Building disease monitoring method based on digital twinborn technology

Abstract

The invention relates to the technical field of building disease monitoring, in particular to a building disease monitoring method based on a digital twinborn technology. The building disease monitoring method based on the digital twinborn technology comprises the following steps of collecting multi-dimensional information such as geometric information, material characteristics, structural characteristics and a construction process of a building; according to the method, building diseases are monitored by adopting a digital twinning technology, the health state of a building structure can be dynamically monitored in real time, a theoretical basis and an analysis method of the structure under different working conditions are provided by utilizing a physical model, and meanwhile, learning and optimization are carried out by depending on a large amount of actual monitoring data through a data driving model, so that the real-time monitoring of the health state of the building structure is realized. By utilizing the synergistic effect of the double models, the disease condition of the building structure can be identified and predicted more accurately, and potential safety hazards can be found in time, so that a scientific basis and an effective support are provided for structure maintenance and management.

Description

Technical Field

[0001] The present invention relates to the technical field of building disease monitoring, and specifically, to a building disease monitoring method based on digital twin technology. Background Art

[0002] With the acceleration of the urbanization process and the extension of the service life of buildings, many buildings face structural aging and disease risks after exceeding their designed service life, and potential safety hazards are becoming increasingly prominent. At the same time, with the improvement of public safety awareness and the frequent occurrence of building accidents, the society's attention to the health status of buildings has been continuously increasing. In addition, the progress of technology has made monitoring means more efficient and intelligent, promoting the widespread application of building disease monitoring. Considering these factors comprehensively, establishing a perfect building disease monitoring system has become an important measure to ensure building safety, extend service life and improve economic benefits.

[0003] Many traditional monitoring methods often rely on regular on-site inspections and manual evaluations, which means that monitoring personnel need to conduct on-site surveys and inspections of buildings at predetermined time intervals. This method usually requires professional technicians to judge the health status of buildings through visual inspections, simple measuring tools or manual instruments.

[0004] Existing monitoring technologies usually cannot achieve real-time data analysis and dynamic monitoring. This limitation makes it difficult to detect potential structural problems at an early stage. Many traditional monitoring methods rely on regular inspections and manual evaluations, and often cannot promptly capture the small changes and abnormal conditions that occur during the use of buildings. This lag not only increases the probability of potential hazards but also may lead to the failure of relevant personnel to take effective preventive measures before the problems evolve into serious damages. In addition, the lack of real-time monitoring also makes the basis for maintenance decisions insufficient, making it difficult to carry out scientific and reasonable resource allocation and maintenance plans, thus affecting the overall safety and service efficiency of buildings. Therefore, the development of efficient real-time monitoring technologies is crucial for timely identifying and solving building disease problems to ensure the long-term safety and stability of buildings.

[0005] Therefore, by combining physical models with data-driven models, the present invention can achieve dynamic real-time monitoring of the health status of building structures, reduce labor costs, and improve response time. At the same time, it also provides decision-making and support solutions, enabling managers to formulate maintenance and reinforcement plans. Summary of the Invention

[0006] The object of the present invention is to provide a building disease monitoring method based on digital twin technology, so as to solve the problems in the above-mentioned background technology that the existing monitoring technologies usually cannot achieve real-time data analysis and dynamic monitoring, and the traditional monitoring methods rely on regular inspections and manual evaluations, and often cannot timely capture the minor changes and abnormal conditions that occur during the use of buildings.

[0007] To achieve the above object, the present invention aims to provide a building disease monitoring method based on digital twin technology, including the following steps:

[0008] S1. Collect multi-dimensional information such as the geometric information, material properties, structural properties, and construction technology of the building, and install various types of sensors such as strain gauges, accelerometers, and temperature and humidity sensors at key parts of the building to monitor the building structure state and environmental changes in real time;

[0009] S2. Transmit the collected data to a centrally managed database through advanced communication devices for systematic backup;

[0010] S3. Use data fusion technology to integrate and process the sensor data, and use machine learning algorithms to deeply analyze the data to predict the building's health life and conduct disease monitoring;

[0011] S4. Build a physical model of the building structure based on the Building Information Model (BIM), and use machine learning and neural network algorithms to build a mathematical model of the digital twin. Combine the physical model with the mathematical model to form a dynamically updated digital twin model;

[0012] S5. Through the digital twin model, realize real-time monitoring and prediction of the health state of the building structure, and set disease detection indicators to evaluate whether the building has disease risks;

[0013] S6. When the system detects a disease, automatically generate a warning message, notify relevant personnel through a mobile application, and provide a decision support tool at the same time.

[0014] As a further improvement of this technical solution, the installation positions of the sensors are reasonably arranged by analyzing the key load-bearing parts and potential disease risk points of the building.

[0015] As a further improvement of this technical solution, the systematic backup includes regular automatic backup and manual backup.

