Real-time monitoring method and system for in-situ durability of concrete under multi-factor coupling

Abstract

The application discloses a method and system for real-time monitoring of in-situ durability of concrete under multi-factor coupling, and relates to the technical field of concrete, comprising: collecting an in-situ durability influence factor set of concrete, performing correlation data mining to obtain an in-situ durability engineering data set of concrete; building a multi-factor durability coupling analysis model, deploying N concrete distributed edge units on the target concrete, performing real-time monitoring and analysis of in-situ durability through the N concrete distributed edge units to obtain N in-situ durability coefficients of concrete; and performing global integrated analysis on the N in-situ durability coefficients of concrete to determine the analysis result of the in-situ durability of the target concrete. The application solves the technical problems in the prior art that multi-factors such as environment, material and construction process cannot be comprehensively coupled and analyzed, and it is difficult to accurately reflect the actual durability state of concrete in a timely manner, and achieves the technical effect of realizing real-time monitoring and accurate evaluation of the in-situ durability of concrete.

Description

Technical Field

[0001] This invention relates to the field of concrete technology, specifically to a method and system for real-time monitoring of in-situ durability of concrete under the coupled effects of multiple factors. Background Technology

[0002] The durability of concrete structures is influenced by a variety of factors, including environmental factors such as temperature and humidity changes and corrosive media, material factors such as mix proportions and admixture performance, and construction process factors such as pouring and spraying methods and vibration compaction. Traditional durability monitoring often relies on the collection and analysis of single factors or limited indicators, lacking a systematic understanding of the coupling and dynamic response mechanisms of multiple key influencing factors. This leads to discrepancies between monitoring results and the actual service condition of the structure, making it difficult to meet the requirements for high-precision, real-time durability evaluation. Summary of the Invention

[0003] This application provides a method and system for real-time monitoring of in-situ durability of concrete under the coupled effects of multiple factors. It is used to address the technical problem that existing technologies cannot perform comprehensive coupled analysis of multiple factors such as environment, materials and construction technology, making it difficult to reflect the actual durability state of concrete in a timely and accurate manner.

[0004] In view of the above problems, this application provides a method and system for real-time monitoring of in-situ durability of concrete under the coupled effects of multiple factors.

[0005] The first aspect of this application provides a method for real-time monitoring of in-situ durability of concrete under the coupled effects of multiple factors, the method comprising:

[0006] A set of factors influencing the in-situ durability of concrete is collected, including environmental factors, concrete material factors, and construction technology factors. Correlation data mining is performed on this set to obtain a concrete in-situ durability engineering dataset. Multi-factor coupling is then performed on the dataset according to the set of factors to build a multi-factor durability coupling analysis model. Based on this model, N distributed edge units are deployed on the target concrete, and real-time in-situ durability monitoring and analysis are conducted using these N units to obtain N concrete in-situ durability coefficients. A global integration analysis is then performed on these N coefficients to determine the in-situ durability analysis results for the target concrete.

[0007] A second aspect of this application provides a real-time monitoring system for in-situ durability of concrete under the coupled effects of multiple factors, the system comprising:

[0008] The system comprises the following modules: a factor acquisition module for collecting a set of factors influencing the in-situ durability of concrete, including environmental factors, concrete material factors, and construction technology factors; a data mining module for performing correlation mining on the set of factors to obtain an engineering dataset of in-situ concrete durability; a multi-factor coupling module for coupling the engineering dataset of in-situ concrete durability according to the set of factors to build a multi-factor durability coupling analysis model; a monitoring and analysis module for deploying N distributed edge units on the target concrete based on the multi-factor durability coupling analysis model, and performing real-time monitoring and analysis of in-situ durability through the N distributed edge units to obtain N in-situ durability coefficients; and a global integration analysis module for performing global integration analysis on the N in-situ durability coefficients to determine the analysis results of the in-situ durability of the target concrete.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application collects a set of factors influencing the in-situ durability of concrete, including environmental factors, concrete material factors, and construction technology factors. Based on this set of factors, correlation data mining is performed to obtain a concrete in-situ durability engineering dataset. The dataset is then coupled with multiple factors to build a multi-factor durability coupling analysis model. Based on this model, N distributed edge units are deployed on the target concrete, and real-time in-situ durability monitoring and analysis are performed using these N units to obtain N concrete in-situ durability coefficients. A global integration analysis is then performed on these N coefficients to determine the target concrete's in-situ durability analysis results. This invention addresses the technical problem in existing technologies where comprehensive coupling analysis of multiple factors such as environment, materials, and construction technology is impossible, making it difficult to reflect the actual durability state of concrete in a timely and accurate manner. Through multi-factor coupling modeling and distributed monitoring and analysis, it achieves the technical effect of real-time in-situ monitoring and accurate assessment of concrete durability. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1A schematic diagram of the real-time monitoring method for in-situ durability of concrete under multi-factor coupling effects provided in the embodiments of this application;

[0013] Figure 2 This is a schematic diagram of the in-situ durability real-time monitoring system for concrete under multi-factor coupling effects provided in the embodiments of this application.

[0014] Figure labeling: Influencing factor acquisition module 11, multi-factor coupling module 12, monitoring and analysis module 13, global integrated analysis module 14. Detailed Implementation

[0015] This application provides a method and system for real-time monitoring of in-situ durability of concrete under the coupling effect of multiple factors. It addresses the technical problem in existing technologies that cannot comprehensively couple and analyze multiple factors such as environment, materials and construction technology, making it difficult to reflect the actual durability state of concrete in a timely and accurate manner. Through multi-factor coupling modeling and distributed monitoring and analysis, it achieves the technical effect of real-time in-situ monitoring and accurate evaluation of concrete durability.

