Hydraulic engineering construction quality detection method and system

Abstract

The invention discloses a water conservancy project construction quality detection method and system, and relates to the technical field of water conservancy project quality monitoring, and the method comprises the steps: collecting multi-source heterogeneous data in a water conservancy project construction process through a distributed sensor network, and carrying out the preprocessing; performing process risk assessment on the construction unit by adopting the process-quality correlation model, calculating a process risk index and marking a potential risk area; dynamically calculating a quality characteristic parameter threshold value based on the quality evolution model; the method comprises the following steps: performing physical quantity spatial reconstruction on sensor monitoring data to obtain spatial distribution results of each physical quantity; performing quality anomaly analysis and structural defect judgment on the construction area to obtain a quality anomaly area and a defect area; and generating a quality state identification result based on the construction process features, the potential risk area, the quality abnormal area and the defect area. According to the invention, by establishing a quality characteristic parameter dynamic threshold calculation mechanism and a multi-dimensional cross validation system, the accuracy and reliability of construction quality detection can be improved.

Description

Technical Field

[0001] This invention relates to the field of water conservancy project quality monitoring technology, and in particular to a method and system for detecting the construction quality of water conservancy projects. Background Technology

[0002] The construction quality of water conservancy projects is influenced by various factors such as material properties, construction techniques, and environmental conditions, exhibiting dynamic evolution characteristics. Construction quality monitoring methods based on distributed sensor networks have been applied in the field of water conservancy engineering. These methods involve deploying sensors in the construction area to collect data on physical quantities such as temperature, strain, and displacement, and then combining this data with processing algorithms to evaluate the construction quality. Typical technical solutions include: using fixed thresholds to determine anomalies in the monitoring data; employing spatial interpolation methods to spatially reconstruct discrete sensor data; and identifying areas of quality anomalies based on statistical analysis of the monitoring data.

[0003] The above-mentioned technical solutions have certain limitations in practical applications. During construction, quality characteristic parameters dynamically change with the construction period and environmental conditions; using fixed thresholds is insufficient to adapt to the differences in quality evolution under different construction stages and environmental conditions. The spatial geometric features and sensor distribution density vary at different locations within the construction area; using uniform spatial interpolation parameters affects reconstruction accuracy. Furthermore, fluctuations in construction process parameters can cause normal changes in monitoring data. Relying solely on comparing monitoring data with thresholds for anomaly detection may misjudge normal process fluctuations as quality anomalies, or it may miss actual quality defects. Summary of the Invention

[0004] The main objective of this invention is to provide a method and system for detecting the construction quality of water conservancy projects, aiming to solve the technical problems of insufficient accuracy and reliability in the existing technology for detecting construction quality.

[0005] In a first aspect, the present invention provides a method for testing the construction quality of water conservancy projects, comprising: Multi-source heterogeneous data is collected during the construction of water conservancy projects through a distributed sensor network and preprocessed; the multi-source heterogeneous data includes sensor monitoring data, construction process parameters and environmental parameters. Based on construction process parameters, a process-quality correlation model is used to assess the process risk of construction units, calculate the process risk index, and mark potential risk areas. Based on construction process parameters and environmental parameters, the threshold values ​​of quality characteristic parameters are dynamically calculated using a quality evolution model. Spatial reconstruction of physical quantities is performed on sensor monitoring data to obtain the spatial distribution results of each physical quantity; Based on the spatial distribution results of various physical quantities and the threshold of quality characteristic parameters, quality anomaly analysis and structural defect determination are carried out on the spatial location within the construction area to obtain quality anomaly areas and defect areas. Based on potential risk areas, quality anomaly areas, and defect areas, a comprehensive analysis of the construction area is conducted to generate a quality status identification result for the construction area.

[0006] Optionally, the process risk assessment of the construction unit using a process-quality correlation model includes: Obtain the construction process parameters corresponding to each construction unit, and filter out the process parameters participating in the coupling analysis according to the construction procedure type to obtain the effective process parameter set; Based on the effective set of process parameters, the coupling relationship of process parameters is constructed.

[0007] Optionally, using a process-quality correlation model to conduct process risk assessment of construction units also includes: Based on the process-quality correlation model and the coupling relationship of process parameters, the process risk index corresponding to each construction unit is calculated; Based on the process risk index, the spatial areas corresponding to construction units that meet the preset risk assessment conditions are marked as potential risk areas, and process early warning information corresponding to the potential risk areas is generated.

