Building node real-time monitoring method and system based on artificial intelligence

Abstract

The invention provides a building node real-time monitoring method and system based on artificial intelligence. The monitoring method comprises the following steps: mapping data monitored by monitoring terminals configured on building nodes into a three-dimensional model of a building; performing feature extraction on the three-dimensional model of the building to obtain building parameters; inputting the building parameters into a pre-configured neural network model to obtain an analysis result; and when the analysis result is abnormal, outputting early warning information. According to the building node real-time monitoring method and system based on artificial intelligence, efficient and accurate building node monitoring is achieved, the health state of a building is analyzed, problems are found in time, and related personnel are notified to solve the problems.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based real-time monitoring method and system for building nodes. Background Art

[0002] Monitoring building joints is a key technical means of ensuring structural safety and extending service life. Monitoring building joints can capture abnormal deformations such as displacement, settlement, and tilt, providing timely warnings of structural instability and preventing collapse accidents caused by joint failure. By continuously monitoring joint aging, crack expansion, or material fatigue, targeted maintenance and reinforcement can be implemented to slow structural degradation. Early detection of damage can reduce large-scale repair costs and avoid cascading damage caused by joint problems. Therefore, how to achieve efficient and accurate monitoring of building joints has always been a technical challenge that needs to be solved. Summary of the Invention

[0003] One of the purposes of the present invention is to provide a real-time monitoring method and system for building nodes based on artificial intelligence, so as to realize efficient and accurate monitoring of building nodes, thereby analyzing the health status of the building, discovering problems in time and notifying relevant personnel to solve them.

[0004] An embodiment of the present invention provides a method for real-time monitoring of building nodes based on artificial intelligence, comprising:

[0005] Mapping the data monitored by monitoring terminals configured at each building node into the three-dimensional model of the building;

[0006] Extract features from the three-dimensional model of the building and obtain building parameters;

[0007] Input building parameters into the pre-configured neural network model to obtain analysis results;

[0008] When there are abnormalities in the analysis results, an early warning message is output.

[0009] Preferably, the monitoring terminal includes: a monitoring sensor, a data acquisition unit, a processing unit and a communication unit;

[0010] Among them, the monitoring sensor, the data acquisition unit and the communication unit are electrically connected to the processing unit respectively; the processing unit collects the monitoring data of the monitoring sensor through the data acquisition unit and sends it to the outside world through the communication unit.

[0011] Preferably, the monitoring sensor includes: a displacement monitoring sensor, an inclination monitoring sensor, a stress monitoring sensor, a force monitoring sensor or one or more combinations thereof;

[0012] The communication unit includes: a Bluetooth communication module, a WIFI communication module, an Internet of Things communication module or one or more combinations thereof.

[0013] Preferably, the building parameters include: parameters representing the building type, parameters representing the position of each building node in the three-dimensional model, and one or more combinations of parameters representing the average value, maximum value, and minimum value of the monitoring data corresponding to each building node.

[0014] Preferably, when constructing the three-dimensional model, the detection data of each secondary node received by the mobile terminal is mapped to the three-dimensional model constructed according to the architectural parameters of the building;

[0015] During the real-time monitoring process, the secondary nodes are tested at preset time intervals to obtain test data and the data mapped to the three-dimensional model is updated;

[0016] In the time interval between every two tests, the historical test data, the monitoring data of the master node and the pre-configured update rules are comprehensively analyzed to update the three-dimensional model based on the analysis results.

[0017] The present invention provides an artificial intelligence-based real-time monitoring system for building nodes, comprising: a mapping module, an extraction module, an analysis module, and an output module; wherein the mapping module maps data monitored by monitoring terminals configured at each building node to a three-dimensional model of the building; the extraction module extracts features from the three-dimensional model of the building to obtain building parameters; the analysis module inputs the building parameters into a pre-configured neural network model to obtain analysis results; and when an abnormality is found in the analysis results, the output module outputs an early warning message.

[0018] Preferably, the monitoring terminal includes: a monitoring sensor, a data acquisition unit, a processing unit and a communication unit;

[0019] Among them, the monitoring sensor, the data acquisition unit and the communication unit are electrically connected to the processing unit respectively; the processing unit collects the monitoring data of the monitoring sensor through the data acquisition unit and sends it to the outside world through the communication unit.