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] It should be noted that any variation of the terms "comprising" and "having" is intended to cover non-exclusive inclusion, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such processes, methods, products, or devices.

[0018] Example 1, as Figure 1 As shown, this application provides a method for real-time monitoring of in-situ durability of concrete under the coupled effects of multiple factors, the method comprising:

[0019] Step S100: Collect a set of factors affecting the in-situ durability of concrete, which includes environmental factors, concrete material factors, and construction technology factors. Based on the set of factors affecting the in-situ durability of concrete, perform correlation data mining to obtain a dataset of engineering data on the in-situ durability of concrete.

[0020] In this embodiment, a set of factors influencing the in-situ durability of concrete is first obtained. This set includes environmental factors, concrete material factors, and construction process factors. Environmental factors refer to the external service conditions acting on the concrete structure, including temperature and humidity changes, chloride ion concentration, carbon dioxide concentration, and freeze-thaw cycles. These are continuously collected by deploying temperature and humidity sensors and corrosion monitoring sensors at key locations on the structure. Concrete material factors refer to the physical and chemical properties of the material itself, including water-cement ratio, type and dosage of admixtures, aggregate gradation, and cementitious material properties. These are collected synchronously through the automatic recording system, flow meter, and particle size detection device of the mixing plant. Construction process factors refer to the process parameters during construction, including pouring method and sequence, spraying angle, spraying distance, layer thickness, vibration frequency, and curing conditions. These are recorded in real time through the parameter interface of the construction equipment and the process monitoring system.

[0021] Next, association data mining is performed based on the set of factors influencing in-situ durability of concrete. This process begins with association data mining based on this set, obtaining a historical in-situ durability factor association dataset containing various types of historical monitoring and recording information. Subsequently, this historical in-situ durability factor association dataset is denoised, cleaned, and standardized to form a standard in-situ durability factor association dataset. Then, a corresponding set of in-situ durability assessment indicators is established according to the standards for in-situ durability analysis of concrete. This set of indicators is then used to identify associations in the standard in-situ durability factor association dataset, ultimately constructing a concrete in-situ durability engineering dataset.

[0022] Furthermore, the method provided in the application embodiments, in obtaining the in-situ durability engineering dataset of concrete, further includes:

[0023] Based on the set of factors influencing in-situ durability of concrete, correlation data mining is performed to obtain a correlation dataset of historical in-situ durability factors of concrete. This historical in-situ durability factor correlation dataset is then denoised, cleaned, and standardized to obtain a standard in-situ durability factor correlation dataset. According to the standards for in-situ durability analysis of concrete, a set of in-situ durability evaluation indicators for concrete is constructed. Based on the set of in-situ durability evaluation indicators for concrete, the standard in-situ durability factor correlation dataset is associated and labeled to obtain the engineering dataset for in-situ durability of concrete.

[0024] In this embodiment, when performing correlation data mining based on the set of factors influencing in-situ durability of concrete, a time series matching algorithm is used to synchronize the original monitoring data of environmental factors, concrete material factors, and construction process factors in time and space. Principal component analysis (PCA) is then used to extract key feature parameters highly correlated with concrete durability. Simultaneously, association rule mining techniques, such as the Apriori algorithm, are used to identify implicit coupling relationships among the three types of factors. For example, increased humidity, a high water-cement ratio, and improper spraying angle control during pouring can all lead to an increase in chloride ion penetration rate. Through this process, dispersed, multi-source, heterogeneous data is transformed into a structured historical in-situ durability factor correlation dataset for concrete.

[0025] Next, the Z-score standardization method was used to process the historical in-situ durability factor association dataset of concrete. By calculating the deviation of each parameter from its mean and standard deviation, outliers were identified and removed, eliminating interference signals caused by sensor errors and fluctuations at the construction site. Based on denoising, the characteristic parameters of different physical quantities were uniformly transformed to ensure that temperature, humidity, chloride ion concentration, water-cement ratio, spraying angle, etc., have a consistent numerical range and scale, forming a standard in-situ durability factor association dataset.

[0026] Subsequently, based on the pre-defined in-situ durability analysis standards for concrete, a set of in-situ durability assessment indicators for concrete was constructed. These standards clearly define the parameters requiring focused analysis and their corresponding threshold ranges, such as impermeability, carbonation resistance, chloride ion diffusion characteristics, and freeze-thaw resistance. The Analytic Hierarchy Process (AHP) was used to calculate the weight relationships of different parameters, ensuring that each parameter has a clear role and calculation basis in the overall analysis. This method resulted in the formation of the set of in-situ durability assessment indicators for concrete.

[0027] Finally, a threshold matching method is used to match and identify the feature values ​​in the standard in-situ durability factor association dataset with the corresponding thresholds in the concrete in-situ durability assessment index set. For example, when data such as temperature and humidity, chloride ion concentration, water-cement ratio, and spraying angle meet the preset range, they are directly associated and stored with the corresponding index; when they exceed the set range, the deviation is recorded synchronously. Through this process, the feature data is mapped to the analysis standards, ultimately yielding the concrete in-situ durability engineering dataset.

[0028] Step S200: Perform multi-factor coupling on the concrete in-situ durability engineering dataset according to the set of factors affecting concrete in-situ durability, and build a multi-factor durability coupling analysis model.

[0029] In this embodiment, when performing multi-factor coupling on the concrete in-situ durability engineering dataset according to the set of influencing factors of concrete in-situ durability, firstly, the durability coefficient of the concrete in-situ durability engineering dataset is evaluated and labeled based on the set of concrete in-situ durability evaluation indicators to obtain a sample set of concrete in-situ durability engineering. Then, the sample set of concrete in-situ durability engineering is clustered and integrated according to the set of influencing factors of concrete in-situ durability to obtain environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction technology factor durability engineering sample clusters.

