Data processing method and system for constructional engineering quality detection

Abstract

The invention relates to the technical field of constructional engineering quality detection, and discloses a data processing method and system for constructional engineering quality detection, and the method comprises the steps: obtaining the stress of a structural layer in a constructional engineering construction environment, and obtaining a stress signal and an actual deformation signal of a building bearing member; calculating a structural layer dependent variable according to the structural layer stress, determining a load-bearing member displacement according to the stress signal and the deformation signal, and taking the structural layer dependent variable and the load-bearing member displacement as quality evaluation parameters; calculating according to the mapping relation among the quality evaluation parameters to obtain a quality evaluation target; processing the quality evaluation target to obtain project quality data; and based on a preset multivariate classification discrimination model, discriminating the project quality data and the quality evaluation parameter corresponding to the quality evaluation target to obtain a project quality detection result. The method can improve the accuracy of the quality detection result.

Description

Technical Field

[0001] The present invention relates to the technical field of construction engineering quality detection, and in particular to a data processing method and system for construction engineering quality detection. Background Art

[0002] In the quality inspection of construction projects, the processing of inspection data is an important link. Through reasonable data processing, the data source of quality inspection can be obtained more comprehensively and accurately, thereby ensuring the scientificity and accuracy of the inspection results. With the development of science and technology, data mining and machine learning related methods can scientifically process quality inspection data, and their application in the field of construction engineering is gradually becoming more widespread.

[0003] In the existing technical solutions, the research on construction project quality inspection methods is mainly focused on specific methods, equipment and processes, mostly based on experience and engineering practice, lacking a systematic quality assessment theory and method system. However, the relevant technologies are still focused on data identification and prediction analysis, and there is little research on systematic methods for quality assessment. At the same time, the research on actual inspection data and engineering cases is not comprehensive enough, and the inspection data lacks a comprehensive and in-depth analysis and evaluation.

[0004] In summary, the quality inspection methods for construction projects in the prior art cannot accurately and effectively analyze the actual situation of project quality, thereby affecting the accuracy of project quality inspection results. Summary of the invention

[0005] The present invention provides a data processing method and system for construction engineering quality detection, so as to improve the accuracy of engineering quality detection results.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a data processing method for construction project quality detection, comprising: Obtain the structural layer stress in the construction environment of the building project, and obtain the stress signal and actual deformation signal on the building load-bearing components; Calculating the strain of the structural layer according to the stress of the structural layer, determining the displacement of the load-bearing component according to the stress signal and the deformation signal, and using the strain of the structural layer and the displacement of the load-bearing component as quality assessment parameters; Calculating according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target; Process the quality assessment targets to obtain engineering quality data; Based on a preset multivariate classification discriminant model, the engineering quality data and the quality assessment parameters corresponding to the quality assessment target are discriminated to obtain an engineering quality detection result.

[0007] In an optional implementation manner, calculating the strain of the structural layer according to the structural layer stress includes: The structural layer strain is calculated by the following formula: in, is the structural layer strain, is the structural layer stress, It is the ultimate stress value of the structural layer obtained based on the inherent properties of engineering materials.

[0008] In an optional implementation, determining the displacement of a load-bearing component according to the stress signal and the deformation signal includes: obtaining stress data according to the stress signal; Inputting the stress data into a pre-trained long short-term memory network model to obtain the predicted displacement of the building load-bearing component under the bearing capacity; The predicted displacement is corrected according to the actual deformation signal, and the corrected predicted displacement is used as the displacement of the load-bearing component.

[0009] In an optional implementation, the predicted displacement is corrected according to the actual deformation signal, and the corrected predicted displacement is used as the displacement of the load-bearing component, including: The deviation correction method is adopted, and the deviation between the actual deformation signal and the predicted displacement is used as the correction value; The predicted displacement is corrected according to the correction amount to obtain a corrected predicted displacement, and the corrected predicted displacement is used as the displacement of the load-bearing component.

[0010] In an optional implementation, calculating according to the mapping relationship between the quality assessment parameters to obtain the quality assessment target includes: The quality assessment target is calculated by the following formula: in, For quality assessment purposes, is the structural layer strain, is the displacement of the load-bearing member, , is a constant term.

[0011] In an optional implementation, the quality assessment target is processed to obtain engineering quality data, including: Calculate the standard deviation of each piece of data in the quality assessment target; Determine whether the standard deviation is less than a set standard threshold, if so, determine that the data meets the condition; if not, determine that the data does not meet the condition; All eligible quality assessment targets are taken as the quality assessment targets; Wherein, the standard deviation is calculated by the following formula: In the formula, represents the standard deviation, Indicates The quality assessment target corresponding to the data is for The mean of is the number of data.

