Intelligent loading acceptance system and method for fire resistance of building structure

Abstract

The invention discloses an intelligent loading acceptance system and method for fire resistance of a building structure, and the system comprises a fire resistance acceptance scheme generation module which is used for obtaining the fire resistance grade requirement of a building component, and formulating a fire resistance acceptance scheme of the building component; the high-temperature simulation and loading module is used for simulating the thermal stress and load action of the building in the fire disaster; the sensor monitoring module is used for monitoring building component reaction data of the building structure in the testing process in real time and storing the data in the fire simulation experiment database; the fire resistance evaluation module is used for evaluating the fire resistance of each building component in the key test area; and the fire resistance acceptance and display module is used for generating a fire resistance acceptance report of the building component. Through the technical method provided by the invention, the acceptance process is optimized, the structural safety of the high-rise building under the fire condition is enhanced, and a more scientific, efficient and reliable fire resistance evaluation scheme is provided for the building industry.

Description

Technical Field

[0001] This invention relates to the field of building information technology and digital acceptance, and in particular to an intelligent loading acceptance system and method for the fire resistance performance of building structures. Background Technology

[0002] Fire resistance performance of building structures refers to the ability of a building structure to withstand high temperatures and maintain its stability, strength, and function during a fire. Specifically, it includes the following aspects: fire resistance limit, structural stability, fire resistance capacity, and post-fire repairability. Intelligent loading acceptance of the fire resistance performance of super high-rise building structures refers to the intelligent simulation and testing of the fire resistance performance of super high-rise buildings to ensure their safety during a fire. Overall, intelligent loading acceptance, through automation and intelligence, makes the fire resistance performance testing of super high-rise building structures more accurate, real-time, and efficient. It can dynamically adjust loading conditions during fire simulation, comprehensively assess the building's fire resistance capacity, and ensure that the building can better protect personnel safety and structural stability in actual fires. Existing fire resistance performance testing methods cannot monitor various data points during the testing process, resulting in an inability to fully understand structural dynamics and affecting the factual processing and evaluation of data. Therefore, those skilled in the art have provided an intelligent loading acceptance system and method for the fire resistance performance of super high-rise building structures to address the problems mentioned in the background. Summary of the Invention

[0003] To address the problems existing in the prior art, this invention provides an intelligent loading and acceptance system and method for the fire resistance performance of building structures.

[0004] The first aspect of this invention provides an intelligent loading and acceptance system for the fire resistance performance of building structures, mainly comprising:

[0005] The fire resistance performance acceptance scheme generation module is used to identify key test areas by using structural drawings, material specifications and fire resistance standards for different types of building components in the building design, obtain the fire resistance rating requirements of building components in the key test areas, and formulate fire resistance performance acceptance schemes for building components.

[0006] The high-temperature simulation and loading module is used to simulate high-temperature environments and apply loading conditions to simulate the thermal stress and load effects on buildings during a fire.

[0007] The sensor monitoring module is used to monitor the component response data of the building structure in real time during the test by using sensors deployed in key test areas, and save the data to the fire simulation experiment database.

[0008] The fire resistance performance assessment module is used to construct a fire resistance performance assessment model for building components based on historical response data of building components, and to assess the fire resistance performance of each building component in key test areas.

[0009] The fire resistance performance acceptance and display module is used to generate a fire resistance performance acceptance report for building components based on the fire resistance performance assessment results, and to present the real-time acquired building structure response data and fire resistance performance assessment results in the form of charts or tables.

[0010] A second aspect of this invention provides an intelligent loading acceptance method for the fire resistance performance of building structures, mainly comprising:

[0011] By using structural drawings, material specifications, and fire resistance standards for different types of building components, key testing areas are identified, and the fire resistance rating requirements for building components within these key testing areas are obtained. A fire resistance performance acceptance plan for building components is then developed.

