Lightweight building material loss prediction method and system

Abstract

The invention provides a loss prediction method and system for a light building material. Wherein the long-term change trend of the environment where the light building material is located is analyzed and processed, and an analysis result is obtained; according to the analysis result, key environmental factors having significant influence on aging of the light building material are identified, and the potential loss risk level of the building material is obtained; based on the potential loss risk level, mining historical data laws extracted from maintenance records, user feedback and a historical case library by using a time sequence analysis technology, and generating a performance degradation estimation curve; and making a maintenance plan and a replacement time table of the light building material by comprehensively considering functional requirements, economic cost and safety standards of the building according to the performance degradation estimation curve. According to the technical scheme provided by the invention, the aging prediction precision and the maintenance efficiency of the light building material are remarkably improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of loss prediction, and in particular, to a method and system for predicting the loss of lightweight building materials. Background Art

[0002] Due to their advantages such as light weight and convenient construction, lightweight building materials are widely used in modern architecture, especially in high-rise buildings, bridges, and temporary structures. However, the aging problems of these materials under different environmental conditions seriously affect their service life and safety. Therefore, there is an urgent need for a method that can accurately predict the material aging process and formulate scientific maintenance strategies to ensure the safety and economic benefits of buildings.

[0003] Currently, for the aging prediction and maintenance strategies of lightweight building materials, it mainly relies on laboratory accelerated aging tests and limited historical data statistical analysis. These methods usually include conducting accelerated aging experiments on material samples under extreme conditions, and empirical evaluations based on the maintenance records of existing buildings and user feedback information. In addition, some studies have also tried to use simple mathematical models to estimate the aging rate of materials.

[0004] The existing solutions have the following main defects: Laboratory accelerated aging tests cannot fully simulate the complex conditions in the actual use environment, and historical data statistical analysis often lacks sufficient time span and diversity, resulting in inaccurate prediction results; The existing maintenance strategies are mostly static solutions and fail to be updated in real time according to the actual use situation and the latest performance data, making it difficult to adapt to the changing environmental conditions and use requirements; The existing methods do not fully identify the key environmental factors affecting material aging and cannot effectively distinguish which factors are the main aging driving factors, thus affecting the effectiveness and pertinence of maintenance measures. Summary of the Invention

[0005] The embodiments of the present application provide a method and system for predicting the loss of lightweight building materials to solve the problems of inaccurate aging prediction and ineffective maintenance measures caused by data limitations and lack of dynamic adjustment in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a method for predicting the loss of lightweight building materials, including: Collecting environmental parameters around the building and high-resolution images of the physical properties and surface states of the lightweight building materials in the building, and analyzing and processing the long-term change trend of the environment where the lightweight building materials are located in combination with a pre-established geographic information system and climate model to obtain an analysis result; According to the analysis results, perform accelerated aging simulation processing on the aging process of lightweight building materials under different environmental conditions, calculate the expected aging rate of lightweight building materials using the decision tree algorithm in machine learning, analyze the contribution degree of each environmental factor in the analysis results to the aging of lightweight building materials through aging sensitivity analysis technology, identify the key influencing factors among the environmental factors, and obtain the potential loss risk level; Based on the potential loss risk level, combined with the maintenance records, user feedback information of the building during its service life, and the historical case database of the same type of building materials, use the grey system theory to model and estimate the long-term performance degradation trend of lightweight building materials under actual use conditions, and use time series analysis technology to mine the historical data laws extracted from the maintenance records, user feedback information of the building during its service life, and the historical case database of the same type of building materials, and generate a performance degradation prediction curve; According to the performance degradation prediction curve, comprehensively consider the functional requirements, economic costs, and safety standards of the building, and formulate a maintenance plan and replacement schedule for lightweight building materials.

[0007] Optionally, the step of performing accelerated aging simulation processing on the aging process of lightweight building materials under different environmental conditions according to the analysis results, calculating the expected aging rate of lightweight building materials using the decision tree algorithm in machine learning, analyzing the contribution degree of each environmental factor in the analysis results to the aging of lightweight building materials through aging sensitivity analysis technology, identifying the key influencing factors among the environmental factors, and obtaining the potential loss risk level includes: Use the analysis results to perform accelerated aging simulation processing on the aging process of lightweight building materials under different environmental conditions, and generate aging process data; According to the aging process data, use the decision tree algorithm in machine learning to analyze the trend of changes in the properties of lightweight building materials obtained from the aging process data over time, and obtain the expected aging rate of lightweight building materials; Based on the expected aging rate of the lightweight building materials, use aging sensitivity analysis technology to quantitatively process the contribution degree of each environmental factor to the aging of the lightweight building materials, identify the key influencing factors, and generate an aging sensitivity report; Use the aging sensitivity report to comprehensively evaluate the aging conditions of lightweight building materials under each environmental condition in the analysis results, and obtain the potential loss risk level.

[0008] Optionally, the step of using aging sensitivity analysis technology to quantitatively process the contribution degree of each environmental factor to the aging of the lightweight building materials based on the expected aging rate of the lightweight building materials, identifying the key influencing factors, and generating an aging sensitivity report includes: Using the expected aging rate of the lightweight building materials, combining various performance change records collected from the lightweight building materials in actual use and the aging prediction data of the lightweight building materials under various hypothetical conditions, applying multiple regression analysis or machine learning models to quantitatively process the contribution degrees of various environmental factors to the aging of the lightweight building materials, and obtaining the quantitative results of the influence of environmental factors; According to the quantitative results of the influence of environmental factors, establish a multi-factor comprehensive evaluation model, consider the interaction between various environmental factors and their comprehensive effects on the aging of lightweight building materials, and obtain the output of the multi-factor comprehensive evaluation model; Based on the output of the multi-factor comprehensive evaluation model, through the aging sensitivity analysis technology, analyze the importance of each environmental factor, identify the key influencing factors that have a significant impact on the aging of lightweight building materials, and generate a list of key influencing factors; Using the list of key influencing factors, integrate all the analysis results, compile a detailed quantitative report on the influence of environmental factors and an analysis of key influencing factors, and form an aging sensitivity report.

[0009] Optionally, using the aging sensitivity report, comprehensively evaluate the aging conditions of the lightweight building materials under each environmental condition in the analysis results to obtain the potential loss risk level, including: Using the key influencing factors and quantitative results in the aging sensitivity report, construct an evaluation framework to comprehensively evaluate the aging possibility and degree of lightweight building materials under different environmental conditions, and generate an environmental condition aging evaluation framework; According to the environmental condition aging evaluation framework, create multiple possible usage scenarios, and through computer simulation or experimental verification methods, simulate the aging performance of lightweight building materials under these scenarios to obtain the scenario simulation analysis results; Based on the scenario simulation analysis results, apply a risk assessment model to quantitatively evaluate the aging degree of lightweight building materials under each environmental condition, determine the level of aging risk through the aging degree, and generate an aging risk assessment report; Using the aging risk assessment report, optimize and adjust the evaluation framework to obtain the potential loss risk level.

[0010] Optionally, based on the potential loss risk level, combining the maintenance records, user feedback information of the building during its service life and the historical case library of the same type of building materials, applying grey system theory modeling to estimate the long-term performance degradation trend of lightweight building materials under actual use conditions, and using time series analysis technology to mine the historical data laws extracted from the maintenance records, user feedback information of the building during its service life and the historical case library of the same type of building materials, and generate a performance decline prediction curve, including: Using the potential loss risk level, integrate and process the maintenance records, user feedback information, and historical case database of the same type of lightweight building materials during the service life of the building to obtain a multi-source information integration report; According to the multi-source information integration report, apply the grey system theory to model and process the long-term performance degradation trend of lightweight building materials under actual use conditions to obtain a grey system model; Based on the grey system model, estimate the performance degradation of lightweight building materials over a period of time in the future to obtain a preliminary performance degradation trend prediction result; Using the preliminary performance degradation trend prediction result, adopt time series analysis technology to mine the historical data law from the multi-source information integration report and generate a historical data law analysis report; Based on the comprehensive processing of the historical data law analysis report and the estimation result of the grey system model, draw a predicted curve reflecting the performance decline of lightweight building materials over time and generate a performance decline prediction curve.

[0011] Optionally, the step of using the preliminary performance degradation trend prediction result, adopting time series analysis technology to mine the historical data law from the multi-source information integration report and generate a historical data law analysis report includes: Using the preliminary performance degradation trend prediction result, organize the performance changes of lightweight building materials in different time periods into an ordered time series data set to obtain a time series data set; According to the time series data set, apply statistical methods or machine learning techniques to extract and preprocess the features of the time series in the time series data set, perform smoothing processing and remove outliers to obtain a preprocessed time series data set; Based on the preprocessed time series data set, adopt time series analysis technology to perform pattern recognition and law mining on the periodic, trend, and random fluctuation components in the historical data formed by the comprehensive performance change records accumulated during the actual use of lightweight building materials after preprocessing to obtain a pattern recognition result; Using the pattern recognition result, combined with the maintenance records, user feedback, and case database in the multi-source information integration report, analyze the correlation between different factors affecting the performance degradation of lightweight building materials to obtain a correlation analysis report; Based on the pattern recognition result and the correlation analysis report, perform comprehensive processing to generate a historical data law analysis report.