[0030] Subsequently, sensitivity analysis and fitting were performed on the environmental factor durability engineering sample clusters, the concrete material factor durability engineering sample clusters, and the construction process factor durability engineering sample clusters, respectively, to construct corresponding environmental factor durability assessment models, concrete material factor durability assessment models, and construction process factor durability assessment models. Finally, the three single-factor assessment models were coupled to construct a multi-factor durability coupling analysis model.

[0031] Furthermore, the method provided in the application embodiments, in building a multi-factor durability coupling analysis model, also includes:

[0032] Based on the aforementioned set of in-situ concrete durability assessment indicators, the durability coefficient of the in-situ concrete durability engineering dataset is evaluated and labeled to obtain a sample set of in-situ concrete durability engineering. The sample set of in-situ concrete durability engineering is then clustered and integrated according to the aforementioned set of influencing factors of in-situ concrete durability to obtain environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction process factor durability engineering sample clusters. Sensitivity analysis and fitting are performed on these sample clusters to obtain environmental factor durability assessment models, concrete material factor durability assessment models, and construction process factor durability assessment models. Finally, multi-factor coupling is performed on these models to construct a multi-factor durability coupling analysis model.

[0033] In this embodiment, when evaluating and labeling the durability coefficient of an in-situ concrete durability engineering dataset based on a set of in-situ concrete durability evaluation indicators, a weighted calculation method is used to compare the actual values ​​of each parameter with a preset threshold range. Specifically, firstly, the features such as temperature and humidity, chloride ion concentration, water-cement ratio, and spraying angle are dimensionless using the Min-Max normalization method. Then, the weights of each parameter are calculated using the Analytic Hierarchy Process (AHP). The normalized values ​​are multiplied by the weight coefficients and summed to obtain the durability coefficient as the sample labeling result. Through this process, the final sample set of in-situ concrete durability engineering is obtained.

[0034] Next, when clustering and integrating the sample set of in-situ concrete durability engineering projects according to the set of factors affecting in-situ concrete durability, the K-means clustering method is adopted. First, the sample set of in-situ concrete durability engineering projects is vectorized, with environmental factors, water-cement ratio, and chloride ion concentration used as the environmental feature space, material proportion parameters used as the concrete material feature space, and parameters such as spraying angle and construction temperature and humidity used as the construction process feature space. Then, the cluster centers are determined by iteratively calculating and minimizing the intra-class squared error, automatically dividing the sample set of in-situ concrete durability engineering projects into environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction process factor durability engineering sample clusters. For example, samples in the sample set of in-situ concrete durability engineering projects with similar humidity and chloride ion concentration will be grouped into the same environmental factor durability engineering sample cluster.

[0035] Subsequently, sensitivity analysis was performed on the environmental factor durability engineering sample clusters, the concrete material factor durability engineering sample clusters, and the construction technology factor durability engineering sample clusters. In this process, firstly, the changes in single-factor values ​​were recorded for each of the three sample clusters. By collecting and organizing the changes in various influencing factors point by point, datasets on environmental factor durability changes, concrete material factor durability changes, and construction technology factor durability changes were formed. Then, factor sensitivity analysis was performed based on these three datasets to determine the sensitivity sets for environmental factors, concrete material factors, and construction technology factors. Finally, using the sensitivity sets of environmental factors, concrete material factors, and construction technology factors, regression fitting analysis was conducted on the sample clusters of environmental factor durability engineering projects, concrete material factor durability engineering projects, and construction technology factor durability engineering projects to form mathematical models that can quantitatively reflect the influence of single factors on the in-situ durability of concrete. Thus, environmental factor durability assessment models, concrete material factor durability assessment models, and construction technology factor durability assessment models were obtained.

[0036] Finally, a multi-factor coupling was performed on the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction technology factor durability assessment model. In this process, firstly, based on the in-situ durability engineering dataset of concrete, the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction technology factor durability assessment model were coupled, and the outputs of the three single-factor assessment models were merged under a unified framework to construct an initial multi-factor durability analysis model. Subsequently, L1 regularization was introduced into the initial multi-factor durability analysis model to calculate performance loss and address overfitting. By constraining invalid or weakly correlated feature terms, the stability and generalization ability of the model were improved, thus establishing a multi-factor durability coupling analysis model.

[0037] Furthermore, the method provided in the application embodiments, which obtains the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction process factor durability assessment model, also includes:

[0038] Single-factor value changes were recorded for the environmental factor durability engineering sample cluster, the concrete material factor durability engineering sample cluster, and the construction process factor durability engineering sample cluster, respectively, to obtain environmental factor durability change datasets, concrete material factor durability change datasets, and construction process factor durability change datasets. Factor sensitivity analysis was performed on these datasets to determine the environmental factor sensitivity set, concrete material factor sensitivity set, and construction process factor sensitivity set. Regression fitting analysis was then performed on the environmental factor durability engineering sample cluster, concrete material factor durability engineering sample cluster, and construction process factor durability engineering sample cluster, respectively, using these sensitivity sets to generate environmental factor durability assessment models, concrete material factor durability assessment models, and construction process factor durability assessment models.

[0039] In this embodiment, when recording the changes in single-factor values ​​for environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction process factor durability engineering sample clusters, continuous sensor acquisition and time series recording methods are used to collect characteristic parameters such as temperature, humidity, chloride ion concentration, water-cement ratio, and spraying angle, and the change curve of each characteristic parameter over time is completely recorded. By synchronizing the time and separating the values ​​of the collected characteristic data, the influence process of each characteristic is extracted from the superposition of multiple factors, allowing it to be stored and analyzed as a separate change sequence. For example, for the characteristic of temperature, after setting the acquisition frequency, the change values ​​at different times are mapped one-to-one with the corresponding durability coefficients to form structured time series data, thereby obtaining datasets for environmental factor durability changes, concrete material factor durability changes, and construction process factor durability changes.

