Quality safety risk management method and system for water conservancy project

Abstract

The invention discloses a quality safety risk management method and system for a water conservancy project, and relates to the technical field of risk management, and the method comprises the steps: obtaining a dam face construction drawing of the water conservancy project, segmenting the dam face construction drawing, and analyzing the multi-dimensional image features of each construction block to determine a construction state; and if the construction state is a paving state, activating an inner layer of the nested management network to perform paving risk analysis, when a paving risk management result accords with a predetermined constraint, collecting dam surface construction information, activating an outer layer network to analyze a rolling risk, and performing quality safety risk management of a water conservancy project according to a rolling risk management result. According to the invention, the technical problem that the real-time and accurate monitoring of the construction process is difficult to realize because the existing hydraulic engineering construction quality safety supervision mainly depends on manual inspection and experience judgment is solved, and the real-time monitoring and risk assessment of the paving and rolling stages are realized by using the intelligent management network. And the real-time performance and the accuracy of construction quality safety supervision are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of risk management, and in particular to a quality safety risk management method and system for water conservancy projects. Background Art

[0002] In water conservancy project construction, quality control of dam surface construction is crucial for ensuring the long-term stability and safety of the project. Traditional quality control methods typically rely on manual inspections and empirical judgment, resulting in low efficiency, a lack of real-time monitoring, and subjective judgments. These methods struggle to effectively address complex construction environments and unexpected issues. Furthermore, existing technologies mostly rely on single sensors or visual inspection systems, failing to integrate data from various stages in real time for intelligent analysis. Especially during the critical stages of paving and compaction, existing systems lack specificity and flexibility, failing to provide accurate and effective construction risk management. Summary of the Invention

[0003] This application provides a quality and safety risk management method and system for water conservancy projects, which is used to solve the technical problem that the existing water conservancy project construction quality and safety supervision mainly relies on manual inspection and experience judgment, making it difficult to achieve real-time and accurate monitoring of the construction process.

[0004] The first aspect of the present application provides a quality and safety risk management method for water conservancy projects, the method comprising: obtaining a dam surface construction drawing of the water conservancy project, and segmenting the dam surface construction drawing to obtain a segmentation result; analyzing a first multidimensional image feature of a first construction block in the segmentation result to obtain a first construction state; if the first construction state is a paving state, activating an inner network in a nested management network to analyze the first multidimensional image feature to obtain a paving risk management result; when the paving risk management result meets predetermined management constraints, collecting dam surface construction information, and activating an outer network in the nested management network to analyze the dam surface construction information to obtain a compaction risk management result; and performing quality and safety risk management of the water conservancy project according to the compaction risk management result.

[0005] The second aspect of the present application provides a quality and safety risk management system for water conservancy projects, the system comprising: a dam surface construction drawing segmentation module, the dam surface construction drawing segmentation module is used to obtain the dam surface construction drawing of the water conservancy project, and segment the dam surface construction drawing to obtain a segmentation result; a construction status analysis module, the construction status analysis module is used to analyze the first multidimensional image feature of the first construction block in the segmentation result to obtain a first construction status; a paving risk management module, the paving risk management module is used to activate the inner network in the nested management network to analyze the first multidimensional image feature if the first construction status is the paving status, and obtain a paving risk management result; a compaction risk management module, the compaction risk management module is used to collect dam surface construction information when the paving risk management result meets the predetermined management constraints, and activate the outer network in the nested management network to analyze the dam surface construction information to obtain a compaction risk management result; a quality and safety risk management module, the quality and safety risk management module is used to perform quality and safety risk management of the water conservancy project according to the compaction risk management result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The quality and safety risk management method and system for water conservancy projects provided in this application relate to the field of risk management technology. By obtaining the dam surface construction drawings of the water conservancy project and segmenting them, the multi-dimensional image features of each construction block are analyzed to judge the construction status. If it is in the paving state, the inner layer of the nested management network is activated to analyze the paving risk. After the paving risk meets the predetermined constraints, the outer network is activated to analyze the rolling risk and perform quality and safety risk management. This solves the technical problem that the existing water conservancy project construction quality and safety supervision mainly relies on manual inspection and experience judgment, and it is difficult to achieve real-time and accurate monitoring of the construction process. It realizes real-time monitoring and risk assessment of the paving and rolling stages through the use of an intelligent management network, improves the real-time and accuracy of construction quality and safety supervision, and thus improves the overall construction efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A flow chart of a quality and safety risk management method for water conservancy projects provided in an embodiment of the present application; Figure 2A schematic structural diagram of a quality and safety risk management system for water conservancy projects provided in an embodiment of the present application.

[0009] Explanation of the accompanying drawings: dam surface construction drawing segmentation module 11, construction status analysis module 12, paving risk management module 13, rolling risk management module 14, quality and safety risk management module 15. DETAILED DESCRIPTION

[0010] This application provides a quality and safety risk management method and system for water conservancy projects, which is used to solve the technical problem that the existing water conservancy project construction quality and safety supervision mainly relies on manual inspection and experience judgment, making it difficult to achieve real-time and accurate monitoring of the construction process.

[0011] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0012] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] Example 1, as Figure 1 As shown, the present application provides a quality safety risk management method for water conservancy projects, the method comprising: P10: Obtain a dam surface construction drawing of a water conservancy project, and segment the dam surface construction drawing to obtain a segmentation result.

