Deformation monitoring system and method

Abstract

The embodiment of the invention provides a deformation monitoring system and method. The deformation monitoring system comprises a first monitoring device, a second monitoring device and a processor, wherein the first monitoring device is used for acquiring first monitoring information; the second monitoring device is used for collecting second monitoring information; the processor is used for acquiring first monitoring information through the first monitoring device; determining an estimated deformation feature of the substructure based on the first monitoring information; determining a first substructure set of the monitoring target based on the estimated deformation features; determining deployment parameters of the second monitoring device based on the first substructure set; and based on the deployment parameters, controlling a second monitoring device to collect second monitoring information, and based on the first monitoring information and the second monitoring information, determining actual deformation data of the substructure. Through the system and the method, the deployment of the second monitoring device can be more refined, the deformation monitoring information can be obtained in a more targeted manner, and thus the dynamic monitoring of the deformation of the monitoring target can be completed more efficiently and accurately.

Description

Technical Field

[0001] The present invention relates to the field of deformation monitoring technology, and in particular to a deformation monitoring system and method. Background Art

[0002] In order to ensure the safety of buildings during construction, use and operation, and to provide reliable data for the design, construction, management and scientific research of buildings, it is necessary to observe the stability of buildings during construction and operation. Beidou GNSS technology is often used for deformation monitoring of buildings. The advantages of this technology are fast speed and all-weather. However, there are problems such as the need for manual re-measurement, low degree of automation, the need to set up a base station, and low accuracy of real-time deformation monitoring.

[0003] In response to the above problems, CN107764231B proposed a building deformation monitoring system and method based on Beidou foundation enhancement. The application focuses on receiving and processing the original observation data of GNSS and tilt sensors to obtain building displacement, settlement and tilt information, and realize remote automatic monitoring, real-time analysis, automatic alarm and report output functions. However, it does not take into account the changes in the construction status of the building under construction, which will lead to the inability to determine sufficiently reliable deformation monitoring data.

[0004] Therefore, it is desirable to provide a deformation monitoring system and method to achieve dynamic monitoring of buildings under construction and obtain sufficiently reliable deformation monitoring data. Summary of the invention

[0005] One of the embodiments of the present specification provides a deformation monitoring system, comprising a first monitoring device, a second monitoring device, and a processor; wherein the first monitoring device is configured as a satellite-based monitoring device for obtaining first monitoring information; the second monitoring device is configured as an on-site monitoring device for collecting second monitoring information; the processor is used to: obtain the first monitoring information through the first monitoring device, the first monitoring information including substructure image information and environmental sensor data of the monitoring target; based on the first monitoring information, determine the estimated deformation characteristics of the substructure, the estimated deformation characteristics including at least one of the estimated deformation type, the estimated deformation intensity and the estimated deformation probability; based on the estimated deformation characteristics, determine a first substructure set of the monitoring target, the first substructure set including at least one key monitoring part of the monitoring target; based on the first substructure set, determine the deployment parameters of the second monitoring device; based on the deployment parameters, control the second monitoring device to collect the second monitoring information, and determine the actual deformation data of the substructure based on the first monitoring information and the second monitoring information.

[0006] One of the embodiments of the present specification provides a deformation monitoring method, which is executed by a processor and includes: acquiring first monitoring information through the first monitoring device, the first monitoring information including image information and environmental sensor data of a substructure of a monitoring target; determining an estimated deformation feature of the substructure based on the first monitoring information, the estimated deformation feature including at least one of an estimated deformation type, an estimated deformation intensity and an estimated deformation probability; determining a first substructure set of the monitoring target based on the estimated deformation feature, the first substructure set including at least one key monitoring part of the monitoring target; determining deployment parameters of the second monitoring device based on the first substructure set; and controlling the second monitoring device to collect second monitoring information based on the deployment parameters, and determining actual deformation data of the substructure based on the first monitoring information and the second monitoring information.

[0007] One of the embodiments of the present specification provides a deformation monitoring device, including a processor, wherein the processor is used to execute the above-mentioned deformation monitoring method.

[0008] One of the embodiments of the present specification provides 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 executes the aforementioned deformation monitoring method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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:

[0010] Figure 1 is a system schematic diagram of a deformation monitoring system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a deformation monitoring method according to some embodiments of this specification;

[0012] Figure 3 It is a schematic diagram of determining estimated deformation characteristics according to some embodiments of this specification.

[0013] Figure 4 It is a schematic diagram of determining deployment parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] Figure 1 is a system schematic diagram of a deformation monitoring system according to some embodiments of this specification.

