A construction method and system for thermal insulation wall

Abstract

An embodiment of the present specification provides a method for constructing an insulation wall, which is executed by a processor of a terminal where a construction APP is located, including: determining the construction stage of the insulation wall based on a monitoring image obtained by a monitoring device; in response to the construction stage being the stage of laying insulation wall panels, acquiring wall data of a target building based on a database, and acquiring thermal imaging data of the wall of the target building based on an infrared camera; acquiring environmental data around the target building; based on the wall data and environmental data, predicting suspected crack information between multiple insulation wall panels on the wall surface, the suspected crack information including potential crack occurrence locations and crack development levels where cracks may be generated subsequently; in response to the crack development level meeting a preset condition, sending additional reinforcement reminder information to construction personnel through the construction APP; in response to the crack development level not meeting the preset condition, sending exterior wall decoration construction reminder information to construction personnel through the construction APP.

Description

Technical Field

[0001] The present invention relates to the field of building insulation technology, and in particular to a construction method and system for an insulation wall. Background Art

[0002] Building insulation renovation can not only reduce energy consumption for heating and cooling and reduce carbon emissions, but also greatly improve physical comfort and bring users a better living experience.

[0003] At present, the commonly used building insulation measures are mainly to add insulation structures to the exterior walls of buildings. By enhancing the thermal barrier performance of the exterior walls of buildings, the heat in the building is prevented from being dissipated to the outside through large areas of walls, thereby improving the insulation performance of the building. After the construction of the insulation wall is completed, the insulation wall often cracks and the insulation layer falls off due to changes in weather, environmental temperature and humidity, which seriously affects the service life of the insulation wall. In order to extend the service life of the insulation wall, relevant technicians have taken various measures, such as changing the material mix ratio, optimizing the construction process, and adding other materials, devices or components. However, this also means that a greater cost is required, making the benefits brought by the insulation wall not proportional to the cost.

[0004] In order to solve the problem that the insulation wall is easily aged and falls off due to weather and environmental conditions, CN115233860A proposes a composite insulation wall and its construction process. By adding corresponding inner and outer coatings on the inner and outer sides of the insulation layer, it can effectively prevent moisture in the high-humidity indoor environment from penetrating to the outside through the base wall, and avoid deformation or even falling off of the insulation layer due to temperature differences between the inner and outer sides; and the outer coating has good flame retardant properties, which can effectively prevent the spread of fire in the event of a fire. However, since not all parts of the insulation wall will age and fall off due to changes in temperature, humidity, etc., this situation often only occurs locally. If the entire insulation wall is coated without distinction, the maintenance cost will be greatly increased.

[0005] Therefore, it is hoped to provide a construction method for an insulation wall, which can increase the service life of the insulation wall while reducing the construction and maintenance costs. Summary of the invention

[0006] One or more embodiments of the present specification provide a method for constructing an insulation wall, the method being executed by a processor of a terminal where a construction APP is located, and comprising: determining a construction stage of the insulation wall based on a monitoring image acquired by a monitoring device; in response to the construction stage being a stage for laying insulation wall panels, acquiring wall data of a target building based on a database, and acquiring thermal imaging data of the wall of the target building based on an infrared camera; the wall data at least includes the size, thickness, and type of the wall; acquiring environmental data around the target building; the environmental data at least includes weather, temperature, humidity, and light; based on the wall data and the environmental data, predicting suspected crack information between multiple insulation wall panels on a wall surface, the suspected crack information including potential crack occurrence locations and crack development levels where cracks may be generated subsequently; the wall surface is a flat layer coated with mortar; in response to the crack development level meeting a preset condition, sending additional reinforcement reminder information to a construction worker through the construction APP; the additional reinforcement reminder information includes the crack occurrence location that needs to be reinforced; in response to the crack development level not meeting the preset condition, sending reminder information for exterior wall decoration construction to the construction worker through the construction APP.

[0007] One or more embodiments of the present specification provide a construction system for an insulation wall, the system comprising: a first determination module for determining the construction stage of the insulation wall based on a monitoring image acquired by a monitoring device; a first acquisition module for acquiring wall data of a target building based on a database and thermal imaging data of the wall of the target building based on an infrared camera in response to the construction stage being the stage of laying insulation wall panels; the wall data at least includes the size, thickness and type of the wall; a second acquisition module for acquiring environmental data around the target building; the environmental data at least includes weather, temperature, humidity and light; a second determination module for acquiring thermal imaging data of the wall of the target building based on the thermal imaging data of the wall of the target building; the thermal imaging data of the wall of the target building at least includes weather, temperature, humidity and light; a second acquisition module for acquiring thermal imaging data of the wall of the target building based on the thermal imaging data of the wall of the target building; the thermal imaging data of the wall of the target building ... The wall data and the environmental data are used to predict suspected crack information between multiple insulation wall panels on the wall surface, the suspected crack information including potential crack occurrence locations and crack development levels that may subsequently generate cracks; the wall surface is a flat layer coated with mortar; a first reminder module is used to send additional reinforcement reminder information to construction personnel through the construction APP in response to the crack development level meeting the preset conditions; the additional reinforcement reminder information includes the crack occurrence locations that need to be reinforced; a second reminder module is used to send reminder information of exterior wall decoration construction to the construction personnel through the construction APP in response to the crack development level not meeting the preset conditions.

[0008] One or more embodiments of the present specification provide a thermal insulation wall construction device, comprising at least one memory and at least one processor; the at least one memory stores computer instructions, and the at least one processor is used to execute part of the computer instructions to implement the thermal insulation wall construction method described in any one of the above embodiments.

[0009] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer runs the insulation wall construction method described in any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0011] Figure 1 is an exemplary module diagram of a construction system for an insulation wall according to some embodiments of this specification;

[0012] Figure 2 is an exemplary flow chart of a construction method of an insulation wall according to some embodiments of this specification;

[0013] Figure 3 is an exemplary flow chart for predicting suspected crack information according to some embodiments of this specification;

[0014] Figure 4 is an exemplary schematic diagram of predicting crack probability and corresponding crack development level based on a first model according to some embodiments of this specification;

[0015] Figure 5 is an exemplary flow chart for predicting anchor density according to some embodiments of the present specification;

[0016] Figure 6 is an exemplary schematic diagram of predicting cracking probability based on an anchor bolt model according to some embodiments of this specification. DETAILED DESCRIPTION

[0017] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0018] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0019] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0020] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0021] The same insulation wall is affected differently by temperature and humidity changes at different locations, so the construction techniques or maintenance methods required at different locations also need to be differentiated to improve the pertinence of insulation wall construction and maintenance, reduce costs, and effectively extend the service life of the insulation wall. CN115233860A only improves the use effect of the entire insulation wall by indiscriminately adding inner coatings and outer coatings to the insulation wall, but some locations of the insulation wall may not age, and uniformly applying inner coatings and outer coatings may increase costs. In addition, some locations may not be able to solve the aging problem by simply applying inner coatings and outer coatings. Therefore, some embodiments of this specification can take targeted measures for locations where cracks may occur by predicting in advance the locations where cracks may occur in the insulation wall and the level of crack development, and different measures can be adopted for different crack development levels, which can improve the pertinence and effectiveness of insulation wall construction and maintenance and reduce construction costs.

