Method and system for optimizing durability of cement concrete for airport runway

Abstract

The invention relates to the technical field of constructional engineering, in particular to a cement concrete durability optimization method and system for an airport runway, and the method comprises the steps: building a data collection frame, and collecting the data of the airport runway; preprocessing the collected data, and performing preliminary analysis based on the processed data to obtain main factors influencing the durability of the cement concrete; based on the preliminary analysis result, using machine learning and deep learning technologies to construct a durability prediction model; a self-learning mechanism is introduced, a feedback loop is established, actual operation data is compared with a prediction result, and model parameters are dynamically adjusted; and based on a prediction result of the durability prediction model, combining a plurality of durability indexes, and adopting a multi-objective optimization algorithm to generate an optimal cement concrete formula and a construction process scheme so as to obtain a final durability optimization scheme. By means of the method, the defects of a traditional method in the aspects of data accuracy and model adaptability are effectively overcome, and the durability optimization level of the airport runway cement concrete is improved.

Description

Technical Field

[0001] The invention relates to the technical field of construction engineering, and in particular to a durability optimization method and system for cement concrete for airport runways. Background Art

[0002] With the rapid development of the aviation transportation industry, the durability and safety of airport runways have become crucial issues. Traditionally, airport runways generally use cement concrete as the main material. However, during use, runways are subject to complex environmental influences such as high-frequency heavy loads, severe climatic conditions (such as drastic temperature changes and freeze-thaw cycles), and chemical corrosion, which lead to durability problems such as cracking and peeling on the runways. In the existing technology, the formula design and construction process of cement concrete mainly rely on experience and standard methods, which cannot fully consider the complex conditions in actual use and it is difficult to effectively improve the long-term durability of the runway.

[0003] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0004] The present invention provides a method and system for optimizing the durability of cement concrete for airport runways, thereby effectively solving the problems pointed out in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: A method for optimizing the durability of cement concrete for airport runways, comprising: Establish a data collection framework to collect environmental condition data, structural stress data and material performance data of airport runways; Preprocess the collected data and conduct preliminary analysis based on the processed data to obtain the main factors affecting the durability of cement concrete; Based on the preliminary analysis results, a durability prediction model is constructed using machine learning and deep learning techniques, wherein the durability prediction model uses historical data and real-time data to predict the impact of the main factors on the durability of cement concrete; Introducing a self-learning mechanism to optimize the durability prediction model through real-time data, and establishing a feedback loop to compare actual operating data with the prediction results and dynamically adjust the model parameters; Based on the prediction results of the durability prediction model, combined with multiple durability indicators, a multi-objective optimization algorithm is used to generate an optimal cement concrete formula and construction process plan; According to the optimal hydraulic concrete formula and construction process plan, the final durability optimization plan is obtained.

[0006] Furthermore, the collected data is preprocessed, and a preliminary analysis is performed based on the processed data to obtain the main factors affecting the durability of cement concrete, including: Clean and standardize the collected data to obtain a preprocessed data set; Perform time series analysis on long-term monitoring data to identify the impact of seasonal and long-term trends on concrete performance; Analyze the correlation between environmental conditions, stress distribution and material properties to identify the key factors affecting concrete durability; The principal component analysis is used to reduce the dimension of multiple influencing factors identified in time series analysis and correlation analysis, and the most representative principal components are extracted; Cluster analysis was performed on the most representative principal components to obtain the variation patterns and main factors of concrete performance under different conditions.

[0007] Furthermore, based on the preliminary analysis results, a durability prediction model was constructed using machine learning and deep learning techniques, including: The main factors extracted from the preliminary analysis are divided into a training set, a validation set and a test set; Using random forest as a machine learning model and long short-term memory network as a deep learning model, and using the training set to simultaneously train the machine learning model and the deep learning model; Use the test set to verify the generalization ability of the machine learning model and deep learning model, and perform cross-validation and hyperparameter tuning; The optimized machine learning model and deep learning model are integrated to obtain the durability prediction model.