[0008] Optionally, dynamically calculating the thresholds for quality characteristic parameters based on the quality evolution model includes: Based on the construction procedure type and construction age recorded by each construction unit, construction units with the same construction procedure type and construction age difference within a preset time window are merged into an evaluation unit. For each assessment unit, the initial parameter set of the quality evolution model is determined according to the construction procedure type of the assessment unit. The initial parameter set includes the target quality characteristic parameter type and its evolution baseline curve. The representative age of the evaluation unit is calculated based on the construction age of each construction unit within the evaluation unit, and the corresponding theoretical value of quality characteristics is determined based on the representative age and the initial parameter set. The theoretical values ​​of quality characteristics are corrected based on the environmental parameters corresponding to the assessment unit; Environmental stability is determined based on the fluctuation characteristics of environmental parameters corresponding to the assessment unit, and the tolerance range of quality characteristic parameters is dynamically adjusted based on the environmental stability determination results. Based on the corrected theoretical values ​​of quality characteristics and tolerance range, the upper and lower limits of the threshold values ​​of the quality characteristic parameters of the evaluation unit are calculated.

[0009] Optionally, spatial reconstruction processing of sensor monitoring data by physical quantities includes: Based on the evaluation unit division results, the sensor monitoring data are classified according to the evaluation unit and the type of physical quantity to form the sub-physical quantity monitoring dataset for each evaluation unit; For each evaluation unit, spatial reconstruction parameters are determined based on the spatial range of the construction units contained in the evaluation unit. The spatial reconstruction parameters include interpolation method, spatial resolution, and boundary constraints. Spatial interpolation processing is performed on the monitoring datasets of physical quantities of each evaluation unit to obtain the spatial distribution results of each physical quantity of each evaluation unit; The spatial distribution results of physical quantities of each assessment unit are spliced ​​together in space to form the spatial distribution results of physical quantities of the complete construction area.

[0010] Optionally, the analysis of quality anomalies and the determination of structural defects in the spatial location within the construction area include: The spatial distribution results of each physical quantity are compared with the corresponding mass characteristic parameter thresholds, and spatial locations that exceed the threshold range are marked as preliminary anomaly locations. Based on the construction process parameters of the construction unit to which the initial abnormal location belongs, determine whether the deviation of physical quantities belongs to the normal fluctuation of the construction process; Preliminary abnormal locations that do not fall under the normal fluctuations of the construction process are identified as spatial locations of quality abnormalities. Spatial connectivity analysis is performed on the spatial locations of quality anomalies to form quality anomaly regions; Acquire image sensor data of areas with quality anomalies and extract defect structural features; A quality anomaly region that simultaneously exhibits physical quantity anomalies and defective structural features is identified as a defect region.

[0011] Optionally, a comprehensive analysis of the construction area may include: Based on the attribution of each spatial location to potential risk areas, quality anomaly areas, and defect areas, determine the area intersection type of each spatial location; Obtain the sequence of regional intersection types changes at different spatial locations during different construction stages, and determine the quality evolution trend based on the sequence of changes; Based on the regional intersection type and quality evolution trend, the quality status identification results of the construction area are generated.

[0012] Secondly, the present invention provides a water conservancy project construction quality inspection system, comprising: The data acquisition and preprocessing module is used to collect multi-source heterogeneous data during the construction process of water conservancy projects through a distributed sensor network and to perform preprocessing. The process risk assessment module is used to assess the process risk of construction units based on construction process parameters and a process-quality correlation model, calculate the process risk index and mark potential risk areas. The quality threshold calculation module is used to dynamically calculate the threshold of quality characteristic parameters based on the quality evolution model, according to construction process parameters and environmental parameters. The physical quantity spatial reconstruction module is used to perform spatial reconstruction processing on sensor monitoring data by physical quantity to obtain the spatial distribution results of each physical quantity. The quality anomaly and defect determination module is used to perform quality anomaly analysis and structural defect determination on the spatial location of the construction area based on the spatial distribution results of various physical quantities and the threshold of quality characteristic parameters, so as to obtain the quality anomaly area and the defect area. The quality status identification module is used to perform a comprehensive analysis of the construction area based on potential risk areas, quality anomaly areas, and defect areas, and generate quality status identification results for the construction area.

[0013] Thirdly, the present invention provides an electronic device, comprising: Memory, used to store computer programs; A processor is used to execute computer programs to implement the aforementioned methods for detecting the construction quality of water conservancy projects.

[0014] Fourthly, the present invention provides a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned method for detecting the construction quality of water conservancy projects.

