A concrete structure temperature gradient precision testing device and testing method

Abstract

The present application provides a concrete structure temperature gradient precision testing device and testing method, which relates to the field of precision testing technology, including: obtaining concrete construction information; extracting concrete features and establishing a concrete feature set; performing concrete grid segmentation, clustering and evaluating temperature anomalies, and distributing optical fiber sensing lines with associated clustering results; performing wavelength change reading conversion to establish a time series temperature field of concrete; authenticating the temperature gradient change of the time series temperature field through a grid association network and generating an associated authentication result; performing time series change analysis and establishing a time series authentication result; and generating a temperature warning. The present application can solve the technical problems of limited arrangement and insufficient precision stability of traditional temperature sensors in the prior art, achieve the technical goal of accurate monitoring and real-time analysis of the temperature gradient of concrete structures, and achieve the technical effect of improving the temperature anomaly detection capability during construction and reducing construction risks.

Description

Technical Field

[0001] The present application relates to the field of precision testing technology, and in particular to a precision testing device and method for temperature gradient of concrete structures. Background Art

[0002] Temperature monitoring of concrete structures is crucial in engineering construction, as temperature changes will directly affect the performance and structural stability of concrete.

[0003] At present, the existing temperature monitoring technology mainly relies on traditional temperature sensors and manual data collection methods, which have many shortcomings. First, the traditional temperature sensors are limited in their arrangement inside the concrete structure and cannot fully cover the entire structure, resulting in low spatial resolution of temperature data. The accuracy and stability of the sensor itself are also limited, especially in harsh construction environments, and are easily affected by external interference and produce errors. Secondly, poor real-time performance also greatly limits the effect of temperature monitoring. The manual data collection method relies on regular on-site measurement and recording, which is not only time-consuming and labor-intensive, but also has poor timeliness of data and cannot timely reflect the real-time changes in the temperature inside the concrete. Poor real-time performance makes it impossible to quickly capture and handle sudden temperature anomalies during the construction process, resulting in cracks or other quality problems in the concrete structure. Therefore, the shortcomings of the existing temperature monitoring technology have led to the inability to detect and handle temperature anomalies in a timely manner. There is an urgent need for a temperature monitoring device with high precision and strong real-time performance to improve the safety and quality of concrete structure construction.

[0004] In summary, the prior art has technical problems such as low spatial resolution and frequent errors of temperature data due to the limited arrangement of traditional temperature sensors and insufficient accuracy and stability, which further affects the timely detection and processing of temperature anomalies in concrete structures. Summary of the invention

[0005] The purpose of this application is to provide a precise testing device and method for the temperature gradient of a concrete structure, so as to solve the technical problem in the prior art that the spatial resolution of temperature data is low and errors are frequent due to the limited arrangement and insufficient accuracy and stability of traditional temperature sensors, which further affects the timely detection and processing of temperature anomalies in concrete structures.

[0006] In view of the above problems, the present application provides a precise testing device and method for the temperature gradient of a concrete structure.

[0007] In a first aspect, the present application provides a precise testing device for the temperature gradient of a concrete structure, which includes: an interaction module for acquiring the construction information of the concrete according to the digital communication, wherein the construction information includes the construction drawing information, construction material information, construction control information and location information of the concrete; a feature extraction module for extracting the features of the concrete according to the construction information and establishing a concrete feature set, wherein the concrete feature set includes a structural feature set, a material feature set, a construction control feature set and a location influence feature set; a layout module for configuring a reference segmentation block, performing mesh segmentation of the concrete according to the reference segmentation block, and meshing the concrete according to the concrete feature set. Cluster evaluation of the temperature anomaly of the segmentation results, establishment of associated clustering results, and distribution of optical fiber sensing lines based on the associated clustering results; a monitoring module for calling an optical fiber spectrometer to read the Bragg wavelength of the optical fiber sensing line, performing wavelength change reading conversion, and establishing a time-series temperature field of the concrete; an associated authentication module for establishing a grid associated network based on the associated clustering results, performing temperature gradient change authentication of the time-series temperature field through the grid associated network, and generating an associated authentication result; a time-series authentication module for performing time-series change analysis based on the time-series temperature field and establishing a time-series authentication result; a management module for generating a temperature warning based on the associated authentication results and the time-series authentication results.

[0008] In a second aspect, the present application provides a method for precisely testing the temperature gradient of a concrete structure, which is implemented by a device for precisely testing the temperature gradient of a concrete structure, and includes: obtaining construction information of the concrete according to digital communication, wherein the construction information includes construction drawing information, construction material information, construction control information and location information of the concrete; extracting features of the concrete according to the construction information, and establishing a concrete feature set, wherein the concrete feature set includes a structural feature set, a material feature set, a construction control feature set and a location influence feature set; configuring a reference segmentation block, performing grid segmentation of the concrete according to the reference segmentation block, clustering and evaluating the temperature anomaly of the grid segmentation result through the concrete feature set, establishing an associated clustering result, and distributing the optical fiber sensing line with the associated clustering result; calling an optical fiber spectrometer to read the Bragg wavelength of the optical fiber sensing line, performing wavelength change reading conversion, and establishing a time series temperature field of the concrete; establishing a grid association network based on the associated clustering result, and performing temperature gradient change authentication of the time series temperature field through the grid association network to generate an associated authentication result; performing time series change analysis based on the time series temperature field to establish a time series authentication result; and generating a temperature warning according to the associated authentication result and the time series authentication result.