[0008] Furthermore, the machine learning model and the deep learning model are integrated through a stacking method.

[0009] Furthermore, a self-learning mechanism is introduced to optimize the durability prediction model through real-time data, including: inputting the preprocessed real-time data into the durability prediction model; Based on the input data and self-learning mechanism, the model automatically triggers the retraining process and updates the model's internal parameters and structure; Through multiple autonomous update optimizations, when the model reaches the preset indicators, iterative optimization stops.

[0010] Furthermore, a feedback loop is established to compare actual operating data with the predicted results, including: During runway operation, actual data is continuously collected and the prediction results of the model are generated to obtain real-time data and prediction results for subsequent error analysis; Comparing the predicted results with the actual data, calculating the errors and performing difference analysis, and generating evaluation results of the model prediction performance; According to the results of the difference analysis, feedback information is generated to automatically adjust the parameters and structure of the model to obtain an adjusted improved model.

[0011] Furthermore, based on the prediction results of the durability prediction model, combined with multiple durability indicators, a multi-objective optimization algorithm is used to generate an optimal cement concrete formula and construction process plan, including: According to the importance of each durability indicator, an optimization target is set, and a corresponding weight is assigned to each durability indicator to establish a weight model; Based on the weight model and the multi-objective optimization algorithm, each scheme is calculated and evaluated to generate multiple optimization schemes that balance various durability indicators; The generated optimization schemes are weightedly scored to screen out the scheme with the highest comprehensive score, which is the cement concrete formula and construction process scheme.

[0012] Furthermore, the multi-objective optimization algorithm is NSGA-II.

[0013] A durability optimization system for cement concrete for airport runways, the system comprising: Runway data collection module collects environmental condition data, structural stress data and material performance data of airport runways; The preliminary data analysis module pre-processes the collected data and performs preliminary analysis based on the processed data to obtain the main factors affecting the durability of cement concrete; A prediction model building module, based on the preliminary analysis results, uses machine learning and deep learning technologies to build a durability prediction model, wherein the durability prediction model uses historical data and real-time data to predict the impact of the main factors on the durability of cement concrete; The self-learning and optimization module introduces a self-learning mechanism to optimize the durability prediction model through implementation data, and establishes a feedback loop to compare the actual operation data with the prediction results and dynamically adjust the model parameters; A multi-objective optimization module, based on the prediction results of the durability prediction model, combined with multiple durability indicators, uses a multi-objective optimization algorithm to generate an optimal cement concrete formula and construction process plan; The optimization scheme generation module obtains the final durability optimization scheme according to the optimal hydraulic concrete formula and construction process scheme.

[0014] Furthermore, the multi-objective optimization module includes: A weight allocation unit, which sets an optimization target according to the importance of each durability indicator, allocates a corresponding weight to each durability indicator, and establishes a weight model; A calculation and evaluation unit, which calculates and evaluates each scheme based on the weight model and the multi-objective optimization algorithm, and generates a plurality of optimization schemes that balance various durability indicators; The weighted average unit performs weighted scoring on the generated optimization schemes and selects the scheme with the highest comprehensive score, wherein the scheme with the highest comprehensive score is the cement concrete formula and construction process scheme.