[0015] The beneficial effects of this invention are as follows: This invention constructs a comprehensive intelligent construction quality detection system covering process risk prediction, dynamic adjustment of quality thresholds, spatial reconstruction of physical quantities, and multi-dimensional anomaly verification. By establishing a correlation model between construction process parameters and quality characteristics, it achieves early warning and precise location of quality problems. By introducing a dynamic correction mechanism for the quality evolution model using environmental parameters, the quality assessment standards can adapt to changes in the actual construction environment, avoiding the limitations of fixed threshold judgments. Through multi-dimensional cross-validation integrating process risk assessment, physical quantity anomaly detection, and structural defect identification, combined with quality evolution trend analysis during construction, it achieves systematic identification from point anomalies to regional quality status, providing a complete technical solution for the intelligent management and control of the entire process of water conservancy project construction quality. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1This is a flowchart illustrating a method for inspecting the construction quality of a water conservancy project, as provided in an embodiment of the present invention.

[0018] Figure 2 A flowchart of the process risk assessment for a water conservancy project construction quality inspection method provided in an embodiment of the present invention.

[0019] Figure 3 This is a structural block diagram of a water conservancy engineering construction quality inspection system provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Reference Figure 1 This invention discloses a method for inspecting the construction quality of water conservancy projects, which may include: S1: Collect multi-source heterogeneous data during the construction of water conservancy projects through a distributed sensor network and perform preprocessing.

[0022] In this embodiment, to achieve comprehensive monitoring of the construction quality of water conservancy projects, the present invention employs a distributed sensor network to collect data from the construction site. The distributed sensor network includes image sensors, temperature sensors, strain sensors, displacement sensors, and compaction parameter sensors; these sensors work together to acquire multi-dimensional information about the construction process.

[0023] Multi-source heterogeneous data includes sensor monitoring data, construction process parameters, and environmental parameters. Sensor monitoring data is collected by the aforementioned sensors; construction process parameters include at least one of the following: construction procedure type, construction age, pouring speed, vibration time, and number of compaction passes; environmental parameters include ambient temperature and ambient humidity.

[0024] It should be noted that, to facilitate accurate data management and subsequent analysis, the construction area was divided into multiple construction units, each recording corresponding construction process parameters and spatial scope. This data organization method based on construction units lays the foundation for correlation analysis between process parameters and quality monitoring data.

[0025] Furthermore, preprocessing includes time alignment, spatial registration, data format conversion, and noise reduction. Spatial registration is used to uniformly map the spatial range of construction process parameters with the spatial coordinate system of sensor monitoring data.

[0026] S2: Based on construction process parameters, a process-quality correlation model is used to assess the process risk of construction units, calculate the process risk index, and mark potential risk areas.

[0027] Specifically, the process risk assessment flowchart is as follows: Figure 2 As shown, it includes: S2.1: Obtain the construction process parameters corresponding to each construction unit, and select the process parameters that participate in the coupling analysis according to the construction procedure type to obtain the effective process parameter set.

[0028] It should be noted that among the construction process parameters, some parameters are used for coupled risk analysis, while others are only used as identifiers or record information. For example, in the concrete pouring process, pouring speed and vibration time are involved in the coupled analysis, while construction process type and construction age are only used as auxiliary information.

[0029] S2.2: Based on the effective set of process parameters, construct the coupling relationship of process parameters.

[0030] In one embodiment, based on the construction procedure type, typical coupling parameter combinations corresponding to the construction procedure are extracted from a preset construction process knowledge base; based on the effective set of process parameters and typical coupling parameter combinations, candidate coupling parameter pairs under the current construction scenario are determined; based on historical construction data, the coupling coefficient of each candidate coupling parameter pair is calculated, and the coupling coefficient characterizes the influence intensity of parameter synergy on construction quality; candidate coupling parameter pairs with coupling coefficients greater than a preset coupling threshold are screened to construct the process parameter coupling relationship.

[0031] The construction technology knowledge base is established based on the construction specifications of water conservancy projects and stores typical coupling parameter combinations for each construction process; the preset coupling threshold is set based on the construction quality acceptance standards and statistical analysis of historical construction data, and is used to filter strongly coupled parameter pairs.

[0032] S2.3: Based on the process-quality correlation model and the coupling relationship of process parameters, calculate the process risk index corresponding to each construction unit.

[0033] It should be noted that the process-quality correlation model is pre-built based on historical construction data and is used to establish the correlation between construction process parameters and construction quality indicators. It can be implemented using machine learning methods or expert scoring systems.