[0040] Next, when conducting factor sensitivity analysis based on datasets of environmental factor durability changes, concrete material factor durability changes, and construction technology factor durability changes, a single-factor perturbation method is used. Specifically, based on the baseline eigenvalue x0 and the corresponding baseline durability coefficient D0, the target characteristic parameter is subjected to equal-amplitude positive and negative perturbations to obtain the perturbed durability coefficient D. + and D - The baseline feature values ​​are taken from the stable monitoring values ​​of corresponding factors in the concrete in-situ durability engineering sample set, and the baseline durability coefficient is derived from the annotation results of the concrete in-situ durability assessment index set on the concrete in-situ durability engineering dataset. Let the perturbation amplitude of the feature parameters be denoted as Δx, then the formula for calculating the sensitivity S is: This calculation method quantifies the impact of each parameter on concrete durability by measuring the proportion of change in the durability coefficient caused by a unit change in characteristic. For example, when humidity rises from 60% to 65%, if the change in the durability coefficient is significantly greater than the change caused by other characteristic disturbances, then the humidity sensitivity value is greater. After calculating all characteristic parameters, sensitivity sets for environmental factors, concrete material factors, and construction process factors are obtained respectively.

[0041] Finally, regression fitting analyses were performed on the environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction process factor durability engineering sample clusters, respectively, using environmental factor sensitivity sets, concrete material factor sensitivity sets, and construction process factor sensitivity sets. In this process, firstly, sensitivity thresholds for influencing factors were set according to the requirements of concrete durability assessment. These thresholds were then used to screen the environmental factor sensitivity sets, concrete material factor sensitivity sets, and construction process factor sensitivity sets, eliminating non-critical features with minimal impact on durability, thus determining the key environmental factor sets, key concrete material factor sets, and key construction process factor sets. Subsequently, based on the screened key factor sets, regression fitting analyses were performed on the environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction process factor durability engineering sample clusters, respectively. Functional models were then constructed to model the key features against the durability response, ultimately generating environmental factor durability assessment models, concrete material factor durability assessment models, and construction process factor durability assessment models.

[0042] Furthermore, the method provided in the application embodiments, which generates the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction process factor durability assessment model, also includes:

[0043] Based on the requirements for concrete durability assessment, sensitivity thresholds for influencing factors are set. These thresholds are then used to screen the sensitivity sets for environmental factors, concrete material factors, and construction technology factors to determine the key environmental factor set, key concrete material factor set, and key construction technology factor set. Regression fitting analyses are then performed on the environmental factor durability engineering sample cluster, concrete material factor durability engineering sample cluster, and construction technology factor durability engineering sample cluster, respectively, based on these sets, to generate the environmental factor durability assessment model, concrete material factor durability assessment model, and construction technology factor durability assessment model.

[0044] In this embodiment, based on the requirements for concrete durability assessment, the sensitivity values ​​of the environmental factor sensitivity set, the concrete material factor sensitivity set, and the construction process factor sensitivity set are first statistically analyzed. Then, the quantile method is used to select the value corresponding to the 80th percentile in the overall numerical distribution as the sensitivity threshold. For example, when the distribution range of a certain type of sensitivity value is between 0.05 and 0.50, the value corresponding to the 80th percentile is 0.40, so 0.40 is set as the sensitivity threshold.

[0045] Subsequently, based on sensitivity thresholds, factors in the environmental factor sensitivity set, concrete material factor sensitivity set, and construction process factor sensitivity set were screened. Factors with sensitivity values ​​greater than or equal to 0.40 were retained, while those with sensitivity values ​​less than 0.40 were eliminated. For example, when the sensitivity of humidity was 0.45, the sensitivity of chloride ion concentration was 0.43, and the sensitivity of water-cement ratio was 0.38, humidity and chloride ion concentration were retained, while water-cement ratio was eliminated. Through this process, the key environmental factor set, key concrete material factor set, and key construction process factor set were determined, respectively.

[0046] Finally, using key environmental factors, key concrete material factors, and key construction technology factors as the main independent variables, and durability coefficients as the dependent variable, regression fitting analyses were performed on the environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction technology factor durability engineering sample clusters, respectively. In this process, the selected key features were fitted with durability coefficients using functions, their correspondences were calculated, and the fitting results were subjected to residual tests and goodness-of-fit verification to ensure the stability and accuracy of the models. Through this step, environmental factor durability assessment models, concrete material factor durability assessment models, and construction technology factor durability assessment models were generated, respectively.

[0047] Furthermore, the method provided in the application embodiment further includes multi-factor coupling of the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction process factor durability assessment model to build a multi-factor durability coupling analysis model, and also includes:

[0048] Based on the concrete in-situ durability engineering dataset, the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction technology factor durability assessment model are coupled in multiple ways to construct an initial multi-factor durability analysis model. L1 regularization is used to calculate performance loss and process overfitting in the initial multi-factor durability analysis model to build the multi-factor durability coupling analysis model.

[0049] In this embodiment, when coupling environmental factor durability assessment models, concrete material factor durability assessment models, and construction technology factor durability assessment models based on a concrete in-situ durability engineering dataset, a feature unification and normalization method is first used to numerically standardize the feature parameters and corresponding durability coefficients in the three types of assessment models, mapping all features to the same scale range. After feature normalization, the three types of feature parameters are mapped and aligned according to time series and spatial location to ensure that each factor has consistent time points and spatial coordinates under the same monitoring conditions. Through this process, the response characteristics and durability coefficients of the three types of assessment models are unified and integrated to form an initial multi-factor durability analysis model.

