Fabricated building performance rapid analysis system based on multi-dimensional parameters

Abstract

The invention relates to the field of data analysis, and provides a multi-dimensional parameter-based fabricated building performance rapid analysis system, which is characterized in that an acquisition module, a model input module and an analysis module are configured, a wind speed field cloud picture and a plurality of local pictures corresponding to each pre-constructed connecting piece acquired every set time length are combined with a differential neural network model, and the multi-dimensional parameter-based fabricated building performance rapid analysis system is obtained. The stability performance of the fabricated building is analyzed by calculating the difference, caused by the real-time wind field, of all local diagrams of the pre-constructed connecting pieces, and a new evaluation mode for the stability performance of the fabricated building is provided.

Description

Technical Field

[0001] The present application relates to the field of data analysis, and more specifically, to a rapid analysis system for prefabricated building performance based on multi-dimensional parameters. Background Art

[0002] Prefabricated buildings are buildings that transfer a large amount of on-site work in traditional construction methods to factories, where building components and accessories (such as floor slabs and wall panels, etc.) are processed and manufactured in factories, transported to construction sites, and assembled and installed on site through reliable connection methods. Prefabricated buildings include multiple different types of foundation components and a variety of corresponding prefabricated connectors, such as reinforced concrete connectors, steel structure connectors, and connectors between precast concrete exterior walls and main structures. Since most of the current buildings are high-rise, the wind force is relatively large for high-rise buildings, especially for the top prefabricated components of high-rise buildings. Generally, the top of high-rise buildings will vibrate or sway under the action of wind to avoid excessive rigidity leading to floor fractures, but the vibration amplitude should be within the standard range. If the vibration amplitude is too large, there will be stability problems, which will lead to safety hazards. Therefore, it is necessary to provide a solution for the performance analysis of prefabricated buildings for high-rise buildings. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the present application provides a rapid analysis system of prefabricated building performance based on multi-dimensional parameters to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above-mentioned purpose, the present application provides a prefabricated building performance rapid analysis system based on multi-dimensional parameters, wherein the multi-dimensional parameters include a plurality of local images and a wind speed field cloud image corresponding to each prefabricated connection member, wherein the plurality of local images are obtained by photographing the corresponding prefabricated connection member with a plurality of fixed-angle cameras at fixed positions, and the prefabricated building performance rapid analysis system based on multi-dimensional parameters includes: An acquisition module, which acquires a wind speed field cloud map of the prefabricated building to be analyzed and a plurality of local maps corresponding to each prefabricated connection member collected at set intervals, wherein the plurality of local maps are obtained by photographing the corresponding prefabricated connection members by multiple fixed-angle cameras at fixed positions; A model input module inputs all local images collected by each prefabricated connector at each sampling time into a difference neural network model corresponding to the prefabricated connector, and outputs the deviation degree from the standard image at each sampling time; The analysis module analyzes and determines the stability performance of the prefabricated building according to the deviation at each sampling moment and the wind speed field cloud map for the prefabricated connection parts.

[0005] Optionally, the difference neural network model includes a channel attention mechanism network, an image cropping layer, a convolutional network and a comparison layer; The input of the channel attention mechanism network is each local image, and the output is used as the input of the image cropping layer. The image cropping layer outputs the image after removing the feature channels with weight coefficients lower than the set threshold, and inputs it to the convolutional network. The output of the convolutional network is used as the input of the comparison layer, which is pre-configured with a standard image of the corresponding pre-constructed connector.

[0006] Optionally, the convolutional network specifically includes: multiple convolutional layers and multiple pooling layers, wherein, during the testing process of the difference neural network model, when multiple test data with a difference lower than a set threshold are sequentially input into the difference neural network model, part of the nodes of any one or more convolutional layers are solidified each time until the output difference of the convolutional network before and after solidification is within a set range, at which time the solidified nodes are output, and the above steps are iteratively performed until all similar training data have been trained or the set solidification ratio is reached, and the final convolutional network is output.

[0007] Optionally, the prefabricated building performance rapid analysis system further includes: A model pre-optimization module, wherein the model pre-optimization module comprises: A removal unit randomly removes nodes of any convolutional layer in the convolutional network, and replaces the removed nodes with nodes with a weight of zero, and re-tests the same test data before and after the removal, and updates the convolutional network if the difference in the test results is within a standard range; The updating unit replaces the initial convolutional network with the updated convolutional network, and trains the convolutional network using the training data to obtain a final convolutional network.

[0008] Optionally, the prefabricated building performance rapid analysis system further includes: A model pre-optimization module, wherein the model pre-optimization module comprises: Deletion unit, randomly remove nodes of any convolutional layer in the convolutional network, and replace the removed nodes with nodes with zero weight, re-test the same test data before and after the removal, and update the convolutional network if the difference in test results is within the standard range; The explosion unit randomly takes at least one node in at least one convolution layer in the updated convolution network as a standard node, adds at least one node according to the weight of the standard node, and inserts it into the corresponding convolution layer; wherein the number of deleted nodes is greater than the number of added nodes.

