A teaching system for intelligently detecting building health and risk prediction

Abstract

The application discloses a kind of intelligent detection building health and risk prediction teaching system, belong to intelligent construction teaching field, including: through intelligent car and the high-definition camera matrix of unmanned aerial vehicle terminal carrying is collected building data and is transmitted to operation super brain;Through the AI recognition big model and structure safety, natural disaster, personnel safety three risk assessment sub-models built-in in operation super brain, the multi-level comprehensive risk assessment of building state is carried out;Through the hazard identified in building digital twin 3D model corresponding position visualization presentation and generating graded warning signal by wisdom management platform, platform supports student login operation to carry out picture digitization, autonomous operation practice and complete experiment report;After completing on-campus laboratory simulation and course practice, form course outline and experiment report and popularize to other colleges and universities.The application enables students to visually observe building hazards, complete risk prediction operations, and promote cross-campus sharing of teaching resources.

Description

Technical Field

[0001] This invention belongs to the field of intelligent construction teaching technology, and in particular relates to a teaching system for intelligent detection of building health and risk prediction. Background Technology

[0002] Currently, in the field of intelligent construction education, the teaching of building health monitoring and risk prediction mainly relies on traditional manual case studies or data demonstrations from single sensors. Existing technologies have seen some teaching support systems attempting to introduce digital methods, such as collecting limited environmental data through fixed monitoring equipment or using multimedia courseware to display images of building damage, to impart basic concepts of building structural safety to students. These methods have, to some extent, helped students establish a preliminary understanding of building health monitoring and provided foundational supporting materials for theoretical teaching.

[0003] However, existing teaching technologies and methods still have significant shortcomings in practical applications. First, current teaching methods are often limited to single-dimensional data presentation, such as explaining solely through smoke sensor or displacement sensor readings. They lack comprehensive collection and analysis of multi-source data on building structural safety, internal and external environmental risks, and human activities, making it difficult for students to develop a systematic understanding of building health. Second, risk information acquired during teaching is often outdated, relying heavily on existing cases or static data. It cannot realistically simulate the dynamic changes in building structural damage, crack propagation, and electrical hazards. Students cannot intuitively grasp the complete chain of risk development from its inception to its evolution, and the lack of practical application severely restricts the cultivation of their risk identification and prediction abilities. Third, under the current technological system, internal and external environmental monitoring are fragmented. For example, the coupling relationship between building structural deformation and external weather disturbances, as well as internal human activities, is difficult to reproduce in teaching experiments, making it difficult to achieve the teaching objective of systematic risk assessment. Furthermore, traditional teaching methods cannot meet the expanded teaching needs of new building cases and cannot effectively support the digital teaching concept of building lifecycle health management. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention proposes an intelligent teaching system for detecting building health and predicting risks, thereby resolving the issues present in the existing technologies.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a teaching system for intelligent detection of building health and risk prediction, comprising: The data acquisition module is used to collect video and image data of buildings through a high-definition camera matrix mounted on intelligent vehicles and drone terminals, and transmit it to the computing supercomputer; The intelligent identification and assessment module is used to intelligently analyze the received data through the AI ​​identification model built into the supercomputer to identify damage points, external cracks, circuit hazards, and pipeline rupture risks in the main building structure; and to conduct a multi-level comprehensive risk assessment of the building status through the structural safety risk assessment sub-model, natural disaster risk assessment sub-model, and personnel safety risk assessment sub-model built into the supercomputer. The teaching presentation and operation module is used to visualize the identified hidden dangers at the corresponding locations in the building's digital twin 3D model through the intelligent management platform, and generate graded early warning signals. The intelligent management platform supports student login and operation, allowing students to practice image digitization, conduct independent operation, and complete experimental reports based on graded early warning signals. The course implementation and promotion module is used to generate a course outline and experimental report after completing the on-campus laboratory simulation and course practice, and to promote it to other institutions.

[0006] Preferably, the data acquisition module further includes a multi-source sensor data acquisition module, which includes a building structure sensor unit, an internal environment sensor unit, an external environment sensor unit, and a personnel activity sensor unit.

