Smart city construction consumable quality monitoring management system and method

Abstract

The invention provides a smart city construction consumable quality monitoring management system and method, and relates to the field of intelligent monitoring. The method comprises the following steps: firstly, respectively acquiring reinforcing steel bar tensile strength values and concrete compressive strength values of a building at a plurality of preset time points in a preset time period through a building reinforcing steel bar tensile strength detection device and a building concrete compressive strength detection device, and then carrying out time sequence analysis on the acquired strength time sequence data values; and finally, judging whether the quality of the construction consumables of the building is qualified or not based on the time sequence characteristics obtained through analysis. In this way, the construction consumables can be monitored more comprehensively and dynamically, and the accuracy and reliability of quality evaluation of the construction consumables can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring, and more specifically, to a system and method for monitoring and managing the quality of consumables for smart city construction. Background Art

[0002] In urban construction, the quality of building consumables is crucial to the safety of buildings. Traditional quality monitoring may simply sample and test building consumables, which cannot fully and dynamically reflect the quality changes of materials throughout the construction process. Specifically, the construction process is a dynamic process, and the quality characteristics of building consumables will also change with factors such as construction progress and environment. If quality problems of construction consumables are not discovered in time, it will lead to hidden dangers in subsequent construction or quality defects in the built parts.

[0003] Therefore, a quality monitoring and management solution for consumables in smart city construction is needed. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present application provides a smart city construction consumables quality monitoring management system and method.

[0005] A smart city construction consumables quality monitoring and management system, comprising: The building construction consumables data acquisition module is used to obtain the steel bar tensile strength value and concrete compressive strength value of the building at multiple predetermined time points within a predetermined time period through the building steel bar tensile strength detection device and the building concrete compressive strength detection device; A building construction consumables data sorting module, used for sorting the steel bar tensile strength values ​​and concrete compressive strength values ​​at the plurality of predetermined time points to obtain a full time series input matrix of construction consumables quality monitoring parameters; A building construction consumables data analysis module, used for performing data encoding on the full time series input matrix of the construction consumables quality monitoring parameters to obtain a full time series fusion feature vector of the construction consumables quality monitoring parameters; The building construction consumables quality result generation module is used to determine whether the quality of the building's construction consumables is qualified based on the information in the full time series fusion feature vector of the construction consumables quality monitoring parameters.

[0006] A method for monitoring and managing the quality of consumables for smart city construction, comprising: The tensile strength test device for building steel bars and the compressive strength test device for building concrete are used to respectively obtain the tensile strength values ​​of steel bars and the compressive strength values ​​of concrete at multiple predetermined time points within a predetermined time period; Arranging data of the steel bar tensile strength values ​​and concrete compressive strength values ​​at the plurality of predetermined time points to obtain a full time series input matrix of construction consumables quality monitoring parameters; Data encoding is performed on the full time series input matrix of the construction consumables quality monitoring parameters to obtain a full time series fusion feature vector of the construction consumables quality monitoring parameters; Whether the quality of the construction consumables of the building is qualified is judged according to the information in the full time series fusion feature vector of the construction consumables quality monitoring parameters.

[0007] This application has significant technical effects due to the adoption of the above technical solutions: The smart city construction consumables quality monitoring management system and method provided by the present application first obtains the steel bar tensile strength value and concrete compressive strength value of the building at multiple predetermined time points in a predetermined time period through a building steel bar tensile strength detection device and a building concrete compressive strength detection device, then performs a time series analysis on these acquired strength time series data values, and finally judges whether the quality of the building's construction consumables is qualified based on the analyzed time series characteristics. In this way, construction consumables can be monitored more comprehensively and dynamically, which is conducive to improving the accuracy and reliability of construction consumables quality assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The various embodiments will be easily understood by the following detailed description in conjunction with the accompanying drawings. For ease of description, the same reference numerals indicate the same structural elements. The various embodiments are illustrated in the figures of the accompanying drawings by way of example and not limitation.

[0009] Figure 1 This is a system block diagram of a smart city construction consumables quality monitoring and management system according to an embodiment of the present application.

[0010] Figure 2 This is a block diagram of a building construction consumables data analysis module in a smart city construction consumables quality monitoring and management system according to an embodiment of the present application.

[0011] Figure 3 This is a block diagram of a building construction consumables quality result generation module in a smart city construction consumables quality monitoring and management system according to an embodiment of the present application.

[0012] Figure 4 This is a flow chart of a method for monitoring and managing the quality of consumables for smart city construction according to an embodiment of the present application.

