as possible.

[0049] Step S200: After the snow melting component is turned on, the real-time RGB value within the top surface boundary is obtained based on a preset detection interval.

[0050] Step S300: When the real-time RGB value is equal to the standard RGB value, the output power of the snow melting component is reduced according to a preset ratio.

[0051] In step S400 , steps S200 to S300 are repeated several times until the real-time RGB value is not equal to the standard RGB value.

[0052] Step S500 , obtaining the output power corresponding to the previous step in which the real-time RGB value is not equal to the standard RGB value and defining it as the minimum output power.

[0053] Step S600: The snow melting component is controlled by a PID control law to adjust the current output power to the minimum output power.

[0054] Preferably, step S600 is designed to prevent power oscillation.

[0055] Furthermore, step S2, based on computer vision, identifies the top surface boundary and the side surface boundary of the top roof from all the side view images and all the top view images, which specifically includes the following steps: Step S21 , obtaining the image position of the top roof in each side view image and each top view image respectively through a target detection algorithm.

[0056] Preferably, the target detection algorithm may adopt Yolo v5.

[0057] Step S22 : converting each side view image and each top view image into a grayscale image using a color space conversion function of a cross-platform computer vision library.

[0058] Preferably, the cross-platform computer vision library is OpenCV, and the color space conversion function is the cv2_color() function Step S23: extract the edges of each grayscale image using an edge detection algorithm.

[0059] Preferably, the edge detection algorithm may adopt canny edge detection.

[0060] Step S24: projecting the image position into the corresponding grayscale image.

[0061] Step S25 : obtaining edges that match the image position based on the current grayscale image and marking them as top and side boundaries.

[0062] Furthermore, step S6, analyzing the time linear regression relationship between all starting timestamps and all environmental climate parameters, and the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters, specifically includes the following steps: Step S61: define all starting timestamps as known dependent variables and all environmental climate parameters as known independent variables.

[0063] Step S62: defining the known dependent variables and the known independent variables of the same preset detection interval into a linear regression equation through multiple linear regression.

[0064] Preferably, the multiple linear regression may adopt lasso linear regression.

[0065] In step S63 , the linear regression equations of all the preset detection intervals are integrated into a linear regression equation group.

[0066] Step S64: solving all unknown linear regression coefficients of the linear regression equations by the least square method.

[0067] Step S65: Substitute all the known linear regression coefficients obtained by solving into the linear regression equation group to obtain the time linear regression relationship.

[0068] In step S66, all known dependent variables are replaced with all real-time circumferences and steps S62 to S65 are repeated to obtain a circumference linear regression relationship.

[0069] Furthermore, in step S9, when the future snow melting start time stamp arrives, the snow melting component is started, and then the following steps are also included: Step S1000, obtaining the activation time of the snow melting component.

[0070] Step S1000, determine whether the on time exceeds a preset time threshold, if so, execute step S3000.

[0071] Step S3000, turn off the snow melting component.

[0072] Furthermore, in step S3000, the snow melting component is turned off, and then the following steps are also included: Step S10000: Send the top surface boundary and the side surface boundary to an external visualization terminal.

[0073] Step S20000: Obtain the opening timestamp and closing timestamp of the snow melting component based on the opening duration.

[0074] Step S30000: Send the minimum output power, the start timestamp, and the close timestamp to the external monitoring terminal.

[0075] This embodiment obtains side and top images of the roof based on a preset detection interval; identifies the top and side boundaries of the roof from all side and top images based on computer vision; determines that snow accumulation has begun when the RGB value within the top boundary approaches the maximum value and the perimeter of the side boundary increases within the same preset detection interval; obtains a starting timestamp for the start of snow accumulation, and obtains the real-time perimeter of the side boundary based on the preset detection interval; obtains environmental climate parameters for the area where the large-span building is located based on the preset detection interval; analyzes the time linear regression relationship between all starting timestamps and all environmental climate parameters, as well as the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; obtains future environmental climate parameters and substitutes them into the time linear regression relationship and the perimeter linear regression relationship to obtain a future starting timestamp and a future perimeter, respectively; when the future perimeter begins to exceed the perimeter of the side boundary, obtains the previous future starting timestamp closest to the exceeded future perimeter and defines it as the future snow melting start timestamp; and when the future snow melting start timestamp arrives, activates the snow melting component. This embodiment uses computer vision to analyze the correlation between a roof's snow accumulation status and environmental factors, thereby determining the likely time when snow accumulation will begin. It then activates the snowmelt component based on this predicted time before the next snowfall. This embodiment is applicable to any roof with a snowmelt component and eliminates the need for pre-prepared data. The process steps in this embodiment can automatically learn and analyze the roof's snow accumulation characteristics after initial installation, allowing for the preparation of countermeasures. Compared to existing technologies, this embodiment addresses a gap in roof snow accumulation prevention while also providing environmentally sensitive self-learning capabilities, ensuring accurate roof snow accumulation prevention.