[0012] In an optional implementation, based on a preset multivariate classification discriminant model, the engineering quality data and the quality assessment parameters corresponding to the quality assessment target are discriminated to obtain an engineering quality detection result, including: Input the engineering quality data and the quality assessment parameters corresponding to the quality assessment target into a multivariate classification discriminant model for discrimination, labeling qualified data as 1 and unqualified data as 0; Sum and count the tag values ​​and calculate the pass rate; Determine whether the qualified rate is greater than a preset qualified threshold value. If so, the project quality inspection result is determined to be qualified; if not, the project quality inspection result is determined to be unqualified.

[0013] In an optional implementation, the training process of the multi-classification discriminant model includes: Acquire historical engineering quality data and historical quality assessment parameters, and construct a data set based on the historical engineering quality data and historical quality assessment parameters; Preprocessing the data set to obtain sample feature data and construct a sample set; The initial multivariate classification discriminant model is trained according to the sample set. When the number of training times reaches the preset maximum number of training times or the loss function value is less than the preset loss value, the trained multivariate classification discriminant model is obtained.

[0014] In a second aspect, the present invention provides a data processing system for construction engineering quality detection, comprising: A data acquisition module is used to obtain the structural layer stress in the construction environment of the building project, and to obtain the stress signal and actual deformation signal on the load-bearing components of the building; A parameter acquisition module, used to calculate the structural layer strain according to the structural layer stress, and determine the load-bearing component displacement according to the stress signal and the deformation signal, and use the structural layer strain and the load-bearing component displacement as quality assessment parameters; A target estimation module, used to calculate according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target; The data processing module is used to process the quality assessment targets and obtain the engineering quality data; The quality detection module is used to discriminate the engineering quality data and the quality assessment parameters corresponding to the quality assessment target based on a preset multivariate classification discrimination model to obtain an engineering quality detection result.

[0015] In a third aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned data processing methods for construction project quality inspection.

[0016] In a fourth aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a data processing method for construction project quality inspection as described above.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a data processing method for construction engineering quality detection, the method comprising obtaining structural layer stress in a construction environment of a construction engineering, and obtaining stress signals and actual deformation signals on load-bearing components of the building; calculating a structural layer strain according to the structural layer stress, and determining a load-bearing component displacement according to the stress signal and the deformation signal, and using the structural layer strain and the load-bearing component displacement as quality assessment parameters; calculating according to a mapping relationship between the quality assessment parameters to obtain a quality assessment target; processing the quality assessment target to obtain engineering quality data; and based on a preset multivariate classification discrimination model, discriminating the engineering quality data and the quality assessment parameters corresponding to the quality assessment target to obtain an engineering quality detection result.

[0018] In the present invention, by accurately obtaining the structural layer stress in the construction environment of the building project and the stress signal and actual deformation signal on the load-bearing components of the building, the structural layer strain and the displacement of the load-bearing components can be accurately calculated. These precise quality assessment parameters provide a reliable basis for subsequent quality assessment. Then, the mapping relationship between these parameters is used for accurate calculation to obtain accurate quality assessment targets. The quality assessment targets are further finely processed to obtain high-quality engineering quality data. Finally, based on the preset multivariate classification and discrimination model, the engineering quality data and its corresponding quality assessment parameters are accurately discriminated, thereby obtaining a high-accuracy engineering quality detection result. This method significantly improves the accuracy of engineering quality detection through multi-level precise processing and discrimination, and provides a more reliable guarantee for construction engineering quality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a data processing method for construction engineering quality inspection provided by the first embodiment of the present invention; Figure 2 is a training diagram of a multi-classification discrimination model provided by the first embodiment of the present invention; Figure 3 It is a flow chart of a multi-classification discrimination model provided by the first embodiment of the present invention; Figure 4 It is a structural schematic diagram of a data processing system for construction project quality inspection provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Reference Figure 1 The first embodiment of the present invention provides a data processing method for construction engineering quality detection, comprising the following steps: S11, obtaining the structural layer stress in the construction environment of the building project, and obtaining the stress signal and actual deformation signal on the building load-bearing components; S12, calculating the strain of the structural layer according to the stress of the structural layer, and determining the displacement of the load-bearing component according to the stress signal and the deformation signal, and taking the strain of the structural layer and the displacement of the load-bearing component as quality assessment parameters; S13, performing calculation according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target; S14, processing the quality assessment target to obtain engineering quality data; S15, based on a preset multivariate classification discrimination model, the engineering quality data and the quality assessment parameters corresponding to the quality assessment target are discriminated to obtain an engineering quality detection result.

