CN117111544A

CN117111544A - Automatic-adaptation building internet of things monitoring method and system

Info

Publication number: CN117111544A
Application number: CN202311341546.9A
Authority: CN
Inventors: 王志杰
Original assignee: China Technology Co ltd Shenzhen Branch
Current assignee: China Technology Co ltd Shenzhen Branch
Priority date: 2023-10-17
Filing date: 2023-10-17
Publication date: 2023-11-24
Anticipated expiration: 2043-10-17
Also published as: CN117111544B

Abstract

The invention relates to the field of monitoring of the Internet of things, and discloses an automatically-adapted building Internet of things monitoring method and system, which are used for improving the efficiency and accuracy of the adaptation of monitoring equipment, further guaranteeing the monitoring effect of a building and improving the safety coefficient of the building. The method comprises the following steps: acquiring three-dimensional structure data of a target building through laser scanning, and constructing a building digital finite element model of the target building according to the three-dimensional structure data; establishing an initial simulation monitoring point set of a target building according to the building digital finite element model, and verifying and optimizing the effectiveness of the initial simulation monitoring point set through a preset PLC (programmable logic controller) to obtain the target simulation monitoring point set; acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC, and extracting characteristics of the monitoring parameter data set to obtain a monitoring characteristic data set; and inputting the monitoring characteristic data set into a preset building anomaly analysis model to perform anomaly analysis on building monitoring data, and obtaining an anomaly analysis result.

Description

Automatic-adaptation building internet of things monitoring method and system

Technical Field

The invention relates to the field of monitoring of the Internet of things, in particular to an automatically-adapted building Internet of things monitoring method and system.

Background

Building monitoring and management becomes critical in order to ensure safety, reliability and efficiency of the building.

Traditional building monitoring methods typically rely on manual inspection and manual data collection, which is time consuming and labor intensive, as well as prone to omission and inaccuracy. With the rapid development of internet of things (IoT) and digital technology, an automatically-adapted building internet of things monitoring method has been developed, which provides a brand-new solution for building monitoring and management by combining laser scanning, finite element model, deep learning and automation technology.

Disclosure of Invention

The invention provides an automatically-adapted building internet of things monitoring method and system, which are used for improving the efficiency and accuracy of monitoring equipment adaptation, further guaranteeing the monitoring effect of a building and improving the safety coefficient of the building.

The first aspect of the invention provides an automatically-adapted building internet of things monitoring method, which comprises the following steps:

acquiring three-dimensional structure data of a target building through laser scanning, and constructing a building digital finite element model of the target building according to the three-dimensional structure data;

establishing an initial simulation monitoring point set of the target building according to the building digital finite element model, and verifying and optimizing the effectiveness of the initial simulation monitoring point set through a preset PLC (programmable logic controller) to obtain the target simulation monitoring point set;

Acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC, and extracting features of the monitoring parameter data set to obtain a monitoring feature data set;

and inputting the monitoring characteristic data set into a preset building anomaly analysis model to perform building monitoring data anomaly analysis to obtain an anomaly analysis result.

With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the obtaining three-dimensional structure data of a target building through laser scanning, and constructing a building digital finite element model of the target building according to the three-dimensional structure data includes:

carrying out three-dimensional laser scanning on a target building through preset laser scanning equipment, and acquiring multi-angle building image data of the target building;

carrying out load area segmentation on the multi-angle building image data to obtain a plurality of building load area images;

digital information extraction is carried out on the building load area images to obtain load area coordinates and geometric information;

carrying out pixel screening on the plurality of building load area images according to the load area coordinates and the geometric information to obtain building pixel data;

Carrying out three-dimensional reconstruction on the target building according to the building pixel point data to obtain three-dimensional structure data;

performing grid discretization on the three-dimensional structure data to obtain discrete grids, and acquiring structural elements of the target building;

and according to the structural elements, grid optimization is carried out on the discrete grids, and a building digital finite element model is generated.

With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the creating an initial analog monitoring point set of the target building according to the building digital finite element model, and performing validity verification and optimization on the initial analog monitoring point set by using a preset PLC to obtain a target analog monitoring point set, includes:

carrying out mechanical property analysis on the target building according to the building digital finite element model to obtain building mechanical property characteristics, and creating an initial simulation monitoring point set of the target building according to the building mechanical property characteristics;

establishing communication connection with the initial simulation monitoring point set through a preset PLC, and performing operation verification on the initial simulation monitoring point set in a simulation environment to obtain an operation verification data set of the initial simulation monitoring point set;

Carrying out validity analysis on the operation verification data set to obtain a validity analysis result, and carrying out group initialization on the initial simulation monitoring point set according to the validity analysis result to obtain an initialization simulation monitoring point group;

and carrying out simulated monitoring point optimization analysis on the initialized simulated monitoring point group through a preset genetic algorithm to generate a target simulated monitoring point set.

With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the performing mechanical performance analysis on the target building according to the building digital finite element model to obtain building mechanical performance characteristics, and creating an initial simulation monitoring point set of the target building according to the building mechanical performance characteristics includes:

carrying out mechanical property analysis on the target building according to the building digital finite element model to obtain building mechanical property data;

performing characteristic analysis on the building mechanical property data to obtain building mechanical property characteristics;

and creating an initial simulation monitoring point set of the target building according to the building mechanical property characteristics.

With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, performing, by a preset genetic algorithm, optimization analysis of the simulation monitor points on the initialized simulation monitor point group, to generate a target simulation monitor point set, includes:

Respectively calculating the fitness of a plurality of first candidate simulation monitoring point sets in the initialized simulation monitoring point group through a preset genetic algorithm to obtain the first fitness of each first candidate simulation monitoring point set;

according to the first fitness of each first candidate simulation monitoring point set, carrying out group division on the plurality of first candidate simulation monitoring point sets to obtain an infected group, an easy-to-infect group and an uninfected group;

performing propagation and mutation operations on the infected population, and performing genetic, propagation and mutation operations on the easy-to-infect population and the uninfected population to obtain a plurality of second candidate simulated monitoring point sets;

and respectively calculating the second fitness of each second candidate simulation monitoring point set, and carrying out optimization analysis on the plurality of second candidate simulation monitoring point sets according to the second fitness to obtain a target simulation monitoring point set.