[0015] The technical solution of the present invention can achieve the following technical effects: It effectively solves the shortcomings of traditional methods in data accuracy and model adaptability, and improves the durability optimization level of airport runway cement concrete. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a durability optimization method for cement concrete used for airport runways; Figure 2 To obtain a flow chart of the main factors affecting the durability of cement concrete; Figure 3 Schematic diagram of the process for building a durability prediction model using machine learning and deep learning techniques; Figure 4 Schematic diagram of the process for optimizing the durability prediction model through real-time data; Figure 5 Schematic diagram of the process of comparing actual operating data with predicted results to establish a feedback loop; Figure 6 Schematic diagram of the process for generating the optimal cement concrete formula and construction process plan. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0020] Embodiment 1 like Figure 1 As shown, the present invention provides a method for optimizing the durability of cement concrete for airport runways, the method comprising: S1: Establish a data collection framework to collect environmental condition data, structural stress data and material performance data of airport runways; Specifically, the data collection framework collects environmental conditions, structural stresses, and material properties of airport runways through the following steps: First, weather stations and surface temperature sensors are deployed near the runway to monitor environmental data such as temperature, humidity, rainfall, and wind speed in real time to ensure a comprehensive understanding of the climatic conditions of the runway; second, strain gauges, pressure sensors, and accelerometers are buried in key areas of the runway to measure in real time the stress distribution and vibration of the runway during aircraft takeoff, landing, and taxiing, so as to accurately evaluate the structural stress of the runway. For material performance data, samples are taken from different areas of the runway every quarter for laboratory tests such as compressive strength and freeze-thaw resistance, and non-destructive testing technology is used to regularly scan defects inside the runway. All data are transmitted to the data center via a wireless network. After cleaning and analysis, real-time monitoring and decision support are provided to optimize the durability of the runway.

[0021] S2: pre-process the collected data, and conduct preliminary analysis based on the processed data to obtain the main factors affecting the durability of cement concrete; Specifically, data preprocessing aims to remove noise, correct errors, and standardize data from different sources so that subsequent analysis can accurately reflect the actual situation. Preliminary analysis of the processed data can identify the important effects of environmental conditions, structural stresses, and material properties on the durability of cement concrete.

[0022] S3: Based on the preliminary analysis results, a durability prediction model is constructed using machine learning and deep learning techniques. The durability prediction model uses historical data and real-time data to predict the impact of major factors on the durability of cement concrete. Specifically, machine learning and deep learning techniques are used to model and predict the relationship between the main factors identified in the preliminary analysis and the durability of cement concrete. By comprehensively analyzing historical data and real-time data, the predictive model can accurately evaluate the impact of these key factors on the durability of cement concrete. The construction of this model not only helps to understand and quantify the role of influencing factors, but also provides forward-looking guidance for the maintenance and optimization of airport runways.

[0023] S4: Introduce a self-learning mechanism to optimize the durability prediction model through real-time data, establish a feedback loop, compare the actual operation data with the prediction results, and dynamically adjust the model parameters; Specifically, by introducing a self-learning mechanism, the durability prediction model has the ability to self-optimize, thereby improving the accuracy and adaptability of the prediction. Through the continuous input of real-time data, the model can dynamically adjust its own parameters and structure, and timely update the prediction of cement concrete durability; establish a feedback loop to compare the actual operating data with the model prediction results, identify and correct prediction errors, so that the model maintains efficient prediction performance when facing new environmental conditions and usage situations. This self-learning and feedback mechanism ensures the robustness and reliability of the model in long-term use. S5: Based on the prediction results of the durability prediction model, combined with multiple durability indicators, a multi-objective optimization algorithm is used to generate the optimal cement concrete formula and construction process plan; Specifically, this step aims to balance and optimize the relationship between different durability indicators (such as compressive strength, freeze-thaw resistance, wear resistance, etc.) to ensure the best performance of cement concrete under different conditions. Through the multi-objective optimization algorithm, the formula and process with the best performance among various durability indicators can be found among multiple possible options, thereby improving the overall durability and service life of the airport runway.

[0024] S6: Based on the optimal hydraulic concrete formula and construction process plan, the final durability optimization plan is obtained.