[0022] In the present invention, by accurately obtaining the structural layer stress in the construction environment of the building project and the stress signal and actual deformation signal on the load-bearing components of the building, the structural layer strain and the displacement of the load-bearing components can be accurately calculated. These precise quality assessment parameters provide a reliable basis for subsequent quality assessment. Then, the mapping relationship between these parameters is used for accurate calculation to obtain accurate quality assessment targets. The quality assessment targets are further finely processed to obtain high-quality engineering quality data. Finally, based on the preset multivariate classification and discrimination model, the engineering quality data and its corresponding quality assessment parameters are accurately discriminated, thereby obtaining a high-accuracy engineering quality detection result. This method significantly improves the accuracy of engineering quality detection through multi-level precise processing and discrimination, and provides a more reliable guarantee for construction engineering quality detection.

[0023] Specifically, in step S11, the structural layer stress in the construction environment of the building project is obtained, and the stress signal and the actual deformation signal on the building load-bearing component are obtained, including: S111, by installing strain sensors on the surface of the structure, the stress of the structural layer under the action of external forces can be measured; S112, the stress signal on the surface or inside of the load-bearing member can be directly measured by the stress sensor installed on the load-bearing member; S113, by installing a displacement sensor, the displacement change of the structure or load-bearing component can be accurately measured to obtain its actual deformation signal.

[0024] In step S111, strain sensors are installed at key locations of the structural layer, such as the surface of beams, columns, walls, etc. These sensors can accurately measure the strain generated by the structure under the action of external forces, that is, the slight deformation of the material. The strain sensor uses a resistance strain gauge or an optical fiber strain sensor, which can convert the strain change into an electrical signal or an optical signal.

[0025] In step S112, stress sensors are installed at key locations of load-bearing components, such as the mid-span of beams, the bottom of columns, and the supports of plates. These sensors can directly measure stress signals on the surface or inside of components.

[0026] In step S113, displacement sensors are installed at key locations of structures or load-bearing components, such as the ends of beams, the tops of columns, the centers of plates, etc. Displacement sensors can accurately measure displacement changes of components under load, including vertical displacement, horizontal displacement, tilt displacement, etc.

[0027] It should be noted that structural layer stress is a physical phenomenon caused by the distribution of internal forces of materials under loading. It reflects the internal stress state of the structure when it is subjected to external loads (such as gravity, wind load, seismic force, etc.). The purpose of obtaining structural layer stress is to analyze whether the structure is in a safe stress state and to promptly discover potential structural problems, such as local overload or material fatigue. Load-bearing components are the key parts of a building that are responsible for bearing loads, such as beams, columns, and plates. The stress signals on load-bearing components reflect the stress distribution of these components during the force-bearing process. The collection of stress signals is of great significance for evaluating the safety and stability of load-bearing components. The actual deformation signal refers to the deformation or displacement of the component under the load of the load-bearing component. The deformation signal reflects the response of the structure and is one of the key indicators for judging whether the building structure is safe and whether it needs to be reinforced.

[0028] It is worth noting that obtaining the stress of the structural layer in the construction environment of a building project is achieved by installing stress sensors at key locations of the structural layer. Force sensors can monitor and record the stress changes that the structural layer is subjected to during the construction process in real time. The data from the sensors is usually transmitted to the data acquisition system by wire or wireless means for subsequent analysis and processing. In order to obtain the stress signal and actual deformation signal on the load-bearing components of the building, strain gauges and displacement sensors can be installed at key locations of the load-bearing components. Strain gauges are used to measure the strain of components when they are subjected to force, that is, the slight deformation of the material, while displacement sensors are used to measure the displacement changes of components under force. These sensors will also transmit data to the data acquisition system for real-time monitoring and recording.

[0029] In step S12, it is necessary to calculate the structural layer strain according to the structural layer stress, and determine the load-bearing component displacement according to the stress signal and the deformation signal, and use the structural layer strain and the load-bearing component displacement as quality evaluation parameters.

[0030] In one implementation, the structural layer strain is calculated based on the structural layer stress using the following formula: in, is the structural layer strain, is the structural layer stress, The ultimate stress value of the structural layer is obtained based on the inherent properties of the engineering material. Through this formula, the actual stress can be normalized into the structural layer strain, which means the ratio of the stress of the structure to the bearing limit of the material. This value is usually between 0 and 1. The closer the value is to 1, the closer the stress is to the limit of the material, and the risk of structural damage may occur.

[0031] In one implementation, the displacement of the load-bearing component is determined according to the stress signal and the deformation signal by the following formula: In the formula, Displacement of load-bearing components, is the stress signal, is Young's modulus, which indicates the stiffness characteristics of the material, and its unit is usually Pascal (Pa). is the length of the structural member.

[0032] It is worth noting that the strain of the structural layer reflects the degree of stress borne by the material, which can help determine whether the structure is subjected to a load that exceeds the safety limit. The displacement of the load-bearing component shows the deformation of the structure under the load, which is especially important for detecting the flexible deformation of the structure, damage during long-term use, and instability under extreme loads. These two parameters combined can provide comprehensive information about the overall stability and safety of the building. In construction projects, real-time monitoring using these two indicators can promptly identify structural problems and ensure the safety of the building.