[0013] Figure 5 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0015] Based on the problems in the above-mentioned background technology, this application proposes a smart city construction consumables quality monitoring and management system. Figure 1 : is a system block diagram of the smart city construction consumables quality monitoring and management system according to an embodiment of the present application. Figure 1 As shown, in the smart city construction consumables quality monitoring and management system 100, it includes: a building construction consumables data acquisition module 110, which is used to obtain the steel bar tensile strength value and concrete compressive strength value of the building at multiple predetermined time points within a predetermined time period through a building steel bar tensile strength detection device and a building concrete compressive strength detection device; a building construction consumables data sorting module 120, which is used to sort the steel bar tensile strength value and concrete compressive strength value at the multiple predetermined time points to obtain a full time series input matrix of construction consumables quality monitoring parameters; a building construction consumables data analysis module 130, which is used to encode the full time series input matrix of the construction consumables quality monitoring parameters to obtain a full time series fusion feature vector of the construction consumables quality monitoring parameters; a building construction consumables quality result generation module 140, which is used to judge whether the quality of the construction consumables of the building is qualified according to the information in the full time series fusion feature vector of the construction consumables quality monitoring parameters.

[0016] In the embodiment of the present application, the building construction consumables data acquisition module 110 is used to obtain the steel bar tensile strength value and concrete compressive strength value of the building at multiple predetermined time points in a predetermined time period through the building steel bar tensile strength detection device and the building concrete compressive detection device. It should be understood that the steel bar tensile strength value itself represents the ability of the steel bar, a building material, to resist tensile force without being damaged. The value obtained at different predetermined time points can intuitively reflect the quality status of the steel bar at the corresponding time. For example, if the tensile strength value meets the requirements of the corresponding standard specifications, it means that the steel bar has sufficient tensile bearing capacity at this time point, and its material, processing technology and other comprehensive factors make its strength performance within the qualified range; on the contrary, if the value is low, it may imply that the steel bar has quality defects, such as poor quality of raw materials, heat treatment in the production process and other links that do not meet the standards. Specifically, as the construction progresses, the environment experienced by the steel bar and the load conditions it bears are different at different time points. For example, in the foundation construction stage, when the steel bars are just being laid, the tensile strength value at this time reflects the performance of the steel bars in the initial state under the foundation environment. In the main structure construction stage, as the building height increases and the structural stress changes, the tensile force on the steel bars also changes. The tensile strength value at the corresponding time point can show the performance changes after the combined effects of long-term stress, different construction operations (such as binding, welding, etc.) and the surrounding environment (such as rust caused by humidity). The compressive strength value of concrete is a key indicator to measure its ability to withstand pressure. Its value depends first on the mix ratio of concrete, including whether the proportion of each component such as cement, sand and gravel, water and admixtures is reasonable. The compressive strength values ​​obtained at each predetermined time point can reflect the quality of concrete from the initial hardening stage after pouring to the subsequent gradual reaching of the design strength. For example, under normal maintenance conditions, the compressive strength value of concrete configured according to the standard mix ratio will steadily increase over time and reach the specified design strength requirements; if the strength value increases slowly or does not reach the expected value, it may mean that the mix ratio is inaccurate, the quality of the raw materials is problematic, or the maintenance measures are not in place. In general, obtaining two time series data, namely the tensile strength of steel bars and the compressive strength of concrete, can comprehensively and dynamically record the changes in the quality characteristics of materials throughout the construction process, fundamentally making up for the defect that traditional monitoring methods cannot reflect quality changes in real time and continuously. This can more accurately grasp the quality of building materials and thus achieve early warning of quality problems of building materials.

[0017] In an embodiment of the present application, the building construction consumables data sorting module 120 is used to sort the steel bar tensile strength values ​​and concrete compressive strength values ​​at the multiple predetermined time points to obtain a full time series input matrix of construction consumables quality monitoring parameters. Specifically, in an embodiment of the present application, the building construction consumables data sorting module is used to: arrange the steel bar tensile strength values ​​and concrete compressive strength values ​​at the multiple predetermined time points according to the time dimension to obtain the full time series input matrix of the construction consumables quality monitoring parameters. It should be understood that in urban construction, the quality of building materials is not fixed, but is constantly changing with various factors such as construction progress and environment. Arranging the steel bar tensile strength values ​​and concrete compressive strength values ​​at multiple predetermined time points according to the time dimension can clearly show the changing trajectory of the quality characteristics of these building consumables over time. For example, from the initial construction stage to the main structure construction, and then to the subsequent decoration and renovation stage and other different time stages, the working conditions faced by steel bars and concrete are different, and their quality indicators such as strength will also change accordingly. This dynamic change can be intuitively captured through the time dimension arrangement, which helps to fully understand the quality evolution process of the material throughout the construction cycle. And after arranging the data in chronological order, it is more in line with the logical requirements of data processing and analysis, and it is convenient to use various data analysis methods to mine the quality-related information contained therein. Each row of data in the arranged full-time input matrix of construction consumables quality monitoring parameters represents the construction consumables quality monitoring parameter information obtained at a specific predetermined time point, and each column of data often corresponds to a specific construction consumables quality monitoring parameter category.