[0019] In some embodiments, Figure 1 As shown, the deformation monitoring system includes a first monitoring device 110 , a second monitoring device 120 , and a processor 130 .

[0020] The first monitoring device 110 is configured to perform monitoring based on a satellite to obtain first monitoring information. As an example only, the first monitoring device may include a camera, a temperature sensor, a humidity sensor, and the like.

[0021] The second monitoring device 120 is configured as a field monitoring device to obtain the second monitoring information. As an example only, the second monitoring device may include an electronic level, a distance meter, etc.

[0022] On-site monitoring devices are devices used to monitor the deformation of buildings, such as drones.

[0023] The processor 130 may be used to process data from at least one component of the deformation monitoring system 100 and generate control instructions. In some embodiments, the processor may obtain first monitoring information through a first monitoring device; determine an estimated deformation feature of a substructure based on the first monitoring information; determine a first substructure set of a monitoring target based on the estimated deformation feature; determine a deployment parameter of a second monitoring device based on the first substructure set; control the second monitoring device to collect second monitoring information based on the deployment parameter, and determine actual deformation data of the substructure based on the first monitoring information and the second monitoring information.

[0024] In some embodiments, the processor may determine the estimated deformation characteristics through a deformation distribution recognition model based on the first monitoring information and the construction project information.

[0025] In some embodiments, the processor may determine a detection path of the second monitoring device based on the first substructure set; and determine a deployment parameter based on the detection path of the second monitoring device.

[0026] In some embodiments, the processor can also generate at least one candidate detection path based on the first substructure set and the building structure of the monitoring target; determine an evaluation value of the candidate detection path, the evaluation value is determined based on the first target value and the second target value; and use the candidate detection path that meets preset conditions as the target detection path.

[0027] For a detailed description of the functions of the deformation monitoring system 100, see Figure 2-Figure 4 and its related description.

[0028] Figure 2 is an exemplary flow chart of a deformation monitoring method according to some embodiments of this specification. Figure 2 As shown, the process 200 may include the following steps. In some embodiments, the process 200 may be executed by a processor.

[0029] Step 210: Acquire first monitoring information through a first monitoring device.

[0030] The first monitoring information refers to information related to the current situation of the building.

[0031] In some embodiments, the first monitoring information can be obtained by a first monitoring device monitoring a building.

[0032] In some embodiments, the first monitoring information includes at least image information of a substructure of a monitoring target and environmental sensor data, wherein the monitoring target refers to a building to be monitored, such as an office building, a bridge, etc.

[0033] Substructure refers to the local structure of the monitoring target, for example, the piers of a bridge under construction, the exterior wall of an office building under construction, etc.

[0034] In some embodiments, the processor may divide the monitoring target in a variety of ways. For example, the building may be divided based on the spatial three-dimensional grid of the building (the grid size is preset). For another example, the building may be divided based on the functional structure of the building.

[0035] The image information of the substructure refers to image data showing the current status of the substructure, for example, an image of a wall, an image of a load-bearing column, etc.

[0036] Environmental sensor data refers to data collected by environmental sensors related to the environment in which the building is located. For example, temperature, humidity, air pressure, light intensity, etc. More other environmental sensor data can also be obtained through corresponding environmental sensors based on actual needs.

[0037] Step 220: determining an estimated deformation feature of the substructure based on the first monitoring information.

[0038] The estimated deformation feature refers to data related to the estimated deformation of the building. In some embodiments, the estimated deformation feature may include at least one of an estimated deformation type, an estimated deformation intensity, and an estimated deformation probability.

[0039] The estimated deformation type is data that characterizes the type of deformation that may occur in a building, such as settlement, tilt, crack, displacement, etc.

[0040] The estimated deformation strength is data that characterizes the strength of the deformation that may occur in a building. For example, the estimated settlement of a building is 10 cm.

[0041] The estimated deformation probability is data that indicates the probability that a building may deform. For example, the estimated probability of a building cracking is 30%.

[0042] In some embodiments, the estimated deformation feature can be determined in a variety of ways. For example, the estimated deformation feature can be determined by querying a reference table of estimated deformation features. The reference table of estimated deformation features can be determined based on prior knowledge or historical data, including at least one reference first monitoring data, and reference deformation features corresponding to each reference first monitoring data. The processor can query the table based on the current first monitoring data to determine the estimated deformation feature.

