Online health monitoring system suitable for large-span roof truss steel structure

Abstract

The invention discloses an online health monitoring system suitable for a large-span roof truss steel structure, and the system comprises a structure analysis module which is used for building a three-dimensional finite element model of the roof truss steel structure, carrying out the application of load and boundary conditions, stress-strain analysis and key position recognition, and providing a monitoring point arrangement suggestion; the real-time measurement module is used for selecting and arranging sensors, collecting and transmitting real-time data, preprocessing and storing the data and providing real-time monitoring and alarming functions; and the intelligent analysis module is used for processing and cleaning the collected data, executing anomaly detection and fault diagnosis, carrying out trend analysis and prediction, optimizing the monitoring and analysis process by utilizing machine learning and artificial intelligence technologies, and generating a visual report. According to the invention, comprehensive, online, real-time and accurate health state monitoring of the roof truss steel structure is realized, the safety and stability of the large-span roof truss steel structure are ensured, the service life is prolonged, the maintenance cost is reduced, and the method has important practical application value.

Description

Technical Field

[0001] The invention belongs to the technical field of safe construction of grid steel structures, and in particular relates to an online health monitoring system suitable for large-span roof grid steel structures. Background Art

[0002] With the development of modern construction technology, roof grid steel structures are increasingly used in large buildings. Due to their complex structural forms and the diversity of loads they bear, real-time monitoring is particularly important to ensure the safety and stability of the structure. Existing monitoring methods often rely on regular inspections and manual operations, and cannot achieve real-time and continuous monitoring of roof grid steel structures. Therefore, it is of great practical significance to develop an online monitoring system that can monitor the status of roof grid steel structures in real time. Summary of the invention

[0003] In order to solve the above-mentioned technical problems existing in the prior art, the present invention provides an online health monitoring system suitable for large-span roof grid steel structures. The system combines structural analysis, real-time measurement and intelligent analysis to realize real-time monitoring of the health status of the grid steel structure, thereby improving the safety of the structure, extending its service life and reducing maintenance costs.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: an online health monitoring system applicable to large-span roof grid steel structures, comprising a structural analysis module, a real-time measurement module and an intelligent analysis module; wherein, Structural analysis module, used to establish a three-dimensional finite element model of the roof grid steel structure, apply loads and boundary conditions, perform stress-strain analysis, identify key locations, and provide suggestions for monitoring point layout; Real-time measurement module, which is used to select and arrange sensors based on structural analysis results, collect and transmit real-time data, perform data preprocessing and storage, and provide real-time monitoring and alarm functions; The intelligent analysis module is used to process and clean the collected data, perform anomaly detection and fault diagnosis, conduct trend analysis and prediction, use machine learning and artificial intelligence technologies to optimize the monitoring and analysis process, and generate visual reports.

[0005] Furthermore, the structural analysis module includes an initial structural modeling unit, a load and boundary condition setting unit, a stress-strain analysis unit, and a key position identification and monitoring point arrangement unit; wherein, Initial structural modeling unit, using finite element analysis software to build a three-dimensional model of the roof grid steel structure and define material properties; Load and boundary condition setting unit, used to identify the type of load borne by the structure and set the corresponding boundary conditions to simulate the stress and deformation under different working conditions; Stress-strain analysis unit, which identifies areas of stress concentration and large deformation in the structure through stress and strain analysis; The key position identification and monitoring point layout unit identifies key positions where deformation and damage may occur based on the analysis results and makes recommendations on sensor layout.

[0006] Furthermore, the real-time measurement module includes a sensor selection and arrangement unit, a data acquisition and transmission unit, and a real-time monitoring and alarm unit; wherein, The sensor selection and layout unit selects appropriate sensor types based on the structural analysis results. Sensor types include strain, acceleration and / or temperature sensors, and arranges sensors reasonably at key monitoring points. Data acquisition and transmission unit collects sensor data in real time and transmits data by wire or wireless method to ensure data time synchronization; Data preprocessing and storage unit, which preprocesses the collected data, filters noise and compresses and stores it to ensure the validity and long-term preservation of the data; The real-time monitoring and alarm unit provides a real-time monitoring interface, sets alarm thresholds, triggers alarms when abnormal signals are detected, and performs data analysis and trend forecasting.