[0007] Preferably, the building structure sensor unit includes a displacement sensor and a crack monitoring sensor; the internal environment sensor unit includes a smoke sensor, a harmful gas sensor, and a noise sensor; the external environment sensor unit includes a wind speed and direction sensor, a ground motion sensor, and a geological disaster monitoring sensor; and the personnel activity sensor unit includes an infrared sensor, a video image sensor, and a personnel positioning sensor.

[0008] Preferably, the personnel safety risk assessment sub-model is constructed based on the analysis of personnel distribution density and behavioral patterns, and is used to assess the personnel safety risks within the building.

[0009] Preferably, the graded early warning signal adopts a three-level early warning system, including: a level 1 early warning with a green indicator, indicating that the building is in normal condition; a level 2 early warning with a yellow indicator, indicating that there is a minor abnormality; and a level 3 early warning with a red indicator, indicating that the risk is extremely high and an emergency response needs to be initiated immediately. The three-level early warning system can be operated independently by students to distinguish the early warning levels and complete the experimental report.

[0010] Preferably, the building digital twin 3D model is constructed using BIM technology and real-time monitoring data, and is used to realize real-time visualization of building status, historical data backtracking, and disaster process simulation.

[0011] Preferably, the intelligent vehicle and drone terminal support switching between remote control mode, fully automatic cruise mode and handheld detection mode; the intelligent vehicle is driven by an encoder motor, the steering servo controls the direction, and the pulley bushing connects the wheels and the motor.

[0012] Preferably, the intelligent identification and assessment module further includes: converting the data obtained from the AI ​​identification model analysis into building health monitoring indicators, and comparing the building health monitoring indicators with preset normal building health indicators to predict potential hazards in the main building structure.

[0013] Preferably, in the teaching presentation and operation module, the intelligent management platform displays early warning information to students through multi-channel communication, and uniformly summarizes and identifies data and early warning information, supporting the function of exporting analysis reports.

[0014] Secondly, the present invention provides a teaching method for intelligent detection of building health and risk prediction, used to implement the system described in the first aspect.

[0015] Compared with the prior art, the present invention has the following advantages and technical effects: This application constructs a complete teaching loop by setting up teaching presentation and operation modules and course implementation and promotion modules. The teaching presentation and operation module, which allows students to log in and operate the "intelligent management platform" for image digitization practice, independent operation practice, and completion of experimental reports based on graded early warning signals, and the course implementation and promotion module, which generates a course outline and experimental report after completing on-campus laboratory simulations and course practice, enable this system to organically combine intelligent detection technology with the intelligent construction curriculum system. Students can obtain complete experimental reports through practical operation, forming reusable course resources, effectively solving the problem of students having limited practical experience and difficulty in independently completing risk identification tasks in traditional teaching.

[0016] This invention, by setting up an intelligent identification and assessment module and incorporating "structural safety risk assessment sub-models, natural disaster risk assessment sub-models, and personnel safety risk assessment sub-models," achieves a comprehensive assessment of building structural safety, natural disaster risks, and personnel safety risks. In particular, the introduction of the personnel safety risk assessment sub-model enables the system to analyze and assess safety risks based on personnel distribution and behavioral patterns, expanding the dimensions of risk assessment. Simultaneously, the teaching presentation and operation module visualizes the identified hazards at their corresponding locations in the "building digital twin 3D model," allowing students to intuitively observe the spatial distribution and evolution of risks, solving the problems of fragmented monitoring of internal and external environments and frequent omissions of systemic risks in traditional teaching.