[0014] Specifically, the first step is to obtain the dam construction drawings for the water conservancy project. These drawings are a crucial part of the water conservancy project design phase, detailing the dam's structural layout, construction details, and related technical parameters. These drawings are typically stored in digital form to facilitate subsequent processing and analysis. These drawings can be obtained in a variety of ways, such as by obtaining electronic copies from the project's design firm or by converting paper drawings into digital format through on-site scanning.

[0015] After obtaining the construction drawings, the key step is to segment the dam surface construction drawings. That is, using image processing technology, the complete dam surface construction drawings are divided into several areas or construction blocks with specific characteristics. For example, this can be achieved based on an image segmentation algorithm, which can accurately identify different construction areas based on the differences in color, texture, shape and other features in the construction drawings. For example, the boundaries of different areas in the construction drawings can be identified through edge detection algorithms, thereby achieving effective segmentation of the construction drawings. In actual operation, mature image processing software or programming tools can be used to implement this function, such as MATLAB, Python, etc. By analyzing the shape, identifier and coordinate information in the construction drawings, different areas in the drawings can be automatically identified and reasonably divided. This processing can greatly reduce manual operation errors, while improving segmentation efficiency and accuracy, making the division of each construction unit more scientific and reasonable.

[0016] After the segmentation is complete, the resulting data is multiple independent construction areas, each containing specific construction requirements, schedules, risk assessments, and other information. This segmented data not only provides a clearer framework for construction site management but also provides the necessary data support for subsequent construction monitoring and quality, safety, and risk management.

[0017] P20: Analyze the first multi-dimensional image feature of the first construction block in the segmentation result to obtain a first construction state.

[0018] Furthermore, step P20 in this embodiment of the present application further includes: P21: Extract the first texture feature from the first multidimensional image feature; P22: Calculate the first deviation value between the first texture feature and the predetermined texture feature, and determine the first construction state based on the first deviation value; wherein, including: if the first deviation value is within the predetermined deviation threshold, the first construction state is the rolling state; if the first deviation value is not within the predetermined deviation threshold, the first construction state is the paving state; wherein, the predetermined texture feature refers to the image texture feature of the dam surface of the water conservancy project in the standard state after the rolling construction.

[0019] It should be understood that the first multi-dimensional image feature analysis is performed on the first construction block in the segmentation results to determine the construction status of the construction block. A key indicator of this analysis process is a series of image features extracted from construction drawings or on-site images. These image features are digital representations of the surface details of the construction block, including but not limited to texture, color distribution, surface smoothness, and other information. By extracting and analyzing these features, the current construction stage or status of the construction block can be accurately determined, providing a basis for subsequent construction management and risk control.

[0020] Specifically, first, the first texture feature is extracted from the multidimensional image features. Texture features usually refer to the pattern, shape or structure of the texture on the image surface, which can reflect the state and degree of treatment of the surface material during the construction process. In the dam surface construction of water conservancy projects, texture features can reflect the quality of construction. For example, the dam surface in the rolling stage will show different texture features from that in the paving stage, usually showing a more compact and uniform surface structure. Through image processing algorithms, such as gray level co-occurrence matrix (GLCM) and local binary pattern (LBP), these methods can quantify texture features and provide a data basis for subsequent deviation calculations. Taking the gray level co-occurrence matrix as an example, statistics such as image contrast, correlation, and energy can be calculated. These statistics can comprehensively reflect the texture characteristics of the image.

[0021] Next, a first deviation value between the first texture feature and a predetermined texture feature is calculated. The predetermined texture feature refers to the texture feature of the dam surface image of the hydraulic engineering dam surface in the standard state after rolling construction. By comparing with the predetermined texture feature, the difference between the current state of the construction block and the ideal state can be quantified. The method for calculating the first deviation value can be to calculate the Euclidean distance between the two texture features. The specific formula is: ,in, represents the i-th statistic of the first texture feature, The i-th statistic representing the predetermined texture feature, where n is the total number of statistics. The first construction state is determined based on the comparison between the first deviation value and the predetermined deviation threshold: if the first deviation value is within the predetermined deviation threshold, the first construction state is the rolling state, indicating that the texture features of the construction block are similar to the qualified state after rolling, indicating that the construction block has completed rolling construction and the construction quality meets the requirements; if the first deviation value is not within the predetermined deviation threshold, the first construction state is the paving state, indicating that the texture features of the construction block are significantly different from the qualified state after rolling, indicating that the construction block has not yet completed rolling construction and may still be in the paving stage.

[0022] During implementation, the characteristics of the construction drawings and construction requirements should be fully considered. Appropriate texture feature extraction methods and deviation calculation methods should be selected, and appropriate deviation thresholds should be set. The predetermined deviation threshold should be determined based on actual engineering experience and experimental data. A reasonable deviation threshold range can be determined through experimental analysis of construction blocks with known conditions. Furthermore, a corresponding data storage and management mechanism should be established to store and manage the extracted texture features and calculated deviation values, allowing for convenient access and processing of this data in subsequent steps. For example, a database or file system could be used to store this information, and corresponding data indexes could be established to improve data retrieval efficiency.

