Method for evaluating dynamic detection bearing capacity of mixed structure of heat absorption tower

Abstract

The invention relates to the technical field of structure health monitoring and bearing capacity evaluation, and discloses a heat absorption tower hybrid structure dynamic detection bearing capacity evaluation method, which comprises the following steps: S1, arranging various sensors on a heat absorption tower structure, including an acceleration sensor, a strain gauge, a temperature sensor and a displacement sensor, collecting dynamic response data of the heat absorption tower under different working conditions; s2, on the basis of data collected by the sensors, a digital twin model of the heat absorption tower is built, and the model comprises finite element three-dimensional models of a tower footing, a tower body and a tower top. Real-time monitoring and high-precision prediction of the heat absorption tower are realized through a sensor network and a digital twinning technology, structural problems can be intelligently identified and early warning can be carried out in advance, meanwhile, a maintenance strategy is optimized based on fault prediction of AI, the maintenance cost is reduced, the equipment operation efficiency is improved, and the accuracy of structural analysis is further improved through introduction of the digital twinning technology. And the long-term safety and stability of the heat absorption tower are ensured.

Description

Technical Field

[0001] The invention relates to the technical field of structural health monitoring and bearing capacity evaluation, and in particular to a method for evaluating the bearing capacity of a heat absorption tower hybrid structure under dynamic detection. Background Art

[0002] As a key component in the solar thermal power generation system, the structural safety and bearing capacity of the heat absorption tower directly affect the stable operation of the entire system. At present, the heat absorption tower is composed of a combination of concrete and steel structures, and is subjected to complex external loads, including wind loads, temperature changes, and earthquakes. Therefore, structural health monitoring and bearing capacity evaluation of the heat absorption tower are necessary means to ensure its long-term safe operation. Traditional heat absorption tower monitoring methods mainly rely on regular manual inspections and static finite element analysis.

[0003] Existing methods for monitoring the health of heat absorption tower structures are based on regular inspections, using static stress analysis or vibration testing to evaluate the structural status. Finite element analysis (FEA) is often used to simulate the stress distribution and load-bearing capacity of heat absorption towers under specific working conditions. This type of method analyzes its dynamic response by simulating the geometry, material properties and external loads of the tower body, and evaluates the structure in combination with data from manual inspections.

[0004] Although existing finite element analysis and manual inspection methods can provide certain structural health assessments, they have significant limitations. First, traditional methods cannot achieve real-time monitoring and dynamic response assessment, which can easily lead to structural problems not being discovered in time during the development process. Secondly, the regular inspection method is lagging behind and cannot predict the fatigue life and potential fault locations of the structure in advance, which can easily lead to sudden structural failure. In addition, since the existing methods rely on manual operations, the maintenance cost is high, and it is difficult to optimize the maintenance strategy through data automation. These problems have affected the long-term safety and operating efficiency of the heat absorption tower, and an innovative method that can monitor in real time, intelligently predict and optimize maintenance is urgently needed. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for evaluating the dynamic detection bearing capacity of a hybrid structure of a heat absorption tower, which solves the problem that the prior art is unable to perform real-time monitoring, intelligent fault prediction and maintenance optimization, resulting in delayed discovery of structural problems and high maintenance costs.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure, comprising the following steps:

[0007] S1. Arrange a variety of sensors on the heat absorption tower structure, including acceleration sensors, strain gauges, temperature sensors and displacement sensors, to collect dynamic response data of the heat absorption tower under different working conditions;

[0008] S2. Based on the data collected by the sensor, a digital twin model of the heat absorption tower is constructed, wherein the model includes a finite element three-dimensional model of the tower base, the tower body and the tower top, and the material properties, geometric shape and boundary conditions of the finite element model match those of the actual heat absorption tower;

[0009] S3. Use artificial intelligence models to analyze the collected power data. The AI ​​model identifies the structural health status of the heat absorption tower by learning historical data and real-time data, and predicts its load-bearing capacity and potential damage locations;

[0010] S4. Combine the digital twin model with the AI ​​analysis results to evaluate the load-bearing capacity of the heat absorption tower and predict the dynamic response and fatigue life of the structure under future working conditions through simulation;

[0011] S5. Based on the load-bearing capacity evaluation results, a health status report of the heat absorption tower is generated, and preventive maintenance suggestions are made.