[0050] Next, L1 regularization is used to calculate performance loss and address overfitting in the initial multi-factor durability analysis model. In this process, the concrete in-situ durability engineering dataset is divided into a training set and a validation set according to a preset ratio. The training set is used to fit the model parameters, while the validation set is used to evaluate model performance and adjust the strength of the regularization penalty term. By introducing a penalty term based on the absolute value of feature weights into the error metric, the feature weights that contribute less to the in-situ durability of concrete are gradually reduced, decreasing the impact of irrelevant features on the overall analysis, while ensuring the stability and generalization ability of the model under different durability conditions. After this process, a multi-factor durability coupled analysis model is obtained.

[0051] Step S300: Based on the multi-factor durability coupling analysis model, deploy N concrete distributed edge units on the target concrete, and perform in-situ durability real-time monitoring and analysis through the N concrete distributed edge units to obtain N concrete in-situ durability coefficients.

[0052] In this embodiment, when deploying N distributed edge units on the target concrete based on a multi-factor durability coupling analysis model, the key parts of the target concrete are first identified according to the concrete structural characteristics and durability monitoring requirements, thus determining N key concrete parts. Subsequently, an analysis of the deployment of monitoring sensors is conducted based on the environmental characteristics and stress state of each key part, selecting sensor types suitable for different monitoring objects, and constructing a multi-source sensor network for the N key parts. After completing the sensor network construction, the multi-source sensor network for the N key parts is integrated and deployed with the multi-factor durability coupling analysis model to form N distributed edge units on the concrete.

[0053] Subsequently, in-situ durability real-time monitoring and analysis were conducted using N distributed concrete edge units. During this process, each distributed concrete edge unit continuously collected key characteristic parameters such as temperature, humidity, chloride ion concentration, water-cement ratio, and spraying angle using multi-source sensors. The collected data was then input into a multi-factor durability coupling analysis model for real-time analysis. Based on the coupling relationship between environmental factors, concrete material factors, and construction process factors, the multi-factor durability coupling analysis model calculated the durability state at each moment, obtaining the corresponding in-situ concrete durability coefficient. By uniformly summarizing and comparing the output results of the N distributed concrete edge units, N in-situ concrete durability coefficients were finally obtained.

[0054] Furthermore, in the method provided in the application embodiments, deploying N distributed edge units on the target concrete based on the multi-factor durability coupling analysis model further includes:

[0055] Based on the structural characteristics and durability monitoring requirements of concrete, key parts of the target concrete are identified to obtain N key concrete parts; monitoring sensor deployment analysis is performed on the N key concrete parts to construct a multi-source sensor network for the N key parts; the multi-source sensor network for the N key parts is integrated with the multi-factor durability coupling analysis model and deployed in a distributed unit to obtain the N concrete distributed edge units.

[0056] In this embodiment, key components of the target concrete are first identified according to the structural characteristics and durability monitoring requirements. During this process, the finite element method (FEM) is used to calculate the stress distribution of the concrete structure under actual loads. Dead and live loads are applied to the concrete structure model to obtain the stress distribution results of the concrete members. Using the global average principal tensile stress as a benchmark, areas with local stress values ​​exceeding 1.5 times the average or principal tensile stresses greater than 2.0 MPa are identified as stress concentration areas. Simultaneously, using environmental exposure intensity calculation methods, measured data of environmental parameters such as temperature, humidity, and chloride concentration are analyzed. Areas with humidity fluctuations exceeding 15% or chloride concentrations exceeding 3% are identified as environmentally exposed areas. Then, construction joints and cold joints in the concrete structure are inspected. Areas with rebound values ​​below 30 MPa are marked as weak points in the construction. For conventional cast-in-place concrete projects, construction joints and cold joints are often locations with weak durability and require focused monitoring. If any one of the following conditions is met—a stress concentration area, an environmentally exposed area, or a weak point in the construction—the area is designated as a critical monitoring area, and N critical concrete parts are obtained.

[0057] Subsequently, monitoring sensor deployment analysis was conducted on N key concrete components, using an equidistant deployment method. Strain sensors were deployed in areas of concentrated stress, with spacing controlled between 0.5 and 1.0 meters; temperature and humidity sensors and chloride ion concentration sensors were deployed in environmentally exposed areas, with a sampling frequency of once every 10 minutes; similar sensors were deployed in weak points in the construction to continuously record changes in key characteristics. To ensure continuous and blind-spot-free monitoring data coverage, the overlap rate of monitoring ranges of adjacent sensors was controlled between 20% and 30%, thus constructing a multi-source sensor network for N key components.

[0058] Finally, a multi-source sensor network of N key components and a multi-factor durability coupling analysis model were integrated and deployed in a distributed unit. Through numerical standardization, characteristic parameters such as temperature, humidity, chloride ion concentration, water-cement ratio, and spraying angle collected by the sensors were uniformly converted to the same numerical scale and input into the multi-factor durability coupling analysis model in real-time calculations, aligned according to time sequence. After integration and processing, N concrete distributed edge units were obtained.

[0059] Step S400: Perform a global integrated analysis on the N concrete in-situ durability coefficients to determine the in-situ durability analysis results of the target concrete.

[0060] In this embodiment, when performing a global integrated analysis of N concrete in-situ durability coefficients, the importance of N key concrete components is first assessed according to the structural characteristics of the target concrete structure. Based on the stress condition, environmental exposure level, and the influence of their location within the overall structure, weight factors for the corresponding N key components are determined. Subsequently, the N key component weight factors are used to perform a global integrated analysis of the N concrete in-situ durability coefficients. The monitoring results of different components are calculated and fused according to their weights to finally determine the target concrete in-situ durability analysis results.

