Dam body leakage diagnosis method and system based on AI technology

Abstract

The invention relates to the technical field of dam body detection, in particular to a dam body leakage diagnosis method and system based on an AI technology. The method comprises the following steps: acquiring a sensor array data set, analyzing the sensor array data set, and determining a unified space-time detection data set; analyzing the unified space-time detection data set, determining a freeze-thaw conversion time axis, tracking and screening corresponding detection data in the unified space-time detection data set according to the freeze-thaw conversion time axis, and determining a target period detection data set; and according to the target period detection data set, evolution simulation is conducted on the seepage development situation of the dam foundation curtain, and dam foundation curtain seepage trend information is determined and output. According to the method, the pushing effect of the freezing and thawing cycle on the dam foundation curtain leakage condition is accurately captured, the dam foundation curtain leakage trend information used for visually representing the dam foundation curtain leakage development state is provided for corresponding dam body maintenance personnel, and the hysteresis of the dam foundation curtain leakage detection result is effectively eliminated.

Description

Technical Field

[0001] The present application relates to the field of dam body detection technology, and in particular to a dam body leakage diagnosis method and system based on AI technology. Background Art

[0002] Leakage is an early sign of dam instability. Detecting dam leakage is a key step in extending the service life of the dam and reducing the risk of dam safety accidents. It can effectively inhibit the accelerated aging effect of dam leakage on dam materials and is one of the core requirements for water conservancy project safety management.

[0003] However, the existing dam leakage detection technology is difficult to timely and accurately control the leakage of dam foundation curtains in high-altitude and cold areas, resulting in the dam foundation curtain leakage detection results often lagging behind the development trend of dam foundation curtain leakage, resulting in unsatisfactory dam maintenance effects based on the dam foundation curtain leakage detection results. Summary of the Invention

[0004] This application provides a dam leakage diagnosis method and system based on AI technology to solve the above technical problems.

[0005] In a first aspect, the present application provides a dam leakage diagnosis method based on AI technology, the method comprising:

[0006] Acquiring a sensor array data set, analyzing the sensor array data set, and determining a unified spatiotemporal detection data set;

[0007] Analyzing the unified spatiotemporal detection dataset to determine a freeze-thaw conversion timeline, and tracking and screening corresponding detection data in the unified spatiotemporal detection dataset based on the freeze-thaw conversion timeline to determine a target period detection dataset;

[0008] Based on the target period detection data set, an evolutionary simulation is performed on the leakage development situation of the dam foundation curtain, and leakage trend information of the dam foundation curtain is determined and output.

[0009] Through this solution, the data in the sensor array data set are subjected to spatiotemporal alignment processing to obtain a unified spatiotemporal detection data set, which effectively eliminates the leakage analysis errors caused by the spatiotemporal deviation of the data, and ensures that the subsequent leakage analysis process is built on a solid and reliable data foundation. According to the unified spatiotemporal detection data set, the focus is on the freeze-thaw conversion time axis of the dam foundation curtain, and the corresponding detection data in the unified spatiotemporal detection data set are tracked and screened to obtain a target period detection data set to reduce the negative impact of data blind spots on the accuracy of leakage analysis. On this basis, the leakage development trend of the dam foundation curtain is simulated, and the driving effect of the freeze-thaw cycle on the leakage of the dam foundation curtain is accurately captured. The dam foundation curtain leakage trend information used to intuitively characterize the development status of the dam foundation curtain leakage is provided to the corresponding dam body maintenance personnel, effectively eliminating the lag of the dam foundation curtain leakage detection results.

[0010] Optionally, the sensor array data set includes a temperature data subset, an osmotic pressure data subset, and a deformation data subset;

[0011] The temperature data subset is obtained by distributed fiber Bragg grating temperature sensors arranged on the dam foundation curtain in a three-dimensional grid topology;

[0012] The seepage pressure data subset is obtained by distributed optical fiber micro-pressure sensors arranged on the dam foundation curtain in the form of the three-dimensional grid topology;

[0013] The deformation data subset is obtained by distributed optical fiber stress sensors arranged on the dam foundation curtain in the form of the three-dimensional grid topology;

[0014] The distributed fiber Bragg grating temperature sensor, the distributed fiber micro-pressure sensor and the distributed fiber stress sensor are all arranged on the side of the dam foundation curtain facing the upstream of the dam body;

[0015] The distributed fiber Bragg grating temperature sensor, the distributed fiber micro-pressure sensor and the distributed fiber stress sensor are connected in series to the same fiber path by using optical wavelength division multiplexing technology.

[0016] Through this solution, distributed fiber Bragg grating temperature sensors, distributed fiber micro-pressure sensors, and distributed fiber stress sensors are respectively arranged on the dam foundation curtain in the form of a three-dimensional grid topology, forming a three-dimensional monitoring network. This allows the development of leakage at horizontal joints and vertical joints to be captured in a timely manner. At the same time, optical wavelength division multiplexing technology is used to realize single-fiber transmission of multi-sensor data, eliminating the signal delay differences caused by traditional multi-cable layout and reducing the sensor layout cost. By restricting the layout of the above-mentioned sensors to the upstream side of the dam body, the sensors can timely capture the characteristics exhibited in the initial stage of leakage development, reducing the lag of subsequent leakage analysis.

[0017] Optionally, analyzing the sensor array dataset to determine a unified spatiotemporal detection dataset includes:

[0018] constructing a dam foundation curtain spatial grid model according to the three-dimensional grid topology of the distributed optical fiber sensors on the dam foundation curtain;

[0019] Analyzing the three-dimensional grid topology according to the dam foundation curtain spatial grid model, determining the relative position coordinates of each sensor, and constructing a unified spatial position coordinate set;

[0020] analyzing the unified set of spatial position coordinates and evaluating a signal processing delay of each sensor based on a relative distance between each sensor and a corresponding signal demodulator;

[0021] performing timestamp correction processing on data collected by each sensor in the sensor array data set according to the signal processing delay to determine a unified timestamp data set;

[0022] According to the unified spatial position coordinate set and the unified timestamp data set, each data in the sensor array data set is spatially marked and timestamp-marked respectively, and the temperature data synchronization subset, the osmotic pressure data synchronization subset and the deformation data synchronization subset after the spatiotemporal unification are determined to construct the unified spatiotemporal detection data set.

[0023] Through this scheme, the temperature data, seepage pressure data and stress data collected by different sensors are strictly aligned in time and space. According to the unified spatial position coordinate set and unified timestamp data set obtained by the time and space alignment, each data in the sensor array data set is spatially marked and timestamped respectively. The temperature data synchronization subset, seepage pressure data synchronization subset and deformation data synchronization subset after the time and space unification are integrated to construct a unified time and space detection data set, which prevents the misjudgment of data coupling relationship due to time and space differences of data, provides high-confidence data for subsequent freeze-thaw-leakage coupling analysis, and significantly improves the reliability of leakage trend prediction and the scientific nature of maintenance decision-making.

[0024] Optionally, analyzing the unified spatiotemporal detection dataset to determine the freeze-thaw transition timeline includes:

[0025] Based on the dam foundation curtain spatial grid model, and according to the temperature data synchronization subset in the unified spatiotemporal detection dataset, constructing a curtain temperature gradient distribution map;

[0026] Based on the dam foundation curtain spatial grid model, and according to the synchronized subset of seepage pressure data in the unified spatiotemporal detection dataset, a seepage pressure change rate distribution map is constructed;

[0027] Performing a spatiotemporal correlation analysis on the curtain temperature gradient distribution map and the osmotic pressure change rate distribution map; when the temperature gradient extreme point distribution in the curtain temperature gradient distribution map forms a spatiotemporal coupling relationship with the osmotic pressure change rate inflection point in the osmotic pressure change rate distribution map, determining that the area corresponding to the current data enters a critical state of freeze-thaw transition, and extracting the timestamp of the corresponding data as the freeze-thaw start time node of the area where the current sensor is located;

[0028] determining a curtain depth of the dam foundation curtain according to the dam foundation curtain spatial grid model;

[0029] Based on the curtain depth, according to the freeze-thaw start time node corresponding to the area where each sensor is located, analyzing the sensor blind area outside the area where the sensor is located to deduce the freeze-thaw state, and determining the freeze-thaw start time node of the sensor blind area;

[0030] The freeze-thaw conversion time axis is constructed according to the freeze-thaw start time nodes corresponding to the area where the sensor is located and the sensor blind area.

[0031] Through this scheme, the temperature data synchronization subset and the seepage pressure data synchronization subset are analyzed to obtain the curtain temperature gradient distribution map and the seepage pressure change rate distribution map respectively, which are used to reflect the temperature and seepage pressure change characteristics. According to the spatiotemporal coupling relationship between the temperature gradient extreme point and the seepage pressure change rate inflection point, the time point when the corresponding area of ​​the sensor enters the critical state of freeze-thaw conversion is captured as the freeze-thaw start time node. On this basis, combined with the depth of the dam foundation curtain where the sensor coverage blind area is located, the freeze-thaw state of the sensor layout blind area is deduced, and then the freeze-thaw start time node of the sensor layout blind area is obtained, so that the analysis of the freeze-thaw time period can cover the entire area of ​​the dam foundation curtain, thereby improving the comprehensiveness and accuracy of the subsequent leakage analysis process.

[0032] Optionally, the freeze-thaw start time node corresponding to the freeze-thaw start time node of each sensor area is analyzed based on the curtain depth, and the freeze-thaw start time node of the sensor blind area outside the sensor area is analyzed to deduce the freeze-thaw state, and the freeze-thaw start time node of the sensor blind area is determined, including:

[0033] Based on the dam foundation curtain spatial grid model and the curtain depth, the dam foundation curtain is divided into a plurality of temperature conduction levels along the vertical depth direction according to preset unit depth intervals;

[0034] Determining the advancement rate of the freeze-thaw transition critical state between adjacent temperature conduction levels based on the freeze-thaw start time nodes corresponding to a plurality of sensors in adjacent temperature conduction levels, and constructing an inter-level freeze-thaw state transmission chain;

[0035] Based on the inter-level freeze-thaw state transmission chain, the freeze-thaw start time node corresponding to each sensor layout blind area is determined according to the freeze-thaw start time nodes corresponding to a number of sensors in adjacent temperature conduction levels.