[0033] It should be noted that the ultimate stress value refers to the maximum stress that a material can withstand without being damaged.

[0034] In this embodiment, the relationship between the quality assessment parameter and the quality assessment target is a many-to-one relationship, and the displacement of the load-bearing component needs to be determined through the stress signal and the deformation signal.

[0035] In one implementation, determining the displacement of a load-bearing component according to the stress signal and the deformation signal includes: S121, obtaining stress data according to the stress signal; S122, inputting the stress data into a pre-trained long short-term memory network model to obtain a predicted displacement of a load-bearing component of the building under a bearing capacity; S123, correcting the predicted displacement according to the actual deformation signal, and using the corrected predicted displacement as the displacement of the load-bearing component.

[0036] In step S121, stress data is obtained according to the stress signal, including: The stress signal is collected in real time by means of stress sensors installed on the load-bearing components; In the data acquisition system, the original stress signal is preprocessed, including filtering, denoising and data format conversion; Stress data is extracted from the preprocessed data to provide a basis for subsequent displacement prediction.

[0037] In step S122, the stress data is input into a pre-trained long short-term memory network model to obtain the predicted displacement of the building load-bearing component under the bearing capacity, including: The LSTM model is trained based on historical data, which usually comes from historical engineering data, experimental data, or simulation data. These data should include stress signals and corresponding displacements. During the training process, the LSTM will learn the complex nonlinear relationship between stress and displacement, especially the dynamic effect of stress on displacement; The real-time acquired stress data is used as the input data of the LSTM network. The network processes the input stress data and outputs the predicted displacement of the building's load-bearing components under a specific load based on the learned pattern.

[0038] The extracted stress data is input into a pre-trained long short-term memory network (LSTM) model. The LSTM model is a special recurrent neural network that has the ability to memorize long-term dependent information and is very suitable for processing time series data. In the present invention, the LSTM model can predict the displacement of the building's load-bearing components under bearing capacity by learning the relationship between stress data and displacement.

[0039] It is worth noting that the displacement of the load-bearing component reflects the overall deformation of the material or structure under the force, while the strain provides an indication of the stress level. In the process of structural quality assessment, the strain is often combined with the displacement of the load-bearing component to determine whether the structure has potential dangers.

[0040] In step S123, the predicted displacement needs to be corrected according to the actual deformation signal, and the corrected predicted displacement is used as the displacement of the load-bearing component, including: The deviation correction method is adopted, and the deviation between the actual deformation signal and the predicted displacement is used as the correction value; The predicted displacement is corrected according to the correction amount to obtain a corrected predicted displacement, and the corrected predicted displacement is used as the displacement of the load-bearing component.

[0041] It should be noted that when evaluating the quality of a structure, there will be certain errors if the displacement of the load-bearing component is estimated solely by relying on theoretical models or prediction models, especially in complex actual working environments, where external factors (such as temperature changes, material inhomogeneity, construction errors, etc.) lead to deviations between the actual deformation and the predicted results. Therefore, correcting the predicted displacement becomes an important step to improve the accuracy of the assessment. In this case, the deviation correction method is used to quantify the difference between the actual deformation signal and the theoretical prediction result, and to ensure that the final displacement of the load-bearing component is more in line with the actual situation by correcting the predicted value.

[0042] In step S13, it is necessary to perform calculations based on the mapping relationship between the quality assessment parameters to obtain a quality assessment target.

[0043] In one implementation, calculating according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target includes: S131, the structural layer strain and load-bearing component displacement obtained in step S12 are used as quality assessment parameters. These parameters are obtained through real-time monitoring and calculation, reflecting the actual stress and deformation of the building project in the construction environment; S132, selecting to use the following formula to calculate the quality assessment target; S133, preset a quality assessment constant item according to actual conditions.

[0044] in, For quality assessment purposes, is the structural layer strain, is the displacement of the load-bearing member, , is a constant term.

[0045] In step S131, a quality assessment target is formed by combining the structural layer strain and the load-bearing component displacement. This calculation process is based on the mapping relationship and obtains the final quality assessment target through linear weighting.

[0046] It should be noted that in practical applications, and It is determined based on engineering experience, experimental data or optimization algorithms. They determine the importance of the structural layer strain and the load-bearing component displacement in the comprehensive evaluation. Specifically: Indicates the degree of influence of the structural layer strain on the quality assessment target. Generally, the structural layer strain reflects the stress distribution of materials and structures during the stress process, and is closely related to factors such as the strength and stiffness of the material; Indicates the degree of influence of the displacement of load-bearing components on the quality assessment target. The displacement of load-bearing components reflects the degree of deformation of the structure and is an important indicator for evaluating the stability and safety of the structure. It is closely related to the overall deformation and service life of the structure.