[0025] Specifically, first, based on the optimization results, suitable materials such as cement, aggregates, additives and admixtures are selected, and the proportion of each material is accurately calculated to ensure that the various durability indicators are optimally balanced. Then, in terms of construction technology, the mixing time and sequence are optimized to ensure the uniformity and full mixing of the concrete ingredients; at the same time, the best pouring and vibration scheme is formulated to avoid the generation of internal voids or stratification and enhance the overall strength of the concrete. In addition, a detailed maintenance plan is also key, including controlling the curing time, temperature and humidity to ensure that the concrete can be fully hardened in the early stages and reduce the formation of cracks. During the construction process, strict quality control and real-time monitoring are used to ensure that each link meets the requirements of the optimization plan, and the construction process is dynamically adjusted according to the field data to ensure the consistency of construction quality; finally, before actual application, a small-scale verification is carried out through the test section to evaluate the actual effect of the optimization plan, and necessary fine-tuning is carried out based on the feedback to finally determine the optimal construction plan. This optimization plan was eventually applied to the comprehensive construction of the airport runway to significantly improve the durability and service life of the runway.

[0026] As a preferred embodiment of the above, Figure 2 As shown, step S2 is to pre-process the collected data and perform preliminary analysis based on the processed data to obtain the main factors affecting the durability of cement concrete, including: S21: Clean and standardize the collected data to obtain a preprocessed data set; S22: Perform time series analysis on long-term monitoring data to identify the impact of seasonal and long-term trends on concrete performance; S23: Analyze the correlation between environmental conditions, stress distribution and material properties to identify the key factors affecting concrete durability; S24: Perform dimensionality reduction processing on multiple influencing factors identified in time series analysis and correlation analysis through principal component analysis, and extract the most representative principal components; S25: Cluster analysis was performed on the most representative principal components to obtain the variation patterns and main factors of concrete performance under different conditions.

[0027] Specifically, first, the collected data is cleaned and standardized. Data cleaning includes removing noise, correcting outliers and filling missing values ​​to ensure the accuracy and consistency of the data. Standardization converts data from different sources and dimensions into a unified scale for subsequent analysis. Next, a time series analysis is performed on the long-term monitoring data. By analyzing the changes in data over time, it is identified that the performance of concrete is affected by seasonal changes (such as periodic fluctuations in temperature and humidity) and long-term trends (such as material aging or deterioration of environmental conditions), so as to understand the potential impact of these factors on the durability of concrete. Then, a correlation analysis is performed to explore the relationship between environmental conditions, stress distribution and material properties. By calculating the correlation coefficient or using Regression analysis was used to identify the strong correlation between these factors and concrete durability, and to find out the key factors that have a significant impact on durability. Principal component analysis (PCA) was used to reduce the dimensionality of the multiple influencing factors identified in the previous step. By extracting the most representative principal components, the dimensions of the data were simplified, the most important information in the data was retained, the complexity of the analysis was reduced, and the core factors that have the greatest impact on durability were highlighted. Finally, cluster analysis was used to classify the extracted principal components and identify the change patterns of concrete performance under different conditions. By dividing the data into several groups, similar patterns of concrete performance under different environments and usage conditions were found, further clarifying how these main factors affect the durability of concrete.

[0028] As a preferred embodiment of the above, Figure 3 As shown in the figure, based on the preliminary analysis results, a durability prediction model is constructed using machine learning and deep learning techniques, including: A10: Divide the main factors extracted from the preliminary analysis into training set, validation set and test set; A20: Use random forest as the machine learning model and long short-term memory network as the deep learning model, and use the training set to train the machine learning model and the deep learning model simultaneously; A30: Use test sets to verify the generalization ability of machine learning models and deep learning models, and perform cross-validation and hyperparameter tuning; A40: Integrate the optimized machine learning model and deep learning model to obtain a durability prediction model.