[0022] Figure 1 1 is an exemplary module diagram of a thermal insulation wall construction system according to some embodiments of the present specification. In some embodiments, the thermal insulation wall construction system 100 may include a first determination module 110, a first acquisition module 120, a second acquisition module 130, a second determination module 140, a first reminder module 150, and a second reminder module 160.

[0023] The first determination module 110 can be used to determine the construction stage of the insulation wall based on the monitoring image obtained by the monitoring device. For more information about the construction stage of the insulation wall, please refer to Figure 3 and its related description.

[0024] The first acquisition module 120 can be used to obtain the wall data of the target building based on the database and the thermal imaging data of the wall of the target building based on the infrared camera in response to the construction stage being the stage of laying the thermal insulation wall panels; the wall data at least includes the size, thickness and type of the wall. For more information about wall data and thermal imaging data, please refer to Figure 3 and its related description.

[0025] The second acquisition module 130 can be used to acquire environmental data around the target building; the environmental data may include at least weather, temperature, humidity, light, etc. For more information about environmental data, see Figure 3 and its related description.

[0026] The second determination module 140 can be used to predict suspected crack information between multiple insulation wall panels on the wall surface based on wall data and environmental data, the suspected crack information including potential crack occurrence locations and crack development levels that may subsequently generate cracks; the wall surface is a flat layer coated with mortar.

[0027] In some embodiments, the second determination module 140 can be further used to: determine temperature distribution data and heat source distribution data based on thermal imaging data; and predict potential crack occurrence locations and crack development levels based on the temperature distribution data and heat source distribution data in combination with wall data. For more information on predicting crack development levels and crack occurrence locations, please refer to Figure 3 and its related description.

[0028] In some embodiments, the second determination module 140 may also be used to predict the density of anchor bolts required for additional reinforcement corresponding to the potential crack occurrence location based on the potential crack occurrence location and the crack development level.

[0029] In some embodiments, the second determination module 140 may be further configured to determine the density of anchor bolts required for additional reinforcement based on thermal bridge effects at different locations.

[0030] More information on predicting anchor density can be found in Figure 5 and its related description.

[0031] The first reminder module 150 can be used to send additional reinforcement reminder information to the construction personnel through the construction APP in response to the crack development level meeting the preset conditions; the additional reinforcement reminder information includes the location of the cracks to be reinforced, and the degree of additional reinforcement. The degree of additional reinforcement can include the density of anchor bolts required for reinforcement. For more information about anchor bolt density, please refer to Figure 5 and its related description.

[0032] The second reminder module 160 can be used to send reminder information of the exterior wall decoration construction to the construction personnel through the construction APP in response to the crack development level not meeting the preset conditions.

[0033] For more information on sending additional reinforcement reminders and exterior wall decoration construction reminders, please refer to Figure 3 and its related description.

[0034] It should be noted that the above description of the construction system and modules of the thermal insulation wall is only for convenience of description and does not limit the present specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, they may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. In some embodiments, Figure 1 The first determination module 110, the first acquisition module 120, the second acquisition module 130, the second determination module 140, the first reminder module 150 and the second reminder module 160 disclosed in the specification can be different modules in a system, or one module can realize the functions of two or more modules mentioned above. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0035] Figure 2 is an exemplary flow chart of a construction method of an insulation wall according to some embodiments of this specification. In some embodiments, process 200 may be executed by a processor. Figure 2 As shown, process 200 includes the following steps:

[0036] Step 210, determining the construction stage of the insulation wall based on the monitoring image acquired by the monitoring device.

[0037] The monitoring device may refer to a device configured at the insulation wall construction site (such as the target building) for capturing images. For example, the monitoring device may be a monitoring camera, a camera, etc.

[0038] The monitoring image may refer to an image related to the construction of the insulation wall taken by the monitoring device. For example, the monitoring image may be an image of the insulation wall at various construction stages taken by the monitoring device. In some embodiments, the processor may send an instruction to the monitoring device based on a preset time interval to obtain the monitoring image. The preset time interval may be set by system default.

[0039] The construction stage can refer to the various stages in the construction process of the insulation wall. For example, the insulation wall construction stage can include wall cleaning, waterproofing, measuring and drawing lines, laying insulation wall panels, etc.

[0040] In some embodiments, the processor can determine the construction stage of the insulation wall based on the monitoring image acquired by the monitoring device through image recognition technology. For example, images of various construction stages of the insulation wall can be taken in advance and stored, and then the monitoring image acquired by the monitoring device and the stored image are compared one by one through image recognition technology, and the one with the highest similarity in the comparison results is used as the construction stage corresponding to the monitoring image.

[0041] Step 220, in response to the construction stage being the stage of laying thermal insulation wall panels, the wall data of the target building is acquired based on the database, and the thermal imaging data of the wall of the target building is acquired based on the infrared camera.

[0042] The database may refer to a storage unit preset in advance for storing various data of the target building. For example, the database may be a storage unit for storing the size information, wall data, location information, etc. of the target building. The target building may refer to a building that needs to be laid with thermal insulation wall panels.

[0043] Wall data may refer to data related to the wall of the target building. For example, the wall data may include the size, thickness, and type of the wall.

[0044] In some embodiments, in response to the construction stage being the stage of laying thermal insulation wall panels, the processor may obtain the wall data of the target building from the database. For example, the processor may directly obtain the wall data stored in advance from the database.

[0045] Thermal imaging data may refer to heat data of a target building acquired through non-contact detection. For example, thermal imaging data may include infrared thermal imaging data. Thermal imaging data may reflect heat distribution information of a wall of a target building.

[0046] In some embodiments, the processor may detect the target building through an infrared detection device to obtain thermal imaging data of the wall of the target building.

[0047] Step 230, obtaining environmental data around the target building; the environmental data at least includes weather, temperature, humidity, and light.

[0048] Environmental data may refer to data in the environment where the target building is located that may affect the construction or life of the insulation wall. For example, environmental data may include weather information, temperature information, humidity information, and light information at the location of the target building.

[0049] In some embodiments, the processor may obtain environmental data around the target building through a weather forecast platform, a climate information platform, etc. at the location of the target building. In some embodiments, the processor may also obtain environmental data around the target building through various detection devices configured around the target building. The detection devices may include a temperature detector, a humidity detector, a light detector, etc.

[0050] Step 240, based on the wall data and the environmental data, predict the suspected crack information between the multiple insulation wall panels on the wall surface, the suspected crack information includes the potential occurrence location of the cracks that may generate cracks in the future and the crack development level; the wall surface is a flat layer coated with mortar.

[0051] Cracks may refer to cracks and peeling that may occur in the insulation wall panels themselves, and may also include gaps between insulation wall panels. Suspected crack information may refer to information related to cracks that may occur in the insulation wall of the target building. For example, suspected crack information may include whether cracks may occur, potential locations of cracks, and crack development levels.