[0012] Simulate a high-temperature environment and apply loading conditions to simulate the thermal stress and load effects on a building during a fire;

[0013] Sensors deployed in key testing areas are used to monitor the structural components' response data in real time during the testing process and save it to the fire simulation experiment database.

[0014] Based on historical response data of building components, a fire resistance performance evaluation model for building components is constructed to evaluate the fire resistance performance of each building component in the key test area.

[0015] Based on the fire resistance performance assessment results of building components, a fire resistance performance acceptance report for the building components is generated, and the real-time acquired building structure response data and fire resistance performance assessment results are presented in the form of charts or tables.

[0016] Furthermore, by using structural drawings, material specifications, and fire resistance standards for different types of building components, key testing areas are identified, and the fire resistance rating requirements for building components within these key testing areas are obtained. A fire resistance performance acceptance plan for the building components is then developed, including:

[0017] By analyzing structural drawings, material specifications, and fire resistance standards for different types of building components, the fire resistance requirements for different areas of the building are determined. Key testing areas are identified, and the fire resistance rating requirements for building components within these areas are obtained. These components include both vertical and horizontal members. Based on the component type, the loading method is determined, including vertical, lateral, or impact loads. Temperature distribution data for different stages of a fire are determined based on the fire resistance rating requirements of the building components. Historical loading intensity data for building components is obtained from a fire simulation database. Combining this data with temperature distribution data at different fire stages, component type, loading method, building layout, and floor level, a long short-term memory network is used to train a model, constructing a loading intensity prediction model for building components to predict their loading intensity at different stages of a fire. Finally, based on the temperature distribution data, loading intensity data, and loading method of the building components at different fire stages, a fire resistance performance acceptance plan for the building components is developed.

[0018] Furthermore, the simulated high-temperature environment, and the application of loading conditions, simulates the thermal stress and load effects experienced by a building during a fire, including:

[0019] Based on the temperature distribution data and loading intensity data of different stages of fire in the fire resistance performance acceptance scheme of building components, a high-temperature furnace or heating device is used to simulate the fire temperature, and a hydraulic or electric loading system is used to simulate the loading method and loading intensity of the building structure under fire conditions. The temperature distribution data in the fire simulation environment is monitored in real time through thermal infrared sensors. If the temperature distribution data in the current fire simulation environment is inconsistent with the preset temperature distribution data in the fire resistance performance acceptance scheme of building components, the temperature is adjusted by using a high-temperature furnace or heating device until the temperature distribution data in the current fire simulation environment is consistent with the preset temperature distribution data.

[0020] Furthermore, the method of monitoring the structural component response data in real time during the test process using sensors deployed in key test areas and saving the data to a fire simulation experiment database includes:

[0021] Temperature sensors, displacement sensors, strain sensors, and smoke and gas sensors are deployed at key structural components of the building in the key testing area to acquire real-time response data of the building components. The response data includes temperature data, displacement data, strain data, and smoke and gas data. The key structural components include beams, columns, and slabs. The acquired response data is processed using Kalman filtering or low-pass filtering algorithms to remove environmental noise and measurement errors, and the data is interpolated to supplement missing data points. Through data normalization and standardization, the data range is adjusted to obtain standardized response data of the building components, and the standardized response data is transmitted to the fire simulation experiment database via wireless or wired network.

[0022] Furthermore, based on historical response data of building components, a fire resistance performance evaluation model for building components is constructed to evaluate the fire resistance performance of each building component within the key test area, including:

[0023] Historical response data of building components were obtained through a fire simulation experiment database, and fire resistance performance data were labeled. A random forest algorithm was used to train the model and construct a fire resistance performance evaluation model for building components. The fire resistance performance data included qualified and unqualified fire resistance performance. Based on the real-time obtained response data of building components, the fire resistance performance of each building component in the key test area was evaluated using the fire resistance performance evaluation model.