[0029] Specifically, first, the main influencing factors extracted from the preliminary analysis are divided into training set, validation set and test set. The training set is used for model learning and fitting, the validation set is used for model adjustment and optimization, and the test set is used to evaluate the performance and generalization ability of the model. The division of the data set usually follows a certain ratio, such as 70% as a training set, 15% as a validation set, and 15% as a test set, to ensure that the model can perform well on different data sets; then, random forest is selected as the machine learning model, and long short-term memory network (LSTM) is selected as the deep learning model. The random forest model improves the accuracy and stability of the model by integrating multiple decision trees, and is suitable for processing complex multidimensional data. LSTM focuses on processing time series data and can capture long-term dependencies in the data. In this step, the training set is used to train the two models simultaneously. The models learn the patterns and relationships in the data by continuously adjusting internal parameters. Then, the trained machine learning model and deep learning model are verified using the test set to evaluate their generalization ability, that is, the performance of the model on unseen data. This step also includes cross-validation, which further ensures the stability of the model through multiple training and validation cycles. At the same time, hyperparameter tuning is performed to find the best parameter combination of the model to improve the prediction accuracy. Finally, the optimized machine learning model and deep learning model are integrated to obtain the final durability prediction model, combining the advantages of the two models to improve the overall prediction performance. This durability prediction model can use historical data and real-time data to accurately predict the impact of major factors on the durability of cement concrete, providing reliable decision support for runway maintenance and optimization.

[0030] As a preferred embodiment of the above embodiment, the machine learning model and the deep learning model are integrated through a stacking method.

[0031] Specifically, the stacking method was selected to integrate the two models of random forest and long short-term memory network (LSTM) in order to improve the accuracy and robustness of the durability prediction model. Random forest is good at processing high-dimensional and nonlinear data, while LSTM performs well in time series analysis and can capture the trend of concrete performance changes over time. Through the stacking method, the advantages of these two models are combined to form a more comprehensive prediction system. The secondary model learns and optimizes the prediction results of the primary model, thereby reducing their respective biases and overfitting risks, and enhancing the adaptability of the model in complex environments. Ultimately, this integrated model not only provides more accurate durability predictions, but also can dynamically adapt to changes in real-time data, providing more reliable support for airport runway maintenance and construction decisions.

[0032] As a preferred embodiment of the above, Figure 4 As shown in the figure, a self-learning mechanism is introduced to optimize the durability prediction model through real-time data, including: B10: Input the pre-processed real-time data into the durability prediction model; B20: The model automatically triggers the retraining process based on the input data and self-learning mechanism to update the model's internal parameters and structure; B30: Through multiple autonomous update optimizations, when the model reaches the preset indicators, iterative optimization stops.

[0033] Specifically, first, the preprocessed real-time data is input into the durability prediction model. These real-time data may include the latest environmental conditions, structural stresses, and material properties, etc. These data can reflect the actual status of the current runway. Preprocessing ensures the data quality and makes it suitable for direct input into the model for analysis and prediction; then, the model uses a self-learning mechanism to automatically trigger the retraining process. Based on the input real-time data, the model will dynamically adjust its internal parameters and structure to update its predictive ability for the durability of cement concrete. This self-learning mechanism enables the model to continuously adapt to new data changes and maintain the accuracy and reliability of its predictions; finally, through multiple autonomous updates and optimizations, the model automatically stops iterative optimization when it reaches the preset performance indicators. This process ensures that the model continues to optimize in performance, but does not cause overfitting or other problems due to over-training. The model optimized by the self-learning mechanism can provide more accurate and dynamic durability predictions and adapt to complex changes in actual applications.

[0034] As a preferred embodiment of the above, Figure 5 As shown, a feedback loop is established to compare actual operating data with predicted results, including: C10: During runway operation, actual data is continuously collected and the prediction results of the model are generated to obtain real-time data and prediction results for subsequent error analysis; C20: Compare the prediction results with the actual data, calculate the error and perform difference analysis to generate an evaluation result of the model prediction performance; C30: Based on the results of the difference analysis, feedback information is generated to automatically adjust the parameters and structure of the model to obtain an adjusted improved model.