[0023] Through the above steps, the construction status of the dam surface can be monitored in real time during construction, thereby determining whether it meets the predetermined quality standards. This method provides a precise status monitoring mechanism for the construction process of water conservancy projects, helping project managers to identify problems in a timely manner and avoid subsequent safety and quality risks caused by substandard construction quality.

[0024] Furthermore, step P21 of the embodiment of the present application further includes: P21-1: Perform discrete cosine transform processing on the first construction block to obtain a first DCT coefficient; P21-2: Read a predetermined texture factor, and use the predetermined texture factor as a weight to adjust the first AC coefficient in the first DCT coefficient to obtain a first texture value; P21-3: Use the first texture value to characterize the first texture feature.

[0025] Optionally, the extraction process of the first texture feature of the first construction block can be further refined. Specifically, the first construction block is first subjected to a discrete cosine transform (DCT) to obtain first DCT coefficients. The discrete cosine transform is a mathematical transformation method that converts an image from the spatial domain to the frequency domain. It concentrates the energy in the image into a small number of coefficients, facilitating subsequent feature extraction and analysis. Through DCT processing, the image data of the first construction block can be converted into DCT coefficients, which reflect the energy distribution of the image at different frequencies.

[0026] Next, a predetermined texture factor is read and, using this predetermined texture factor as a weight, the first AC coefficient within the first DCT coefficient is adjusted to obtain a first texture value. The predetermined texture factor is a pre-set weighting parameter based on the texture characteristics of the dam surface construction of a hydraulic project. It emphasizes the important frequency components associated with the construction texture. The first AC coefficient refers to the alternating current (AC) portion of the DCT coefficient, which contains the texture information of the image. By weighting the first AC coefficient, a first texture value that better reflects the texture characteristics of the construction block is obtained.

[0027] Finally, the first texture value is used to represent the first texture feature. The first texture value is a weighted DCT coefficient that effectively characterizes the texture characteristics of the first construction block. This extracted texture feature not only considers the image's frequency distribution but also incorporates predetermined texture factors. This improves the representativeness and discriminability of the texture feature, providing a more accurate basis for subsequent construction status identification.

[0028] In practical applications, the calculation of the discrete cosine transform can be implemented using the fast Fourier transform (FFT) algorithm to improve computational efficiency. The setting of the predetermined texture factor needs to be optimized based on the specific texture characteristics of the dam surface construction of the hydraulic project. Appropriate weighting parameters can be determined by analyzing a large amount of sample data. Furthermore, a corresponding data storage and management mechanism should be established to store and manage the extracted first texture values so that subsequent steps can easily access and process this data. For example, a database or file system can be used to store this information, and corresponding data indexes can be established to improve data retrieval efficiency.

[0029] In summary, through the discrete cosine transform processing, weighted adjustment, and texture value representation in the above steps, the first texture feature of the first construction block can be accurately extracted. This process not only provides an important basis for subsequent construction status identification, but also improves the accuracy and reliability of texture feature extraction.

[0030] P30: If the first construction state is the paving state, activate the inner network in the nested management network to analyze the first multi-dimensional image features to obtain a paving risk management result.

[0031] Furthermore, step P30 in this embodiment of the present application further includes: P31: Extract the first hue feature from the first multidimensional image feature; P32: Weight the first hue feature and the first texture feature to obtain the first eigenvalue of the first construction block; P33: Extract the first significance index from the first multidimensional image feature; P34: Use the first eigenvalue and the first significance index as input variables of the paving risk identification model in the inner network to obtain output information; P35: Use the output information as the paving risk management result; wherein, the paving risk identification model refers to an intelligent model obtained by supervised machine learning on a training data set based on historical dam surface construction drawings, and the training data set includes the eigenvalues, significance indexes and an indication of whether there is a paving risk of the historical dam surface construction drawings.

[0032] It should be understood that when determining whether the first construction state is the paving state, if the first construction state is determined to be the paving state, the inner network in the nested management network is activated, and further analysis of the first multidimensional image features is performed to obtain paving risk management results during the paving process. The paving stage is one of the key stages in the dam surface construction of water conservancy projects. The paving quality directly affects the subsequent rolling effect. Therefore, the management of paving risks is crucial.

[0033] Specifically, the first hue feature is first extracted from the first multidimensional image feature. The hue feature describes the distribution of colors in the image and is usually used to reflect the surface uniformity during dam construction. For example, during the paving process, if the hue distribution is uneven, it may mean that the paving material is unevenly laid, or there are problems in the construction (such as uneven material distribution). By extracting these hue features, a preliminary basis can be provided for judging the paving quality. The method for extracting hue features can be to convert the image from the RGB color space to other color spaces (such as HSV or LAB), and then calculate the statistics of the hue component, such as the mean, variance, etc. These statistics can quantify the hue characteristics and provide data support for subsequent risk assessment.

[0034] Next, the first hue feature and the first texture feature are weighted to produce a combined first eigenvalue. This weighting process assigns different weights to hue and texture features based on their importance in paving risk management. For example, if texture is more critical in identifying paving risk, it will be given a higher weight. This weighting allows for a comprehensive eigenvalue, combining both hue and texture characteristics, for subsequent risk assessment.

