Steel bar strength prediction system based on digital twinning

Abstract

The invention discloses a steel bar strength prediction system based on digital twinning, and the system comprises a high-precision data collection module which employs an optical fiber sensor and an MEMS sensor, and monitors the stress, strain and temperature parameters of a steel bar in real time; according to the digital twinborn model, the high-precision digital twinborn model is established by adopting a multi-source data fusion technology and combining physical characteristics and environmental factors of reinforcing steel bars, and the digital twinborn model can adapt to reinforcing steel bar structures of different types and scales and support expansion to adapt to new technologies and data sources. According to the method, efficient data processing is adopted, real-time data streams can be better processed and analyzed, the accuracy and the real-time performance of data are ensured, the accuracy of the digital twin model and the adaptability to different steel bar main structures are enhanced by introducing machine learning and deep learning technologies, and the accuracy and the real-time performance of the digital twin model are improved. The safety risk of the steel bar main body structure can be evaluated in real time, and related personnel can be notified in time through the early warning system, so that potential safety problems can be prevented.

Description

Technical Field

[0001] The present invention relates to the field of metal strength prediction, and in particular to a steel bar strength prediction system based on digital twins. Background Art

[0002] With the continuous development of construction projects, steel bars are an important part of building structures, such as reinforced concrete bridges. The strength prediction of steel bars is of great significance to the quality and safety of projects. Traditional steel bar strength prediction methods often rely on experience and simple mathematical models, which cannot accurately reflect the actual state of steel bars in complex environments. As an emerging technology, digital twin technology can achieve real-time monitoring and prediction of steel bar status by building a virtual model of steel bars.

[0003] At present, the steel bar strength prediction system based on digital twin is mainly used in the health monitoring and construction safety assessment of steel structures. These systems usually include distributed data acquisition systems, remote data transmission and control systems, and steel structure safety performance prediction modules.

[0004] However, the prior art has the following disadvantages:

[0005] Insufficient real-time performance of data collection and transmission: Due to delays in data collection and transmission, the system cannot reflect the actual status of the steel bars in real time, resulting in reduced accuracy of the prediction results.

[0006] Low model accuracy: During the construction process of existing digital twin models, some key parameters are often ignored, resulting in insufficient model accuracy and inability to accurately predict the strength changes of steel bars.

[0007] In addition, existing technologies often ignore the impact of environmental factors on the strength of steel bars, such as temperature fluctuations, humidity changes, and load changes, resulting in inaccurate assessment of structural safety. To this end, a steel bar strength prediction system based on digital twins is provided to solve the above problems. Summary of the invention

[0008] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a steel bar strength prediction system based on digital twins.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0010] The present invention provides a reinforcement strength prediction system based on digital twin, comprising:

[0011] High-precision data acquisition module, using optical fiber sensors and MEMS sensors to monitor the stress, strain and temperature parameters of steel bars in real time;

[0012] The digital twin model uses multi-source data fusion technology to combine the physical characteristics of steel bars and environmental factors to establish a high-precision digital twin model that can adapt to steel structures of different types and sizes and support expansion to adapt to new technologies and data sources;

[0013] Intelligent algorithm module, combining machine learning and deep learning algorithms, intelligently analyzes and processes the collected data to improve the performance of the prediction model;

[0014] Multi-source data integration module, which is used to integrate data from multiple sources, including sensor data, historical records, and real-time monitoring data, to improve the accuracy and efficiency of prediction;

[0015] The real-time data transmission module, including data compression, decompression, data redundancy and backup units, transmits data to the central control system in real time through the network.

[0016] As a preferred technical solution of the present invention, it also includes:

[0017] Real-time risk assessment and early warning module, which is used to assess the safety risks of steel structures in real time and issue early warnings, helping construction site workers take timely measures to prevent potential safety issues. It also includes an automatic alarm mechanism to automatically notify relevant personnel when potential safety risks are detected;

[0018] Cloud services and edge computing modules enable rapid data processing and analysis, improve system response speed and efficiency, and include distributed computing, data encryption and secure transmission functions to ensure data security and confidentiality;

[0019] Dynamic environmental adaptability module, which adjusts the parameters of the digital twin model according to real-time environmental changes to improve the accuracy of prediction and the adaptability of the system;

[0020] The prediction result visualization module displays the prediction results to users in the form of graphs and charts, which facilitates users to quickly understand and make decisions;

[0021] The remote control and operation module allows users to control and operate the system through a remote interface, improving the accessibility and convenience of the system.