[0052] The potential location of cracks may refer to the potential location of cracks on the insulation wall panels or between the insulation wall panels. The crack development level may refer to the possible size level of the cracks, which can be measured by the crack range, length and width.

[0053] In some embodiments, the potential crack occurrence position can be represented by a matrix. For example, the processor can divide the wall into grids, each grid corresponds to a position and a matrix element, and the matrix element of the grid corresponding to the potential crack occurrence position is marked as 1, and the matrix elements of the grid corresponding to other positions are marked as 0, so as to form a matrix of the potential crack occurrence position.

[0054] In some embodiments, the crack development level can also be represented by a matrix. For example, the processor can divide various possible crack development levels into primary, secondary, tertiary, and quaternary levels, represented by numbers 1, 2, 3, and 4, respectively. After determining the crack development level at a certain position of the wall, the matrix element of the grid corresponding to the position is marked with a number corresponding to the crack development level.

[0055] In some embodiments, the processor may predict suspected crack information between multiple insulation wall panels on the wall surface based on the wall data and the environmental data. For example, the processor may obtain historical crack data of the installed insulation wall panels of a building with the same wall data and the same environmental data, and predict suspected crack information of the insulation wall panels of the target building based on the historical crack data. Exemplarily, the processor may directly determine the historical crack data as suspected crack information of the insulation wall panels of the target building.

[0056] In some embodiments, the processor can determine temperature distribution data and heat source distribution data based on thermal imaging data; based on the temperature distribution data and heat source distribution data, combined with wall data, predict the potential location of cracks and the level of crack development. For more information on predicting the potential location of cracks and the level of crack development, please refer to Figure 3 and its related description.

[0057] Step 250, in response to the crack development level meeting the preset conditions, additional reinforcement reminder information is sent to the construction personnel through the construction APP; the additional reinforcement reminder information includes the location where the cracks need to be reinforced.

[0058] The preset condition may refer to the size of the preset crack development level. For example, the crack development level may be divided into level 1, level 2, level 3, level 4, etc., where level 1 < level 2 < level 3 < level 4, and the preset condition may be that the crack development level is greater than level 1. In some embodiments, the preset condition may be determined based on construction experience, etc.

[0059] The additional reinforcement reminder may refer to a reminder to the construction personnel that the insulation wall panels need additional reinforcement. For example, the additional reinforcement reminder information may include the location of the additional reinforcement, the degree of the additional reinforcement, etc., wherein the degree of the additional reinforcement may include the density of anchor bolts required for reinforcement. Exemplarily, the additional reinforcement reminder may be "The potential crack location of the insulation wall panel is XXX, the crack development level is X, and the preset conditions are met. Additional reinforcement is required, and the degree of additional reinforcement is XXX".

[0060] In some embodiments, in response to the crack development level meeting a preset condition, the processor may send additional reinforcement reminder information to the construction personnel through the construction APP to remind the construction personnel to perform additional reinforcement on the corresponding positions of the insulation wall panels.

[0061] Step 260 , in response to the crack development level not satisfying the preset condition, a reminder message of the exterior wall decoration construction is sent to the construction personnel via the construction APP.

[0062] The reminder information of the exterior wall decoration construction may refer to information reminding the construction personnel to decorate the exterior wall. For example, the reminder information of the exterior wall decoration construction may be "the development level of the crack at the XXX position of the insulation wall panel does not meet the preset conditions, and the exterior wall decoration can be carried out".

[0063] In some embodiments, in response to the crack development level not meeting the preset conditions, the processor may send exterior wall decoration construction reminder information to the construction personnel through the construction APP to remind the construction personnel to perform exterior wall decoration construction on the corresponding location.

[0064] In some embodiments of this specification, by predicting suspected crack information of the insulation wall panels of the target building based on the wall data and environmental data of the target building, additional reinforcement can be performed in advance at the insulation wall panel locations where cracks may occur. If cracks are not predicted to occur or the cracks do not meet the preset conditions, the construction personnel can be notified in time to perform exterior wall decoration. This method can improve the pertinence of the reinforcement of the insulation wall panels of the target building, improve construction efficiency, and reduce costs.

[0065] Figure 3 FIG. 300 is an exemplary flow chart of predicting suspected crack information according to some embodiments of this specification. In some embodiments, process 300 may be executed by a processor. Figure 3 As shown, process 300 may include the following steps:

[0066] Step 310, determining temperature distribution data and heat source distribution data based on the thermal imaging data.

[0067] The temperature distribution data may refer to the temperature distribution of the wall of the target building. For example, the temperature distribution data may include information such as the temperature distribution characteristics of the wall of the target building, the temperature magnitudes at different wall locations, etc. The temperature distribution characteristics may refer to the temperature distribution characteristics of the wall of the target building, such as the temperature magnitude changes at different locations, the temperature difference magnitude, etc.

[0068] The heat source distribution data may refer to the heat source distribution of the wall of the target building. For example, the heat source distribution data may include information such as the heat source distribution position and heat source size of the wall of the target building, wherein the heat source position may be reflected as the light direction and light position, and the heat source size may be reflected as the light intensity, etc.

[0069] In some embodiments, the processor may determine temperature distribution data based on a thermal imaging image formed by thermal imaging data. For example, the temperature distribution may be determined based on the temperature magnitude corresponding to each position in the thermal imaging image.

[0070] In some embodiments, the processor may determine the heat source distribution data based on the thermal imaging image. For example, the processor may determine the distribution data of the heat source (such as the lighting direction, lighting range, and lighting intensity) based on the colors of different wall positions (areas) in the thermal imaging image. Exemplarily, in the thermal imaging image, the color of the illuminated area tends to be red, and the color of the unilluminated area tends to be blue or green, so the heat source distribution data may be determined based on the color distribution of different areas in the thermal imaging image.

[0071] In some embodiments, the temperature distribution data may be represented by a temperature distribution matrix. For example, the processor may divide the wall of the target building into grids, one grid corresponding to one matrix element, and determine the temperature data of the wall position corresponding to each grid as the matrix element corresponding to the grid to form a temperature distribution matrix.

[0072] In some embodiments, similarly, the heat source distribution data can also be represented by a heat source distribution matrix. For example, the processor can determine the heat source data of the wall position corresponding to each grid as the matrix element corresponding to the grid to form a heat source distribution matrix. Among them, in the heat source distribution matrix, the heat source data corresponding to each matrix element includes the heat source size. Among them, the heat source size can be reflected as light intensity, and different colors in different areas of the thermal imaging image can represent different light intensities, such as the closer to red, the greater the light intensity, and vice versa, the smaller the light intensity. For example, the processor can preset the corresponding heat source size values ​​for different colors in the thermal imaging image in advance and store them, and then obtain the heat source size value corresponding to the color based on the color of the thermal imaging image of the wall position corresponding to each grid, as the value of the matrix element corresponding to each grid. According to the numerical values ​​corresponding to the matrix elements in the heat source distribution matrix, the heat source position and direction (such as the upper left and lower left of the wall, etc.) can be determined. For example, the wall area with a larger and more concentrated numerical value corresponding to the matrix element is the heat source position and direction.