[0007] Furthermore, the intelligent analysis module includes a data processing and cleaning unit, an anomaly detection and fault diagnosis unit, a trend analysis and prediction unit, a machine learning and artificial intelligence application unit, and a visualization and report generation unit: Data processing and cleaning unit, which ensures the accuracy and integrity of real-time measurement data through noise filtering, data correction and missing data processing; Anomaly detection and fault diagnosis unit, which identifies structural problems based on set thresholds and anomaly detection algorithms, and analyzes possible fault types and locations through fault diagnosis; Trend analysis and prediction unit, which performs trend analysis based on historical data, evaluates the structural health status, and provides maintenance recommendations through predictive algorithms; The machine learning and artificial intelligence application unit uses historical data to train and update machine learning models, automate data analysis and decision-making, and improve the accuracy of anomaly detection and fault diagnosis; Visualization and reporting unit to intuitively display the structural health status and regularly generate and share monitoring reports.

[0008] Furthermore, the intelligent analysis module further includes a feedback and optimization unit for collecting user feedback, continuously optimizing analysis algorithms and system functions, and continuously adjusting monitoring parameters and analysis models through adaptive algorithms.

[0009] By adopting the above technical scheme, compared with the prior art, the present invention has the following beneficial effects: the present invention realizes all-round online, real-time and accurate health status monitoring of the roof grid steel structure through the mutual cooperation and collaborative work of the three parts of the structural analysis module, the real-time measurement module and the intelligent analysis module, thereby ensuring the safety and stability of the large-span roof grid steel structure, improving the service life and reducing the maintenance cost, and has important practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of the first part of the system provided by the present invention - structural analysis; Figure 2 A flowchart of the second part of the system provided by the present invention - real-time measurement; Figure 3 A flow chart of the third part of the system - intelligent analysis - provided by the present invention. DETAILED DESCRIPTION

[0011] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and examples.

[0012] The online health monitoring system for large-span roof grid steel structures of the present invention comprises three main parts: a structural analysis module, a real-time measurement module and an intelligent analysis module. The specific implementation methods of each part are described in detail below.

[0013] The first part is the structural analysis module, and the main steps of its structural analysis are as follows: S1. Initial structural modeling: In the present invention, a finite element analysis (FEA) software such as HYPERMESH is used to establish an accurate three-dimensional model of the roof grid steel structure. The main steps are as follows: First, create a geometric model of the structure based on the design drawings and actual structural conditions; Then, define the material properties, including the elastic modulus, Poisson’s ratio, yield strength, etc. of the steel, to ensure that the model can truly reflect the physical characteristics of the structure.

[0014] S2. Application of loads and boundary conditions. The steps are as follows: Through analysis, identify the various loads that the structure may be subjected to, including static loads such as deadweight and steady loads, and dynamic loads such as wind loads and earthquake loads; Boundary conditions are set according to the actual installation situation to ensure that the model can truly reflect the working status of the structure.

[0015] Simulate different working conditions, such as normal use conditions and limit conditions, and analyze the stress and deformation of the structure under these conditions.

[0016] S3, stress-strain analysis, the steps are as follows: Use finite element analysis to calculate the stress distribution of each component and node and identify stress concentration areas; Analyze the deformation of components and nodes, paying special attention to the parts with maximum deformation and large relative displacement; If the effect of temperature changes on the structure is considered, thermal stress analysis is also required to evaluate the thermal deformation caused by temperature changes.

[0017] S4, deformation and damage prediction, the steps are as follows: Based on the stress and strain analysis results, identify the areas with the largest deformation and potential damage locations in the structure; Through further simulation, possible failure modes such as local buckling, node loosening and rod cracking are predicted to evaluate the weakness of the structure and provide a basis for subsequent monitoring.

[0018] S5. Suggestions for monitoring point layout, the steps are as follows: Based on the above stress and strain analysis results, key locations with concentrated stress and large deformation are selected as monitoring points, and a sensor layout plan is formulated to ensure real-time monitoring of key areas; Combined with actual installation conditions, the number and location of sensors are optimized to balance monitoring coverage and system cost.

[0019] S6. Result verification and optimization, the steps are as follows: Verify the accuracy of simulation analysis results through field testing or comparison with existing data; Based on the verification results, the structural model and monitoring point layout plan are optimized to ensure the effectiveness and reliability of the final plan.