[0012] Optionally, according to the performance decline prediction curve, comprehensively consider the functional requirements, economic costs, and safety standards of the building to formulate a maintenance plan and replacement schedule for lightweight building materials, including: Using the performance degradation prediction curve, analyze the performance requirements of lightweight building materials at different usage stages of the building and the safety standards related to lightweight building materials, evaluate the building function requirements and safety standards, and obtain key performance indicators and safety thresholds; According to the performance degradation prediction curve, combined with the economic costs within the building life cycle, conduct cost-benefit analysis processing to obtain a cost-benefit analysis report; Based on the cost-benefit analysis report, formulate preliminary maintenance plans and replacement schedules for different types of lightweight building materials; Using the preliminary maintenance plan and replacement schedule, design a dynamic adjustment mechanism that allows real-time updating of maintenance strategies according to actual usage conditions and the latest performance data, and generate a dynamic adjustment mechanism plan; Based on the key performance indicators and safety thresholds, cost-benefit analysis report, preliminary maintenance plan and replacement schedule, and dynamic adjustment mechanism plan, formulate the final maintenance plan and replacement schedule for lightweight building materials.

[0013] In a second aspect, an embodiment of the present application provides a loss prediction system for lightweight building materials, including: An acquisition module, configured to acquire environmental parameters around the building and high-resolution images of the physical properties and surface states of lightweight building materials in the building, combine a pre-established geographic information system and climate model, and analyze and process the long-term change trend of the environment where the lightweight building materials are located to obtain an analysis result; An identification module, configured to perform accelerated aging simulation processing on the aging process of lightweight building materials under different environmental conditions according to the analysis result, calculate the expected aging rate of lightweight building materials by applying the decision tree algorithm in machine learning, analyze the contribution degree of each environmental factor in the analysis result to the aging of lightweight building materials through aging sensitivity analysis technology, identify the key influencing factors among the environmental factors, and obtain the potential loss risk level; An estimation module, configured to estimate the long-term performance degradation trend of lightweight building materials under actual usage conditions based on the potential loss risk level, combined with the maintenance records, user feedback information during the usage period of the building, and the historical case database of the same type of building materials, apply grey system theory modeling for estimation processing, and use time series analysis technology to mine the historical data laws extracted from the maintenance records, user feedback information during the usage period of the building, and the historical case database of the same type of building materials to generate a performance degradation prediction curve; A formulation module, configured to formulate a maintenance plan and replacement schedule for lightweight building materials in accordance with the performance degradation prediction curve, comprehensively considering the functional requirements, economic costs, and safety standards of the building.

[0014] In the embodiments of the present application, environmental parameters around a building are collected, as well as high-resolution images of the physical properties and surface conditions of lightweight building materials in the building. Combining with a pre-established geographic information system and climate model, the long-term change trend of the environment where the lightweight building materials are located is analyzed and processed to obtain an analysis result. According to the analysis result, the aging process of the lightweight building materials under different environmental conditions is subjected to accelerated aging simulation processing, and the decision tree algorithm in machine learning is used to calculate the expected aging rate of the materials. Through the aging sensitivity analysis technology, the contribution degree of the environmental factors extracted from the analysis result to the aging of the lightweight building materials is analyzed, the key environmental factors that have a significant impact on the aging of the lightweight building materials are identified, and the potential loss risk level of the building materials is obtained. Based on the potential loss risk level, combining with the maintenance records, user feedback information and historical case library of the same type of building materials during the service life of the building, the gray system theory is used to model and estimate the long-term performance degradation trend of the lightweight building materials under actual use conditions, and the time series analysis technology is used to mine the historical data rules extracted from the maintenance records, user feedback and historical case library to generate a performance decline prediction curve. According to the performance decline prediction curve, considering the functional requirements, economic costs and safety standards of the building, a maintenance plan and replacement schedule for the lightweight building materials are formulated.

[0015] The technical solution of the present application has the following beneficial effects: By collecting high-resolution images of the environmental parameters around the building and the physical properties and surface conditions of the materials, and combining with Geographic Information System (GIS) and climate models, the real environmental conditions where the building materials are located can be more comprehensively reflected, thus improving the accuracy of the aging process simulation; by applying accelerated aging simulation processing, the aging process of materials under various environmental conditions can be simulated in a short time, providing a more accurate expected aging rate; by quantitatively evaluating the environmental factors extracted from the analysis results, the key environmental factors that have a significant impact on material aging can be identified. This helps to concentrate resources and measures to address the most significant influencing factors and optimize the maintenance strategy; based on the aging rate calculated by the decision tree algorithm and the results of aging sensitivity analysis, the potential loss risk levels under different environmental conditions can be accurately evaluated, providing a scientific basis for subsequent performance degradation trend prediction and maintenance planning; by applying grey system theory modeling and combining the maintenance records, user feedback information during the building's service life and the historical case database of the same type of materials, the long-term performance degradation trend of lightweight building materials under actual use conditions can be estimated more accurately; by using time series analysis technology to mine the laws in historical data and generate a performance decline prediction curve, the long-term performance management can be made more scientific and reasonable; according to the performance decline prediction curve, considering the functional requirements, economic costs and safety standards of the building comprehensively, a personalized and dynamically adjusted maintenance plan and replacement schedule are formulated to ensure that the maintenance strategy not only meets the safety and reliability requirements of the building, but also takes into account economic benefits; by introducing a dynamic adjustment mechanism, the maintenance strategy is allowed to be updated in real time according to the actual use situation and the latest performance data, ensuring that the plan can adapt to the changing environmental conditions and use requirements; through scientific prediction and optimized maintenance strategy, potential problems can be discovered and addressed in advance, effectively extending the service life of lightweight building materials and reducing unnecessary replacement and maintenance costs; considering the safety standards of the building comprehensively, ensuring that the maintenance strategy not only focuses on technical feasibility, but also fully considers safety and economic benefits, providing a strong guarantee for the long-term stable operation of the building.

[0016] Furthermore, by using the analysis results for accelerated aging simulation and combining with the decision tree algorithm and aging sensitivity analysis technology in machine learning, this method can generate detailed aging process data, accurately calculate the expected aging rate of the materials, quantify the contribution degree of each environmental factor to the aging of lightweight building materials, identify the key influencing factors, and determine the potential loss risk level. This systematic processing flow not only significantly improves the accuracy of aging prediction, but also ensures that the maintenance strategy can be optimized and adjusted for the most critical influencing factors, overcoming the problems of inaccurate aging prediction and inadequate maintenance measures caused by data limitations and static maintenance strategies in the existing solutions, thus effectively extending the service life of building materials and enhancing the safety and economic benefits of the building.

[0017] Furthermore, by integrating maintenance records, user feedback information, and historical case databases of the same type of building materials during the building's life cycle based on the potential loss risk level, and applying grey system theory modeling and time series analysis techniques, this method can generate a detailed multi-source information integration report, construct an accurate grey system model, and estimate the long-term performance degradation trend of lightweight building materials under actual usage conditions. Further, by using time series analysis techniques to mine the laws of historical data and generate a performance decline prediction curve, this process not only overcomes the problem of inaccurate long-term performance evaluation caused by data fragmentation and static prediction models in existing solutions but also provides a scientific basis for dynamic adjustment. The resulting performance decline prediction curve can more accurately reflect the change of material performance over time, providing a solid foundation for formulating personalized and dynamically adjusted maintenance strategies, significantly enhancing the safety and economic benefits of buildings, and ensuring that maintenance measures are more scientific, reasonable, timely, and effective.

[0018] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a flowchart of a method for predicting the loss of a lightweight building material provided by an embodiment of the present application; Figure 2 It is a schematic structural diagram of a system for predicting the loss of a lightweight building material provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application.

[0022] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations can be executed not in the order in which they appear herein or in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations can be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0023] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0024] Figure 1 The flowchart of a method for predicting the loss of a lightweight building material provided by an embodiment of the present application is as Figure 1 shown, and the method includes: 101. Collect the environmental parameters around the building and high-resolution images of the physical properties and surface conditions of the lightweight building materials in the building, and combine the pre-established geographic information system and climate model to analyze and process the long-term change trend of the environment where the lightweight building materials are located to obtain an analysis result; In this step, collect the environmental parameters around the building (such as temperature, humidity, light intensity, etc.) and high-resolution images of the physical properties and surface conditions of the lightweight building materials in the building. These data are used to combine the pre-established geographic information system (GIS) and climate model to analyze the long-term change trend of the environment where the lightweight building materials are located, and finally form an analysis result. The analysis result is a data set recording various environmental conditions and their change patterns experienced by the material at different time periods.