With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the obtaining, by the PLC, a monitoring parameter data set corresponding to the target analog monitoring point set, and performing feature extraction on the monitoring parameter data set, to obtain a monitoring feature data set, includes:

Acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC;

performing data cleaning and parameter standardization processing on the monitoring parameter data set to obtain a standard parameter data set;

according to the monitoring parameter types, parameter clustering is carried out on the standard parameter data set to obtain standard parameter data corresponding to each monitoring parameter type;

carrying out time sequence association processing on the standard parameter data corresponding to each monitoring parameter type to obtain time sequence standard parameters corresponding to each monitoring parameter type;

performing curve fitting on the time sequence standard parameters corresponding to each monitoring parameter type to obtain a target monitoring curve corresponding to each monitoring parameter type;

extracting curve characteristics of the target monitoring curve respectively to obtain a curve characteristic set corresponding to each monitoring parameter type;

and generating a corresponding monitoring characteristic data set according to the curve characteristic set corresponding to each monitoring parameter type.

With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, inputting the monitoring feature data set into a preset building anomaly analysis model to perform anomaly analysis on building monitoring data, to obtain an anomaly analysis result, includes:

Normalizing the monitoring feature data set to obtain a plurality of normalized monitoring features, and vector encoding the plurality of normalized monitoring features to generate a target monitoring feature vector;

inputting the target monitoring feature vector into a preset building abnormality analysis model, wherein the building abnormality analysis model comprises a two-layer convolution long short-time memory network, a full-connection layer and an output layer;

performing high-dimensional feature extraction on the target monitoring feature vector through the two-layer convolution long-short-time memory network to obtain a high-dimensional monitoring feature vector;

carrying out abnormal probability prediction on the high-dimensional monitoring feature vector through the full connection layer to obtain an abnormal probability prediction value;

constructing a mapping relation table between the abnormal probability and the abnormal result, matching the mapping relation table according to the abnormal probability predicted value, and outputting a corresponding abnormal analysis result through the output layer, wherein the abnormal analysis result comprises: types of anomalies, locations, and causes of anomalies.

The second aspect of the present invention provides an automatically adapted building internet of things monitoring system, the automatically adapted building internet of things monitoring system comprising:

The acquisition module is used for acquiring three-dimensional structure data of a target building through laser scanning and constructing a building digital finite element model of the target building according to the three-dimensional structure data;

the building digital finite element model is used for establishing a building digital finite element model, and acquiring a building digital finite element model, wherein the building digital finite element model is used for acquiring a building digital finite element model;

the feature extraction module is used for acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC, and carrying out feature extraction on the monitoring parameter data set to obtain a monitoring feature data set;

and the analysis module is used for inputting the monitoring characteristic data set into a preset building anomaly analysis model to perform anomaly analysis on building monitoring data so as to obtain an anomaly analysis result.

A third aspect of the present invention provides an automatically adapted building internet of things monitoring device, comprising: a memory and at least one processor, the memory having instructions stored therein; and the at least one processor calls the instruction in the memory so that the automatically-adapted building internet of things monitoring equipment executes the automatically-adapted building internet of things monitoring method.

A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein that, when run on a computer, cause the computer to perform the above-described automatically adapted building internet of things monitoring method.

According to the technical scheme provided by the invention, three-dimensional structure data of a target building are obtained through laser scanning, and a building digital finite element model of the target building is constructed according to the three-dimensional structure data; establishing an initial simulation monitoring point set of a target building according to the building digital finite element model, and verifying and optimizing the effectiveness of the initial simulation monitoring point set through a preset PLC (programmable logic controller) to obtain the target simulation monitoring point set; acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC, and extracting characteristics of the monitoring parameter data set to obtain a monitoring characteristic data set; the monitoring characteristic data set is input into a preset building anomaly analysis model to perform building monitoring data anomaly analysis to obtain an anomaly analysis result. Compared with the traditional manual inspection, the system can greatly improve the monitoring efficiency, monitor the building state in real time, and reduce the monitoring and maintenance cost. Through the digital finite element model, the response of the building under different working conditions can be accurately simulated. This provides more accurate monitoring data, facilitates early detection of structural problems, anomalies, or performance degradation, and takes timely action to repair and improve. The combination of the automatically adapted monitoring point set and the PLC enables the monitoring data to be transmitted and analyzed in real time. When abnormality is found, the system can immediately give out early warning, thereby being beneficial to preventing potential danger and reducing loss. Through a deep learning model, the method can conduct high-dimensional feature extraction and analysis on the monitoring data. Such deep analysis helps to understand building behavior more deeply, detect implicit problems, and provide detailed anomaly analysis results, including anomaly type, location, and cause. The optimization of the monitoring point set and the automatic verification of the PLC enable the system to automatically adjust the monitoring points and parameters so as to adapt to different working conditions and requirements, so that the efficiency and accuracy of the monitoring equipment adaptation are improved, the monitoring effect of the building is further guaranteed, and the safety coefficient of the building is improved.

Drawings

Fig. 1 is a schematic diagram of an embodiment of a building internet of things monitoring method automatically adapted in an embodiment of the present invention;

FIG. 2 is a flow chart of validation and optimization in accordance with an embodiment of the present invention;

FIG. 3 is a flow chart of creating an initial set of simulated monitoring points in an embodiment of the present invention;

FIG. 4 is a flow chart of an exemplary monitoring point optimization analysis in accordance with an embodiment of the present invention;

FIG. 5 is a schematic diagram of an embodiment of an automatically adapted building Internet of things monitoring system according to an embodiment of the present invention;

fig. 6 is a schematic diagram of an embodiment of an automatically adapted building internet of things monitoring device according to an embodiment of the present invention.

Detailed Description

The embodiment of the invention provides an automatically-adaptive building internet of things monitoring method and system, which are used for improving the efficiency and accuracy of monitoring equipment adaptation, further guaranteeing the monitoring effect of a building and improving the safety coefficient of the building. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For easy understanding, a specific flow of the embodiment of the present invention is described below, referring to fig. 1, and one embodiment of an automatically adapted building internet of things monitoring method in the embodiment of the present invention includes:

s101, acquiring three-dimensional structure data of a target building through laser scanning, and constructing a building digital finite element model of the target building according to the three-dimensional structure data;

it can be understood that the execution body of the invention can be an automatically-adapted building internet of things monitoring system, and can also be a terminal or a server, and the execution body is not limited in the specific description. The embodiment of the invention is described by taking a server as an execution main body as an example.