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

[0010] The construction information of concrete is obtained according to digital communication, and the construction information includes construction drawing information, construction material information, construction control information and location information of concrete; the feature of concrete is extracted according to the construction information, and a concrete feature set is established, and the concrete feature set includes a structural feature set, a material feature set, a construction control feature set and a location influence feature set; a reference segmentation block is configured, and a grid segmentation of concrete is performed according to the reference segmentation block, and a temperature anomaly degree clustering evaluation of the grid segmentation result is performed through the concrete feature set, and an associated clustering result is established, and an optical fiber sensing line is distributed according to the associated clustering result; a fiber optic spectrometer is called to read the Bragg wavelength of the optical fiber sensing line, and a reading conversion of a wavelength change is performed to establish a time series temperature field of concrete; a grid associated clustering result is established based on the associated clustering result. A grid-associated network is connected, and the temperature gradient change authentication of the time-series temperature field is performed through the grid-associated network to generate an associated authentication result; a time-series change analysis is performed based on the time-series temperature field to establish a time-series authentication result; a temperature warning is generated according to the associated authentication result and the time-series authentication result, that is, concrete construction information is obtained through digital communication, features are extracted to establish a feature set, and fiber optic sensing technology and intelligent algorithms are used to perform grid segmentation, temperature monitoring and time-series analysis to generate a temperature warning, and the monitoring and warning process is optimized in combination with user feedback to achieve high-precision, real-time temperature gradient monitoring, and ultimately achieve the technical goal of accurate monitoring and real-time analysis of the temperature gradient of the concrete structure, so as to achieve the technical effect of improving the temperature anomaly detection capability during the construction process, reducing construction risks, and improving the quality of the concrete structure and construction efficiency.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or 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 in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a schematic structural diagram of a precise testing device for temperature gradient of concrete structure according to the present application.

[0014] Figure 2The present invention is a flow chart of a method for precisely testing the temperature gradient of a concrete structure.

[0015] Description of reference numerals:

[0016] Interaction module 11, feature extraction module 12, deployment module 13, monitoring module 14, association authentication module 15, timing authentication module 16, management module 17. DETAILED DESCRIPTION

[0017] This application provides a precise testing device and method for the temperature gradient of concrete structures, which solves the technical problem in the prior art that the spatial resolution of temperature data is low and errors are frequent due to the limited arrangement and insufficient precision stability of traditional temperature sensors, which further affects the timely discovery and handling of temperature anomalies in concrete structures. The technical goal of accurate monitoring and real-time analysis of the temperature gradient of concrete structures is achieved, and the technical effect of improving the ability to detect temperature anomalies during construction, reducing construction risks, and improving the quality of concrete structures and construction efficiency is achieved.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] For example, please refer to the attached Figure 1 The present application provides a concrete structure temperature gradient precision testing device, which specifically includes:

[0020] The interactive module 11 is used to obtain the construction information of the concrete according to the digital communication, and the construction information includes the construction drawing information, construction material information, construction control information and location information of the concrete; the feature extraction module 12 is used to extract the features of the concrete according to the construction information and establish a concrete feature set, and the concrete feature set includes a structural feature set, a material feature set, a construction control feature set and a location influence feature set; the layout module 13 is used to configure the reference segmentation block, perform grid segmentation of the concrete according to the reference segmentation block, perform clustering evaluation of the temperature anomaly of the grid segmentation result through the concrete feature set, and establish an association Clustering results, distributing optical fiber sensing lines with the associated clustering results; a monitoring module 14, used to call the optical fiber spectrometer to read the Bragg wavelength of the optical fiber sensing line, perform wavelength change reading conversion, and establish a time-series temperature field of the concrete; an associated authentication module 15, used to establish a grid associated network based on the associated clustering results, perform temperature gradient change authentication of the time-series temperature field through the grid associated network, and generate an associated authentication result; a time-series authentication module 16, used to perform time-series change analysis based on the time-series temperature field, and establish a time-series authentication result; a management module 17, used to generate a temperature warning according to the associated authentication results and the time-series authentication results.

[0021] Furthermore, the feature extraction module 12 in the concrete structure temperature gradient precision testing device is also used for:

[0022] Establishing a principal component recognition model; performing principal component recognition of concrete feature sets of each grid segmentation result through the principal component recognition model to establish recognition results; performing temperature anomaly clustering evaluation based on the recognition results to establish associated clustering results.