[0035] Specifically, first, during the actual operation of the runway, actual data such as environmental conditions, stress distribution, and material properties are continuously collected, and the prediction results of the durability prediction model are generated at the same time, so that real-time data and corresponding prediction data for subsequent error analysis can be obtained; then, the prediction results of the model are compared with the actual data collected, the error between the two is calculated, and a detailed difference analysis is performed. By analyzing the size and trend of the error, the prediction performance of the model can be evaluated, and the conditions under which the model performs better or worse can be identified; finally, based on the results of the difference analysis, feedback information is generated. This feedback information is used to automatically adjust the parameters and structure of the model so that the model can better adapt to new data features. The adjusted model will be reapplied to the actual operating environment to continuously improve its prediction accuracy. Through this feedback loop, the model can be dynamically optimized to improve its prediction ability for the durability of cement concrete, ensuring that the model remains efficient and accurate over a long period of time.

[0036] As a preferred embodiment of the above, Figure 6 As shown, step S5, based on the prediction results of the durability prediction model, combined with multiple durability indicators, a multi-objective optimization algorithm is used to generate the optimal cement concrete formula and construction process plan, including: S51: according to the importance of each durability indicator, set the optimization target, assign a corresponding weight to each durability indicator, and establish a weight model; S52: Based on the weight model and multi-objective optimization algorithm, various schemes are calculated and evaluated to generate multiple optimization schemes that balance various durability indicators; S53: Perform weighted scoring on the generated optimization schemes to screen out the scheme with the highest comprehensive score. The scheme with the highest comprehensive score is the cement concrete formula and construction process scheme.

[0037] Specifically, first, according to the importance of each durability index, the optimization target is set. These durability indexes may include compressive strength, freeze-thaw resistance, wear resistance, crack resistance, etc. According to actual needs and project goals, a corresponding weight is assigned to each durability index. These weights reflect the priority of different indicators in the overall durability optimization, and then a weight model is established to provide a basis for multi-objective optimization; then, based on the weight model set in the previous step, a multi-objective optimization algorithm is used to calculate and evaluate various possible cement concrete formulas and construction process schemes. The multi-objective optimization algorithm can handle multiple conflicting objectives and generate multiple optimization schemes that achieve a balance between various durability indicators through iterative calculations. These schemes have different performances on different indicators, providing a variety of feasible options in practical applications; finally, in S53 In the process, each generated optimization scheme is weightedly scored. The weighted scoring is based on the weight model. The performance of each scheme on different durability indicators is calculated according to the weight to get a comprehensive score. The scheme with the highest comprehensive score is screened out as the optimal cement concrete formula and construction process scheme. This optimal scheme achieves the best balance between various durability indicators and can effectively improve the overall durability and service life of the runway.

[0038] As a preferred embodiment of the above embodiment, the multi-objective optimization algorithm is NSGA-II.

[0039] Specifically, NSGA-II, with its excellent performance and wide application, is particularly suitable for dealing with optimization problems involving multiple conflicting durability indicators. In the specific implementation, the NSGA-II algorithm is optimized through the following steps: First, NSGA-II generates an initial population, each individual represents a possible cement concrete formula and construction process scheme. The individuals in the population are randomly generated or based on experience, covering the diversity of durability indicators. For each individual in the population, NSGA-II performs non-dominated sorting and classifies different non-inferior solution sets (Pareto frontiers). These non-inferior solution sets represent solutions that cannot surpass each other in multiple durability indicators. At the same time, the crowding distance is calculated to evaluate the diversity of solutions and maintain a wide distribution of solution sets. NSGA-II selects high-quality individuals from the current population through selection operations, and performs crossover and mutation operations to generate new offspring. This process ensures the evolution of the population and gradually tends to the optimal balance in various durability indicators. The algorithm continuously optimizes the population in each generation through multiple iterations, and selects more and more superior solutions. After multiple rounds of iterations, NSGA-II will generate a set of balanced optimization solutions, which have achieved good performance in multiple durability indicators. According to the weighted scoring method in the aforementioned step S53, the NSGA-II algorithm selects high-quality individuals from the current population and generates new offspring through crossover and mutation operations. This process ensures the evolution of the population and gradually tends to the optimal balance in various durability indicators. The generated non-inferior solutions are concentrated and screened out with the highest comprehensive score as the final optimal cement concrete formula and construction process solution.