[0073] Step 320 , based on the temperature distribution data and the heat source distribution data, combined with the wall data, predict the potential location of cracks and the level of crack development.

[0074] In some embodiments, the processor may determine the potential crack occurrence location and crack development level of the insulation wall panels of the target building based on the crack data of the installed insulation wall panels with the same temperature distribution data and heat source distribution data and the same wall data. For example, the crack data of the installed insulation wall panels with the same temperature distribution data and heat source distribution data and the same wall data are directly determined as the potential crack occurrence location and crack development level of the target building.

[0075] In some embodiments, the processor can obtain temperature distribution data and heat source distribution data of the wall based on a thermal imaging device; based on the temperature distribution data and heat source distribution data, predict the potential location and level of crack development caused by excessive temperature difference, and further perform additional reinforcement processing.

[0076] In some embodiments, the processor may obtain temperature data of multiple positions of the wall based on the thermal imaging device to generate temperature distribution data. In some embodiments, the processor may determine the heat source distribution based on the thermal imaging image obtained by the thermal imaging device and the color distribution of different areas in the thermal imaging image. For example, the processor may determine the wall position corresponding to the area whose color is close to red in the thermal imaging image as the heat source distribution position.

[0077] In some embodiments, the processor can determine the temperature difference at multiple locations of the wall based on the temperature distribution data and the heat source distribution data, and predict the potential location of cracks and the level of crack development caused by excessive temperature differences based on the temperature differences. For example, the processor can determine the numerical values ​​of the matrix elements in the heat source distribution matrix based on the heat source distribution matrix, determine the area with a larger numerical difference as the area with a larger temperature difference, and further determine the temperature difference based on the temperature distribution data of the area with a larger temperature difference. In some embodiments, the processor can obtain historical crack data caused by historical temperature differences in historical data, determine cracks and crack levels that may be caused by different historical temperature differences based on the historical crack data, and determine the crack level corresponding to the historical temperature difference that is the same as the current temperature difference from the historical crack data based on the current temperature difference as the crack development level corresponding to the current wall position.

[0078] In some embodiments, the processor can obtain temperature distribution data and heat source distribution data of the target building wall for a period of time through a thermal imaging device, and determine the temperature difference data of different positions of the wall through statistical analysis; based on the temperature difference data, determine which positions of the wall have a temperature difference exceeding a temperature difference threshold, and the number of times the temperature difference threshold is exceeded. Wherein, a period of time can be a plurality of representative dates or time periods, such as dates or time periods that may cause a large change in temperature distribution data and heat source distribution data; the temperature difference threshold can be preset based on construction experience, etc.

[0079] In some embodiments, the processor may determine a wall position where the temperature difference exceeds a temperature difference threshold, or the number of times the temperature difference exceeds the temperature difference threshold is greater than a preset number of times as a potential crack occurrence position, wherein the preset number of times may be set by the system by default. Further, based on the temperature difference size at the potential crack occurrence position, and the number of times the temperature difference exceeds the temperature difference threshold, the corresponding crack development level is determined. For example, based on construction experience, the processor may preset corresponding crack development levels for different temperature difference sizes and the number of times the temperature difference exceeds the temperature difference threshold in advance, and when determining the temperature difference size at the potential crack occurrence position, and the number of times the temperature difference exceeds the temperature difference threshold, directly obtain the corresponding preset crack development level as the crack development level at the position.

[0080] In some embodiments of the present specification, temperature distribution data and heat source distribution data are obtained by a thermal imaging device, so that the accuracy of the obtained temperature distribution data and heat source distribution data can be improved; the potential occurrence location and crack development level caused by excessive temperature difference can be predicted based on the temperature distribution data and heat source distribution data, and the prediction can be made based on the temperature difference at each position of the insulation wall panel, so that the result is more accurate.

[0081] In some embodiments, the potential location of cracks and the crack development level can be predicted by a first model, and the first model is a machine learning model. In some embodiments, the first model may include a first embedding layer for processing thermal imaging data to determine temperature distribution data and heat source distribution data; a temperature difference layer for processing temperature distribution data, heat source distribution data, environmental data, and material characteristics to determine temperature difference gradient prediction results; and a first prediction layer for processing temperature difference gradient prediction results, insulation wallboard feature distribution, and environmental data to determine crack probability distribution and their corresponding crack development levels.

[0082] In some embodiments, the first model may include at least one of a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), or other custom networks.

[0083] Figure 4 is an exemplary schematic diagram of predicting crack probability and corresponding crack development level based on the first model according to some embodiments of this specification. Figure 4 As shown, the first model may include a first embedding layer 420, a temperature difference layer 440, and a first prediction layer 460. In some embodiments, the network structures of the first embedding layer 420 and the temperature difference layer 440 may be CNN, and the network structure of the first prediction layer 460 may be NN.

[0084] In some embodiments, the input of the first embedded layer 420 may be thermal imaging data 410, and the output may be temperature distribution data 432 and heat source distribution data 434. For more information about the thermal imaging data 410, the temperature distribution data 432, and the heat source distribution data 434, see Figure 2 and its related description.

[0085] In some embodiments, the input of the temperature difference layer 440 may be temperature distribution data 432, heat source distribution data 434, material characteristics 436, and environmental data 438, and the output may be a temperature difference gradient prediction result 452. The temperature gradient prediction result 452 output by the temperature difference layer 440 is a prediction result when the temperature change exceeds the change threshold and the temperature reaches the temperature extreme value, discarding data with small or almost no temperature change, reducing useless data from a large amount of data, and reducing the data processing pressure of the model. Among them, the change threshold and the temperature extreme value can be based on construction experience or system default settings.

[0086] The material features 436 may include the material features of the insulation wallboard and the material features of the exterior wall decoration, which may be determined based on information such as the quality parameters of the insulation wallboard and the quality parameters of the exterior wall decoration material, wherein the material features of the insulation wallboard may include the material type, thickness, and size of the insulation wallboard. Different insulation wallboard materials and different exterior wall decoration materials have different heat absorption and heat release capabilities. Using the material features as the input of the temperature difference layer 440 takes into account the heat absorption and heat release capabilities of different materials, which can improve the accuracy of the predicted temperature difference gradient prediction result 452.

[0087] The temperature gradient prediction result 452 may refer to the temperature gradient of a certain position of the wall of the target building relative to the adjacent positions. The temperature gradient may be determined by taking the maximum value of the temperature gradient difference between the position and the adjacent positions. For more information about the environmental data 438, see Figure 2 and its related description.