[0025] In the embodiment of the present application, the environmental parameters are collected in real time by deploying a multi-point sensing network, and high-resolution images are obtained by using an unmanned aerial vehicle or a fixed camera. The data analysis and processing are carried out in combination with the GIS and climate model to generate a detailed analysis result. This step provides basic data support for subsequent aging prediction and ensures the accuracy and reliability of the prediction result.

[0026] 102. According to the analysis results, perform accelerated aging simulation processing on the aging process of lightweight building materials under different environmental conditions, calculate the expected aging rate of lightweight building materials using the decision tree algorithm in machine learning, analyze the contribution degree of each environmental factor in the analysis results to the aging of lightweight building materials through aging sensitivity analysis technology, identify the key influencing factors among the environmental factors, and obtain the potential loss risk level; In this step, according to the analysis results, perform accelerated aging simulation processing on the aging process of lightweight building materials under different environmental conditions. Calculate the expected aging rate of the material by applying the decision tree algorithm in machine learning, and analyze the contribution degree of the environmental factors extracted from the analysis results to the material aging through aging sensitivity analysis technology. Identify the key environmental factors that have a significant impact on the material aging, and finally obtain the potential loss risk level of the building materials.

[0027] In the embodiment of the present application, based on the environmental parameters in the analysis results, construct a virtual extreme environmental scenario to simulate the aging process of the material under these conditions. Use the decision tree algorithm to analyze the change trend of the material properties over time, predict the aging rate, and identify the key influencing factors through aging sensitivity analysis to evaluate the potential loss risk level. This step helps to accurately identify the main causes leading to material aging and guide the formulation of subsequent maintenance strategies.

[0028] 103. Based on the potential loss risk level, combine the maintenance records, user feedback information during the service life of the building, and the historical case library of the same type of building materials, apply grey system theory modeling to estimate the long-term performance degradation trend of lightweight building materials under actual use conditions, and use time series analysis technology to mine the historical data laws extracted from the maintenance records, user feedback information during the service life of the building, and the historical case library of the same type of building materials to generate a performance degradation prediction curve; In this step, based on the potential loss risk level, combine the maintenance records, user feedback information during the service life of the building, and the historical case library of the same type of building materials, apply grey system theory modeling to estimate the long-term performance degradation trend of lightweight building materials under actual use conditions, and use time series analysis technology to mine the historical data laws to generate a performance degradation prediction curve. The performance degradation prediction curve reflects the change trend of the material performance over time and provides a scientific basis for subsequent maintenance strategies.

[0029] In the embodiments of the present application, the maintenance records of the building, user feedback, and the historical case database of the same type of materials are integrated, and the grey system theory is applied to model to predict the long-term performance degradation trend of lightweight building materials under actual use conditions. Subsequently, time series analysis technology is used to mine the laws in historical data to generate a predicted curve of performance decline. This step ensures that the maintenance strategy can adapt to changing environmental conditions and usage requirements, improving the accuracy and practicality of the prediction.

[0030] 104. According to the predicted curve of performance decline, comprehensively considering the functional requirements, economic costs, and safety standards of the building, formulate a maintenance plan and replacement schedule for lightweight building materials.

[0031] In this step, according to the predicted curve of performance decline, comprehensively considering the functional requirements, economic costs, and safety standards of the building, formulate a personalized and dynamically adjustable maintenance plan and replacement schedule for lightweight building materials to obtain an optimized maintenance strategy. The maintenance strategy not only meets the safety and reliability requirements of the building but also takes into account economic benefits, ensuring that the plan is both scientific and reasonable and flexible to adapt to the actual situation.

[0032] In the embodiments of the present application, according to the predicted curve of performance decline, combined with the functional requirements, economic costs, and safety standards of the building, formulate a personalized maintenance plan and replacement schedule. At the same time, a dynamic adjustment mechanism is introduced to allow real-time updating of the maintenance strategy according to the actual usage situation and the latest performance data, ensuring that the plan can adapt to changing environmental conditions and usage requirements and improving the safety and economic benefits of the building.

[0033] In summary, steps 101 to 104 cover the complete process from environmental parameter collection to maintenance strategy formulation, aiming to provide a scientific and reasonable aging prediction and maintenance management plan for lightweight building materials to meet the safety and economic benefit requirements of the building. This series of steps significantly improves the safety and reliability and economic benefits of the building through systematic data collection, accurate aging simulation and sensitivity analysis, reliable performance decline prediction, and dynamically adjustable maintenance strategies, ensuring the effectiveness and timeliness of maintenance measures.

[0034] To solve the problem of inaccurate aging prediction in existing methods, in some embodiments, in step 102, according to the analysis results, an accelerated aging simulation process is performed on the aging process of lightweight building materials under different environmental conditions, and the decision tree algorithm in machine learning is applied to calculate the expected aging rate of the materials. Through the aging sensitivity analysis technology, the contribution degree of the environmental factors extracted from the analysis results to the aging of lightweight building materials is analyzed, the key environmental factors that have a significant impact on the aging of lightweight building materials are identified, and the potential loss risk level of the building materials is obtained, including: Using the analysis results, perform accelerated aging simulation processing on the aging process of lightweight building materials under different environmental conditions to generate aging process data; according to the aging process data, apply the decision tree algorithm in machine learning to analyze the trend of material properties changing with time, and obtain the expected aging rate of the material; based on the expected aging rate of the material, through aging sensitivity analysis technology, quantify the contribution degree of each environmental factor to material aging, identify key influencing factors, and generate an aging sensitivity report; use the aging sensitivity report to comprehensively evaluate the aging situation of materials under each environmental condition to ensure that the selected key influencing factors can accurately reflect the aging characteristics of the material under various conditions, and obtain the potential loss risk level.

[0035] In this embodiment, the analysis results include the surrounding environment parameters of the building (such as temperature, humidity, light intensity, etc.) and high-resolution images of the physical properties and surface conditions of lightweight building materials. These data are used for accelerated aging simulation to generate detailed aging process data; the aging process data is then used for the training of the machine learning model to predict the aging rate of the material; the aging sensitivity report summarizes the contribution degree of each environmental factor to material aging and identifies key influencing factors; finally, by comprehensively evaluating the aging situation of materials under each environmental condition, the potential loss risk level is determined.

[0036] In the embodiment of the present application, first, based on the multi-source data in the analysis results, construct a virtual extreme environment scenario, perform accelerated aging simulation to generate aging process data; second, use these aging process data to train the decision tree algorithm in machine learning, analyze the trend of material properties changing with time, and predict the expected aging rate of the material; third, through aging sensitivity analysis technology, quantify the contribution degree of each environmental factor to material aging, identify key influencing factors, and generate an aging sensitivity report; finally, use the aging sensitivity report to comprehensively evaluate the aging situation of materials under each environmental condition to ensure that the selected key influencing factors can accurately reflect the aging characteristics of the material under various conditions, so as to obtain the potential loss risk level.

[0037] To solve the problem of inaccurate aging prediction in the existing methods, in some embodiments, the step of quantifying the contribution degree of each environmental factor to material aging, identifying key influencing factors, and generating an aging sensitivity report based on the expected aging rate of the material through aging sensitivity analysis technology includes: Using the expected aging rate of the lightweight building materials, combining various performance change records collected from the lightweight building materials in actual use and the aging prediction data of the lightweight building materials under various hypothetical conditions, applying multiple regression analysis or machine learning models to quantitatively process the contribution degrees of various environmental factors to the aging of the lightweight building materials, and obtaining the quantitative results of the influence of environmental factors; according to the quantitative results of the influence of environmental factors, establishing a multi-factor comprehensive evaluation model, considering the interaction between different environmental factors and their comprehensive effects on material aging, and obtaining the output of the multi-factor comprehensive evaluation model; based on the output of the multi-factor comprehensive evaluation model, through aging sensitivity analysis technology, analyzing the importance of each environmental factor, identifying the key influencing factors that have a significant impact on material aging, and generating a list of key influencing factors; using the list of key influencing factors, integrating all analysis results, compiling a detailed quantitative report on the influence of environmental factors and an analysis of key influencing factors, and forming an aging sensitivity report.

[0038] In this embodiment, the expected aging rate of the material is data obtained based on accelerated aging simulation and decision tree algorithms, and is used to evaluate the aging trend of the lightweight building materials under different environmental conditions. The quantitative results of the influence of environmental factors are calculated through multiple regression analysis or machine learning models, and their input data are based on the expected aging rate of the lightweight building materials, combined with various performance change records of the lightweight building materials collected in actual use and the aging prediction data of the lightweight building materials under various hypothetical conditions, reflecting the specific influence degrees of various environmental factors (such as temperature, humidity, light intensity, etc.) on material aging. The multi-factor comprehensive evaluation model considers the interaction between different environmental factors and their comprehensive effects on material aging. The final generated quantitative report on the influence of environmental factors and the analysis of key influencing factors constitute the aging sensitivity report, providing a scientific basis to guide the formulation of maintenance strategies.