[0034] Preferably, based on the process-quality correlation model, the single-parameter risk score of each parameter in the effective process parameter set is calculated; for each coupled parameter pair in the process parameter coupling relationship, the coupling risk increment is calculated according to the single-parameter risk score of each parameter and the corresponding coupling coefficient; the single-parameter risk score of each parameter and all coupling risk increments are combined to obtain the process risk index.

[0035] Among them, the single-parameter risk score reflects the degree of risk of a single parameter deviating from the standard, while the coupled risk increment reflects the risk amplification effect caused by the synergistic effect of parameters.

[0036] S2.4: Based on the process risk index, mark the spatial area corresponding to the construction unit that meets the preset risk judgment conditions as a potential risk area, and generate process early warning information corresponding to the potential risk area.

[0037] Furthermore, based on preset risk assessment conditions, the risk level of the process risk index of each construction unit is determined, and the spatial area corresponding to the construction unit that meets the preset risk assessment conditions is marked as a potential risk area; based on the location information, process risk index and risk level of the potential risk area, process early warning information is generated.

[0038] In one embodiment, the preset risk assessment criteria are set according to the construction process type and the water conservancy project construction quality acceptance standards, including a process risk index threshold and risk level classification rules. For example, in the concrete pouring process, a process risk index less than 0.3 is considered low risk, 0.3-0.7 is considered medium risk, and greater than 0.7 is considered high risk.

[0039] This invention, S2, employs a multi-dimensional coupled risk assessment mechanism to fully consider the synergistic effects of construction process parameters on construction quality, achieving more accurate risk identification. By spatially marking potential risk areas, abstract risk indices are transformed into specific spatial location information, facilitating rapid location of problem areas by on-site management personnel. The generated process early warning information integrates location, risk quantification, and dominant risk factors, providing clear decision-making basis and rectification directions for quality control, effectively improving the pertinence and effectiveness of water conservancy project construction quality management.

[0040] S3: Based on construction process parameters and environmental parameters, dynamically calculate the threshold of quality characteristic parameters using a quality evolution model.

[0041] Specifically, S3 includes: S3.1: Based on the construction procedure type and construction age recorded in each construction unit, construction units with the same construction procedure type and construction age differences within a preset time window are merged into an evaluation unit.

[0042] It should be noted that different construction ages correspond to different stages of quality evolution, and the normal ranges of quality characteristic parameters vary. Construction units with different construction ages within a preset time window are merged into evaluation units, and the corresponding quality characteristic parameter thresholds are subsequently calculated for each evaluation unit. The preset time window is determined according to the type of construction procedure; for example, the time window for normal concrete pouring is 3 days, and the time window for roller-compacted concrete construction is 1 day.

[0043] S3.2: For each assessment unit, determine the initial parameter set of the quality evolution model based on the construction procedure type of the assessment unit.

[0044] In one embodiment, based on the construction procedure type, the target quality characteristic parameter type corresponding to the procedure is obtained from a preset quality evolution knowledge base; for each target quality characteristic parameter type, the corresponding evolutionary benchmark curve and initial tolerance range are extracted from the quality evolution knowledge base to form an initial parameter set.

[0045] The quality evolution knowledge base is built based on hydraulic engineering construction specifications and historical construction data. The target quality characteristic parameter type refers to the quality characteristic parameter that needs to be monitored for this construction process. For example, the target quality characteristic parameter types for the concrete pouring process include temperature, stress, and displacement. The evolutionary baseline curve describes the standard evolution trend of the quality characteristic parameter with the construction age, and the initial tolerance range describes the allowable deviation of the quality characteristic parameter at different ages.

[0046] S3.3: Calculate the representative age of the evaluation unit based on the construction age of each construction unit within the evaluation unit, and determine the corresponding theoretical value of quality characteristics based on the representative age and the initial parameter set.

[0047] Furthermore, the average construction age of each construction unit within the evaluation unit is calculated as the representative age; for each type of target quality characteristic parameter in the initial parameter set, the representative age is substituted into the corresponding evolutionary benchmark curve to obtain the theoretical value of the quality characteristic at that age.

[0048] S3.4: Correct the theoretical values ​​of quality characteristics based on the environmental parameters corresponding to the assessment unit.

[0049] In practice, the average environmental parameters within the spatial range corresponding to the assessment unit are obtained; the correction method is determined according to the type of quality characteristic parameter: when the quality characteristic parameter is a temperature-related parameter, the temperature influence coefficient is calculated based on the ambient temperature and the theoretical value of the quality characteristic is corrected; when the quality characteristic parameter is an intensity-related parameter, the comprehensive correction coefficient is calculated based on the ambient temperature and ambient humidity and the theoretical value of the quality characteristic is corrected.