[0020] Preferably, the monitoring sensor includes: a displacement monitoring sensor, an inclination monitoring sensor, a stress monitoring sensor, a force monitoring sensor or one or more combinations thereof;

[0021] The communication unit includes: a Bluetooth communication module, a WIFI communication module, an Internet of Things communication module or one or more combinations thereof.

[0022] Preferably, the building parameters include: parameters representing the building type, parameters representing the position of each building node in the three-dimensional model, and one or more combinations of parameters representing the average value, maximum value, and minimum value of the monitoring data corresponding to each building node.

[0023] Preferably, the artificial intelligence-based real-time monitoring system for building nodes further includes: a construction module and an update module;

[0024] When constructing the three-dimensional model, the construction module maps the detection data of each secondary node received through the mobile terminal to the three-dimensional model constructed according to the architectural parameters of the building;

[0025] During the real-time monitoring process, the update module updates the data mapped to the three-dimensional model based on the detection data obtained by detecting the secondary nodes at preset time intervals;

[0026] In the time interval between every two detections, the update module comprehensively analyzes the historical detection data, the monitoring data of the master node and the pre-configured update rules, and updates the three-dimensional model based on the analysis results.

[0027] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0028] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0030] Figure 1 Schematic diagram of a method for real-time monitoring of building nodes based on artificial intelligence in an embodiment of the present invention;

[0031] Figure 2 Schematic diagram of a real-time monitoring system for building nodes based on artificial intelligence in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0033] Example 1:

[0034] The embodiment of the present invention provides a method for real-time monitoring of building nodes based on artificial intelligence, such as Figure 1 As shown, including:

[0035] Step 1: Map the data monitored by the monitoring terminals configured at each building node into the three-dimensional model of the building;

[0036] Step 2: Extract features from the three-dimensional model of the building to obtain building parameters;

[0037] Step 3: Input the building parameters into the pre-configured neural network model to obtain analysis results. The neural network model is pre-trained and converged for real-time analysis of the building, primarily analyzing whether the displacement, inclination, and stress data of each building node are within the permitted range.

[0038] Step 4: When the analysis results are abnormal, an early warning message is output. For example, abnormal situations include displacement exceeding a preset threshold, inclination exceeding a preset angle threshold, stress exceeding a preset stress threshold, etc.

[0039] The monitoring terminal includes: a monitoring sensor, a data acquisition unit, a processing unit, and a communication unit; wherein the monitoring sensor, the data acquisition unit, and the communication unit are electrically connected to the processing unit respectively; the processing unit collects the monitoring data of the monitoring sensor through the data acquisition unit and sends it to the outside world through the communication unit. The data acquisition unit mainly samples and collects the data of the monitoring sensor, and then the processing unit sends it to the server through the communication unit;

[0040] Among them, the monitoring sensors include: one or more combinations of displacement monitoring sensors, inclination monitoring sensors, stress monitoring sensors, and force monitoring sensors; for example, the displacement sensor can be a laser displacement meter or a fiber optic displacement sensor; the inclination monitoring sensor can be a three-axis inclination sensor, which can monitor the three-dimensional inclination angle of the building in real time and thus provide early warning of foundation settlement or structural deformation; the strain monitoring sensor can be a fiber grating strain gauge or a resistance strain gauge; the force monitoring sensor can be an axial force meter, etc.

[0041] The communication unit includes: one or more combinations of Bluetooth communication module, WIFI communication module, and Internet of Things communication module. The main function of the communication unit is to send data from the monitoring terminal to the server. Different combinations of communication units can be selected according to actual conditions.

[0042] The building parameters include: parameters indicating the building type, parameters indicating the position of each building node in the three-dimensional model, and one or more combinations of parameters indicating the average value, maximum value, and minimum value of the monitoring data corresponding to each building node.