[0017] This invention, by setting up a course implementation and promotion module, clarifies the technical path for "promotion to other institutions," enabling the system to move beyond single-school laboratory applications and be exported across schools through standardized course outlines and experimental reports. This technical design makes intelligent construction teaching resources replicable and scalable, solving the problem that traditional teaching cases are difficult to extend to new types of buildings and cannot meet the teaching needs of the entire building lifecycle. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a front view of the teaching-type intelligent building health detection and imaging vehicle according to an embodiment of the present invention; Figure 2 A side view of the teaching-type intelligent building health detection and imaging vehicle according to an embodiment of the present invention; Figure 3 A view of the power box of the teaching-type intelligent building health detection and imaging vehicle according to an embodiment of the present invention; Figure 4 This is a view of the lidar of the teaching-type intelligent building health detection and imaging vehicle according to an embodiment of the present invention; Figure 5 This is a view of the floor of a teaching-type intelligent building health detection and imaging vehicle according to an embodiment of the present invention. Figure 6 This is a schematic diagram of a teaching system for intelligent detection of building health and risk prediction according to an embodiment of the present invention; 1. Central control power box; 2. Camera; 3. Support plate; 4. Wheel; 5. Main control board; 6. Telescopic rotating column; 7. Sensor; 8. Power positive terminal; 9. Power negative terminal; 10. LiDAR USB interface; 11. LiDAR housing; 12. Upper base plate; 13. Lower base plate. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0021] Example 1 like Figure 6As shown, this embodiment provides a teaching system for intelligent detection of building health and risk prediction, including: The data acquisition module is used to collect video and image data of buildings through a high-definition camera matrix mounted on intelligent vehicles and drone terminals, and transmit it to the computing supercomputer; Furthermore, the intelligent vehicle and drone terminal support switching between remote control mode, fully automatic cruise mode and handheld detection mode; the intelligent vehicle is driven by an encoder motor, the steering servo controls the direction, and the pulley bushing connects the wheels and the motor.

[0022] Furthermore, the data acquisition module also includes a multi-source sensor data acquisition module, which includes a building structure sensor unit, an internal environment sensor unit, an external environment sensor unit, and a personnel activity sensor unit.

[0023] Furthermore, the building structure sensor unit includes a displacement sensor and a crack monitoring sensor; the internal environment sensor unit includes a smoke sensor, a harmful gas sensor, and a noise sensor; the external environment sensor unit includes a wind speed and direction sensor, a ground motion sensor, and a geological disaster monitoring sensor; and the personnel activity sensor unit includes an infrared sensor, a video image sensor, and a personnel positioning sensor.

[0024] Specifically, the data acquisition module includes a tracking intelligent vehicle and a drone that collect images and videos. The captured external images and videos are integrated and transmitted to the multi-source sensor data acquisition module through remote control or fully automatic cruise. It can also be used by students for image digitization as a practical module.

[0025] like Figure 1 , Figure 2 , Figure 4 As shown, an infrared camera 2 for shooting is fixedly connected to the top of the car. It is controlled by a telescopic rotating column 6 to shoot scenes in all directions. The infrared camera 2 identifies the time and location through an intelligent identification network. The infrared camera 2 contains a movable main control board 5. The main control board 5 is connected to a remote and terminal control system. The main control board 5 is controlled by a central control power box 1 and is connected to a laser radar housing 11 via a laser radar USB interface 10. A support plate 3 is also fixed on the plate to support the telescopic rotating column 6. In addition to supporting the telescopic rotating column 6, it also connects the telescopic rotating column 6, the upper structure of the camera 2, and the main control board 5 and its lower structure. This allows the camera 2 to move freely during the movement of the car and can be connected to the central control operating system. Under the control of the operating system, there are wheel axles connecting the wheels 4. One axle is set on each of the front and rear sides, and the wheels 4 are connected and installed through a rotating shaft.

[0026] The main control board 5 is used to export and process building information and data simultaneously. It has four protruding corners and a central axis inside for connecting the propellers used for navigation. There are four propellers in total, which facilitates maintaining flight balance and stable shooting.

[0027] Sensor 7 is placed on the main control board 5. It integrates and converts images from the car and the drone into building visualization information, classifies hazards or disasters by changes in displacement or shape, and transmits the data to the data preprocessing module for further analysis.

[0028] like Figure 3 As shown, the positive line of the central control board 5, the central control operating system, and the positive line of the drive wheel 4 are connected to the positive power supply 8, the positive line of the sensor 7, the negative power supply 9 is connected to another terminal of the board connected to the positive power supply and the outflow connection of the wiring harness, the negative line of the drive wheel 4, and the negative line of the sensor 7, which serve as the power supply equipment for the entire car.