[0050] S3.5: Determine environmental stability based on the fluctuation characteristics of environmental parameters corresponding to the assessment unit, and dynamically adjust the tolerance range of quality characteristic parameters based on the environmental stability determination results.

[0051] In one embodiment, the rate of change of the environmental parameters corresponding to the evaluation unit within the age span of the evaluation unit is calculated; the rate of change is compared with the environmental stability judgment threshold to determine environmental stability; when the rate of change of the environmental parameters exceeds the environmental stability judgment threshold, the environment is determined to be unstable, and the tolerance range of the quality characteristic parameters is adjusted according to the type of quality characteristic parameters and the degree of environmental fluctuation.

[0052] It should be noted that the environmental stability threshold is determined based on the rate of change of the evolutionary baseline curve at the representative age. Environmental instability leads to an increased normal fluctuation range of quality characteristic parameters; dynamically adjusting the tolerance range can avoid misjudgments caused by environmental fluctuations.

[0053] S3.6: Based on the corrected theoretical values ​​of quality characteristics and tolerance range, calculate the upper and lower limits of the threshold values ​​of the quality characteristic parameters of the evaluation unit.

[0054] This invention, S3, achieves dynamic calculation of quality characteristic parameter thresholds through a quality evolution model. By employing an evaluation unit division mechanism, construction units with similar processes and ages are merged for analysis, and thresholds are determined separately for different evolution stages, solving the threshold adaptation problem in construction sites with multiple ages coexisting. Through a dual correction mechanism for environmental parameters, the theoretical values ​​of quality characteristics are corrected based on environmental values, and the tolerance range is dynamically adjusted according to environmental fluctuations, ensuring that the thresholds adapt to actual construction environmental conditions. This partitioned dynamic threshold calculation method avoids the one-sidedness of fixed thresholds and improves the accuracy of anomaly detection, providing a reliable basis for precise monitoring of the construction quality of water conservancy projects.

[0055] S4: Perform spatial reconstruction processing on the sensor monitoring data to obtain the spatial distribution results of each physical quantity.

[0056] Specifically, S4 includes: S4.1: Evaluation unit division results. The sensor monitoring data are classified according to the evaluation unit and the type of physical quantity to form the sub-physical quantity monitoring dataset for each evaluation unit.

[0057] S4.2: For each assessment unit, determine the spatial reconstruction parameters based on the spatial range of the construction units contained in the assessment unit.

[0058] The spatial reconstruction parameters include the interpolation method, spatial resolution, and boundary constraints.

[0059] Specifically, the geometric characteristic parameters of the spatial extent of the construction units contained in the evaluation unit are calculated, including at least one of spatial volume, maximum span, and shape complexity; the spatial distribution density of sensor monitoring data within the evaluation unit is statistically analyzed; the interpolation method and spatial resolution are determined based on the geometric characteristic parameters and spatial distribution density; and the boundary constraints for spatial reconstruction are determined based on the boundary coordinates of the construction units contained in the evaluation unit.

[0060] S4.3: Perform spatial interpolation on the monitoring datasets of the physical quantities of each evaluation unit to obtain the spatial distribution results of each physical quantity of each evaluation unit.

[0061] Furthermore, based on the spatial resolution and boundary constraints in the spatial reconstruction parameters, regular grid points are generated within the spatial range of the evaluation unit; based on the interpolation method in the spatial reconstruction parameters, the physical quantity interpolation at each regular grid point is calculated; the validity of the interpolation results is verified, and interpolation points that do not meet the physical constraints are removed; based on the valid interpolation points, the spatial distribution field of each physical quantity in the evaluation unit is constructed.

[0062] S4.4: Spatially stitch together the spatial distribution results of physical quantities of each assessment unit to form the spatial distribution results of physical quantities of the complete construction area.

[0063] This invention establishes an adaptive correlation mechanism between spatial reconstruction parameters and the geometric features of construction units and sensor distribution density, achieving intelligent matching between interpolation methods and spatial resolution. This ensures that evaluation units with different spatial characteristics can obtain appropriate reconstruction accuracy. By introducing physical constraints to verify the effectiveness of the interpolation results, unreasonable values ​​that may be generated by traditional interpolation methods are avoided, ensuring the physical reliability of the spatial distribution field and providing a reliable data foundation for subsequent quality assessment.

[0064] S5: Based on the spatial distribution results of each physical quantity and the threshold of quality characteristic parameters, perform quality anomaly analysis and structural defect determination on the spatial location within the construction area to obtain quality anomaly areas and defect areas.