[0043] The artificial intelligence-based real-time monitoring method for building nodes in this embodiment regresses the monitoring data of the building nodes into the three-dimensional model of the building, and then performs a comprehensive analysis through a neural network model to detect whether any abnormalities have occurred. By mapping the monitoring data to the three-dimensional model, the data of different building nodes are jointly analyzed through the three-dimensional model to achieve more accurate analysis.

[0044] Example 2:

[0045] An embodiment of the present invention provides a method for real-time monitoring of building nodes based on artificial intelligence, comprising:

[0046] Mapping the data monitored by monitoring terminals configured at each building node into the three-dimensional model of the building;

[0047] Extract features from the three-dimensional model of the building and obtain building parameters;

[0048] Input building parameters into the pre-configured neural network model to obtain analysis results;

[0049] When there are abnormalities in the analysis results, an early warning message is output.

[0050] Wherein, when constructing the three-dimensional model, the detection data of each secondary node received through the mobile terminal is mapped to the three-dimensional model constructed according to the architectural parameters of the building;

[0051] During the real-time monitoring process, the secondary nodes are tested at preset time intervals to obtain test data and the data mapped to the three-dimensional model is updated;

[0052] In the time interval between every two tests, the historical test data, the monitoring data of the master node and the pre-configured update rules are comprehensively analyzed to update the three-dimensional model based on the analysis results.

[0053] The working principle and beneficial effects of the above technical solution are:

[0054] The artificial intelligence-based real-time monitoring method for building nodes of this embodiment divides building nodes into primary nodes and secondary nodes; primary nodes are more important than secondary nodes, and monitoring terminals are configured on primary nodes to realize real-time monitoring. The reason why secondary nodes are not configured with monitoring terminals is due to cost considerations. In order to take into account both cost and monitoring effect, since secondary nodes are not monitored in real time, how to combine them with the real-time monitoring data of primary nodes to perform accurate anomaly analysis, wherein historical detection data, monitoring data of primary nodes and pre-configured update rules are comprehensively analyzed, and the three-dimensional model is updated with the analysis results. Since different types of data are analyzed in different ways, they are generally based on historical detection data, monitoring data of related primary nodes and pre-configured update rules, and different weight combinations are configured to cope with the analysis of different types of data. The specific analysis steps include: calculating the changes between the real data of each historical monitoring in the historical monitoring data, and determining the first relationship value based on the changes; through The second relationship value is determined by the change value of the data of the pre-configured associated main node and the pre-configured correlation coefficient; the third relationship value in the pre-configured update rule is extracted; the first relationship value, the second relationship value and the third relationship value are weighted and calculated to obtain the update value; the secondary node data is updated according to the update value; wherein the pre-configured update rule includes a parameter corresponding to the time-step; the third relationship value is obtained by the product of the time from the last detection and the parameter; the first relationship value is the average value of the difference between two adjacent data; the second relationship value is the sum of the product of the change value of each associated main node and the correlation coefficient; in addition, in order to update more accurately, in the process of calculating the first relationship value, the average value of the difference between the real data of the historical monitoring data and the value updated at the last moment in the corresponding previous time interval is also considered as the adjustment value of the first relationship value; adjustment guidance is provided by the difference between the historical real value and the predicted value, which helps to make the data of this update closer to the actual situation.

[0055] Example 3:

[0056] The embodiment of the present invention provides a real-time monitoring system for building nodes based on artificial intelligence, such as Figure 2 As shown, it includes: a mapping module 1, an extraction module 2, an analysis module 3 and an output module 4; wherein, the mapping module 1 maps the data monitored by the monitoring terminal configured on each building node to the three-dimensional model of the building; the extraction module 2 extracts features from the three-dimensional model of the building to obtain building parameters; the analysis module 3 inputs the building parameters into a pre-configured neural network model to obtain analysis results; when there is an abnormality in the analysis result, the output module 4 outputs an early warning message.

[0057] The monitoring terminal includes: a monitoring sensor, a data acquisition unit, a processing unit and a communication unit;

[0058] Among them, the monitoring sensor, the data acquisition unit and the communication unit are electrically connected to the processing unit respectively; the processing unit collects the monitoring data of the monitoring sensor through the data acquisition unit and sends it to the outside world through the communication unit.