[0036] Through this scheme, the entire area corresponding to the dam foundation curtain is divided into several temperature conduction levels according to the preset unit depth interval, and the granularity of the analysis is further refined. On the basis of the freeze-thaw start time nodes corresponding to several sensors in adjacent temperature conduction levels, the advancement rate of the critical state of freeze-thaw conversion between temperature conduction levels is analyzed, and a freeze-thaw state transmission chain between levels is constructed. The freeze-thaw start time nodes corresponding to the blind areas of sensor layout are thus deduced, so that the subsequent leakage analysis process can cover the entire area of ​​the dam foundation curtain based on the precise time axis, thereby preventing misjudgment of leakage caused by monitoring blind areas.

[0037] Optionally, tracking and screening corresponding detection data in the unified spatiotemporal detection dataset according to the freeze-thaw conversion time axis to determine a target period detection dataset includes:

[0038] Based on the freeze-thaw conversion time axis, extracting the temperature data synchronization subset, the osmotic pressure data synchronization subset, and the deformation data synchronization subset that are temporally correlated with the freeze-thaw start time node in the unified spatiotemporal detection dataset to construct a sensor coverage area synchronization dataset;

[0039] Based on the advancement rate in the freeze-thaw state transmission chain between the layers and the relative spatial distance between the sensor blind area and adjacent sensors, a spatiotemporal interpolation function model is established;

[0040] Based on the spatiotemporal interpolation function model and the synchronous data set of the sensor coverage area, the temperature data, the osmotic pressure data, and the deformation data of the sensor blind area on the freeze-thaw conversion time axis are interpolated in a spatiotemporal continuity manner to generate a blind area interpolation data sequence;

[0041] The blind spot interpolation data sequence is spatially and temporally aligned with the data sequence in the synchronous data set of the sensor coverage area, and the target periodic detection data set covering the entire dam foundation curtain area is constructed based on the synchronous data set of the sensor coverage area and the spatially and temporally aligned blind spot interpolation data sequence.

[0042] Through this scheme, based on the synchronized dataset of the sensor coverage area, according to the advancement rate in the freeze-thaw state transmission chain between layers, combined with the relative spatial distance between the sensor blind spot and the adjacent sensors, a blind spot interpolation strategy driven by the physical conduction mechanism is used to generate a blind spot interpolation data sequence. Based on the synchronized dataset of the sensor coverage area and the blind spot interpolation data sequence after spatiotemporal alignment, a target period detection dataset is jointly constructed, which significantly improves the spatial coverage of the target period detection dataset, effectively eliminates monitoring blind spots, and improves the accuracy and comprehensiveness of leakage analysis results.

[0043] Optionally, performing an evolutionary simulation on the leakage development trend of the dam foundation curtain based on the target period detection data set to determine and output leakage trend information of the dam foundation curtain includes:

[0044] Analyzing the dam foundation curtain space grid model to identify and mark the cylindrical structural joint areas;

[0045] According to the material leakage test data, basic leakage influence weights are assigned to the temperature data, the seepage pressure data and the deformation data in the target period detection data set respectively;

[0046] Based on the joint leakage test data, the basic leakage influence weight of the temperature data, seepage pressure data and deformation data corresponding to the joint area of ​​the cylindrical structure in the target period detection data set is corrected for the key area influence to determine the joint area leakage influence weight;

[0047] Based on the target period detection data set, according to the basic leakage impact weight and the joint area leakage impact weight, a weighted fusion analysis is performed on the temperature data, seepage pressure data, and deformation data corresponding to different areas in the target period detection data set to determine the real-time leakage risk corresponding to the different areas;

[0048] Determine a number of high-risk leakage areas based on the real-time leakage risks and corresponding deformation data corresponding to different areas, and construct a leakage risk distribution heat map based on the high-risk leakage areas;

[0049] The leakage risk distribution heat map is visualized and output as the leakage trend information of the dam foundation curtain.

[0050] Through this scheme, the spatial grid model of the dam foundation curtain is analyzed, the cylindrical structure joint area is identified, and on the basis of the foundation leakage influence weight, the influence of the corresponding data of the cylindrical structure joint area is corrected to determine the leakage influence weight of the joint area. On this basis, according to the foundation leakage influence weight and the joint area leakage influence weight, the temperature data, seepage pressure data and deformation data in different areas are weighted fusion analysis to obtain the real-time leakage risk corresponding to different areas, and the corresponding leakage risk distribution heat map is generated as the dam foundation curtain leakage trend information for visualization output, so that the leakage risk assessment of the cylindrical structure joint area, which is an area with higher leakage risk, is more accurate.

[0051] Optionally, the step of performing key area impact correction processing on the basic leakage influence weights of the temperature data, seepage pressure data, and deformation data corresponding to the cylindrical structure joint area in the target period detection data set based on the joint leakage experimental data to determine the joint area leakage influence weights includes:

[0052] Extracting joint width variation data, joint filling material thermal conductivity, and joint interface shear strength degradation coefficient based on the joint leakage test data;

[0053] The seam width variation data is positively correlated with the leakage impact weight of the seam area;

[0054] The thermal conductivity of the joint filling material is negatively correlated with the leakage influence weight of the joint area;

[0055] The degradation coefficient of the joint interface shear strength is positively correlated with the weight of the joint area leakage impact;

[0056] Based on the foundation leakage impact weight, and in accordance with the joint width variation data, the thermal conductivity of the joint filling material, and the joint interface shear strength degradation coefficient, a joint area impact correction function is constructed;

[0057] According to the seam area impact correction function, the basic leakage impact weight is subjected to key area impact correction processing to quantify the seam area leakage impact weight.

[0058] Through this scheme, the correlation between the joint width change data in the joint leakage experimental data, the thermal conductivity coefficient of the joint filling material and the shear strength degradation coefficient of the joint interface and the leakage influence weight of the joint area are respectively constructed, and a joint area influence correction function is constructed. According to the joint area influence correction function, the basic leakage influence weight is corrected for the key area influence, and the joint area leakage influence weight is quantified. The multi-parameter coupling correction mechanism is used to reduce the assessment error of the leakage risk of the joint area.

[0059] Optionally, determining several high-risk leakage areas according to the real-time leakage risks and corresponding deformation data of different areas includes:

[0060] Comparing the real-time leakage risks corresponding to different areas with risk precursor benchmark values ​​respectively, and marking the areas where the real-time leakage risks exceed the risk precursor benchmark values ​​as key analysis areas according to the comparison results;

[0061] According to the target period detection data set, taking the key analysis area as a benchmark, extracting deformation data corresponding to each key analysis area in the target period detection data set and the temperature conduction layer adjacent thereto, to construct a key area deformation data set;

[0062] Analyze the deformation development direction of the current key analysis area according to the deformation data set of the key area, and determine the tracking target area;

[0063] The current tracking target area and the key analysis area are regarded as the high-risk leakage areas.

[0064] Through this solution, during the assessment of high-risk leakage areas, the key analysis areas and tracking target areas are integrated into high-risk leakage areas through a dual assessment mechanism of real-time leakage risk and deformation development direction. By analyzing areas with potential leakage and spread risks, the lag in risk identification is reduced.

[0065] In a second aspect, the present application provides a dam leakage diagnosis system based on AI technology, the system comprising:

[0066] a data alignment module, configured to acquire a sensor array data set, analyze the sensor array data set, and determine a unified spatiotemporal detection data set;

[0067] a data tracking module, configured to analyze the unified spatiotemporal detection dataset, determine a freeze-thaw conversion timeline, and track and filter corresponding detection data in the unified spatiotemporal detection dataset based on the freeze-thaw conversion timeline to determine a target period detection dataset;

[0068] The risk analysis module is used to simulate the evolution of the leakage development situation of the dam foundation curtain according to the target period detection data set, and determine and output the leakage trend information of the dam foundation curtain. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0070] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application;

[0071] Figure 2 A flowchart of a dam leakage diagnosis method based on AI technology provided in one embodiment of the present application;

[0072] Figure 3 A schematic structural diagram of a dam leakage diagnosis system based on AI technology provided in one embodiment of the present application. DETAILED DESCRIPTION

[0073] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0074] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0075] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0076] The existing dam leakage detection technology is unable to timely and accurately control the leakage of dam foundation curtains in high-altitude and cold areas, resulting in the dam foundation curtain leakage detection results often lagging behind the development trend of dam foundation curtain leakage, resulting in unsatisfactory dam maintenance effects based on the dam foundation curtain leakage detection results.

[0077] Based on this, the present application provides a dam leakage diagnosis method and system based on AI technology. The data in the sensor array data set are subjected to spatiotemporal alignment processing to obtain a unified spatiotemporal detection data set, which effectively eliminates the leakage analysis error caused by the spatiotemporal deviation of the data, and ensures that the subsequent leakage analysis process is based on a solid and reliable data foundation. According to the unified spatiotemporal detection data set, the focus is on the freeze-thaw conversion time axis of the dam foundation curtain, and the corresponding detection data in the unified spatiotemporal detection data set are tracked and screened to obtain a target cycle detection data set to reduce the negative impact of data blind spots on the accuracy of leakage analysis. On this basis, the leakage development trend of the dam foundation curtain is simulated, and the driving effect of the freeze-thaw cycle on the leakage of the dam foundation curtain is accurately captured. The dam foundation curtain leakage trend information used to intuitively characterize the development status of the dam foundation curtain leakage is provided to the corresponding dam maintenance personnel, effectively eliminating the lag of the dam foundation curtain leakage detection results.