[0047] It is worth noting that quality assessment targets are usually dynamic and will change over time. As the structure undergoes different loads, environmental changes, or aging processes, the values ​​of structural layer strain and load-bearing component displacement will also change. Therefore, in practical applications, the quality assessment target should be a dynamic indicator that is continuously updated with monitoring data.

[0048] In step S14, the quality assessment target needs to be processed to obtain engineering quality data.

[0049] In one implementation, the quality assessment target is processed to obtain engineering quality data, including: S141, calculating the standard deviation of each piece of data in the quality assessment target; S142, determining whether the standard deviation is less than a set standard threshold, if so, determining that the data piece meets the condition; if not, determining that the data piece does not meet the condition; S143, taking all the quality assessment targets that meet the conditions as the quality assessment targets; It is worth mentioning that standard deviation is a commonly used statistical indicator to measure the degree of dispersion or fluctuation range of data. For quality assessment targets, the purpose of calculating standard deviation is to evaluate the stability and reliability of each assessment target. If the standard deviation of a quality assessment target is too large, it means that the data of the target has large fluctuations or anomalies during the measurement process.

[0050] In step S141, the standard deviation is calculated by the following formula: In the formula, represents the standard deviation, Indicates The quality assessment target corresponding to the data is for The mean of is the number of data.

[0051] It is worth noting that the standard deviation threshold is a standard for judging whether the data meets the expected fluctuation range. In this embodiment, a predetermined standard threshold is set to judge whether the fluctuation of each quality assessment target data is within an acceptable range. If the standard deviation of a piece of data exceeds the set threshold, it means that the data fluctuates greatly, there is measurement error, sensor failure or external environmental influence, and it cannot be used as reliable evaluation data; if the standard deviation is less than the set threshold, it means that the data is relatively stable and can reflect the true state of the structure.

[0052] In step S15, it is necessary to discriminate the engineering quality data and the quality assessment parameters corresponding to the quality assessment target based on a preset multivariate classification discriminant model to obtain an engineering quality detection result.

[0053] like Figure 2 As shown, in step S15, based on a preset multivariate classification discriminant model, the engineering quality data and the quality assessment parameters corresponding to the quality assessment target are discriminated to obtain engineering quality detection results, including: S151, inputting the engineering quality data and the quality assessment parameters corresponding to the quality assessment target into a multivariate classification discriminant model for discrimination, labeling qualified data as 1 and unqualified data as 0; S152, summing and counting the tag values, and calculating the pass rate; S153, judging whether the qualified rate is greater than a preset qualified threshold value, if so, judging the engineering quality inspection result as qualified; if not, judging the engineering quality inspection result as unqualified.

[0054] In step S151, the engineering quality data and the quality assessment parameters corresponding to the quality assessment target are input into a multivariate classification discriminant model for identification, including: It is necessary to combine the engineering quality data and quality assessment parameters to form an input feature vector. Each feature vector should contain various indicators related to engineering quality; Before entering the multivariate classification discriminant model, the data was standardized to avoid the dimensional differences between different features affecting the discriminant effect; The multivariate classification discriminant model gives the discrimination result based on the input data.

[0055] In step S152, the tag values ​​are summed and counted, and the qualified rate is calculated, including: For all input data (including multiple engineering samples or quality data at multiple time points), we first need to count the labels. Assume that N sample data are input, and each data has a label (0 or 1). We need to count the number of labels 1 (qualified) and 0 (unqualified); Calculate the pass rate, that is, the proportion of qualified samples.

[0056] For example, suppose there are 100 sample data, of which: 60 samples are labeled 1 (qualified), and 40 samples are labeled 0 (unqualified). The qualified rate is calculated as: 60 / 100=60%.

[0057] In step S153, it is determined whether the qualified rate is greater than a preset qualified threshold value. If so, the engineering quality inspection result is determined to be qualified; if not, the engineering quality inspection result is determined to be unqualified, including: A qualified threshold is set according to specific standards and requirements. This threshold is an empirical value or standard value used to determine whether it can be judged as "qualified". In this embodiment, the qualified threshold is 80%; If the pass rate is greater than or equal to the preset pass threshold, the project quality inspection result is "qualified"; if the pass rate is lower than the preset pass threshold, the project quality inspection result is "unqualified".

[0058] like Figure 3 As shown, in step S15, the training process of the multi-classification discrimination model includes: S251, obtaining historical engineering quality data and historical quality assessment parameters, and constructing a data set based on the historical engineering quality data and the historical quality assessment parameters; S252, preprocessing the data set to obtain sample feature data and construct a sample set; S253, training the initial multi-classification discriminant model according to the sample set, and obtaining a trained multi-classification discriminant model when the number of training times reaches a preset maximum number of training times or the loss function value is less than a preset loss value.