[0022] As a preferred technical solution of the present invention, the data collected by the high-precision data acquisition module is sent to the real-time data transmission module;

[0023] The real-time data transmission module transmits data to the central control system in real time through the network;

[0024] The multi-source data integration module receives data from the real-time data transmission module and provides it to the digital twin model after data processing;

[0025] The dynamic environmental adaptability module receives feedback from the digital twin model;

[0026] The prediction results of the digital twin model are analyzed by the intelligent algorithm module;

[0027] The prediction results of the intelligent algorithm module are transmitted to the prediction result visualization module for display;

[0028] The prediction result visualization module provides a visual display of the prediction results and allows the user to control and operate the system through the remote control and operation module;

[0029] The real-time risk assessment and early warning module receives the analysis results of the intelligent algorithm module, assesses the safety risks of the steel structure in real time and issues early warnings;

[0030] The cloud service and edge computing modules receive data from the multi-source data integration module and the digital twin model, enable rapid data processing and analysis, and ensure data security and privacy through distributed computing, data encryption, and secure transmission functions.

[0031] As a preferred technical solution of the present invention, the multi-source data integration module includes a data cleaning unit and a pre-processing unit to optimize data quality.

[0032] As a preferred technical solution of the present invention, the digital twin model includes a structural health status monitoring function to monitor the status of the steel structure in real time.

[0033] As a preferred technical solution of the present invention, the intelligent algorithm module includes an adaptive learning function to automatically adjust and optimize the prediction model according to new data.

[0034] As a preferred technical solution of the present invention, the high-precision data acquisition module includes an automatic calibration module for calibrating the sensor to ensure the accuracy of data acquisition.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention adopts efficient data processing, which can better process and analyze real-time data streams and ensure the accuracy and real-time nature of the data. By introducing machine learning and deep learning technologies, the accuracy of the digital twin model and its adaptability to different steel bar main structures are enhanced. It also integrates multiple modules such as data acquisition, transmission, processing and analysis to form an efficient and coordinated whole, thereby improving the overall performance and efficiency of the system. It can evaluate the safety risks of steel bar main structures in real time and promptly notify relevant personnel through an early warning system to help prevent potential safety issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0038] Figure 1 It is a system structure flow chart of the present invention; DETAILED DESCRIPTION

[0039] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0040] Example 1

[0041] like Figure 1 As shown, the present invention provides a reinforcement strength prediction system based on digital twin, comprising:

[0042] High-precision data acquisition module, using optical fiber sensors and MEMS sensors to monitor the stress, strain and temperature parameters of steel bars in real time;

[0043] The digital twin model uses multi-source data fusion technology to combine the physical characteristics of steel bars and environmental factors to establish a high-precision digital twin model that can adapt to steel structures of different types and sizes and support expansion to adapt to new technologies and data sources;

[0044] Intelligent algorithm module, combining machine learning and deep learning algorithms, intelligently analyzes and processes the collected data to improve the performance of the prediction model;

[0045] Multi-source data integration module, which is used to integrate data from multiple sources, including sensor data, historical records, and real-time monitoring data, to improve the accuracy and efficiency of prediction;

[0046] The real-time data transmission module, including data compression, decompression, data redundancy and backup units, transmits data to the central control system in real time through the network.

[0047] Furthermore, it also includes:

[0048] Real-time risk assessment and early warning module, which is used to assess the safety risks of steel structures in real time and issue early warnings, helping construction site workers take timely measures to prevent potential safety issues. It also includes an automatic alarm mechanism to automatically notify relevant personnel when potential safety risks are detected;

[0049] Cloud services and edge computing modules enable rapid data processing and analysis, improve system response speed and efficiency, and include distributed computing, data encryption and secure transmission functions to ensure data security and confidentiality;

[0050] Dynamic environmental adaptability module, which adjusts the parameters of the digital twin model according to real-time environmental changes to improve the accuracy of prediction and the adaptability of the system;

[0051] The prediction result visualization module displays the prediction results to users in the form of graphs and charts, which facilitates users to quickly understand and make decisions;

[0052] The remote control and operation module allows users to control and operate the system through a remote interface, improving the accessibility and convenience of the system.