[0018] In the embodiment of the present application, the building construction consumables data analysis module 130 is used to perform data encoding on the full time series input matrix of the construction consumables quality monitoring parameters to obtain the full time series fusion feature vector of the construction consumables quality monitoring parameters. Specifically, Figure 2 FIG. 1 is a block diagram of a building construction consumables data analysis module in a smart city construction consumables quality monitoring and management system according to an embodiment of the present application. Figure 2As shown, the building construction consumables data analysis module 130 includes: a construction consumables quality monitoring parameter full time series feature generation unit 131, which is used to extract the time series features of the construction consumables quality monitoring parameter full time series input matrix to obtain the construction consumables quality monitoring parameter full time series feature matrix; a construction consumables quality monitoring parameter full time series feature dimension reduction unit 132, which is used to expand the construction consumables quality monitoring parameter full time series feature matrix to obtain the construction consumables quality monitoring parameter full time series feature vector; a construction consumables quality monitoring parameter full time series emphasis feature generation unit 133, which is used to extract the time series features of the construction consumables quality monitoring parameter full time series feature matrix to obtain the construction consumables quality monitoring parameter full time series feature vector; The full-time-series feature matrix is ​​used for feature screening to obtain the full-time-series emphasis feature matrix of the quality monitoring parameters of construction consumables; the full-time-series emphasis feature dimension reduction unit 134 of the quality monitoring parameters of construction consumables is used to expand the full-time-series emphasis feature matrix of the quality monitoring parameters of construction consumables to obtain the full-time-series emphasis feature vector of the quality monitoring parameters of construction consumables; the full-time-series fusion feature generation unit 135 of the quality monitoring parameters of construction consumables is used to fuse the full-time-series feature vector of the quality monitoring parameters of construction consumables and the full-time-series emphasis feature vector of the quality monitoring parameters of construction consumables to obtain the full-time-series fusion feature vector of the quality monitoring parameters of construction consumables.

[0019] In the embodiment of the present application, the construction consumables quality monitoring parameter full time series feature generation unit 131 is used to extract the time series features of the construction consumables quality monitoring parameter full time series input matrix to obtain the construction consumables quality monitoring parameter full time series feature matrix. Specifically, in the embodiment of the present application, the construction consumables quality monitoring parameter full time series feature generation unit is used to: pass the construction consumables quality monitoring parameter full time series input matrix through the construction consumables quality monitoring parameter change attention device to obtain the construction consumables quality monitoring parameter full time series feature matrix. It should be understood that the construction consumables quality monitoring parameter full time series input matrix contains a large amount of original data such as the tensile strength value of steel bars and the compressive strength value of concrete at multiple predetermined time points. Although these data fully record the changes in the quality of construction consumables over time, the amount of data is large and relatively complicated, and contains a lot of redundant information. In order to extract the most critical and representative information for judging the quality of construction consumables from these complicated data, such as reflecting the key features such as the quality change trend and abnormal fluctuation points of these two construction consumables, it is necessary to perform time series feature extraction processing on the construction consumables quality monitoring parameter full time series input matrix. The specific method is to input this matrix into the construction consumables quality monitoring parameter change observer. In this application, the construction consumables quality monitoring parameter change observer specifically refers to a convolutional neural network model using a two-dimensional convolution kernel. In detail, when processing matrix data, the two-dimensional convolution kernel can focus on local areas for feature perception, and by performing convolution operations on the entire matrix through sliding convolution kernels, the associations and features between local data can be captured. Moreover, with the stacking of convolution layers, local features at different levels can be further fused to form more abstract and representative global features. For situations such as construction consumables quality monitoring that require comprehensive consideration of the relationship between different time points and different material quality parameters, this local to global feature fusion capability can better mine the quality-related information contained in the data.

[0020] In an embodiment of the present application, the full-time feature dimension reduction unit 132 of the construction consumables quality monitoring parameter is used to expand the full-time feature matrix of the construction consumables quality monitoring parameter to obtain the full-time feature vector of the construction consumables quality monitoring parameter. Accordingly, considering that the feature matrix has been extracted and the key information related to the quality of construction consumables has been extracted, when it exists in the form of a matrix, the structure of the data is relatively scattered, and each element is distributed in different row and column positions. Through the expansion operation, these feature information originally organized in the form of a matrix can be integrated into a one-dimensional vector, making the data representation more concise and clear. This helps to grasp all the key features extracted from the feature matrix as a whole, and avoids difficulties in data understanding and processing due to the complexity of the matrix structure in the subsequent processing process.