[0076] like Figure 2 As shown, this embodiment provides an embodiment of a snow melting control system for a large-span roof. In this embodiment, the snow melting control system is applied to the snow melting control method as described above.

[0077] Specifically, the snow melting control system includes a top roof view image acquisition module 1, a top roof image boundary acquisition module 2, a top roof snow accumulation determination module 3, a top roof snow accumulation parameter acquisition module 4, a building environment climate parameter acquisition module 5, a snow accumulation linear regression relationship analysis module 6, a top roof snow accumulation parameter prediction module 7, a future snow melting start time definition module 8, and a snow melting component start module 9, which are electrically connected in sequence.

[0078] Among them, the top roof view image acquisition module 1 is used to obtain the side view image and the top view image of the top roof based on the preset detection interval; the top roof image boundary acquisition module 2 is used to identify the top surface boundary and the side boundary of the top roof from all the side view images and all the top view images respectively based on computer vision; the top roof snow accumulation judgment module 3 is used to judge that snow accumulation has begun when the RGB value within the top surface boundary of the same preset detection interval approaches the full value and the circumference of the side boundary increases; the top roof snow accumulation parameter acquisition module 4 is used to obtain the starting timestamp of the start of snow accumulation and obtain the real-time circumference of the side boundary based on the preset detection interval; the building environment climate parameter acquisition module 5 is used to obtain the environmental parameters of the area where the large-span building is located based on the preset detection interval. Environmental climate parameters; the snow linear regression relationship analysis module 6 is used to analyze the time linear regression relationship between all starting timestamps and all environmental climate parameters, as well as the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; the top roof snow parameter prediction module 7 is used to obtain future environmental climate parameters and substitute them into the time linear regression relationship and the perimeter linear regression relationship respectively to obtain the future starting timestamp and the future perimeter respectively; the future snow melting start time definition module 8 is used to obtain the previous future starting timestamp closest to the exceeded future perimeter when the future perimeter begins to exceed the perimeter of the side boundary and define it as the future snow melting start timestamp; the snow melting component activation module 9 is used to activate the snow melting component when the future snow melting start timestamp arrives.

[0079] Furthermore, the snow melting control system also includes a real-time environmental climate parameter acquisition module, a data similarity acquisition module, a distorted environmental climate parameter definition module, and a correction module that are electrically connected in sequence; the real-time environmental climate parameter acquisition module is electrically connected to the snow melting component start module 9.

[0080] Among them, the real-time environmental climate parameter acquisition module is used to obtain the real-time environmental climate parameters of the area where the large-span building is located when the future snow melting start timestamp arrives; the data similarity acquisition module is used to obtain the data similarity between the real-time environmental climate parameters and the future environmental climate parameters; the distorted environmental climate parameter definition module is used to define all future environmental climate parameters as distorted environmental climate parameters if the data similarity is less than the preset similarity threshold; the correction module is used to substitute the real-time environmental climate parameters into the snow accumulation linear regression relationship analysis module 6 to update the time linear regression relationship and the circumference linear regression relationship.

[0081] Furthermore, the snow melting control system also includes a standard RGB value definition module, a real-time RGB value acquisition module, an output power reduction module, a repeated iteration module, a minimum output power definition module, and a minimum output power output module, which are electrically connected in sequence; the standard RGB value definition module is electrically connected to the snow melting component start module 9.

[0082] Among them, the standard RGB value definition module is used to obtain the RGB value of the top surface boundary in an uncovered state and define it as the standard RGB value; the real-time RGB value acquisition module is used to obtain the real-time RGB value within the top surface boundary based on a preset detection interval after the snow melting component is turned on; the output power reduction module is used to reduce the output power of the snow melting component according to a preset ratio when the real-time RGB value is equal to the standard RGB value; the repeated iteration module is used to repeatedly execute the real-time RGB value acquisition module to the output power reduction module several times until the real-time RGB value is not equal to the standard RGB value; the minimum output power definition module is used to obtain the output power corresponding to the previous step when the real-time RGB value is not equal to the standard RGB value and define it as the minimum output power; the minimum output power output module is used to adjust the current output power of the snow melting component to the minimum output power through the PID control law.