[0024] Furthermore, based on the fire resistance performance assessment results of the building components, a fire resistance performance acceptance report for the building components is generated, and the real-time acquired building structure reaction data and fire resistance performance assessment results are presented through a user interface, including:

[0025] Based on the fire resistance performance assessment results of each building component, a fire resistance performance acceptance report is generated. This report includes the testing process, response data, fire resistance limit, structural fire resistance performance assessment results, and optimized design for unqualified fire resistance components. Optimized design for unqualified fire resistance components includes replacing fire-resistant materials and strengthening the component structure. Visualization technology is used to present real-time structural response data and fire resistance performance assessment results in charts or tables via a web interface or dedicated control panel. If stress, deformation, displacement, or load-bearing capacity data exceeds the preset safety range, it is displayed in different colors in the charts or tables, triggering an alarm. This alarm is then sent to relevant management personnel via SMS, email, or app push notifications, allowing them to start or stop high-temperature simulations, adjust loading intensity, and calibrate sensors via the control panel.

[0026] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0027] This invention provides an intelligent loading acceptance system and method for assessing the fire resistance performance of building structures. This invention integrates structural design data, building component material properties, and fire resistance rating standards to accurately identify key testing areas and clearly define fire resistance acceptance indicators for components, thus improving the scientific rigor and relevance of testing scheme development. By simulating high-temperature environments and applying multiple loading conditions, it realistically reproduces the thermo-mechanical coupling effects on structural components under fire conditions, making component response data more closely reflect actual fire scenarios. By deploying temperature, strain, displacement, and smoke sensors at key structural locations and collecting and transmitting data in real time, it ensures the integrity, continuity, and timeliness of data during testing, while providing a high-quality data source for subsequent model training. The fire resistance performance evaluation model built based on historical response data possesses adaptive judgment capabilities, enabling rapid and accurate assessment of the fire resistance performance of components in key testing areas, improving the intelligence level of acceptance judgment. Through the automatic generation and visualization of fire resistance performance acceptance reports, it intuitively displays the response, fire resistance limit, and evaluation conclusions of each component under fire loading, and provides color-coded warnings and alarm pushes for data exceeding safety thresholds, supporting timely decision-making and design optimization by management personnel, thereby improving the safety and management level of fire resistance acceptance for high-rise buildings. This invention provides an intelligent loading acceptance system and method for the fire resistance performance of building structures. It not only improves the accuracy and real-time performance of fire resistance assessment, but also optimizes the acceptance process through intelligent data monitoring and processing, enhancing the structural safety of high-rise buildings under fire conditions. It provides the construction industry with a more scientific, efficient and reliable fire resistance performance assessment solution. Attached Figure Description

[0028] Figure 1 This is a flowchart of an intelligent loading and acceptance system for the fire resistance performance of a building structure according to the present invention;

[0029] Figure 2 This is a flowchart of an intelligent loading acceptance method for the fire resistance performance of a building structure according to the present invention;

[0030] Figure 3 This is a schematic diagram of an intelligent loading acceptance method for the fire resistance performance of a building structure according to the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] like Figure 1 This embodiment of an intelligent loading and acceptance system for the fire resistance performance of building structures may specifically include:

[0033] The fire resistance performance acceptance scheme generation module is used to identify key test areas by using structural drawings, material specifications, and fire resistance standards for different types of building components in the building design, obtain the fire resistance rating requirements of building components in the key test areas, and formulate fire resistance performance acceptance schemes for building components.

[0034] The high-temperature simulation and loading module is used to simulate high-temperature environments and apply loading conditions to simulate the thermal stress and load effects on buildings during a fire.

[0035] The sensor monitoring module is used to monitor the component response data of the building structure in real time during the test process through sensors deployed in key test areas, and save the data to the fire simulation experiment database.

[0036] The fire resistance performance assessment module is used to construct a fire resistance performance assessment model for building components based on historical response data of the building components, and to assess the fire resistance performance of each building component in the key test area.