[0009] Optionally, the model pre-optimization module further includes: An image segmentation layer, wherein the image segmentation layer is used to segment the local image into a plurality of sub-images; The image splicing layer, for each of the three adjacent sub-images, inserts the starting N columns of the first sub-image before the first column of the sub-image in the middle, and inserts the last M columns of the last sub-image after the last column of the sub-image in the middle, regenerates the sub-image in the middle, replaces the local image, and inputs it into the convolution layer.

[0010] Optionally, the model pre-optimization module further includes: An image division layer randomly divides the local image into a plurality of regions, each of which has the same or different size, and the size of the largest region is constrained within a preset range; The image deletion layer randomly deletes one or more of the regions, and performs a zero-filling operation on part of the region to form an updated local map, and replaces the current local map to input into the convolution layer. If the deviation change rate of the output corresponding to the same test data is higher than the standard threshold, the deleted area is restored and the random deletion operation is performed again until the deviation change rate of the output corresponding to the same test data is lower than the standard threshold, and the current updated local map is retained as the final input of the convolution layer.

[0011] Optionally, the analysis module includes: An alignment unit, for each prefabricated connection, superimposes a preset time offset and a sampling time to calibrate the alignment sampling time and the time coordinate in the wind speed field cloud map; A search unit, for the aligned sampling moment, searches the wind field state data at the corresponding moment from the wind speed field cloud map; The determination unit analyzes and determines the stability performance of the prefabricated building based on the wind field state data and the corresponding deviation data at the sampling moment after the alignment.

[0012] Optionally, the wind field state data includes wind speed and wind direction of each unit area in the spatial area, and the determining unit includes: The comprehensive wind field determination subunit determines, for each prefabricated connector, the comprehensive wind direction and comprehensive wind force in the spatial area according to the spatial area where the prefabricated connector is located and the wind speed and wind direction of each unit area; A sorting subunit determines the wind direction influence sorting of all local images according to the comprehensive wind direction and the shooting angle of the fixed-angle camera; A weight coefficient generating subunit dynamically generates a deviation weight coefficient of each local graph according to the wind direction influence ranking; The subunits are determined, and the stability performance of the prefabricated building is analyzed and determined according to the deviation weight coefficient of each local graph and the deviation of each local graph, combined with the comprehensive wind force at the corresponding time point.

[0013] Optionally, the determining subunit includes: According to the comprehensive wind force and the initial standard wind force, the deviation weight coefficient of the corresponding time point is re-determined, wherein if the comprehensive wind force is greater than the initial standard wind force, the deviation weight coefficient of the local map corresponding to the first K1 position in the wind direction influence ranking is reduced, wherein the ratio of the reduction amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force, and the deviation weight coefficient of the local map corresponding to the last K2 position in the wind direction influence ranking is increased, wherein the ratio of the increase amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force. The ratio of the difference in wind force to the initial standard wind force; if the comprehensive wind force is less than the initial standard wind force, the deviation weight coefficient of the local map corresponding to the first K1 positions in the wind direction influence ranking is increased, wherein the ratio of the increase to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force, and the deviation weight coefficient of the local map corresponding to the last K2 positions in the wind direction influence ranking is reduced, wherein the ratio of the reduction to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force; A weighted average calculation is performed based on the final deviation weight coefficient of each local graph and the deviation of each local graph, and the final deviation of the prefabricated connector is output; The stability performance of the prefabricated building is determined according to the final deviation of all prefabricated connecting parts and the position of each prefabricated connecting part.

[0014] Technical effects of this application: The present application provides a rapid analysis system for the performance of prefabricated buildings based on multi-dimensional parameters. By configuring an acquisition module, a model input module and an analysis module, the system uses a wind speed field cloud map and multiple local maps corresponding to each prefabricated connector collected at set time intervals, combined with a difference neural network model, to analyze the stability performance of the prefabricated building by calculating the differences in each local map of the prefabricated connector caused by the real-time wind field, thereby providing a new method for evaluating the stability performance of prefabricated buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a scenario in an embodiment of the present application; Figure 2 A schematic diagram of the system structure in an embodiment of the present application; Figure 3This is a schematic diagram of the channel attention mechanism network processing in an embodiment of the present application; Figure 4 Schematic diagram of the principle of convolution layer solidification in the embodiment of the present application; Figure 5 This is a schematic diagram of image stitching in an embodiment of the present application; Figure 6 Schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0016] In the technical field of the present application, when the technical solutions of the embodiments of the present application are described in conjunction with the accompanying drawings, it will be found that the embodiments discussed only constitute a part of all the embodiments of the present application but not the entire scope. In view of the diversity of the embodiments of the present application, other relevant embodiments that can be obtained by ordinary technicians in this field based on the existing embodiments without creative labor investment are within the protection limit set by the present application.