[0059] In step S251, historical engineering quality data and historical quality assessment parameters are obtained, and a data set is constructed based on the historical engineering quality data and historical quality assessment parameters, including: Collect historical project quality data based on monitoring and inspection data from the construction process covering many years; Obtain historical quality assessment parameters through actual quality testing and inspection reports; By combining historical quality data with quality assessment parameters, a dataset containing input features and output labels is constructed. The labels usually represent the evaluation results of engineering quality, such as "qualified" or "unqualified".

[0060] It is worth noting that the construction of the dataset needs to consider the integrity of the data and ensure that each piece of data contains sufficient information to support the subsequent training process. For example, for each data record, it is necessary to include basic information of the construction project, relevant quality data (stress, displacement, etc.) and evaluation results (whether it is qualified).

[0061] In step S252, the data set is preprocessed to obtain sample feature data and construct a sample set, including: The collected raw data needs to be cleaned and missing values ​​need to be filled in an appropriate way. In this embodiment, interpolation method is used; Check the data for outliers, especially data points that are significantly higher or lower than expected values, and remove these outliers; Select features with high correlation with engineering quality from historical data and remove invalid features that are irrelevant to the prediction target; Standardize the data; The processed data set is used to construct a training sample set, each sample containing feature data and corresponding labels. The sample set can be divided into a training set, a validation set, and a test set. In this embodiment, the ratio is 70%:15%:15% to ensure that the model can be verified and tested on different data sets.

[0062] In step S253, the initial multi-classification discriminant model is trained according to the sample set. When the number of training times reaches the preset maximum number of training times or the loss function value is less than the preset loss value, a trained multi-classification discriminant model is obtained, including: Select a suitable multivariate classification discriminant model. The model used in this embodiment is principal component analysis-support vector machine; The sample set (input features and labels) is fed into the selected model. The training process involves adjusting the model’s internal parameters so that the model can make accurate predictions based on the input features. Constrain the model training through the preset cross entropy loss function; When the training reaches the maximum number of times or the loss value drops to the preset threshold, the training stops and the multivariate classification discriminant model is obtained; Use the validation set to validate the model to ensure the generalization ability of the model, and make further adjustments to the model (such as hyperparameter adjustment) based on the results of the validation set.

[0063] In this embodiment, step S15 discriminates the engineering quality data and its corresponding quality assessment parameters based on a preset multivariate classification discriminant model, thereby obtaining the final engineering quality inspection result. The core of this process is to use a multivariate classification discriminant model to classify and identify the collected quality data, and make a final qualified judgment based on the qualified rate. The classification model in the specific process can be modeled and trained by combining principal component analysis (PCA) with support vector machine (SVM) to improve the accuracy and generalization ability of the model.

[0064] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0065] In this embodiment, the present invention provides a data processing method for construction engineering quality detection. The method includes obtaining the structural layer stress in the construction environment of the construction project, and obtaining the stress signal and the actual deformation signal on the load-bearing components of the building; calculating the structural layer strain according to the structural layer stress, and determining the displacement of the load-bearing components according to the stress signal and the deformation signal, and using the structural layer strain and the displacement of the load-bearing components as quality assessment parameters; calculating according to the mapping relationship between the quality assessment parameters to obtain the quality assessment target; processing the quality assessment target to obtain engineering quality data; based on a preset multivariate classification discrimination model, discriminating the engineering quality data and the quality assessment parameters corresponding to the quality assessment target to obtain the engineering quality detection result. This method can improve the accuracy of the quality detection result.

[0066] Specifically, step one: During the construction process, a series of sensors are first arranged at the construction site. These sensors include strain sensors, stress sensors, and displacement sensors. Strain sensors are installed at key locations of the structural layer and can measure the strain changes of the structure in real time; stress sensors are directly installed on load-bearing components to monitor the stress signals inside or on the surface of the components; displacement sensors are used to measure the displacement of components. These data can effectively reflect the deformation of the components after being subjected to force. All sensors transmit real-time data to the central data processing center through the data acquisition system to ensure that the signals from each monitoring point can be accurately transmitted and analyzed in a timely manner.

[0067] Step 2: After the data is transmitted to the central data processing center, data preprocessing is first performed. This process includes removing noise signals, performing data cleaning, converting formats, etc. to ensure the accuracy and availability of the data. The preprocessed data will be input into the preset quality assessment model for further analysis. The quality assessment model is based on historical engineering data, experimental data, and structural engineering theory. The model can identify different types of stress, strain, and deformation, and give reasonable quality assessment parameters.