[0023] Furthermore, the feature extraction module 12 in the concrete structure temperature gradient precision testing device is also used for:

[0024] The preprocessing layer of the principal component recognition model is called, and the preprocessing layer is provided with a total proportion screening threshold of feature influence; the concrete feature sets of each grid segmentation result are sorted in order of feature influence, and the order sorting and screening of each grid segmentation result is screened by the total proportion screening threshold, and a sequential sorting and screening result is established; the unselected order result in the sequential sorting is obtained according to the sequential sorting and screening result, and the minimum feature influence deviation between the unselected order result and the sequential sorting and screening result is compared; the sequential sorting and screening result is reconstructed according to the deviation comparison result, and the reconstructed sequential sorting and screening result is output as the recognition result.

[0025] Furthermore, the feature extraction module 12 in the concrete structure temperature gradient precision testing device is also used for:

[0026] Generate a first transition incentive based on the deviation comparison result; obtain the feature influence value of the unselected priority result, and establish a second transition incentive based on the proportion of the feature influence value in the total feature influence value of the unreconstructed sequential sorting screening result; determine whether to be selected based on the first transition incentive and the second transition incentive; if the determination result is a passing result, reconstruct the sequential sorting screening result.

[0027] Furthermore, the associated authentication module 15 in the concrete structure temperature gradient precision testing device is also used for:

[0028] The association clustering result is divided into dynamic clustering results, and the grid association network is optimized with the dynamic clustering results; the temperature gradient change authentication of the time series temperature field is performed with the optimized grid association network, and the association authentication result is updated.

[0029] Furthermore, the timing authentication module 16 in the concrete structure temperature gradient precision testing device is also used for:

[0030] The time series temperature field is evaluated for time series changes based on each grid segmentation result, and an adaptive long and short time series window is established; the long and short time series changes of the time series temperature field are analyzed through the adaptive long and short time series window, and a time series authentication result is established.

[0031] Furthermore, the management module 17 in the concrete structure temperature gradient precision testing device is also used for:

[0032] A feedback management module is used to issue the temperature warning, create a feedback cycle based on the temperature warning, perform user processing feedback within the feedback cycle, and establish feedback verification data; an optimization module is used to perform warning processing evaluation based on the feedback verification data, generate an optimized data set through the warning processing evaluation, and feed back the optimized data set to the user.

[0033] A concrete structure temperature gradient precision testing device and specific examples are also applicable to a concrete structure temperature gradient precision testing method of this embodiment. Through the detailed description of a concrete structure temperature gradient precision testing method, those skilled in the art can clearly know a concrete structure temperature gradient precision testing device of this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0034] Embodiment 2: Based on the same invention concept as the device for precisely testing the temperature gradient of a concrete structure in the above embodiment, this application also provides a method for precisely testing the temperature gradient of a concrete structure. Figure 2 ,include:

[0035] Step 1: Acquire concrete construction information according to digital communication, wherein the construction information includes concrete construction drawing information, construction material information, construction control information and location information.

[0036] Specifically, the construction information of concrete is obtained through digital communication. The construction information covers the construction drawing information, construction material information, construction control information and location information of concrete. Construction drawing information refers to the architectural drawing, which contains the specific design requirements such as the size, shape, and construction sequence of the concrete structure, which helps to obtain the layout and construction plan of the structure. The construction material information includes the type, proportion, source and other details of the concrete materials used to ensure that the materials meet the design and quality standards. The construction control information involves various control parameters used in the construction process, such as pouring speed, vibration method, and curing conditions, to ensure the controllability and quality of the construction process. The location information refers to the specific location of the construction site and the positioning data of each construction stage to ensure that the construction is carried out according to the planned location and sequence. The acquisition and use of construction information plays an important role in ensuring the accuracy and reliability of the temperature gradient test of the concrete structure, that is, to ensure the accuracy and comprehensiveness of the temperature gradient test by obtaining various aspects of construction information.

[0037] Step 2: Extract concrete features based on the construction information and establish a concrete feature set, which includes a structure feature set, a material feature set, a construction control feature set, and a location influence feature set.

[0038] Specifically, the features of concrete are extracted according to the construction information, and a concrete feature set is established. The concrete feature set includes a structural feature set, a material feature set, a construction control feature set, and a location influence feature set. The structural feature set refers to the data obtained by extracting features from the construction drawing information, such as the size, shape, and construction sequence of the concrete structure, which helps to analyze the structural stability and mechanical properties. The material feature set refers to the data obtained by extracting features from the construction material information, such as the type, proportion, and source of concrete materials, to ensure that the quality and performance of the materials meet the design requirements. The construction control feature set refers to the feature extraction data of the construction control information, such as the pouring speed, vibration method, and curing conditions, which have an important impact on the final quality and performance of the concrete. The location influence feature set refers to the feature extraction data of the location information, such as the specific location of the construction site and the positioning data of each construction stage, which helps to evaluate the impact of the external environment on the characteristics of the concrete. The establishment of the concrete feature set provides detailed data support for subsequent analysis and testing.