[0037] The fire resistance performance acceptance and display module is used to generate a fire resistance performance acceptance report for building components based on the fire resistance performance assessment results, and to present the real-time acquired building structure response data and fire resistance performance assessment results in the form of charts or tables.

[0038] like Figures 2-3 This embodiment provides an intelligent loading acceptance method for the fire resistance performance of building structures, which may specifically include:

[0039] Step S101: Identify key test areas by using structural drawings, material specifications, and fire resistance standards for different types of building components in the architectural design, obtain the fire resistance rating requirements for building components within the key test areas, and formulate a fire resistance performance acceptance plan for building components.

[0040] By analyzing structural drawings, material specifications, and fire resistance standards for different types of building components, the fire resistance requirements for different areas of the building are determined. Key testing areas are identified, and the fire resistance rating requirements for building components within these areas are obtained. These components include both vertical and horizontal members. Based on the component type, the loading method is determined, including vertical, lateral, or impact loads. According to the fire resistance rating requirements of the building components, temperature distribution data for different stages of a fire are determined. Historical loading intensity data for building components is obtained from a fire simulation database. Combined with temperature distribution data from different fire stages, component type, loading method, building layout, and floor level, a long short-term memory network is used to train a model, constructing a loading intensity prediction model for building components to predict their loading intensity at different stages of a fire. Based on the temperature distribution data, loading intensity data, and loading method of the building components at different fire stages, a fire resistance performance acceptance plan for the building components is developed.

[0041] Exemplarily, based on the structural drawings and material property descriptions of a 50-story super high-rise building, the vertical members in the core tube area are determined. The fire resistance rating requirement for the vertical support columns is 3 hours, while for the horizontal members, the fire resistance rating requirement for the floor slabs of the outer frame is 2 hours. Based on the building layout and usage, the 30th floor is selected as the key test area because it is more concentratedly heated in a high-rise fire. Through consulting the fire resistance standard, it is determined that the maximum vertical load that the support columns in this area need to bear in a fire is 8000 kN, and the floor slabs need to bear a lateral load of 2000 kN / m 2 . When designing the loading scheme, a hydraulic loading system is used to simulate the external force of the fire on the building structure. For the support columns, a temperature load is applied according to the ISO834 standard heating curve, and at the same time, a vertical load is applied through a hydraulic jack. In the initial stage of the fire within 30 minutes, the temperature rises to 500 °C, and at this time, the hydraulic system applies 80% of the design load, which is 6400 kN, simulating that the structure can still bear most of the load in the initial stage of the fire. As the fire continues, about 1 hour later, the temperature reaches 800 °C, and a 50% design load of 4000 kN is applied to observe whether the column can still maintain stability at high temperature. For the floor slabs, a multi-point loading system is used to apply the lateral load, and a heat radiation heating device is combined to simulate the fire temperature distribution. Historical loading data of similar structures are obtained through the building fire experiment database. For example, in a certain experiment, a concrete support column under a load of 4000 kN showed a creep deformation of 0.5 mm / min at a high temperature of 800 °C, while the floor slab deflected more than L / 20 under a load of 2000 kN / m 2 . Combining the historical loading data, a long short-term memory network is used for model training to construct a prediction model for the loading strength of building components to predict the variation law of the loading strength with temperature and time. The model output shows that the critical bearing strength of the building support column is 4500 kN at 800 °C, while the critical bearing strength of the floor slab is 1800 kN / m 2 at 700 °C, which is lower than the original design value. Based on the above data, a fire resistance performance acceptance plan is finally formulated: under the simulated fire heating conditions, the support column needs to maintain a load of 4000 kN at 800 °C for ≥2 hours, and the floor slab needs to maintain a load of 1800 kN / m 2 for ≥1.5 hours, and at the same time, monitor whether the deformation rate exceeds the limit value, the column creep <1 mm / min, and the floor slab deflection <L / 25. If the measured data meets these standards, it is determined that the fire resistance performance of the component is qualified.

[0042] Step S102, simulate the high-temperature environment and apply the loading conditions to simulate the thermal stress and load effects on the building in a fire.