[0061] Furthermore, the method provided in the application embodiments, in determining the in-situ durability analysis results of the target concrete, further includes:

[0062] The importance of the N key concrete components is assessed according to the target concrete structural characteristics, and the weighting factors of the N key components are determined. Based on the weighting factors of the N key components, a global integrated analysis is performed on the N in-situ durability coefficients of the concrete to determine the in-situ durability analysis results of the target concrete.

[0063] In this embodiment, when assessing the importance of N key concrete components according to the target concrete structural characteristics, a finite element model is first established based on these characteristics. Then, the load-bearing capacity of the N key concrete components is simulated using this model, calculating the principal stress values ​​and stress concentration of each component. The importance of the key components is quantitatively assessed based on the simulation results, and these results are used as the basis for determining the weighting factors, ultimately determining the weighting factors for the N key components.

[0064] Next, a global integrated analysis of N concrete in-situ durability coefficients is performed based on N weighting factors for key components. In this process, a weighted average method is used to calculate the in-situ durability coefficients of each key concrete component by weighting them with their corresponding weighting factors. This yields a comprehensive durability coefficient reflecting the overall durability level of the target concrete, which is then output as the result of the in-situ durability analysis of the target concrete.

[0065] Furthermore, in the method provided in the application embodiments, determining the weight factors of N key parts further includes:

[0066] Based on the target concrete structure characteristics, a finite element model is generated to produce a concrete finite element model. The load-bearing capacity and importance of the N key concrete components are simulated and evaluated using the concrete finite element model to determine the weight factors of the N key components.

[0067] In this embodiment, when performing finite element modeling based on the characteristics of the target concrete structure, a three-dimensional solid model is first established according to the actual geometric dimensions of the target concrete structure. The concrete structure is then divided into mesh elements using the finite element discretization method. A fixed mesh size is used to divide the overall structure into several elements, and material parameters, including the elastic modulus and Poisson's ratio, are set. Corresponding boundary conditions and external loads are applied. The overall structure is then subjected to stress analysis using static analysis methods to obtain the principal stress distribution field and displacement field, thus obtaining the concrete finite element model.

[0068] Subsequently, the load-bearing capacity and importance of N key concrete components were simulated and assessed using a concrete finite element model. In this process, the principal stress values ​​and peak displacements of each key concrete component were first extracted under a uniform stress condition, with the global average principal stress used as the criterion. After setting a threshold, the load-bearing response characteristics of key concrete components with principal stresses exceeding the threshold were identified, and the relative magnitude of their principal stress values ​​was used as the basis for quantifying importance. The threshold was set at 1.5 times the global average principal stress.

[0069] After completing the load-bearing capacity simulation and importance assessment, the weighting factors of N key concrete components are determined by a proportional allocation method. This involves calculating the ratio of the principal stress value of each key concrete component to the sum of the principal stresses of all key concrete components to form a normalized weighting factor, thus determining the weighting factors of N key components.

[0070] In summary, the embodiments of this application have at least the following technical effects:

[0071] This application collects a set of factors influencing the in-situ durability of concrete, including environmental factors, concrete material factors, and construction technology factors. Based on this set of factors, correlation data mining is performed to obtain a concrete in-situ durability engineering dataset. The dataset is then coupled with multiple factors to build a multi-factor durability coupling analysis model. Based on this model, N distributed edge units are deployed on the target concrete, and real-time in-situ durability monitoring and analysis are performed using these N units to obtain N concrete in-situ durability coefficients. A global integration analysis is then performed on these N coefficients to determine the target concrete's in-situ durability analysis results. This invention addresses the technical problem in existing technologies where comprehensive coupling analysis of multiple factors such as environment, materials, and construction technology is impossible, making it difficult to reflect the actual durability state of concrete in a timely and accurate manner. Through multi-factor coupling modeling and distributed monitoring and analysis, it achieves the technical effect of real-time in-situ monitoring and accurate assessment of concrete durability.

[0072] Example 2, based on the same inventive concept as the real-time monitoring method for in-situ durability of concrete under multi-factor coupling effects in the aforementioned examples, such as... Figure 2 As shown, this application provides a real-time monitoring system for in-situ durability of concrete under the coupled effects of multiple factors. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0073] The influencing factor acquisition module 11 is used to acquire a set of influencing factors for in-situ durability of concrete, which includes environmental factors, concrete material factors, and construction technology factors. Based on the set of influencing factors, correlation data mining is performed to obtain an engineering dataset for in-situ durability of concrete. The multi-factor coupling module 12 is used to perform multi-factor coupling on the engineering dataset for in-situ durability of concrete according to the set of influencing factors, and to build a multi-factor durability coupling analysis model. The monitoring and analysis module 13 is used to deploy N distributed edge units on the target concrete based on the multi-factor durability coupling analysis model, and to perform real-time monitoring and analysis of in-situ durability through the N distributed edge units to obtain N in-situ durability coefficients. The global integration analysis module 14 is used to perform global integration analysis on the N in-situ durability coefficients to determine the analysis results of the in-situ durability of the target concrete.

[0074] Furthermore, the system is also used to implement the following functions:

[0075] Based on the set of factors influencing in-situ durability of concrete, correlation data mining is performed to obtain a correlation dataset of historical in-situ durability factors of concrete. This historical in-situ durability factor correlation dataset is then denoised, cleaned, and standardized to obtain a standard in-situ durability factor correlation dataset. According to the standards for in-situ durability analysis of concrete, a set of in-situ durability evaluation indicators for concrete is constructed. Based on the set of in-situ durability evaluation indicators for concrete, the standard in-situ durability factor correlation dataset is associated and labeled to obtain the engineering dataset for in-situ durability of concrete.