[0039] In the embodiments of the present application, first, this process first integrates three types of core input data: the expected aging rate of lightweight building materials (usually predicted based on accelerated aging simulation and decision tree algorithms, reflecting the theoretical aging trend of materials in different environments), various performance change records of lightweight building materials collected during actual use (this is the key empirical data in the actual service environment, recording the physical, chemical, or mechanical property degradation of materials under the action of environmental factors such as temperature, humidity, light, and pollutants during actual exposure, such as strength loss, color change, and cracking degree), and the aging prediction data of lightweight building materials under various hypothetical conditions (simulating the possible performance evolution of materials under different environmental combinations or extreme conditions through a simulation model). Based on this multi-dimensional data that combines theoretical prediction, actual observation, and simulation deduction, multivariate regression analysis or machine learning models (such as linear / nonlinear regression, random forest, gradient boosting tree, or neural network, etc.) are applied for modeling analysis; in this model, various environmental factors (such as temperature, humidity, ultraviolet irradiance, salt fog concentration, acid rain pH value, etc.) are used as independent variables (features), and the aging degree or rate of the material is used as the dependent variable (target). The core objective of model training is to quantitatively process the contribution of each environmental factor to the aging of lightweight building materials, that is, to analyze the relative influence magnitude of each factor alone and in interaction with other factors on the aging result (measured by indicators such as regression coefficients, feature importance scores, SHAP values, etc.). Finally, through the analysis and calculation of the model, the quantification result of the environmental factor influence is obtained, and this result clearly shows the specific action intensity of different environmental factors in driving the aging process of lightweight building materials in a numerical form (such as weights, percentages, rankings, etc.), laying an accurate data foundation for subsequent identification of key influencing factors and formulation of targeted protection strategies.

[0040] Secondly, based on these quantification results, a multi-factor comprehensive evaluation model is established, considering the interaction between different environmental factors and their comprehensive effect on material aging, to obtain the output of the multi-factor comprehensive evaluation model; thirdly, based on the output of the multi-factor comprehensive evaluation model, through aging sensitivity analysis technology, the importance of each environmental factor is analyzed, and the key influencing factors that have a significant impact on material aging are identified to generate a list of key influencing factors; finally, using the list of key influencing factors, all analysis results are integrated to compile a detailed quantification report on the influence of environmental factors and an analysis of key influencing factors, forming an aging sensitivity report.

[0041] Through the above steps, this embodiment not only improves the understanding of the aging process of lightweight building materials, but also can accurately identify the key environmental factors that have a significant impact on material aging, providing a scientific basis for subsequent maintenance strategies and ensuring the safety and economic benefits of the warehouse.

[0042] To address the issue of inaccurate aging prediction in existing methods, in some embodiments, the aging sensitivity report is utilized to comprehensively evaluate the aging conditions of materials under various environmental conditions, ensuring that the selected key influencing factors can accurately reflect the aging characteristics of materials under various conditions, and obtaining the potential loss risk level, including: Using the key influencing factors and quantification results in the aging sensitivity report, construct an evaluation framework to comprehensively evaluate the aging possibility and degree of materials under different environmental conditions, and generate an environmental condition aging evaluation framework; according to the environmental condition aging evaluation framework, create multiple possible usage scenarios, and through computer simulation or experimental verification methods, simulate the aging performance of materials in these scenarios to obtain scenario simulation analysis results; based on the scenario simulation analysis results, apply a risk assessment model to quantitatively evaluate the aging of materials under each environmental condition, determine the level of aging risk, and generate an aging risk assessment report; use the aging risk assessment report to optimize and adjust the evaluation framework to ensure its applicability to a wider range of environmental conditions, and obtain the potential loss risk level.

[0043] In this embodiment, the aging sensitivity report contains the identified key influencing factors and their quantification results, which are used to construct the evaluation framework. The evaluation framework aims to systematically evaluate the aging possibility and degree of materials under different environmental conditions and generate an environmental condition aging evaluation framework. The scenario simulation analysis results are obtained through computer simulation or experimental verification and reflect the aging performance of materials under different usage scenarios. The aging risk assessment report quantitatively evaluates the aging risk of materials under each environmental condition by applying a risk assessment model, and finally generates the potential loss risk level to ensure the effectiveness and scientific nature of the maintenance strategy.

[0044] In the embodiments of the present application, first, use the key influencing factors and quantification results in the aging sensitivity report to construct a comprehensive evaluation framework to systematically evaluate the aging possibility and degree of materials under different environmental conditions, and generate an environmental condition aging evaluation framework; second, according to this evaluation framework, create multiple possible usage scenarios, and through computer simulation or experimental verification methods, simulate the aging performance of materials in these scenarios to obtain scenario simulation analysis results; third, based on these scenario simulation analysis results, apply a risk assessment model to quantitatively evaluate the aging of materials under each environmental condition, determine the level of aging risk, and generate an aging risk assessment report; finally, use the aging risk assessment report to optimize and adjust the evaluation framework to ensure its applicability to a wider range of environmental conditions, thereby obtaining the potential loss risk level.

[0045] Through the above steps, this embodiment not only improves the understanding of the aging process of lightweight building materials, but also can accurately identify the aging risks of materials under different environmental conditions, providing a scientific basis for subsequent maintenance strategies and ensuring the long-term safe and reliable operation of rail transit projects.

[0046] This application considers that in the prior art, due to the lack of sufficient preprocessing and refined analysis of the analysis result data, the prediction of the material aging rate is not accurate enough, making it difficult to effectively guide the formulation of maintenance strategies. In addition, the transition between the aging rate prediction and the maintenance plan in the traditional method is relatively rigid, and the advantages of machine learning algorithms are not fully utilized for dynamic adjustment. Therefore, the embodiment of the present invention proposes this alternative solution. By introducing preprocessing steps such as data cleaning, feature engineering, and model initialization, the accuracy and representativeness of the input data are ensured; the decision tree algorithm is applied to calculate the expected aging rate of the material and generate a node selection score to guide the formulation of maintenance strategies, thereby achieving a smooth transition from the aging rate prediction to the maintenance plan and solving the problems of inaccurate prediction and inflexible maintenance strategies in the prior art.

[0047] Optionally, applying the decision tree algorithm in machine learning to analyze and process the trend of material properties changing over time according to the aging process data to obtain the expected aging rate of the material includes: Before calculating the expected aging rate of the material it is necessary to perform preprocessing such as data cleaning, feature engineering, and model initialization on the data in the analysis result to ensure the accuracy and representativeness of the input data and lay a foundation for the aging rate prediction; ; represents the expected aging rate of the lightweight building material; represents the initial material performance coefficient; represents the time decay factor; represents time; represents the temperature sensitivity coefficient; represents the environmental condition base value; represents the temperature influence weight; represents the actual temperature; represents the humidity response coefficient; represents the humidity change frequency factor; represents the actual humidity; represents the relative humidity; represents the humidity square term adjustment coefficient; represents the humidity-temperature interaction coefficient; represents the comprehensive adjustment factor; represents the time sensitivity factor; represents the average aging rate; After the calculation generate the decision tree node selection score through steps such as aging rate correction, feature importance evaluation, and node selection scoring to guide the formulation of maintenance strategies and ensure a smooth transition from aging rate prediction to maintenance planning; ; represents the decision tree node selection score; represents the node selection preference coefficient; represents the non - linear adjustment coefficient; represents the expected aging rate of lightweight building materials; represents the sensitivity coefficient of the change rate of lightweight building material properties; represents the average aging rate; represents the feature fluctuation coefficient; represents the leaf node convergence speed; represents the feature importance score; represents the decision tree depth adjustment factor; represents the data distribution smoothing coefficient; represents the dataset base value; represents the data feature weight; represents the data feature value; After the calculation obtain the expected aging rate of the material and a scientific and reasonable maintenance strategy through additional steps such as comprehensive evaluation, designing a dynamic adjustment mechanism, and compiling an optimized maintenance strategy document to ensure the safety and economic benefits of the building.

[0048] This formula aims to more accurately predict the aging rate of lightweight building materials and optimize maintenance strategies. Two key formulas are introduced in this scheme: the expected aging rate of the material and the decision tree node selection score . These two formulas aim to comprehensively consider various environmental factors (such as temperature, humidity) and their interactions, as well as the influence of time factors, provide a scientific and reasonable aging rate prediction model, and evaluate the effectiveness of different maintenance strategies through the decision tree algorithm to ensure the safety and economic benefits of the building.

[0049] The following briefly introduces the design reasons for each item of this formula: ; : This item is used to describe the exponential decay characteristic of material properties over time, where reflects the influence of the initial state of the material, Represents the time decay factor, specifically referring to the decay rate of time on the aging rate. By introducing the exponential function, it can accurately capture the gradual decline trend of material properties during long-term use, providing a basis for aging rate prediction.