[0012] Preferably, the acceleration sensors are arranged in the middle and top of the tower body of the heat absorption tower, the strain gauges are arranged at the tower base, key nodes of the tower body and steel-concrete connection parts, the temperature sensors are arranged at the outside and inside positions of the tower base, tower body and tower top, and the displacement sensor is used to monitor the displacement changes of the tower top.

[0013] Preferably, the material properties of the finite element three-dimensional model are defined as:

[0014] Elastic modulus E of steel structure s , Poisson's ratio ν s , yield strength σ t ;

[0015] The elastic modulus of concrete is E c , Poisson's ratio ν c , and the nonlinear stress-strain relationship σ c =f(ε), where ε is the strain, σ c is the concrete stress;

[0016] The temperature field is simulated by the equation T = T0 + ΔT(x, t), where T0 is the initial temperature and ΔT(x, t) is the temperature gradient that changes with time.

[0017] Preferably, the AI ​​model includes a convolutional neural network and a long short-term memory network, which are used to process and analyze the collected time series data, and predict potential cracks, fatigue damage and load-bearing capacity reduction trends through a damage identification model.

[0018] Preferably, the simulation of the digital twin model includes dynamic analysis of wind load, temperature change, vibration multi-physics field coupling, using nonlinear dynamic equations:

[0019]

[0020] Among them, M is the mass matrix, C is the damping matrix, K is the stiffness matrix, F(t) is the external load, u(t), are the displacement, velocity and acceleration responses respectively.

[0021] Preferably, in S4, the boundary conditions and material properties of the digital twin model are adjusted through the input of real-time data, so that the virtual model is synchronized with the working conditions of the physical heat absorption tower, and the dynamic response within a specific time period in the future is predicted.

[0022] Preferably, in S5, a health status report is generated based on the bearing capacity calculation results, and the report includes a health score of the heat absorption tower, stress distribution and crack propagation prediction of key structural parts, and a recommended preventive maintenance schedule.

[0023] Preferably, the sensor data is collected at a frequency of 10-100 Hz, and the sensor network transmits the data to a data processing center via LoRa, NB-IoT or 4G / 5G wireless communications, and edge computing devices are used to preprocess and preliminarily analyze the data.

[0024] Preferably, in the method, the prediction of fatigue life is based on cumulative damage theory, using the following fatigue life prediction formula:

[0025]

[0026] Where D is the cumulative fatigue damage, N t is the number of stress cycles in the i-th cycle, N f is the fatigue life under this stress. When D=1, the structure is considered to have reached the fatigue limit.

[0027] Preferably, the system automatically generates structural optimization suggestions based on the simulation and analysis results of the digital twin technology and AI model, and optimizes the design and structural performance of the heat absorption tower by adjusting the mesh division and material selection of the finite element model.

[0028] The present invention provides a method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure. It has the following beneficial effects:

[0029] 1. The present invention realizes real-time monitoring of the heat absorption tower structure through the combination of sensor network and digital twin technology, and can capture the dynamic response of the tower body under various working conditions, especially the stress, displacement and vibration under the external loads of wind load and temperature change. Through the introduction of artificial intelligence model, the system can analyze data with high precision, update the structural health status in real time, provide accurate bearing capacity evaluation, and predict future fatigue life and fault location in advance, avoiding the lag of traditional periodic detection methods and ensuring structural safety.

[0030] 2. The present invention utilizes artificial intelligence technology, combined with historical and real-time data, to automatically analyze the operating status of the heat absorption tower, identify potential problems in the structure and make intelligent predictions. Through the AI ​​model's prediction of fatigue life and structural crack expansion trends, the system can generate maintenance recommendations in advance, achieve preventive maintenance, avoid sudden failures and excessive maintenance, greatly reduce maintenance costs, and improve the operating efficiency and safety of the equipment.