[0043] In some embodiments, the processor can determine the estimated deformation characteristics through the deformation distribution recognition model based on the first monitoring information and the construction project information. For more information about this part, please refer to Figure 3 and its related description.

[0044] Step 230: determining a first substructure set of the monitoring target based on the estimated deformation characteristics.

[0045] In some embodiments, the first substructure set may include at least one first substructure, and the at least one first substructure corresponds to at least one key monitoring location of the monitoring target.

[0046] Key monitoring locations refer to substructures that need to be monitored in the monitoring target, such as bridge piers that are expected to crack, load-bearing columns that are expected to tilt, etc.

[0047] In some embodiments, the processor may determine the first substructure set based on at least one substructure in the monitoring target that meets a preset condition, wherein the preset condition may include that the estimated deformation strength and estimated deformation probability of the substructure reach a monitoring threshold, and the monitoring threshold may be determined based on prior experience or actual needs.

[0048] Step 240: Determine deployment parameters of a second monitoring device based on the first substructure set.

[0049] The deployment parameters refer to the working parameters of the second monitoring device set according to monitoring needs, for example, the monitoring position, angle, duration, etc. of the second monitoring device.

[0050] In some embodiments, the deployment parameters can be determined in a variety of ways. For example, the estimated deformation characteristics can be determined by querying a deployment parameter reference table. The deployment parameter reference table can be determined based on prior knowledge or historical data, including at least one reference first substructure set, and reference deployment parameters of the second monitoring device corresponding to each reference first substructure set. The processor can perform a table lookup based on the current first substructure set to determine the deployment parameters.

[0051] In some embodiments, the processor may determine the detection path of the second monitoring device based on the first substructure set; and determine the deployment parameters based on the detection path of the second monitoring device. For more information about this section, please refer to Figure 4 and its related description.

[0052] Step 250: Based on the deployment parameters, control the second monitoring device to collect second monitoring information, and determine the actual deformation data of the substructure based on the first monitoring information and the second monitoring information.

[0053] The second monitoring information refers to monitoring parameters related to the deformation of the monitoring target, such as the location of the settlement point, the location of the monitoring point, etc. More other types of data can be determined according to actual monitoring needs.

[0054] In some embodiments, the processor may be in communication with the second monitoring device and send a collection instruction to the second monitoring device to control the second monitoring device to collect the second monitoring information, wherein the collection instruction includes at least the deployment parameters and the data to be collected.

[0055] The actual deformation data is data that represents the actual deformation of the building, for example, a crack appears on the outer wall of the building, and the length of the crack is 1 meter.

[0056] In some embodiments, the processor may obtain actual deformation data by calculation based on the first monitoring information and the second monitoring information. The calculation method may include a method used for building deformation monitoring. For example, the current settlement amount in building settlement observation is the difference between the elevation obtained in this observation and the elevation obtained in the previous observation. Another example is the gypsum board marking method used in building crack observation. Another example is the angle forward intersection method used in building displacement observation.

[0057] In some embodiments of the present specification, the processor can determine the parts of the monitoring target that need to be monitored based on the estimated deformation characteristics, so that the deployment of the second monitoring device is more refined, and the deformation monitoring information is obtained more specifically, thereby completing the dynamic monitoring of the deformation of the monitoring target more efficiently and accurately.

[0058] Figure 3 It is a schematic diagram of determining estimated deformation characteristics according to some embodiments of this specification.

[0059] In some embodiments, Figure 3 As shown, the processor can determine the estimated deformation characteristics through a deformation distribution recognition model based on the first monitoring information 310 and the construction project information 320, and the deformation distribution recognition model is a machine learning model.

[0060] In some embodiments, the deformation distribution recognition model may be any one or a combination of a deep neural network model (DNN), a convolutional neural network model (CNN), or other customized model structures.

[0061] In some embodiments, the input of the deformation distribution recognition model includes at least the first monitoring information and the construction project information. The construction project information refers to data information related to the construction project. For example, it includes the construction progress, the building type, etc. For the relevant description of the first monitoring information, please refer to Figure 2 and its related description.

[0062] In some embodiments, the output of the deformation distribution recognition model includes an estimated deformation feature. For an explanation of the estimated deformation feature, see Figure 2 and its related description.

[0063] like Figure 3 As shown, in some embodiments, the deformation distribution recognition model includes an image recognition layer 340 and a probability calculation layer 350 .

[0064] In some embodiments, the image recognition layer 340 may be a machine learning model, such as a deep neural network model (DNN), a convolutional neural network model (CNN), and the like.