[0088] In some embodiments, the input of the first prediction layer 460 may be the temperature gradient prediction result 452, the insulation wall panel feature distribution 454 and the environmental data 438, and the output is the crack probability distribution and the corresponding crack development level 470. Among them, the insulation wall panel feature distribution 454 may refer to the characteristics of the insulation wall panels at various positions of the wall of the target building, and the insulation wall panel feature distribution may be represented by the insulation wall panel feature matrix, and each element in the matrix is ​​the thickness and size information of the insulation wall panels at the corresponding position of the divided wall grid. The crack probability distribution may refer to the probability of cracks occurring at various positions of the wall of the target building, and may be represented by the crack probability distribution matrix, and each element in the matrix is ​​the crack probability at the position corresponding to the divided wall grid; the corresponding crack development level may refer to the crack development level corresponding to the probability of cracks occurring at various positions of the wall of the target building, and similarly, it may also be represented by the crack development level matrix, and each element in the matrix is ​​the crack development level at the position corresponding to the predicted wall grid.

[0089] In some embodiments, the first model can be obtained through training. In some embodiments, the first training sample for training the first model can be sample thermal imaging data, sample material features, sample insulation wall panel feature distribution, and sample environmental data of a sample insulation wall panel. In some embodiments, the first training sample can be preset, or it can be historical data of other installed insulation wall panels obtained by the processor. Among them, the historical data of other installed insulation wall panels can exist in two situations, that is, the historical data can include two situations: cracks occur at the same location and no cracks occur.

[0090] In some embodiments, the first label for training the first model may be the sample crack probability distribution and the corresponding sample crack development grade distribution of the sample insulation wallboard corresponding to the first training sample. The sample probability crack distribution and the sample crack development grade distribution may be represented by a sample crack distribution matrix and a sample crack development grade distribution matrix, respectively, and may be determined by the historical data of other laid insulation wallboards. For example, the position of the crack in the historical data of the sample insulation wallboard may be marked as 1, and the position without the crack may be marked as 0 to form a sample crack distribution matrix; and then the corresponding numerical value of the crack development grade corresponding to the position of the crack may be marked to form a sample crack development grade distribution matrix. Further, the processor may determine the sample crack probability distribution based on the sample crack distribution matrix. Exemplarily, the processor may determine the sample crack probability of the position based on the amount of data marked as 1 in the sample crack distribution matrix corresponding to the multiple first training samples and the sum of the data marked as 0 and 1 in the same position in the multiple first training samples (i.e., the total number of the first training samples), and then the sample crack probabilities of the multiple positions may constitute the sample crack probability distribution.

[0091] In some embodiments, the processor can input the sample thermal imaging data into the initial first embedding layer to obtain the initial temperature distribution data and the initial heat source distribution data; input the initial temperature distribution data, the initial heat source distribution data, the sample material characteristics and the sample environment data into the initial temperature difference layer to obtain the initial temperature difference gradient prediction result; input the initial temperature difference gradient prediction result, the sample insulation wall characteristics and the sample environment data into the initial first prediction layer to obtain the initial crack probability distribution and the corresponding initial crack development level distribution. Based on the initial crack probability distribution and the corresponding initial crack development level distribution and the first label, a loss function is constructed, and the parameters of the initial first embedding layer, the initial temperature difference layer and the initial first prediction layer are synchronously updated based on the loss function, and the trained first model is obtained through parameter update.

[0092] In some embodiments of the present specification, by using a first model to process the thermal imaging data of the target building wall, the surrounding environmental data, the material characteristics, and the insulation wall panel characteristics, the self-learning ability of the machine learning model can be used to find patterns from various data that may affect the occurrence of cracks in the insulation wall panels, thereby improving the efficiency of prediction and the accuracy of the prediction results.

[0093] In some embodiments, when the first model is trained, the loss function may include a gradient loss term and a crack loss term, and the weight of the crack loss term is positively correlated with the crack distribution variance of the training data. The gradient loss term corresponds to the temperature difference layer, and the crack loss term corresponds to the first prediction layer.

[0094] The gradient loss term may refer to a loss function constructed based on the initial temperature difference gradient prediction result output by the initial temperature difference layer and the corresponding temperature difference gradient label. The temperature difference gradient label may refer to the actual temperature difference gradient characteristics of the wall of the target building corresponding to the initial temperature distribution data, initial heat source distribution data, sample material characteristics and sample environment data when the temperature difference layer in the first model is trained separately.

[0095] The crack loss term may refer to a loss function constructed based on the initial crack probability distribution output by the initial first prediction layer and the corresponding initial crack development level distribution and the first label.

[0096] The crack distribution variance can refer to a parameter used to measure whether the crack distribution in the training data is uniform. For example, when the crack distribution is relatively uniform, the difference between the crack conditions at various locations of the wall and the average value is relatively small, and the crack distribution variance is also relatively small; conversely, the crack distribution variance is relatively large.

[0097] In some embodiments, the weight of the crack loss term is positively correlated with the crack distribution variance of the training data. When the crack distribution variance in the training data is larger, the weight of the crack loss term is also correspondingly larger.

[0098] In some embodiments, when the weight of the crack loss term is positively correlated with the variance of the temperature distribution in the training data, when the variance of the temperature distribution in the training data is large, the weight of the gradient loss term is correspondingly large. The temperature distribution variance may refer to a parameter used to measure whether the temperature distribution in the training data is uniform. For example, if the temperature at each location of the wall in the training data is less different from the average value, the temperature distribution variance is also relatively small; otherwise, the temperature distribution variance is relatively large.

[0099] Cracks are greatly affected by accidental factors in construction, and some training data may be inaccurate. By determining different loss terms for the temperature difference layer and the first prediction layer, and determining the weight of the crack loss term based on the crack distribution variance in the training data, the impact of training data with common cracks or no cracks can be reduced to improve the accuracy and reliability of the model output.

[0100] In some embodiments of the present specification, temperature distribution data and heat source distribution data are determined based on thermal imaging data of the walls of the target building, and the locations of possible cracks in the insulation wall panels and the level of crack development are predicted based on the temperature distribution data and the heat source distribution data. Possible cracks in the insulation panels can be predicted in advance so that corresponding measures can be taken in advance, thereby improving the pertinence and efficiency of the insulation wall panel construction and reducing construction costs.

[0101] It should be noted that the above description of process 300 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0102] In some embodiments, the processor may predict the density of anchor bolts required for additional reinforcement corresponding to the potential crack occurrence location based on the potential crack occurrence location and the crack development level.

[0103] The additional reinforcement may refer to additional reinforcement of the insulation wall panels at the wall locations where cracks may occur. The anchor density required for the additional reinforcement may refer to the installation density of the anchors required when additional reinforcement is performed at the locations where cracks may potentially occur.

[0104] In some embodiments, the processor may predict the density of anchor bolts required for additional reinforcement corresponding to the potential location of crack occurrence based on the vector distance. In some embodiments, the processor may construct a feature vector based on the potential location of crack occurrence, the crack development level, and the height of the potential location of crack occurrence. In some embodiments, the processor may obtain multiple sets of historical data of the laid insulation wall panels, construct multiple historical vectors based on the historical crack locations, historical heights, and historical crack levels of the insulation wall panels in the multiple sets of historical data, and store the corresponding historical anchor bolt density in the historical data in association with each historical vector. In some embodiments, the processor may determine the vector distance between the feature vector and the multiple historical vectors, and determine the historical vector whose vector distance with the feature vector meets the preset distance condition as the reference vector. Among them, the preset distance condition may be the minimum vector distance, and the vector distance may be the cosine distance, the Euclidean distance, etc. In some embodiments, the processor may determine the historical anchor bolt density stored in association with the reference vector as the anchor bolt density required for additional reinforcement of the crack location of the insulation wall panels of the target building.