[0059] The monitoring sensor includes one or more combinations of a displacement monitoring sensor, an inclination monitoring sensor, a stress monitoring sensor, and a force monitoring sensor;

[0060] The communication unit includes: a Bluetooth communication module, a WIFI communication module, an Internet of Things communication module or one or more combinations thereof.

[0061] The building parameters include: parameters indicating the building type, parameters indicating the position of each building node in the three-dimensional model, and one or more combinations of parameters indicating the average value, maximum value, and minimum value of the monitoring data corresponding to each building node.

[0062] Example 4:

[0063] The embodiment of the present invention provides a real-time monitoring system for building nodes based on artificial intelligence, such as Figure 2 As shown, it includes: a mapping module 1, an extraction module 2, an analysis module 3 and an output module 4; wherein, the mapping module 1 maps the data monitored by the monitoring terminal configured on each building node to the three-dimensional model of the building; the extraction module 2 extracts features from the three-dimensional model of the building to obtain building parameters; the analysis module 3 inputs the building parameters into a pre-configured neural network model to obtain analysis results; when there is an abnormality in the analysis result, the output module 4 outputs an early warning message.

[0064] In addition, it also includes: building modules and updating modules;

[0065] When constructing the three-dimensional model, the construction module maps the detection data of each secondary node received through the mobile terminal to the three-dimensional model constructed according to the architectural parameters of the building;

[0066] During the real-time monitoring process, the update module updates the data mapped to the three-dimensional model based on the detection data obtained by detecting the secondary nodes at preset time intervals;

[0067] In the time interval between every two detections, the update module comprehensively analyzes the historical detection data, the monitoring data of the master node and the pre-configured update rules, and updates the three-dimensional model based on the analysis results.

[0068] Example 5:

[0069] An embodiment of the present invention provides a method for real-time monitoring of building nodes based on artificial intelligence, comprising:

[0070] Mapping the data monitored by monitoring terminals configured at each building node into the three-dimensional model of the building;

[0071] Extract features from the three-dimensional model of the building and obtain building parameters;

[0072] Input building parameters into a pre-configured neural network model to obtain analysis results. The neural network model is trained and converged in advance and is used for real-time analysis of the building, mainly analyzing whether the displacement, inclination and stress data of each building node are within the permitted range.

[0073] When there are abnormalities in the analysis results, an early warning message is output.

[0074] In addition, it also includes: obtaining monitoring and analysis data of related buildings associated with the building;

[0075] Adjust the analysis results based on monitoring and analysis data to obtain predictive data;

[0076] Generate forecast and warning information based on predictive data, and generate manual monitoring tasks based on the forecast and warning information;

[0077] The 3D model is updated based on the results of the manual monitoring task and the warning information is regenerated after the update. The updating of the 3D model is to map the monitoring data contained in the execution results to the 3D model;

[0078] The determination of the relevant buildings includes: extracting features from the initial three-dimensional model to obtain a plurality of first feature parameters; the first feature parameters include: parameters indicating the type of the three-dimensional model (i.e., the type of the building), parameters indicating the size of each position of the three-dimensional model, etc.;

[0079] Finite element segmentation is performed on the initial three-dimensional model and a finite element model is constructed. Feature extraction is performed on the finite element model to obtain a plurality of second characteristic parameters. The finite element segmentation rule may adopt an equal volume segmentation method for segmentation, and attributes such as the weight and material type of the entity corresponding to the segmented unit are assigned to the finite element unit. The second characteristic parameters include parameters representing the distribution of various attributes in the finite element unit within corresponding preset intervals.

[0080] Extracting features from the soil layer data at the location of the building to obtain multiple third characteristic parameters; the third characteristic parameters include: parameters indicating the type of soil layer, parameters indicating the content of each component of the soil layer, etc.;

[0081] Extract features of surface objects within a preset area around the building to obtain multiple fourth feature parameters; the fourth feature parameters include: parameters indicating the type of each surface object, parameters indicating the relative position relationship (direction, distance) between each surface object and the building, etc.;

[0082] The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter are combined to obtain a data set for association analysis; the data set is formed by arranging the first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter in sequence;