[0065] In some embodiments, the input of the image recognition layer 340 includes substructure image information 330 of the monitored target. For a description of the substructure image information, see Figure 2 The output of the image recognition layer includes an image feature vector 360 of the substructure.

[0066] An image feature vector refers to a feature vector that can reflect a substructure image. For example, an image feature vector can reflect the texture, grayscale value, and edge information of a substructure image. Texture, grayscale value, and edge information can respectively reflect whether the substructure in the substructure image has cracks, damage, the type of substructure, and the gaps between substructures.

[0067] In some embodiments, the input of the probability calculation layer 350 includes the image feature vector 360 of the substructure, the first monitoring information 310 and the construction project information 320, and the output includes the deformation type and deformation probability 370 of the substructure. For the deformation type and deformation probability of the substructure, please refer to Figure 2 and its related description.

[0068] In some embodiments, the construction project information 320 also includes construction completion intervals of substructures.

[0069] The construction completion interval of a substructure refers to the time interval between the time when the substructure is completed and the current time.

[0070] In some implementations, the processor may obtain the historical moment when the construction of the substructure is completed through historical data, thereby determining the construction completion interval of the substructure.

[0071] In some embodiments, the construction completion interval can reflect the construction sequence of different substructures, and the construction sequence will determine the changes in the historical stress conditions of the substructures. For example, when constructing a multi-story building, the first bottom floor needs to bear the weight of all the floors constructed later, so the size and time of the load it bears is greater than that of the upper floors constructed later. Therefore, the construction completion interval is input into the deformation distribution recognition model, which can more accurately evaluate the historical stress conditions and possible deformation risks of each substructure, and improve the accuracy of the output of the predicted deformation distribution recognition model.

[0072] In some embodiments, the output of the image recognition layer can be the input of the probability calculation layer, and the image recognition layer and the probability calculation layer can be obtained through joint training.

[0073] In some embodiments, the first training sample for training the deformation distribution recognition model includes sample first monitoring information, sample substructure image information, and sample construction project information. The first training sample can be obtained based on historical data. The first label is the actual deformation type of the substructure corresponding to the first training sample, which can be obtained based on the deformation result annotation of the historical actual substructure.

[0074] In some embodiments, the processor can input the sample substructure image information into the initial image recognition layer to obtain the initial image feature vector; input the initial image feature vector, the sample first monitoring information, and the sample construction project information into the initial probability calculation layer to obtain the deformation type and deformation probability of the initial substructure. A loss function is constructed based on the deformation type and deformation probability of the initial substructure and the first label, and the loss function is used to synchronously update the parameters of the initial image recognition layer and the initial probability calculation layer. By updating the parameters, a trained image recognition layer and probability calculation layer are obtained, that is, a trained deformation distribution recognition model is obtained.

[0075] In some embodiments, the processor may also determine the deformation type and deformation probability of the monitored target based on the probability calculation model. The probability calculation model 390 may be a graph neural network model (GNN), the input of the probability calculation model 390 may include the architectural structure feature map 380 of the monitored target, and the output of the probability calculation model may include the deformation type and deformation probability 370 of the monitored target.

[0076] The building structure feature map refers to a map that can reflect the building structure and structural features of the monitoring target. In some embodiments, the building structure feature map 380 may include a node 380-1 and an edge 380-2.

[0077] Node 380 - 1 represents a substructure, and edge 380 - 2 represents a connection relationship between substructures.

[0078] Node features refer to parameters that can be used to reflect the characteristics of a building substructure. In some embodiments, the node features include the substructure type, the substructure physical features, the image feature vector of the substructure, and the construction completion interval of the substructure. For example, the substructure type may include whether the substructure is a pier or a wall; the substructure physical features may include the surface area, volume, material, etc. of the substructure. The image feature vector of the substructure may be determined based on the aforementioned image recognition layer.

[0079] Edge features refer to parameters that can be used to reflect the characteristics of the connection relationship between building substructures. In some embodiments, edge features include connection type and connection strength. Connection types may include cold connection (such as bolt connection) and hot connection (such as welding connection, cement bonding connection, etc.). Different connection types have different methods of expressing connection strength. For example, the connection strength of cold connection is expressed by the number of bolts, and the connection strength of hot connection is expressed by the contact area and the bonding strength of the bonding material.

[0080] In some embodiments, the processor may obtain node features and edge features from architectural drawings and construction status records.