[0017] Since prefabricated components are assembled on site, the stability of prefabricated buildings needs to be evaluated after they are built, especially the stability evaluation of the top area of ​​high-rise buildings. At this time, the construction equipment has not yet been evacuated and needs to be evacuated after the stability is confirmed to be qualified. At present, the assessment of stability is mostly based on long-term observation to obtain the difference, and then the difference is compared to determine its stability. It takes a long time, often several months, which seriously affects the progress of the construction period.

[0018] Based on this, the present application has found that the structure of prefabricated components is complex, and most of the prefabricated components are fixedly connected to multiple other prefabricated components. Even if they are observed for a long time, there are serious problems with the measurement accuracy due to the small difference. The present application cleverly performs local analysis on the connectors of the prefabricated components, installs a fixed-angle camera on the construction equipment that has not yet been evacuated or on the building body, and then uses the fixed-angle camera to capture local images of the prefabricated connectors at various angles and directions. By performing pixel-level comparison on the images, the deviation is magnified, and the stability performance of the building can be measured more accurately without the need for long-term observation.

[0019] like Figure 1 The schematic diagram of the scene architecture applicable to the present application is shown. It should be noted that the building of the present application is a high-rise building 1. Generally speaking, the height of the high-rise building 1 can be greater than 60 meters, and the present application does not impose any restrictions on this. The camera 3 with a fixed angle and a fixed orientation in the embodiment of the present application can be installed on construction equipment 2 such as lifting equipment, tower crane equipment, construction elevators, etc., and can also be installed on the main body of the high-rise building 1, such as the walls, beams or other main structures of the high-rise building 1, and the present application does not impose any restrictions on this.

[0020] See also Figure 2 As shown, an embodiment of the present application provides a system for rapid analysis of prefabricated building performance based on multi-dimensional parameters.

[0021] It should be noted that the multi-dimensional parameters of the present application include multiple local images and wind speed field cloud images corresponding to each prefabricated connector. The local images correspond to image visual parameters, and the wind speed field cloud images correspond to wind field parameters. The multiple local images are obtained by shooting the corresponding prefabricated connectors with multiple fixed-angle cameras at fixed positions. The positions and configuration angles of the cameras are shown in FIG. Figure 1 As shown, this application will not elaborate on this.

[0022] Combine the following Figure 2 The embodiments of the present application are described in detail. Figure 2 As shown, the multi-dimensional parameter-based rapid analysis system for prefabricated building performance includes: An acquisition module 10 is used to acquire a wind speed field cloud map of the prefabricated building to be analyzed and a plurality of local maps corresponding to each prefabricated connection member collected at set intervals, wherein the plurality of local maps are obtained by photographing the corresponding prefabricated connection member with a plurality of fixed-angle cameras at fixed positions; The model input module 20 inputs all the local images collected by each prefabricated connection component at each sampling time into the difference neural network model corresponding to the prefabricated connection component, and outputs the deviation degree from the standard image at each sampling time; The analysis module 30 analyzes and determines the stability performance of the prefabricated building according to the deviation at each sampling moment and the wind speed field cloud map for the prefabricated connection parts.

[0023] In an optional embodiment, the difference neural network model includes a channel attention mechanism network, an image cropping layer, a convolutional network and a comparison layer; The input of the channel attention mechanism network is each local image, and the output is used as the input of the image cropping layer. The image cropping layer outputs the image after removing the feature channels with weight coefficients lower than the set threshold, and inputs it to the convolutional network. The output of the convolutional network is used as the input of the comparison layer, which is pre-configured with a standard image of the corresponding pre-constructed connector.

[0024] It should be emphasized that the wind speed field cloud map of the present application can be obtained through public channels or through corresponding wind speed equipment testing. The wind speed field cloud map can display the corresponding wind speed size through different colors or different grayscales, and display the corresponding wind direction through flow direction. Since the wind speed field cloud map belongs to public information in this field, no further graphical display is given for this.

[0025] It should be noted that the implementation process of the channel attention mechanism network of this application is as follows: (1) Squeeze (Fsq): Through global average pooling, the two-dimensional features (H*W) of each channel are compressed into 1 real number, and the feature map is transformed from [h, w, c] ==> [1,1,c].

[0026] (2) excitation (Fex): Generate a weight value for each feature channel and build the correlation between channels through two fully connected layers. The number of output weight values ​​is the same as the number of channels in the input feature map, [1,1,c] ==> [1,1,c].

[0027] (3) Scale (Fscale): Add the normalized weight obtained above to the features of each channel. This application can use multiplication, multiplying each channel by the weight coefficient, [h,w,c]*[1,1,c]==>[h,w,c].

[0028] Please combine the following Figure 3 , this application uses the SE attention mechanism in EfficientNet to illustrate this process: squeeze operation: The feature map is globally averaged pooled and compressed into a feature vector [1, 1, c].