Specifically, the server uses preset laser scanning equipment to perform three-dimensional laser scanning on the target building so as to acquire detailed building structure information. This process captures multi-angle building image data of the building from different angles, providing rich input for subsequent steps. Subsequently, the multi-angle building image data is subjected to load region segmentation. By splitting, the server is able to divide building image data into multiple load area images, each representing a different portion or area within the building. For example, in a multi-story building, each floor may be considered a load zone. And extracting digital information from each load area image, wherein the digital information comprises coordinates and geometric information of the load area. This information is critical to subsequent data processing and modeling because it helps the server to understand the structure and characteristics of each region. After the coordinates and the geometric information of the load area are obtained, the server performs pixel screening to determine the position and the attribute of each pixel. The purpose of this step is to refine the server data further, providing a more accurate input for three-dimensional reconstruction. Through this screening process, the server can obtain building pixel data reflecting details and features of the building. And carrying out three-dimensional reconstruction by using the building pixel point data. At this stage, the server converts the pixel point data into three-dimensional structure data of the building, creating an accurate building model. The model contains the shape, size and structure of the building, and provides a solid foundation for monitoring and analysis. Then, grid discretization processing is carried out on the generated three-dimensional structure data, and the building is divided into small discrete grids. This step helps to divide the building structure into smaller units for finer analysis and modeling. Meanwhile, the server also acquires structural elements of the building, and the elements are key for constructing a digital finite element model. And (3) carrying out grid optimization on the discrete grids according to the obtained structural elements, and generating a digital finite element model of the building. This model is a highly accurate representation that can be used to monitor the status of a building, perform simulations, and perform analyses.

S102, creating an initial simulation monitoring point set of a target building according to a building digital finite element model, and verifying and optimizing the effectiveness of the initial simulation monitoring point set through a preset PLC to obtain the target simulation monitoring point set;

specifically, the server performs mechanical property analysis according to the building digital finite element model to obtain mechanical property characteristics of the building. This step is to understand the structural features and mechanical behavior of the building. For example, for a building, this involves analyzing its load-bearing structure, vibration characteristics, etc. And creating an initial simulation monitoring point set according to the mechanical property characteristics of the building. These monitoring sites are designed to effectively monitor the mechanical properties of the building and provide real-time data when needed. These points may include sensors, measuring devices, etc. Then, a communication connection with the initial set of analog monitoring points is established by a preset Programmable Logic Controller (PLC), and the initial set of analog monitoring points is run and verified in the analog environment. In this process, the simulation environment simulates the actual running situation of the building to ensure the function and effectiveness of the initial monitoring point set. Next, a validity analysis is performed on the operation verification data set. This step aims to evaluate the performance, including accuracy and stability, of the initial set of simulated monitoring points. The results of the validity analysis will be used to determine if optimization of the set of monitoring points is required. And initializing the initial simulation monitoring point set in groups according to the effectiveness analysis result, and adjusting the monitoring point set to improve the performance and adaptability of the monitoring point set. This initialized simulated monitoring point population may include a set of modified monitoring points. And carrying out simulated monitoring point optimization analysis on the initialized simulated monitoring point group through a preset genetic algorithm. The genetic algorithm is an optimization technology, and can automatically find the optimal monitoring point position configuration so as to meet specific performance requirements. The result of this step will be a target set of simulated monitoring points that optimally adapt to the point configuration of the building's monitoring needs, taking into account the building's mechanical properties and effectiveness analysis. Consider, for example, a high-rise building. And (3) carrying out mechanical property analysis according to the building digital finite element model, and finding that certain floors are easily affected by wind power. Based on this analysis, the initial set of simulated monitoring points includes wind speed and direction sensors. These sensors are then validated in a simulated environment by the PLC to obtain a running validation dataset. Validity analysis shows that under certain conditions, these sensor data are not accurate enough. Thus, initializing a population of simulated monitoring points will include more sensors, such as wind pressure sensors, to improve the accuracy of the monitoring. The genetic algorithm can automatically select the optimal monitoring point position configuration to ensure that the mechanical properties of the building are effectively monitored under various conditions.

The server analyzes the mechanical properties of the target building by using the building digital finite element model. This step involves calculating the behavior of the building under different mechanical conditions, such as stress, vibration, etc. And the server obtains the mechanical property data of the building through a finite element analysis method. After the mechanical property data of the building are obtained, the data are required to be subjected to characteristic analysis so as to extract key mechanical property characteristics. This may involve techniques of statistical analysis, pattern recognition, spectrum analysis, etc., to determine which aspects of performance characteristics are most critical to monitoring of the building. According to the mechanical property characteristics of the building, an initial simulation monitoring point set can be created. This set of points should include the location and type of sensors or monitoring devices to capture and monitor the mechanical performance characteristics of the building when needed. These monitoring points should be able to effectively reflect the dynamic behavior of the building. Consider, for example, the case of a high-rise office building. And the server obtains the vibration condition of the building under different wind speeds through the mechanical property analysis of the building digital finite element model. In this embodiment, the server focuses on the vibration frequency and amplitude of the building as mechanical performance characteristics. Through the data feature analysis, the server determines the primary vibration frequency and amplitude of the building at a particular wind speed. These characteristics indicate which vibrations are most pronounced, affecting the stability of the building structure. Based on these mechanical properties, the server creates an initial set of simulated monitoring points. The server comprises a vibration sensor which is arranged at a key structural part of the building so as to monitor the vibration condition in real time. In addition, the server may also include wind speed and wind direction sensors to capture external environmental factors. As wind speed increases, the vibration sensor may detect changes in vibration frequency and amplitude and transmit data to the monitoring system. The server analyzes the data and if an abnormal vibration signature is detected, an alarm will be triggered or appropriate action will be taken, such as notifying a building manager or closing a portion of the floors to ensure safety.