[0043] Based on the temperature distribution data and loading intensity data at different stages of a fire in the fire resistance performance acceptance scheme for building components, a high-temperature furnace or heating device is used to simulate fire temperature, and a hydraulic or electric loading system is used to simulate the loading method and loading intensity of the building structure under fire conditions. Temperature distribution data in the fire simulation environment is monitored in real time using thermal infrared sensors. If the current temperature distribution data in the fire simulation environment is inconsistent with the preset temperature distribution data in the fire resistance performance acceptance scheme for building components, the temperature is adjusted using the high-temperature furnace or heating device until the current temperature distribution data in the fire simulation environment matches the preset temperature distribution data.

[0044] For example, a fire resistance performance acceptance test was conducted on the reinforced concrete support column in the core tube area of ​​the eight-story building. Based on the temperature distribution data and loading intensity data at different stages of a fire in the fire resistance performance acceptance scheme for building components, the support column needed to withstand the combined action of a high temperature of 800℃ and an axial load of 6500kN for 2 hours under the RABT standard temperature rise curve conditions. At the start of the test, a gas-fired high-temperature furnace was used to heat the specimen according to the RABT curve, raising the temperature to 800℃ within 30 minutes and maintaining a constant temperature. Simultaneously, a constant axial load of 6500kN was applied to the specimen using a 1000-ton hydraulic servo actuator. During the test, 64 K-type thermocouples were used, with 4 temperature measuring points per meter along the column height, to monitor the temperature field distribution in real time. When the test was 45 minutes in, the monitoring data showed that the temperature on the south side of the column was only 740℃, which was 60℃ different from the preset 800℃. At this time, by adjusting the gas flow of the burner on the south side of the high-temperature furnace to increase the heating intensity of the area, after 15 minutes of adjustment, the temperature on the south side reached 798℃, which met the temperature control accuracy requirement of ±5℃ in the fire resistance performance acceptance scheme of building components.

[0045] Step S103: Using sensors deployed in key test areas, monitor the component response data of the building structure in real time during the test process and save it to the fire simulation experiment database.

[0046] Temperature, displacement, strain, and smoke / gas sensors are deployed at key structural components of the building in the key testing area to acquire real-time response data of the building components. This data includes temperature, displacement, strain, and smoke / gas parameters. Key structural components include beams, columns, and slabs. Kalman filtering or low-pass filtering algorithms are used to denoise the acquired response data, removing environmental noise and measurement errors. Interpolation is then performed to supplement missing data points. Data normalization and standardization are applied to adjust the data range, resulting in standardized response data for the building components. This standardized response data is then transmitted wirelessly or via wired network to a fire simulation experiment database.

[0047] For example, in a fire resistance performance test of a certain building, real-time monitoring was conducted on the reinforced concrete frame of the 36-story core tube area. During the test, 56 thermocouple temperature sensors were deployed at key locations: one every 2 meters on beams, four on each floor of columns, and one every 5 square meters on slabs. 38 laser displacement sensors were deployed at key points such as the mid-span of beams, the middle of columns, and the center of slabs. 42 fiber optic strain gauges were deployed at stress concentration points such as the bending moment zones at beam ends, column bases, and the negative bending moment zones of slabs. Additionally, 18 smoke and carbon dioxide concentration sensors were used. During the experiment, when the temperature reached 750℃, thermocouple B3 on the northwest corner frame column recorded a temperature reading of 802℃. Simultaneously, displacement sensor D5 measured a lateral displacement of 12.3 mm in the middle of the column, and strain gauge S7 showed that the concrete strain in the compression zone reached 3250 με. Displacement data exhibited fluctuations of ±0.5mm due to electromagnetic interference. Noise reduction was achieved using a preset 0.1-20Hz bandpass filter, stabilizing the effective displacement data within the 11.8-12.5mm range. For the three temperature data points missing due to network latency, cubic spline interpolation was used to supplement the data at 748℃, 756℃, and 761℃. Finally, all monitoring data underwent normalization within the [0,1] interval; for example, the highest temperature of 1200℃ was set to 1.0, and 802℃ was normalized to 0.67. This data was then transmitted in real-time to the fire simulation experiment database via a dedicated 5G network at a 100Hz sampling frequency.