[0078] Figure 1 This is a schematic diagram of an application scenario provided by this application. During the process of leak detection of dam foundation curtains, the method provided by this application is applied to accurately capture the driving effect of freeze-thaw cycles on dam foundation curtain leakage, effectively eliminating the lag in dam foundation curtain leakage detection results.

[0079] Specifically, the method of the present application is applied to any server, which communicates with the sensor array, obtains the sensor array data set provided by the sensor array through the server, performs spatiotemporal alignment processing on the data in the sensor array data set, and obtains a unified spatiotemporal detection data set, effectively eliminating the leakage analysis error caused by the spatiotemporal deviation of the data, and ensuring that the subsequent leakage analysis process is based on a solid and reliable data foundation. According to the unified spatiotemporal detection data set, focus on the freeze-thaw conversion time axis of the dam foundation curtain, track and screen the corresponding detection data in the unified spatiotemporal detection data set, and obtain a target period detection data set to reduce the negative impact of data blind spots on the accuracy of leakage analysis. On this basis, the leakage development trend of the dam foundation curtain is evolved and simulated, and the driving effect of the freeze-thaw cycle on the leakage of the dam foundation curtain is accurately captured. The dam foundation curtain leakage trend information used to intuitively characterize the development status of the dam foundation curtain leakage is provided to the corresponding dam body maintenance personnel, effectively eliminating the lag of the dam foundation curtain leakage detection results.

[0080] For specific implementation methods, please refer to the following embodiments.

[0081] Figure 2 This is a flowchart of a dam leakage diagnosis method based on AI technology provided in one embodiment of the present application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes:

[0082] S201: Acquire a sensor array data set, analyze the sensor array data set, and determine a unified spatiotemporal detection data set.

[0083] The sensor array data set may be a set of multi-dimensional physical parameters of the dam foundation curtain collected in real time by the sensor array, including subsets of temperature, seepage pressure, and deformation data.

[0084] The unified spatiotemporal detection dataset can be a sensor data set that has been spatiotemporally calibrated, and contains a data set with unified timestamps and spatial coordinate markers, eliminating the data asynchrony problem caused by differences in sensor deployment locations.

[0085] Specifically, the core purpose of constructing a dam foundation curtain is to block or control the infiltration path of groundwater in the dam foundation rock or soil through an artificially constructed anti-seepage barrier, thereby ensuring the safe and stable operation of the dam; the dam foundation curtains equipped with dams located in high-altitude cold areas are easily affected by the soil freeze-thaw cycle. Repeated freeze-thaw and shrinkage will accelerate the aging and cracking of the dam curtain material, thereby exacerbating the development of the leakage situation. Moreover, since the dam foundation curtain is underground and large in scale, the existing technology for detecting leakage of the dam foundation curtain during the freeze-thaw cycle is difficult to guarantee and has obvious lag. By deploying a sensor array, the large-scale dam foundation curtain is divided into different monitoring areas based on the sensor position. Through the spatiotemporal alignment algorithm, the detection data collected in the sensor array data set is unified in time and space to obtain a unified spatiotemporal detection data set, which provides scientific data in the same spatiotemporal dimension for subsequent leakage analysis, reducing the analysis error caused by data asynchrony.

[0086] S202: Analyze the unified spatiotemporal detection dataset, determine the freeze-thaw conversion timeline, and track and screen the corresponding detection data in the unified spatiotemporal detection dataset based on the freeze-thaw conversion timeline to determine the target period detection dataset.

[0087] The freeze-thaw transition timeline can be used to characterize the time series when different areas of the dam foundation curtain enter the freeze-thaw critical state.

[0088] The target period detection dataset may be a data set consisting of data on the freeze-thaw conversion time axis within the unified spatiotemporal detection dataset.

[0089] Specifically, since the changes in key influencing factors such as temperature and seepage pressure during the freeze-thaw process have nonlinear characteristics, and the sensors cannot completely cover the entire area of ​​the dam foundation curtain, it is difficult for existing technologies to effectively analyze the continuous impact of freeze-thaw contraction on the leakage of the dam foundation curtain. According to the unified spatiotemporal detection dataset, by combining the extreme value of the temperature gradient (reflecting the release of latent heat of phase change) and the seepage pressure inflection point (reflecting the sudden change in water pressure caused by the ice-water phase change), the spatiotemporal boundary of the freeze-thaw conversion is accurately identified, and the freeze-thaw conversion timeline is obtained. On this basis, the changing trends of different influencing factors within the freeze-thaw conversion timeline are tracked, and the changing status of the influencing factors in the area not covered by the sensors is deduced, and then a data analysis framework that can cover the entire dam foundation curtain area is constructed, and a target period detection dataset for mapping the leakage conditions of each area of ​​the dam foundation curtain is obtained.

[0090] S203: Based on the target period detection data set, an evolutionary simulation is performed on the leakage development trend of the dam foundation curtain to determine and output the leakage trend information of the dam foundation curtain.

[0091] The leakage development trend may be the development state of the dam foundation curtain leakage situation.

[0092] Evolutionary simulation can be a process of simulating the progress of dam foundation curtain leakage based on current detection data.

[0093] The dam foundation curtain leakage trend information may be information used to visually represent the dam foundation curtain leakage situation and trend.

[0094] Specifically, after obtaining the target period detection data set, a weighted fusion strategy is used to evaluate the leakage risks of different areas of the dam foundation curtain based on a series of data in the target period detection data set that are used to directly or indirectly map the leakage conditions of different areas of the dam foundation curtain. Then, based on the spatial transmission characteristics of the leakage, the diffusion path of the high leakage risk area is tracked, and the dam foundation curtain leakage trend information is generated for visually representing the development trend of the dam foundation curtain leakage. The dam foundation curtain leakage trend information is then provided to the corresponding dam maintenance personnel through human-computer interaction hardware equipment, such as high-definition display screens, as intuitive reference data for subsequent dam maintenance personnel to formulate maintenance strategies.

[0095] Through this scheme, the data in the sensor array data set are spatiotemporally aligned to obtain a unified spatiotemporal detection data set, which effectively eliminates the leakage analysis errors caused by the spatiotemporal deviation of the data and ensures that the subsequent leakage analysis process is built on a solid and reliable data foundation. According to the unified spatiotemporal detection data set, the focus is on the freeze-thaw conversion time axis of the dam foundation curtain, and the corresponding detection data in the unified spatiotemporal detection data set are tracked and screened to obtain the target period detection data set to reduce the negative impact of data blind spots on the accuracy of leakage analysis. On this basis, the leakage development trend of the dam foundation curtain is simulated, and the driving effect of the freeze-thaw cycle on the leakage of the dam foundation curtain is accurately captured. The dam foundation curtain leakage trend information used to intuitively characterize the development status of the dam foundation curtain leakage is provided to the corresponding dam body maintenance personnel, effectively eliminating the lag of the dam foundation curtain leakage detection results.

[0096] In some embodiments, the sensor array data set includes a temperature data subset, a seepage pressure data subset, and a deformation data subset; the temperature data subset is obtained by a distributed fiber optic Bragg grating temperature sensor arranged on the dam foundation curtain in a three-dimensional grid topology; the seepage pressure data subset is obtained by a distributed fiber optic micro-pressure sensor arranged on the dam foundation curtain in a three-dimensional grid topology; the deformation data subset is obtained by a distributed fiber optic stress sensor arranged on the dam foundation curtain in a three-dimensional grid topology; the distributed fiber optic Bragg grating temperature sensor, the distributed fiber optic micro-pressure sensor, and the distributed fiber optic stress sensor are all arranged on the side of the dam foundation curtain facing the upstream of the dam body; and the distributed fiber optic Bragg grating temperature sensor, the distributed fiber optic micro-pressure sensor, and the distributed fiber optic stress sensor are connected in series to the same optical fiber path using optical wavelength division multiplexing technology.

[0097] The temperature data subset may be a time series data set reflecting temperature changes in different areas of the dam foundation curtain.

[0098] The seepage pressure data subset may be a time series data set reflecting the changes in the pore water pressure of the dam foundation curtain.

[0099] The deformation data subset may be a time series data set reflecting the deformation of the dam foundation curtain structure.

[0100] The three-dimensional grid topology can be a three-dimensional monitoring network topology in which sensors are arranged on the surface of the dam foundation curtain and in the depth direction according to equally spaced cubic nodes.

[0101] A distributed fiber Bragg grating temperature sensor can be a sensor that realizes continuous temperature measurement along an optical fiber based on the shift of the grating reflection wavelength.

[0102] The distributed optical fiber micro-pressure sensor can be a sensor that realizes distributed micro-pressure perception based on the change of optical fiber micro-bending loss.

[0103] The distributed optical fiber stress sensor may be a sensor that realizes distributed stress perception based on optical fiber polarization light time domain reflection.

[0104] Optical wavelength division multiplexing technology can be a technology that can realize parallel transmission of multi-sensor data by allocating different wavelength channels in the same optical fiber.