[0040] Embodiment 2 Based on the same inventive concept as the method for optimizing the durability of cement concrete for airport runways in the aforementioned embodiment, the present invention further provides a system for optimizing the durability of cement concrete for airport runways, the system comprising: Runway data collection module collects environmental condition data, structural stress data and material performance data of airport runways; The preliminary data analysis module pre-processes the collected data and performs preliminary analysis based on the processed data to obtain the main factors affecting the durability of cement concrete; The prediction model building module uses machine learning and deep learning technologies to build a durability prediction model based on the preliminary analysis results. The durability prediction model uses historical data and real-time data to predict the impact of major factors on the durability of cement concrete. The self-learning and optimization module introduces a self-learning mechanism to optimize the durability prediction model through implementation data, and establishes a feedback loop to compare the actual operation data with the prediction results and dynamically adjust the model parameters; The multi-objective optimization module generates the optimal cement concrete formula and construction process plan based on the prediction results of the durability prediction model, combined with multiple durability indicators, and using a multi-objective optimization algorithm; The optimization scheme generation module obtains the final durability optimization scheme based on the optimal hydraulic concrete formula and construction process scheme.

[0041] The above-mentioned optimization system in the present invention can effectively implement the durability optimization method of cement concrete for airport runways. The technical effects that can be achieved are as described in the above-mentioned embodiments and will not be repeated here.

[0042] As a preferred embodiment of the above, the multi-objective optimization module includes: The weight allocation unit sets the optimization target according to the importance of each durability index, allocates a corresponding weight to each durability index, and establishes a weight model; The calculation and evaluation unit calculates and evaluates each scheme based on the weight model and multi-objective optimization algorithm, and generates multiple optimization schemes that balance various durability indicators; The weighted average unit performs weighted scoring on the generated optimization schemes and selects the scheme with the highest comprehensive score. The scheme with the highest comprehensive score is the cement concrete formula and construction process scheme.

[0043] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0044] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined therein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for optimizing the durability of cement concrete for airport runways, characterized in that: include: Establish a data collection framework to collect environmental condition data, structural stress data and material performance data of airport runways; Preprocess the collected data and conduct preliminary analysis based on the processed data to obtain the main factors affecting the durability of cement concrete; Based on the preliminary analysis results, a durability prediction model is constructed using machine learning and deep learning techniques, wherein the durability prediction model uses historical data and real-time data to predict the impact of the main factors on the durability of cement concrete; Introducing a self-learning mechanism to optimize the durability prediction model through real-time data, and establishing a feedback loop to compare actual operating data with the prediction results and dynamically adjust the model parameters; Based on the prediction results of the durability prediction model, combined with multiple durability indicators, a multi-objective optimization algorithm is used to generate an optimal cement concrete formula and construction process plan; According to the optimal hydraulic concrete formula and construction process plan, the final durability optimization plan is obtained.

2. The durability optimization method for cement concrete for airport runways according to claim 1, characterized in that: The collected data is preprocessed and a preliminary analysis is performed based on the processed data to obtain the main factors affecting the durability of cement concrete, including: Clean and standardize the collected data to obtain a preprocessed data set; Perform time series analysis on long-term monitoring data to identify the impact of seasonal and long-term trends on concrete performance; Analyze the correlation between environmental conditions, stress distribution and material properties to identify the key factors affecting concrete durability; The principal component analysis is used to reduce the dimension of multiple influencing factors identified in time series analysis and correlation analysis, and the most representative principal components are extracted; Cluster analysis was performed on the most representative principal components to obtain the variation patterns and main factors of concrete performance under different conditions.