[0029] like Figure 5 As shown, various electrical circuits and electrodes, as well as the circuit boards for calculation and analysis data, and the upper part of various device interfaces and wiring terminals attached to the upper side of the board are all located on the upper base plate 12. The wiring ports required on the reverse side of the circuit, the interfaces required for remote control system conversion, the car charging interface, and various lower connection points on the upper plate, and the central axle of the wheel 4 are all attached to the lower base plate 13. The upper and lower base plates are connected by corresponding wiring harnesses to ensure that the data analysis and processing performed on the upper and lower base plates can be transmitted and run on the board, and it has good adaptability to more complex equipment. It can be connected to both ends between the upper and lower plates, which greatly expands the connection space of the board and the space for external devices, so that the car has room for updating the hardware system, and can be connected to the outside of the car via USB and other means for software system iteration.

[0030] In this embodiment, the data acquisition module includes: a building structure sensor unit, including displacement sensors and crack monitoring sensors, for real-time monitoring of building structure deformation and crack propagation; an internal environment sensor unit, including smoke sensors, harmful gas sensors, and noise sensors, for monitoring the quality of the building's internal environment; an external environment sensor unit, including wind speed and direction sensors, seismic sensors, and geological disaster monitoring sensors, for monitoring changes in the natural environment surrounding the building; and a personnel activity sensor unit, including infrared sensors, video image sensors, and personnel positioning sensors, for monitoring the distribution, movement, and abnormal behavior of personnel within the building. The data acquisition module can be used for demonstration in the early stages of the course to stimulate students' interest in self-directed learning.

[0031] The intelligent identification and assessment module is used to intelligently analyze the received data through the AI ​​identification model built into the supercomputer to identify damage points, external cracks, circuit hazards, and pipeline rupture risks in the main building structure; and to conduct a multi-level comprehensive risk assessment of the building status through the structural safety risk assessment sub-model, natural disaster risk assessment sub-model, and personnel safety risk assessment sub-model built into the supercomputer. Furthermore, the personnel safety risk assessment sub-model is constructed based on the analysis of personnel distribution density and behavioral patterns, and is used to assess the safety risks of personnel within the building.

[0032] Furthermore, the intelligent identification and assessment module also includes: converting the data obtained from the AI ​​identification model analysis into building health monitoring indicators, and comparing the building health monitoring indicators with preset normal building health indicators to predict potential hazards in the main building structure.

[0033] Specifically, the intelligent risk identification and assessment module contains multi-level risk assessment models, built into the terminal baseboard of intelligent vehicles and drones. These include: a structural safety risk assessment sub-model, which assesses the safety status of building structures based on structural mechanics; a natural disaster risk assessment sub-model, which predicts potential structural risks based on a combination of building structure and geological and meteorological data; and a personnel safety risk assessment sub-model, which analyzes and assesses personnel safety risks based on personnel distribution density and behavioral patterns. The intelligent risk identification and assessment module is also used to demonstrate to students and stimulate their interest in secondary development using professional courses such as structural mechanics.

[0034] The teaching presentation and operation module is used to visualize the identified hidden dangers at the corresponding locations in the building's digital twin 3D model through the intelligent management platform, and generate graded early warning signals. The intelligent management platform supports student login and operation, allowing students to practice image digitization, conduct independent operation, and complete experimental reports based on graded early warning signals. Furthermore, the graded early warning signal adopts a three-level early warning system, including: a level 1 early warning with a green indicator, indicating that the building is in normal condition and no special action is required; a level 2 early warning with a yellow indicator, indicating that there is a minor abnormality and that monitoring needs to be strengthened; and a level 3 early warning with a red indicator, indicating that the risk is extremely high and an emergency response needs to be initiated immediately. The three-level early warning system can be operated independently by students to distinguish the early warning levels and complete the experimental report.

[0035] Furthermore, the building digital twin 3D model is constructed using BIM technology and real-time monitoring data, and is used to realize real-time visualization of building status, historical data backtracking, and disaster process simulation.

[0036] Furthermore, in the teaching presentation and operation module, the intelligent management platform displays early warning information to students through multi-channel communication, and uniformly summarizes and identifies data and early warning information, supporting the function of exporting analysis reports.

[0037] Specifically, the alarm settings on the smart management platform are categorized into different levels. The warning indicator lights on the smart management platform are used to remind back-end administrators of the level of potential hazards, prompting them to formulate and implement corresponding solutions.

[0038] The course implementation and promotion module is used to generate a course outline and experimental report after completing the on-campus laboratory simulation and course practice, and to promote it to other institutions.