[0105] Figure 5 is an exemplary flow chart of predicting anchor density according to some embodiments of this specification. In some embodiments, process 500 can be executed by a smart gas equipment management platform. Figure 5 As shown, process 500 may include the following steps:

[0106] Step 510: predict the probability of cracking due to an increase in anchor density based on the predicted anchor densities at different locations.

[0107] The probability of cracking may refer to the probability or risk that cracks may occur in the insulation wall panels and exterior wall decorations after the exterior wall decoration construction is completed due to insufficient mortar bonding due to too many anchor bolts. For example, the cracks described here may include cracks, bulges, pores, etc. between the insulation wall panels, exterior wall decorations (such as tiles, coatings, etc.), and mortar bonding layers, and do not involve cracks in the original wall (such as rough wall). It should be understood that the cracks described here can be related to Figure 2 and Figure 3 The cracks described in the examples are different and may not be cracks in the same position.

[0108] In some embodiments, the processor can obtain multiple sets of historical data of other laid insulation wall panels with the same wall data, environmental data, and anchor density as the target building, determine the number of historical data where cracks occurred based on the historical data, and determine the ratio of the historical data to the total number of historical data as the cracking probability.

[0109] In some embodiments, the cracking probability can be predicted based on an anchor model, and the anchor model is a machine learning model. In some embodiments, the anchor model can include a first embedding layer, a second embedding layer, and a second prediction layer: the first embedding layer can be used to process thermal imaging data to determine temperature distribution data and heat source distribution data; the second embedding layer can be used to process anchor density at different locations and output density distribution characteristics; the second prediction layer can be used to process temperature distribution data, heat source distribution data, density distribution characteristics, and material characteristics to determine the cracking probability distribution. In some embodiments, the anchor model can share the first embedding layer with the first model.

[0110] In some embodiments, the anchor model may include at least one of a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), or other custom networks.

[0111] Figure 6 6 is an exemplary schematic diagram of predicting cracking probability based on an anchor model according to some embodiments of the present specification. In some embodiments, the anchor model may include a first embedding layer 620, a second embedding layer 650, and a second prediction layer 680, wherein the first embedding layer 620 may be shared with the first model. In some embodiments, the network structure of the first embedding layer 620 may be a CNN, and the network structures of the second embedding layer 650 and the second prediction layer 680 may be NN.

[0112] In some embodiments, the input of the first embedded layer 620 may be thermal imaging data 610, and the output may be temperature distribution data 632 and heat source distribution data 634. For more information about the thermal imaging data 610, the temperature distribution data 632, and the heat source distribution data 634, see Figure 2 and its related description.

[0113] In some embodiments, the input of the second embedded layer 650 may be the density of anchor bolts 640 at different positions of the insulation wall panel, and the output may be the density distribution feature 660. For more information about the density of anchor bolts 640, see Figure 5 The density distribution feature 660 may refer to the density distribution of anchor bolts at different positions of the insulation wallboard, including the density of the anchor bolts, the number of the anchor bolts, and the like.

[0114] In some embodiments, the input of the second prediction layer 680 may be the temperature distribution data 632, the heat source distribution data 634, the density distribution feature 660 and the material feature 670, and the output may be the crack probability distribution 690 of different positions of the insulation wallboard. For more information about the material feature 670, please refer to Figure 4 and its related description; for more information on cracking probability distribution 690, see Figure 5 and its related description.

[0115] In some embodiments, the anchor model can be obtained through training. In some embodiments, the second training sample for training the anchor model can be sample thermal imaging data, anchor density at different positions of the sample insulation wallboard, and sample material characteristics. In some embodiments, the second training sample can be preset, or it can be historical data of other laid insulation wallboards obtained by the processor. The second training sample data is the data of the entire wall, and there can be two situations, that is, some positions of the wall are cracked, and some positions are not cracked.

[0116] In some embodiments, the second label for training the anchor model may be the actual cracking probability of each position of the insulation wallboard corresponding to the second training sample. The second training label may be represented as a sample cracking probability distribution matrix, which may be preset based on construction experience or obtained by manual annotation. For example, the processor may mark the cracked positions in each group of second training samples as 1 and the uncracked positions as 0 to form a sample cracking distribution matrix. Furthermore, the processor may determine the sample cracking probability of the position as the ratio of the number of positions marked as 1 in all second training samples to the sum of the data marked as 0 and 1 in the same position in all second training samples (i.e., the total amount of second training samples). By the same method, the sample cracking probabilities of all positions of the wall in the second training sample are determined to form a sample cracking probability distribution matrix.

[0117] In some embodiments, the processor can input the sample thermal imaging data into the initial first embedding layer to obtain the initial temperature distribution data and the initial heat source distribution data; input the anchor density of different positions of the sample insulation wallboard into the initial second embedding layer to obtain the initial density distribution characteristics; input the initial temperature distribution data, the initial heat source distribution data and the initial density distribution characteristics into the initial second prediction layer to obtain the initial cracking probability distribution. A loss function is constructed based on the initial cracking probability distribution and the second label, and the parameters of the initial first embedding layer, the initial second embedding layer and the initial second prediction layer are synchronously updated using the loss function. Through parameter updating, a trained anchor model is obtained.

[0118] In some embodiments, the first embedding layer can be obtained by training a temperature anomaly model. The temperature anomaly model can include a first embedding layer and an anomaly layer. The first embedding layer has thermal imaging data as input and temperature distribution data and heat source distribution data as output. The anomaly layer has temperature distribution data and heat source distribution data as input and temperature anomaly points in the input thermal imaging image as output. For details about thermal imaging data, temperature distribution data and heat source distribution data, please refer to Figure 2 and its related description.

[0119] The location point of temperature anomaly may refer to a location (area) in the thermal imaging image generated by the thermal imaging data where the temperature difference is large or the temperature changes frequently. In some embodiments, the processor may Figure 3 , Figure 4 The thermal imaging image is divided into grids using the same method. Each grid corresponds to a position point and a matrix element. The grid data corresponding to the position point of the temperature anomaly output by the abnormal layer can be marked as 1, and the data of other grids can be marked as 0 to form a temperature anomaly matrix, which is used as the output result representation of the abnormal layer.