[0053] Further, the data collected by the high-precision data acquisition module is sent to the real-time data transmission module;

[0054] The real-time data transmission module transmits data to the central control system in real time through the network;

[0055] The multi-source data integration module receives data from the real-time data transmission module and provides it to the digital twin model after data processing;

[0056] The dynamic environmental adaptability module receives feedback from the digital twin model;

[0057] The prediction results of the digital twin model are analyzed by the intelligent algorithm module;

[0058] The prediction results of the intelligent algorithm module are transmitted to the prediction result visualization module for display;

[0059] The prediction result visualization module provides a visual display of the prediction results and allows the user to control and operate the system through the remote control and operation module;

[0060] The real-time risk assessment and early warning module receives the analysis results of the intelligent algorithm module, assesses the safety risks of the steel structure in real time and issues early warnings;

[0061] The cloud service and edge computing modules receive data from the multi-source data integration module and the digital twin model, enable rapid data processing and analysis, and ensure data security and privacy through distributed computing, data encryption, and secure transmission functions.

[0062] Furthermore, the multi-source data integration module includes a data cleaning unit and a pre-processing unit to optimize data quality.

[0063] Furthermore, the digital twin model includes a structural health monitoring function to monitor the status of the steel structure in real time.

[0064] Furthermore, the intelligent algorithm module includes an adaptive learning function to automatically adjust and optimize the prediction model based on new data.

[0065] Furthermore, the high-precision data acquisition module includes an automatic calibration module for calibrating the sensor to ensure the accuracy of data acquisition.

[0066] Specifically, a strength prediction analysis was conducted on a reinforced concrete bridge with a design life of 50 years. The bridge is 200 meters long and 20 meters wide, and mainly bears the loads of vehicles and pedestrians.

[0067] The specific operations are as follows:

[0068] first step:

[0069] Fiber optic sensors and MEMS sensors are installed at the key bearing points of the bridge to ensure that they can accurately monitor the stress, strain and temperature parameters of the steel bars. The sensor parameters are:

[0070] Fiber optic sensor: sensitivity 0.1N / m, measurement range 0-1000N;

[0071] MEMS sensor: sensitivity 0.01%, measurement range 0-2%;

[0072] The measurement frequency is once per minute;

[0073] Configure the real-time data transmission module to enable it to transmit data to the central control system in real time through the network;

[0074] Set the initial parameters of the digital twin model, including the physical properties of the bridge steel bars and environmental factors.

[0075] Step 2:

[0076] Start the multi-source data integration module and start real-time monitoring of the bridge reinforcement structure data;

[0077] The real-time data transmission module transmits data to the central control system in real time through the network.

[0078] Step 3:

[0079] The multi-source data integration module receives data from the real-time data transmission module and provides it to the digital twin model after data cleaning and preprocessing;

[0080] Digital Twin Model Parameters

[0081] Physical properties of steel bars: diameter 20 mm, elastic modulus 200 GPa, yield strength 400 MPa;

[0082] Environmental factors: temperature range -20℃ to 40℃, relative humidity range 10% to 90%;

[0083] The digital twin model is established based on the processed data, combining the physical properties of the bridge steel bars and environmental factors to simulate the stress and deformation of the bridge under different load and environmental conditions. The model is updated once a day, taking into account factors such as temperature changes, wind loads and traffic flow.

[0084] Step 4:

[0085] Use cloud services and edge computing modules to process and analyze data to improve the response speed of predictions. Cloud computing resources are allocated to each model with 4-core CPUs and 16GB of memory.

[0086] The intelligent algorithm module applies machine learning and deep learning algorithms to analyze data and improve the performance of the prediction model;

[0087] Intelligent algorithm parameters:

[0088] Machine learning algorithm: support vector machine (SVM), regularization coefficient C = 100, kernel function parameter γ = 0.1;

[0089] Deep learning algorithm: Convolutional neural network (CNN), input layer dimension 500, hidden layer dimension 1000, output layer dimension 500, learning rate 0.001;

[0090] Use machine learning algorithms to analyze data and predict changes in bridge strength over the next year. The algorithm training set contains data from the past five years, with a prediction accuracy target of 95%;

[0091] The prediction results of the digital twin model are analyzed by the intelligent algorithm module.

[0092] Step 5:

[0093] The forecast result visualization module displays the forecast results to users in the form of graphs and charts. The visualization interface is updated in real time and supports user-defined views and reports.

[0094] Users control and operate the system through the remote control and operation module, improving the accessibility and convenience of the system. The remote operation interface supports multi-platform access, including desktop and mobile devices.

[0095] Step 6:

[0096] The real-time risk assessment and early warning module receives the analysis results of the intelligent algorithm module and evaluates the safety risks of the bridge's steel structure in real time. The risk assessment threshold is set at steel bar stress exceeding 80% of the design stress. When potential safety risks are detected, the system automatically issues an early warning to notify staff to take timely measures.