[0021] In the embodiment of the present application, the construction consumables quality monitoring parameter full time series emphasized feature generation unit 133 is used to perform feature screening on the construction consumables quality monitoring parameter full time series emphasized feature matrix to obtain the construction consumables quality monitoring parameter full time series emphasized feature matrix. Specifically, in the embodiment of the present application, the construction consumables quality monitoring parameter full time series emphasized feature generation unit is used to: pass the construction consumables quality monitoring parameter full time series emphasized feature matrix through the construction consumables quality monitoring parameter change emphasizer to obtain the construction consumables quality monitoring parameter full time series emphasized feature matrix. It should be understood that although the construction consumables quality monitoring parameter full time series emphasized feature matrix obtained by the previous data processing contains a lot of characteristic information related to the quality of construction consumables extracted from the original data, these characteristics are not all equally important in judging whether the quality of construction consumables is qualified. Some features may only reflect some minor changes that have little impact on the overall quality, and there are some key features that are directly related to the core elements of quality qualification, such as abnormal changes in material strength and unreasonable correlations between quality parameters. Feature screening of the original feature matrix is ​​to focus on these key features and remove redundant or interfering information, so as to make the subsequent quality judgment based on the features more accurate and improve the accuracy and reliability of the judgment. Specifically, the feature screening method is to input the full time series feature matrix of the construction consumables quality monitoring parameters into the construction consumables quality monitoring parameter change emphasizer. Here, the construction consumables quality monitoring parameter change emphasizer specifically refers to a convolutional neural network model using a spatial attention mechanism. This structure automatically assigns corresponding importance weights to different features by learning on a large amount of training data (such as construction consumables quality monitoring data under different quality conditions). Those features with higher weights are more critical to judging quality. This automatic learning method is more flexible and accurate than the traditional method of relying on experience or fixed formulas to screen features, and can adapt to the changing importance of features in complex and changeable construction consumables quality monitoring scenarios. For example, in the early stages of a building's construction, certain features related to the initial performance of basic materials may be the focus of attention; while in the main structure construction stage, quality features related to structural stress will be given a higher weight. Through this dynamic attention method, the most valuable features for judging the quality of construction consumables in each specific stage can be accurately screened out, thereby adapting to the actual needs of different stages in the quality monitoring process in real time.

[0022] In an embodiment of the present application, the construction consumables quality monitoring parameter full time series emphasized feature dimension reduction unit 134 is used to expand the construction consumables quality monitoring parameter full time series emphasized feature matrix to obtain the construction consumables quality monitoring parameter full time series emphasized feature vector. Similarly, from a computational point of view, data in vector form is usually more efficient than matrix form in terms of computer memory access, operation logic implementation, etc. By expanding the construction consumables quality monitoring parameter full time series emphasized feature matrix into a vector, the processing efficiency of the model data can be improved, especially when processing a large amount of construction consumables quality monitoring data, this efficiency improvement effect will be more significant.

[0023] In an embodiment of the present application, the full-time fusion feature generation unit 135 of the construction consumables quality monitoring parameter is used to fuse the full-time feature vector of the construction consumables quality monitoring parameter and the full-time emphasis feature vector of the construction consumables quality monitoring parameter to obtain the full-time fusion feature vector of the construction consumables quality monitoring parameter. It should be understood that the full-time feature vector of the construction consumables quality monitoring parameter and the full-time emphasis feature vector respectively carry key information related to the quality of construction consumables extracted from different angles. The full-time feature vector is obtained by extracting features from the original full-time input matrix of quality monitoring parameters. It contains general important feature information such as the trend of changes in the quality of construction consumables and the correlation between various quality parameters mined from the basic data. The full-time emphasis feature vector is obtained after feature screening, focusing on highlighting those features that play a key role in judging quality, have important correlations in spatial dimensions, etc., and can reflect the importance of key stages of quality changes. The fusion of these two vectors can integrate the key information mined from different dimensions and focuses to form a more comprehensive and integrated quality feature representation, avoiding the problem of incomplete quality judgment caused by the limited information of a single vector.

[0024] In the embodiment of the present application, the building construction consumables quality result generation module 140 is used to determine whether the quality of the building construction consumables is qualified according to the information in the full time series fusion feature vector of the construction consumables quality monitoring parameters. Specifically, Figure 3 FIG. 1 is a block diagram of a building construction consumables quality result generation module in a smart city construction consumables quality monitoring and management system according to an embodiment of the present application. Figure 3As shown, the building construction consumables quality result generation module 140 includes: a construction consumables quality monitoring parameter feature optimization unit 141, which is used to interactively explore the full-time fusion feature vector of the construction consumables quality monitoring parameters based on the characteristic intrinsic connection mode to obtain an optimized full-time fusion feature vector of the construction consumables quality monitoring parameters; a construction consumables quality monitoring parameter feature classification unit 142, which is used to pass the optimized full-time fusion feature vector of the construction consumables quality monitoring parameters through a quality detection classifier to obtain a classification result, and the classification result is used to indicate whether the quality of the building's construction consumables is qualified.