[0105] Specifically, in the process of leakage detection of dam foundation curtains in high-altitude cold areas during the freeze-thaw cycle, temperature data reveals the migration of the freeze-thaw interface, seepage pressure data reflects the sudden change of pore water pressure, and deformation data captures the trend of structural cracking. The spatiotemporal correlation of the three can map the leakage situation. The existing technology has the following defects in the data collection stage in the leakage detection of dam foundation curtains in high-altitude cold areas: traditional point sensors can only obtain local temperature or pressure data and cannot capture the three-dimensional expansion characteristics of the leakage path caused by the freeze-thaw cycle; discrete sensors have data timestamp deviations due to independent power supply and communication lines, and it is difficult to establish a causal relationship between temperature gradient, seepage pressure mutation and deformation response; conventional electronic sensors are prone to drift or failure in low temperature and high humidity environments; dam foundation curtains are usually composed of several concrete cylinders spliced ​​together, and there are joints between the concrete cylinders, and the surface in contact with the soil is not a plane. , but a wavy surface. The existing sensor layout method is difficult to adapt to this three-dimensional curved surface structure. This solution forms a three-dimensional monitoring network by laying out distributed fiber optic Bragg grating temperature sensors, distributed fiber optic micro-pressure sensors and distributed fiber optic stress sensors on the surface of the dam foundation curtain, so that the development of leakage at horizontal joints and vertical joints can be captured in time. At the same time, optical wavelength division multiplexing technology is used to realize single-fiber transmission of multi-sensor data, eliminating the signal delay difference caused by traditional multi-cable layout and reducing the sensor layout cost. The distributed fiber optic Bragg grating temperature sensor, distributed fiber optic micro-pressure sensor and distributed fiber optic stress sensor are all laid on the side of the dam foundation curtain facing the upstream of the dam body, so that the sensors can capture the characteristics of the initial stage of leakage development in time. If the above sensors are laid on the downstream side of the dam body, the hysteresis of leakage analysis will be significantly enhanced.

[0106] Through this solution, distributed fiber Bragg grating temperature sensors, distributed fiber micro-pressure sensors, and distributed fiber stress sensors are respectively arranged on the dam foundation curtain in the form of a three-dimensional grid topology, forming a three-dimensional monitoring network. This allows the development of leakage at horizontal joints and vertical joints to be captured in a timely manner. At the same time, optical wavelength division multiplexing technology is used to realize single-fiber transmission of multi-sensor data, eliminating the signal delay differences caused by traditional multi-cable layout and reducing the sensor layout cost. By restricting the layout of the above-mentioned sensors to the upstream side of the dam body, the sensors can timely capture the characteristics exhibited in the initial stage of leakage development, reducing the lag of subsequent leakage analysis.

[0107] In some embodiments, a dam foundation curtain spatial grid model is constructed based on the three-dimensional grid topology of distributed optical fiber sensors on the dam foundation curtain; based on the dam foundation curtain spatial grid model, the three-dimensional grid topology is analyzed to determine the relative position coordinates of each sensor and construct a unified spatial position coordinate set; the unified spatial position coordinate set is analyzed to evaluate the signal processing delay of each sensor based on the relative distance between each sensor and the corresponding signal demodulator; based on the signal processing delay, the data collected by each sensor in the sensor array data set is timestamp corrected to determine a unified timestamp data set; based on the unified spatial position coordinate set and the unified timestamp data set, each data in the sensor array data set is spatially marked and timestamped respectively to determine the temperature data synchronization subset, the seepage pressure data synchronization subset and the deformation data synchronization subset after the time and space unification is completed, and construct a unified time and space detection data set.

[0108] The dam foundation curtain space grid model can be a digital three-dimensional space model for representing a three-dimensional monitoring area established based on the three-dimensional grid topology layout of distributed optical fiber sensors on the dam foundation curtain.

[0109] The relative position coordinates may be the three-dimensional coordinate values ​​of the sensor in the dam foundation curtain space grid model.

[0110] The unified spatial position coordinate set may be a data set recording the position coordinates of all sensors in the dam foundation curtain space grid model.

[0111] The signal demodulator may be a component that converts the modulated optical signal output by the optical fiber sensor into an electrical signal.

[0112] Signal processing delay can be the time it takes for the data collected by the sensor to be converted from physical signals to digital signals and transmitted to the signal demodulator.

[0113] The timestamp correction process can be to calibrate the time stamp of the original sensor data according to the signal processing delay to eliminate the time synchronization problem caused by the difference in the transmission path.

[0114] The unified timestamp dataset can be a time series dataset formed by correcting the timestamps of all sensor data, ensuring that the data of different sensors are strictly aligned on the time axis.

[0115] The temperature data synchronization subset may be a temperature data set that has been processed through spatiotemporal synchronization.

[0116] The synchronized subset of the osmotic pressure data may be a set of osmotic pressure data that has been processed with spatiotemporal synchronization.

[0117] The deformation data synchronization subset may be a deformation data set that has been processed through spatiotemporal synchronization.

[0118] Specifically, sensor data is prone to timestamp deviation due to differences in transmission distance (time differences caused by spatial differences, and spatiotemporal inconsistency), which cannot accurately reflect the dynamic coupling relationship between temperature, osmotic pressure, and deformation during freeze-thaw. For example, the osmotic pressure change caused by a sudden temperature drop may be incorrectly associated with the subsequent time period due to the signal delay caused by the spatial model transmission processing, resulting in a delayed leakage warning. Through the finite element mesh generation algorithm, the three-dimensional grid is divided according to the three-dimensional grid topology of the distributed optical fiber sensors on the dam foundation curtain, and a dam foundation curtain spatial grid model is constructed. Based on the coordinate system of the dam foundation curtain spatial grid model, the relative position coordinates of each sensor are marked to construct a unified spatial position coordinate set, so that the measurement standards of each sensor in the spatial dimension are consistent and spatial alignment is achieved. On this basis, the transmission distance of each sensor signal through the optical fiber path to the demodulator is determined. Combined with the optical signal propagation speed and the inherent delay of the demodulator signal processing, the signal processing delay of each sensor is evaluated. Based on this signal processing delay, the timestamp corresponding to the original sensor data is subtracted and corrected to construct a unified timestamp data set, so that the measurement standards of each sensor data in the time dimension are consistent and temporal alignment is achieved.

[0119] Through this scheme, the temperature data, seepage pressure data and stress data collected by different sensors are strictly aligned in time and space. According to the unified spatial position coordinate set and unified timestamp data set obtained by the time and space alignment, each data in the sensor array data set is spatially marked and timestamped respectively. The temperature data synchronization subset, seepage pressure data synchronization subset and deformation data synchronization subset after the time and space unification are integrated to construct a unified time and space detection data set, which prevents the misjudgment of data coupling relationship due to time and space differences of data, provides high-confidence data for subsequent freeze-thaw-leakage coupling analysis, and significantly improves the reliability of leakage trend prediction and the scientific nature of maintenance decision-making.

[0120] In some embodiments, based on the dam foundation curtain space grid model, a curtain temperature gradient distribution map is constructed according to a synchronized subset of temperature data in a unified spatiotemporal detection dataset; based on the dam foundation curtain space grid model, a seepage pressure change rate distribution map is constructed according to a synchronized subset of seepage pressure data in a unified spatiotemporal detection dataset; a spatiotemporal correlation analysis is performed on the curtain temperature gradient distribution map and the seepage pressure change rate distribution map, and when the temperature gradient extreme point distribution in the curtain temperature gradient distribution map forms a spatiotemporal coupling relationship with the seepage pressure change rate inflection point in the seepage pressure change rate distribution map, it is determined that the area corresponding to the current data enters a critical state of freeze-thaw conversion, and the timestamp of the corresponding data is extracted as the freeze-thaw start time node of the current sensor area; according to the dam foundation curtain space grid model, the curtain depth of the dam foundation curtain is determined; based on the curtain depth, according to the freeze-thaw start time node corresponding to the area where each sensor is located, the sensor layout blind area outside the sensor area is analyzed to deduce the freeze-thaw state, and the freeze-thaw start time node of the sensor layout blind area is determined; according to the freeze-thaw start time nodes corresponding to the sensor area and the sensor layout blind area respectively, a freeze-thaw conversion time axis is constructed.

[0121] The curtain temperature gradient distribution map can be a three-dimensional temperature change thermodynamic map generated based on a synchronized subset of temperature data, reflecting the temperature gradient distribution characteristics of different areas of the dam foundation curtain.

[0122] The osmotic pressure change rate distribution diagram may be a dynamic pressure change trend diagram generated based on a synchronized subset of osmotic pressure data, and is used to characterize the rate of change of the osmotic pressure inside the curtain over time.

[0123] The temperature gradient extreme point can be the spatial coordinate point where the gradient value exceeds the set threshold in the temperature gradient distribution diagram, reflecting the dynamic migration position of the freeze-thaw interface.

[0124] The inflection point of the osmotic pressure change rate can be the spatiotemporal node where the second-order derivative is zero in the osmotic pressure change rate distribution diagram, indicating the key position where the osmotic pressure trend is reversed.

[0125] Spatiotemporal correlation analysis can be a process of jointly analyzing the coupling relationship between the extreme points of temperature gradient and the inflection points of osmotic pressure change rate in time series and spatial positions.

[0126] The spatiotemporal coupling relationship can be the correlation locking relationship formed between the extreme point of temperature gradient and the inflection point of osmotic pressure change rate in the time dimension and space dimension.

[0127] The freeze-thaw transition critical state can be the transition stage where the dam foundation curtain material changes from a frozen state to a thawed state (or vice versa).

[0128] The freeze-thaw start time node may be a timestamp when the region enters a critical state of freeze-thaw transition.

[0129] The curtain depth can be the vertical distance between the top and bottom of the dam foundation curtain.