[0035] Furthermore, a first saliency index is extracted from the first multidimensional image features. The saliency index refers to the prominence of certain regions or features relative to other regions in the image. It can reflect possible anomalies or critical areas within the construction block. There are various methods for extracting a saliency index, such as methods based on visual saliency models, which can identify areas within the image that attract the human eye, providing important information about potential problem areas within the construction block for subsequent risk identification.

[0036] The first eigenvalue and the first significance index are then used as input variables for the paving risk identification model in the inner network, yielding output information. The paving risk identification model is an intelligent model derived through supervised machine learning of a training dataset based on historical dam surface construction drawings. This training dataset contains the eigenvalues and significance index of the historical dam surface construction drawings, as well as an indicator of whether paving risks exist. Using machine learning algorithms (such as support vector machines and neural networks), the model learns the relationship between the eigenvalues and significance index and paving risks, enabling accurate identification of paving risks. The first eigenvalue and the first significance index are input into the model, which then outputs information about paving risks based on this knowledge.

[0037] Finally, the output information is used as the paving risk management results. These include the identification of potential pavement problems (such as cracks, looseness, and rutting). If the model output indicates a paving risk, such as cracks, looseness, or rutting, appropriate risk control measures are required. If the model output indicates no paving risk, the next step, compaction construction, can be carried out.

[0038] In practical applications, the extraction methods for tonal and texture features, as well as the calculation method for the significance index, should be appropriately selected based on the specific construction conditions of the dam surface of a hydraulic project. Furthermore, the paving risk identification model needs to be fully trained and validated to ensure its accuracy and reliability. Furthermore, a corresponding data storage and management mechanism should be established to store and manage the extracted feature values and significance indexes, as well as the model's output information, so that subsequent steps can easily access and process this data. For example, a database or file system could be used to store this information, and corresponding data indexes could be established to improve data retrieval efficiency.

[0039] In general, through the above steps, the system can monitor the quality status of the paving process in real time. By combining image features and intelligent models, it can automatically judge and feedback potential risks in the paving process, provide guidance for subsequent construction operations, and ensure the stability and safety of the dam surface construction quality of water conservancy projects.

[0040] Furthermore, step P33 of the embodiment of the present application also includes: P33-1: Using a feature extraction channel, extract features of predetermined feature dimensions from the first construction block to obtain a first extracted feature; the predetermined feature dimensions include brightness, red hue, green hue, blue hue, and direction. P33-2: Perform center-periphery difference analysis on the first extracted feature to obtain a first feature comparison map. P33-3: Normalize the area of the significant regions in the first feature comparison map to obtain the first significance index.

[0041] Optionally, the process of extracting the first saliency index for the first construction block can be further refined. Specifically, the feature extraction channel first extracts features of predetermined feature dimensions from the first construction block to obtain a first extracted feature. In this process, the predetermined feature dimensions include brightness, red hue, green hue, blue hue, and direction. Brightness features reflect the lightness or darkness of the construction block, while red, green, and blue hue features help capture the color information of the construction material. Direction features reveal the directionality of lines or textures within the construction block. By combining these feature dimensions, a comprehensive description of the visual characteristics of the first construction block can be achieved, laying the foundation for subsequent saliency analysis.

[0042] Subsequently, a center-surrounding difference analysis is performed on the first extracted feature to generate a first feature comparison map. Center-surrounding difference analysis is a method commonly used in image processing, which is mainly used to highlight the difference between the central area and the surrounding area of the image. In construction quality monitoring, the central area is often the key area of construction, and any unevenness or defects will be manifested in this part. Therefore, through this difference analysis, for each pixel in the first extracted feature, the difference between it and the surrounding pixels in feature dimensions such as brightness, hue and direction is calculated, which can clearly identify potential problems in the construction area, especially during the paving process. The difference between the central and surrounding areas may reflect the unevenness of construction materials or deficiencies in construction operations. The generated first feature comparison map will show the difference information of each area in the image, helping managers to understand the spatial distribution of construction quality more clearly.

[0043] Next, the areas of the significant regions in the first feature comparison map are normalized to obtain the first significance index. The purpose of normalization is to adjust the values of the significant regions to a uniform range, such as [0, 1]. This facilitates subsequent comparison and analysis and helps eliminate the impact of size differences between construction blocks. Specifically, the ratio of the significant region area to the total area of the construction block can be calculated and used as the first significance index. A higher significance index indicates a greater proportion of the significant region in the construction block, and potential problems or anomalies are more worthy of attention.

[0044] In practical applications, feature extraction channels can be implemented using a variety of image processing techniques and algorithms. For example, brightness features can be extracted using grayscale processing; hue features can be extracted by converting the image from RGB to HSV color space and then extracting the hue component. Directional features can be extracted using edge detection algorithms such as the Sobel operator or the Canny operator to detect edge directions in the image. Center-surround difference analysis can be achieved by calculating the feature difference between a pixel and its neighboring pixels, while normalization can be performed using simple mathematical operations.

[0045] Furthermore, to ensure the accuracy and reliability of the saliency index, the feature extraction pipeline and difference analysis algorithm need to be thoroughly tested and optimized. Experimental analysis of images with known salient regions can be conducted to adjust algorithm parameters to improve the performance of saliency detection. Furthermore, appropriate data storage and management mechanisms should be established to store and manage the extracted first saliency index, allowing for convenient access and processing of this data in subsequent steps. For example, a database or file system could be used to store this information, and corresponding data indexes could be established to improve data retrieval efficiency.