[0029] Excitation operation: FC1 layer + Swish activation + FC2 layer + Sigmoid activation. Through the fully connected layer (FC1), the channel dimension of the feature map vector is reduced to the original 1 / r, that is, [1,1,c*1 / r]; then it passes through the Swish activation function; and then passes through a fully connected layer (FC2) to increase the feature map of the feature map vector back to the original [1,1,c]; and then it is converted into a normalized weight vector between 0 and 1 through the sigmoid function.

[0030] Scale operation: multiply the normalized weights and the original input feature map channel by channel to generate a weighted feature map.

[0031] It should be noted that the channel attention mechanism network of the present application adopts the existing network structure. The technical contribution of the present application to the prior art is not to provide a specific network architecture, but to cleverly select the channel attention mechanism network to cooperate with the image cropping layer to crop the input image, thereby reducing the amount of data input to the convolutional network, thereby reducing the amount of data processing while ensuring obvious features, and achieving the effect of rapid analysis. At the same time, one of the core concepts of the present application is to increase the difference in deviation through feature enhancement, thereby amplifying the stability difference and solving the problem that the current stability analysis requires long-term monitoring.

[0032] The following focuses on a detailed description of the convolutional network of this application.

[0033] In an optional embodiment, if Figure 4 As shown, it should be noted that Figure 4 The number of nodes and layers shown in the figure are only for illustration. The number of nodes and layers of the actual convolutional network is much larger than the number of nodes and layers shown in the figure. This application does not elaborate on this. Specifically, the convolutional network specifically includes: multiple convolutional layers and multiple pooling layers. During the testing of the difference neural network model, when multiple test data with a difference lower than a set threshold are sequentially input into the difference neural network model, part of the nodes of any one or more convolutional layers are solidified each time until the output difference of the convolutional network before and after solidification is within the set range. At this time, the solidified nodes are output, and the iterative operation of the above steps is performed until all similar training data have been trained or the set solidification ratio is reached, and the final convolutional network is output.

[0034] In the embodiment of the present application, the convolution layer uses similar test data as input in the testing phase of the model and "randomly" solidifies some nodes, so that it can converge faster during model training without the need for model training, thereby reducing the number of model training times.

[0035] Furthermore, the setting values ​​such as the setting range of the present application can be obtained based on experience or experimental demonstration. For example, the setting range of the present embodiment can be controlled within 5%. In this way, on the one hand, the number of model training times can be reduced, and only unsolidified nodes are updated during the training process. On the other hand, in the subsequent model prediction process, although the solidified nodes are randomly selected, they have undergone difference verification, which means that the importance of the node has been confirmed, indicating that the importance of the unsolidified nodes is relatively low. At this time, by solidifying the important nodes, the weights can be prevented from being destroyed, thereby ensuring the accuracy of the data.

[0036] It should be noted that, for the local image of the prefabricated connector collected in the embodiment of the present application, there is almost no difference in its overall color and material, so the difference or deviation is difficult to be highlighted, and it is difficult to analyze by conventional means. The present application finds that when some parts of the prefabricated connector are offset, the pixels of other objects will inevitably be introduced due to the fixed shooting angle of the camera. For example, when the prefabricated connector is offset to the left by 5 mm, then correspondingly, in its local image, the 5 mm area on the right may be a view of other parts of the prefabricated connector. Although its color and material are difficult to be different, its surface morphology, stripes, etc. will be different. On the other hand, it may be other prefabricated components or no other objects. At this time, the color, surface, etc. in the 5 mm area on the right will have a large difference. It can be seen that when the prefabricated connector is in different situations, the importance of the feature dimensions is different. The present application combines the channel attention mechanism network and the convolutional network configuration solidification node method to ensure the importance of the retained feature dimensions. Important feature dimensions and nodes will not be destroyed, thereby highlighting important features and expanding the difference in deviation.

[0037] Furthermore, in other optional embodiments, the system for rapid analysis of prefabricated building performance further includes: A model pre-optimization module, wherein the model pre-optimization module comprises: A removal unit randomly removes nodes of any convolutional layer in the convolutional network, and replaces the removed nodes with nodes with a weight of zero, and re-tests the same test data before and after the removal, and updates the convolutional network if the difference in the test results is within a standard range; The updating unit replaces the initial convolutional network with the updated convolutional network, and trains the convolutional network using the training data to obtain a final convolutional network.

[0038] The present application has found that for the local graph of the prefabricated connector, the overall surface difference of the central area is small even when the prefabricated connector vibrates, shifts, etc. With the help of this feature, combined with the aforementioned embodiment mentioned solidifying the nodes, the weights of important nodes can be solidified to avoid weight destruction. Based on the core concept of the aforementioned embodiment, the embodiment of the present application can be further configured with the concept of eliminating some unimportant nodes, that is, by using the same test data for testing, if the difference in the test results is within the standard range, it means that the impact of the node is small, so the node can be configured with a weight of 0, thereby reducing the number of nodes and lightweighting the model structure. At the same time, due to the reduction in the number of nodes (the weight is 0, which corresponds to the removal of the node), the speed of model prediction is improved.