[0025] In an embodiment of the present application, the construction consumables quality monitoring parameter feature optimization unit 141 is used to perform interactive exploration based on the characteristic intrinsic connection mode revelation of the full time series fusion feature vector of the construction consumables quality monitoring parameters to obtain an optimized full time series fusion feature vector of the construction consumables quality monitoring parameters. In particular, considering that the original data includes the tensile strength value of the steel bar and the compressive strength value of the concrete, these data may be affected by various factors (such as environmental conditions, equipment errors, etc.) during the collection process, resulting in the presence of noise or outliers in the data. This will further lead to the presence of noise in the full time series fusion feature vector of the construction consumables quality monitoring parameters obtained by extracting the original data, which in turn makes it difficult for the quality detection classifier to capture the main characteristics of the data, thereby reducing the quality classifier's ability to identify unqualified consumables. Therefore, in the technical solution of the present application, it is necessary to perform interactive exploration based on the characteristic intrinsic connection mode revelation of the full time series fusion feature vector of the construction consumables quality monitoring parameters to obtain an optimized full time series fusion feature vector of the construction consumables quality monitoring parameters.

[0026] Specifically, in an embodiment of the present application, the construction consumables quality monitoring parameter feature optimization unit is used to: extract the target construction consumables quality classification parameter matrix of the quality detection classifier; perform node-based decomposition of the target construction consumables quality classification parameter matrix in units of row vectors to obtain a set of target construction consumables quality classification parameter node encoding vectors; use each target construction consumables quality classification parameter node encoding vector in the set of target construction consumables quality classification parameter node encoding vectors as the wandering topological space, and perform topological spatial constraints on the full time series fusion feature vectors of the construction consumables quality monitoring parameters respectively to obtain a set of constrained full time series fusion feature vectors of the construction consumables quality monitoring parameters; calculate the positional mean vector of the set of the constrained full time series fusion feature vectors of the construction consumables quality monitoring parameters to obtain the optimized full time series fusion feature vector of the construction consumables quality monitoring parameters.

[0027] More specifically, in an embodiment of the present application, each target construction consumables quality classification parameter node encoding vector in the set of the target construction consumables quality classification parameter node encoding vector is used as a wandering topological space, and the full time series fusion feature vector of the construction consumables quality monitoring parameter is topologically constrained to obtain a set of constrained construction consumables quality monitoring parameter full time series fusion feature vectors, including: multiplying the full time series fusion feature vector of the construction consumables quality monitoring parameter and the transposed vector of the target construction consumables quality classification parameter node encoding vector, and calculating the natural exponential function value of the multiplication result to obtain the construction consumables quality classification weighted exponential response weight; calculating the construction consumables quality monitoring parameter full time series fusion feature vector and the transposed vector of the target construction consumables quality classification parameter node encoding vector. Assume the Euclidean distance between the full time series fusion feature vector of consumables quality monitoring parameters and the target construction consumables quality classification parameter node coding vector to obtain the construction consumables quality classification node coding distance value; perform point multiplication on the construction consumables quality classification node coding distance value and the full time series fusion feature vector of the construction consumables quality monitoring parameters, and calculate the natural exponential function value for each eigenvalue of the vector after the point multiplication to obtain the construction consumables quality classification distance guidance index feature vector; perform point multiplication on the construction consumables quality classification weighted index response weight and the construction consumables quality classification distance guidance index feature vector to obtain the full time series fusion feature vector of the constrained construction consumables quality monitoring parameters.

[0028] In the embodiment of the present application, specifically, the construction consumables quality monitoring parameter feature optimization unit is used to: process the construction consumables quality monitoring parameter full time series fusion feature vector using the following optimization formula to obtain the optimized construction consumables quality monitoring parameter full time series fusion feature vector; wherein the optimization formula is: ;in, represents the target construction consumables quality classification parameter matrix, The first, second, and third nodes of the set of target construction consumables quality classification parameter node encoding vectors are represented , The target construction consumables quality classification parameter node encoding vector, represents the transpose of a vector, represents the natural exponential function, Represents the full time series fusion feature vector of construction consumables quality monitoring parameters, represents matrix multiplication, It means point multiplication by position. Represents the calculation vector and vector The Euclidean distance between The first one represents the set of all-time series fusion feature vectors of the quality monitoring parameters of construction consumables after constraints. After the constraints are set, the full time series fusion feature vector of the consumables quality monitoring parameters is constructed. Represents the total number of sets of full-time fusion feature vectors of quality monitoring parameters of construction consumables after constraints, Represents the full time series fusion feature vector of optimized construction consumables quality monitoring parameters.