[0046] Through these steps, the system can not only extract and analyze multi-dimensional features in construction images, but also deeply explore the spatial difference information in the images, further improving the detection accuracy of paving quality.

[0047] Furthermore, if the first construction state is a paving state, activating an inner network in the nested management network to analyze the first multi-dimensional image features to obtain a paving risk management result, and then further comprising: P31a: Continuously monitor the operation of the paver to obtain paving operation information; P32a: Compare the paving operation information with the predetermined paving operation information, and analyze to obtain the paving health; P33a: Use the paving health to verify the paving risk management results.

[0048] In a possible embodiment of the present application, after obtaining the paving risk management results, in order to further ensure the accuracy and reliability of the results, it is necessary to monitor and analyze the operating status of the paver.

[0049] First, the paver is continuously monitored to obtain paving operation information. This information covers various operating parameters of the paver during construction, such as paving speed, paving temperature, hopper level, auger speed, and screed plate temperature. Various sensors installed on the paver collect these operating parameters in real time, enabling continuous monitoring of the paver's operating status. Sensor types include speed sensors, temperature sensors, and level sensors. These sensors convert the collected physical quantities into electrical signals, which are then transmitted to the monitoring system for processing and analysis.

[0050] Next, the collected paving operation information is compared with the predetermined paving operation information and analyzed to obtain the paving health. The predetermined paving operation information is a parameter range or standard value pre-set according to the normal operating status of the paver. It reflects the operation of the paver under ideal construction conditions. By comparing the actual paving operation information with the predetermined paving operation information, abnormal conditions that may occur during the operation of the paver can be identified. For example, if the paving speed is lower than the predetermined speed range, it may indicate that the paver has insufficient power or poor material feeding; if the paving temperature is too high or too low, it may affect the performance of the construction material and the paving quality. By comprehensively analyzing the comparison results of various operating parameters, the health status of the paver, that is, the paving health, can be evaluated. The assessment of paving health can be carried out using a quantitative method, such as setting a weight for each operating parameter and calculating the health score based on the degree of deviation from the predetermined value.

[0051] Finally, the paving risk management results are validated using the paving health. The validation of paving health can be based on the following principle: Paving problems, such as cracks, looseness, and rutting, are more likely to occur when equipment operating problems occur. If the paving health is low, indicating that the paver is operating poorly, then the construction quality should be reassessed even if the paving risk management results indicate no paving risk, as equipment failure could lead to undetected problems during construction. Conversely, if the paving health is high and the paving risk management results also indicate no paving risk, then the construction quality can be considered good with greater confidence, and the next construction phase, compaction, can be advanced.

[0052] In practical applications, continuous operation monitoring of paver machines can be achieved through a network of sensors installed on the paver. These sensors should be highly accurate and reliable to ensure the accuracy of the collected operational information. A real-time monitoring system is also needed to rapidly process and analyze the collected operational data and provide timely feedback on paving health. Furthermore, the parameter ranges and standard values for the predetermined paving operation information should be appropriately set based on the specific construction requirements and paver model. Regular calibration and maintenance of the monitoring system should be performed to ensure long-term stable operation.

[0053] This process not only improves the accuracy of paving risk management, but also provides a basis for timely detection and resolution of paver operation problems, thereby further ensuring the quality and safety of dam surface construction of water conservancy projects.

[0054] P40: When the paving risk management result meets the predetermined management constraints, dam surface construction information is collected and the outer network in the nested management network is activated to analyze the dam surface construction information to obtain a compaction risk management result. The dam surface construction information includes the number of compaction passes, vibration frequency, driving speed, driving direction, and compaction meter value (CMV).

[0055] Furthermore, step P40 in this embodiment of the present application further includes: P41: The dam surface construction information is analyzed through the compaction risk identification model in the outer network to obtain the predicted dam surface relative density; P42: The compaction coefficient is introduced to weight the predicted dam surface relative density to obtain the dam surface compaction quality index; P43: The compaction risk management result is characterized by the dam surface compaction quality index.

[0056] It should be understood that when the paving risk management results meet the pre-defined management constraints, indicating that there are no significant risks during the paving construction phase, the system will then collect information related to dam surface construction and activate the outer network within the nested management network to further analyze the collected dam surface construction information to obtain the compaction risk management results. Dam surface construction information includes multiple parameters, such as the number of rolling passes, vibration frequency, vehicle speed, driving direction, and compaction meter value (CMV). These parameters are key indicators for evaluating compaction construction quality and reflect the execution and effectiveness of the compaction process. The number of rolling passes and vibration frequency directly reflect the performance of the roller during construction, while vehicle speed and driving direction affect compaction quality. The compaction meter value (CMV) is an important indicator for assessing the degree of compaction of the soil or construction surface.

[0057] Specifically, the compaction risk identification model in the outer network first analyzes the collected dam surface construction information to obtain a predicted dam surface relative density. This intelligent model, trained based on historical data, predicts the relative density of the dam surface based on current dam surface construction information. Relative density is a key indicator of soil compaction, reflecting the relationship between the soil's density after compaction and its maximum density. Predicting the relative density of the dam surface provides a preliminary assessment of the quality of compaction construction.