[0039] In addition, another lightweight solution is further provided in the embodiment of the present application. Specifically, in another optional embodiment, the prefabricated building performance rapid analysis system further includes: A model pre-optimization module, wherein the model pre-optimization module comprises: Deletion unit, randomly remove nodes of any convolutional layer in the convolutional network, and replace the removed nodes with nodes with zero weight, re-test the same test data before and after the removal, and update the convolutional network if the difference in test results is within the standard range; The explosion unit randomly takes at least one node in at least one convolution layer in the updated convolution network as a standard node, adds at least one node according to the weight of the standard node, and inserts it into the corresponding convolution layer; wherein the number of deleted nodes is greater than the number of added nodes.

[0040] In this embodiment, the explosion module first randomly selects a node as the standard, and then adds the standard node to the convolutional layer. Since the number of deleted nodes is greater than the number of added nodes, the overall network presents a lightweight characteristic. Furthermore, since the randomly selected nodes are not "unimportant nodes" in the convolutional network, the weights of important nodes can be further improved. While ensuring lightweight, the difference in deviation can be greater, so that the data results are easier to analyze for stability.

[0041] In a preferred embodiment, the present application may configure the standard nodes to be selected from the solidified nodes in the aforementioned embodiments, so that the selected standard nodes are the nodes with the highest importance, thereby further amplifying the difference in deviation.

[0042] Furthermore, the present application also provides a method for amplifying the deviation difference, and it is understandable that all the methods for amplifying the deviation difference of the present application can be freely combined, and the present application does not limit this. In an optional embodiment, the model pre-optimization module also includes: An image segmentation layer, wherein the image segmentation layer is used to segment the local image into a plurality of sub-images; The image splicing layer, for each of the three adjacent sub-images, inserts the starting N columns of the first sub-image before the first column of the sub-image in the middle, and inserts the last M columns of the last sub-image after the last column of the sub-image in the middle, regenerates the sub-image in the middle, replaces the local image, and inputs it into the convolution layer.

[0043] like Figure 5As shown, in this embodiment, the cooperation of the image segmentation layer and the image stitching layer is equivalent to reducing the original image to one third, and through stitching, the N columns and M columns on both sides are included in the sub-image in the middle position. Combined with the fact that the edge features of the prefabricated connector are more prominent when vibrating or deformed, this application brings the edge N columns and M columns together into the middle sub-image, so that the pixel positions where the edge features are located are more, the edge features are more obvious, and the difference in deviation is further amplified.

[0044] In addition, in other optional embodiments, the present application may further combine the test results of the same test data to delete some unimportant sub-regions. Specifically, the model pre-optimization module further includes: An image division layer randomly divides the local image into a plurality of regions, each of which has the same or different size, and the size of the largest region is constrained within a preset range; The image deletion layer randomly deletes one or more of the regions, and performs a zero-filling operation on part of the region to form an updated local map, and replaces the current local map to input into the convolution layer. If the deviation change rate of the output corresponding to the same test data is higher than the standard threshold, the deleted area is restored and the random deletion operation is performed again until the deviation change rate of the output corresponding to the same test data is lower than the standard threshold, and the current updated local map is retained as the final input of the convolution layer.

[0045] In the embodiment of the present application, by combining the concept of the same test data, the deleted sub-region is judged. If the deviation is reduced, it means that the sub-region is more important, and the deleted region is restored. The iteration is performed until the rate of change of the deviation is lower than the standard threshold, for example, lower than 5%. This means that the rate of change between removing and not removing the sub-region is not large, which means that the sub-region is relatively less important. After removing the sub-region, the model prediction speed can be greatly improved and the model structure can be optimized.

[0046] In an optional embodiment, the analysis module includes: An alignment unit, for each prefabricated connection, superimposes a preset time offset and a sampling time to calibrate the alignment sampling time and the time coordinate in the wind speed field cloud map; A search unit, for the aligned sampling moment, searches the wind field state data at the corresponding moment from the wind speed field cloud map; The determination unit analyzes and determines the stability performance of the prefabricated building based on the wind field state data and the corresponding deviation data at the sampling moment after the alignment.

[0047] In this embodiment, the present application finds that there is a certain time delay between the real-time wind field reflected in the wind speed field cloud map and the vibration of the prefabricated connecting parts. Therefore, the present application first calibrates the preset time offset through calibration. Most of the time offsets are within 2s. By first calibrating the time delay, the error caused by the delay in wind speed data is reduced.

[0048] It should be understood that since the deviation data of this application is relatively accurate, the error caused by objective factors can be reduced by configuring delay calibration, thereby further improving the accuracy of the data.

[0049] The following is a detailed description of the present application specifically combining the wind field status data and the corresponding deviation data to analyze and determine the stability performance of the prefabricated building.