[0130] Specifically, since the dam foundation curtain in the high-altitude cold area is directly affected by the freeze-thaw cycle, before analyzing the leakage performance of the dam foundation curtain during the freeze-thaw cycle, it is necessary to first determine whether the current dam foundation curtain is in the freeze-thaw conversion cycle. Since the dam foundation curtain is large in scale and the freeze-thaw conversion is a long time process, there are differences in the time when different areas of the dam foundation curtain enter the freeze-thaw conversion cycle. It is necessary to discuss in different regions to ensure the accuracy of the leakage analysis process; according to the temperature data synchronization subset, the temperature performance of different areas at different times is analyzed, the temperature change gradient between the areas corresponding to different temperature sensors is quantified, the curtain temperature gradient distribution map is constructed, and the seepage pressure data synchronization subset is extracted synchronously to analyze the temperature performance of different areas at different times. The osmotic pressure value changes, quantify the osmotic pressure change rate between the corresponding areas of different osmotic pressure sensors, and generate an osmotic pressure change rate distribution map. According to the curtain temperature gradient distribution map and the pressure change rate distribution map, the temperature gradient extreme point (by fitting the temperature gradient extreme value judgment threshold by experimental data, such as 3°C / m) and the osmotic pressure change rate inflection point (by using data to fit the osmotic pressure change rate inflection point judgment threshold, such as 10 Pa / min) are extracted respectively. The temperature gradient extreme point and the osmotic pressure inflection point are aligned along the time axis. When the two overlap in space and the time difference is less than the corresponding difference benchmark (such as 30s), the area is judged to have entered the critical state of freeze-thaw transition. The timestamp corresponding to the data point that meets the above conditions is extracted as the freeze-thaw start time node of the grid unit where the sensor is located.

[0131] On this basis, since the dam foundation curtain is buried vertically underground, there is a large height difference between its top and bottom, and the freeze-thaw cycle is affected by the ground temperature conduction. The starting time point of the freeze-thaw cycle at the top of the dam foundation curtain will be significantly earlier than that at the bottom of the dam foundation curtain, and the starting time node of the freeze-thaw cycle shows a downward increasing trend based on the depth of the dam foundation curtain, resulting in different freeze-thaw cycles showing staggered characteristics on the same time axis. Therefore, for the analysis of the freeze-thaw starting time node of the sensor coverage blind area, the freeze-thaw status of the sensor layout blind area can be deduced based on the sensor data and the depth of the dam foundation curtain where the sensor coverage blind area is located, and then the freeze-thaw starting time node of the sensor layout blind area is obtained, so that the analysis of the freeze-thaw time cycle can cover the entire area of ​​the dam foundation curtain, thereby improving the comprehensiveness and accuracy of the subsequent leakage analysis process.

[0132] Through this scheme, the temperature data synchronization subset and the seepage pressure data synchronization subset are analyzed to obtain the curtain temperature gradient distribution map and the seepage pressure change rate distribution map respectively, which are used to reflect the temperature and seepage pressure change characteristics. According to the spatiotemporal coupling relationship between the temperature gradient extreme point and the seepage pressure change rate inflection point, the time point when the corresponding area of ​​the sensor enters the critical state of freeze-thaw conversion is captured as the freeze-thaw start time node. On this basis, combined with the depth of the dam foundation curtain where the sensor coverage blind area is located, the freeze-thaw state of the sensor layout blind area is deduced, and then the freeze-thaw start time node of the sensor layout blind area is obtained, so that the analysis of the freeze-thaw time period can cover the entire area of ​​the dam foundation curtain, thereby improving the comprehensiveness and accuracy of the subsequent leakage analysis process.

[0133] In some embodiments, based on the dam foundation curtain spatial grid model and the curtain depth, the dam foundation curtain is divided into several temperature conduction levels along the vertical depth direction according to a preset unit depth interval; according to the freeze-thaw start time nodes corresponding to several sensors in adjacent temperature conduction levels, the advancement rate of the freeze-thaw conversion critical state between adjacent temperature conduction levels is determined, and an inter-level freeze-thaw state transmission chain is constructed; based on the inter-level freeze-thaw state transmission chain, according to the freeze-thaw start time nodes corresponding to several sensors in adjacent temperature conduction levels, the freeze-thaw start time node corresponding to each sensor layout blind area is determined.

[0134] The preset unit depth interval may be a unit depth referenced in the process of dividing the temperature conduction layer. The preset unit depth interval is set according to the sensor layout spacing and the overall layout depth of the dam foundation curtain.

[0135] The temperature conduction level may be a hierarchical structure in which the dam foundation curtain is divided into preset unit depths (eg, 2 meters) along the vertical depth direction.

[0136] The spatiotemporal correlation can be the degree of matching between the temperature gradient extreme points and the osmotic pressure inflection points of sensor nodes at adjacent levels in terms of time series and spatial distribution.

[0137] The advancement rate can be regarded as the average speed at which the critical state of freeze-thaw transition migrates between adjacent temperature conduction levels.

[0138] The inter-layer freeze-thaw state transmission chain can be a logical model that describes the migration path of the freeze-thaw front between temperature conduction layers.

[0139] Specifically, according to the preset unit depth interval, the boundaries of each level are marked in the dam foundation curtain space grid model, and the dam foundation curtain is divided into several temperature conduction levels along the vertical depth direction. The freeze-thaw start time nodes of all sensors in adjacent levels (such as level 1 and level 2) are extracted, and the inter-level time difference of each sensor pair is calculated. According to the ratio of the inter-level distance to the inter-level time difference, the local advancement rate corresponding to each sensor is taken as the advancement rate between the current levels. According to the advancement rates between different levels, the freeze-thaw state transmission chain between levels is constructed. On this basis, according to the relative distance between the blind areas of different sensors and their adjacent sensors, combined with the freeze-thaw start time nodes of the adjacent sensors, the freeze-thaw start time nodes corresponding to the blind areas of the sensors are derived.

[0140] Through this scheme, the entire area corresponding to the dam foundation curtain is divided into several temperature conduction levels according to the preset unit depth interval, and the granularity of the analysis is further refined. On the basis of the freeze-thaw start time nodes corresponding to several sensors in adjacent temperature conduction levels, the advancement rate of the critical state of freeze-thaw conversion between temperature conduction levels is analyzed, and a freeze-thaw state transmission chain between levels is constructed. The freeze-thaw start time nodes corresponding to the blind areas of sensor layout are thus deduced, so that the subsequent leakage analysis process can cover the entire area of ​​the dam foundation curtain based on the precise time axis, thereby preventing misjudgment of leakage caused by monitoring blind areas.

[0141] In some embodiments, based on the freeze-thaw conversion time axis, a temperature data synchronization subset, a seepage pressure data synchronization subset, and a deformation data synchronization subset that are temporally correlated with the freeze-thaw start time node in the unified spatiotemporal detection dataset are extracted to construct a sensor coverage area synchronization dataset; based on the advancement rate in the freeze-thaw state transmission chain between levels, combined with the relative spatial distance between the sensor blind area and the adjacent sensors, a spatiotemporal interpolation function model is established; based on the spatiotemporal interpolation function model, according to the sensor coverage area synchronization dataset, the temperature data, seepage pressure data, and deformation data of the sensor blind area on the freeze-thaw conversion time axis are spatiotemporally continuous interpolated to generate a blind area interpolation data sequence; the blind area interpolation data sequence is spatiotemporally aligned with the data sequence in the sensor coverage area synchronization dataset, and based on the sensor coverage area synchronization dataset and the spatiotemporally aligned blind area interpolation data sequence, a target period detection dataset covering the entire dam foundation curtain area is constructed.

[0142] The sensor coverage area synchronization dataset can be a data set consisting of a subset of temperature, osmotic pressure, and deformation data collected by sensors directly associated with the freeze-thaw start time node, which is extracted from the unified spatiotemporal detection dataset.

[0143] The relative spatial distance may be the relative distance between the blind area of ​​the sensor and the adjacent sensor in the temperature conduction level division.

[0144] The spatiotemporal interpolation function model can be a data interpolation model constructed based on the relationship between the advancement rate and spatial distance of the freeze-thaw state transmission chain, which is used to deduce the changes in physical quantities in the sensor blind area.

[0145] The blind zone interpolation data sequence can be a temperature, seepage pressure, and deformation data sequence of the sensor blind zone generated by the spatiotemporal interpolation function model to fill the spatiotemporal data gap in the unmonitored area.

[0146] Spatiotemporal continuity interpolation can be an interpolation method that maintains data continuity in the time dimension and the space dimension, avoiding the mutation distortion caused by traditional interpolation.

[0147] Specifically, after the freeze-thaw start time node corresponding to the sensor blind area is derived, since the temperature data, seepage pressure data and deformation data corresponding to the sensor blind area are blank, it is necessary to further deduce the corresponding data parameters in the sensor blind area to ensure the continuity and accuracy of the leakage analysis and prevent the problem of high leakage analysis error caused by data fragmentation. The temperature data synchronization subset, seepage pressure data synchronization subset and deformation data synchronization subset that are temporally correlated with the freeze-thaw start time node in the unified spatiotemporal detection dataset are analyzed. Since the temperature data, seepage pressure data and deformation data corresponding to the current sensor blind area are blank, the above-mentioned temperature data synchronization subset, seepage pressure data synchronization subset and deformation data synchronization subset are the data directly collected by all current sensors, so as to construct a synchronous dataset of the sensor coverage area. At the same time, according to the advancement rate and relative spatial distance, the impact corresponding to the current data blind area is quantified. The influence coefficient is used to characterize the adjustment range of the data in the blind area of ​​the current sensor coverage based on the data collected by the adjacent sensors. Specifically, the advancement rate is positively correlated with the influence coefficient, and the relative spatial distance is negatively correlated with the influence coefficient. The corresponding correlation coefficient is fitted through experimental data. According to the influence coefficients in the blind areas of different sensor coverage, a spatiotemporal difference function model is constructed. On this basis, according to the corresponding influence coefficients mapped in the spatiotemporal difference function model, the corresponding data in the synchronous data set of the sensor coverage area are adjusted in proportion to generate a blind area interpolation data sequence. The timestamps of the blind area interpolation data sequence are uniformly calibrated to the freeze-thaw conversion time axis, and the spatial coordinates are mapped to the corresponding temperature conduction level to achieve spatiotemporal alignment. The synchronous data set of the sensor coverage area and the blind area interpolation data sequence after spatiotemporal alignment are integrated into a data set, namely the target period detection data set.