[0050] : This sub-item considers the logarithmic effect of temperature on the material aging rate, where is the temperature sensitivity coefficient, is the basic value of environmental conditions, is the temperature influence weight, is the actual temperature. Through the logarithmic function, it can effectively simulate the non-linear effect of temperature change on material aging, especially the aging acceleration effect when the temperature approaches the critical value.

[0051] : This sub-item is used to describe the periodic effect of humidity on the material aging rate, where is the humidity response coefficient, is the humidity change frequency factor, is the actual humidity. Through the sine function, it can capture the periodic effect of humidity fluctuation (such as seasonal change) on material aging, reflecting the change characteristics of humidity in different time periods.

[0052] : This sub-item considers the effect of the interaction between humidity and temperature on the material aging rate, where is the relative humidity, is the humidity square term adjustment coefficient, is the humidity-temperature interaction coefficient. Through the square term, it enhances the effect of the combined action of humidity and temperature, especially suitable for environmental conditions where humidity and temperature have a significant mutual influence.

[0053] : This sub-item is used to adjust the overall aging rate, where is the comprehensive adjustment factor, is the time sensitivity factor, is the average aging rate. Through the exponential function, it can dynamically adjust the aging rate to ensure the adaptability and accuracy of the model on different time scales, especially for aging prediction dealing with long time spans.

[0054] The following briefly introduces the acquisition methods of each parameter in this formula: Initial material property coefficient Obtained from laboratory tests; Time decay factor Derived from historical data analysis; Time Recorded by the system; Temperature sensitivity coefficient Determined through experiments; Basic value of environmental conditions Set according to historical data; temperature influence weight Determined by statistical analysis; actual temperature Collected in real time by environmental monitoring equipment; humidity response coefficient Determined by experiment; humidity change frequency factor Statistically analyzed according to historical data; actual humidity Collected in real time by environmental monitoring equipment; relative humidity Directly measured by humidity sensor; humidity square term adjustment coefficient Optimized by experiment; humidity-temperature interaction coefficient Determined by multivariate regression analysis; comprehensive adjustment factor Adjusted by model training; time sensitivity factor Analyzed by historical data; average aging rate Calculated from long-term monitoring data The following briefly introduces the design reasons for each item of this formula:

[0055] : This item is used to evaluate the node selection preference, where is the node selection preference coefficient, is the non-linear adjustment coefficient, is the expected aging rate of the material. Through the sine function, the periodic change of the aging rate can be captured, especially when selecting key nodes in the decision tree algorithm, ensuring that the node selection has a certain periodicity and regularity.

[0056] : This item is used to measure the sensitivity of the change rate of material properties, where is the sensitivity coefficient of the change rate of material properties, is the expected aging rate of the material, is the average aging rate. Through the square root function, the degree of deviation of the material aging rate from the average value can be amplified, highlighting abnormal aging situations and improving the sensitivity of the model to abnormal data.

[0057] : This item is used to evaluate the influence of feature fluctuations on the score, where is the feature fluctuation coefficient, is the node selection preference coefficient, is the convergence speed of leaf nodes. Through the cosine function, the periodic change of feature fluctuations can be captured, especially in the process of decision tree node selection, ensuring that the model can adapt to the periodic change of features and improving the robustness of the model.

[0058] : This item is used to adjust the depth of the decision tree, where is the decision tree depth adjustment factor, is the leaf node convergence rate, is the feature importance score. Through the exponential function, it can dynamically adjust the depth of the decision tree to ensure the adaptability and accuracy of the model under different complexities, especially when dealing with high-dimensional data, preventing overfitting or underfitting.

[0059] : This item is used to smooth the data distribution, where is the data distribution smoothing coefficient, is the dataset base value, is the data feature weight, is the data feature value. Through the logarithmic function, it can effectively smooth the data distribution, especially when dealing with extreme values or sparse data, ensuring the stability and reliability of the model and improving the prediction accuracy.

[0060] The following briefly introduces the methods for obtaining the parameters of this formula: Node selection preference coefficient Optimized through experiments; Nonlinear adjustment coefficient Adjusted through model training; Expected aging rate of the material From the above formula: Calculated; Material property change rate sensitivity coefficient Determined through experiments; Average aging rate Calculated from long-term monitoring data; Feature fluctuation coefficient Optimized through experiments; Leaf node convergence rate Output by the decision tree model; Feature importance score Calculated through the feature selection algorithm; Decision tree depth adjustment factor Adjusted through model training; Data distribution smoothing coefficient Optimized through experiments; Dataset base value Set according to historical data; Data feature weight Determined through the feature selection algorithm; Data feature value Obtained from actual data; Suppose a construction project, the initial material performance coefficient , time decay factor , time is years, temperature sensitivity coefficient , environmental condition base value , temperature influence weight , actual temperature , humidity response coefficient , humidity change frequency factor , actual humidity , relative humidity , humidity square term adjustment coefficient , humidity-temperature interaction coefficient , comprehensive adjustment factor , time sensitivity factor , average aging rate ; Substitute into the formula for calculation to obtain .

[0061] Assume a certain construction project, node selection preference coefficient , non-linear adjustment coefficient , expected aging rate of materials , sensitivity coefficient of material property change rate , average aging rate , characteristic fluctuation coefficient , leaf node convergence speed , characteristic importance score , decision tree depth adjustment factor , data distribution smoothing coefficient , dataset base value , data feature weight , data feature value ; Substitute into the formula for calculation to obtain .

[0062] Through the above steps, this embodiment not only improves the prediction accuracy of the expected aging rate of materials, but also can identify the key factors affecting material aging, providing a scientific basis for subsequent maintenance strategies. In particular, by introducing the decision tree node selection score , a smooth transition from aging rate prediction to maintenance plan is achieved, ensuring that the maintenance strategy is both scientific and reasonable and flexibly adapts to the actual situation. Assume that the set threshold is . Since the result is greater than the set threshold, it indicates that the proposed maintenance strategy has high reliability and effectiveness, significantly improving the safety and economic benefits of the building.

[0063] To solve the problem of inaccurate prediction of the long-term performance degradation trend in existing methods, in some embodiments, in step 103, based on the potential loss risk level, combined with the maintenance records, user feedback information of the building during its service life, and the historical case database of the same type of building materials, the grey system theory is applied to model and estimate the long-term performance degradation trend of lightweight building materials under actual use conditions, and the time series analysis technology is used to mine the historical data rules extracted from the maintenance records, user feedback, and historical case database to generate a performance decline prediction curve, including: Using the potential loss risk level, integrate the maintenance records, user feedback information, and historical case database of the same type of materials during the building's service life to obtain a multi-source information integration report; according to the multi-source information integration report, apply grey system theory to model and process the long-term performance degradation trend of lightweight building materials under actual use conditions to obtain a grey system model; based on the grey system model, estimate the performance degradation of lightweight building materials over a period of time in the future to obtain a preliminary performance degradation trend prediction result; use the preliminary performance degradation trend prediction result and adopt time series analysis technology to mine the historical data rules from the multi-source information integration report to generate a historical data rule analysis report; based on the historical data rule analysis report and the estimation result of the grey system model, comprehensively process and draw a predicted curve reflecting the decline of material performance over time to generate a performance decline prediction curve.

[0064] In this embodiment, the potential loss risk level is the result obtained through the aging sensitivity analysis of environmental factors and is used to evaluate the aging risk of materials under different environmental conditions. The multi-source information integration report contains the data in the maintenance records, user feedback information, and historical case database of the same type of building materials during the building's service life, and these data are used to construct the grey system model. The grey system model is used to predict the long-term performance degradation trend of lightweight building materials under actual use conditions, while the time series analysis technology is used to mine the rules in the historical data, and finally a performance decline prediction curve is generated to provide a scientific basis for the maintenance strategy.

[0065] In the embodiment of the present application, first, use the potential loss risk level to integrate the maintenance records, user feedback information, and historical case database of the same type of materials during the building's service life to form a multi-source information integration report; second, according to the multi-source information integration report, apply grey system theory to model and process the long-term performance degradation trend of lightweight building materials under actual use conditions to obtain a grey system model; third, based on the grey system model, estimate the material performance degradation over a period of time in the future to obtain a preliminary performance degradation trend prediction result; fourth, use the preliminary performance degradation trend prediction result and adopt time series analysis technology to mine the historical data rules from the multi-source information integration report to generate a historical data rule analysis report; finally, based on the historical data rule analysis report and the estimation result of the grey system model, comprehensively process and draw a predicted curve reflecting the decline of material performance over time to generate a performance decline prediction curve.

[0066] Through the above steps, this embodiment not only improves the prediction accuracy of the long-term performance degradation trend of lightweight building materials, but also can identify the key factors affecting material performance, provides a solid foundation for formulating a scientific and reasonable maintenance strategy, and ensures the safety and economic benefits of the commercial complex.