[0081] In some embodiments, the probability calculation model can be obtained by iteratively updating the parameters of the initial probability calculation model through multiple labeled second training samples by gradient descent or other methods. In some embodiments, the second training sample can at least include a sample building structure feature map of the sample monitoring target, and the label corresponding to the second training sample can include the deformation of the sample monitoring target. Among them, the sample building structure feature map can be determined based on the building structure and structural characteristics of the sample monitoring target in the historical data, and the specific determination method can refer to the determination of the aforementioned building structure feature map. The label corresponding to the second training sample can be determined based on the actual deformation of the sample monitoring target in the historical data.

[0082] In some embodiments, the building structure feature map is input into the probability calculation layer to predict and estimate the deformation characteristics, fully considering the coupling relationship between different substructures, thereby improving the prediction accuracy.

[0083] By utilizing the self-learning ability of the machine learning model, namely the deformation distribution recognition model, calculations can be performed based on the first monitoring information, construction project information and other data information to improve the accuracy of the estimated deformation characteristics predicted by the deformation distribution recognition model, save manual analysis time and improve monitoring efficiency, thereby timely discovering potential risks of building structures and preventing safety accidents.

[0084] Figure 4 FIG. 1 is a schematic diagram of determining deployment parameters according to some embodiments of this specification. Figure 4 As shown, the process 400 may include the following steps. In some embodiments, the process 400 may be executed by a processor.

[0085] In some embodiments, the processor may determine the detection path of the second monitoring device based on the first substructure set. For an explanation of the first substructure set, see Figure 2 and its related description.

[0086] The detection path refers to the specific route that the second monitoring device takes to detect the monitoring target. For example, if the second monitoring device is configured as a drone, the detection path is the specific flight route that the drone takes from the starting point, passes through a series of points to be detected, and returns to the end point. Each point to be detected represents a location that needs to be detected.

[0087] In some embodiments, the processor may determine the detection path of the second monitoring device in a variety of ways, such as by using a path planning algorithm, a genetic algorithm, etc.

[0088] In some embodiments, the detection path is related to the building structure and the construction progress, and the processor can determine the substructure detection difficulty of the first substructure set based on the building structure and the construction progress, and then determine the detection path of the second monitoring device based on the substructure detection difficulty. Specifically, the following steps 410 and 420 are included.

[0089] Step 410 , determining the substructure detection difficulty based on the building structure, the construction progress and the first substructure set.

[0090] Building structures can include reinforced concrete structures, steel structures, wooden structures, etc. Construction progress can be expressed as a percentage of completion.

[0091] Substructure detection difficulty refers to the difficulty of detecting a substructure. Substructure detection difficulty can be expressed in numerical values, and the larger the numerical value, the higher the difficulty. Substructure detection difficulty is positively correlated with the construction progress and the average distance of the substructure from the surrounding substructures. Among them, the substructure detection difficulty also has a corresponding relationship with the substructure type, which can be determined based on historical substructure detection data. For example, based on historical substructure detection data, the detection difficulty of walls is lower than that of stairs.

[0092] In some embodiments, the processor may determine the substructure detection difficulty by using the following formula (1).

[0093] (1)

[0094] Among them, N represents the difficulty of substructure detection; , , represents the coefficient, which can be preset based on historical experience; a represents the substructure type, which can be obtained from the architectural drawings; b represents the construction progress, which can be obtained from the construction schedule; c represents the average distance between the substructure and the surrounding substructures. The processor can obtain the first substructure set from the architectural drawings, thereby obtaining the substructure location information, and then calculate c based on the location information. According to formula (1), it can be seen that

[0095] Step 420 : determining a detection path based on the substructure detection difficulty.

[0096] In some embodiments, the processor may determine the difficulty of detecting substructures of a monitoring target (e.g., a building), determine the structure with the greatest difficulty in detecting substructures as the starting point of the detection path, and sequentially detect the structures of the detection target in order of decreasing difficulty in detecting substructures.

[0097] In some embodiments, the processor may also detect the structure of the detection target in order of increasing difficulty of substructure detection, so as to obtain more substructure detection information as quickly as possible to provide data support for subsequent deformation analysis.

[0098] In some embodiments, the detection difficulty of the substructure is determined and the detection path of the second monitoring device is determined accordingly, thereby improving the detection efficiency and accuracy of the second detection device and detecting potential deformation risks at an early stage.

[0099] In some embodiments, the processor may generate at least one candidate detection path, determine a target detection path from the at least one candidate detection path, and use the target detection path as the detection path of the second monitoring device. Specifically, the following steps 430 to 450 are included.

[0100] Step 430: Generate at least one candidate detection path based on the first substructure set and the building structure of the monitoring target.