[0020] The second part is the real-time measurement module. The main steps of real-time measurement are as follows: (1) Sensor selection and configuration, the steps are as follows: According to the structural analysis results, select the appropriate sensor type, such as strain sensor, acceleration sensor, temperature sensor, etc.; Ensure that the sensor's measurement accuracy and range can capture subtle changes in key monitoring points.

[0021] (2) Sensor layout and installation, the steps are as follows: Arrange sensors at key monitoring points determined by structural analysis to ensure coverage of all areas with concentrated stress and large deformation; Use appropriate installation methods to ensure that the sensor is firmly connected to the structure and reduce the impact of external interference on the measurement results; arrange the connection lines between the sensor and the data acquisition system, and use anti-interference wiring methods to ensure the stability of signal transmission.

[0022] (3) Data collection and transmission, the steps are as follows: Collect data from each sensor in real time through the data acquisition system, and ensure that the acquisition frequency meets the monitoring requirements; According to the needs of the monitoring system, select wired or wireless transmission mode to transmit data to the central processing unit; Ensure the time synchronization of data from different sensors to avoid timing errors affecting the analysis results.

[0023] (4) Data preprocessing and storage, the steps are as follows: Pre-process the collected raw data, filter out noise signals, and clean the data to ensure the validity of the data; Real-time data is compressed to save storage space, and a reliable storage mechanism is set up to ensure the long-term preservation and traceability of data.

[0024] (5) Real-time monitoring and alarm, the steps are as follows: Develop a real-time monitoring interface to display real-time stress, strain, displacement and other parameters of key parts of the structure, so as to facilitate real-time monitoring of the health status of the structure; Set a threshold. When the system detects an abnormal signal exceeding the threshold, it will automatically trigger an alarm to prompt management personnel to conduct inspections and maintenance. Combining real-time and historical data, algorithms are used to perform trend analysis and prediction to identify possible structural problems in advance.

[0025] (6) System integration and debugging, the steps are as follows: Conduct integration testing of sensors, data acquisition systems, data transmission systems, and monitoring software to ensure that all parts work together; Carry out on-site debugging and adjust system parameters and sensor layout according to actual conditions to ensure stable system operation and accurate monitoring results.

[0026] The third part is the intelligent analysis module, and the main steps of its intelligent analysis are as follows: 1) Intelligent analysis is data processing and cleaning, and its steps are as follows: Use filtering algorithms to filter noise from real-time measurement data and remove external interference; Correct the collected data according to the sensor characteristics and installation errors to ensure the accuracy of the data; Missing data is processed through interpolation or other data recovery methods to ensure data integrity.

[0027] 2) Data storage and management, the steps are as follows: Establish a dedicated database to classify and store sensor data and support fast query and retrieval; Compress and store large amounts of monitoring data, and set up a regular backup mechanism to ensure data security and traceability; Ensure secure access and operation of data through permission management.

[0028] 3) Anomaly detection and fault diagnosis. The steps are as follows: Based on the structural analysis results and historical data, reasonable thresholds of stress, strain and other parameters are set for each monitoring point; Use real-time monitoring data for anomaly detection to identify potential structural problems through algorithms based on thresholds, statistical models, or machine learning; Further analyze the detected anomalies to determine the possible fault type and location, and generate a fault report.

[0029] 4) Trend analysis and forecasting, the steps are as follows: Conduct retrospective analysis of historical monitoring data to identify long-term trends and seasonal changes; Using trend analysis results, the health status of the roof grid steel structure is evaluated in real time to generate a health score or status report; Predict possible future structural problems and provide maintenance recommendations based on time series analysis or machine learning models.

[0030] 5) Machine learning and artificial intelligence applications, the steps are as follows: Collect and annotate historical fault data, train machine learning models (such as decision trees, support vector machines, etc.), and improve the accuracy of anomaly detection and fault diagnosis; Continuously collect new data and dynamically update machine learning models to adapt to different working conditions and structural states; Leverage artificial intelligence to automate data analysis, conduct real-time assessments of structural health, and automatically generate alerts and maintenance plans.

[0031] 6) Visualization and report generation, the steps are as follows: Develop data visualization interface to intuitively display the structural health status in the form of charts, curves, heat maps, etc. Generate monitoring reports regularly, summarize the system's analysis results, and support automatic sending to relevant personnel via email or other means.