[0120] In some embodiments, the first embedding layer and the abnormal layer of the temperature anomaly model can be obtained by joint training. In some embodiments, the third training sample of the joint training can be sample thermal imaging data, which can be determined by preset; the third training label is the point of temperature anomaly in the sample thermal imaging image formed by the sample thermal imaging data, which can be obtained by manual annotation. In some embodiments, the processor can input the sample thermal imaging data into the initial first embedding layer to obtain initial temperature distribution data and initial heat source distribution data; input the initial temperature distribution data and the initial heat source distribution data into the initial abnormal layer to obtain the position point of the initial temperature anomaly. A loss function is constructed based on the position point of the initial temperature anomaly and the position point of the actual temperature anomaly, and the parameters of the initial first embedding layer and the initial abnormal layer are synchronously updated using the loss function. Through parameter update, the trained first embedding layer and abnormal layer are obtained.

[0121] In some embodiments of the present specification, the first embedding layer is obtained by training the temperature anomaly model, which can avoid the problem that the training labels are difficult to obtain when the first embedding layer is trained alone.

[0122] In some embodiments, the trained first embedding layer can be applied to both the first model and the anchor model.

[0123] In some embodiments of the present specification, the thermal imaging data, the anchor density and material characteristics at different positions of the insulation wall panels are processed by training the anchor model to determine the cracking probability at different positions of the insulation wall panels. The self-learning ability of the machine learning model can be used to find the relationship between the cracking probability of the insulation wall panels and the thermal imaging data, the anchor density and the material characteristics in a large amount of data, thereby improving the data processing efficiency and the accuracy of the prediction.

[0124] Step 520 , determining a final anchor density based on the cracking probability.

[0125] In some embodiments, the processor may preset corresponding anchor density for various cracking probabilities in advance. In some embodiments, the processor may determine the corresponding preset anchor density as the final anchor density based on the predicted cracking probability.

[0126] In some embodiments, the processor may compare the cracking probability with a probability threshold, and in response to the cracking probability being greater than the probability threshold, reduce the density of anchor bolts at the corresponding position; the reduction amplitude is proportional to the cracking probability.

[0127] The probability threshold may refer to a threshold condition that a pre-set probability of cracking needs to meet. For example, the probability threshold may be 80%, 85%, etc. In some embodiments, the probability threshold may be determined based on construction experience.

[0128] In some embodiments, in response to the probability of cracking being greater than the probability threshold, the processor may reduce the density of the anchor bolts at the corresponding position based on the reduction amplitude. In some embodiments, the reduction amplitude may be determined based on the probability of cracking. In some embodiments, the processor may preset the corresponding reduction amplitude for each probability of cracking in advance. For example, when the probability of cracking is 50%, the preset corresponding reduction amplitude is reduced by 5%; when the probability of cracking is 80%, the preset reduction amplitude is reduced by 10%, etc. Exemplarily, assuming that the probability of cracking is 90%, which is greater than the probability threshold of 85%, the processor may reduce the density of the anchor bolts at the corresponding position based on the preset reduction amplitude; assuming that when the probability of cracking is 90%, the corresponding preset reduction amplitude is reduced by 12%, then the processor may correspondingly reduce the density of the anchor bolts at the position by 12%.

[0129] In some embodiments of the present specification, the anchor density at the corresponding position is lowered based on the probability of cracking. While considering increasing the anchor density to provide additional reinforcement for the insulation wall panels to prevent cracks, the effect of a larger anchor density on the bonding performance of the insulation board, exterior wall decoration and mortar is also considered. By appropriately reducing the anchor density, other cracking risks can be avoided.

[0130] In some embodiments, the processor may determine the density of anchors required for additional reinforcement based on thermal bridging effects at different locations.

[0131] The thermal bridge effect may refer to the physical effect of heat conduction caused by the large temperature difference between the inside and outside of the insulation wall panel. The thermal bridge effect may cause condensation, mold, or even dripping of the insulation wall panel. In some embodiments, the processor may determine whether a thermal bridge effect will occur at each location based on the temperature, humidity, and heat at each location of the wall of the target building, and determine the extent of the thermal bridge effect. For example, the processor may determine whether a thermal bridge effect will occur and the extent of the thermal bridge effect based on the temperature, humidity, and heat at each location of the wall of the target building according to construction experience.

[0132] In some embodiments, the processor may determine the anchor density required for additional reinforcement based on the degree of thermal bridge effect at different locations of the thermal insulation wall panel. In some embodiments, the processor may preset corresponding anchor densities for different degrees of thermal bridge effect in advance based on construction experience. When the degree of thermal bridge effect at each location of the thermal insulation wall panel is determined, the corresponding anchor density may be directly obtained.

[0133] In some embodiments, the processor may determine the final anchor density based on weighted subtraction of thermal bridge effects at different locations from anchor density; the weight of the weighted subtraction is proportional to the severity of the hazard caused by the thermal bridge effect.

[0134] In some embodiments, the processor may determine the final anchor density by weighted subtraction of thermal bridge effects at different locations from the anchor density based on the following formula (1).

[0135] C = α*A-β*B (1) Wherein, A is the anchor density required for additional reinforcement corresponding to the predicted potential crack occurrence location based on the potential crack occurrence location and the crack development level; B is the thermal bridge effect influencing factor; α and β are weight coefficients; C is the final anchor density. In some embodiments, the thermal bridge effect influencing factor B can be determined by preset. For example, the processor can preset the corresponding thermal bridge effect influencing factors for different degrees of thermal bridge effects in advance based on the calculation requirements.

[0136] In some embodiments, the processor may determine a weight coefficient corresponding to the thermal bridge effect based on the severity of the harm caused by the thermal bridge effect. The higher the severity of the harm caused by the thermal bridge effect, the greater the corresponding weight coefficient (ie, β).

[0137] Some embodiments of this specification determine the anchor density required for the final additional reinforcement by combining the thermal bridge effect, taking into account the impact of the thermal bridge effect caused by the anchors. When the thermal bridge effect is predicted to be more serious, the anchor density is appropriately reduced to avoid affecting the wall insulation effect, thereby meeting user needs.

[0138] In some embodiments of the present specification, by predicting the density of anchor bolts required for additional reinforcement corresponding to potential crack occurrence locations based on potential crack occurrence locations and crack development levels, it is possible to carry out targeted reinforcement of the insulation wall panels that may be affected by potential cracks, thereby improving the targeted construction of the insulation wall panels and improving construction efficiency; by predicting the probability of cracking at different locations of the insulation wall panels and adjusting the density of anchor bolts at corresponding locations of the insulation wall panels based on the cracking probability, other cracking hazards caused by the density of anchor bolts can be avoided.

[0139] It should be noted that the above description of process 500 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 500 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0140] One of the embodiments of the present specification also provides a construction device for an insulation wall, comprising at least one processor and at least one memory, wherein the at least one memory stores computer instructions; the at least one processor is used to execute part of the computer instructions to implement the construction method for the insulation wall described in any one of the embodiments of the present specification.

[0141] One of the embodiments of this specification also provides a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the insulation wall construction method described in the embodiment of this specification.