[0065] Specifically, S5 includes: S5.1: Compare the spatial distribution results of each physical quantity with the corresponding quality characteristic parameter threshold, and mark the spatial locations that exceed the threshold range as preliminary anomaly locations.

[0066] S5.2: Based on the construction process parameters of the construction unit to which the preliminary abnormal location belongs, determine whether the deviation of physical quantities belongs to the normal fluctuation of the construction process.

[0067] In one embodiment, the construction unit to which the initial abnormal location belongs is determined based on its spatial coordinates, and the construction procedure type and construction age of the construction unit are obtained; based on the construction procedure type, the normal fluctuation range of the corresponding physical quantity is obtained from a preset process fluctuation knowledge base; based on the construction age, the normal fluctuation range of the physical quantity is time-varyingly corrected; it is determined whether the deviation value of the physical quantity at the initial abnormal location is within the corrected normal fluctuation range. If it is within the range, it is determined to be a normal fluctuation of the construction process; otherwise, it is determined to be an abnormal fluctuation.

[0068] S5.3: Identify the initial abnormal locations that do not belong to the normal fluctuations of the construction process as the spatial locations of quality abnormalities.

[0069] S5.4: Perform spatial connectivity analysis on the spatial locations of quality anomalies to form quality anomaly regions.

[0070] Furthermore, based on the spatial coordinates of the spatial locations of the quality anomalies, the spatial distance between any two spatial locations of quality anomalies is calculated; spatial locations of quality anomalies with a spatial distance less than a preset connectivity threshold are determined to be spatially connected; based on the spatial connectivity relationship, the spatial locations of quality anomalies are clustered; for each cluster, the spatial range it covers is determined to form a quality anomaly region.

[0071] In one embodiment, the preset connectivity threshold is set based on the spatial resolution in the spatial reconstruction parameters.

[0072] S5.5: Acquire image sensor data of the quality abnormal area and extract the defect structure features.

[0073] Furthermore, based on the spatial range of the quality anomaly area, the corresponding image sensor and its acquisition time are determined; image data of the image sensor at the corresponding acquisition time are acquired; the image data is preprocessed, including at least one of image enhancement, noise reduction, and edge detection; based on the preprocessed image data, a defect recognition model is used to extract defect structural features, including defect type, defect size, and defect location.

[0074] S5.6: Quality anomaly areas that simultaneously exhibit physical quantity anomalies and defective structural features are identified as defect areas.

[0075] This invention introduces a time-varying correction mechanism for construction process parameters, enabling intelligent differentiation between physical quantity anomalies and normal construction fluctuations, effectively avoiding misjudging normal construction differences as quality issues. By integrating the spatial distribution of physical quantities with the defect structural features of image sensors for dual verification, a cross-verification mechanism of physical characteristics and structural morphology is established, ensuring the reliability of defect determination and significantly improving the accuracy of quality anomaly identification.

[0076] S6: Based on potential risk areas, quality anomaly areas, and defect areas, a comprehensive analysis of the construction area is conducted to generate the quality status identification results of the construction area.

[0077] Specifically, S6 includes: S6.1: Determine the area intersection type of each spatial location based on its affiliation in potential risk areas, quality anomaly areas, and defect areas.

[0078] Preferably, for each spatial location within the construction area, it is determined whether it is located within a potential risk area to obtain a risk marking result; it is determined whether each spatial location is located within a quality anomaly area to obtain an anomaly marking result; it is determined whether each spatial location is located within a defect area to obtain a defect marking result; based on the risk marking result, the anomaly marking result, and the defect marking result, each spatial location is divided into an area intersection type, which includes: risk-only type, risk-anomaly type, risk-anomaly-defect type, anomaly-only type, anomaly-defect type, defect-only type, and normal type.

[0079] S6.2: Obtain the change sequence of regional intersection type at each spatial location in different construction stages, and judge the quality evolution trend based on the change sequence.

[0080] Furthermore, for each spatial location, according to the time sequence of the construction progress stages, the regional intersection type in each construction progress stage is obtained, forming a regional intersection type change sequence; according to the preset type risk level mapping relationship, the regional intersection type change sequence is converted into a risk level change sequence; the change trend of risk level in the risk level change sequence is analyzed; based on the risk level change trend, the quality evolution trend is judged: if the risk level shows a downward trend, it is judged as a quality improvement trend; if the risk level shows an upward trend, it is judged as a quality deterioration trend; if the risk level remains stable, it is judged as a quality stability trend.

[0081] S6.3: Based on the regional intersection type and quality evolution trend, generate the quality status identification results of the construction area.