[0083] Furthermore, the top roof image boundary acquisition module 2 specifically includes a first top roof image boundary acquisition unit, a second top roof image boundary acquisition unit, a third top roof image boundary acquisition unit, a fourth top roof image boundary acquisition unit, and a fifth top roof image boundary acquisition unit, which are electrically connected in sequence; the first top roof image boundary acquisition unit is electrically connected to the top roof view image acquisition module 1, and the fifth top roof image boundary acquisition unit is electrically connected to the top roof snow accumulation judgment module 3.

[0084] Among them, the first top roof image boundary acquisition unit is used to obtain the image position of the top roof in each side view image and each top view image through the target detection algorithm; the second top roof image boundary acquisition unit is used to convert each side view image and each top view image into a grayscale image through the color space conversion function of the cross-platform computer vision library; the third top roof image boundary acquisition unit is used to extract the edges of each grayscale image through the edge detection algorithm; the fourth top roof image boundary acquisition unit is used to project the image position into the corresponding grayscale image; the fifth top roof image boundary acquisition unit is used to obtain the edges that match the image position based on the current grayscale image and mark them as the top surface boundary and the side boundary.

[0085] Furthermore, the snow accumulation linear regression relationship analysis module 6 specifically includes a first snow accumulation linear regression relationship analysis unit, a second snow accumulation linear regression relationship analysis unit, a third snow accumulation linear regression relationship analysis unit, a fourth snow accumulation linear regression relationship analysis unit, a fifth snow accumulation linear regression relationship analysis unit, and a sixth snow accumulation linear regression relationship analysis unit, which are electrically connected in sequence; the first snow accumulation linear regression relationship analysis unit is electrically connected to the building environment climate parameter acquisition module 5, and the sixth snow accumulation linear regression relationship analysis unit is electrically connected to the top roof snow parameter prediction module 7.

[0086] Among them, the first snow linear regression relationship analysis unit is used to define all starting timestamps as known dependent variables and all environmental climate parameters as known independent variables; the second snow linear regression relationship analysis unit is used to define the known dependent variables and known independent variables of the same preset detection interval as a linear regression equation through multiple linear regression; the third snow linear regression relationship analysis unit is used to integrate the linear regression equations of all preset detection intervals into a linear regression equation group; the fourth snow linear regression relationship analysis unit is used to solve all unknown linear regression coefficients of the linear regression equation group through the least squares method; the fifth snow linear regression relationship analysis unit is used to substitute all the solved known linear regression coefficients into the linear regression equation group to obtain a time linear regression relationship; the sixth snow linear regression relationship analysis unit is used to replace all known dependent variables with all real-time circumferences and repeatedly execute the second snow linear regression relationship analysis unit to the fifth snow linear regression relationship analysis unit to obtain a circumference linear regression relationship.

[0087] Furthermore, the snow melting control system also includes a snow melting component on time acquisition module, a snow melting component on time judgment module, and a snow melting component closing module, which are electrically connected in sequence; the snow melting component on time acquisition module is electrically connected to the snow melting component on module 9.

[0088] Among them, the snow melting component on-time acquisition module is used to obtain the on-time of the snow melting component; the snow melting component on-time judgment module is used to judge whether the on-time exceeds the preset time threshold; the snow melting component off module is used to turn off the snow melting component if so.

[0089] Furthermore, the snow melting control system also includes a boundary sending module, a snow melting component opening and closing timestamp acquisition module, and a snow melting component parameter sending module, which are electrically connected in sequence; the boundary sending module is electrically connected to the snow melting component closing module.

[0090] Among them, the boundary sending module is used to send the top surface boundary and the side boundary to the external visualization terminal; the snow melting component opening and closing timestamp acquisition module is used to obtain the opening timestamp and closing timestamp of the snow melting component based on the opening time; the snow melting component parameter sending module is used to send the minimum output power, opening timestamp, and closing timestamp to the external monitoring end.

[0091] It should be noted that this embodiment is a functional module item embodiment based on the above-mentioned method embodiment. Additional contents such as the preference, expansion, limitation, and example illustration of this embodiment can be found in the above-mentioned method embodiment, and will not be repeated in this embodiment.