[0142] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) by predicting suspected crack information of the insulation wall panels of the target building based on the wall data and environmental data of the target building, the insulation wall panels at the locations where cracks may occur can be additionally reinforced in advance. If it is predicted that cracks will not occur or the cracks do not meet the preset conditions, the construction personnel can be notified in time to carry out exterior wall decoration, which can improve the targeted reinforcement of the insulation wall panels of the target building, improve construction efficiency and reduce costs; (2) based on the thermal imaging data of the wall of the target building, the temperature distribution data and the heat source distribution data are determined, and then based on the temperature distribution data and the heat source distribution data, the insulation wall panels are predicted to have cracks. By predicting the location and development level of cracks in the insulation board, the possible occurrence of cracks in the insulation board can be predicted in advance, so that corresponding measures can be taken in advance to improve the pertinence and efficiency of the insulation wall panel construction and reduce construction costs; (3) by predicting the density of anchor bolts required for additional reinforcement at the potential crack location based on the potential crack location and crack development level, the impact of potential cracks on the insulation wall panel can be targeted and reinforced, thereby improving the pertinence of the insulation wall panel construction and improving construction efficiency; by predicting the cracking probability at different locations of the insulation wall panel and adjusting the anchor bolt density at the corresponding location of the insulation wall panel based on the cracking probability, other cracking hazards caused by the anchor bolt density can be avoided.

[0143] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0144] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0145] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0146] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0147] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0148] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0149] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for constructing an insulation wall, characterized in that: The method is executed by a processor of a terminal where the construction APP is located, and includes: Determining the construction stage of the thermal insulation wall based on the monitoring image acquired by the monitoring device; In response to the construction stage being the stage of laying thermal insulation wall panels, acquiring wall data of the target building based on a database, and acquiring thermal imaging data of the wall of the target building based on an infrared camera; the wall data at least includes the size, thickness, and type of the wall; Acquire environmental data around the target building; the environmental data at least includes weather, temperature, humidity, and light; Based on the wall data and the environmental data, predicting suspected crack information between multiple insulation wall panels on the wall surface includes: determining temperature distribution data and heat source distribution data based on the thermal imaging data; predicting potential crack occurrence locations and crack development levels based on the temperature distribution data and the heat source distribution data in combination with the wall data; the determining the temperature distribution data and the heat source distribution data based on the thermal imaging data includes: acquiring the temperature distribution data and the heat source distribution data of the current wall based on a thermal imaging device; the predicting the potential crack occurrence locations and crack development levels based on the temperature distribution data and the heat source distribution data in combination with the wall data includes: predicting the potential crack occurrence locations and the crack development levels using a first model; the first model includes a first embedded layer, a temperature difference layer and a first prediction layer, and the first embedded layer includes a temperature difference layer and a first prediction layer. The input of an embedding layer includes the thermal imaging data, the output of the first embedding layer includes the temperature distribution data and the heat source distribution data, the input of the temperature difference layer includes the temperature distribution data, the heat source distribution data, material characteristics and the environmental data, the output of the temperature difference layer includes a temperature difference gradient prediction result, the input of the first prediction layer includes the temperature difference gradient prediction result, the insulation wallboard characteristic distribution and the environmental data, the output of the first prediction layer includes a crack probability distribution and the crack development levels corresponding thereto, the loss function during the training of the first model includes a gradient loss term and a crack loss term, and the weight of the crack loss term is positively correlated with the crack distribution variance of the training data; the suspected crack information includes a potential crack occurrence location and a crack development level where cracks may be generated subsequently; the wall surface is a flat layer coated with mortar; In response to the crack development level meeting a preset condition, sending additional reinforcement reminder information to construction personnel through the construction APP; the additional reinforcement reminder information includes the location of the crack that needs to be reinforced; In response to the crack development level not satisfying the preset condition, reminder information for exterior wall decoration construction is sent to the construction personnel via the construction APP.

2. The method according to claim 1, characterized in that The method further comprises: Based on the potential crack occurrence location and the crack development level, the density of anchor bolts required for additional reinforcement corresponding to the potential crack occurrence location is predicted.

3. The method according to claim 2, characterized in that The method further comprises: Based on the thermal bridge effects at different locations, the density of the anchor bolts required for the additional reinforcement is determined.

4. A construction system for an insulation wall, characterized in that: The system comprises: A first determination module, used to determine the construction stage of the thermal insulation wall based on the monitoring image acquired by the monitoring device; A first acquisition module is used for acquiring the wall data of the target building based on the database and acquiring the thermal imaging data of the wall of the target building based on the infrared camera in response to the construction stage being the stage of laying the thermal insulation wall panels; the wall data at least includes the size, thickness and type of the wall; A second acquisition module is used to acquire environmental data around the target building; the environmental data at least includes weather, temperature, humidity, and light; The second determination module is used to predict suspected crack information between multiple insulation wall panels on the wall surface based on the wall data and the environmental data, including: determining temperature distribution data and heat source distribution data based on the thermal imaging data; predicting potential crack occurrence locations and crack development levels based on the temperature distribution data and the heat source distribution data in combination with the wall data; the determination of the temperature distribution data and the heat source distribution data based on the thermal imaging data includes: acquiring the temperature distribution data and the heat source distribution data of the current wall based on a thermal imaging device; the prediction of the potential crack occurrence locations and crack development levels based on the temperature distribution data and the heat source distribution data in combination with the wall data includes: predicting the potential crack occurrence locations and the crack development levels using a first model; the first model includes a first embedded layer, a temperature difference layer and a first prediction layer. layer, the input of the first embedding layer includes the thermal imaging data, the output of the first embedding layer includes the temperature distribution data and the heat source distribution data, the input of the temperature difference layer includes the temperature distribution data, the heat source distribution data, material characteristics and the environmental data, the output of the temperature difference layer includes the temperature difference gradient prediction result, the input of the first prediction layer includes the temperature difference gradient prediction result, the insulation wallboard characteristic distribution and the environmental data, the output of the first prediction layer includes the crack probability distribution and the crack development level corresponding to it, the loss function during the training of the first model includes the gradient loss term and the crack loss term, and the weight of the crack loss term is positively correlated with the crack distribution variance of the training data; the suspected crack information includes the potential occurrence position of cracks that may generate cracks in the future and the crack development level; the wall surface is a flat layer coated with mortar; A first reminder module, configured to send additional reinforcement reminder information to construction personnel through a construction APP in response to the crack development level meeting a preset condition; the additional reinforcement reminder information includes a location where cracks need to be reinforced; The second reminder module is used to send reminder information of the exterior wall decoration construction to the construction personnel through the construction APP in response to the crack development level not satisfying the preset condition.

5. The system according to claim 4, characterized in that: The second determining module is further used for: Based on the potential crack occurrence location and the crack development level, the density of anchor bolts required for additional reinforcement corresponding to the potential crack occurrence location is predicted.

6. The system according to claim 5, characterized in that The second determining module is further used for: Based on the thermal bridge effects at different locations, the density of the anchor bolts required for the additional reinforcement is determined.

7. A construction device for an insulation wall, characterized in that: It comprises at least one memory and at least one processor; the at least one memory stores computer instructions, and the at least one processor is used to execute part of the computer instructions to implement the construction method of the insulation wall as described in any one of claims 1-3.

8. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the insulation wall construction method as described in any one of claims 1-3.

Images