[0082] Furthermore, based on the regional intersection type and quality evolution trend of each spatial location, the quality status level of each spatial location is determined; according to the quality status level, a treatment suggestion type is assigned to each spatial location; spatial locations with the same quality status level are spatially aggregated to form quality status partitions; based on the quality status level, treatment suggestion type, and quality status partition of each spatial location, the quality status identification result of the construction area is generated.

[0083] This invention achieves multi-dimensional comprehensive identification of construction quality problems by cross-validating potential risk areas, quality anomaly areas, and defect areas, combined with the temporal evolution characteristics of the construction progress stage. This method can distinguish between process warnings and actual quality deterioration, identify the development trend of quality problems, avoid the risk of misjudgment from a single data source, and provide differentiated handling criteria for quality problems of different natures. Through the combined analysis of spatial cross-types and temporal evolution trends, it can accurately identify different stages of quality problem development, especially reversible and irreversible defects in the construction process, thereby supporting dynamic control and timely intervention of construction quality, improving the accuracy of quality inspection and the ability to ensure project safety.

[0084] Accordingly, refer to Figure 3 This invention also provides a water conservancy project construction quality inspection system, which may include: The data acquisition and preprocessing module is used to collect multi-source heterogeneous data during the construction process of water conservancy projects through a distributed sensor network and to perform preprocessing. The process risk assessment module is used to assess the process risk of construction units based on construction process parameters and a process-quality correlation model, calculate the process risk index and mark potential risk areas. The quality threshold calculation module is used to dynamically calculate the threshold of quality characteristic parameters based on the quality evolution model, according to construction process parameters and environmental parameters. The physical quantity spatial reconstruction module is used to perform spatial reconstruction processing on sensor monitoring data by physical quantity to obtain the spatial distribution results of each physical quantity. The quality anomaly and defect determination module is used to perform quality anomaly analysis and structural defect determination on the spatial location of the construction area based on the spatial distribution results of various physical quantities and the threshold of quality characteristic parameters, so as to obtain the quality anomaly area and the defect area. The quality status identification module is used to perform a comprehensive analysis of the construction area based on potential risk areas, quality anomaly areas, and defect areas, and generate quality status identification results for the construction area.

[0085] This invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program; when the computer program is executed by the processor, the processor performs the steps of the water conservancy engineering construction quality detection method as described in any of the above embodiments.

[0086] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the water conservancy engineering construction quality detection method as described in any of the above embodiments.

[0087] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0088] For a description of the computer-readable storage medium provided by the present invention, please refer to the above method embodiments; the present invention will not be described in detail here.

[0089] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be found in the method section.

[0090] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0091] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for inspecting the construction quality of water conservancy projects, characterized in that, include: Multi-source heterogeneous data is collected during the construction of water conservancy projects through a distributed sensor network and preprocessed; the multi-source heterogeneous data includes sensor monitoring data, construction process parameters, and environmental parameters. Based on construction process parameters, a process-quality correlation model is used to assess the process risk of construction units, calculate the process risk index, and mark potential risk areas. Based on construction process parameters and environmental parameters, the threshold values ​​of quality characteristic parameters are dynamically calculated using a quality evolution model. Spatial reconstruction of physical quantities is performed on sensor monitoring data to obtain the spatial distribution results of each physical quantity; Based on the spatial distribution results of various physical quantities and the threshold of quality characteristic parameters, quality anomaly analysis and structural defect determination are carried out on the spatial location within the construction area to obtain quality anomaly areas and defect areas. Based on potential risk areas, quality anomaly areas, and defect areas, a comprehensive analysis of the construction area is conducted to generate a quality status identification result for the construction area.

2. The method for testing the construction quality of water conservancy projects according to claim 1, characterized in that, The process risk assessment of construction units using the process-quality correlation model includes: Obtain the construction process parameters corresponding to each construction unit, and filter out the process parameters participating in the coupling analysis according to the construction procedure type to obtain the effective process parameter set; Based on the set of effective process parameters, a coupling relationship between process parameters is constructed.

3. The method for testing the construction quality of water conservancy projects according to claim 1, characterized in that, The process risk assessment of construction units using the process-quality correlation model also includes: Based on the process-quality correlation model and the coupling relationship of process parameters, the process risk index corresponding to each construction unit is calculated; Based on the process risk index, the spatial area corresponding to the construction unit that meets the preset risk judgment conditions is marked as a potential risk area, and process early warning information corresponding to the potential risk area is generated.