[0029] That is, in response to the above technical problems, in the technical solution of the present application, the full time series fusion feature vector of the construction consumables quality monitoring parameters is interactively explored based on the revelation of the intrinsic connection pattern of the features. The process first extracts the key parameters for decision-making from the trained quality inspection classifier. These parameters form a matrix in a high-dimensional space, and each row represents the weight or influencing factor on a different dimension. The target construction consumables quality classification parameter matrix can provide insight into the location and shape of the model decision boundary, and then infer which input features are most critical to the prediction results.

[0030] Next, the target construction consumables quality classification parameter matrix is ​​node-decomposed in units of row vectors to obtain a set of node encoding vectors of target construction consumables quality classification parameters. Here, each row vector is a node in graph theory, which means that each set of parameters is now regarded as an entity with potential connectivity. This transformation allows the application of methods from graph theory and network science to explore the interactions between features. The node encoding vector not only carries information about the original parameters, but also implies knowledge about the topological structure of the entire system. Node decomposition further reveals the intrinsic connection pattern or structure of the data, so that the optimized feature vector can better adapt to new task requirements.

[0031] Then, each target construction consumables quality classification parameter node encoding vector in the set of the target construction consumables quality classification parameter node encoding vector is used as the walking topological space, and the full time series fusion feature vector of the construction consumables quality monitoring parameter is respectively subjected to topological space constraints to obtain a set of full time series fusion feature vectors of the construction consumables quality monitoring parameter after constraints. "Walking" in the topological space defined by the node encoding vector is actually simulating an exploratory process, the purpose of which is to find those feature transformations that can best maintain the characteristics of the original data structure. Each step determines the position of the next step based on the probability distribution of the current state. The topological space constraints ensure that even in different contexts, the feature representation still retains certain invariances. At the same time, it can also promote cross-domain transfer learning because it emphasizes the universal relationship between features rather than the details of a specific field. In this way, the reconstruction of the feature space is achieved, making the optimized feature vector more compact and having better generalization ability.

[0032] Finally, the positional mean vector of the set of the constrained full-time series fusion feature vectors of the quality monitoring parameters of construction consumables is calculated to obtain the optimized full-time series fusion feature vector of the quality monitoring parameters of construction consumables. Calculating the mean vector is a statistical aggregation method used to integrate the optimal solution from multiple perspectives. The idea behind this step is to reduce the deviation caused by a single estimate by fusing the information provided by different sample points. The averaging process is equivalent to performing a soft voting, which enhances the expressiveness of common features and makes the optimized feature vector more stable and reliable.

[0033] In the embodiment of the present application, the construction consumables quality monitoring parameter feature classification unit 142 is used to pass the optimized construction consumables quality monitoring parameter full time series fusion feature vector through the quality detection classifier to obtain a classification result, and the classification result is used to indicate whether the quality of the construction consumables of the building is qualified. It should be understood that the optimized construction consumables quality monitoring parameter full time series fusion feature vector obtained by data processing of different modules is a feature representation in a high-dimensional space. In order to realize the qualitative judgment of the quality of construction consumables based on the feature information in this vector, it is necessary to input the optimized construction consumables quality monitoring parameter full time series fusion feature vector into the quality detection classifier. The quality detection classifier can be trained and learned on a large number of labeled (known quality qualified or not) sample data to master the correspondence between these feature patterns and quality classification results. Then, when the new optimized full time series fusion feature vector of the building to be detected is input, it can accurately judge whether the quality of the construction consumables of the building belongs to the qualified or unqualified category based on the learned pattern recognition ability, so as to give full play to its advantages in processing complex feature data and making classification decisions, and assist in completing high-quality quality monitoring work. The classification result clearly indicates whether the quality of the building's construction consumables is qualified, which is the core output information of the entire quality monitoring and management work. For relevant entities such as construction units, construction units, and regulatory departments, this result can be directly used to determine whether the quality of the consumables used in the current construction project meets the requirements. If the classification result shows that it is qualified, the project construction can continue according to the normal construction process; if the result is unqualified, it is necessary to take corresponding corrective measures immediately, such as replacing unqualified construction consumables, troubleshooting construction process problems, etc., thereby providing a key basis for subsequent construction decisions to ensure the quality and safety of the construction project.