[0031] 3. The present invention introduces digital twin technology to keep the virtual simulation model and the dynamic state of the physical structure synchronized in real time. By combining multi-physical field coupling simulation, the stress distribution and bearing capacity of the heat absorption tower under different working conditions are comprehensively analyzed. The two-way feedback of simulation results and real-time sensor data enables the system to adapt to changes in complex environments, improves the accuracy of analysis, ensures the reliability of structural health assessment and bearing capacity prediction, and thus optimizes the design and operation management of the heat absorption tower. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a process flow chart of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Please see attached Figure 1 The present invention proposes a method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure based on a combination of sensor networks, digital twin technology and artificial intelligence (AI) models. It uses real-time data and virtual simulation to predict the dynamic response and structural life of the heat absorption tower, which can greatly improve the monitoring accuracy and real-time performance, thereby effectively avoiding the occurrence of structural failure accidents.

[0035] Implementation steps

[0036] Step 1: Sensor placement and data collection

[0037] First, a sensor network is deployed at key locations of the heat absorption tower to collect real-time dynamic response data of the structure. The sensors include:

[0038] Acceleration sensor: arranged in key positions such as the middle and top of the tower body to monitor the vibration response of the tower body in real time and analyze the dynamic characteristics caused by wind load or earthquake.

[0039] Strain gauges: arranged at the tower base, key nodes of the tower body and the steel-concrete junction, used to monitor stress concentration, structural deformation and fatigue crack propagation.

[0040] Temperature sensors: arranged at the tower base, tower top, and inside and outside the tower body to monitor the temperature distribution and temperature difference of the tower body and study the impact of temperature on structural performance.

[0041] Displacement sensor: Arranged at the top of the tower, it is used to monitor the horizontal and vertical displacement of the top of the tower and analyze the overall stability of the tower.

[0042] Sensor data is transmitted to the data processing center in real time through wireless communication networks (such as LoRa, NB-IoT or 4G / 5G) to ensure data continuity and reliability.

[0043] Step 2: Construction of digital twin model

[0044] Based on the physical heat absorption tower, the digital twin model of the heat absorption tower is constructed using **Finite Element Analysis (FEA)** software. The digital twin model has the same geometry, material properties and boundary conditions as the actual structure, mainly including the following:

[0045] Geometric model: Use BIM or CAD modeling tools to build a three-dimensional geometric model of the heat absorption tower, including the detailed structural features of the tower base, tower body and tower top.

[0046] Material property definitions:

[0047] Elastic modulus E of steel structure s , Poisson's ratio ν s , yield strength σ t .

[0048] The elastic modulus of concrete is E c , Poisson's ratio ν c and the nonlinear stress-strain relationship σ c =f(ε), where ε is the strain, σ c is the concrete stress.

[0049] Boundary conditions and external loads: Set fixed constraints on the tower foundation and apply actual external loads such as wind load, gravity and temperature gradient.

[0050] Temperature field simulation: The temperature changes inside and outside the heat absorption tower are simulated through the equation T=T0+ΔT(x,t), and the influence of temperature on the bearing capacity of the structure is analyzed.

[0051] Step 3: Analysis of AI Models

[0052] Based on the sensor data, an AI-based structural health monitoring model is established. The AI ​​model uses convolutional neural networks (CNN) and long short-term memory networks (LSTM) to extract and analyze the features of time series data such as stress, strain, vibration and temperature collected by sensors to achieve structural health status assessment and load-bearing capacity prediction.

[0053] The main functions of the AI ​​model include:

[0054] Anomaly Detection: Automatically identify stress concentration, crack propagation, and vibration anomalies by learning the structural response patterns under normal operating conditions.

[0055] Fatigue life prediction: Based on the cumulative damage theory, the fatigue life of the structure is calculated by the following formula:

[0056]

[0057] Where D is the cumulative fatigue damage, N t is the number of stress cycles in the i-th cycle, N f is the fatigue life under this stress, and when D=1, it means that the structure has reached the fatigue limit.

[0058] Real-time analysis and prediction: Based on real-time sensor data and historical data, the AI ​​model can dynamically predict the future health status of the structure and generate predictions of load-bearing capacity change trends and potential fault locations.

[0059] Step 4: Simulation and prediction based on digital twin and AI

[0060] In this invention, the digital twin model is combined with AI analysis to simulate and predict the dynamic response and load-bearing capacity of the heat absorption tower. The material parameters and boundary conditions in the digital twin model are automatically updated through real-time data collected by sensors to ensure that the virtual simulation is synchronized with the physical structure.