[0068] Step 3: Analyze the input data through the quality assessment model. The system will obtain the strain of the structural layer and the displacement of the load-bearing components based on the calculated quality assessment parameters. These indicators will serve as the key basis for subsequent judgment of structural safety. The strain of the structural layer reflects the stress level that the building materials are subjected to under the action of external forces, while the displacement of the load-bearing components can show the deformation of the building components. Based on this information, the system will generate a quality assessment target value, which is usually obtained through a linear weighted function and can comprehensively reflect the overall state of the building structure.

[0069] Step 4: After the quality assessment target is obtained, the system will compare it with the preset safety threshold. If the assessment target value does not meet the safety requirements, the system will issue an alarm to prompt the building engineer to perform necessary inspections and maintenance. In this embodiment, the preset safety threshold is determined based on the bearing capacity of different materials and the building design specifications. If the assessment value is higher than the threshold, it means that the structure is in a normal and safe state; if it is lower than the threshold, there is a potential safety hazard, and the system will automatically trigger the alarm mechanism.

[0070] Step 5: When quality problems occur, the data processing system will generate a detailed alarm report based on the analysis results and send it to the operators at the construction site through the wireless communication network. After receiving the alarm, the operators will immediately take corresponding measures, such as stopping construction, checking whether the load-bearing components are damaged, adjusting the construction plan, etc. These measures will help reduce the expansion of risks and the occurrence of potential accidents.

[0071] Step 6: In addition to direct on-site responses, the system will also make further corrections and optimizations based on the relationship between various quality assessment parameters. Using advanced machine learning algorithms such as long short-term memory networks, on-site monitoring data can be dynamically corrected based on historical data, further improving the accuracy and real-time nature of quality assessment.

[0072] Step 7: The system uploads all detected quality assessment data to the cloud platform for storage, so that managers can view historical monitoring records at any time. The cloud platform will also generate visual construction quality reports based on different quality assessment goals to help construction engineers, project managers and relevant decision makers better understand the quality status of construction projects. These reports can provide reference for subsequent project acceptance, warranty and maintenance.

[0073] Step 8: When the quality problem is repaired or improved, the system will recalibrate the relevant quality parameters and resume the normal monitoring process. Through continuous quality monitoring and intelligent analysis, the construction project will receive more scientific and accurate quality assurance to ensure the safety and stability of the building.

[0074] In summary, the present invention discloses a data processing method for construction project quality inspection, the method comprising obtaining structural layer stress in a construction environment of a construction project, and obtaining stress signals and actual deformation signals on load-bearing components of the building; calculating the structural layer strain according to the structural layer stress, and determining the displacement of the load-bearing component according to the stress signal and the deformation signal, and taking the structural layer strain and the displacement of the load-bearing component as quality assessment parameters; calculating according to a mapping relationship between the quality assessment parameters to obtain a quality assessment target; processing the quality assessment target to obtain engineering quality data; based on a preset multivariate classification discrimination model, discriminating the engineering quality data and the quality assessment parameters corresponding to the quality assessment target to obtain an engineering quality inspection result.

[0075] In the present invention, by accurately obtaining the structural layer stress in the construction environment of the building project and the stress signal and actual deformation signal on the load-bearing components of the building, the structural layer strain and the displacement of the load-bearing components can be accurately calculated. These precise quality assessment parameters provide a reliable basis for subsequent quality assessment. Then, the mapping relationship between these parameters is used for accurate calculation to obtain accurate quality assessment targets. The quality assessment targets are further finely processed to obtain high-quality engineering quality data. Finally, based on the preset multivariate classification and discrimination model, the engineering quality data and its corresponding quality assessment parameters are accurately discriminated, thereby obtaining a high-accuracy engineering quality detection result. This method significantly improves the accuracy of engineering quality detection through multi-level precise processing and discrimination, and provides a more reliable guarantee for construction engineering quality detection.

[0076] Reference Figure 4 The second embodiment of the present invention provides a data processing system for construction engineering quality detection, comprising: A data acquisition module is used to obtain the structural layer stress in the construction environment of the building project, and to obtain the stress signal and actual deformation signal on the load-bearing components of the building; A parameter acquisition module, used to calculate the structural layer strain according to the structural layer stress, and determine the load-bearing component displacement according to the stress signal and the deformation signal, and use the structural layer strain and the load-bearing component displacement as quality assessment parameters; A target estimation module, used to calculate according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target; The data processing module is used to process the quality assessment targets and obtain the engineering quality data; The quality detection module is used to discriminate the engineering quality data and the quality assessment parameters corresponding to the quality assessment target based on a preset multivariate classification discrimination model to obtain an engineering quality detection result.

[0077] It should be noted that the data processing system for construction project quality inspection provided by an embodiment of the present invention is used to execute all the process steps of the data processing method for construction project quality inspection in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be elaborated on.

[0078] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, the steps in the above-mentioned data processing method for construction project quality detection are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned system embodiments are realized, such as the data acquisition module.