[0034] In summary, the smart city construction consumables quality monitoring and management system 100 based on the embodiment of the present application is explained, which first obtains the steel bar tensile strength value and concrete compressive strength value of the building at multiple predetermined time points in a predetermined time period through the building steel bar tensile strength detection device and the building concrete compressive strength detection device, and then performs time series analysis on these acquired strength time series data values, and finally judges whether the quality of the building's construction consumables is qualified based on the analyzed time series characteristics. In this way, construction consumables can be monitored more comprehensively and dynamically, which is conducive to improving the accuracy and reliability of construction consumables quality assessment.

[0035] Figure 4 Flow chart of the method for monitoring and managing the quality of consumables for smart city construction according to an embodiment of the present application. Figure 4 As shown, in the smart city construction consumables quality monitoring and management method, it includes: S1, respectively obtaining the steel bar tensile strength value and concrete compressive strength value of the building at multiple predetermined time points within a predetermined time period through a building steel bar tensile strength detection device and a building concrete compressive strength detection device; S2, sorting the steel bar tensile strength value and concrete compressive strength value at the multiple predetermined time points to obtain a full time series input matrix of construction consumables quality monitoring parameters; S3, data encoding the full time series input matrix of construction consumables quality monitoring parameters to obtain a full time series fusion feature vector of construction consumables quality monitoring parameters; S4, judging whether the quality of the construction consumables of the building is qualified according to the information in the full time series fusion feature vector of the construction consumables quality monitoring parameters.

[0036] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned smart city construction consumables quality monitoring and management method have been referenced above. Figures 1 to 3 The description of the smart city construction consumables quality monitoring and management system has been introduced in detail, and therefore, its repeated description will be omitted.

[0037] In summary, the quality monitoring and management method of smart city construction consumables based on the embodiment of the present application is explained. First, the tensile strength detection device of the building steel bar and the compressive strength detection device of the building concrete are used to obtain the tensile strength value of the steel bar and the compressive strength value of the concrete at multiple predetermined time points in a predetermined time period, and then the obtained strength time series data values ​​are analyzed in time series, and finally the quality of the building's construction consumables is judged based on the analyzed time series characteristics. In this way, the construction consumables can be monitored more comprehensively and dynamically, which is conducive to improving the accuracy and reliability of the quality assessment of the construction consumables.

[0038] Below, reference Figure 5 To describe an electronic device according to an embodiment of the present application. Figure 5 FIG. 1 is a block diagram of an electronic device according to an embodiment of the present application. Figure 5As shown, the electronic device may include: a processor 11, a communication interface 12, a memory 13 and a communication bus 14, wherein the processor 11, the communication interface 12 and the memory 13 communicate with each other through the communication bus 14. The processor 11 may call the logic instructions in the memory 13 to execute the above-mentioned smart city construction consumables quality monitoring and management method.

[0039] In addition, the logic instructions in the above-mentioned memory 13 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

Claims

1. A smart city construction consumables quality monitoring and management system, characterized in that: include: The building construction consumables data acquisition module is used to obtain the steel bar tensile strength value and concrete compressive strength value of the building at multiple predetermined time points within a predetermined time period through the building steel bar tensile strength detection device and the building concrete compressive strength detection device; A building construction consumables data sorting module, used for sorting the steel bar tensile strength values ​​and concrete compressive strength values ​​at the plurality of predetermined time points to obtain a full time series input matrix of construction consumables quality monitoring parameters; A building construction consumables data analysis module, used for performing data encoding on the full time series input matrix of the construction consumables quality monitoring parameters to obtain a full time series fusion feature vector of the construction consumables quality monitoring parameters; The building construction consumables quality result generation module is used to determine whether the quality of the building's construction consumables is qualified based on the information in the full time series fusion feature vector of the construction consumables quality monitoring parameters.

2. The smart city construction consumables quality monitoring and management system according to claim 1 is characterized in that: The building construction consumables data sorting module is used to: arrange the steel bar tensile strength values ​​and concrete compressive strength values ​​at the plurality of predetermined time points according to the time dimension to obtain the full time series input matrix of the construction consumables quality monitoring parameters.