[0067] In order to solve the problem of insufficient mining of historical data patterns in existing methods, in some embodiments, using the preliminary performance degradation trend prediction result, time series analysis technology is adopted to mine historical data patterns from the multi-source information integration report and generate a historical data pattern analysis report, including: Using the preliminary performance degradation trend prediction result, organize the performance changes of lightweight building materials in different time periods into an ordered time series data set to obtain a time series data set; according to the time series data set, apply statistical methods or machine learning techniques to extract features and preprocess the time series, remove outliers and perform smoothing processing to obtain a preprocessed time series data set; based on the preprocessed time series data set, adopt time series analysis technology to perform pattern recognition and rule mining on the periodic, trend, and random fluctuation components in historical data to obtain a pattern recognition result; use the pattern recognition result, combined with the maintenance records, user feedback, and case library in the multi-source information integration report, to analyze the correlation between different factors to obtain a correlation analysis report; based on the pattern recognition result and the correlation analysis report, perform comprehensive processing to generate a historical data pattern analysis report.

[0068] In this embodiment, the preliminary performance degradation trend prediction result is data obtained by estimating the material performance degradation situation in a future period through a grey system model. The time series data set contains the performance changes of lightweight building materials in different time periods, and these data are organized for subsequent time series analysis. The preprocessed time series data set improves the quality and reliability of the data by removing outliers and performing smoothing processing. The pattern recognition result is the periodic, trend, and random fluctuation components in historical data identified from the preprocessed data. The correlation analysis report analyzes the correlation between different factors by combining the maintenance records, user feedback, and case library in the multi-source information integration report, and finally generates a historical data pattern analysis report to provide a scientific basis for subsequent maintenance strategies.

[0069] In the embodiments of the present application, first, using the preliminary performance degradation trend prediction results, the performance changes of lightweight building materials in different time periods are sorted into an ordered time series data set to obtain the time series data set; second, according to the time series data set, applying statistical methods or machine learning techniques, feature extraction and preprocessing are performed on the time series, outliers are removed and smoothing processing is performed to obtain the preprocessed time series data set; third, based on the preprocessed time series data set, time series analysis techniques are used to perform pattern recognition and rule mining on the periodic, trend, and random fluctuation components in the historical data to obtain the pattern recognition results; then, using the pattern recognition results, combining the maintenance records, user feedback, and case library in the multi-source information integration report, the relevance between different factors is analyzed to obtain the relevance analysis report; finally, based on the pattern recognition results and the relevance analysis report, comprehensive processing is performed to generate a historical data law analysis report.

[0070] Through the above steps, this embodiment not only improves the understanding of the performance change law of lightweight building materials, but also can accurately identify the key factors affecting the material performance, providing a solid foundation for formulating scientific and reasonable maintenance strategies and ensuring the safety and economic benefits of airport terminals.

[0071] The present application considers that in the prior art, due to the lack of comprehensive integration and refined modeling of multi-source information, the long-term performance degradation trend prediction of lightweight building materials is not accurate enough, making it difficult to effectively guide the formulation of maintenance strategies. In addition, the transition between the degradation trend prediction and the rate correction in traditional methods is relatively rigid, and the advantages of the grey system theory are not fully utilized for dynamic adjustment. Therefore, the embodiments of the present invention propose this optional solution. By introducing pre-analysis steps such as data integration and preprocessing, environmental factor modeling, initial condition setting, and multi-factor comprehensive evaluation, the comprehensiveness and representativeness of the input data are ensured; the grey system theory is applied to model and calculate the long-term performance degradation trend , and a performance degradation rate correction value is generated , thus realizing a smooth transition between the degradation trend prediction and the rate correction, and solving the problems of inaccurate prediction and inflexible maintenance strategies in the prior art.

[0072] Optionally, according to the multi-source information integration report, applying the grey system theory to model and perform modeling processing on the long-term performance degradation trend of lightweight building materials under actual use conditions to obtain a grey system model, including: Before calculating the long-term performance degradation trend , pre-analysis such as data integration and preprocessing, environmental factor modeling, initial condition setting, and multi-factor comprehensive evaluation is required to ensure the comprehensiveness and representativeness of the input data and lay a foundation for accurately predicting the material degradation trend; ; Indicates the long-term performance degradation trend of lightweight building materials under actual use conditions; Indicates the initial performance level coefficient; Indicates the time growth factor; Indicates time; Indicates the time power adjustment factor; Indicates the usage frequency sensitivity coefficient; Indicates the environmental condition base value; Indicates the usage frequency influence weight; Indicates the usage frequency; Indicates the external stress; Indicates the stress influence weight; Indicates the relative stress; Indicates the stress power adjustment factor; Indicates the comprehensive adjustment factor; Indicates the non-linear adjustment coefficient; Indicates the modulus of lightweight building materials; After calculation Through transitional steps such as degradation trend correction, feature importance evaluation, and node selection scoring, a performance degradation rate correction value is generated to ensure a smooth transition from degradation trend prediction to rate correction and guide the formulation of subsequent maintenance strategies; ; Indicates the performance degradation rate correction value; Indicates the rate correction preference coefficient; Indicates the non-linear adjustment coefficient; Indicates the long-term performance degradation trend; Indicates the feature fluctuation coefficient; Indicates the average degradation trend; Indicates the data feature weight; Indicates the data feature value; Indicates the model depth adjustment factor; Indicates the non-linear adjustment coefficient; Indicates the wear rate of lightweight building materials; Indicates the comprehensive adjustment factor; Indicates the average degradation trend; After calculation Through additional steps such as model verification and optimization, design of a dynamic adjustment mechanism, and model integration and application, a complete grey system model is obtained, providing a scientific basis for the aging prediction of lightweight building materials.

[0073] After calculation After that, through additional steps such as model verification and optimization, designing a dynamic adjustment mechanism, and model integration and application, a complete grey system model is obtained to ensure the reliability and practicality of its prediction results, providing a scientific basis for the aging prediction of lightweight building materials.

[0074] This formula aims to more accurately predict the long-term performance degradation trend of lightweight building materials under actual use conditions and optimize the maintenance strategy. Two key formulas are introduced in this solution: the long-term performance degradation trend and the performance degradation rate correction value . These two formulas aim to comprehensively consider various environmental factors (such as time, usage frequency, external stress) and their interactions, providing a scientific and reasonable degradation trend prediction model, and evaluating the effectiveness of different maintenance strategies through the rate correction value to ensure the safety and economic benefits of the building.

[0075] The following briefly introduces the design reasons for each item of this formula:

[0076] ; : This item is used to describe the non-linear growth or decay trend of the initial performance level of lightweight building materials over time. By introducing a power function, it can capture the change characteristics of material performance during long-term use, especially the rapid change in the initial stage and the gradual stabilization in the later stage. This provides a basis for predicting the degradation trend of materials throughout their life cycle.

[0077] : This item considers the influence of usage frequency on the material degradation trend. The hyperbolic tangent function can effectively simulate the non-linear influence of usage frequency on material performance, especially the sharp change in material performance under high-frequency usage conditions. This helps to more accurately reflect the material degradation under actual use conditions.

[0078] : This item is used to evaluate the influence of external stress and its interaction with relative stress on the material degradation trend. Through power function adjustment, the expression of the combined effect of external stress and relative stress is enhanced, especially suitable for environmental conditions where stress significantly affects material performance. This ensures that the model can comprehensively consider the influence of stress factors.

[0079] : This item is used to capture the periodic influence brought about by the change in material modulus. The sine function can reflect the fluctuation characteristics of material physical properties (such as modulus) at different time periods, especially the aging acceleration effect when material properties show periodic changes. This helps to improve the sensitivity of the model to the periodic changes of materials.

[0080] The following briefly introduces the acquisition methods of each parameter of this formula: Initial performance level coefficient Obtained from laboratory tests; Time growth factor Derived from historical data analysis; Time Recorded by the system; Time power adjustment factor Determined by experimental optimization; Usage frequency sensitivity coefficient Measured through experiments; Basic environmental conditions Set according to historical data; Influence weight of usage frequency Determined by statistical analysis; Usage frequency Collected in real - time from usage records; External stress Measured by stress sensors; Stress influence weight Determined by experimental optimization; Relative stress Directly measured by stress sensors; Stress power adjustment factor Determined by experimental optimization; Comprehensive adjustment factor Adjusted through model training; Non - linear adjustment coefficient Determined by experimental optimization; Material modulus Obtained through material tests; The following briefly introduces the design reasons for each item in this formula: ; : This item is used to adjust the non - linear change of the degradation trend. The exponential function can dynamically adjust the degradation rate, especially the change rate when the degradation trend is close to the limit value. This enables the model to maintain a high prediction accuracy at different degradation stages and ensures a smooth transition from degradation trend prediction to rate correction.