[0039] Step 3: Configure a reference segmentation block, perform grid segmentation of concrete according to the reference segmentation block, cluster and evaluate the temperature anomaly of the grid segmentation result through the concrete feature set, establish an associated clustering result, and distribute the optical fiber sensing line according to the associated clustering result.

[0040] Specifically, a reference segmentation block is configured, and the concrete is meshed according to the reference segmentation block. According to the geometric characteristics and construction requirements of the concrete structure, the concrete structure is divided into several areas, each of which is called a reference segmentation block, which is convenient for accurate monitoring and analysis. The reference segmentation block is used as the segmentation reference for mesh segmentation, and the concrete is meshed. Then, in the mesh segmentation process, the data in the concrete feature set is used to cluster and evaluate the temperature anomaly of each segmentation block. The temperature anomaly clustering evaluation is to identify the reference segmentation block with temperature anomaly by analyzing the temperature data of each reference segmentation block, and cluster them with the temperature data as the clustering standard, so as to better understand the temperature distribution law and abnormal conditions. The results of cluster analysis are associated with the reference segmentation block, and the associated clustering results are established to form a comprehensive temperature anomaly distribution map. Finally, the optical fiber sensing line is arranged according to the associated clustering results, and the temperature change is monitored and fed back in real time through the optical fiber sensing line to ensure the accuracy and real-time performance of temperature monitoring. Through mesh segmentation and clustering evaluation, combined with optical fiber sensing technology, accurate monitoring and analysis of concrete temperature distribution is achieved.

[0041] Step 4: Call the fiber optic spectrometer to read the Bragg wavelength of the fiber optic sensing circuit, perform wavelength change reading conversion, and establish the time-series temperature field of the concrete.

[0042] Specifically, the fiber optic spectrometer is called to read the Bragg wavelength of the fiber optic sensing line. The Bragg wavelength is a characteristic wavelength in the fiber Bragg grating, which changes with temperature. Therefore, the temperature change of concrete can be monitored by reading the Bragg wavelength. The fiber optic spectrometer can accurately measure the Bragg wavelength and convert the wavelength change into a specific temperature reading. In order to ensure the accuracy and real-time performance of the data, the reading conversion of the wavelength change is performed, and the measured wavelength change is accurately converted into a temperature value. The conversion process relies on a known relationship model between wavelength and temperature to ensure that the converted temperature reading accurately reflects the actual temperature inside the concrete. Further, the time-series temperature field of concrete is established. The time-series temperature field refers to the temperature distribution at various locations inside the concrete structure at different time points. By continuously reading and converting the Bragg wavelength, temperature data at different time points can be generated, thereby forming a dynamic temperature field, which can not only be used to monitor the temperature changes of concrete during construction and maintenance, but also help identify potential temperature anomalies and risks, and provide protection for structural safety.

[0043] Step 5: A grid association network is established based on the association clustering result, and the temperature gradient change authentication of the time series temperature field is performed through the grid association network to generate an association authentication result.

[0044] Specifically, a grid association network is established based on the association clustering results. The association clustering results are obtained by analyzing the clustering of temperature data, indicating the temperature relationship and mutual influence between different grids. Establishing a grid association network is to transform the clustering results into a systematic network model. The nodes in the network represent each grid, and the connections between the nodes represent the temperature correlation between the grids, thereby more clearly showing the mutual influence and correlation between the temperatures of each grid.

[0045] Step 6: Perform timing change analysis based on the timing temperature field and establish timing certification results.

[0046] Specifically, a time series change analysis is performed based on the time series temperature field. The time series temperature field contains the temperature data of each position of the concrete structure at different times, reflecting the temperature change trend over time. Time series change analysis is a systematic analysis of temperature data to identify the laws and patterns of temperature changes over time, which can help understand the thermal dynamic behavior of concrete in different time periods and evaluate the rationality and potential anomalies of its temperature changes. Establish a time series certification result. Through the analysis of the time series temperature field, the module can identify anomalies, mutation points or gradual trends in temperature changes. The time series certification results include a detailed description and evaluation of the changes, providing a comprehensive temperature change dynamic report, which not only helps to understand the causes of temperature changes, but also provides data support for preventing and responding to temperature anomalies.

[0047] Step 7: Generate a temperature warning based on the association authentication result and the timing authentication result.

[0048] Specifically, the temperature anomaly areas and severity in the associated authentication results are analyzed to show the temperature correlation and anomaly distribution between different grids, and to identify potential risk areas and abnormal patterns of temperature changes. Secondly, combined with the time series authentication results, the time variation characteristics of temperature anomalies are evaluated, including short-term mutations and long-term trends. Through time series data, the evolution of temperature anomalies is predicted to determine whether there is a risk of continued increase or sudden temperature anomalies. After a comprehensive analysis of the associated authentication results and the time series authentication results, a temperature warning is generated. The temperature warning includes specific abnormal areas, anomaly types, severity and possible development trends. The warning information details the location, time and potential impact of the temperature anomaly, helping users to take timely countermeasures to prevent the adverse effects of temperature anomalies on concrete structures.