[0092] This embodiment obtains side and top images of the roof based on a preset detection interval; identifies the top and side boundaries of the roof from all side and top images based on computer vision; determines that snow accumulation has begun when the RGB value within the top boundary approaches the maximum value and the perimeter of the side boundary increases within the same preset detection interval; obtains a starting timestamp for the start of snow accumulation, and obtains the real-time perimeter of the side boundary based on the preset detection interval; obtains environmental climate parameters for the area where the large-span building is located based on the preset detection interval; analyzes the time linear regression relationship between all starting timestamps and all environmental climate parameters, as well as the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; obtains future environmental climate parameters and substitutes them into the time linear regression relationship and the perimeter linear regression relationship to obtain a future starting timestamp and a future perimeter, respectively; when the future perimeter begins to exceed the perimeter of the side boundary, obtains the previous future starting timestamp closest to the exceeded future perimeter and defines it as the future snow melting start timestamp; and when the future snow melting start timestamp arrives, activates the snow melting component. This embodiment uses computer vision to analyze the correlation between a roof's snow accumulation status and environmental factors, thereby determining the likely time when snow accumulation will begin. It then activates the snowmelt component based on this predicted time before the next snowfall. This embodiment is applicable to any roof with a snowmelt component and eliminates the need for pre-prepared data. The process steps in this embodiment can automatically learn and analyze the roof's snow accumulation characteristics after initial installation, allowing for the preparation of countermeasures. Compared to existing technologies, this embodiment addresses a gap in roof snow accumulation prevention while also providing environmentally sensitive self-learning capabilities, ensuring accurate roof snow accumulation prevention.

[0093] like Figure 3 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0094] The memory 102 stores program instructions for implementing the snow melting control method for a large-span roof according to any of the above embodiments.

[0095] The processor 101 is configured to execute program instructions stored in the memory 102 to control snow melting of a large-span roof.

[0096] Processor 101 may also be referred to as a CPU (Central Processing Unit). Processor 101 may be an integrated circuit chip with data processing capabilities. Processor 101 may also be a general-purpose processor, a digital data processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. A general-purpose processor may be a microprocessor or any conventional processor.

[0097] Further, Figure 4 This is a schematic diagram of the structure of a storage medium in an embodiment of the present application. The storage medium 11 in the embodiment of the present application stores program instructions 111 that can implement all of the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, server, mobile phone, and tablet.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0099] In addition, the functional units in the various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0100] The above detailed description of the specific embodiments of the present application is intended only as an example, and the present application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions made to the present application are also within the scope of the present application. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present application should be included within the scope of the present application.

Claims

1. A snow melting control method for a large-span roof, wherein the snow melting control method is applied to the top roof of a large-span building, wherein the top roof is equipped with a snow melting assembly, and the snow melting range of the snow melting assembly covers the top roof, and wherein: The snow melting control method comprises: Step S1, acquiring a side view image and a top view image of the top roof based on a preset detection interval; Step S2, identifying the top surface boundary and the side surface boundary of the top roof from all the side view images and all the top view images respectively based on computer vision; Step S3: When the RGB value within the top surface boundary of the same preset detection interval approaches the maximum value and the perimeter of the side boundary increases, it is determined that snow accumulation has begun; Step S4, obtaining a starting timestamp of snow accumulation, and obtaining a real-time perimeter of the side boundary based on the preset detection interval; Step S5, obtaining environmental climate parameters of the area where the long-span building is located based on the preset detection interval; Step S6, analyzing the time linear regression relationship between all starting timestamps and all environmental climate parameters, and the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; Step S7, obtaining future environmental climate parameters and substituting them into the time linear regression relationship and the circumference linear regression relationship, respectively, to obtain a future starting timestamp and a future circumference; Step S8, when the future perimeter begins to exceed the perimeter of the side boundary, obtaining the previous future start timestamp closest to the exceeded future perimeter and defining it as the future snowmelt start timestamp; Step S9: When the future snow melting start timestamp arrives, start the snow melting component.

2. The snow melting control method according to claim 1, characterized in that: Step S9, when the future snow melting start timestamp arrives, starts the snow melting component, and then includes: Step S10, when the future snow melting start timestamp arrives, obtaining real-time environmental climate parameters of the area where the large-span building is located; Step S20, obtaining data similarity between the real-time environmental climate parameter and the future environmental climate parameter, and if the data similarity is less than a preset similarity threshold, executing step S30; Step S30, defining all future environmental climate parameters as distorted environmental climate parameters; Step S40 , substituting the real-time environmental climate parameters into step S6 to update the time linear regression relationship and the circumference linear regression relationship.