[0050] In an optional embodiment, the wind field state data includes wind speed and wind direction of each unit area in the spatial area, and the determining unit includes: The comprehensive wind field determination subunit determines, for each prefabricated connector, the comprehensive wind direction and comprehensive wind force in the spatial area according to the spatial area where the prefabricated connector is located and the wind speed and wind direction of each unit area; A sorting subunit determines the wind direction influence sorting of all local images according to the comprehensive wind direction and the shooting angle of the fixed-angle camera; A weight coefficient generating subunit dynamically generates a deviation weight coefficient of each local graph according to the wind direction influence ranking; The subunits are determined, and the stability performance of the prefabricated building is analyzed and determined according to the deviation weight coefficient of each local graph and the deviation of each local graph, combined with the comprehensive wind force at the corresponding time point.

[0051] In this embodiment, the determination of the comprehensive wind direction and the comprehensive wind force can be calculated based on the vector algorithm. Specifically, the wind direction and the corresponding wind speed data of each unit area are first collected, and then a vector is drawn to represent each individual wind force with each wind direction as the direction and the wind speed as the length. For example, the north wind can be represented as a vector along the positive direction of the y-axis, and the east wind can be represented as a vector along the positive direction of the x-axis. Specifically, the wind direction and wind speed can be converted into u and v components, where u is the component in the east-west direction and v is the component in the north-south direction. Then, in a common coordinate system, all wind force vectors are connected end to end to form a closed polygon, and finally starting from a vertex of the polygon and walking along the edge of the polygon to the vertex on the opposite side, the vector is the composite wind vector. Finally, the direction and length of the composite wind vector are read, which is the wind direction and wind speed of the composite wind. The wind direction can be calculated by inverse trigonometric functions (such as atan2), and the wind speed is the length of the composite vector.

[0052] It should be noted that the calculation of comprehensive wind force belongs to public knowledge technology, and this application does not impose any restrictions on this. At the same time, this application can also adopt other comprehensive wind field calculation methods. It should be further noted that the unit area of ​​this application can generally be configured as 10 square meters or a larger area, and this application does not impose any restrictions on this. Specifically, in urban space, shuttle winds will be formed between high-rise buildings. Therefore, this application needs to consider the impact of local wind fields to avoid calculation errors caused by uneven local wind field data. Obviously, for example, in open areas, if the wind field does not cause local unevenness, the wind field can be simplified and calculated with the same wind field data to reduce the amount of data processing. This application does not impose any restrictions on this.

[0053] After the comprehensive wind force and comprehensive wind direction are determined, the degree of influence of the local image on the comprehensive wind force and comprehensive wind direction can be determined in combination with the shooting angle of the camera and the position and connection relationship of the prefabricated connecting parts. For example, if the comprehensive wind direction is facing the surface of the prefabricated connecting parts and the local image is the surface of the prefabricated connecting parts, it can be known that the comprehensive wind force will only make the vibration direction of the prefabricated connecting parts the same as the comprehensive wind direction. Therefore, for the local image, no matter how large the vibration is, it will not produce obvious differences in the image. Therefore, the local image can be eliminated or the influence of the local image can be reduced. The specific improvement plan is described in detail below.

[0054] In this improved solution, the determining subunit includes: The deviation weight coefficient at the corresponding time point is re-determined according to the comprehensive wind force and the initial standard wind force.

[0055] Specifically, if the comprehensive wind force is greater than the initial standard wind force, the deviation weight coefficient of the local map corresponding to the first K1 positions in the wind direction influence ranking is reduced, wherein the ratio of the reduction amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force, and the deviation weight coefficient of the local map corresponding to the last K2 positions in the wind direction influence ranking is increased, wherein the ratio of the increase amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force; if the comprehensive wind force is less than the initial standard wind force, the deviation weight coefficient of the local map corresponding to the first K1 positions in the wind direction influence ranking is increased, wherein the ratio of the increase amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force, and the deviation weight coefficient of the local map corresponding to the last K2 positions in the wind direction influence ranking is reduced, wherein the ratio of the reduction amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force; A weighted average calculation is performed based on the final deviation weight coefficient of each local graph and the deviation of each local graph, and the final deviation of the prefabricated connector is output; The stability performance of the prefabricated building is determined according to the final deviation of all prefabricated connecting parts and the position of each prefabricated connecting part.

[0056] In this embodiment, if the comprehensive wind force is large, it means that the overall vibration amplitude of the prefabricated connector is large. At this time, the influence of wind direction on the vibration is small, even for the local map with small wind direction influence. At this time, by reducing the deviation weight coefficient of the local map corresponding to the first K1 position in the wind direction influence ranking, since the sum of the weights is 1, the deviation weight coefficient of the local map corresponding to the last K2 position in the wind direction influence ranking is correspondingly increased, so as to ensure that the total weight is dynamically 1. At this time, although the weight in the middle position does not change, if K2 is set to be smaller than K1, the weight ratio is relatively improved. Therefore, by configuring the size of K2 and K1, the weight of the local map with the greatest influence can be relatively reduced, and the weight of the local map with the smallest influence can be increased, which conforms to the characteristics of the impact brought by the comprehensive wind force and makes the prediction result more accurate.