And calculating the fitness of a plurality of first candidate simulated monitoring point sets in the initialized simulated monitoring point group by using a genetic algorithm. Fitness evaluation is typically based on specific performance indicators or objective functions, related to monitoring needs and performance criteria of the building. This step helps to understand the efficacy of each candidate point set in meeting the monitoring objective. The plurality of first candidate simulated monitoring point sets are divided into different groups according to the first fitness of each first candidate simulated monitoring point set. Typically, these populations include "infected populations" (typically containing a set of points with a high fitness, representing good monitoring performance), "vulnerable populations" (requiring improved sets of points), and "uninfected populations" (sets of points with a relatively low fitness). Different genetic operations are performed on the simulated monitoring point sets in different populations. For "infected populations," breeding and mutation operations can be performed to preserve and improve the high fitness monitoring point set. Genetic, reproductive and mutation operations are also required for "susceptible population" and "uninfected population" to introduce diversity and improvement to help search for better monitoring point sets. For each second set of candidate simulated monitoring points, a second fitness is calculated. This fitness represents the performance of the newly generated set of monitoring points in meeting the monitoring objective after genetic manipulation. Based on the second fitness, an optimization analysis is performed to determine which second set of candidate simulated monitoring points perform best. This analysis involves selecting the most appropriate set of monitoring points or trade-offs and optimizations based on a number of performance metrics. Ultimately, this process generates a set of target simulated monitoring points for actual monitoring.

S103, acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC, and extracting features of the monitoring parameter data set to obtain a monitoring feature data set;

it should be noted that, a PLC system is used to establish a communication connection with a sensor or a monitoring device in the target simulation monitoring point set, so as to obtain a real-time monitoring parameter data set. These data include various parameters related to building performance and safety, such as temperature, humidity, vibration, etc. And after the monitoring parameter data are obtained, data cleaning and parameter standardization processing are carried out. Data cleansing may include removing outliers, processing missing data, etc., to ensure the quality and reliability of the data. The parameter normalization process may unify the data of different sensors on the same scale for subsequent processing and analysis. And carrying out parameter clustering on the standard parameter data set according to different monitoring parameter types. This step may help to classify parameters of similar nature for subsequent processing and analysis. For example, temperature and humidity data are clustered together, and vibration data are clustered together. And carrying out time sequence association processing on the standard parameter data of each monitoring parameter type. This involves correlating the data at different points in time to obtain time series data. This helps to understand the trend of the monitored parameter over time. And performing curve fitting on the time sequence standard parameters of each monitoring parameter type. This step aims at finding the best mathematical model to describe the variation of the parameters over time. The fitted curve may be a linear, polynomial, exponential, or other different type of function. And carrying out curve characteristic extraction on the fitting curve of each monitoring parameter type. This includes extracting key features of the curve such as maxima, minima, averages, fluctuations, periodicity, etc. These features enable capturing important properties of the monitored parameters. And generating a monitoring characteristic data set according to the curve characteristic set corresponding to each monitoring parameter type. This data set includes monitoring features for each parameter type for subsequent analysis and decision-making. For example, consider a monitoring system for a tall building that includes temperature, humidity and vibration sensors. The PLC system periodically acquires data from these sensors. These data were data cleaned to remove any outliers and the temperature and humidity data were normalized to the same temperature and humidity range. Then, parameter clustering is performed on the standard parameter data set, temperature and humidity data are clustered together, and vibration data are clustered independently. And carrying out time sequence association processing on each parameter type to acquire time sequence data of temperature, humidity and vibration. Curve fitting is performed on the time series data, for example, using an exponential function to fit the trend of temperature over time. Features such as maximum temperature, minimum humidity, vibration amplitude, etc. are then extracted from these fitted curves. A monitoring characteristic dataset is generated including monitoring characteristics of temperature, humidity and vibration. This data set can be used for real-time monitoring and anomaly detection of the building to ensure the safety and performance of the building.

S104, inputting the monitoring characteristic data set into a preset building anomaly analysis model to perform anomaly analysis on building monitoring data, and obtaining an anomaly analysis result.

Specifically, the monitoring feature data set is normalized to ensure that different features have the same scale. This helps to improve the performance of the model. The plurality of normalized monitoring features are then combined into a target monitoring feature vector. This vector contains key features for building monitoring. And inputting the target monitoring feature vector into a preset building anomaly analysis model. This model is typically composed of multiple layers, including a two-layer convolutional long short-Term Memory network (LSTM), fully-connected layers, and output layers, according to the description. These layers will work cooperatively to extract features and conduct anomaly analysis. And extracting high-dimensional characteristics of the target monitoring characteristic vector through a two-layer convolution LSTM network. The convolution LSTM network can effectively capture the time sequence relation and the space relation between the features, so that the dynamic property of the monitoring data is better understood. And after the high-dimensional feature extraction, carrying out anomaly probability prediction on the high-dimensional monitoring feature vector through the full-connection layer. The goal of this step is to generate an anomaly probability prediction value indicating whether the monitored data is anomalous. And constructing a mapping relation table between the abnormal probability and the abnormal result, wherein the table correlates different abnormal probabilities with the abnormal type, the abnormal position and the abnormal reason. And matching the mapping relation table according to the abnormal probability predicted value, and obtaining a corresponding abnormal analysis result from the output layer. This result typically includes the type of anomaly (e.g., temperature anomaly, humidity anomaly, etc.), location (at a particular location of the building), and the cause of the anomaly (e.g., equipment failure, external factors, etc.). Consider, for example, a monitoring system for a high-rise office building that monitors indoor temperature and humidity. And inputting the monitoring characteristic data set of the indoor temperature and the indoor humidity into a building anomaly analysis model for analysis. And normalizing the temperature and humidity data, and constructing a target monitoring feature vector which comprises normalized temperature and humidity features. This target monitoring feature vector is input into the building anomaly analysis model, comprising a two-layer convolution LSTM network, a full connection layer, and an output layer. The convolution LSTM network can conduct high-dimensional feature extraction on temperature and humidity data, and captures time sequence and spatial relation between the temperature and humidity data. Then, the full connection layer predicts the anomaly probability of the high-dimensional features. The model then uses the mapping table to map the anomaly probabilities to anomaly analysis results. For example, if the abnormality probability indicates a temperature abnormality and the abnormality probability is high, the output abnormality analysis result includes the abnormality type, the position, and the cause of the abnormality.