[0081] : This item is used to measure the influence of feature fluctuations on the corrected degradation rate value. The logarithmic function can amplify the influence of feature fluctuations and highlight abnormal data points, especially when dealing with complex and variable data features, ensuring that the model has a high sensitivity to feature fluctuations and improving the prediction accuracy.

[0082] : This item is used to evaluate the periodic change of the material wear rate. The cosine function can capture the periodic fluctuations of the material wear rate, especially the aging influence when the wear rate shows periodic changes. This helps to improve the sensitivity of the model to the material wear situation and ensure the scientific nature and effectiveness of the maintenance strategy.

[0083] : This sub-item is used again to evaluate the periodic changes in the material wear rate. The cosine function can capture the periodic fluctuations in the material wear rate, especially the aging effect when the wear rate shows periodic changes. This helps improve the sensitivity of the model to the material wear situation and ensure the scientific nature and effectiveness of the maintenance strategy.

[0084] The following is a brief introduction to the methods for obtaining the parameters of this formula: Rate correction preference coefficient Optimized through experiments; Nonlinear adjustment coefficient Adjusted through model training; Long-term performance degradation trend Calculated; Feature fluctuation coefficient Optimized through experiments; Average degradation trend Calculated from long-term monitoring data; Data feature weight Determined through feature selection algorithm; Data feature value Obtained from actual data; Model depth adjustment factor Adjusted through model training; Nonlinear adjustment coefficient Optimized through experiments; Material wear rate Obtained through wear test; Comprehensive adjustment factor Adjusted through model training; Average degradation trend Calculated from long-term monitoring data; Assume a bridge project, initial performance level coefficient , Time growth factor , Time is years, Time power adjustment factor , Usage frequency sensitivity coefficient , Environmental condition base value , Usage frequency influence weight , Usage frequency times per day, External stress , Stress influence weight , Relative stress , Stress power adjustment factor , Comprehensive adjustment factor , Nonlinear adjustment coefficient , Material modulus ; Substitute into the formula to calculate and obtain .

[0085] Assume a bridge project, rate correction preference coefficient , Nonlinear adjustment coefficient , Long-term performance degradation trend , Feature fluctuation coefficient , Average degradation trend , Data feature weight , data eigenvalue , model depth adjustment factor , non - linear adjustment coefficient , material wear rate , comprehensive adjustment factor , average degradation trend ; Substitute into the formula and calculate to obtain .

[0086] Through the above steps, this embodiment not only improves the accuracy of predicting the long - term performance degradation trend of lightweight building materials, but also can identify the key factors affecting material degradation, providing a scientific basis for subsequent maintenance strategies. Especially by introducing the performance degradation rate correction value , a smooth transition from degradation trend prediction to rate correction is achieved, ensuring that the maintenance strategy is both scientific and reasonable and flexibly adaptable to the actual situation. Assume that the set threshold is , since the result is greater than the set threshold, it indicates that the proposed maintenance strategy has high reliability and effectiveness, significantly improving the safety and economic benefits of the building.

[0087] To solve the problem of insufficient personalization and dynamic adjustment of maintenance strategies in existing methods, in some embodiments, in step 104, according to the performance decline prediction curve, comprehensively considering the functional requirements, economic costs, and safety standards of the building, formulate a maintenance plan and replacement schedule for lightweight building materials, including: Use the performance decline prediction curve to analyze the material performance requirements and related safety standards of the building at different usage stages, evaluate the building's functional requirements and safety standards, and obtain key performance indicators and safety thresholds; According to the performance decline prediction curve, combined with the economic costs during the building's life cycle, conduct cost - benefit analysis processing to obtain a cost - benefit analysis report; Based on the cost - benefit analysis report, formulate preliminary maintenance plans and replacement schedules for different types of lightweight building materials; Use the preliminary maintenance plan and replacement schedule to design a dynamic adjustment mechanism that allows real - time updating of the maintenance strategy according to the actual usage situation and the latest performance data to generate a dynamic adjustment mechanism plan; Based on the key performance indicators and safety thresholds, cost - benefit analysis report, preliminary maintenance plan and replacement schedule, and dynamic adjustment mechanism plan, formulate the final maintenance plan and replacement schedule for lightweight building materials.

[0088] In this embodiment, the performance degradation prediction curve is data generated through time series analysis techniques, reflecting the change trend of the performance of lightweight building materials over time. Key performance indicators and safety thresholds are used to evaluate the material performance requirements of the building at different usage stages and related safety standards, ensuring that the maintenance strategy meets the functional requirements and safety requirements. The cost-benefit analysis report combines the economic costs within the building life cycle to evaluate the cost-benefit of different maintenance measures. The preliminary maintenance plan and replacement schedule are developed based on the cost-benefit analysis report, covering the specific maintenance arrangements for different types of lightweight building materials. The dynamic adjustment mechanism scheme allows for real-time updating of the maintenance strategy according to the actual usage situation and the latest performance data, ensuring its flexibility and adaptability. Finally, the optimized maintenance strategy document, that is, the final maintenance plan and replacement schedule for lightweight building materials, integrates all the above information and provides scientific and reasonable maintenance guidance.

[0089] In the embodiment of the present application, first, using the performance degradation prediction curve, analyze the material performance requirements of the building at different usage stages and related safety standards, evaluate the building functional requirements and safety standards, and obtain key performance indicators and safety thresholds; second, according to the performance degradation prediction curve, combine the economic costs within the building life cycle, perform cost-benefit analysis processing, and obtain a cost-benefit analysis report; third, based on the cost-benefit analysis report, for different types of lightweight building materials, develop a preliminary maintenance plan and replacement schedule; fourth, using the preliminary maintenance plan and replacement schedule, design a dynamic adjustment mechanism that allows for real-time updating of the maintenance strategy according to the actual usage situation and the latest performance data, generating a dynamic adjustment mechanism scheme; finally, based on the key performance indicators and safety thresholds, cost-benefit analysis report, preliminary maintenance plan and replacement schedule, and dynamic adjustment mechanism scheme, comprehensively process and compile a detailed optimized maintenance strategy document to obtain an optimized maintenance strategy, that is, the final maintenance plan and replacement schedule for lightweight building materials.

[0090] Through the above steps, this embodiment not only improves the personalization and dynamic adjustment ability of the maintenance strategy, but also ensures that the building maximizes economic benefits on the premise of meeting functional requirements and safety standards, providing a scientific and reasonable maintenance guidance plan.

[0091] Figure 2 The structural schematic diagram of a loss prediction system for lightweight building materials is provided for the embodiment of the present application, as Figure 2 shown, the device includes: The acquisition module 21 is used to collect the environmental parameters around the building, obtain high-resolution images of the physical properties and surface conditions of the lightweight building materials, analyze and process the long-term change trends of the microenvironment where the lightweight building materials are located in combination with the geographic information system and the climate model, and obtain the analysis results. The analysis results include the entire life cycle of the lightweight building materials; The identification module 22 is used to perform accelerated aging simulation processing on the aging process of the lightweight building materials under different environmental conditions according to the analysis results, calculate the expected aging rate of the materials by applying the decision tree algorithm in machine learning, analyze the contribution degree of each environmental factor to the material aging through the aging sensitivity analysis technology, identify the key influencing factors, and obtain the potential loss risk level; The estimation module 23 is used to estimate the long-term performance degradation trend of the lightweight building materials under actual use conditions based on the potential loss risk level, in combination with the maintenance records, user feedback information during the building usage period, and the historical case database of the same type of materials, apply the grey system theory to model, and use the time series analysis technology to mine the historical data law to generate a performance decline prediction curve; The formulation module 24 is used to formulate a personalized and dynamically adjustable maintenance plan and replacement schedule for the lightweight building materials according to the performance decline prediction curve, taking into account the functional requirements, economic costs, and safety standards of the building, and obtain an optimized maintenance strategy.

[0092] Figure 2 The described loss prediction system for lightweight building materials can execute Figure 1 The loss prediction method for a lightweight building material described in the embodiment shown, the implementation principle and technical effects will not be elaborated. For the loss prediction system for a lightweight building material in the above embodiment, the specific ways in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting the loss of a lightweight building material, characterized in that, Including: Collecting high-resolution images of the environmental parameters around the building, as well as the physical properties and surface conditions of the lightweight building materials in the building, analyzing and processing the long-term change trends of the environment where the lightweight building materials are located in combination with the pre-established geographic information system and climate model to obtain analysis results; According to the analysis results, performing accelerated aging simulation processing on the aging process of the lightweight building materials under different environmental conditions, calculating the expected aging rate of the lightweight building materials by applying the decision tree algorithm in machine learning, analyzing the contribution degree of each environmental factor in the analysis results to the aging of the lightweight building materials through aging sensitivity analysis technology, identifying the key influencing factors among the environmental factors to obtain the potential loss risk level; Based on the potential loss risk level, combining the maintenance records, user feedback information during the service life of the building and the historical case database of the same type of building materials, applying the grey system theory to model and estimate the long-term performance degradation trend of the lightweight building materials under actual use conditions, and using time series analysis technology to mine the historical data laws extracted from the maintenance records, user feedback information during the service life of the building and the historical case database of the same type of building materials to generate a performance decline prediction curve; According to the performance decline prediction curve, comprehensively considering the functional requirements, economic costs and safety standards of the building, formulating a maintenance plan and replacement schedule for the lightweight building materials.