[0058] Next, the predicted relative density of the dam surface is weighted by the compaction coefficient to obtain the dam surface compaction quality index. The compaction coefficient is a parameter set based on engineering experience and specific construction requirements. It reflects the degree to which compaction quality affects the final construction quality. By weighting the predicted relative density of the dam surface, a dam surface compaction quality index that comprehensively considers the compaction coefficient can be obtained. This index more comprehensively reflects the quality of the rolling construction.

[0059] Finally, the dam surface compaction quality index (DQI) is used to characterize the results of rolling risk management. This index is a quantitative indicator that intuitively reflects the quality and risk profile of rolling operations. If the DQI meets the predetermined standard, it indicates good rolling quality and no significant risks. Conversely, if the index falls below the predetermined standard, appropriate risk control measures are necessary, such as adjusting rolling parameters or increasing the number of rolling passes.

[0060] Furthermore, the process of constructing the crushing risk identification model includes: P41-1a: Collect historical dam surface compaction construction records and extract the first historical record from the historical dam surface compaction construction records; P41-2a: Extract the first historical dam surface construction information and the first historical dam surface relative density from the first historical record and form a first data set; P41-3a: Train the first data set and verify it to obtain the compaction risk identification model.

[0061] Specifically, first collect the historical dam surface compaction construction records and extract the first historical records from them. These historical records contain detailed information in the previous construction process and are an important data basis for building the model. Then, extract the first historical dam surface construction information and the first historical dam surface relative density from the first historical records and form the first data set. These data sets provide rich samples for model training, enabling the model to learn the intrinsic relationship between construction information and dam surface relative density. The first data set is trained and tested to obtain a compaction risk identification model. The training process can use machine learning algorithms such as linear regression, support vector machines or neural networks to ensure that the model has good predictive performance and generalization capabilities. The testing process evaluates the accuracy and reliability of the model through methods such as cross-validation, thereby obtaining an effective compaction risk identification model.

[0062] In practical applications, to ensure the accuracy and reliability of compaction risk management results, precise collection and recording of dam surface construction information is necessary. Furthermore, the construction and training of compaction risk identification models should be based on a large amount of high-quality historical data and employ advanced machine learning algorithms and optimization techniques. Furthermore, the compaction coefficient should be adjusted according to specific project requirements and construction conditions to ensure that the dam surface compaction quality index truly reflects construction quality. These measures can effectively assess the quality and risks of compaction construction, providing strong support for the construction of water conservancy projects.

[0063] In summary, through a series of data collection, feature extraction, weighted processing, and intelligent model analysis, the system can accurately assess risks during the compaction process and provide corresponding quality control recommendations. By verifying the compaction risk management results in real time, it ensures that the quality of the dam surface construction during the compaction phase of the water conservancy project meets the design standards, thereby improving the overall stability and safety of the project.

[0064] P50: Conduct quality and safety risk management of the water conservancy project based on the compaction risk management results.

[0065] Specifically, based on the compaction risk management results obtained in the above steps, the overall quality and safety of the water conservancy project is comprehensively managed. This process is a key link in the quality and safety risk management of the entire water conservancy project. By integrating the risk assessment results of the early paving and compaction construction phases, the quality and safety of the entire construction process are guaranteed.

[0066] First, a comprehensive analysis of the compaction risk management results is conducted. These results are presented as a dam surface compaction quality index, which integrates dam surface construction information (such as the number of rolling passes, vibration frequency, vehicle speed, driving direction, and compaction meter value (CMV)) and the influence of the compaction coefficient. If the dam surface compaction quality index meets or exceeds the predetermined standard, it indicates that the compaction construction quality is good and there are no significant risks, allowing subsequent construction processes to proceed. Conversely, if the index falls below the predetermined standard, it indicates possible quality issues with the compaction construction, such as insufficient or uneven compaction, and appropriate risk control measures are required.

[0067] Next, based on the results of compaction risk management, a corresponding quality and safety risk control strategy is developed. If risks exist, the causes must be analyzed and targeted corrective measures implemented. For example, a low compaction quality index may be due to insufficient compaction passes, an inappropriate vibration frequency, or excessive vehicle speed. These issues can be addressed by increasing the number of compaction passes, adjusting the vibration frequency, or reducing vehicle speed. Furthermore, already compacted sections may require additional compaction or recompaction to ensure the dam surface compaction quality meets design requirements.

[0068] After implementing risk control measures, the effectiveness of the corrective actions needs to be verified. This can be achieved by collecting dam surface construction data again and reassessing the dam surface compaction quality index using the compaction risk identification model. If the post-correction compaction quality index meets the predetermined standard, the risk can be confirmed to have been effectively controlled, and subsequent construction can proceed. If the corrective actions are unsatisfactory, further analysis of the causes is necessary, and more effective corrective measures should be implemented until the risk is fully controlled.

[0069] Furthermore, risk management results from the paving and compaction phases must be integrated to form a comprehensive assessment of the overall quality and safety of the water conservancy project. This includes comprehensive consideration of potential quality issues such as cracks, looseness, and rutting during construction, as well as monitoring and evaluation of the operating status of construction equipment. This comprehensive management approach ensures that every aspect of the water conservancy project construction process meets quality requirements, thereby guaranteeing the quality and safety of the entire project.