[0016] As a further improvement of this technical solution, the data fusion technology includes Kalman filtering, complementary filtering, or particle filtering algorithms.

[0017] As a further improvement of this technical solution, during the construction process of the digital twin model, the influence of environmental factors needs to be considered, including temperature, humidity, and corrosion.

[0018] As a further improvement of this technical solution, during the disease monitoring process, the health status of the building is comprehensively evaluated according to the disease detection indicators set based on historical data and industry standards.

[0019] As a further improvement of this technical solution, the disease detection indicators include crack width, deformation amount, and vibration frequency.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0021] 1. In the present invention, by adopting digital twin technology, a virtual building structure model is created, and at the same time, sensors and monitoring videos are deployed to transmit the parameters of the building in real time, achieving the effect of real-time monitoring. At the same time, the digital twin model can calculate based on the data input by sensors and monitoring videos to predict the health life of the building. When diseases occur in the building, it can alarm in time and provide decision support tools. Subsequently, the digital twin model can be continuously updated according to the monitoring results and maintenance effects of the building to improve the accuracy and detection effect of the model.

[0022] 2. In the present invention, by combining the physical model with the data-driven model, it is possible to realize the dynamic real-time monitoring of the health status of the building structure, reduce labor costs, improve response time, and at the same time provide decision-making and support solutions, enabling managers to formulate maintenance and reinforcement plans. The physical model provides the theoretical basis and analysis methods for the structure under different working conditions, while the data-driven model depends on a large amount of actual monitoring data for learning and optimization. By utilizing the synergistic effect of the dual models, it is possible to more accurately identify and predict the disease conditions of the building structure, timely discover potential safety hazards, and thus provide a scientific basis and effective support for structure maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a principle block diagram of the building disease monitoring method based on digital twin technology of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] In a specific embodiment, as Figure 1As shown in the figure, the present invention provides a building disease monitoring method based on digital twin technology, including the following steps:

[0026] I. Data monitoring and acquisition module.

[0027] First of all, it is necessary to collect multi-dimensional information such as the geometric information, building materials, structural characteristics, and construction technology of the building, which helps to construct a 3D model of the building subsequently. Secondly, various types of sensors need to be installed at key parts of the building, such as strain gauges, accelerometers, temperature and humidity sensors, etc. These sensors can monitor the structural state and environmental changes of the building in real time and provide accurate data feedback. The strain gauge can be used to monitor the deformation of the building structure, the accelerometer can detect vibrations and dynamic loads, and the temperature and humidity sensors are responsible for monitoring the temperature and humidity changes inside and outside the building. By reasonably arranging sensors at different key positions, the operating state of the building can be comprehensively captured to ensure the comprehensiveness and representativeness of the data. At the same time, it is necessary to monitor the video to conduct real-time monitoring of the parts to be monitored and collect some building disease data for subsequent training.

[0028] II. Data transmission and storage module.

[0029] The collected data is transmitted to a centrally managed database through advanced communication devices, which ensures the timely and accurate transmission of the data. After the data transmission is completed, the database will systematically back up the collected data to prevent data loss or damage. This backup process can not only ensure the security and integrity of the data, but also provide a reliable basis for subsequent data analysis and processing. In addition, the backed-up data can be conveniently retrieved and called, thus providing strong data support for decision-making support and business optimization.

[0030] III. Data processing and analysis module.

[0031] Integrate and process the data collected by different sensors, and ensure the accuracy and consistency of real-time data through efficient data fusion technology. Adopt machine learning algorithms to deeply process the data collected by sensors in real time and predict the building's health life. At the same time, label the collected disease pictures, and then send the labeled pictures into the neural network for training and learning to prepare for the subsequent identification of building diseases.

[0032] IV. Digital twin model construction module.

[0033] The Building Information Model is adopted to construct the physical model of the building structure. During the model design process, the influences of different types of loads will be fully considered, such as dead loads, live loads, wind loads and seismic loads, as well as the influences of environmental factors on the structural performance, such as temperature changes, humidity and corrosion, etc. Through the comprehensive analysis of these factors, we can more accurately simulate the actual use situation of the building, thus providing a solid foundation for subsequent analysis and monitoring. At the same time, the material properties of various components need to be defined in detail, including their elastic modulus, compressive strength and tensile strength, etc. The accurate description of these material properties is crucial for the stability and reliability of the model. In addition, the geometric shape of the building should be comprehensively considered to ensure that all components such as beams, columns and foundations are truly reflected in the model. At the same time, the design of the connection method cannot be ignored. A reasonable connection method can effectively improve the integrity and seismic resistance of the structure.

[0034] Machine learning algorithms and neural network algorithms are used to construct the mathematical model of the digital twin. During the model design process, the collected sensor data is trained by machine learning algorithms to obtain weights and construct a disease prediction model; the video surveillance data is put into the neural network for training to obtain a disease monitoring model.