[0049] The method for precisely testing the temperature gradient of a concrete structure is applied to a device for precisely testing the temperature gradient of a concrete structure, which can achieve the technical goal of precisely monitoring and analyzing the temperature gradient of the concrete structure in real time, thereby achieving the technical effect of improving the ability to detect temperature anomalies during construction, reducing construction risks, and improving the quality of concrete structures and construction efficiency.

[0050] Furthermore, the present application also includes:

[0051] Establishing a principal component recognition model; performing principal component recognition of concrete feature sets of each grid segmentation result through the principal component recognition model to establish recognition results; performing temperature anomaly clustering evaluation based on the recognition results to establish associated clustering results.

[0052] Specifically, the feature extraction module 12 is also responsible for establishing a principal component recognition model for analyzing and identifying the main components in the concrete feature set. The principal component recognition model is used to extract the principal components that can explain the maximum variation of the data by analyzing the variables in the concrete feature set, thereby simplifying the data structure and improving the analysis efficiency. After the principal component recognition model is established, the feature extraction module 12 uses the principal component recognition model to perform principal component recognition on the concrete feature set in each grid segmentation result. Principal component recognition can convert complex multidimensional feature data into a small number of principal components, retaining the most important information in the original data, and facilitating subsequent analysis.

[0053] Then, after the principal component is identified, the feature extraction module 12 will cluster and evaluate the temperature anomaly of the concrete according to the identification results. The temperature anomaly cluster evaluation uses the identified principal components to analyze the temperature data of each grid segmentation result, identify the temperature anomaly area, and cluster it, so as to better understand the law and anomaly of temperature distribution. Finally, the feature extraction module 12 establishes an associated clustering result, associates the results of the cluster analysis with the results of each grid segmentation, forms a comprehensive temperature anomaly distribution map, and accurately monitors and analyzes the temperature distribution and changes of the concrete.

[0054] By extracting key features through the principal component recognition model and combining it with clustering evaluation technology, accurate analysis and monitoring of concrete temperature anomalies can be achieved.

[0055] Furthermore, the present application also includes:

[0056] The preprocessing layer of the principal component recognition model is called, and the preprocessing layer is provided with a total proportion screening threshold of feature influence; the concrete feature sets of each grid segmentation result are sorted in order of feature influence, and the order sorting and screening of each grid segmentation result is screened by the total proportion screening threshold, and a sequential sorting and screening result is established; the unselected order result in the sequential sorting is obtained according to the sequential sorting and screening result, and the minimum feature influence deviation between the unselected order result and the sequential sorting and screening result is compared; the sequential sorting and screening result is reconstructed according to the deviation comparison result, and the reconstructed sequential sorting and screening result is output as the recognition result.

[0057] Specifically, the preprocessing layer of the principal component recognition model is called, and the preprocessing layer sets the total proportion screening threshold of the feature influence, which is used to screen the importance of the feature to ensure that the model only considers the features that have a significant impact on the grid segmentation results. First, the concrete feature sets in each grid segmentation result are sorted in order of feature influence, and sorted according to the influence of the features on the concrete performance or temperature distribution. The results of the sequential sorting are screened by the total proportion screening threshold, and only the grid segmentation results whose overall influence ratio is within the total proportion screening threshold range are retained, that is, the minimum number of grid segmentation results that can meet the total proportion screening threshold are screened to establish the sequential sorting screening results. For example, if the total proportion screening threshold is set to 60%, the sequential sorting screening results are A feature accounting for 30%, B feature accounting for 25%, C feature accounting for 15%, D feature accounting for 10%, E feature accounting for 8%, F feature accounting for 7%, G feature accounting for 5%, then the sequential sorting screening results are ABC.

[0058] Next, based on the results of the sequential sorting, the unselected results in the sequential sorting are further obtained. The unselected results are features with less impact but may still be meaningful. For example, if the total proportion screening threshold is set to 60%, the sequential sorting screening results are A feature accounting for 30%, B feature accounting for 25%, C feature accounting for 15%, D feature accounting for 10%, E feature accounting for 8%, F feature accounting for 7%, G feature accounting for 5%, then the unselected results are DEFG. Compare the unselected results with the minimum feature impact in the selected sequential sorting results, and evaluate whether the unselected results should be included in the final feature set through the deviation comparison results. For example, if the total proportion screening threshold is set to 60%, the sequential sorting screening results are A feature accounting for 30%, B feature accounting for 25%, C feature accounting for 15%, D feature accounting for 10%, E feature accounting for 8%, F feature accounting for 7%, G feature accounting for 5%, DEFG and C are compared respectively to obtain the deviation comparison results.

[0059] Next, the sequential sorting screening results are reconstructed according to the deviation comparison results, and the features that are important in the deviation comparison are re-incorporated into the final feature set. For example, if there is a mesh segmentation result in the unselected sequence results whose feature impact is greater than or equal to the minimum feature impact in the sequential sorting screening results, the unselected sequence results are added to the sequential sorting screening results, and the mesh segmentation results with the minimum feature impact in the sequential sorting screening results are removed or retained. The reconstructed sequential sorting screening results will be output as the recognition results to ensure that the recognition model can accurately reflect the key factors of concrete properties and temperature distribution.