[0032] Through the above implementation, the present invention realizes all-round online monitoring of the roof grid steel structure, ensures the safety and stability of the structure, increases its service life, and reduces maintenance costs.

[0033] The above embodiments illustrate the basic principles and features of the present invention, but the above only illustrates the preferred embodiments of the present invention and is not limited to the embodiments. Under the inspiration of this patent, a person skilled in the art can make many forms of deformation and improvement without departing from the scope of protection of the present invention and the claims, which are all within the protection scope of the present invention. Therefore, the patent and protection scope of the present invention shall be subject to the attached claims.

Claims

1. Online health monitoring system for large-span roof grid steel structures, characterized by: It includes structural analysis module, real-time measurement module and intelligent analysis module; among them, Structural analysis module, used to establish a three-dimensional finite element model of the roof grid steel structure, apply loads and boundary conditions, perform stress-strain analysis, identify key locations, and provide suggestions for monitoring point layout; Real-time measurement module, which is used to select and arrange sensors based on structural analysis results, collect and transmit real-time data, perform data preprocessing and storage, and provide real-time monitoring and alarm functions; The intelligent analysis module is used to process and clean the collected data, perform anomaly detection and fault diagnosis, conduct trend analysis and prediction, use machine learning and artificial intelligence technologies to optimize the monitoring and analysis process, and generate visual reports.

2. The online health monitoring system for large-span roof grid steel structures according to claim 1 is characterized in that: The structural analysis module includes the initial structural modeling unit, the load and boundary condition setting unit, the stress-strain analysis unit, and the key position identification and monitoring point arrangement unit; Initial structural modeling unit, using finite element analysis software to build a three-dimensional model of the roof grid steel structure and define material properties; Load and boundary condition setting unit, used to identify the type of load borne by the structure and set the corresponding boundary conditions to simulate the stress and deformation under different working conditions; Stress-strain analysis unit, which identifies areas of stress concentration and large deformation in the structure through stress and strain analysis; The key position identification and monitoring point layout unit identifies key positions where deformation and damage may occur based on the analysis results and makes recommendations on sensor layout.

3. The online health monitoring system for large-span roof grid steel structures according to claim 1 is characterized in that: The real-time measurement module includes a sensor selection and arrangement unit, a data acquisition and transmission unit, and a real-time monitoring and alarm unit; The sensor selection and layout unit selects appropriate sensor types based on the structural analysis results. Sensor types include strain, acceleration and / or temperature sensors, and arranges sensors reasonably at key monitoring points. Data acquisition and transmission unit collects sensor data in real time and transmits data by wire or wireless method to ensure data time synchronization; Data preprocessing and storage unit, which preprocesses the collected data, filters noise and compresses and stores it to ensure the validity and long-term preservation of the data; The real-time monitoring and alarm unit provides a real-time monitoring interface, sets alarm thresholds, triggers alarms when abnormal signals are detected, and performs data analysis and trend forecasting.

4. The online health monitoring system for large-span roof grid steel structures according to claim 1 is characterized in that: The intelligent analysis module includes data processing and cleaning unit, anomaly detection and fault diagnosis unit, trend analysis and prediction unit, machine learning and artificial intelligence application unit and visualization and report generation unit: Data processing and cleaning unit, which ensures the accuracy and integrity of real-time measurement data through noise filtering, data correction and missing data processing; Anomaly detection and fault diagnosis unit, which identifies structural problems based on set thresholds and anomaly detection algorithms, and analyzes possible fault types and locations through fault diagnosis; Trend analysis and prediction unit, which performs trend analysis based on historical data, evaluates the structural health status, and provides maintenance recommendations through predictive algorithms; The machine learning and artificial intelligence application unit uses historical data to train and update machine learning models, automate data analysis and decision-making, and improve the accuracy of anomaly detection and fault diagnosis; Visualization and reporting unit to intuitively display the structural health status and regularly generate and share monitoring reports.

5. The online health monitoring system for large-span roof grid steel structures according to claim 4 is characterized in that: The intelligent analysis module further includes a feedback and optimization unit, which is used to collect user feedback, continuously optimize the analysis algorithm and system functions, and continuously adjust the monitoring parameters and analysis models through adaptive algorithms.

Images