In the embodiment of the invention, three-dimensional structure data of a target building is obtained through laser scanning, and a building digital finite element model of the target building is constructed according to the three-dimensional structure data; establishing an initial simulation monitoring point set of a target building according to the building digital finite element model, and verifying and optimizing the effectiveness of the initial simulation monitoring point set through a preset PLC (programmable logic controller) to obtain the target simulation monitoring point set; acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC, and extracting characteristics of the monitoring parameter data set to obtain a monitoring characteristic data set; the monitoring characteristic data set is input into a preset building anomaly analysis model to perform building monitoring data anomaly analysis to obtain an anomaly analysis result. Compared with the traditional manual inspection, the system can greatly improve the monitoring efficiency, monitor the building state in real time, and reduce the monitoring and maintenance cost. Through the digital finite element model, the response of the building under different working conditions can be accurately simulated. This provides more accurate monitoring data, facilitates early detection of structural problems, anomalies, or performance degradation, and takes timely action to repair and improve. The combination of the automatically adapted monitoring point set and the PLC enables the monitoring data to be transmitted and analyzed in real time. When abnormality is found, the system can immediately give out early warning, thereby being beneficial to preventing potential danger and reducing loss. Through a deep learning model, the method can conduct high-dimensional feature extraction and analysis on the monitoring data. Such deep analysis helps to understand building behavior more deeply, detect implicit problems, and provide detailed anomaly analysis results, including anomaly type, location, and cause. The optimization of the monitoring point set and the automatic verification of the PLC enable the system to automatically adjust the monitoring points and parameters so as to adapt to different working conditions and requirements, so that the efficiency and accuracy of the monitoring equipment adaptation are improved, the monitoring effect of the building is further guaranteed, and the safety coefficient of the building is improved.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Carrying out three-dimensional laser scanning on a target building through preset laser scanning equipment, and acquiring multi-angle building image data of the target building;

(2) Carrying out load area segmentation on the multi-angle building image data to obtain a plurality of building load area images;

(3) Digital information extraction is carried out on a plurality of building load area images, and load area coordinates and geometric information are obtained;

(4) Carrying out pixel screening on a plurality of building load area images according to the load area coordinates and the geometric information to obtain building pixel data;

(5) Carrying out three-dimensional reconstruction on the target building according to the building pixel point data to obtain three-dimensional structure data;

(6) Performing grid discretization on the three-dimensional structure data to obtain discrete grids, and acquiring structural elements of a target building;

(7) And (3) carrying out grid optimization on the discrete grids according to the structural elements to generate the building digital finite element model.

Specifically, the server performs three-dimensional laser scanning on the target building through preset laser scanning equipment. This process generates multiple angles of building image data that contains shape and structure information for the building. And carrying out load region segmentation on the multi-angle building image data. The building image is segmented into a plurality of load zone images, each zone representing a particular zone or load zone within the building. On each load area image, digital information extraction is performed. This includes extracting coordinate information and geometric information, such as shape, size, location, etc., of the payload region. And according to the extracted load area coordinates and geometric information, screening pixel points of the multiple building load area images. The purpose of this step is to select pixel data associated with the building structure for subsequent three-dimensional reconstruction. And performing three-dimensional reconstruction by using the screened building pixel point data. This may be achieved by different three-dimensional reconstruction algorithms, such as point cloud reconstruction or voxel methods. The result is three-dimensional structural data of the target building. And performing grid discretization processing on the obtained three-dimensional structure data. This step divides the continuous three-dimensional structure data into discrete grids for numerical simulation and analysis. And (3) carrying out grid optimization on the discrete grids according to the structural elements of the building. This may include removing unnecessary grid points, optimizing grid resolution to accommodate the complexity of different load regions, and ensuring accuracy of the model. Finally, a digital finite element model of the building is generated according to the discrete grid optimized by the grid. The model comprises geometric information, structural information and grid data of the building, and can be used for structural analysis, monitoring and simulation of the building. For example, consider the monitoring and structural analysis of a high-rise building. The building is three-dimensionally laser scanned by a laser scanning device. The scan results include image data for a plurality of angles. These image data are segmented through the load zones, dividing the building into multiple load zones, such as walls, columns, floors, etc. Each load area is then subjected to digital information extraction, including coordinates, shape, size, etc. In the pixel screening stage, according to the information of each load area, the pixel relevant to the structure is selected. The pixel points are used for carrying out three-dimensional reconstruction and generating three-dimensional structure data of the building. Subsequently, the three-dimensional structure data is subjected to a grid discretization process, and is divided into discrete grid cells. These grids are optimized according to the structural elements of the building to ensure that the model accurately reflects the structure of the building. Finally, a digital finite element model of the building is generated, the model including geometric and structural information of the building. This model can be used for structural analysis, monitoring and simulation to ensure the safety and performance of the building.

In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:

s201, carrying out mechanical property analysis on a target building according to a building digital finite element model to obtain building mechanical property characteristics, and creating an initial simulation monitoring point set of the target building according to the building mechanical property characteristics;

s202, establishing communication connection with an initial simulation monitoring point set through a preset PLC, and performing operation verification on the initial simulation monitoring point set in a simulation environment to obtain an operation verification data set of the initial simulation monitoring point set;

s203, carrying out validity analysis on the operation verification data set to obtain a validity analysis result, and carrying out group initialization on the initial simulation monitoring point set according to the validity analysis result to obtain an initialized simulation monitoring point group;

s204, performing simulated monitoring point optimization analysis on the initialized simulated monitoring point group through a preset genetic algorithm to generate a target simulated monitoring point set.