[0060] The feature selection process of the principal component recognition model is optimized through feature influence sorting and screening, deviation comparison and result reconstruction, thereby improving the recognition accuracy and reliability of the model.

[0061] Furthermore, the present application also includes:

[0062] Generate a first transition incentive based on the deviation comparison result; obtain the feature influence value of the unselected priority result, and establish a second transition incentive based on the proportion of the feature influence value in the total feature influence value of the unreconstructed sequential sorting screening result; determine whether to be selected based on the first transition incentive and the second transition incentive; if the determination result is a passing result, reconstruct the sequential sorting screening result.

[0063] Specifically, a first transition stimulus is generated according to the deviation comparison result. The first transition stimulus is based on the evaluation of the comparison result and is intended to determine whether certain features need to be further considered.

[0064] Next, the feature impact values ​​of the unselected ranking results are obtained, that is, the specific impact values ​​of the features that were not selected in the preliminary screening. The second transition incentive is established based on the proportion of the feature impact values ​​of the unselected ranking results to the total feature impact value in the unreconstructed sequential sorting screening results. The second transition incentive is to evaluate the importance of the unselected features by calculating their proportion in the overall feature impact.

[0065] Then, according to the first transition stimulus and the second transition stimulus, it is judged whether the unselected feature is selected. The judgment process is to combine the results of the two transition stimuli to evaluate whether the unselected feature should be included in the final feature set. If the judgment result is passed, it means that the unselected feature that passed the judgment shows sufficient importance and influence in the judgment process, and then the reconstruction order is sorted and the screening results are performed.

[0066] Then, the reconstruction process adds the features that have passed the judgment back into the final feature set to ensure that the features that have passed the judgment are considered in the subsequent analysis and recognition process, thereby enabling the feature extraction module 12 to not only screen out the most important features, but also dynamically adjust and optimize the feature set to better reflect the actual situation of concrete properties and temperature distribution.

[0067] By distinguishing and adjusting the first transition excitation and the second transition excitation, the feature extraction module 12 can flexibly optimize the feature selection process and improve the accuracy and effectiveness of the principal component recognition model.

[0068] Furthermore, the present application also includes:

[0069] The association clustering result is divided into dynamic clustering results, and the grid association network is optimized with the dynamic clustering results; the temperature gradient change authentication of the time series temperature field is performed with the optimized grid association network, and the association authentication result is updated.

[0070] Specifically, segmenting the association clustering results into dynamic clustering results is the first step of the association authentication module 15. The dynamic clustering results are obtained by continuously analyzing and clustering the temperature data, and can reflect the temperature correlation that changes over time. Dynamic clustering can more accurately capture the changing trend and potential abnormalities of the temperature data.

[0071] Then, the grid association network is optimized based on the dynamic clustering results. The optimization process includes adjusting the structure and weight of the grid association network to better reflect the temperature correlation revealed by the dynamic clustering results. The grid association network can more effectively display the dynamic relationship of temperature changes and improve the accuracy and reliability of temperature gradient change authentication.

[0072] Next, the optimized grid association network is used to authenticate the temperature gradient change of the time series temperature field. The authentication process uses the optimized network structure to analyze and verify the temperature data at different times, and identify the gradient and abnormal conditions of temperature changes. Through the dynamic grid association network, the authentication process can more flexibly and accurately reflect the actual temperature changes.

[0073] Next, updating the associated authentication result is the final step of the associated authentication module 15. The updated associated authentication result includes the latest temperature gradient change and related authentication evaluation, which can not only provide real-time temperature change information, but also identify potential temperature anomalies, provide early warning and further analysis support.

[0074] By segmenting and optimizing the dynamic clustering results, the association authentication module can improve the accuracy of the grid association network and authenticate the temperature gradient changes through the optimized network, thereby updating and providing more accurate and reliable association authentication results.

[0075] Furthermore, the present application also includes:

[0076] The time series temperature field is evaluated for time series changes based on each grid segmentation result, and an adaptive long and short time series window is established; the long and short time series changes of the time series temperature field are analyzed through the adaptive long and short time series window, and a time series authentication result is established.

[0077] Specifically, the first step of the time series authentication module 16 is to evaluate the time series changes of the time series temperature field based on the results of each grid segmentation. Each grid segmentation result contains the temperature data in the grid at different times. By evaluating the changes in the data, the dynamic characteristics of the temperature over time can be identified. The time series change evaluation can reveal the temperature change pattern of each grid in the short and long term, and provide basic data for subsequent analysis.

[0078] Then, based on the results of the time series change evaluation, the adaptive long and short time series windows are established. The adaptive long and short time series windows are time windows that are dynamically adjusted according to the characteristics of temperature changes, and can flexibly capture short-term mutations and long-term trends. The adaptive window can more accurately adapt to the volatility and change patterns of temperature data, and improve the accuracy and sensitivity of the analysis.