3. The smart city construction consumables quality monitoring and management system according to claim 2 is characterized in that: The building construction consumables data analysis module includes: A construction consumables quality monitoring parameter full time series feature generation unit, used for extracting time series features from the construction consumables quality monitoring parameter full time series input matrix to obtain a construction consumables quality monitoring parameter full time series feature matrix; A full-time series feature dimension reduction unit for construction consumables quality monitoring parameters, used for expanding the full-time series feature matrix of construction consumables quality monitoring parameters to obtain a full-time series feature vector of construction consumables quality monitoring parameters; A construction consumables quality monitoring parameter full time series emphasized feature generation unit, used for performing feature screening on the construction consumables quality monitoring parameter full time series emphasized feature matrix to obtain the construction consumables quality monitoring parameter full time series emphasized feature matrix; A construction consumables quality monitoring parameter full time series emphasized feature dimension reduction unit, used for expanding the construction consumables quality monitoring parameter full time series emphasized feature matrix to obtain a construction consumables quality monitoring parameter full time series emphasized feature vector; The construction consumables quality monitoring parameter full time series fusion feature generation unit is used to fuse the construction consumables quality monitoring parameter full time series feature vector and the construction consumables quality monitoring parameter full time series emphasis feature vector to obtain the construction consumables quality monitoring parameter full time series fusion feature vector.

4. The smart city construction consumables quality monitoring and management system according to claim 3 is characterized in that: The construction consumables quality monitoring parameter full time series feature generation unit is used to: pass the construction consumables quality monitoring parameter full time series input matrix through the construction consumables quality monitoring parameter change observer to obtain the construction consumables quality monitoring parameter full time series feature matrix.

5. The smart city construction consumables quality monitoring and management system according to claim 4 is characterized in that: The construction consumables quality monitoring parameter full time series emphasized feature generation unit is used to: pass the construction consumables quality monitoring parameter full time series emphasized feature matrix through the construction consumables quality monitoring parameter change emphasizer to obtain the construction consumables quality monitoring parameter full time series emphasized feature matrix.

6. The smart city construction consumables quality monitoring and management system according to claim 5, characterized in that: The construction consumables quality monitoring parameter change attention device is a convolutional neural network model using a two-dimensional convolution kernel, and the construction consumables quality monitoring parameter change emphasizer is a convolutional neural network model using a spatial attention mechanism.

7. The smart city construction consumables quality monitoring and management system according to claim 6, characterized in that: The building construction consumables quality result generation module includes: A construction consumables quality monitoring parameter feature optimization unit, used for interactively exploring the construction consumables quality monitoring parameter full time series fusion feature vector based on the characteristic intrinsic connection mode to obtain an optimized construction consumables quality monitoring parameter full time series fusion feature vector; The construction consumables quality monitoring parameter feature classification unit is used to pass the optimized construction consumables quality monitoring parameter full time series fusion feature vector through the quality detection classifier to obtain a classification result, and the classification result is used to indicate whether the quality of the construction consumables of the building is qualified.

8. The smart city construction consumables quality monitoring and management system according to claim 7, characterized in that: The construction consumables quality monitoring parameter feature optimization unit is used to: Extracting a target construction consumables quality classification parameter matrix of the quality detection classifier; Decomposing the target construction consumables quality classification parameter matrix into nodes in units of row vectors to obtain a set of target construction consumables quality classification parameter node encoding vectors; Taking each target construction consumables quality classification parameter node encoding vector in the set of target construction consumables quality classification parameter node encoding vectors as the walking topological space, topological space constraints are respectively performed on the full time series fusion feature vectors of the construction consumables quality monitoring parameters to obtain a set of constrained construction consumables quality monitoring parameter full time series fusion feature vectors; The positional mean vector of the set of the constrained construction consumables quality monitoring parameter full time series fusion feature vector is calculated to obtain the optimized construction consumables quality monitoring parameter full time series fusion feature vector.

9. A method for monitoring and managing the quality of consumables for smart city construction, characterized in that: include: The tensile strength test device for building steel bars and the compressive strength test device for building concrete are used to respectively obtain the tensile strength values ​​of steel bars and the compressive strength values ​​of concrete at multiple predetermined time points within a predetermined time period; Arranging data on the steel bar tensile strength values ​​and concrete compressive strength values ​​at the plurality of predetermined time points to obtain a full time series input matrix of construction consumables quality monitoring parameters; Data encoding is performed on the full time series input matrix of the construction consumables quality monitoring parameters to obtain a full time series fusion feature vector of the construction consumables quality monitoring parameters; Whether the quality of the construction consumables of the building is qualified is judged based on the information in the full time series fusion feature vector of the construction consumables quality monitoring parameters.

10. The method for monitoring and managing the quality of consumables for smart city construction according to claim 9, characterized in that: Judging whether the quality of the construction consumables of the building is qualified according to the information in the full time series fusion feature vector of the construction consumables quality monitoring parameter, including: Performing interactive exploration on the full-time fusion feature vector of the construction consumables quality monitoring parameters based on the characteristic intrinsic connection mode to obtain an optimized full-time fusion feature vector of the construction consumables quality monitoring parameters; The optimized construction consumables quality monitoring parameter full time series fusion feature vector is passed through a quality detection classifier to obtain a classification result, and the classification result is used to indicate whether the quality of the construction consumables of the building is qualified.

Images