[0061] The simulation was performed using multi-physics coupling analysis, including nonlinear analysis of wind load, temperature field, and vibration response. The equations are as follows:

[0062] Mu(t)+Cu(t)+Ku(t)=F(t)

[0063] Where M is the mass matrix, C is the damping matrix, K is the stiffness matrix, F(t) is the external load, and u(t), u(t), and u(t) are the displacement, velocity, and acceleration responses, respectively.

[0064] Through simulation, the dynamic response of the tower under different future working conditions is predicted, the ultimate bearing capacity and fatigue life of the structure are evaluated, and the maintenance strategy is further optimized.

[0065] Step 5: Health status report and maintenance recommendations

[0066] After completing the simulation and AI analysis, the system generates a health status report for the heat sink. The report includes:

[0067] Health Score: A quantitative score is given to the health status of the heat sink based on a comprehensive analysis of stress, strain, vibration and temperature.

[0068] Stress distribution and crack prediction: Generate stress distribution diagrams of key parts of the heat absorption tower to predict the expansion trend and possible location of cracks.

[0069] Fatigue life and preventive maintenance recommendations: Provides fatigue life estimates based on prediction results and recommends a preventive maintenance schedule to avoid structural failure.

[0070] Example 1: Heat absorption tower power detection and load-bearing capacity evaluation based on multi-sensor network

[0071] Step 1: Sensor placement and data collection

[0072] The following sensors are arranged at key locations of the heat absorption tower:

[0073] Accelerometer: Arranged at the top and middle of the tower to monitor vibration response. Sensor model: ADXL345, sampling frequency set to 100Hz.

[0074] Strain gauge: Installed at the tower base and the tower body steel-concrete connection to detect structural strain changes. Model: HITECHT-110, sampling frequency is 50Hz.

[0075] Temperature sensor: installed outside and inside the tower to detect temperature gradient. Model: PT100, sampling frequency is 10Hz.

[0076] Displacement sensor: Arranged on the top of the tower, monitoring horizontal and vertical displacement. Model: Novotechnik LWH series, sampling frequency is 20Hz.

[0077] Step 2: Finite element model establishment

[0078] Use ANSYS software to build a three-dimensional finite element model of the heat absorption tower:

[0079] Geometric modeling: The tower height is 120 meters, the base diameter is 30 meters, the top diameter is 15 meters, the thickness of the steel structure is 15 mm, and the thickness of the concrete is 20 cm.

[0080] Material properties: Elastic modulus E of steel structure s =2.1×10 5 MPa, Poisson's ratio ν s =0.3; concrete elastic modulus E c =30GPa, Poisson's ratio ν c =0.2.

[0081] Meshing: Six-node tetrahedral elements are used, and the mesh density in the key area is 50 mm.

[0082] Boundary conditions: The tower base is fixed, the external wind load is 25 meters per second, and the temperature field is calculated by the formula Indicates the temperature difference between day and night.

[0083] Step 3: AI model training and prediction

[0084] Training AI models, including CNN+LSTM structures. Data collection lasts for 1 month, and the sample size of the data set is 10,000 groups.

[0085] CNN is used for feature extraction to extract characteristic patterns in stress, vibration, and temperature data.

[0086] LSTM is used for time series prediction to predict structural fatigue life based on stress changes.

[0087] Prediction result: Cracks on the top of the tower may expand within the next 5,000 hours.

[0088] Step 4: Simulation and predictive analysis

[0089] The real-time data from the sensors is input into the finite element model to simulate and analyze the stress distribution of the tower under dynamic wind load and temperature changes:

[0090] The stress at the tower base is concentrated at 140MPa, and the local stress at the tower top reaches 90MPa.

[0091] Through simulation prediction, the tower body will suffer fatigue damage within the next 3,000 hours, and local reinforcement and maintenance are recommended.

[0092] Step 5: Health status report and maintenance recommendations

[0093] Generate a report with a health score of 0.8 and recommend that the tower top be reinforced within the next 1500 hours and monitored every 1000 hours.