4. The method for testing the construction quality of water conservancy projects according to claim 1, characterized in that, The threshold for dynamically calculating quality characteristic parameters based on the quality evolution model includes: Based on the construction procedure type and construction age recorded by each construction unit, construction units with the same construction procedure type and construction age difference within a preset time window are merged into an evaluation unit. For each assessment unit, an initial parameter set for the quality evolution model is determined based on the construction procedure type of the assessment unit. The initial parameter set includes the target quality characteristic parameter type and its evolution benchmark curve. The representative age of the evaluation unit is calculated based on the construction age of each construction unit within the evaluation unit, and the corresponding theoretical value of quality characteristics is determined based on the representative age and the initial parameter set. The theoretical values ​​of the quality characteristics are corrected based on the environmental parameters corresponding to the evaluation unit; The environmental stability is determined based on the fluctuation characteristics of the environmental parameters corresponding to the assessment unit, and the tolerance range of the quality characteristic parameters is dynamically adjusted based on the environmental stability determination results. Based on the corrected theoretical values ​​of the quality characteristics and the tolerance range, the upper and lower limits of the threshold values ​​of the quality characteristic parameters of the evaluation unit are calculated.

5. The method for testing the construction quality of water conservancy projects according to claim 1, characterized in that, The spatial reconstruction processing of the sensor monitoring data by physical quantities includes: Based on the evaluation unit division results, the sensor monitoring data are classified according to the evaluation unit and the type of physical quantity to form the sub-physical quantity monitoring dataset for each evaluation unit; For each evaluation unit, spatial reconstruction parameters are determined based on the spatial range of the construction units contained in the evaluation unit. The spatial reconstruction parameters include interpolation method, spatial resolution, and boundary constraints. Spatial interpolation processing is performed on the monitoring datasets of physical quantities of each evaluation unit to obtain the spatial distribution results of each physical quantity of each evaluation unit; The spatial distribution results of physical quantities of each assessment unit are spliced ​​together in space to form the spatial distribution results of physical quantities of the complete construction area.

6. The method for testing the construction quality of water conservancy projects according to claim 1, characterized in that, The analysis of quality anomalies and determination of structural defects in the spatial location within the construction area includes: The spatial distribution results of each physical quantity are compared with the corresponding mass characteristic parameter thresholds, and spatial locations that exceed the threshold range are marked as preliminary anomaly locations. Based on the construction process parameters of the construction unit to which the initial abnormal location belongs, determine whether the deviation of physical quantities belongs to the normal fluctuation of the construction process; Preliminary abnormal locations that do not fall under the normal fluctuations of the construction process are identified as spatial locations of quality abnormalities. Spatial connectivity analysis is performed on the spatial locations of the quality anomalies to form quality anomaly regions; Acquire image sensor data of the quality anomaly area and extract defect structural features; A quality anomaly region that simultaneously exhibits physical quantity anomalies and defective structural features is identified as a defect region.

7. The method for testing the construction quality of water conservancy projects according to claim 1, characterized in that, The comprehensive analysis of the construction area includes: Based on the attribution of each spatial location to potential risk areas, quality anomaly areas, and defect areas, determine the area intersection type of each spatial location; Obtain the sequence of regional intersection types changes at different spatial locations during different construction stages, and determine the quality evolution trend based on the sequence of changes; Based on the regional intersection type and quality evolution trend, the quality status identification results of the construction area are generated.

8. A construction quality inspection system for water conservancy projects, characterized in that, include: The data acquisition and preprocessing module is used to collect multi-source heterogeneous data during the construction process of water conservancy projects through a distributed sensor network and to perform preprocessing. The process risk assessment module is used to assess the process risk of construction units based on construction process parameters and a process-quality correlation model, calculate the process risk index and mark potential risk areas. The quality threshold calculation module is used to dynamically calculate the threshold of quality characteristic parameters based on the quality evolution model, according to construction process parameters and environmental parameters. The physical quantity spatial reconstruction module is used to perform spatial reconstruction processing on sensor monitoring data by physical quantity to obtain the spatial distribution results of each physical quantity. The quality anomaly and defect determination module is used to perform quality anomaly analysis and structural defect determination on the spatial location of the construction area based on the spatial distribution results of various physical quantities and the threshold of quality characteristic parameters, so as to obtain the quality anomaly area and the defect area. The quality status identification module is used to perform a comprehensive analysis of the construction area based on potential risk areas, quality anomaly areas, and defect areas, and generate quality status identification results for the construction area.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the water conservancy project construction quality inspection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program, wherein the computer program, when executed by a processor, implements the water conservancy project construction quality inspection method as described in any one of claims 1 to 7.

Images