[0070] In summary, the embodiments of the present application have at least the following technical effects: This application realizes real-time monitoring of construction status such as paving and rolling through segmentation and multi-dimensional image feature analysis of dam surface construction drawings, which can timely identify anomalies and risks in the construction process to ensure construction progress and quality; combines nested management networks to perform intelligent risk analysis of the paving and rolling stages, automatically evaluates construction quality and potential risks, provides data-driven decision support, and optimizes quality control during the construction process; collects dam surface construction information (such as the number of rolling times, vibration frequency, etc.) in real time and analyzes it in combination with historical construction data to improve the comprehensive utilization efficiency of construction data and ensure the accuracy of construction quality assessment; through timely identification and effective management of risks, reduces quality hazards and safety accidents in construction, ensures the smooth progress of water conservancy project construction, and improves overall construction efficiency and safety.

[0071] The technical effect of using the intelligent management network to conduct real-time monitoring and risk assessment during the paving and rolling stages has been achieved, thereby improving the real-time and accuracy of construction quality and safety supervision, and thereby enhancing overall construction efficiency and safety.

[0072] Example 2, based on the same inventive concept as the quality safety risk management method for water conservancy projects in the previous embodiment, Figure 2 As shown, this application provides a quality safety risk management system for water conservancy projects. The system and method embodiments in the embodiments of this application are based on the same inventive concept. The system includes: The dam surface construction drawing segmentation module 11 is used to obtain the dam surface construction drawing of the water conservancy project and segment the dam surface construction drawing to obtain a segmentation result.

[0073] The construction status analysis module 12 is configured to analyze the first multi-dimensional image feature of the first construction block in the segmentation result to obtain a first construction status.

[0074] The paving risk management module 13 is used to activate the inner network in the nested management network to analyze the first multi-dimensional image features if the first construction state is the paving state, so as to obtain a paving risk management result.

[0075] The compaction risk management module 14 is used to collect dam surface construction information when the paving risk management result meets the predetermined management constraints, and activate the outer network in the nested management network to analyze the dam surface construction information to obtain the compaction risk management result.

[0076] The quality and safety risk management module 15 is used to perform quality and safety risk management of the water conservancy project according to the compaction risk management result.

[0077] Furthermore, the construction status analysis module 12 is further configured to perform the following steps: Extract the first texture feature from the first multidimensional image feature; calculate the first deviation value between the first texture feature and the predetermined texture feature, and determine the first construction state according to the first deviation value; wherein, including: if the first deviation value is within the predetermined deviation threshold, the first construction state is the rolling state; if the first deviation value is not within the predetermined deviation threshold, the first construction state is the paving state; wherein, the predetermined texture feature refers to the image texture feature of the dam surface of the water conservancy project in the standard state after the rolling construction.

[0078] Furthermore, the construction status analysis module 12 is further configured to perform the following steps: Performing discrete cosine transform processing on the first construction block to obtain a first DCT coefficient; reading a predetermined texture factor, and adjusting a first AC coefficient in the first DCT coefficient using the predetermined texture factor as a weight to obtain a first texture value; and characterizing the first texture feature using the first texture value.

[0079] Furthermore, the paving risk management module 13 is further configured to perform the following steps: Extract the first hue feature from the first multidimensional image feature; weight the first hue feature and the first texture feature to obtain the first eigenvalue of the first construction block; extract the first significance index from the first multidimensional image feature; use the first eigenvalue and the first significance index as input variables of the paving risk identification model in the inner network to obtain output information; use the output information as the paving risk management result; wherein, the paving risk identification model refers to an intelligent model obtained by supervised machine learning of a training data set composed based on historical dam surface construction drawings, and the training data set includes the eigenvalue, significance index and an indication of whether there is a paving risk of the historical dam surface construction drawings.

[0080] Furthermore, the paving risk management module 13 is further configured to perform the following steps: A feature extraction channel is used to extract features of predetermined feature dimensions from the first construction block to obtain a first extracted feature. The predetermined feature dimensions include brightness, red hue, green hue, blue hue, and direction. A center-periphery difference analysis is performed on the first extracted feature to obtain a first feature comparison map. The area of the significant region in the first feature comparison map is normalized to obtain a first significance index.

[0081] Furthermore, the paving risk management module 13 is further configured to perform the following steps: Continuously monitor the operation of the paver to obtain paving operation information; compare the paving operation information with predetermined paving operation information and analyze to obtain paving health; and verify the paving risk management results using the paving health.

[0082] Furthermore, the crushing risk management module 14 is further configured to perform the following steps: The dam surface construction information is analyzed using the compaction risk identification model in the outer network to obtain a predicted dam surface relative density; the predicted dam surface relative density is weighted by introducing a compaction coefficient to obtain a dam surface compaction quality index; the dam surface compaction quality index is used to characterize the compaction risk management results; wherein, the construction process of the compaction risk identification model includes: collecting historical dam surface compaction construction records and extracting a first historical record from the historical dam surface compaction construction records; extracting the first historical dam surface construction information and the first historical dam surface relative density from the first historical record to form a first data set; training the first data set and verifying it to obtain the compaction risk identification model. wherein, the dam surface construction information includes the number of compaction passes, vibration frequency, driving speed, driving direction, and compaction meter value (CMV).