[0039] Specifically, the system will be integrated and simulated in the school's laboratories. The intelligent management platform will collect and identify data and early warning information in a unified manner, making it easy to export analysis reports. The system will be initially designed to be used in the school's intelligent construction professional courses for demonstration and for students to conduct practical operation simulations. After the system is implemented in the school to form a standardized course outline and process and produce course experiment reports, it can be promoted and exported to other universities through cross-school reports or online video promotion, thereby promoting the progress and digitalization of intelligent construction teaching in universities.

[0040] Example 2 Based on the same inventive concept, this embodiment also provides a teaching method for intelligent detection of building health and risk prediction, used to implement the system described in Embodiment 1.

[0041] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A teaching system for intelligent detection of building health and risk prediction, characterized in that, include: The data acquisition module is used to collect video and image data of buildings through a high-definition camera matrix mounted on intelligent vehicles and drone terminals, and transmit it to the computing supercomputer; The intelligent identification and assessment module is used to intelligently analyze the received data through the AI ​​identification model built into the supercomputer to identify damage points, external cracks, circuit hazards, and pipeline rupture risks in the main building structure; and to conduct a multi-level comprehensive risk assessment of the building status through the structural safety risk assessment sub-model, natural disaster risk assessment sub-model, and personnel safety risk assessment sub-model built into the supercomputer. The teaching presentation and operation module is used to visualize the identified hidden dangers at the corresponding locations in the building's digital twin 3D model through the intelligent management platform, and generate graded early warning signals. The intelligent management platform supports student login and operation, allowing students to practice image digitization, conduct independent operation, and complete experimental reports based on graded early warning signals. The course implementation and promotion module is used to generate a course outline and experimental report after completing the on-campus laboratory simulation and course practice, and to promote it to other institutions.

2. The system according to claim 1, characterized in that, The data acquisition module also includes a multi-source sensor data acquisition module, which includes a building structure sensor unit, an internal environment sensor unit, an external environment sensor unit, and a personnel activity sensor unit.

3. The system according to claim 2, characterized in that, The building structure sensor unit includes a displacement sensor and a crack monitoring sensor; the internal environment sensor unit includes a smoke sensor, a harmful gas sensor, and a noise sensor; the external environment sensor unit includes a wind speed and direction sensor, a ground motion sensor, and a geological disaster monitoring sensor; and the personnel activity sensor unit includes an infrared sensor, a video image sensor, and a personnel positioning sensor.

4. The system according to claim 1, characterized in that, The personnel safety risk assessment sub-model is constructed based on the analysis of personnel distribution density and behavioral patterns, and is used to assess the safety risks of personnel within buildings.

5. The system according to claim 1, characterized in that, The graded early warning signal adopts a three-level early warning system, including: Level 1 early warning with green markings, indicating that the building is in normal condition; Level 2 early warning with yellow markings, indicating that there is a minor abnormality; and Level 3 early warning with red markings, indicating that the risk is extremely high and an emergency response needs to be initiated immediately. The three-level early warning system can be operated independently by students to distinguish the warning levels and complete the experimental report.

6. The system according to claim 1, characterized in that, The building digital twin 3D model is constructed using BIM technology and real-time monitoring data, and is used to realize real-time visualization of building status, historical data backtracking, and disaster process simulation.

7. The system according to claim 1, characterized in that, The intelligent vehicle and drone terminal support switching between remote control mode, fully automatic cruise mode and handheld detection mode; the intelligent vehicle is driven by an encoder motor, the steering servo controls the direction, and the pulley bushing connects the wheels and the motor.

8. The system according to claim 1, characterized in that, The intelligent identification and assessment module further includes: converting the data obtained from the AI ​​identification model into building health monitoring indicators, and comparing the building health monitoring indicators with preset normal building health indicators to predict potential hazards in the main structure of the building.

9. The system according to claim 1, characterized in that, In the teaching presentation and operation module, the intelligent management platform displays early warning information to students through multi-channel communication, and uniformly summarizes and identifies data and early warning information, supporting the function of exporting analysis reports.

10. A teaching method for intelligent detection of building health and risk prediction, characterized in that, For implementing the system according to any one of claims 1-9.

Images