[0148] Through this scheme, based on the synchronized dataset of the sensor coverage area, according to the advancement rate in the freeze-thaw state transmission chain between layers, combined with the relative spatial distance between the sensor blind spot and the adjacent sensors, a blind spot interpolation strategy driven by the physical conduction mechanism is used to generate a blind spot interpolation data sequence. Based on the synchronized dataset of the sensor coverage area and the blind spot interpolation data sequence after spatiotemporal alignment, a target period detection dataset is jointly constructed, which significantly improves the spatial coverage of the target period detection dataset, effectively eliminates monitoring blind spots, and improves the accuracy and comprehensiveness of leakage analysis results.

[0149] In some embodiments, the spatial grid model of the dam foundation curtain is analyzed to identify and mark the cylindrical structure joint area; based on the material leakage test data, basic leakage influence weights are assigned to the temperature data, seepage pressure data and deformation data in the target period detection data set respectively; based on the joint leakage test data, the basic leakage influence weights of the temperature data, seepage pressure data and deformation data corresponding to the cylindrical structure joint area in the target period detection data set are subjected to key area influence correction processing to determine the joint area leakage influence weight; based on the target period detection data set, according to the basic leakage influence weight and the joint area leakage influence weight, the temperature data, seepage pressure data and deformation data corresponding to different areas in the target period detection data set are subjected to weighted fusion analysis to determine the real-time leakage risks corresponding to different areas; based on the real-time leakage risks and corresponding deformation data corresponding to different areas, several high-risk leakage areas are determined, and based on the several high-risk leakage areas, a leakage risk distribution heat map is constructed; the leakage risk distribution heat map is visualized and output as the dam foundation curtain leakage trend information.

[0150] The cylindrical structure joint area can be the joint area formed by splicing precast concrete cylinders in the dam foundation curtain, and its leakage risk is significantly higher than that of the homogeneous structure area.

[0151] The foundation leakage impact weight can be the basic impact ratio of temperature, seepage pressure and deformation data given by the inherent properties of dam concrete material on leakage risk assessment.

[0152] The joint leakage test data may be experimental data obtained from an accelerated aging leakage test on concrete column joints.

[0153] The key area impact correction process can be a process of adjusting the basic impact weights of various influencing parameters in the joint area based on the characteristics that the leakage analysis of the cylindrical structure joint area is significantly higher than the average structure area.

[0154] The joint area leakage impact weight may be a leakage risk assessment weight that is corrected for the high risk of the joint area.

[0155] Weighted fusion analysis can be a process of superimposing temperature, seepage pressure, and deformation data according to weights to analyze the comprehensive leakage risk of the region.

[0156] The real-time leakage risk can be a quantitative indicator that represents the possibility of leakage occurring in a certain area of ​​the dam foundation curtain at the current moment.

[0157] The high-risk leakage area can be a collection of dam curtain areas with high leakage analysis.

[0158] The leakage risk distribution heat map can be a visualization map that maps the spatial distribution of real-time leakage risks with gradients marked with different colors.

[0159] Specifically, in the process of leakage analysis on the dam foundation curtain, the existing technology usually treats the dam foundation curtain as a uniform whole, without considering that the specific impact of the influencing factors will be amplified in the joint area where the leakage risk is significantly higher due to the multi-cylinder splicing structure of the dam foundation curtain itself; by loading the dam foundation curtain space grid model, extracting the spatial coordinates and diameter parameters of all cylindrical components, generating the joint center line along the axis of the cylinder, and extending it to both sides to form a joint influence zone (the joint influence zone is a hyperbolic paraboloid), highlighting the joint influence zone in the three-dimensional model, determining the cylindrical structure joint area, and then calling the material leakage experimental data, according to the material characteristics of the dam curtain, assigning the basic leakage influence weight to the temperature data, seepage pressure data and deformation data in the target period detection data set, Furthermore, based on the basic leakage impact weight and combined with the joint leakage experimental data, the data impact corresponding to the cylindrical structure joint area is corrected to obtain the joint area leakage impact weight. The temperature, seepage pressure, and deformation data corresponding to each area are multiplied by the corresponding weight value and risk conversion coefficient, and the sum is obtained to obtain the real-time leakage risk corresponding to the area. All real-time leakage risk values ​​are mapped to the HSV color space (high risk: hue 0° red, low risk: hue 240° blue), and the corresponding color gradient is rendered on the surface of the three-dimensional dam foundation curtain model to generate a leakage risk distribution heat map. At the same time, a timeline control can be integrated into the leakage risk distribution heat map to support the playback of the risk evolution process according to the freeze-thaw stage. The above leakage risk distribution heat map can be visualized and output through human-computer interaction equipment, such as high-definition display screens.

[0160] Through this scheme, the spatial grid model of the dam foundation curtain is analyzed, the cylindrical structure joint area is identified, and on the basis of the foundation leakage influence weight, the influence of the corresponding data of the cylindrical structure joint area is corrected to determine the leakage influence weight of the joint area. On this basis, according to the foundation leakage influence weight and the joint area leakage influence weight, the temperature data, seepage pressure data and deformation data in different areas are weighted fusion analysis to obtain the real-time leakage risk corresponding to different areas, and the corresponding leakage risk distribution heat map is generated as the dam foundation curtain leakage trend information for visualization output, so that the leakage risk assessment of the cylindrical structure joint area, which is an area with higher leakage risk, is more accurate.

[0161] In some embodiments, based on the joint leakage experimental data, the joint width change data, the thermal conductivity of the joint filling material and the joint interface shear strength degradation coefficient are extracted; the joint width change data is positively correlated with the joint area leakage influence weight; the thermal conductivity of the joint filling material is negatively correlated with the joint area leakage influence weight; the joint interface shear strength degradation coefficient is positively correlated with the joint area leakage influence weight; based on the basic leakage influence weight, according to the joint width change data, the thermal conductivity of the joint filling material and the joint interface shear strength degradation coefficient, a joint area influence correction function is constructed; according to the joint area influence correction function, the basic leakage influence weight is subjected to key area influence correction processing to quantify the joint area leakage influence weight.

[0162] The joint width change data may be monitoring data reflecting the dynamic change of the joint width under the action of freeze-thaw cycles.

[0163] The thermal conductivity of the joint filling material may be a physical parameter that characterizes the thermal conductivity of the joint filling material.

[0164] The degradation coefficient of shear strength of joint interface can be an indicator to quantify the degree of shear performance degradation of joint concrete interface due to freeze-thaw damage.

[0165] The joint area impact correction function may be a mathematical function that relates joint characteristic parameters to leakage risk weights.

[0166] Specifically, according to the positive correlation influence conversion ratio (positive number) between the joint width change data and the joint area leakage influence weight, the negative correlation influence conversion ratio (negative number) between the thermal conductivity of the joint filling material and the joint area leakage influence weight, and the exponential correlation influence conversion ratio (positive number) between the joint interface shear strength degradation coefficient and the joint area leakage influence weight, the comprehensive influence factor is obtained according to the sum of the above three conversion ratios. The basic leakage influence weight is used as the benchmark value. According to the product of the basic leakage influence weight and the comprehensive influence factor, the joint area influence correction function is constructed to realize the key area influence correction processing of the basic leakage influence weight, and the joint area leakage influence weight is obtained.

[0167] Through this scheme, the correlation between the joint width change data in the joint leakage experimental data, the thermal conductivity coefficient of the joint filling material and the shear strength degradation coefficient of the joint interface and the leakage influence weight of the joint area are respectively constructed, and a joint area influence correction function is constructed. According to the joint area influence correction function, the basic leakage influence weight is corrected for the key area influence, and the joint area leakage influence weight is quantified. The multi-parameter coupling correction mechanism is used to reduce the assessment error of the leakage risk of the joint area.

[0168] In some embodiments, the real-time leakage risks corresponding to different areas are compared with the risk precursor benchmark values ​​respectively. According to the comparison results, the areas where the real-time leakage risks exceed the risk precursor benchmark values ​​are marked as key analysis areas; according to the target period detection data set, with the key analysis area as the benchmark, the deformation data corresponding to each key analysis area and the adjacent temperature conduction layer in the target period detection data set are extracted to construct a key area deformation data set; according to the key area deformation data set, the deformation development direction of the current key analysis area is analyzed to determine the tracking target area; the current tracking target area and the key analysis area are regarded as high-risk leakage areas.

[0169] The risk precursor benchmark value may be a pre-set leakage risk threshold value, which is used to distinguish between a normal risk state and an abnormal risk state that requires special attention. The risk precursor benchmark value may be obtained by fitting experimental data.

[0170] The key analysis area may be the dam foundation curtain sub-area where the real-time leakage risk exceeds the risk precursor benchmark value.

[0171] The key area deformation dataset may be a set containing deformation data of the key analysis area and its adjacent temperature conduction layers.

[0172] The tracking target area may be a spatial area corresponding to the current maximum deformation value in the deformation dataset.

[0173] Specifically, in the process of evaluating high-risk leakage areas, since leakage situations will spread and develop dynamically, the judgment of high-risk leakage areas cannot simply rely on the level of real-time leakage risks. It is necessary to include adjacent areas in the deformation development direction according to the deformation development direction corresponding to the area with high real-time leakage risk into the high-risk leakage area. By analyzing areas with potential leakage spread risks, the lag in risk identification can be reduced. According to the numerical comparison results of different real-time leakage risks with risk precursor benchmark values, key analysis areas are screened out, and then, based on the deformation data set of key areas, the stress concentration direction of the key analysis area (the relative direction between the key analysis area and the area where the stress increase in the adjacent layer exceeds the average value) is analyzed. The stress concentration direction is the deformation development direction, and the area in the deformation development direction is determined as the tracking target area. Then, by integrating the current tracking target area and the key analysis area, the high-risk leakage area is obtained.

[0174] Through this solution, during the assessment of high-risk leakage areas, the key analysis areas and tracking target areas are integrated into high-risk leakage areas through a dual assessment mechanism of real-time leakage risk and deformation development direction. By analyzing areas with potential leakage and spread risks, the lag in risk identification is reduced.