[0094] Example 2: Evaluation of the carrying capacity of a heat absorption tower based on real-time dynamic data and cloud analysis

[0095] Step 1: Sensor placement and data collection

[0096] The sensor settings are the same as those in Example 1. The sensor data is transmitted to the cloud in real time via the NB-IoT network. The data sampling frequency is the same as that in Example 1.

[0097] Step 2: Digital twin model construction

[0098] The three-dimensional finite element model of the heat absorption tower was created online using SimScale software. The model parameters were the same as those in Example 1, and the material properties and boundary conditions were also consistent.

[0099] Step 3: AI model online training

[0100] The data is transmitted to the AI ​​model in real time through the cloud API. The model is trained online and the model parameters are updated based on the real-time data. Five days of data are used for training, and the data sample size is 5,000 groups.

[0101] CNN is used for vibration feature analysis to predict abnormal vibrations that may occur in the next 72 hours.

[0102] LSTM is used to predict stress changes and output the structural stress change trend for the next 500 hours.

[0103] Step 4: Simulation and Analysis

[0104] The digital twin model is updated in real time and combined with sensor data to simulate the stress changes caused by the temperature difference at the top of the tower:

[0105] The peak stress at the tower top is 85MPa, and the peak stress at the tower base is 135MPa.

[0106] The simulation predicts that no cracks will appear in the tower body within the next 4,000 hours, but the tower base will need to be monitored regularly.

[0107] Step 5: Health Status Report

[0108] Generate a report, health score: 0.85, recommend routine maintenance in the next 2000 hours, and pay special attention to the tower base area.

[0109] Example 3: Heat absorption tower health monitoring based on edge computing and local real-time analysis

[0110] Step 1: Sensor placement and data collection

[0111] The sensor type and location are the same as in Example 1. The data is pre-processed locally by the edge computing device, and the transmission frequency is adjusted to once every 30 seconds.

[0112] Step 2: Finite element model construction

[0113] Use Abaqus software to build a three-dimensional finite element model:

[0114] The geometric modeling and material properties are the same as those in Example 1.

[0115] The mesh density is adjusted to 80 mm to simplify the model and improve the simulation speed.

[0116] Step 3: Offline training of AI model

[0117] The AI ​​model is trained offline with 2,000 sets of data and a simple LSTM model structure.

[0118] LSTM is used for time series prediction of stress, temperature and vibration.

[0119] Model accuracy: 90%.

[0120] Step 4: Real-time simulation and prediction

[0121] By processing data through edge computing devices and updating the simulation every 30 minutes, the stress changes at the top of the tower are predicted for the next 500 hours. It is concluded that the stress at the top of the tower is below 95MPa and the maximum stress at the base of the tower is 120MPa.

[0122] Step 5: Maintenance Recommendations

[0123] Generate a report with a health score of 0.75. It is recommended that local reinforcement maintenance of the tower base be carried out within the next 1000 hours.

[0124] Comparative example: Traditional periodic detection method

[0125] Step 1: Periodic manual inspection

[0126] The heat absorption tower is manually inspected every six months, including routine stress measurement and crack inspection, without installing sensors for real-time monitoring.

[0127] Step 2: Finite Element Static Analysis

[0128] The heat sink tower is analyzed using a static finite element model, without considering real-time data, using standard wind and temperature loads, and setting material properties to fixed values.

[0129] Step 3: Result Report

[0130] The report generated based on the static model and manual test results cannot predict future fatigue life and can only provide a health report of the current status.

[0131] Comparative experiment

[0132] Experimental design

[0133] In the actual operating environment of the heat absorption tower, the solutions of Example 1, Example 2, Example 3 and the comparative example are used respectively to detect the stress, displacement and temperature response of the heat absorption tower under different working conditions, and compare their prediction accuracy for the structural health status and fatigue life.

[0134] Experimental data:

[0135]

[0136] According to the table, Example 1, Example 2 and Example 3 can update the model in real time through sensor data, accurately predict the stress distribution, displacement change and fatigue life of the heat absorption tower, and ensure a higher health score and more reliable maintenance recommendations; in contrast, the control example can only provide current status detection and lacks the ability to predict future fatigue life, which may lead to premature or late maintenance, affecting safety and economic benefits, showing the significant advantages of the evaluation method, especially in real-time monitoring, fault prediction and maintenance optimization.