[0083] Calculate the similarity between the building and the corresponding associated data sets of each other building; associate the other buildings with similarities greater than a preset threshold and in the top N positions with the building; and use the similarity as the corresponding association degree;

[0084] Taking the inclination angle as an example, the analysis results are adjusted based on the monitoring and analysis data to obtain predictive data, including:

[0085] Analyze the monitoring and analysis data of each related building to determine the data change; wherein the data change is the average value of the difference between the data of two adjacent monitoring times;

[0086] A weighted analysis array is formed based on the distance values ​​and correlation between other buildings;

[0087] The corresponding weight set is retrieved from the pre-configured weight analysis library using the weight analysis data; the weight set in the weight analysis library corresponds one-to-one with the weight analysis data. When constructing the weight analysis library, the smaller the distance value, the greater the weight; the greater the correlation, the greater the weight.

[0088] The average value is weighted and calculated based on the weights in the weight set, and then the weighted sum is calculated with the difference between the corresponding data in the analysis result and the previous value of the data. The sum of the obtained value and the value of the previous data is used as the predicted value; wherein the first weight and the second weight used in the second weighted sum correspond to the difference between the corresponding data in the analysis result and the previous data and the value calculated by the first weighted sum, respectively;

[0089] Among them, based on the predictive data, predictive warning information is generated, and based on the predictive warning information, manual monitoring tasks are generated, including:

[0090] Use the rules for generating early warning information to judge the predictive data and generate predictive warning information;

[0091] According to the prediction and warning information, the corresponding manual monitoring task is retrieved from the pre-configured manual monitoring task generation library; the manual monitoring task generation library is configured for prior analysis, and the prediction and warning information is correspondingly associated with the task group composed of manual monitoring tasks in the library; the task group includes at least one manual monitoring task, and the manual monitoring task includes: the location of the detected node in the building, the type of data to be monitored, the monitoring operation guide, etc.

[0092] This embodiment performs predictive analysis on buildings by performing correlation analysis and prediction, thereby performing predictive warnings and arranging manual monitoring and determination on this basis to further ensure the health of the buildings.

[0093] Example 6:

[0094] An embodiment of the present invention provides an artificial intelligence-based real-time monitoring system for building nodes, comprising: a mapping module, an extraction module, an analysis module, and an output module; wherein the mapping module maps the data monitored by the monitoring terminals configured on each building node to a three-dimensional model of the building; the extraction module extracts features from the three-dimensional model of the building to obtain building parameters; the analysis module inputs the building parameters into a pre-configured neural network model to obtain analysis results; and when there is an abnormality in the analysis result, the output module outputs an early warning message.

[0095] In addition, it also includes: association prediction analysis module;

[0096] The association prediction analysis module performs the following operations:

[0097] Obtain monitoring and analysis data of related buildings associated with the building;

[0098] Adjust the analysis results based on monitoring and analysis data to obtain predictive data;

[0099] Generate forecast and warning information based on predictive data, and generate manual monitoring tasks based on the forecast and warning information;

[0100] The 3D model is updated based on the results of the manual monitoring task and the warning information is regenerated after the update. The updating of the 3D model is to map the monitoring data contained in the execution results to the 3D model;

[0101] The determination of the relevant buildings includes: extracting features from the initial three-dimensional model to obtain a plurality of first feature parameters; the first feature parameters include: parameters indicating the type of the three-dimensional model (i.e., the type of the building), parameters indicating the size of each position of the three-dimensional model, etc.;

[0102] Finite element segmentation is performed on the initial three-dimensional model and a finite element model is constructed. Feature extraction is performed on the finite element model to obtain a plurality of second characteristic parameters. The finite element segmentation rule may adopt an equal volume segmentation method for segmentation, and attributes such as the weight and material type of the entity corresponding to the segmented unit are assigned to the finite element unit. The second characteristic parameters include parameters representing the distribution of various attributes in the finite element unit within corresponding preset intervals.