[0101] A candidate detection path refers to at least one detection path that may serve as a target detection path.

[0102] In some embodiments, the processor may generate at least one candidate detection path in a variety of ways. For example, the processor may generate several candidate detection paths based on the architectural drawings of the detection target (building) through a path planning algorithm (such as Dijkstra or A* algorithm). For another example, according to the spatial layout of the detection target (building), the size and relationship of each structure, several candidate detection paths are constructed based on the order of detection difficulty from easy to difficult.

[0103] Step 440: Determine the evaluation value of the candidate detection path.

[0104] The evaluation value refers to a value used to evaluate the possibility that the candidate detection path can be used as the target detection path. The evaluation value can be expressed as a value or a percentage. The larger the value or percentage, the higher the possibility that the candidate detection path can be used as the target detection path.

[0105] In some embodiments, the evaluation value of the candidate detection path may be determined based on the first target value and the second target value.

[0106] The first target value can characterize the length of the candidate detection path and is one of the parameters used to calculate the evaluation value of the candidate detection path. In some embodiments, the first target value is determined based on the length of the candidate detection path. For example, the first target value is the reciprocal of the total length of the candidate detection path A.

[0107] The second target value is one of the parameters used to calculate the evaluation value of the candidate detection path. In some embodiments, the second target value is determined based on the weighted sum of the detection order of the first substructure of the candidate detection path.

[0108] In some embodiments, the second target value is positively correlated to the estimated deformation type of each detected first substructure in the candidate detection path, and negatively correlated to the sequence value of each detected first substructure in the candidate detection path.

[0109] In some embodiments, the processor may determine the second target value of the candidate detection path by using the following formula (2).

[0110] (2)

[0111] Wherein, n can represent any positive integer, indicating the nth first substructure in the candidate detection path; S represents the second target value; represents the estimated deformation type of the first, second, ... nth detected first substructure in the candidate detection path, each deformation type having a preset value determined according to the degree of harm; Indicates the order of the first substructures to be inspected, i.e., n, in the candidate inspection path (if the nth substructure is inspected, the order is n); represents the weighted weight, and the weight is positively correlated to the estimated deformation strength and the estimated deformation probability of the nth detected first substructure n in the candidate detection path.

[0112] In some embodiments, the weighted weights in formula (2) It is also relevant to the time interval for construction completion. For example, Negatively correlated to the construction completion interval of the first substructure n detected in the candidate detection path. For an explanation of the construction completion time interval, see Figure 3 and its related description.

[0113] The shorter the construction completion interval of the first substructure n in the candidate detection path, the higher its instability. By correlating the weighted weight (such as negative correlation) with the construction completion interval, the weight corresponding to the first substructure n with a shorter construction completion interval is larger, and the second target value is larger, which can increase the possibility that the candidate detection path can be used as the target detection path, thereby ensuring that the first substructure with a short construction completion interval can be detected first.

[0114] In some embodiments, the evaluation values ​​of the candidate detection paths are positively correlated to the first target value and the second target value, respectively.

[0115] In some embodiments, the processor may determine the evaluation value by the following formula (3).

[0116] (3)

[0117] Where P represents the evaluation value of the candidate detection path; , Indicates the preset coefficient, which is determined according to actual needs (for example, the total length of the path is given priority, Greater than ); represents the first target value; S represents the second target value.

[0118] In some embodiments, the evaluation value of the candidate detection path is also related to the third target value of the candidate detection path, and the third target value is determined based on the weighted sum of the average detection sequence distances of the key focus points in the candidate detection path. The key focus points are locations where the deformation meets the preset conditions, and the key focus points are determined based on historical data.

[0119] The key focus points refer to a number of detection points where the probability of deformation anomalies occurring simultaneously within a preset time threshold is greater than a preset support threshold. In some embodiments, the processor can obtain the key focus points based on historical data. The preset support threshold refers to a pre-set probability threshold of deformation anomalies occurring simultaneously between key focus points.

[0120] The average detection priority distance refers to the summed average of the priority distances between any two of at least one key focus point in the candidate detection path. Among them, the priority distance between any two key focus points in the candidate detection path refers to the distance of the detection priority. For example, the detection priority of detection point 1 in the candidate detection path is 1, and the detection priority of detection point 2 in the candidate detection path is 8. Then the detection priority distance between detection point 1 and detection point 2 in detection path A is the absolute value of the difference between the two, that is, 7.