Specifically, the server uses a building digital finite element model to analyze the mechanical properties of the target building. This includes analyzing the structure, load distribution, stress distribution, etc. of the building to obtain the mechanical performance characteristics of the building. These characteristics may include maximum stress, displacement, strain, etc. Based on the mechanical property analysis result, an initial simulation monitoring point set of the target building is created. These monitoring points are typically located at key locations of the building in order to monitor and evaluate the structural performance of the building. And establishing communication connection with the initial simulation monitoring point set by using a preset PLC device. This allows the monitoring point to exchange data with the monitoring system and control operations in the simulated environment. In a simulation environment, performing operation verification on an initial simulation monitoring point set. This includes modeling building behavior under different scenarios and loads. Meanwhile, data of monitoring points are collected, including displacement, stress, temperature and the like. And carrying out validity analysis on the collected operation verification data set. The purpose of this step is to determine whether the monitoring points reflect the actual behavior of the building with sufficient accuracy. Factors such as calibration, noise, errors, etc. need to be considered. And initializing the group of the initial simulation monitoring point set according to the result of the effectiveness analysis, and adjusting the parameters such as the position of the monitoring point, the type of the sensor, the sampling frequency and the like so as to improve the performance of the monitoring system. And carrying out optimization analysis on the simulated monitoring points of the initialized simulated monitoring point group by using a preset genetic algorithm and other optimization methods. This step aims to optimize the location and configuration of the monitoring points to maximize the efficiency and accuracy of the monitoring system. And generating a target simulation monitoring point set according to the optimization result. This set includes optimal monitoring point locations and configurations to ensure that the mechanical properties of the building are accurately monitored and evaluated. For example, consider a high-rise office building whose goal is to monitor the mechanical properties of its structure, such as displacement and stress distribution, to ensure the safety of the building. According to the building digital finite element model, an initial set of analog monitoring points is first created, including sensors on different floors and structural elements. Then, a communication connection is established using the PLC device, and verification is run in the simulation environment. This means simulating the response of the building under different load conditions such as earthquake, wind power and the like, and recording the data of the monitoring points. In some cases, the position of the monitoring point needs to be fine-tuned to improve data accuracy. Thus, population initialization is performed, and the position and sampling frequency of the monitoring points are adjusted. By using genetic algorithms, optimization analysis of the monitoring point locations and configurations is performed to ensure optimal monitoring system performance. Finally, a target simulation monitoring point set is generated, and the set can accurately monitor the mechanical property of the building and discover any potential problems in time so as to ensure the structural safety of the building.

In a specific embodiment, as shown in fig. 3, the process of executing step S201 may specifically include the following steps:

s301, carrying out mechanical property analysis on a target building according to a building digital finite element model to obtain building mechanical property data;

s302, carrying out characteristic analysis on building mechanical property data to obtain building mechanical property characteristics;

s303, an initial simulation monitoring point set of the target building is created according to the building mechanical property characteristics.

Specifically, the server can perform deep analysis on the mechanical properties of the target building by using a building digital finite element model. This model allows the server to simulate the behavior of the building under various loading conditions, such as earthquake, wind, loading, etc. Through these simulations, the server obtains a large amount of mechanical property data about the building, including displacement, stress, strain, deformation, and the like. And the server performs characteristic analysis on the mechanical property data. This step aims to extract the most representative and informative features from the vast amount of data to better understand the behavior of the building. The feature resolution includes the following aspects: determination of maximum displacement and maximum stress point: by analyzing the simulation data, the server determines the maximum displacement point and the maximum stress point of the building under different load conditions. The location and number of these points are important bases for evaluating the performance of the structure. For example, in seismic modeling, the server may identify the maximum displacement point, which helps determine the area that needs to be monitored with emphasis; analysis of natural frequencies and vibration modes: the simulation may also provide natural frequencies and vibration modes of the building. This information is important to understand the vibration characteristics and resonance phenomena of the building. Generation of stress distribution and strain cloud patterns: by analyzing the simulation data, the server generates stress distribution and strain clouds. This helps to determine hot spot areas and potential stress concentration problems in the structure; vibration amplitude and spectral analysis: by analyzing the amplitude and frequency spectrum of the vibration data, the server is better aware of the response of the building under external stimulus. The results of the feature analysis will provide key features of the building mechanics that reflect the behavior and response of the building under different conditions. For example, in seismic modeling, the server identifies the location and value of the maximum displacement point, the maximum stress point, and the natural frequency. These features will be the basis for creating an initial set of simulated monitoring points. According to the building mechanical property characteristics, the server creates an initial simulation monitoring point set of the target building. This set of monitoring points will include the location, type and parameter configuration of the sensors in order to monitor the building's mechanical properties in real time. For example, mounting displacement sensors on critical nodes of the structure to monitor displacement changes; a stress sensor is installed near the point of maximum stress to monitor the stress condition of the structure.

In a specific embodiment, as shown in fig. 4, the process of executing step S204 may specifically include the following steps:

s401, respectively calculating the fitness of a plurality of first candidate simulation monitoring point sets in the initialized simulation monitoring point group through a preset genetic algorithm to obtain the first fitness of each first candidate simulation monitoring point set;

s402, according to the first fitness of each first candidate simulation monitoring point set, carrying out group division on a plurality of first candidate simulation monitoring point sets to obtain an infected group, an easy-to-infect group and an uninfected group;

s403, carrying out propagation and mutation operation on the infected population, and carrying out inheritance, propagation and mutation operation on the easy-to-infect population and the uninfected population to obtain a plurality of second candidate simulation monitoring point sets;

s404, respectively calculating second fitness of each second candidate simulation monitoring point set, and carrying out optimization analysis on a plurality of second candidate simulation monitoring point sets according to the second fitness to obtain a target simulation monitoring point set.

Specifically, the server calculates fitness of a plurality of first candidate simulated monitoring point sets in the initialized simulated monitoring point population. Fitness is an index used to evaluate the performance of each set of monitoring points in a particular monitoring task. This can be achieved by defining an appropriate evaluation function that takes into account the location, type and parameter configuration of the set of monitoring points. For example, assuming that the server wants to monitor the displacement response of a high-rise building, in a genetic algorithm, the fitness function may consider whether the location of the set of monitoring points covers a critical area of the structure and has sufficient sensitivity to detect displacement. And according to the first fitness of each first candidate simulation monitoring point set, the server performs group division on the plurality of first candidate simulation monitoring point sets. This step divides the set of monitoring points into an infected population, a susceptible population and an uninfected population. The infected group contains a monitoring point set with higher fitness, the easy-to-infect group contains a monitoring point set with moderate fitness, and the uninfected group contains a monitoring point set with lower fitness. This division helps to concentrate on a set of potential monitoring points to improve efficiency. The server performs breeding and mutation operations on the infected population to create a second plurality of candidate simulated monitoring point sets. These operations are the core of genetic algorithms that improve the performance of the monitoring point set by simulating the process of biological evolution. For example, by a crossover operation, features of two highly compliant monitoring point sets may be combined together to produce a new monitoring point set. The mutation operation introduces randomness and helps to jump out of the local optimal solution. The server calculates a second fitness of each second candidate simulation monitoring point set, and performs optimization analysis on the plurality of second candidate simulation monitoring point sets according to the second fitness. This process aims at determining the final set of target simulated monitoring points whose performance is optimal for a given monitoring task. The genetic algorithm may iterate between multiple candidate point sets until a stopping condition is reached, such as a maximum number of iterations is reached or a set of monitoring points is found that meets performance requirements. For example, considering the monitoring task of a large bridge, a server would like to monitor the vibration response of the bridge by sensors as well as temperature changes. Using genetic algorithms, the server generates different sets of monitoring points, each set containing the position and parameter configuration of the vibration sensor and the temperature sensor. By calculating the fitness, the server evaluates the performance of each set of points in detecting vibration and temperature changes. With the iteration of the genetic algorithm, the server gradually finds the optimal set of monitoring points so that the bridge monitoring task can be performed in an optimal manner.