[0103] Extracting features from the soil layer data at the location of the building to obtain multiple third characteristic parameters; the third characteristic parameters include: parameters indicating the type of soil layer, parameters indicating the content of each component of the soil layer, etc.;

[0104] Extract features of surface objects within a preset area around the building to obtain multiple fourth feature parameters; the fourth feature parameters include: parameters indicating the type of each surface object, parameters indicating the relative position relationship (direction, distance) between each surface object and the building, etc.;

[0105] The first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter are combined to obtain a data set for association analysis; the data set is formed by arranging the first characteristic parameter, the second characteristic parameter, the third characteristic parameter and the fourth characteristic parameter in sequence;

[0106] Calculate the similarity between the building and the corresponding associated data sets of each other building; associate the other buildings with similarities greater than a preset threshold and in the top N positions with the building; and use the similarity as the corresponding association degree;

[0107] Taking the inclination angle as an example, the analysis results are adjusted based on the monitoring and analysis data to obtain predictive data, including:

[0108] Analyze the monitoring and analysis data of each related building to determine the data change; wherein the data change is the average value of the difference between the data of two adjacent monitoring times;

[0109] A weighted analysis array is formed based on the distance values ​​and correlation between other buildings;

[0110] The corresponding weight set is retrieved from the pre-configured weight analysis library using the weight analysis data; the weight set in the weight analysis library corresponds one-to-one with the weight analysis data. When constructing the weight analysis library, the smaller the distance value, the greater the weight; the greater the correlation, the greater the weight.

[0111] The average value is weighted and calculated based on the weights in the weight set, and then the weighted sum is calculated with the difference between the corresponding data in the analysis result and the previous value of the data. The sum of the obtained value and the value of the previous data is used as the predicted value; wherein the first weight and the second weight used in the second weighted sum correspond to the difference between the corresponding data in the analysis result and the previous data and the value calculated by the first weighted sum, respectively;

[0112] Among them, based on the predictive data, predictive warning information is generated, and based on the predictive warning information, manual monitoring tasks are generated, including:

[0113] Use the rules for generating early warning information to judge the predictive data and generate predictive warning information;

[0114] According to the prediction and warning information, the corresponding manual monitoring task is retrieved from the pre-configured manual monitoring task generation library; the manual monitoring task generation library is configured for prior analysis, and the prediction and warning information is correspondingly associated with the task group composed of manual monitoring tasks in the library; the task group includes at least one manual monitoring task, and the manual monitoring task includes: the location of the detected node in the building, the type of data to be monitored, the monitoring operation guide, etc.

[0115] Example 7:

[0116] An embodiment of the present invention provides a method for real-time monitoring of building nodes based on artificial intelligence, comprising:

[0117] Mapping the data monitored by monitoring terminals configured at each building node into the three-dimensional model of the building;

[0118] Extract features from the three-dimensional model of the building and obtain building parameters;

[0119] Input building parameters into a pre-configured neural network model to obtain analysis results. The neural network model is trained and converged in advance and is used for real-time analysis of the building, mainly analyzing whether the displacement, inclination and stress data of each building node are within the permitted range.

[0120] When there are abnormalities in the analysis results, an early warning message is output.

[0121] Also includes:

[0122] Get the warning information of the associated buildings;

[0123] Analyze the warning information and determine the relevant nodes of the warning; the relevant nodes are the nodes corresponding to the triggering of the warning information;

[0124] Determine the node corresponding to the relevant node from the building, and generate a manual monitoring task based on the node; the corresponding node on the building corresponds to the relevant node, and the corresponding relationship can be determined by the similarity between the node description sets of each node pre-configured, that is, if the similarity between the node description set of each node on the building and the node description set of the relevant node is greater than or equal to a similarity threshold, it can be considered that the two are in a corresponding relationship; the parameters in the node description set include: parameters representing the position of the node in the three-dimensional model, parameters representing the distribution of various attributes in the finite element unit of the relevant area corresponding to the node (the area with a preset distance from the node as the center) within each corresponding preset interval, etc.

[0125] The three-dimensional model is updated according to the execution results of the manual monitoring task and the early warning judgment is re-performed after the update.

[0126] This embodiment performs manual monitoring of buildings through early warning of associated buildings, realizes associated early warning of the same group, and further ensures the health status of the buildings.