[0175] Figure 3 A schematic diagram of a dam leakage diagnosis system based on AI technology is provided in one embodiment of the present application. Figure 3 As shown, a dam leakage diagnosis system 300 based on AI technology in this embodiment includes: a data alignment module 301 , a data tracking module 302 and a risk analysis module 303 .

[0176] A data alignment module 301 is configured to acquire a sensor array data set, analyze the sensor array data set, and determine a unified spatiotemporal detection data set;

[0177] The data tracking module 302 is configured to analyze the unified spatiotemporal detection dataset, determine a freeze-thaw conversion timeline, and track and filter corresponding detection data in the unified spatiotemporal detection dataset based on the freeze-thaw conversion timeline to determine a target period detection dataset.

[0178] The risk analysis module 303 is used to perform evolutionary simulation on the leakage development situation of the dam foundation curtain according to the target period detection data set, and determine and output the leakage trend information of the dam foundation curtain.

[0179] Optionally, in the data alignment module 301, the sensor array data set includes a temperature data subset, an osmotic pressure data subset, and a deformation data subset;

[0180] The temperature data subset is obtained by distributed fiber Bragg grating temperature sensors arranged on the dam foundation curtain in a three-dimensional grid topology;

[0181] The seepage pressure data subset is obtained by distributed optical fiber micro-pressure sensors arranged on the dam foundation curtain in the form of the three-dimensional grid topology;

[0182] The deformation data subset is obtained by distributed optical fiber stress sensors arranged on the dam foundation curtain in the form of the three-dimensional grid topology;

[0183] The distributed fiber Bragg grating temperature sensor, the distributed fiber micro-pressure sensor and the distributed fiber stress sensor are all arranged on the side of the dam foundation curtain facing the upstream of the dam body;

[0184] The distributed fiber Bragg grating temperature sensor, the distributed fiber micro-pressure sensor and the distributed fiber stress sensor are connected in series to the same fiber path by using optical wavelength division multiplexing technology.

[0185] Optionally, the data alignment module 301 is specifically configured to:

[0186] constructing a dam foundation curtain spatial grid model according to the three-dimensional grid topology of the distributed optical fiber sensors on the dam foundation curtain;

[0187] Analyzing the three-dimensional grid topology according to the dam foundation curtain spatial grid model, determining the relative position coordinates of each sensor, and constructing a unified spatial position coordinate set;

[0188] analyzing the unified set of spatial position coordinates and evaluating a signal processing delay of each sensor based on a relative distance between each sensor and a corresponding signal demodulator;

[0189] performing timestamp correction processing on data collected by each sensor in the sensor array data set according to the signal processing delay to determine a unified timestamp data set;

[0190] According to the unified spatial position coordinate set and the unified timestamp data set, each data in the sensor array data set is spatially marked and timestamp-marked respectively, and the temperature data synchronization subset, the osmotic pressure data synchronization subset and the deformation data synchronization subset after the spatiotemporal unification are determined to construct the unified spatiotemporal detection data set.

[0191] Optionally, when analyzing the unified spatiotemporal detection dataset to determine the freeze-thaw conversion timeline, the data tracking module 302 is specifically configured to:

[0192] Based on the dam foundation curtain spatial grid model, and according to the temperature data synchronization subset in the unified spatiotemporal detection dataset, constructing a curtain temperature gradient distribution map;

[0193] Based on the dam foundation curtain spatial grid model, and according to the synchronized subset of seepage pressure data in the unified spatiotemporal detection dataset, a seepage pressure change rate distribution map is constructed;

[0194] Performing a spatiotemporal correlation analysis on the curtain temperature gradient distribution map and the osmotic pressure change rate distribution map; when the temperature gradient extreme point distribution in the curtain temperature gradient distribution map forms a spatiotemporal coupling relationship with the osmotic pressure change rate inflection point in the osmotic pressure change rate distribution map, determining that the area corresponding to the current data enters a critical state of freeze-thaw transition, and extracting the timestamp of the corresponding data as the freeze-thaw start time node of the area where the current sensor is located;

[0195] determining a curtain depth of the dam foundation curtain according to the dam foundation curtain spatial grid model;

[0196] Based on the curtain depth, according to the freeze-thaw start time node corresponding to the area where each sensor is located, analyzing the sensor blind area outside the area where the sensor is located to deduce the freeze-thaw state, and determining the freeze-thaw start time node of the sensor blind area;

[0197] The freeze-thaw conversion time axis is constructed according to the freeze-thaw start time nodes corresponding to the area where the sensor is located and the sensor blind area.

[0198] Optionally, the data tracking module 302 analyzes the sensor blind area outside the sensor area to deduce the freeze-thaw state based on the curtain depth and the freeze-thaw start time node corresponding to the area where each sensor is located, and determines the freeze-thaw start time node of the sensor blind area, specifically for:

[0199] Based on the dam foundation curtain spatial grid model and the curtain depth, the dam foundation curtain is divided into a plurality of temperature conduction levels along the vertical depth direction according to preset unit depth intervals;

[0200] Determining the advancement rate of the freeze-thaw transition critical state between adjacent temperature conduction levels based on the freeze-thaw start time nodes corresponding to a plurality of sensors in adjacent temperature conduction levels, and constructing an inter-level freeze-thaw state transmission chain;

[0201] Based on the inter-level freeze-thaw state transmission chain, the freeze-thaw start time node corresponding to each sensor layout blind area is determined according to the freeze-thaw start time nodes corresponding to a number of sensors in adjacent temperature conduction levels.

[0202] Optionally, when the data tracking module 302 tracks and filters the corresponding detection data in the unified spatiotemporal detection dataset according to the freeze-thaw conversion time axis to determine the target period detection dataset, it is specifically configured to:

[0203] Based on the freeze-thaw conversion time axis, extracting the temperature data synchronization subset, the osmotic pressure data synchronization subset, and the deformation data synchronization subset that are temporally correlated with the freeze-thaw start time node in the unified spatiotemporal detection dataset to construct a sensor coverage area synchronization dataset;

[0204] Based on the advancement rate in the freeze-thaw state transmission chain between the layers and the relative spatial distance between the sensor blind area and adjacent sensors, a spatiotemporal interpolation function model is established;

[0205] Based on the spatiotemporal interpolation function model and the synchronous data set of the sensor coverage area, the temperature data, the osmotic pressure data, and the deformation data of the sensor blind area on the freeze-thaw conversion time axis are interpolated in a spatiotemporal continuity manner to generate a blind area interpolation data sequence;

[0206] The blind spot interpolation data sequence is spatially and temporally aligned with the data sequence in the synchronous data set of the sensor coverage area, and the target periodic detection data set covering the entire dam foundation curtain area is constructed based on the synchronous data set of the sensor coverage area and the spatially and temporally aligned blind spot interpolation data sequence.

[0207] Optionally, the risk analysis module 303 is specifically configured to:

[0208] Analyzing the dam foundation curtain space grid model to identify and mark the cylindrical structural joint areas;

[0209] According to the material leakage test data, basic leakage influence weights are assigned to the temperature data, the seepage pressure data and the deformation data in the target period detection data set respectively;

[0210] Based on the joint leakage test data, the basic leakage influence weight of the temperature data, seepage pressure data and deformation data corresponding to the joint area of ​​the cylindrical structure in the target period detection data set is corrected for the key area influence to determine the joint area leakage influence weight;

[0211] Based on the target period detection data set, according to the basic leakage impact weight and the joint area leakage impact weight, a weighted fusion analysis is performed on the temperature data, seepage pressure data, and deformation data corresponding to different areas in the target period detection data set to determine the real-time leakage risk corresponding to the different areas;

[0212] Determine a number of high-risk leakage areas based on the real-time leakage risks and corresponding deformation data corresponding to different areas, and construct a leakage risk distribution heat map based on the high-risk leakage areas;

[0213] The leakage risk distribution heat map is visualized and output as the leakage trend information of the dam foundation curtain.

[0214] Optionally, the risk analysis module 303 performs key area impact correction processing on the basic leakage impact weight of the temperature data, seepage pressure data, and deformation data corresponding to the cylindrical structure joint area in the target period detection data set based on the joint leakage test data, and determines the joint area leakage impact weight specifically for:

[0215] Extracting joint width variation data, joint filling material thermal conductivity, and joint interface shear strength degradation coefficient based on the joint leakage test data;

[0216] The seam width variation data is positively correlated with the leakage impact weight of the seam area;

[0217] The thermal conductivity of the joint filling material is negatively correlated with the leakage influence weight of the joint area;

[0218] The degradation coefficient of the joint interface shear strength is positively correlated with the weight of the joint area leakage impact;

[0219] Based on the foundation leakage impact weight, and in accordance with the joint width variation data, the thermal conductivity of the joint filling material, and the joint interface shear strength degradation coefficient, a joint area impact correction function is constructed;

[0220] According to the seam area impact correction function, the basic leakage impact weight is subjected to key area impact correction processing to quantify the seam area leakage impact weight.

[0221] Optionally, when determining a number of high-risk leakage areas based on the real-time leakage risks and corresponding deformation data corresponding to different areas, the risk analysis module 303 is specifically configured to:

[0222] Comparing the real-time leakage risks corresponding to different areas with risk precursor benchmark values ​​respectively, and marking the areas where the real-time leakage risks exceed the risk precursor benchmark values ​​as key analysis areas according to the comparison results;

[0223] According to the target period detection data set, taking the key analysis area as a benchmark, extracting deformation data corresponding to each key analysis area in the target period detection data set and the temperature conduction layer adjacent thereto, to construct a key area deformation data set;

[0224] Analyze the deformation development direction of the current key analysis area according to the deformation data set of the key area, and determine the tracking target area;

[0225] The current tracking target area and the key analysis area are regarded as the high-risk leakage areas.