In a specific embodiment, the process of executing step S103 may specifically include the following steps:

(1) Acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through a PLC;

(2) Performing data cleaning and parameter standardization processing on the monitoring parameter data set to obtain a standard parameter data set;

(3) According to the monitoring parameter types, parameter clustering is carried out on the standard parameter data sets to obtain standard parameter data corresponding to each monitoring parameter type;

(4) Carrying out time sequence association processing on the standard parameter data corresponding to each monitoring parameter type to obtain time sequence standard parameters corresponding to each monitoring parameter type;

(5) Performing curve fitting on the time sequence standard parameters corresponding to each monitoring parameter type to obtain a target monitoring curve corresponding to each monitoring parameter type;

(6) Extracting curve characteristics of the target monitoring curve respectively to obtain a curve characteristic set corresponding to each monitoring parameter type;

(7) And generating a corresponding monitoring characteristic data set according to the curve characteristic set corresponding to each monitoring parameter type.

Specifically, a monitoring parameter data set corresponding to a target simulation monitoring point set is obtained through a PLC. The monitored parameters may include data collected by various sensors, such as temperature, humidity, displacement, pressure, vibration, etc. A PLC is a hardware device for real-time control and data acquisition that can be connected to various sensors and acquire its output data. And performing data cleaning and parameter standardization processing on the monitoring parameter data set. The data cleaning is to remove existing outliers or noise to ensure accuracy and reliability of the data. The parameter normalization is to unify the data of different sensors to the same scale for subsequent analysis. For example, if the data of the temperature sensor and the displacement sensor have different dimensions and units, the normalization may convert them into the same standard units, such as degrees celsius or millimeters. And carrying out parameter clustering on the standard parameter data set according to the monitoring parameter types. This step groups the monitoring parameters by their type, e.g. putting all temperature related parameters in one group and all displacement related parameters in another group. This facilitates independent processing of different types of monitored parameters. And carrying out time sequence association processing on the standard parameter data corresponding to each monitoring parameter type. Timing correlation is the process of aligning and correlating data acquired by different sensors in time. This is because different sensors have different sampling rates or time stamps, which need to be synchronized for subsequent analysis. And performing curve fitting on the time sequence standard parameters corresponding to each monitoring parameter type. This step aims at describing the trend of the monitored parameter over time by means of a mathematical model or curve. For example, a polynomial fit, exponential fit, or other mathematical method may be used to fit a curve of temperature over time. And respectively extracting curve characteristics of the target monitoring curves. This step involves extracting key features, such as maxima, minima, mean, volatility, etc., from the fitted curve that are relevant to the monitored parameters. These features can be used to describe the importance and trend of the monitored parameters. And generating a corresponding monitoring characteristic data set according to the curve characteristic set corresponding to each monitoring parameter type. This dataset includes features extracted from different monitoring parameters that can be used for subsequent building monitoring data anomaly analysis.

In a specific embodiment, the process of executing step S104 may specifically include the following steps:

(1) Carrying out normalization processing on the monitoring feature data set to obtain a plurality of normalization monitoring features, and carrying out vector coding on the plurality of normalization monitoring features to generate a target monitoring feature vector;

(2) Inputting a target monitoring feature vector into a preset building abnormality analysis model, wherein the building abnormality analysis model comprises a two-layer convolution long short-time memory network, a full-connection layer and an output layer;

(3) High-dimensional feature extraction is carried out on the target monitoring feature vector through a two-layer convolution long-short-term memory network, so that the high-dimensional monitoring feature vector is obtained;

(4) Carrying out abnormal probability prediction on the high-dimensional monitoring feature vector through the full-connection layer to obtain an abnormal probability prediction value;

(5) Constructing a mapping relation table between the abnormal probability and the abnormal result, and matching the mapping relation table according to the predicted value of the abnormal probability, and outputting a corresponding abnormal analysis result through an output layer, wherein the abnormal analysis result comprises: types of anomalies, locations, and causes of anomalies.

Specifically, the monitoring characteristic data set is normalized. The purpose is to unify the data of different features into the same scale range for subsequent analysis. Normalization may use different methods, such as min-max normalization or normalization. This will yield a plurality of normalized monitoring features. And vector encoding is carried out on the plurality of normalized monitoring features, and a target monitoring feature vector is generated. Vector coding is a process of combining multiple features into one vector for input into a deep learning model for analysis. This vector should capture aspects of the monitored data such as temperature, humidity, vibration, etc. Then, the target monitoring feature vector is input into a preset building anomaly analysis model. This model typically includes multiple layers for extracting useful information from the feature data. In this embodiment, the building anomaly analysis model includes a two-layer convolutional long short-term memory network (LSTM), a full-connection layer, and an output layer. And extracting high-dimensional characteristics of the target monitoring characteristic vector through a two-layer convolution long-short-term memory network. Convolution LSTM is a deep learning network that can effectively capture complex patterns in time series data. This hierarchy converts the target surveillance feature vector into a high-dimensional surveillance feature vector for further analysis. And then, carrying out abnormal probability prediction on the high-dimensional monitoring feature vector through the full connection layer. The fully connected layer is a neural network hierarchy for learning complex relationships between features. In this step, the model maps the high-dimensional monitoring feature vector to an anomaly probability prediction value that represents the nature of the monitored data anomaly. And constructing a mapping relation table between the abnormal probability and the abnormal result. The mapping relation table can be defined in advance, or can be obtained by automatic learning according to training data. It is used to map the anomaly probability prediction value to specific anomaly analysis results, including anomaly type, location, and anomaly cause. And outputting a corresponding abnormal analysis result through an output layer. These results can provide detailed information about anomalies in the monitored data, helping maintenance personnel to quickly identify and resolve problems.