2. The loss prediction method for the lightweight building material according to claim 1, wherein The step of, according to the analysis results, performing accelerated aging simulation processing on the aging process of the lightweight building materials under different environmental conditions, calculating the expected aging rate of the lightweight building materials by applying the decision tree algorithm in machine learning, analyzing the contribution degree of each environmental factor in the analysis results to the aging of the lightweight building materials through aging sensitivity analysis technology, identifying the key influencing factors among the environmental factors to obtain the potential loss risk level, includes: Using the analysis results to perform accelerated aging simulation processing on the aging process of the lightweight building materials under different environmental conditions to generate aging process data; According to the aging process data, applying the decision tree algorithm in machine learning to analyze and process the trend of the properties of the lightweight building materials obtained from the aging process data changing with time to obtain the expected aging rate of the lightweight building materials; Based on the expected aging rate of the lightweight building materials, through aging sensitivity analysis technology, quantitatively processing the contribution degree of each environmental factor to the aging of the lightweight building materials, identifying the key influencing factors, and generating an aging sensitivity report; Using the aging sensitivity report to comprehensively evaluate the aging conditions of the lightweight building materials under each environmental condition in the analysis results to obtain the potential loss risk level.

3. The loss prediction method of the lightweight building material according to claim 2, characterized in that, The step of, based on the expected aging rate of the lightweight building materials, through aging sensitivity analysis technology, quantitatively processing the contribution degree of each environmental factor to the aging of the lightweight building materials, identifying the key influencing factors, and generating an aging sensitivity report, includes: Using the expected aging rate of the lightweight building materials, combining various performance change records collected from the lightweight building materials in actual use and the aging prediction data of the lightweight building materials under various hypothetical conditions, applying multiple regression analysis or machine learning models to quantitatively process the contribution degree of each environmental factor to the aging of the lightweight building materials, and obtaining the quantitative result of the environmental factor influence; According to the quantitative result of the environmental factor influence, establish a multi-factor comprehensive evaluation model, consider the interaction between environmental factors and their comprehensive effect on the aging of lightweight building materials, and obtain the output of the multi-factor comprehensive evaluation model; Based on the output of the multi-factor comprehensive evaluation model, through the aging sensitivity analysis technology, analyze the importance of each environmental factor, identify the key influencing factors that have a significant impact on the aging of lightweight building materials, and generate a list of key influencing factors; Using the list of key influencing factors, integrate all analysis results, compile a detailed quantitative report on the environmental factor influence and an analysis of key influencing factors, and form an aging sensitivity report.

4. The loss prediction method for the lightweight building material according to claim 2, wherein Using the aging sensitivity report, comprehensively evaluate the aging situation of the lightweight building materials under each environmental condition in the analysis results, and obtain the potential loss risk level, including: Using the key influencing factors and quantitative results in the aging sensitivity report, construct an evaluation framework, comprehensively evaluate the aging possibility and degree of the lightweight building materials under different environmental conditions, and generate an environmental condition aging evaluation framework; According to the environmental condition aging evaluation framework, create multiple possible usage scenarios, and through computer simulation or experimental verification methods, simulate the aging performance of the lightweight building materials under these scenarios, and obtain the scenario simulation analysis results; Based on the scenario simulation analysis results, apply a risk assessment model to quantitatively evaluate the aging degree of the lightweight building materials under each environmental condition, determine the level of aging risk through the aging degree, and generate an aging risk assessment report; Using the aging risk assessment report, optimize and adjust the evaluation framework to obtain the potential loss risk level.

5. The loss prediction method of the lightweight building material according to claim 1, characterized in that, Based on the potential loss risk level, combining the maintenance records, user feedback information of the building during its service life and the historical case library of the same type of building materials, applying grey system theory modeling to estimate the long-term performance degradation trend of the lightweight building materials under actual use conditions, and using time series analysis technology to mine the historical data laws extracted from the maintenance records, user feedback information of the building during its service life and the historical case library of the same type of building materials, and generate a performance decline prediction curve, including: Using the potential loss risk level, integrate the maintenance records, user feedback information of the building during its service life and the historical case library of the same type of lightweight building materials to obtain a multi-source information integration report; According to the multi-source information integration report, apply grey system theory modeling to model the long-term performance degradation trend of the lightweight building materials under actual use conditions, and obtain a grey system model; Based on the grey system model, estimate the performance degradation of lightweight building materials over a period of time in the future to obtain a preliminary prediction result of the performance degradation trend; Using the preliminary prediction result of the performance degradation trend, adopt time series analysis technology to mine the historical data law from the multi-source information integration report and generate a historical data law analysis report; Based on the comprehensive processing of the historical data law analysis report and the estimation result of the grey system model, draw a predicted curve reflecting the performance degradation of lightweight building materials over time and generate a performance degradation predicted curve.

6. The loss prediction method for lightweight building materials according to claim 5, characterized in that, The step of using the preliminary prediction result of the performance degradation trend, adopting time series analysis technology to mine the historical data law from the multi-source information integration report and generate a historical data law analysis report includes: Using the preliminary prediction result of the performance degradation trend, organize the performance changes of lightweight building materials in different time periods into an ordered time series data set to obtain a time series data set; According to the time series data set, apply statistical methods or machine learning techniques to extract and preprocess the features of the time series in the time series data set, perform smoothing processing and remove outliers to obtain a preprocessed time series data set; Based on the preprocessed time series data set, adopt time series analysis technology to perform pattern recognition and law mining on the periodic, trend and random fluctuation components in the historical data formed after comprehensive performance change records of lightweight building materials accumulated during actual use, and obtain a pattern recognition result; Using the pattern recognition result, combine the maintenance records, user feedback and case library in the multi-source information integration report to analyze the correlation between different factors affecting the performance degradation of lightweight building materials and obtain a correlation analysis report; Based on the pattern recognition result and the correlation analysis report, perform comprehensive processing to generate a historical data law analysis report.

7. The loss prediction method for the lightweight building material according to claim 1, characterized in that, The step of formulating a maintenance plan and replacement schedule for lightweight building materials by comprehensively considering the functional requirements, economic costs and safety standards of the building according to the performance degradation predicted curve includes: Using the performance degradation predicted curve, analyze the performance requirements of lightweight building materials in different usage stages of the building and the safety standards related to lightweight building materials, and evaluate the building functional requirements and safety standards to obtain key performance indicators and safety thresholds; According to the performance degradation predicted curve, combine the economic costs during the building life cycle to perform cost-benefit analysis and obtain a cost-benefit analysis report; Based on the cost-benefit analysis report, formulate a preliminary maintenance plan and replacement schedule for different types of lightweight building materials; Using the preliminary maintenance plan and replacement schedule, design a dynamic adjustment mechanism that allows real-time updating of the maintenance strategy according to the actual usage situation and the latest performance data to generate a dynamic adjustment mechanism plan; Based on the key performance indicators and safety thresholds, cost-benefit analysis report, preliminary maintenance plan and replacement schedule, and dynamic adjustment mechanism plan, formulate the final maintenance plan and replacement schedule for lightweight building materials.

8. A loss prediction system for a lightweight building material, characterized in that, Including: A collection module, which is used to collect the environmental parameters around the building and high-resolution images of the physical properties and surface conditions of the lightweight building materials in the building, analyze and process the long-term change trend of the environment where the lightweight building materials are located by combining the pre-established geographic information system and climate model, and obtain the analysis result; An identification module, which is used to perform accelerated aging simulation processing on the aging process of the lightweight building materials under different environmental conditions according to the analysis result, calculate the expected aging rate of the lightweight building materials by applying the decision tree algorithm in machine learning, analyze the contribution degree of each environmental factor in the analysis result to the aging of the lightweight building materials through the aging sensitivity analysis technology, identify the key influencing factors in each of the environmental factors, and obtain the potential loss risk level; An estimation module, which is used to estimate the long-term performance degradation trend of the lightweight building materials under actual use conditions based on the potential loss risk level, combine the maintenance records, user feedback information of the building during its service life and the historical case database of the same type of building materials, apply the grey system theory to model and estimate, and use time series analysis technology to mine the historical data rules extracted from the maintenance records, user feedback information of the building during its service life and the historical case database of the same type of building materials, and generate a performance decline prediction curve; A formulation module, which is used to formulate the maintenance plan and replacement schedule of the lightweight building materials according to the performance decline prediction curve, comprehensively considering the functional requirements, economic costs and safety standards of the building.

Images