[0226] The system of this embodiment can be used to execute the method of any of the above embodiments. Its implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. A dam leakage diagnosis method based on AI technology, characterized in that: include: Acquiring a sensor array data set, analyzing the sensor array data set, and determining a unified spatiotemporal detection data set; Analyzing the unified spatiotemporal detection dataset to determine a freeze-thaw conversion timeline, and tracking and screening corresponding detection data in the unified spatiotemporal detection dataset based on the freeze-thaw conversion timeline to determine a target period detection dataset; Based on the target period detection data set, an evolutionary simulation is performed on the leakage development situation of the dam foundation curtain, and leakage trend information of the dam foundation curtain is determined and output.

2. The method according to claim 1, characterized in that The sensor array data set includes a temperature data subset, an osmotic pressure data subset, and a deformation data subset; The temperature data subset is obtained by distributed fiber Bragg grating temperature sensors arranged on the dam foundation curtain in a three-dimensional grid topology; The seepage pressure data subset is obtained by distributed optical fiber micro-pressure sensors arranged on the dam foundation curtain in the form of the three-dimensional grid topology; The deformation data subset is obtained by distributed optical fiber stress sensors arranged on the dam foundation curtain in the form of the three-dimensional grid topology; The distributed fiber Bragg grating temperature sensor, the distributed fiber micro-pressure sensor and the distributed fiber stress sensor are all arranged on the side of the dam foundation curtain facing the upstream of the dam body; The distributed fiber Bragg grating temperature sensor, the distributed fiber micro-pressure sensor and the distributed fiber stress sensor are connected in series to the same fiber path by using optical wavelength division multiplexing technology.

3. The method according to claim 2, characterized in that The analyzing the sensor array data set to determine a unified spatiotemporal detection data set includes: constructing a dam foundation curtain spatial grid model according to the three-dimensional grid topology of the distributed optical fiber sensors on the dam foundation curtain; Analyzing the three-dimensional grid topology according to the dam foundation curtain spatial grid model, determining the relative position coordinates of each sensor, and constructing a unified spatial position coordinate set; analyzing the unified set of spatial position coordinates and evaluating a signal processing delay of each sensor based on a relative distance between each sensor and a corresponding signal demodulator; performing timestamp correction processing on data collected by each sensor in the sensor array data set according to the signal processing delay to determine a unified timestamp data set; According to the unified spatial position coordinate set and the unified timestamp data set, each data in the sensor array data set is spatially marked and timestamp-marked respectively, and the temperature data synchronization subset, the osmotic pressure data synchronization subset and the deformation data synchronization subset after the spatiotemporal unification are determined to construct the unified spatiotemporal detection data set.

4. The method according to claim 3, characterized in that The analyzing the unified spatiotemporal detection dataset to determine the freeze-thaw transition timeline includes: Based on the dam foundation curtain spatial grid model, and according to the temperature data synchronization subset in the unified spatiotemporal detection dataset, constructing a curtain temperature gradient distribution map; Based on the dam foundation curtain spatial grid model, and according to the synchronized subset of seepage pressure data in the unified spatiotemporal detection dataset, a seepage pressure change rate distribution map is constructed; Performing a spatiotemporal correlation analysis on the curtain temperature gradient distribution map and the osmotic pressure change rate distribution map; when the temperature gradient extreme point distribution in the curtain temperature gradient distribution map forms a spatiotemporal coupling relationship with the osmotic pressure change rate inflection point in the osmotic pressure change rate distribution map, determining that the area corresponding to the current data enters a critical state of freeze-thaw transition, and extracting the timestamp of the corresponding data as the freeze-thaw start time node of the area where the current sensor is located; determining a curtain depth of the dam foundation curtain according to the dam foundation curtain spatial grid model; Based on the curtain depth, according to the freeze-thaw start time node corresponding to the area where each sensor is located, analyzing the sensor blind area outside the area where the sensor is located to deduce the freeze-thaw state, and determining the freeze-thaw start time node of the sensor blind area; The freeze-thaw conversion time axis is constructed according to the freeze-thaw start time nodes corresponding to the area where the sensor is located and the sensor blind area.

5. The method according to claim 4, characterized in that The method of analyzing the sensor blind area outside the sensor area to deduce the freeze-thaw state based on the curtain depth and the freeze-thaw start time node corresponding to the area where each sensor is located, and determining the freeze-thaw start time node of the sensor blind area includes: Based on the dam foundation curtain spatial grid model and the curtain depth, the dam foundation curtain is divided into a plurality of temperature conduction levels along the vertical depth direction according to preset unit depth intervals; Determining the advancement rate of the freeze-thaw transition critical state between adjacent temperature conduction levels based on the freeze-thaw start time nodes corresponding to a plurality of sensors in adjacent temperature conduction levels, and constructing an inter-level freeze-thaw state transmission chain; Based on the inter-level freeze-thaw state transmission chain, the freeze-thaw start time node corresponding to each sensor layout blind area is determined according to the freeze-thaw start time nodes corresponding to a number of sensors in adjacent temperature conduction levels.

6. The method according to claim 5, characterized in that Tracking and screening the corresponding detection data in the unified spatiotemporal detection dataset according to the freeze-thaw conversion time axis to determine the target period detection dataset includes: Based on the freeze-thaw conversion time axis, extracting the temperature data synchronization subset, the osmotic pressure data synchronization subset, and the deformation data synchronization subset that are temporally correlated with the freeze-thaw start time node in the unified spatiotemporal detection dataset to construct a sensor coverage area synchronization dataset; Based on the advancement rate in the freeze-thaw state transmission chain between the layers and the relative spatial distance between the sensor blind area and adjacent sensors, a spatiotemporal interpolation function model is established; Based on the spatiotemporal interpolation function model and the synchronous data set of the sensor coverage area, the temperature data, the osmotic pressure data, and the deformation data of the sensor blind area on the freeze-thaw conversion time axis are interpolated in a spatiotemporal continuity manner to generate a blind area interpolation data sequence; The blind spot interpolation data sequence is spatially and temporally aligned with the data sequence in the synchronous data set of the sensor coverage area, and the target periodic detection data set covering the entire dam foundation curtain area is constructed based on the synchronous data set of the sensor coverage area and the spatially and temporally aligned blind spot interpolation data sequence.

7. The method according to claim 6, characterized in that The step of performing an evolutionary simulation on the leakage development trend of the dam foundation curtain based on the target period detection data set, and determining and outputting the leakage trend information of the dam foundation curtain, includes: Analyzing the dam foundation curtain space grid model to identify and mark the cylindrical structural joint areas; According to the material leakage test data, basic leakage influence weights are assigned to the temperature data, the seepage pressure data and the deformation data in the target period detection data set respectively; Based on the joint leakage test data, the basic leakage influence weight of the temperature data, seepage pressure data and deformation data corresponding to the joint area of ​​the cylindrical structure in the target period detection data set is corrected for the key area influence to determine the joint area leakage influence weight; Based on the target period detection data set, according to the basic leakage impact weight and the joint area leakage impact weight, a weighted fusion analysis is performed on the temperature data, seepage pressure data, and deformation data corresponding to different areas in the target period detection data set to determine the real-time leakage risk corresponding to the different areas; Determine a number of high-risk leakage areas based on the real-time leakage risks and corresponding deformation data corresponding to different areas, and construct a leakage risk distribution heat map based on the high-risk leakage areas; The leakage risk distribution heat map is visualized and output as the leakage trend information of the dam foundation curtain.

8. The method according to claim 7, characterized in that The method of performing key area impact correction processing on the basic leakage influence weight of the temperature data, seepage pressure data, and deformation data corresponding to the cylindrical structure joint area in the target period detection data set based on the joint leakage experimental data to determine the joint area leakage influence weight includes: Extracting joint width variation data, joint filling material thermal conductivity, and joint interface shear strength degradation coefficient based on the joint leakage test data; The seam width variation data is positively correlated with the leakage impact weight of the seam area; The thermal conductivity of the joint filling material is negatively correlated with the leakage influence weight of the joint area; The degradation coefficient of the joint interface shear strength is positively correlated with the weight of the joint area leakage impact; Based on the foundation leakage impact weight, and in accordance with the joint width variation data, the thermal conductivity of the joint filling material, and the joint interface shear strength degradation coefficient, a joint area impact correction function is constructed; According to the seam area impact correction function, the basic leakage impact weight is subjected to key area impact correction processing to quantify the seam area leakage impact weight.

9. The method according to claim 8, characterized in that The method of determining several high-risk leakage areas based on the real-time leakage risks and corresponding deformation data of different areas includes: Comparing the real-time leakage risks corresponding to different areas with risk precursor benchmark values ​​respectively, and marking the areas where the real-time leakage risks exceed the risk precursor benchmark values ​​as key analysis areas according to the comparison results; According to the target period detection data set, taking the key analysis area as a benchmark, extracting deformation data corresponding to each key analysis area in the target period detection data set and the temperature conduction layer adjacent thereto, to construct a key area deformation data set; Analyze the deformation development direction of the current key analysis area according to the deformation data set of the key area, and determine the tracking target area; The current tracking target area and the key analysis area are regarded as the high-risk leakage areas.

10. A dam leakage diagnosis system based on AI technology, characterized in that: include: a data alignment module, configured to acquire a sensor array data set, analyze the sensor array data set, and determine a unified spatiotemporal detection data set; a data tracking module, configured to analyze the unified spatiotemporal detection dataset, determine a freeze-thaw conversion timeline, and track and filter corresponding detection data in the unified spatiotemporal detection dataset based on the freeze-thaw conversion timeline to determine a target period detection dataset; The risk analysis module is used to simulate the evolution of the leakage development situation of the dam foundation curtain according to the target period detection data set, and determine and output the leakage trend information of the dam foundation curtain.

Images