[0079] Next, the long and short time series change analysis of the time series temperature field is performed through the adaptive long and short time series window. Long time series analysis focuses on identifying the long-term trend and change law of temperature, while short time series analysis focuses on capturing mutations and fluctuations in the short term. Combining the two analysis methods, we can fully understand the change of temperature over time, so as to more accurately identify anomalies and risks in temperature changes.

[0080] Next, establish the time series certification results. The time series certification results contain a detailed report of the long and short time series change analysis, including the trend of temperature change, mutation points, periodic characteristics, etc. The time series certification results can not only be used to monitor the health of concrete structures, but also provide a scientific basis for preventing temperature anomalies and formulating corresponding countermeasures.

[0081] By evaluating the timing changes of each grid segmentation result, establishing adaptive long and short timing windows, and analyzing the long and short timing changes, the timing authentication module 16 finally establishes detailed timing authentication results, providing important support for temperature change monitoring and anomaly identification.

[0082] Furthermore, the present application also includes:

[0083] A feedback management module is used to issue the temperature warning, create a feedback cycle based on the temperature warning, perform user processing feedback within the feedback cycle, and establish feedback verification data; an optimization module is used to perform warning processing evaluation based on the feedback verification data, generate an optimized data set through the warning processing evaluation, and feed back the optimized data set to the user.

[0084] Specifically, the feedback management module is used to issue temperature warnings and create a feedback cycle based on temperature warnings. After the temperature warning is issued, the feedback management module sets a specific feedback cycle during which users can process the warnings and provide feedback. The user's processing feedback includes confirmation of abnormal temperature conditions, response measures, and effect evaluation. Feedback verification data is established by collecting and organizing user processing feedback.

[0085] Then, the optimization module performs an early warning processing evaluation based on the feedback verification data. The early warning processing evaluation is to evaluate the processing measures and their effects reported by users, and determine the effectiveness and reliability of the measures in dealing with temperature anomalies. Through the early warning processing evaluation, the optimization module can identify the advantages and disadvantages of the processing process, and then generate an optimized data set. The optimized data set contains improvement suggestions and optimization measures, aiming to improve the efficiency and effectiveness of future temperature early warning processing. By providing the optimized data set to users, users can optimize their processing flow based on the suggestions and measures, and enhance their ability to respond to temperature anomalies. This can not only improve the overall performance of the temperature monitoring device, but also provide users with more targeted early warning processing strategies to ensure the safety and stability of concrete structures.

[0086] Through the circular feedback mechanism of temperature warning, feedback cycle, processing feedback, warning processing evaluation and optimization of data sets, the temperature monitoring and warning processing process is continuously improved and optimized, providing users with effective temperature anomaly management solutions.

[0087] In summary, the method for precise testing of temperature gradient of concrete structure provided by this application has the following technical effects:

[0088] The construction information of concrete is obtained according to digital communication, and the construction information includes construction drawing information, construction material information, construction control information and location information of concrete; the feature of concrete is extracted according to the construction information, and a concrete feature set is established, and the concrete feature set includes a structural feature set, a material feature set, a construction control feature set and a location influence feature set; a reference segmentation block is configured, and a grid segmentation of concrete is performed according to the reference segmentation block, and a temperature anomaly degree clustering evaluation of the grid segmentation result is performed through the concrete feature set, and an associated clustering result is established, and an optical fiber sensing line is distributed according to the associated clustering result; a fiber optic spectrometer is called to read the Bragg wavelength of the optical fiber sensing line, and a reading conversion of a wavelength change is performed to establish a time series temperature field of concrete; a grid associated clustering result is established based on the associated clustering result. A grid-associated network is connected, and the temperature gradient change authentication of the time-series temperature field is performed through the grid-associated network to generate an associated authentication result; a time-series change analysis is performed based on the time-series temperature field to establish a time-series authentication result; a temperature warning is generated according to the associated authentication result and the time-series authentication result, that is, concrete construction information is obtained through digital communication, features are extracted to establish a feature set, and fiber optic sensing technology and intelligent algorithms are used to perform grid segmentation, temperature monitoring and time-series analysis to generate a temperature warning, and the monitoring and warning process is optimized in combination with user feedback to achieve high-precision, real-time temperature gradient monitoring, and ultimately achieve the technical goal of accurate monitoring and real-time analysis of the temperature gradient of the concrete structure, so as to achieve the technical effect of improving the temperature anomaly detection capability during the construction process, reducing construction risks, and improving the quality of the concrete structure and construction efficiency.