[0076] Furthermore, the system is also used to implement the following functions:

[0077] Based on the aforementioned set of in-situ concrete durability assessment indicators, the durability coefficient of the in-situ concrete durability engineering dataset is evaluated and labeled to obtain a sample set of in-situ concrete durability engineering. The sample set of in-situ concrete durability engineering is then clustered and integrated according to the aforementioned set of influencing factors of in-situ concrete durability to obtain environmental factor durability engineering sample clusters, concrete material factor durability engineering sample clusters, and construction process factor durability engineering sample clusters. Sensitivity analysis and fitting are performed on these sample clusters to obtain environmental factor durability assessment models, concrete material factor durability assessment models, and construction process factor durability assessment models. Finally, multi-factor coupling is performed on these models to construct a multi-factor durability coupling analysis model.

[0078] Furthermore, the system is also used to implement the following functions:

[0079] Single-factor value changes were recorded for the environmental factor durability engineering sample cluster, the concrete material factor durability engineering sample cluster, and the construction process factor durability engineering sample cluster, respectively, to obtain environmental factor durability change datasets, concrete material factor durability change datasets, and construction process factor durability change datasets. Factor sensitivity analysis was performed on these datasets to determine the environmental factor sensitivity set, concrete material factor sensitivity set, and construction process factor sensitivity set. Regression fitting analysis was then performed on the environmental factor durability engineering sample cluster, concrete material factor durability engineering sample cluster, and construction process factor durability engineering sample cluster, respectively, using these sensitivity sets to generate environmental factor durability assessment models, concrete material factor durability assessment models, and construction process factor durability assessment models.

[0080] Furthermore, the system is also used to implement the following functions:

[0081] Based on the requirements for concrete durability assessment, sensitivity thresholds for influencing factors are set. These thresholds are then used to screen the sensitivity sets for environmental factors, concrete material factors, and construction technology factors to determine the key environmental factor set, key concrete material factor set, and key construction technology factor set. Regression fitting analyses are then performed on the environmental factor durability engineering sample cluster, concrete material factor durability engineering sample cluster, and construction technology factor durability engineering sample cluster, respectively, based on these sets, to generate the environmental factor durability assessment model, concrete material factor durability assessment model, and construction technology factor durability assessment model.

[0082] Furthermore, the system is also used to implement the following functions:

[0083] Based on the concrete in-situ durability engineering dataset, the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction technology factor durability assessment model are coupled in multiple ways to construct an initial multi-factor durability analysis model. L1 regularization is used to calculate performance loss and process overfitting in the initial multi-factor durability analysis model to build the multi-factor durability coupling analysis model.

[0084] Furthermore, the system is also used to implement the following functions:

[0085] Based on the structural characteristics and durability monitoring requirements of concrete, key parts of the target concrete are identified to obtain N key concrete parts; monitoring sensor deployment analysis is performed on the N key concrete parts to construct a multi-source sensor network for the N key parts; the multi-source sensor network for the N key parts is integrated with the multi-factor durability coupling analysis model and deployed in a distributed unit to obtain the N concrete distributed edge units.

[0086] Furthermore, the system is also used to implement the following functions:

[0087] The importance of the N key concrete components is assessed according to the target concrete structural characteristics, and the weighting factors of the N key components are determined. Based on the weighting factors of the N key components, a global integrated analysis is performed on the N in-situ durability coefficients of the concrete to determine the in-situ durability analysis results of the target concrete.

[0088] Furthermore, the system is also used to implement the following functions:

[0089] Based on the target concrete structure characteristics, a finite element model is generated to produce a concrete finite element model. The load-bearing capacity and importance of the N key concrete components are simulated and evaluated using the concrete finite element model to determine the weight factors of the N key components.

[0090] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0091] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for real-time monitoring of in-situ durability of concrete under the coupled effects of multiple factors, characterized in that, The method includes: A set of factors affecting the in-situ durability of concrete was collected, which included environmental factors, concrete material factors, and construction technology factors. Based on the set of factors affecting the in-situ durability of concrete, correlation data mining was performed to obtain a dataset of engineering data on the in-situ durability of concrete. Based on the set of factors affecting the in-situ durability of concrete, the in-situ durability engineering dataset of concrete is coupled with multiple factors to build a multi-factor durability coupling analysis model. Based on the multi-factor durability coupling analysis model, N concrete distributed edge units are deployed on the target concrete. In-situ durability is monitored and analyzed in real time through the N concrete distributed edge units to obtain N concrete in-situ durability coefficients. A global integrated analysis was performed on the N concrete in-situ durability coefficients to determine the in-situ durability analysis results of the target concrete. The dataset of in-situ durability engineering of concrete was obtained, including: Based on the set of factors affecting the in-situ durability of concrete, correlation data mining is performed to obtain a correlation dataset of historical in-situ durability factors of concrete. The historical in-situ durability factor association dataset of concrete is denoised, cleaned, and standardized to obtain a standard in-situ durability factor association dataset. Based on the standard for in-situ durability analysis of concrete, a set of evaluation indicators for in-situ durability of concrete is constructed. Based on the concrete in-situ durability assessment index set, the standard in-situ durability factor association dataset is associated and identified to obtain the concrete in-situ durability engineering dataset. A multi-factor durability coupling analysis model was constructed, including: Based on the in-situ durability evaluation index set of concrete, the durability coefficient of the in-situ durability engineering dataset of concrete is evaluated and labeled to obtain the in-situ durability engineering sample set of concrete. The in-situ durability engineering sample set of concrete is clustered and integrated according to the in-situ durability influencing factor set of concrete to obtain environmental factor durability engineering sample cluster, concrete material factor durability engineering sample cluster and construction process factor durability engineering sample cluster. Sensitivity analysis was performed on the environmental factor durability engineering sample cluster, the concrete material factor durability engineering sample cluster, and the construction process factor durability engineering sample cluster, respectively, to obtain the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction process factor durability assessment model. The environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction process factor durability assessment model are coupled in multiple ways to build a multi-factor durability coupling analysis model.