3. The snow melting control method according to claim 1, characterized in that: Step S9, when the future snow melting start timestamp arrives, starts the snow melting component, and then includes: Step S100, obtaining the RGB value of the top surface boundary in an uncovered state and defining it as a standard RGB value; Step S200, after the snow melting component is turned on, obtaining the real-time RGB value within the top surface boundary based on a preset detection interval; Step S300: when the real-time RGB value is equal to the standard RGB value, reducing the output power of the snow melting component according to a preset ratio; Step S400, repeatedly executing steps S200 to S300 several times until the real-time RGB value is not equal to the standard RGB value; Step S500, obtaining the output power corresponding to the previous step in which the real-time RGB value is not equal to the standard RGB value and defining it as the minimum output power; Step S600: adjusting the current output power of the snow melting component to the minimum output power through the PID control law.

4. The snow melting control method according to claim 1, characterized in that: Step S2, based on computer vision, identifies the top surface boundary and the side surface boundary of the top roof from all side view images and all top view images, including: Step S21, obtaining the image position of the top roof in each side view image and each top view image respectively through a target detection algorithm; Step S22, converting each side view image and each top view image into a grayscale image using a color space conversion function of a cross-platform computer vision library; Step S23, extracting the edges of each grayscale image using an edge detection algorithm; Step S24, projecting the image position into a corresponding grayscale image; Step S25 : obtaining edges that match the image position based on the current grayscale image and marking them as the top surface boundary and the side surface boundary.

5. The snow melting control method according to claim 1, characterized in that: Step S6, parsing the time linear regression relationship between all starting timestamps and all environmental climate parameters, and the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters, including: Step S61, defining all starting timestamps as known dependent variables and all environmental climate parameters as known independent variables; Step S62, defining the known dependent variables and the known independent variables of the same preset detection interval into a linear regression equation through multiple linear regression; Step S63, integrating the linear regression equations of all preset detection intervals into a linear regression equation group; Step S64, solving all unknown linear regression coefficients of the linear regression equations by the least square method; Step S65, substituting all the known linear regression coefficients obtained by solving into the linear regression equation group to obtain the time linear regression relationship; Step S66, replacing all known dependent variables with all real-time circumferences and repeating steps S62 to S65 to obtain the circumference linear regression relationship.

6. The snow melting control method according to claim 3, characterized in that: Step S9, when the future snow melting start time stamp arrives, start the snow melting component, and then include: Step S1000, obtaining the activation time of the snow melting component; Step S1000, determining whether the on time exceeds a preset time threshold, if so, executing step S3000; Step S3000: Turn off the snow melting component.

7. The snow melting control method according to claim 6, characterized in that: Step S3000, closing the snow melting component, then includes: Step S10000: sending the top surface boundary and the side surface boundary to an external visualization terminal; Step S20000: obtaining a start timestamp and a close timestamp of the snow melting component based on the start duration; Step S30000: Send the minimum output power, the start timestamp, and the shutdown timestamp to an external monitoring terminal.

8. A snow melting control system for a large-span roof, the snow melting control system being applied to the snow melting control method according to any one of claims 1 to 7, characterized in that: The snow melting control system includes: A top roof view image acquisition module is used to acquire a side view image and a top view image of the top roof based on a preset detection interval; A top roof image boundary acquisition module is used to identify the top surface boundary and side boundary of the top roof from all side view images and all top view images based on computer vision; The module for determining whether snow accumulation has begun on the roof is used to determine whether snow accumulation has begun when the RGB values ​​within the top surface boundary of the same preset detection interval approach the maximum value and the perimeter of the side boundary increases; A top roof snow accumulation parameter acquisition module is used to obtain a starting timestamp of snow accumulation and obtain a real-time perimeter of the side boundary based on the preset detection interval; A building environmental climate parameter acquisition module, configured to acquire environmental climate parameters of an area where a large-span building is located based on the preset detection interval; Snow linear regression relationship analysis module, used to analyze the time linear regression relationship between all starting timestamps and all environmental climate parameters, as well as the perimeter linear regression relationship between all real-time perimeters and all environmental climate parameters; A top roof snow parameter prediction module is used to obtain future environmental climate parameters and substitute them into the time linear regression relationship and the perimeter linear regression relationship respectively to obtain a future starting timestamp and a future perimeter respectively; A future snowmelt start time definition module is configured to obtain a previous future start timestamp closest to the exceeded future perimeter when the future perimeter begins to exceed the perimeter of the side boundary and define the previous future start timestamp as the future snowmelt start timestamp; The snow melting component activation module is configured to activate the snow melting component when the future snow melting activation timestamp arrives.

9. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the snow melting control method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the snow melting control method according to any one of claims 1 to 7 can be implemented.

Images