The above describes the method for monitoring the building internet of things automatically adapted in the embodiment of the present invention, and the following describes the system for monitoring the building internet of things automatically adapted in the embodiment of the present invention, please refer to fig. 5, and one embodiment of the system for monitoring the building internet of things automatically adapted in the embodiment of the present invention includes:

the acquisition module 501 is used for acquiring three-dimensional structure data of a target building through laser scanning and constructing a building digital finite element model of the target building according to the three-dimensional structure data;

the creating module 502 is configured to create an initial analog monitoring point set of the target building according to the building digital finite element model, and perform validity verification and optimization on the initial analog monitoring point set through a preset PLC to obtain a target analog monitoring point set;

the feature extraction module 503 is configured to obtain, by using the PLC, a monitoring parameter data set corresponding to the target analog monitoring point set, and perform feature extraction on the monitoring parameter data set, to obtain a monitoring feature data set;

and the analysis module 504 is used for inputting the monitoring characteristic data set into a preset building anomaly analysis model to perform anomaly analysis on building monitoring data so as to obtain an anomaly analysis result.

Acquiring three-dimensional structure data of a target building through laser scanning by the cooperative cooperation of the components, and constructing a building digital finite element model of the target building according to the three-dimensional structure data; establishing an initial simulation monitoring point set of a target building according to the building digital finite element model, and verifying and optimizing the effectiveness of the initial simulation monitoring point set through a preset PLC (programmable logic controller) to obtain the target simulation monitoring point set; acquiring a monitoring parameter data set corresponding to the target simulation monitoring point set through the PLC, and extracting characteristics of the monitoring parameter data set to obtain a monitoring characteristic data set; the monitoring characteristic data set is input into a preset building anomaly analysis model to perform building monitoring data anomaly analysis to obtain an anomaly analysis result. Compared with the traditional manual inspection, the system can greatly improve the monitoring efficiency, monitor the building state in real time, and reduce the monitoring and maintenance cost. Through the digital finite element model, the response of the building under different working conditions can be accurately simulated. This provides more accurate monitoring data, facilitates early detection of structural problems, anomalies, or performance degradation, and takes timely action to repair and improve. The combination of the automatically adapted monitoring point set and the PLC enables the monitoring data to be transmitted and analyzed in real time. When abnormality is found, the system can immediately give out early warning, thereby being beneficial to preventing potential danger and reducing loss. Through a deep learning model, the method can conduct high-dimensional feature extraction and analysis on the monitoring data. Such deep analysis helps to understand building behavior more deeply, detect implicit problems, and provide detailed anomaly analysis results, including anomaly type, location, and cause. The optimization of the monitoring point set and the automatic verification of the PLC enable the system to automatically adjust the monitoring points and parameters so as to adapt to different working conditions and requirements, so that the efficiency and accuracy of the monitoring equipment adaptation are improved, the monitoring effect of the building is further guaranteed, and the safety coefficient of the building is improved.

Fig. 5 above describes the automatically adapted building internet of things monitoring system in the embodiment of the present invention in detail from the perspective of a modularized functional entity, and the automatically adapted building internet of things monitoring device in the embodiment of the present invention is described in detail from the perspective of hardware processing below.

Fig. 6 is a schematic structural diagram of an automatically-adapted building internet of things monitoring device according to an embodiment of the present invention, where the automatically-adapted building internet of things monitoring device 600 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the automatically adapted building internet of things monitoring device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the automatically adapted building internet of things monitoring device 600.

The automatically adapted building internet of things monitoring device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the automatically adapted building internet of things monitoring device structure shown in fig. 6 does not constitute a limitation of the automatically adapted building internet of things monitoring device, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

The invention also provides an automatically-adapted building internet of things monitoring device, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the automatically-adapted building internet of things monitoring method in the above embodiments.

The invention also provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium, and can also be a volatile computer readable storage medium, wherein instructions are stored in the computer readable storage medium, and when the instructions run on a computer, the computer is caused to execute the steps of the automatically adapted building internet of things monitoring method.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The automatic-adaptation building internet of things monitoring method is characterized by comprising the following steps of:

2. The method for monitoring the internet of things of the building automatically adapted according to claim 1, wherein the steps of obtaining three-dimensional structure data of a target building through laser scanning, and constructing a building digital finite element model of the target building according to the three-dimensional structure data include:

3. The method for monitoring the internet of things of automatically adapting building according to claim 1, wherein creating the initial analog monitoring point set of the target building according to the building digital finite element model, and verifying and optimizing the effectiveness of the initial analog monitoring point set by a preset PLC to obtain the target analog monitoring point set, comprises:

4. The method for monitoring the internet of things of the building automatically adapted according to claim 3, wherein the performing mechanical property analysis on the target building according to the building digital finite element model to obtain building mechanical property characteristics, and creating an initial simulation monitoring point set of the target building according to the building mechanical property characteristics comprises:

5. The method for automatically adapting building internet of things monitoring according to claim 3, wherein the performing, by a preset genetic algorithm, optimization analysis of the simulation monitoring points on the initialized simulation monitoring point group to generate a target simulation monitoring point set includes:

6. The method for monitoring the internet of things of the building according to claim 1, wherein the obtaining, by the PLC, the monitoring parameter data set corresponding to the target analog monitoring point set, and performing feature extraction on the monitoring parameter data set, to obtain a monitoring feature data set, includes:

7. The method for monitoring the internet of things of the building according to claim 1, wherein the step of inputting the monitoring feature data set into a preset building anomaly analysis model to perform anomaly analysis on building monitoring data to obtain anomaly analysis results comprises the following steps:

8. Automatic building thing networking monitored control system of adaptation, its characterized in that, building thing networking monitored control system of automatic adaptation includes:

9. Automatic building thing networking supervisory equipment of adaptation, its characterized in that, building thing networking supervisory equipment of automatic adaptation includes: a memory and at least one processor, the memory having instructions stored therein;

the at least one processor invoking the instructions in the memory to cause the automatically adapted building internet of things monitoring device to perform the automatically adapted building internet of things monitoring method of any of claims 1-7.

10. A computer readable storage medium having instructions stored thereon, wherein the instructions when executed by a processor implement the automatically adapted building internet of things monitoring method of any of claims 1-7.