[0137] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure, characterized in that: The following steps are involved: S1. Arrange a variety of sensors on the heat absorption tower structure, including acceleration sensors, strain gauges, temperature sensors and displacement sensors, to collect dynamic response data of the heat absorption tower under different working conditions; S2. Based on the data collected by the sensor, a digital twin model of the heat absorption tower is constructed, wherein the model includes a finite element three-dimensional model of the tower base, the tower body and the tower top, and the material properties, geometric shape and boundary conditions of the finite element model match those of the actual heat absorption tower; S3. Use artificial intelligence models to analyze the collected power data. The AI ​​model identifies the structural health status of the heat absorption tower by learning historical data and real-time data, and predicts its load-bearing capacity and potential damage locations; S4. Combine the digital twin model with the AI ​​analysis results to evaluate the load-bearing capacity of the heat absorption tower and predict the dynamic response and fatigue life of the structure under future working conditions through simulation; S5. Based on the load-bearing capacity evaluation results, a health status report of the heat absorption tower is generated, and preventive maintenance suggestions are made.

2. A method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1, characterized in that: The acceleration sensors are arranged at the middle and top of the tower body of the heat absorption tower, the strain gauges are arranged at the tower base, key nodes of the tower body and steel-concrete connection parts, the temperature sensors are arranged at the outside and inside positions of the tower base, tower body and tower top, and the displacement sensor is used to monitor the displacement changes of the tower top.

3. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1 is characterized in that: The material properties of the finite element 3D model are defined as: Elastic modulus E of steel structure s , Poisson's ratio ν s , yield strength σ t ; The elastic modulus of concrete is E c , Poisson's ratio ν c , and the nonlinear stress-strain relationship σ c =f(ε), where ε is the strain, σ c is the concrete stress; The temperature field is simulated by the equation T = T0 + ΔT(x, t), where T0 is the initial temperature and ΔT(x, t) is the temperature gradient that changes with time.

4. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1 is characterized in that: The AI ​​model includes a convolutional neural network and a long short-term memory network, which are used to process and analyze the collected time series data, and predict potential cracks, fatigue damage and load-bearing capacity reduction trends through a damage identification model.

5. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1, characterized in that: The simulation of the digital twin model includes dynamic analysis of wind load, temperature change, vibration multi-physics field coupling, using nonlinear dynamic equations: Mu(t)+Cu(t)+Ku(t)=F(t) Where M is the mass matrix, C is the damping matrix, K is the stiffness matrix, F(t) is the external load, and u(t), u(t), and u(t) are the displacement, velocity, and acceleration responses, respectively.

6. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1 is characterized in that: In the S4, the boundary conditions and material properties of the digital twin model are adjusted through the input of real-time data, so that the virtual model is synchronized with the working conditions of the physical heat absorption tower, and the dynamic response within a specific time period in the future is predicted.

7. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1 is characterized in that: In S5, a health status report is generated based on the load-bearing capacity calculation results, and the report includes a health score of the heat absorption tower, stress distribution and crack propagation prediction of key structural parts, and a recommended preventive maintenance schedule.

8. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1 is characterized in that: The sensor data is collected at a frequency of 10-100 Hz. The sensor network transmits the data to the data processing center via LoRa, NB-IoT or 4G / 5G wireless communications, and uses edge computing devices to preprocess and preliminarily analyze the data.

9. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1, characterized in that: The method described, wherein the prediction of fatigue life is based on the cumulative damage theory, uses the following fatigue life prediction formula: Where D is the cumulative fatigue damage, N t is the number of stress cycles in the i-th cycle, N f is the fatigue life under this stress. When D=1, the structure is considered to have reached the fatigue limit.

10. The method for evaluating the dynamic detection bearing capacity of a heat absorption tower hybrid structure according to claim 1, characterized in that: Based on the simulation and AI model analysis results of the digital twin technology, the system automatically generates structural optimization suggestions and optimizes the design and structural performance of the heat absorption tower by adjusting the mesh division and material selection of the finite element model.

Images