2. The method for real-time monitoring of in-situ durability of concrete under multi-factor coupling as described in claim 1, characterized in that, The following models were obtained: environmental factor durability assessment model, concrete material factor durability assessment model, and construction process factor durability assessment model, including: The single-factor value changes of the environmental factor durability engineering sample cluster, the concrete material factor durability engineering sample cluster, and the construction process factor durability engineering sample cluster were recorded respectively to obtain the environmental factor durability change dataset, the concrete material factor durability change dataset, and the construction process factor durability change dataset. Based on the aforementioned datasets of environmental factor durability changes, concrete material factor durability changes, and construction process factor durability changes, factor sensitivity analysis was performed to determine the environmental factor sensitivity set, concrete material factor sensitivity set, and construction process factor sensitivity set. The environmental factor sensitivity set, concrete material factor sensitivity set, and construction process factor sensitivity set are used to perform regression fitting analysis on the environmental factor durability engineering sample cluster, concrete material factor durability engineering sample cluster, and construction process factor durability engineering sample cluster, respectively, to generate environmental factor durability assessment models, concrete material factor durability assessment models, and construction process factor durability assessment models.

3. The method for real-time monitoring of in-situ durability of concrete under multi-factor coupling as described in claim 2, characterized in that, Generate durability assessment models for environmental factors, concrete material factors, and construction process factors, including: Based on the requirements for concrete durability assessment, sensitivity thresholds for influencing factors are set; The sensitivity thresholds for the influencing factors are used to screen the sensitivity sets for environmental factors, concrete material factors, and construction technology factors to determine the key environmental factor set, key concrete material factor set, and key construction technology factor set. Based on the aforementioned key environmental factor set, key concrete material factor set, and key construction process factor set, regression fitting analysis is performed on the environmental factor durability engineering sample cluster, concrete material factor durability engineering sample cluster, and construction process factor durability engineering sample cluster, respectively, to generate the environmental factor durability assessment model, concrete material factor durability assessment model, and construction process factor durability assessment model.

4. The method for real-time monitoring of in-situ durability of concrete under multi-factor coupling as described in claim 1, characterized in that, The environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction technology factor durability assessment model are coupled in multiple ways to build a multi-factor durability coupling analysis model, including: Based on the concrete in-situ durability engineering dataset, the environmental factor durability assessment model, the concrete material factor durability assessment model, and the construction process factor durability assessment model are coupled in multiple ways to construct an initial multi-factor durability analysis model. L1 regularization was used to calculate performance loss and process overfitting in the initial multi-factor durability analysis model, and the multi-factor durability coupled analysis model was built.

5. The method for real-time monitoring of in-situ durability of concrete under multi-factor coupling as described in claim 1, characterized in that, Based on the aforementioned multi-factor durability coupling analysis model, N distributed edge units of concrete are deployed on the target concrete, including: Based on the structural characteristics and durability monitoring requirements of concrete, key parts of the target concrete are identified, resulting in N key concrete parts. The deployment and analysis of monitoring sensors for the N key concrete components were carried out to construct a multi-source sensor network for the N key components. The N key component multi-source sensor networks are integrated with the multi-factor durability coupling analysis model and deployed in a distributed unit to obtain the N concrete distributed edge units.

6. The method for real-time monitoring of in-situ durability of concrete under multi-factor coupling as described in claim 5, characterized in that, Determine the results of the in-situ durability analysis of the target concrete, including: The importance of the N key concrete components is assessed according to the target concrete structure characteristics, and the weighting factors of the N key components are determined. Based on the weighting factors of the N key components, a global integrated analysis is performed on the N in-situ durability coefficients of concrete to determine the in-situ durability analysis results of the target concrete.

7. The method for real-time monitoring of in-situ durability of concrete under multi-factor coupling as described in claim 6, characterized in that, Determine the weighting factors for N key components, including: Finite element modeling is performed based on the target concrete structure characteristics to generate a concrete finite element model. The load-bearing capacity and importance of the N key concrete components are simulated and evaluated using the concrete finite element model, and the weight factors of the N key components are determined.

8. A real-time monitoring system for in-situ durability of concrete under the coupled effects of multiple factors, characterized in that, The system is used to perform the real-time monitoring method for in-situ durability of concrete under multi-factor coupling as described in any one of claims 1-7, and the system includes: The influencing factor collection module is used to collect a set of influencing factors of in-situ concrete durability. The set of influencing factors of in-situ concrete durability includes environmental factors, concrete material factors and construction technology factors. Based on the set of influencing factors of in-situ concrete durability, correlation data mining is performed to obtain a dataset of in-situ concrete durability engineering. The multi-factor coupling module is used to perform multi-factor coupling on the concrete in-situ durability engineering dataset according to the set of factors affecting concrete in-situ durability, and to build a multi-factor durability coupling analysis model. The monitoring and analysis module is used to deploy N concrete distributed edge units on the target concrete based on the multi-factor durability coupling analysis model, and to perform in-situ durability real-time monitoring and analysis through the N concrete distributed edge units to obtain N concrete in-situ durability coefficients. The global integrated analysis module is used to perform a global integrated analysis on the N concrete in-situ durability coefficients to determine the target concrete in-situ durability analysis results.

Images