[0048] Step S104: Based on the historical response data of building components, construct a fire resistance performance evaluation model for building components and evaluate the fire resistance performance of each building component in the key test area.

[0049] Historical response data of building components were obtained from a fire simulation experiment database, and fire resistance performance data was labeled. A random forest algorithm was used to train the model, constructing a fire resistance performance evaluation model for building components. The fire resistance performance data included both qualified and unqualified fire resistance performance. Based on real-time acquired building component response data, the fire resistance performance of each building component in the key test area was evaluated using the fire resistance performance evaluation model.

[0050] For example, in the fire resistance performance assessment of the building's core tube, the project team retrieved 300 sets of historical test data from a fire simulation experiment database. Each set of data included four characteristic parameters: temperature, displacement, stress, and smoke and gas data. For instance, one set of data indicating substandard fire resistance showed that when the southwest corner support column was subjected to 850℃ for 90 minutes, the temperature in the middle of the column reached 892℃, and the axial deformation reached 15.2mm, exceeding the allowable limit of 12mm. Simultaneously, the concrete protective layer peeled off. Another set of data indicating acceptable fire resistance recorded that the north beam, after being subjected to 780℃ for 120 minutes, had a maximum deflection of only 8.7mm, less than the limit L / 20 = 10.5mm. Based on this labeled data, a random forest algorithm containing 200 decision trees was used to train the model, constructing a fire resistance performance assessment model for building components. The input layer included real-time data from 8 temperature monitoring points, 6 displacement sensors, and 4 strain gauges. The output layer provided a binary classification result: acceptable fire resistance or unacceptable fire resistance. After training, the model achieved a cross-validation accuracy of 92%. In actual assessments, during a simulated fire test, when the southeast section of the 36-story core tube was monitored in real time with a beam temperature of 815℃, a mid-span displacement of 9.8mm, and a maximum tensile stress of 18.6MPa, the building component fire resistance performance assessment model output a qualified fire resistance assessment result within 0.3 seconds based on these input data. However, when the northwest corner column reached a temperature of 867℃ and a deformation of 13.5mm, the model determined it to be unqualified in terms of fire resistance and highlighted the risk of concrete spalling in that area.

[0051] Step S105: Based on the fire resistance performance assessment results of the building components, generate a fire resistance performance acceptance report for the building components, and present the real-time acquired building structure reaction data and fire resistance performance assessment results through the user interface.

[0052] Based on the fire resistance performance assessment results of each building component, a fire resistance performance acceptance report is generated. This report includes the testing process, response data, fire resistance limit, structural fire resistance performance assessment results, and optimized design for components failing fire resistance tests. Optimized design for components failing fire resistance tests includes replacing fire-resistant materials and strengthening the component structure. Visualization technology is used to present real-time structural response data and fire resistance performance assessment results in charts or tables via a web interface or dedicated control panel. If stress, deformation, displacement, or load-bearing capacity data exceeds preset safety limits, it is displayed in different colors in the charts or tables, triggering an alarm. This alarm is then sent to relevant management personnel via SMS, email, or app push notifications, allowing them to initiate or stop high-temperature simulations, adjust loading intensity, and calibrate sensors via the control panel.