3. The durability optimization method for cement concrete for airport runways according to claim 1, characterized in that: Based on the preliminary analysis results, a durability prediction model was constructed using machine learning and deep learning techniques, including: The main factors extracted from the preliminary analysis are divided into a training set, a validation set and a test set; Using random forest as a machine learning model and long short-term memory network as a deep learning model, and using the training set to simultaneously train the machine learning model and the deep learning model; Use the test set to verify the generalization ability of the machine learning model and deep learning model, and perform cross-validation and hyperparameter tuning; The optimized machine learning model and deep learning model are integrated to obtain the durability prediction model.

4. The durability optimization method for cement concrete for airport runways according to claim 3, characterized in that: The machine learning model and the deep learning model are integrated by stacking method.

5. The durability optimization method for cement concrete for airport runways according to claim 1, characterized in that: A self-learning mechanism is introduced to optimize the durability prediction model through real-time data, including: inputting the preprocessed real-time data into the durability prediction model; Based on the input data and self-learning mechanism, the model automatically triggers the retraining process and updates the model's internal parameters and structure; Through multiple autonomous update optimizations, when the model reaches the preset indicators, iterative optimization stops.

6. The durability optimization method for cement concrete for airport runways according to claim 1, characterized in that: Establish a feedback loop to compare actual operating data with predicted results, including: During runway operation, actual data is continuously collected and the prediction results of the model are generated to obtain real-time data and prediction results for subsequent error analysis; Comparing the predicted results with the actual data, calculating the errors and performing difference analysis, and generating evaluation results of the model prediction performance; According to the results of the difference analysis, feedback information is generated to automatically adjust the parameters and structure of the model to obtain an adjusted improved model.

7. The method for optimizing the durability of cement concrete for airport runways according to claim 1, characterized in that: Based on the prediction results of the durability prediction model, combined with multiple durability indicators, a multi-objective optimization algorithm is used to generate the optimal cement concrete formula and construction process plan, including: According to the importance of each durability indicator, an optimization target is set, and a corresponding weight is assigned to each durability indicator to establish a weight model; Based on the weight model and the multi-objective optimization algorithm, each scheme is calculated and evaluated to generate multiple optimization schemes that balance various durability indicators; The generated optimization schemes are weightedly scored to screen out the scheme with the highest comprehensive score, which is the cement concrete formula and construction process scheme.

8. The method for optimizing the durability of cement concrete for airport runways according to claim 1, characterized in that: The multi-objective optimization algorithm is NSGA-II.

9. A durability optimization system for cement concrete for airport runways, characterized in that: The system comprises: Runway data collection module collects environmental condition data, structural stress data and material performance data of airport runways; The preliminary data analysis module pre-processes the collected data and performs preliminary analysis based on the processed data to obtain the main factors affecting the durability of cement concrete; A prediction model building module, based on the preliminary analysis results, uses machine learning and deep learning technologies to build a durability prediction model, wherein the durability prediction model uses historical data and real-time data to predict the impact of the main factors on the durability of cement concrete; The self-learning and optimization module introduces a self-learning mechanism to optimize the durability prediction model through implementation data, and establishes a feedback loop to compare the actual operation data with the prediction results and dynamically adjust the model parameters; A multi-objective optimization module, based on the prediction results of the durability prediction model, combined with multiple durability indicators, uses a multi-objective optimization algorithm to generate an optimal cement concrete formula and construction process plan; The optimization scheme generation module obtains the final durability optimization scheme according to the optimal hydraulic concrete formula and construction process scheme.

10. The durability optimization system for cement concrete for airport runways according to claim 9, characterized in that: The multi-objective optimization module comprises: A weight allocation unit, which sets an optimization target according to the importance of each durability indicator, allocates a corresponding weight to each durability indicator, and establishes a weight model; A calculation and evaluation unit, which calculates and evaluates each scheme based on the weight model and the multi-objective optimization algorithm, and generates a plurality of optimization schemes that balance various durability indicators; The weighted average unit performs weighted scoring on the generated optimization schemes and selects the scheme with the highest comprehensive score, wherein the scheme with the highest comprehensive score is the cement concrete formula and construction process scheme.

Images