[0097] Experimental Results

[0098] During the 30-day continuous operation test, the system successfully predicted the stress increase caused by continuous high temperature and increased traffic load. The deviation between the predicted maximum stress value and the actual measured value was less than 5%, proving the high accuracy of the model. During the test period, the system issued a total of 3 warnings, each of which received timely response and maintenance, avoiding potential safety accidents.

[0099] In summary, through the high-precision data acquisition module, the present invention enables the system to monitor the stress, strain and temperature parameters of steel bars in real time, provide a continuous data stream, and thus realize continuous monitoring of the health status of the structure; the digital twin model comprehensively considers the physical properties and environmental factors of the steel bars, such as temperature, humidity and load, to improve the accuracy of strength prediction; the intelligent algorithm module can analyze multi-source data, and automatically adjust the prediction model according to new data through adaptive learning functions to ensure the timeliness and accuracy of the prediction results; the real-time risk assessment and early warning module can promptly detect potential safety risks, and notify relevant personnel through an automatic alarm mechanism, thereby improving emergency response capabilities; the cloud service and edge computing modules provide data encryption and secure transmission functions to ensure data security and privacy protection.

[0100] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A steel bar strength prediction system based on digital twin, characterized in that: include: High-precision data acquisition module, using optical fiber sensors and MEMS sensors to monitor the stress, strain and temperature parameters of steel bars in real time; The digital twin model uses multi-source data fusion technology to combine the physical characteristics of steel bars and environmental factors to establish a high-precision digital twin model that can adapt to steel structures of different types and sizes and support expansion to adapt to new technologies and data sources; Intelligent algorithm module, combining machine learning and deep learning algorithms, intelligently analyzes and processes the collected data to improve the performance of the prediction model; Multi-source data integration module, which is used to integrate data from multiple sources, including sensor data, historical records, and real-time monitoring data, to improve the accuracy and efficiency of prediction; The real-time data transmission module, including data compression, decompression, data redundancy and backup units, transmits data to the central control system in real time through the network.

2. A reinforcement strength prediction system based on digital twin according to claim 1, characterized in that: Also includes: Real-time risk assessment and early warning module, which is used to assess the safety risks of steel structures in real time and issue early warnings, helping construction site workers take timely measures to prevent potential safety issues. It also includes an automatic alarm mechanism to automatically notify relevant personnel when potential safety risks are detected; Cloud services and edge computing modules enable rapid data processing and analysis, improve system response speed and efficiency, and include distributed computing, data encryption and secure transmission functions to ensure data security and confidentiality; Dynamic environmental adaptability module, which adjusts the parameters of the digital twin model according to real-time environmental changes to improve the accuracy of prediction and the adaptability of the system; The prediction result visualization module displays the prediction results to users in the form of graphs and charts, which facilitates users to quickly understand and make decisions; The remote control and operation module allows users to control and operate the system through a remote interface, improving the accessibility and convenience of the system.

3. A reinforcement strength prediction system based on digital twin according to claim 2, characterized in that: The data collected by the high-precision data collection module is sent to the real-time data transmission module; The real-time data transmission module transmits data to the central control system in real time through the network; The multi-source data integration module receives data from the real-time data transmission module and provides it to the digital twin model after data processing; The dynamic environmental adaptability module receives feedback from the digital twin model; The prediction results of the digital twin model are analyzed by the intelligent algorithm module; The prediction results of the intelligent algorithm module are transmitted to the prediction result visualization module for display; The prediction result visualization module provides a visual display of the prediction results and allows the user to control and operate the system through the remote control and operation module; The real-time risk assessment and early warning module receives the analysis results of the intelligent algorithm module, assesses the safety risks of the steel structure in real time and issues early warnings; The cloud service and edge computing modules receive data from the multi-source data integration module and the digital twin model, enable rapid data processing and analysis, and ensure data security and privacy through distributed computing, data encryption, and secure transmission functions.

4. A reinforcement strength prediction system based on digital twin according to claim 3, characterized in that: The multi-source data integration module includes a data cleaning unit and a pre-processing unit to optimize data quality.

5. The steel bar strength prediction system based on digital twin according to claim 3 is characterized in that: The digital twin model includes a structural health monitoring function to monitor the status of the steel structure in real time.

6. The steel bar strength prediction system based on digital twin according to claim 3 is characterized in that: The intelligent algorithm module includes an adaptive learning function to automatically adjust and optimize the prediction model according to new data.

7. The steel bar strength prediction system based on digital twin according to claim 3 is characterized in that: The high-precision data acquisition module includes an automatic calibration module for calibrating the sensor to ensure the accuracy of data acquisition.

Images