[0127] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A real-time monitoring method for building nodes based on artificial intelligence, characterized in that: include: Mapping the data monitored by monitoring terminals configured at each building node into the three-dimensional model of the building; Extract features from the three-dimensional model of the building and obtain building parameters; Input building parameters into the pre-configured neural network model to obtain analysis results; When there are abnormalities in the analysis results, an early warning message is output.

2. The method for real-time monitoring of building nodes based on artificial intelligence according to claim 1, characterized in that: The monitoring terminal includes: monitoring sensor, data acquisition unit, processing unit and communication unit; Among them, the monitoring sensor, the data acquisition unit and the communication unit are electrically connected to the processing unit respectively; the processing unit collects the monitoring data of the monitoring sensor through the data acquisition unit and sends it to the outside world through the communication unit.

3. The method for real-time monitoring of building nodes based on artificial intelligence according to claim 2, characterized in that: The monitoring sensor includes: a combination of one or more of a displacement monitoring sensor, an inclination monitoring sensor, a stress monitoring sensor, and a force monitoring sensor; The communication unit includes: a Bluetooth communication module, a WIFI communication module, an Internet of Things communication module or one or more combinations thereof.

4. The method for real-time monitoring of building nodes based on artificial intelligence according to claim 1, characterized in that: The building parameters include: parameters representing the building type, parameters representing the position of each building node in the three-dimensional model, and one or more combinations of parameters representing the average value, maximum value, and minimum value of the monitoring data corresponding to each building node.

5. The method for real-time monitoring of building nodes based on artificial intelligence according to claim 1, wherein: When constructing the three-dimensional model, the detection data of each secondary node received by the mobile terminal is mapped to the three-dimensional model constructed according to the architectural parameters of the building; During the real-time monitoring process, the secondary nodes are tested at preset time intervals to obtain test data and the data mapped to the three-dimensional model is updated; In the time interval between every two tests, the historical test data, the monitoring data of the master node and the pre-configured update rules are comprehensively analyzed to update the three-dimensional model based on the analysis results.

6. A real-time monitoring system for building nodes based on artificial intelligence, characterized in that: include: Mapping module, extraction module, analysis module and output module; among them, the mapping module maps the data monitored by the monitoring terminals configured on each building node to the three-dimensional model of the building; the extraction module extracts features from the three-dimensional model of the building and obtains building parameters; the analysis module inputs the building parameters into a pre-configured neural network model to obtain analysis results; when there is an abnormality in the analysis result, the output module outputs an early warning message.

7. The artificial intelligence-based real-time monitoring system for building nodes according to claim 6, characterized in that: The monitoring terminal includes: monitoring sensor, data acquisition unit, processing unit and communication unit; Among them, the monitoring sensor, the data acquisition unit and the communication unit are electrically connected to the processing unit respectively; the processing unit collects the monitoring data of the monitoring sensor through the data acquisition unit and sends it to the outside world through the communication unit.

8. The artificial intelligence-based real-time monitoring system for building nodes according to claim 7, characterized in that: The monitoring sensor includes: a combination of one or more of a displacement monitoring sensor, an inclination monitoring sensor, a stress monitoring sensor, and a force monitoring sensor; The communication unit includes: a Bluetooth communication module, a WIFI communication module, an Internet of Things communication module or one or more combinations thereof.

9. The artificial intelligence-based real-time monitoring system for building nodes according to claim 6, characterized in that: The building parameters include: parameters representing the building type, parameters representing the position of each building node in the three-dimensional model, and one or more combinations of parameters representing the average value, maximum value, and minimum value of the monitoring data corresponding to each building node.

10. The artificial intelligence-based real-time monitoring system for building nodes according to claim 6, characterized in that: Also includes: Building modules and updating modules; When constructing the three-dimensional model, the construction module maps the detection data of each secondary node received through the mobile terminal to the three-dimensional model constructed according to the architectural parameters of the building; During the real-time monitoring process, the update module updates the data mapped to the three-dimensional model based on the detection data obtained by detecting the secondary nodes at preset time intervals; In the time interval between every two detections, the update module comprehensively analyzes the historical detection data, the monitoring data of the master node and the pre-configured update rules, and updates the three-dimensional model based on the analysis results.

Images