[0053] For example, in the fire resistance performance assessment of the core tube of this super-building, a comprehensive evaluation was conducted on the 22-story core tube structure. The test report showed that among the four columns on the east side, column L3 maintained full load for 130 minutes under simulated 900℃ fire conditions, with a limit deformation of 9.8mm, less than the allowable value of 15mm, and was assessed as qualified. However, column L4 showed a deformation of 13.2mm after 75 minutes, exceeding the limit by 12mm, and the protective layer peeled off over 35% of the area, and was deemed unqualified. The report recommended two optimization measures for column L4: first, replacing the C60 concrete with C80 fire-resistant concrete with added polypropylene fibers; and second, adding a 15mm thick fireproof board to the outside of the column. Visualization technology was used to present the real-time acquired building structure response data and fire resistance performance assessment results in the form of charts or tables through a web interface or dedicated control panel. When the test data was displayed in real time using visualization technology, the system automatically changed the data bar from green to orange when beam WL5 in the west zone reached its maximum deflection of 11.3 mm after 98 minutes of testing, with a critical value of 12 mm. Conversely, when column L4 in the north zone exceeded the deformation limit, the data bar immediately turned red, triggering a three-level early warning mechanism including audible and visual alarms and SMS notifications. The monitoring platform pushed a real-time alarm via 4G network to the project manager, Engineer A, on their engineering management app, containing the specific exceedance values ​​of 13.2 mm / 12 mm and the component location 92F-NE-L4. Engineer A was required to reduce the hydraulic loading system from 6500 kN to the safe load of 4500 kN using the control panel. The complete acceptance report ultimately presented the distribution of fire resistance time for each component in the form of a three-dimensional heat map. The green area (over 120 minutes, 83%), the orange area (90-120 minutes, 12%), and the red area (less than 90 minutes, 5%) provided a clear basis for key modifications.

[0054] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the concept of this application. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. An intelligent loading and acceptance system for the fire resistance performance of building structures, characterized in that, The system includes: The fire resistance performance acceptance scheme generation module is used to identify key test areas by using structural drawings, material specifications and fire resistance standards for different types of building components in the building design, obtain the fire resistance rating requirements of building components in the key test areas, and formulate fire resistance performance acceptance schemes for building components. The high-temperature simulation and loading module is used to simulate high-temperature environments and apply loading conditions to simulate the thermal stress and load effects on buildings during a fire. The sensor monitoring module is used to monitor the component response data of the building structure in real time during the test by using sensors deployed in key test areas, and save the data to the fire simulation experiment database. The fire resistance performance assessment module is used to construct a fire resistance performance assessment model for building components based on historical response data of building components, and to assess the fire resistance performance of each building component in key test areas. The fire resistance performance acceptance and display module is used to generate a fire resistance performance acceptance report for building components based on the fire resistance performance assessment results, and to present the real-time acquired building structure response data and fire resistance performance assessment results in the form of charts or tables.

2. A smart loading acceptance method for the fire resistance performance of a building structure, applied to the smart loading acceptance system for the fire resistance performance of a building structure as described in claim 1, characterized in that, The method includes: By using structural drawings, material specifications, and fire resistance standards for different types of building components, key testing areas are identified, and the fire resistance rating requirements for building components within these key testing areas are obtained. A fire resistance performance acceptance plan for building components is then developed. Simulate a high-temperature environment and apply loading conditions to simulate the thermal stress and load effects on a building during a fire; Sensors deployed in key testing areas are used to monitor the structural components' response data in real time during the testing process and save it to the fire simulation experiment database. Based on historical response data of building components, a fire resistance performance evaluation model for building components is constructed to evaluate the fire resistance performance of each building component in the key test area. Based on the fire resistance performance assessment results of building components, a fire resistance performance acceptance report for the building components is generated, and the real-time acquired building structure response data and fire resistance performance assessment results are presented in the form of charts or tables.