[0121] As an example only, the key focus points include detection point 1, detection point 2 and detection point 3, then the average detection order distance of the key focus points is the average of the following detection order distances, including: the detection order distance between detection point 1 and detection point 2 in the candidate detection path, the detection order distance between detection point 1 and detection point 3 in the candidate detection path, and the detection order distance between detection point 2 and detection point 3 in the candidate detection path.

[0122] The third target value may be one of the parameters used to calculate the evaluation value of the candidate detection path. In some embodiments, the third target value is positively correlated with the support of the key focus point and the average detection sequence distance of the key control point in the candidate detection path.

[0123] In some embodiments, the processor may determine the third target value of the candidate detection path by using the following formula (4).

[0124] (4)

[0125] Wherein, n can represent any positive integer, indicating the nth first substructure in the candidate detection path; represents the third target value; represents the weighted weights, which are positively correlated to the support of their respective first substructures; Represents the average detection sequence distance of the first substructure in the candidate detection path.

[0126] In some embodiments, the evaluation value is positively correlated to the first target value, the second target value, and the third target value.

[0127] In some embodiments, the processor may also determine the evaluation value by using the following formula (5).

[0128] (5)

[0129] Where P represents the evaluation value of the candidate detection path; , , Indicates the preset coefficient, which is determined according to actual needs (for example, the total length of the path is given priority, Greater than , ); represents the first target value; S represents the second target value; represents the third target value.

[0130] In some embodiments, the processor may set the detection sequence between the key points to be larger. For example, the key points include detection point 1 and detection point 2, and both have a high probability of abnormal deformation at the same time. Then, when the second detection device is used for detection, detection point 1 and detection point 2 do not need to be detected continuously. Based on this, repeated detection of key points with similar deformation conditions can be reduced, thereby improving the detection efficiency of the detection device.

[0131] Step 450: taking the candidate detection path that meets the preset conditions as the target detection path.

[0132] The preset condition refers to a pre-set condition that enables the candidate detection path to be used as the target detection path. For example, the preset condition may be that the evaluation value of the candidate detection path is greater than a preset evaluation value threshold, and the preset evaluation value threshold is determined based on historical data.

[0133] The target detection path refers to a candidate detection path with the best detection effect or the largest evaluation value when the second detection device monitors the monitoring target based on multiple candidate detection paths. In some embodiments, the processor can determine the candidate detection path with the largest evaluation value as the target detection path of the second detection device based on the evaluation value corresponding to each candidate detection path.

[0134] In some embodiments, the processor generates multiple candidate detection paths and selects the optimal detection path, i.e., the target detection path, according to the corresponding evaluation value, to ensure that the second detection device can effectively and quickly complete the detection and improve the detection efficiency. The evaluation value of the candidate detection path is determined by weighted summing the first target value and the second target value, which fully considers the influence of the path length and the estimated deformation characteristics, thereby ensuring the reliability of determining the target detection path.

[0135] Step 460, determining deployment parameters based on the detection path of the second monitoring device.

[0136] In some embodiments, the processor may determine the deployment parameters in a variety of ways based on the detection path of the second monitoring device. For example, the processor may determine the deployment parameters such as the flight altitude, flight speed, and flight mode of the second monitoring device (such as a drone) based on the detection range covered by the detection path.

[0137] In some embodiments, the deployment parameters are also related to the estimated deformation characteristics, and the processor can determine the detection type based on the estimated deformation characteristics. For example, if the estimated deformation characteristic is a change in the vertical displacement of the building foundation or the ground, then the second detection device can determine that the detection type is settlement detection.

[0138] The detection type refers to the type of detection performed by the second detection device on the monitoring target. For example, the detection type includes settlement detection, structural crack detection, corrosion detection, etc. of the detection target, and more detection types can also be selected based on actual needs.

[0139] In some embodiments, the processor may determine the deployment parameters based on the detection type and the detection path. For example, if the detection type is settlement detection, the deployment parameters are the arrangement mode for settlement detection of the monitoring target. For another example, the processor may determine the horizontal reference point layout position in the detection path as the settlement observation point of the second detection device.

[0140] In some embodiments, the detection type of the second detection device is determined by estimating the deformation characteristics, thereby determining the deployment parameters of the second detection device, so that it can perform the detection task at a suitable position, thereby improving the detection efficiency and accuracy.

[0141] In some embodiments, the detection path of the second monitoring device is determined through the first substructure set, which can effectively ensure the reliability of the detection path and its detection efficiency; and the deployment parameters of the second monitoring device are determined through the detection path, so that the second monitoring device can perform detection at a suitable deployment position with suitable working parameters, further improving the detection efficiency and effectiveness of the second monitoring device.