[0083] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0085] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A quality safety risk management method for water conservancy projects, characterized in that: include: Obtaining a dam surface construction drawing of a water conservancy project, and segmenting the dam surface construction drawing to obtain a segmentation result; Analyzing a first multi-dimensional image feature of a first construction block in the segmentation result to obtain a first construction state; If the first construction state is a paving state, activating an inner network in the nested management network to analyze the first multi-dimensional image features to obtain a paving risk management result; When the paving risk management result meets the predetermined management constraint, dam surface construction information is collected, and the outer network in the nested management network is activated to analyze the dam surface construction information to obtain a rolling risk management result; Quality and safety risk management of the water conservancy project is carried out based on the compaction risk management results.

2. The quality safety risk management method for water conservancy projects according to claim 1, characterized in that: Analyzing a first multi-dimensional image feature of the first construction block in the segmentation result to obtain a first construction state includes: extracting a first texture feature from the first multidimensional image feature; calculating a first deviation value between the first texture feature and a predetermined texture feature, and determining the first construction state according to the first deviation value; Among them, include: If the first deviation value is within a predetermined deviation threshold, the first construction state is a rolling state; If the first deviation value is not within the predetermined deviation threshold, the first construction state is a paving state; The predetermined texture features refer to the image texture features of the dam surface of the water conservancy project in a standard-compliant state after compaction construction.

3. The quality safety risk management method for water conservancy projects according to claim 2, characterized in that: Extracting a first texture feature from the first multidimensional image feature includes: Performing discrete cosine transform processing on the first construction block to obtain a first DCT coefficient; Reading a predetermined texture factor, and adjusting a first AC coefficient in the first DCT coefficient using the predetermined texture factor as a weight to obtain a first texture value; The first texture feature is represented by the first texture value.

4. The quality safety risk management method for water conservancy projects according to claim 2, characterized in that: If the first construction state is the paving state, activating the inner network in the nested management network to analyze the first multi-dimensional image features to obtain a paving risk management result, including: extracting a first hue feature from the first multidimensional image features; weighting the first hue feature and the first texture feature to obtain a first feature value of the first construction block; extracting a first significance index from the first multidimensional image feature; Using the first eigenvalue and the first significance index as input variables of a paving risk identification model in the inner network to obtain output information; Using the output information as the paving risk management result; Among them, the paving risk identification model refers to an intelligent model obtained by supervised machine learning on a training data set based on historical dam surface construction drawings, and the training data set includes the characteristic values, significance index and identification of whether there is a paving risk of the historical dam surface construction drawings.

5. The quality safety risk management method for water conservancy projects according to claim 4, characterized in that: Extracting a first significance index from the first multidimensional image feature includes: Performing feature extraction of a predetermined feature dimension on the first construction block through a feature extraction channel to obtain a first extracted feature; performing a center-periphery difference analysis on the first extracted features to obtain a first feature comparison graph; Normalizing the area of the significant region in the first feature comparison image to obtain the first significance index.

6. The quality safety risk management method for water conservancy projects according to claim 5, characterized in that: The predetermined characteristic dimensions include brightness, red hue, green hue, blue hue and direction.

7. The quality safety risk management method for water conservancy projects according to claim 1, characterized in that: If the first construction state is the paving state, activating the inner network in the nested management network to analyze the first multi-dimensional image features to obtain a paving risk management result, and then further comprising: Continuously monitor the paver operation to obtain paving operation information; Comparing the paving operation information with predetermined paving operation information and analyzing to obtain paving health; The paving risk management results are verified using the paving health.

8. The quality safety risk management method for water conservancy projects according to claim 1, characterized in that: When the paving risk management result meets the predetermined management constraints, dam surface construction information is collected, and the outer network in the nested management network is activated to analyze the dam surface construction information to obtain the rolling risk management result, including: Analyzing the dam surface construction information through the compaction risk identification model in the outer network to obtain a predicted dam surface relative density; Introducing a compaction coefficient to weight the predicted dam surface relative density to obtain a dam surface compaction quality index; The dam surface compaction quality index is used to characterize the rolling risk management result; The construction process of the crushing risk identification model includes: Collecting historical dam surface rolling construction records, and extracting a first historical record from the historical dam surface rolling construction records; Extracting first historical dam surface construction information and first historical dam surface relative density from the first historical records and forming a first data set; The first data set is trained and tested to obtain the crushing risk identification model.

9. The quality safety risk management method for water conservancy projects according to claim 1, characterized in that: The dam surface construction information includes the number of rolling passes, vibration frequency, driving speed, driving direction and compaction meter value CMV.

10. A quality safety risk management system for water conservancy projects, characterized in that: The system comprises: A dam surface construction drawing segmentation module, which is used to obtain a dam surface construction drawing of a water conservancy project and segment the dam surface construction drawing to obtain a segmentation result; a construction status analysis module, configured to analyze a first multi-dimensional image feature of a first construction block in the segmentation result to obtain a first construction status; a paving risk management module, configured to activate an inner network in a nested management network to analyze the first multi-dimensional image features and obtain a paving risk management result if the first construction state is a paving state; a compaction risk management module, configured to collect dam surface construction information and activate an outer network in the nested management network to analyze the dam surface construction information to obtain a compaction risk management result when the paving risk management result meets predetermined management constraints; A quality and safety risk management module is used to perform quality and safety risk management of the water conservancy project based on the compaction risk management results.

Images