[0089] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0090] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and 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 equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A precise testing device for temperature gradient of concrete structure, characterized in that: The concrete structure temperature gradient precision testing device digitally communicates with the concrete construction system, comprising: An interactive module, used for acquiring concrete construction information according to the digital communication, wherein the construction information includes concrete construction drawing information, construction material information, construction control information and location information; A feature extraction module, used to extract features of concrete according to the construction information and establish a concrete feature set, wherein the concrete feature set includes a structure feature set, a material feature set, a construction control feature set and a position influence feature set; A layout module is used to configure a reference segmentation block, perform grid segmentation of concrete according to the reference segmentation block, cluster and evaluate the temperature anomaly of the grid segmentation result through a concrete feature set, establish an associated clustering result, distribute the optical fiber sensing line according to the associated clustering result, and the associated clustering result is used to indicate the temperature relationship and mutual influence between different grids; A monitoring module, used to call a fiber optic spectrometer to read the Bragg wavelength of the fiber optic sensing circuit, perform reading conversion of wavelength changes, and establish a time-series temperature field of concrete; An association authentication module is used to establish a grid association network based on the association clustering result, and to perform temperature gradient change authentication of the time series temperature field through the grid association network to generate an association authentication result. The grid association network is a network model, and the nodes in the grid association network represent each grid, and the connection between the nodes represents the temperature correlation between the grids. The timing authentication module is used to analyze the timing changes based on the timing temperature field and establish the timing authentication results; A management module, used to generate a temperature warning according to the association authentication result and the timing authentication result; The feature extraction module is also used for: Establish principal component identification model; Perform principal component recognition of the concrete feature set of each grid segmentation result by using the principal component recognition model to establish a recognition result; Performing temperature anomaly degree clustering evaluation based on the recognition results and establishing associated clustering results; The association authentication module is also used for: dividing the association clustering result into dynamic clustering results, and optimizing the grid association network with the dynamic clustering results; Use the optimized grid association network to authenticate the temperature gradient change of the time series temperature field and update the association authentication result; The timing authentication module is also used for: Performing a time series change evaluation on the time series temperature field based on each grid segmentation result, and establishing an adaptive long and short time series window; The long and short time series variation analysis of the time series temperature field is performed through the adaptive long and short time series window to establish a time series authentication result.

2. A concrete structure temperature gradient precision testing device as claimed in claim 1, characterized in that: The method of performing principal component identification of the concrete feature set of each grid segmentation result by using the principal component identification model and establishing the identification result also includes: Calling a preprocessing layer of a principal component recognition model, wherein the preprocessing layer is provided with a total proportion screening threshold of feature influence; The concrete feature sets of each grid segmentation result are sorted in order of feature influence, and the order of each grid segmentation result is sorted and screened by the total proportion screening threshold to establish a sequential sorting screening result; Obtaining unselected priority results in the sequential sorting according to the sequential sorting screening results, and comparing the minimum feature impact deviations in the unselected priority results and the sequential sorting screening results; The sequential sorting and screening results are reconstructed according to the deviation comparison results, and the reconstructed sequential sorting and screening results are output as the recognition results.

3. A concrete structure temperature gradient precision testing device as claimed in claim 2, characterized in that: The reconstructing the order sorting and screening results according to the deviation comparison results also includes: generating a first transition stimulus according to the deviation comparison result; Acquire the feature influence value of the unselected ranking result, and establish a second transition incentive based on the proportion of the feature influence value to the total feature influence value of the unreconstructed sequence sorting screening result; Determining whether the first transition stimulus and the second transition stimulus are selected; If the judgment result is a passing result, the screening results are sorted in a reconstructed order.

4. A concrete structure temperature gradient precision testing device as claimed in claim 1, characterized in that: The concrete structure temperature gradient precision testing device also includes: A feedback management module, used to issue the temperature warning, create a feedback cycle according to the temperature warning, perform user processing feedback within the feedback cycle, and establish feedback verification data; The optimization module is used to perform early warning processing evaluation based on the feedback verification data, generate an optimized data set through the early warning processing evaluation, and feed back the optimized data set to the user.

5. A method for precise testing of temperature gradient of concrete structure, characterized in that: The method is implemented by a precise testing device for temperature gradient of concrete structure as claimed in any one of claims 1 to 4, comprising: Acquiring concrete construction information according to digital communication, wherein the construction information includes concrete construction drawing information, construction material information, construction control information and location information; Extracting features of concrete according to the construction information and establishing a concrete feature set, wherein the concrete feature set includes a structural feature set, a material feature set, a construction control feature set, and a location influence feature set; Configure a reference segmentation block, perform grid segmentation of concrete according to the reference segmentation block, perform clustering evaluation of temperature anomaly of the grid segmentation result through a concrete feature set, establish an associated clustering result, distribute the optical fiber sensing line according to the associated clustering result, and use the associated clustering result to indicate the temperature relationship and mutual influence between different grids; Calling a fiber optic spectrometer to read the Bragg wavelength of the fiber optic sensing circuit, performing a reading conversion of wavelength changes, and establishing a time-series temperature field of the concrete; A grid association network is established based on the association clustering result, and the temperature gradient change authentication of the time series temperature field is performed through the grid association network to generate an association authentication result. The grid association network is a network model, and the nodes in the grid association network represent each grid, and the connection between the nodes represents the temperature correlation between the grids; Perform timing change analysis based on the timing temperature field and establish timing certification results; Generate temperature warning based on the association authentication results and timing authentication results.

Images