[0142] Some embodiments of the present specification also disclose a deformation monitoring device, which includes a processor for executing the above-mentioned deformation monitoring method.

[0143] Some embodiments of the present specification further disclose a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer runs the aforementioned deformation monitoring method.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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 the digits. Although the numerical domains and parameters used to confirm the breadth of the 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.

[0149] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its 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.

[0150] 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 deformation monitoring system, characterized in that: It includes a first monitoring device, a second monitoring device, and a processor; wherein, The first monitoring device is configured to perform monitoring based on a satellite to obtain first monitoring information, wherein the first monitoring information includes at least one of substructure image information and environmental sensor data of a monitoring target; The second monitoring device is configured as an on-site monitoring device to collect second monitoring information; The processor is configured to: Acquiring the first monitoring information through the first monitoring device; Determine, based on the first monitoring information, an estimated deformation feature of a substructure of the monitoring target, wherein the estimated deformation feature includes at least one of an estimated deformation type, an estimated deformation intensity, and an estimated deformation probability; Based on the estimated deformation characteristics, determining a first substructure set of the monitoring target, wherein the first substructure set includes at least one key monitoring part of the monitoring target; determining, based on the first substructure set, deployment parameters of the second monitoring device; Based on the deployment parameters, controlling the second monitoring device to collect the second monitoring information; the second monitoring information is a monitoring parameter related to the deformation of the monitoring target; Based on the first monitoring information and the second monitoring information, actual deformation data of the substructure is determined; wherein The determining, based on the first substructure set, deployment parameters of the second monitoring device includes: Based on the first substructure set and the building structure of the monitoring target, generating at least one candidate detection path; The candidate detection path that meets the preset conditions is used as a target detection path, and the target detection path is used as a detection path of the second monitoring device; Deployment parameters are determined based on the detection path of the second monitoring device.

2. The deformation monitoring system according to claim 1, characterized in that: The processor is further configured to: Based on the first monitoring information and the construction project information, the estimated deformation characteristics are determined by a deformation distribution recognition model, and the deformation distribution recognition model is a machine learning model.

3. The deformation monitoring system according to claim 1, characterized in that: The processor is further configured to: Determine an evaluation value of the candidate detection path, wherein the evaluation value is determined based on a first target value and a second target value; wherein, The first target value is determined based on the length of the candidate detection path, and the second target value is determined based on the detection order of the first substructure of the candidate detection path.

4. A deformation monitoring method, characterized in that: The method is executed by a processor, comprising: Acquiring first monitoring information through a first monitoring device, wherein the first monitoring information includes image information of a substructure of a monitoring target and environmental sensor data; Determine, based on the first monitoring information, an estimated deformation feature of a substructure of the monitoring target, wherein the estimated deformation feature includes at least one of an estimated deformation type, an estimated deformation intensity, and an estimated deformation probability; Based on the estimated deformation characteristics, determining a first substructure set of the monitoring target, wherein the first substructure set includes at least one key monitoring part of the monitoring target; determining, based on the first substructure set, deployment parameters of a second monitoring device; Based on the deployment parameters, controlling the second monitoring device to collect second monitoring information; the second monitoring information is a monitoring parameter related to the deformation of the monitoring target; Based on the first monitoring information and the second monitoring information, actual deformation data of the substructure is determined; wherein, The determining, based on the first substructure set, deployment parameters of the second monitoring device includes: Based on the first substructure set and the building structure of the monitoring target, generating at least one candidate detection path; The candidate detection path that meets the preset conditions is used as a target detection path, and the target detection path is used as a detection path of the second monitoring device; Deployment parameters are determined based on the detection path of the second monitoring device.

5. The deformation monitoring method according to claim 4, characterized in that: The determining, based on the first monitoring information, the estimated deformation feature of the substructure includes: Based on the first monitoring information and the construction project information, the estimated deformation characteristics are determined by a deformation distribution recognition model, and the deformation distribution recognition model is a machine learning model.

6. The deformation monitoring method according to claim 4, characterized in that: The method further comprises: Determine an evaluation value of the candidate detection path, wherein the evaluation value is determined based on at least a first target value and a second target value, wherein the first target value is determined based on a length of the candidate detection path, and the second target value is determined based on a detection order of a first substructure of the candidate detection path.

7. 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 executes the deformation monitoring method according to any one of claims 4 to 6.

Images