[0035] The physical model is combined with the mathematical model to obtain the digital twin model. This digital twin model can not only truly reflect the physical characteristics of the building, but also be dynamically updated to reflect the changes of the building in real time during the use process. This combination enables the model to more comprehensively present the operation state of the building.

[0036] V. Real-time Monitoring and Prediction Module.

[0037] Through the digital twin model, the real-time monitoring and prediction functions of the health state of the building structure can be realized. When the data transmitted by the sensor is received, the prediction model predicts the health state of the building. In the disease detection link, the system will set a series of disease detection indicators and thresholds, which are obtained based on industry standards and historical data analysis. Using these indicators, the system can conduct a comprehensive health assessment of the building structure and determine whether there is a disease risk.

[0038] Adopting advanced pattern recognition technology, the system can automatically identify abnormal situations in the structure and classify them, such as diseases of types like cracks, deformations, rusts, etc. Through an automated method, the efficiency and accuracy of disease detection are significantly improved, and the errors and omissions that may be brought about by manual evaluation are reduced.

[0039] VI. Early Warning Decision-making and Support Module.

[0040] Once the system detects a disease, it will automatically generate warning messages. These warning messages will be promptly notified to relevant personnel through the mobile application so that they can quickly take measures to prevent the disease from worsening. A timely warning mechanism not only helps to ensure building safety but also reduces potential economic losses.

[0041] In addition, the system also provides decision support tools to help managers formulate effective maintenance and reinforcement plans. These tools provide feasibility assessments of various maintenance plans by analyzing the severity of the disease and the possible scope of influence, ensuring that managers can make scientific and reasonable decisions.

[0042] VII. Feedback and Optimization Module.

[0043] Based on the monitoring results and maintenance effects, the system will continuously update the digital twin model. Through the feedback mechanism, the system can continuously learn and optimize the monitoring algorithm to improve the accuracy of the model and the monitoring effect. This dynamic update process not only enhances the model's ability to respond to the actual state of the building but also improves the system's prediction accuracy of future potential diseases, thus better maintaining the safety and service life of the building.

[0044] The building disease monitoring method based on digital twin technology provided by the present invention addresses the problem that the prior art cannot achieve dynamic real-time monitoring of the health status of building structures. By adopting digital twin technology, a virtual building structure model is created, and at the same time, sensors and monitoring videos are deployed to transmit the parameters of the building in real time, achieving the effect of real-time monitoring. At the same time, the digital twin model can calculate based on the data input by sensors and monitoring videos, predict the health life of the building, and can promptly alarm and provide decision support tools when the building has diseases. Subsequently, the digital twin model can be continuously updated according to the monitoring results and maintenance effects of the building to improve the accuracy of the model and the detection effect.

[0045] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A building disease monitoring method based on digital twin technology, characterized in that: The following steps are involved: S1. Collect multi-dimensional information such as the building's geometric information, material properties, structural properties, and construction technology, and install various types of sensors such as strain gauges, accelerometers, temperature and humidity sensors at key locations of the building to monitor the building's structural status and environmental changes in real time; S2, transmit the collected data to a centrally managed database through advanced communication equipment for systematic backup; S3. Use data fusion technology to integrate and process sensor data, and use machine learning algorithms to conduct in-depth data analysis to predict the healthy life of buildings and conduct disease monitoring; S4. Build a physical model of the building structure based on the building information model (BIM), and use machine learning and neural network algorithms to build a mathematical model of the digital twin, combining the physical model with the mathematical model to form a dynamically updated digital twin model; S5. Achieve real-time monitoring and prediction of the health status of the building structure through the digital twin model, and set disease detection indicators to assess whether the building has disease risks; S6. When the system detects a disease, it automatically generates warning information and notifies relevant personnel through mobile applications, while providing decision support tools.

2. The building disease monitoring method based on digital twin technology according to claim 1 is characterized in that: The installation positions of the sensors are rationally arranged by analyzing the key load-bearing parts and potential disease risk points of the building.

3. The building disease monitoring method based on digital twin technology according to claim 1 is characterized in that: The systematic backup includes regular automatic backup and manual backup.

4. The building disease monitoring method based on digital twin technology according to claim 1 is characterized in that: The data fusion technology includes Kalman filtering, complementary filtering or particle filtering algorithm.

5. The building disease monitoring method based on digital twin technology according to claim 1 is characterized in that: During the construction of the digital twin model, it is necessary to consider the influence of environmental factors, including temperature, humidity and corrosion.

6. The building disease monitoring method based on digital twin technology according to claim 1 is characterized in that: During the disease monitoring process, a comprehensive assessment of the building's health status is conducted based on historical data and disease detection indicators set in industry standards.

7. The building disease monitoring method based on digital twin technology according to claim 6 is characterized in that: The disease detection indicators include crack width, deformation and vibration frequency.

Images