[0079] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0080] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0081] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0082] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0083] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0084] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0085] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A data processing method for construction engineering quality detection, characterized in that: Executed by a computer, including: Obtain the structural layer stress in the construction environment of the building project, and obtain the stress signal and actual deformation signal on the building load-bearing components; Calculating the strain of the structural layer according to the stress of the structural layer, and determining the displacement of the load-bearing component according to the stress signal and the deformation signal, and using the strain of the structural layer and the displacement of the load-bearing component as quality assessment parameters; Calculating according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target; Process the quality assessment targets to obtain engineering quality data; Based on a preset multivariate classification discriminant model, the engineering quality data and the quality assessment parameters corresponding to the quality assessment target are discriminated to obtain an engineering quality detection result.

2. The data processing method for construction engineering quality detection according to claim 1 is characterized in that: The structural layer strain is calculated according to the structural layer stress, including: The structural layer strain is calculated by the following formula: in, is the structural layer strain, is the structural layer stress, It is the ultimate stress value of the structural layer obtained based on the inherent properties of engineering materials.

3. The data processing method for construction engineering quality detection according to claim 1 is characterized in that: Determining the displacement of the load-bearing component according to the stress signal and the deformation signal includes: obtaining stress data according to the stress signal; Inputting the stress data into a pre-trained long short-term memory network model to obtain the predicted displacement of the building load-bearing component under the bearing capacity; The predicted displacement is corrected according to the actual deformation signal, and the corrected predicted displacement is used as the displacement of the load-bearing component.

4. The data processing method for construction engineering quality detection according to claim 3 is characterized in that: The method of correcting the predicted displacement according to the actual deformation signal and using the corrected predicted displacement as the displacement of the load-bearing component includes: The deviation correction method is adopted, and the deviation between the actual deformation signal and the predicted displacement is used as the correction value; The predicted displacement is corrected according to the correction amount to obtain a corrected predicted displacement, and the corrected predicted displacement is used as the displacement of the load-bearing component.

5. The data processing method for construction engineering quality detection according to claim 1 is characterized in that: Calculation is performed according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target, including: The quality assessment target is calculated by the following formula: in, For quality assessment purposes, is the structural layer strain, is the displacement of the load-bearing member, , is a constant term.

6. The data processing method for construction engineering quality detection according to claim 1 is characterized in that: Process the quality assessment targets to obtain engineering quality data, including: Calculate the standard deviation of each piece of data in the quality assessment target; Determine whether the standard deviation is less than a set standard threshold, if so, determine that the data meets the condition; if not, determine that the data does not meet the condition; All eligible quality assessment targets are taken as the quality assessment targets; Wherein, the standard deviation is calculated by the following formula: In the formula, represents the standard deviation, Indicates The quality assessment target corresponding to the data is for The mean of is the number of data.

7. The data processing method for construction engineering quality detection according to claim 1 is characterized in that: Based on a preset multivariate classification discriminant model, the engineering quality data and the quality assessment parameters corresponding to the quality assessment target are discriminated to obtain engineering quality detection results, including: Input the engineering quality data and the quality assessment parameters corresponding to the quality assessment target into a multivariate classification discriminant model for discrimination, labeling qualified data as 1 and unqualified data as 0; Sum and count the tag values ​​and calculate the pass rate; Determine whether the qualified rate is greater than a preset qualified threshold value. If so, the project quality inspection result is determined to be qualified; if not, the project quality inspection result is determined to be unqualified.

8. The data processing method for construction engineering quality detection according to claim 1 is characterized in that: The training process of the multi-classification discriminant model includes: Acquire historical engineering quality data and historical quality assessment parameters, and construct a data set based on the historical engineering quality data and historical quality assessment parameters; Preprocessing the data set to obtain sample feature data and construct a sample set; The initial multivariate classification discriminant model is trained according to the sample set. When the number of training times reaches the preset maximum number of training times or the loss function value is less than the preset loss value, the trained multivariate classification discriminant model is obtained.

9. A data processing system for construction engineering quality inspection, characterized in that: include: A data acquisition module is used to obtain the structural layer stress in the construction environment of the building project, and to obtain the stress signal and actual deformation signal on the load-bearing components of the building; A parameter acquisition module, used to calculate the structural layer strain according to the structural layer stress, and determine the load-bearing component displacement according to the stress signal and the deformation signal, and use the structural layer strain and the load-bearing component displacement as quality assessment parameters; A target estimation module, used to calculate according to the mapping relationship between the quality assessment parameters to obtain a quality assessment target; The data processing module is used to process the quality assessment targets and obtain the engineering quality data; The quality detection module is used to discriminate the engineering quality data and the quality assessment parameters corresponding to the quality assessment target based on a preset multivariate classification discrimination model to obtain an engineering quality detection result.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a data processing method for construction project quality inspection as described in any one of claims 1 to 8.

Images