3. The method according to claim 2, wherein, The process involves identifying key testing areas using structural drawings, material specifications, and fire resistance standards for different types of building components. It also involves obtaining the fire resistance rating requirements for building components within these key testing areas and developing a fire resistance performance acceptance plan for the building components, including: By analyzing structural drawings, material specifications, and fire resistance standards for different types of building components, the fire resistance requirements for different areas of the building are determined. Key testing areas are identified, and the fire resistance rating requirements for building components within these key testing areas are obtained. Building component types include vertical and horizontal components. Based on the type of building component, the loading method is determined, including vertical loads, lateral loads, or impact loads. Based on the fire resistance rating requirements of the building components, temperature distribution data for different stages of a fire are determined. Historical loading intensity data of building components is obtained from a fire simulation experiment database. Combining this data with temperature distribution data for different stages of a fire, the type of building component, the loading method, the building layout, and the floors in use, a long short-term memory network is used to train the model, constructing a building component loading intensity prediction model to predict the loading intensity data of building components at different stages of a fire. Based on the temperature distribution data, loading intensity data, and loading method of the building components at different stages of a fire, a fire resistance performance acceptance plan for the building components is formulated.

4. The method according to claim 2, wherein, The simulated high-temperature environment, with applied loading conditions, simulates the thermal stress and load effects experienced by a building during a fire, including: Based on the temperature distribution data and loading intensity data of different stages of fire in the fire resistance performance acceptance scheme of building components, a high-temperature furnace or heating device is used to simulate the fire temperature, and a hydraulic or electric loading system is used to simulate the loading method and loading intensity of the building structure under fire conditions. The temperature distribution data in the fire simulation environment is monitored in real time through thermal infrared sensors. If the temperature distribution data in the current fire simulation environment is inconsistent with the preset temperature distribution data in the fire resistance performance acceptance scheme of building components, the temperature is adjusted by using a high-temperature furnace or heating device until the temperature distribution data in the current fire simulation environment is consistent with the preset temperature distribution data.

5. The method according to claim 2, wherein, The method involves using sensors deployed in key testing areas to monitor the structural component response data in real time during the testing process and saving it to a fire simulation experiment database, including: Temperature sensors, displacement sensors, strain sensors, and smoke and gas sensors are deployed at key structural components of the building in the key testing area to acquire real-time response data of the building components. The response data includes temperature data, displacement data, strain data, and smoke and gas data. The key structural components include beams, columns, and slabs. The acquired response data is processed using Kalman filtering or low-pass filtering algorithms to remove environmental noise and measurement errors, and the data is interpolated to supplement missing data points. Through data normalization and standardization, the data range is adjusted to obtain standardized response data of the building components, and the standardized response data is transmitted to the fire simulation experiment database via wireless or wired network.

6. The method according to claim 2, wherein, Based on historical response data of building components, a fire resistance performance evaluation model for building components is constructed to evaluate the fire resistance performance of each building component in key test areas, including: Historical response data of building components were obtained through a fire simulation experiment database, and fire resistance performance data were labeled. A random forest algorithm was used to train the model and construct a fire resistance performance evaluation model for building components. The fire resistance performance data included qualified and unqualified fire resistance performance. Based on the real-time obtained response data of building components, the fire resistance performance of each building component in the key test area was evaluated using the fire resistance performance evaluation model.

7. The method according to claim 2, wherein, The process involves generating a fire resistance performance acceptance report for the building components based on their fire resistance performance assessment results, and presenting the real-time acquired structural response data and fire resistance performance assessment results through a user interface, including: Based on the fire resistance performance assessment results of each building component, a fire resistance performance acceptance report is generated. This report includes the testing process, response data, fire resistance limit, structural fire resistance performance assessment results, and optimized design for unqualified fire resistance components. Optimized design for unqualified fire resistance components includes replacing fire-resistant materials and strengthening the component structure. Visualization technology is used to present real-time structural response data and fire resistance performance assessment results in charts or tables via a web interface or dedicated control panel. If stress, deformation, displacement, or load-bearing capacity data exceeds the preset safety range, it is displayed in different colors in the charts or tables, triggering an alarm. This alarm is then sent to relevant management personnel via SMS, email, or app push notifications, allowing them to start or stop high-temperature simulations, adjust loading intensity, and calibrate sensors via the control panel.

Images