[0057] When the overall wind force is relatively small, the difference of the local map with large wind direction influence is relatively large, while the difference of the local map with small wind force influence is difficult to be obviously reflected in the local map due to the limitation of vibration direction. At this time, a similar concept can be used for configuration. Specifically, the deviation weight coefficient of the local map corresponding to the first K1 positions in the wind direction influence ranking is increased, and the deviation weight coefficient of the local map corresponding to the last K2 positions in the wind direction influence ranking is reduced, so that the weight of the local map with the greatest influence is relatively increased, and the weight of the local map with the least influence is reduced, which is in line with the characteristics of the impact brought by the low overall wind force, making the prediction result more accurate.

[0058] Furthermore, in the embodiment of the present application, a weighted average calculation is performed based on the final deviation weight coefficient of each local graph and the deviation of each local graph, and the final deviation of the prefabricated connector is output. Specifically, the deviation of each local graph can be multiplied by its corresponding weight coefficient, and then all the results are added to obtain the total weighted deviation. The formula can be expressed as:

[0059] Where n is the number of local graphs, deviation i is the deviation of the i-th local graph, and weight i is the deviation weight coefficient of the i-th local graph.

[0060] Furthermore, in the embodiment of the present application, if the deviation is large, it means that the stability of the building is poor, so the stability can be evaluated by configuring the deviation to divide the levels.

[0061] For example, the stability performance of the prefabricated building is determined according to the final deviation of all prefabricated connectors and the position of each prefabricated connector, specifically including: If the deviation is higher than Y1, the stability is poor; if the deviation is within the range of Y2-Y1, the stability is moderate; if the deviation is between Y3-Y2, the stability is good, among which Y1 is greater than Y2, and Y2 is greater than Y3, and this application does not impose any restrictions on this.

[0062] Of course, the present application may also adopt other methods or set other stability determination standards, but it should be understood that the current stability evaluation includes evaluations of the center of gravity, structural stability, etc., which is not required for the present application. The core concept of the present application is to make judgments based on image deviation, that is, to judge stability directly by the position displacement caused by vibration, and cleverly combines the characteristics that the top of high-rise buildings is greatly affected by wind force, making it more accurate than other existing technologies, and due to the high data accuracy, there is no need for long-term observation, so that rapid analysis can be performed.

[0063] See also Figure 6 As shown, the electronic device of this embodiment includes: a processor 11 ( Figure 6 Only one processor is shown), a memory 12, and a computer program 13 stored in the memory 12 and executable on the processor 11. When the processor 11 executes the computer program 13, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 2 The functions of each module are shown.

[0064] Exemplarily, the computer program 13 may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 11 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 13 in the terminal device.

[0065] Those skilled in the art will understand that Figure 6It is only an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or less components than shown in the figure, or combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc. The processor 11 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0066] The memory 12 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The memory 12 may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the terminal device. Further, the memory 12 may also include both an internal storage unit of the terminal device and an external storage device. The memory 12 is used to store the computer program and other programs and data required by the terminal device. The memory 12 may also be used to temporarily store data that has been output or is to be output.

[0067] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A rapid analysis system for prefabricated building performance based on multi-dimensional parameters, characterized by: The multidimensional parameters include a plurality of local images and wind speed field cloud images corresponding to each prefabricated connector, wherein the plurality of local images are obtained by photographing the corresponding prefabricated connectors with a plurality of fixed-angle cameras at fixed positions. The multidimensional parameter-based prefabricated building performance rapid analysis system includes: An acquisition module, which acquires a wind speed field cloud map of the prefabricated building to be analyzed and a plurality of local maps corresponding to each prefabricated connection part collected at set intervals; A model input module inputs all local images collected by each prefabricated connector at each sampling time into a difference neural network model corresponding to the prefabricated connector, and outputs the deviation degree from the standard image at each sampling time; The analysis module analyzes and determines the stability performance of the prefabricated building according to the deviation at each sampling moment and the wind speed field cloud map for the prefabricated connection parts.

2. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 1 is characterized in that: The difference neural network model includes a channel attention mechanism network, an image cropping layer, a convolutional network and a comparison layer; The input of the channel attention mechanism network is each local image, and the output is used as the input of the image cropping layer. The image cropping layer outputs the image after removing the feature channels with weight coefficients lower than the set threshold, and inputs it to the convolutional network. The output of the convolutional network is used as the input of the comparison layer, which is pre-configured with a standard image of the corresponding pre-constructed connector.

3. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 2 is characterized in that: The convolutional network specifically includes: multiple convolutional layers and multiple pooling layers, wherein, during the testing process of the difference neural network model, when multiple test data with a difference degree lower than a set threshold are sequentially input into the difference neural network model, part of the nodes of any one or more convolutional layers are solidified each time until the output difference of the convolutional network before and after solidification is within a set range, at which time the solidified nodes are output, and an iterative operation is performed until all similar training data have been trained or the set solidification ratio is reached, and the final convolutional network is output.

4. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 3 is characterized in that: The prefabricated building performance rapid analysis system also includes: A model pre-optimization module, wherein the model pre-optimization module comprises: A removal unit randomly removes nodes of any convolutional layer in the convolutional network, and replaces the removed nodes with nodes with a weight of zero, and re-tests the same test data before and after the removal, and updates the convolutional network if the difference in the test results is within a standard range; The updating unit replaces the initial convolutional network with the updated convolutional network, and trains the convolutional network using the training data to obtain a final convolutional network.

5. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 3 is characterized in that: The prefabricated building performance rapid analysis system also includes: A model pre-optimization module, wherein the model pre-optimization module comprises: Deletion unit, randomly remove nodes of any convolutional layer in the convolutional network, and replace the removed nodes with nodes with zero weight, re-test the same test data before and after the removal, and update the convolutional network if the difference in test results is within the standard range; The explosion unit randomly takes at least one node in at least one convolution layer in the updated convolution network as a standard node, adds at least one node according to the weight of the standard node, and inserts it into the corresponding convolution layer; wherein the number of deleted nodes is greater than the number of added nodes.

6. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 4 or 5, characterized in that: The model pre-optimization module also includes: An image segmentation layer, wherein the image segmentation layer is used to segment the local image into a plurality of sub-images; The image splicing layer, for each of the three adjacent sub-images, inserts the starting N columns of the first sub-image before the first column of the sub-image in the middle, and inserts the last M columns of the last sub-image after the last column of the sub-image in the middle, regenerates the sub-image in the middle, replaces the local image, and inputs it into the convolution layer.

7. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 4 or 5, characterized in that: The model pre-optimization module also includes: An image division layer randomly divides the local image into a plurality of regions, each of which has the same or different size, and the size of the largest region is constrained within a preset range; The image deletion layer randomly deletes one or more of the regions, and performs a zero-filling operation on part of the region to form an updated local map, and replaces the current local map to input into the convolution layer. If the deviation change rate of the output corresponding to the same test data is higher than the standard threshold, the deleted area is restored and the random deletion operation is performed again until the deviation change rate of the output corresponding to the same test data is lower than the standard threshold, and the current updated local map is retained as the final input of the convolution layer.

8. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 1 is characterized in that: The analysis module comprises: An alignment unit, for each prefabricated connection, superimposes a preset time offset and a sampling time to calibrate the alignment sampling time and the time coordinate in the wind speed field cloud map; A search unit, for the aligned sampling moment, searches the wind field state data at the corresponding moment from the wind speed field cloud map; The determination unit analyzes and determines the stability performance of the prefabricated building based on the wind field state data and the corresponding deviation data at the sampling moment after the alignment.

9. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 8, characterized in that: The wind field state data includes wind speed and wind direction of each unit area in the spatial area, and the determination unit includes: The comprehensive wind field determination subunit determines, for each prefabricated connector, the comprehensive wind direction and comprehensive wind force in the spatial area according to the spatial area where the prefabricated connector is located and the wind speed and wind direction of each unit area; A sorting subunit determines the wind direction influence sorting of all local images according to the comprehensive wind direction and the shooting angle of the fixed-angle camera; A weight coefficient generating subunit dynamically generates a deviation weight coefficient of each local graph according to the wind direction influence ranking; The subunits are determined, and the stability performance of the prefabricated building is analyzed and determined according to the deviation weight coefficient of each local graph and the deviation of each local graph, combined with the comprehensive wind force at the corresponding time point.

10. The multi-dimensional parameter-based rapid analysis system for prefabricated building performance according to claim 9, characterized in that: The determining subunit comprises: According to the comprehensive wind force and the initial standard wind force, the deviation weight coefficient of the corresponding time point is re-determined, wherein if the comprehensive wind force is greater than the initial standard wind force, the deviation weight coefficient of the local map corresponding to the first K1 position in the wind direction influence ranking is reduced, wherein the ratio of the reduction amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force, and the deviation weight coefficient of the local map corresponding to the last K2 position in the wind direction influence ranking is increased, wherein the ratio of the increase amplitude to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force. The ratio of the difference in wind force to the initial standard wind force; if the comprehensive wind force is less than the initial standard wind force, the deviation weight coefficient of the local map corresponding to the first K1 positions in the wind direction influence ranking is increased, wherein the ratio of the increase to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force, and the deviation weight coefficient of the local map corresponding to the last K2 positions in the wind direction influence ranking is reduced, wherein the ratio of the reduction to the original deviation weight coefficient is the ratio of the difference between the comprehensive wind force and the initial standard wind force to the initial standard wind force; A weighted average calculation is performed based on the final deviation weight coefficient of each local graph and the deviation of each local graph, and the final deviation of the prefabricated connector is output; The stability performance of the prefabricated building is determined according to the final deviation of all prefabricated connecting parts and the position of each prefabricated connecting part.

Images