Water conservancy project quality detection method and system

Abstract

The invention relates to a water conservancy project quality detection method and system, and relates to the field of water conservancy project quality detection.The method comprises the steps that pipeline information, environment parameters and water quality parameters of a water conservancy project first water conveying pipeline with a plurality of water inlet branches are obtained; obtaining a corrosion contribution degree list; according to a corrosion contribution degree list and the corrosive substance list, performing pipe section clustering on the first water conveying pipeline to obtain a water conveying pipeline segmentation result; and traversing the segmentation result of the water conveying pipeline, processing the corrosive substance concentration list and the corrosion contribution degree list, calibrating a pipeline failure prediction moment, and sending the pipeline failure prediction moment to a water conservancy project quality detection end for detection task allocation. The technical problem that in the prior art, in order to guarantee the detection precision, short-period detection needs to be set as far as possible during corrosion state quality detection of a pipeline with a plurality of water inlet branches, and the detection time is increased or decreased, so that the detection efficiency is low is solved.

Description

Technical Field

[0001] The present invention relates to the field of water conservancy project quality inspection, and particularly to a water conservancy project quality inspection method and system. Background Art

[0002] For the quality inspection of the water conveyance pipelines of traditional water conservancy projects, there is a lack of guidance. Usually, it is a periodic full inspection. The detection method is usually to detect the pipeline status at specific intervals and perform maintenance when there are quality defects. However, since the actual water conveyance pipelines usually have multiple water inlet branches, the defect conditions inside such pipelines, especially the corrosion state, present multimodality. Detection in the mode of a longer fixed interval may result in missed detections, and detection in the mode of a shorter fixed interval may result in waste of resources and increased detection costs. Summary of the Invention

[0003] In view of the technical problem in the prior art that when detecting the quality of the corrosion state of pipelines with multiple water inlet branches, in order to ensure the detection accuracy, it is necessary to set a short detection period as much as possible, increasing the detection duration, resulting in low detection efficiency, the present invention provides a water conservancy project quality inspection method and system to solve this problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a water conservancy project quality inspection method, including: Obtaining the pipeline information, environmental parameters, and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches, wherein the environmental parameters of the first water conveyance pipeline are consistent throughout the whole section, and the water quality parameters of the first water conveyance pipeline are different throughout the whole section; Calibrating the contribution degree of the corrosion substance list of the water quality parameters according to the environmental parameters and the pipeline material information of the pipeline information, and obtaining a corrosion contribution degree list; Performing pipe section clustering on the first water conveyance pipeline according to the corrosion contribution degree list and the corrosion substance list, and obtaining a water conveyance pipeline segmentation result; Traversing the water conveyance pipeline segmentation result, processing the corrosion substance concentration list and the corrosion contribution degree list through a pre-trained pipeline thickness loss prediction model, generating a pipeline thickness loss time series prediction value, and calibrating the pipeline failure prediction time in combination with the pipeline thickness information of the pipeline information; Sending the pipeline failure prediction time to the water conservancy project quality inspection end for detection task allocation.

[0005] In a second aspect, the present invention provides a water conservancy project quality inspection system, including: A data acquisition module, which is used to obtain pipeline information, environmental parameters, and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches. Among them, the environmental parameters of the first water conveyance pipeline are the same throughout the whole section, and the water quality parameters of the first water conveyance pipeline vary throughout the whole section. A contribution degree calibration module, which is used to calibrate the contribution degree of the corrosion substance list of the water quality parameters according to the environmental parameters and the pipeline material information of the pipeline information, so as to obtain a corrosion contribution degree list. A pipe section clustering module, which is used to cluster the first water conveyance pipeline according to the corrosion contribution degree list and the corrosion substance list, so as to obtain a water conveyance pipeline segmentation result. A pipeline failure calibration module, which is used to traverse the water conveyance pipeline segmentation result, process the corrosion substance concentration list and the corrosion contribution degree list through a pre-trained pipeline thickness loss prediction model, generate a time series prediction value of the pipeline thickness loss, and combine the pipeline thickness information of the pipeline information to calibrate the pipeline failure prediction time. A detection task allocation module, which is used to send the pipeline failure prediction time to the water conservancy project quality detection end for detection task allocation.

[0006] The beneficial effects of the present invention are as follows: By collecting the pipeline information, environmental parameters, and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches, and then using the pipeline material and environmental parameters to calibrate the contribution degree of the corrosion substance list to obtain a corrosion contribution degree list; further, clustering the pipe sections according to the corrosion contribution degree lists and the corrosion substance lists at multiple positions to obtain the segmentation result of the first water conveyance pipeline; for each segment, processing the corrosion substance concentration list and the corrosion contribution degree list through a pipeline thickness loss prediction model to obtain a time series prediction value of the pipeline thickness loss; furthermore, extracting the pipeline thickness information, the thickness reduction can be carried out according to the time series, so as to calibrate the pipeline failure prediction time, which is used as the resource allocation for the subsequent quality detection task. The spatial positioning of the pipe section is realized by segmentation, and the time domain positioning of the pipe section is realized by predicting the failure time, realizing targeted quality detection and achieving the technical effect of improving the quality detection efficiency. Description of the Drawings

[0007] Figure 1 It is a schematic flow chart of a water conservancy project quality detection method provided by the present invention; Figure 2 It is a schematic structural diagram of a water conservancy project quality detection system provided by the present invention. Detailed Embodiments

[0008] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present invention.

[0009] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0010] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0011] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides a method for detecting the quality of a water conservancy project, including the steps of: S10: Obtain the pipeline information, environmental parameters, and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches, wherein the environmental parameters of the first water conveyance pipeline are consistent throughout the section, and the water quality parameters of the first water conveyance pipeline vary throughout the section; Specifically, the maintenance of the water conveyance pipeline is an important part of the water conservancy project. In order to ensure the healthy operation of the water conservancy project, it is necessary to detect the quality of the water conveyance pipeline to facilitate the immediate repair of the conveyance pipeline. The scenario of the embodiment of this application is currently defined for the water conveyance pipeline with multiple water inlet branches.

[0012] The first water conveyance pipeline of the water conservancy project is an exemplary illustration of all pipelines. Pipeline information refers to the basic information related to the pipeline, including pipeline material information, pipeline service duration information, and pipeline thickness information. Environmental parameters refer to the environmental data inside the pipeline, including temperature, pH, humidity, etc. Generally speaking, since external environmental conditions such as the temperature, humidity, and soil pH value of the water conveyance pipeline remain relatively constant along the entire pipeline length, which is usually achieved by a unified installation environment or external protective measures (such as thermal insulation layers), the environmental parameters in the embodiments of this application are parameters that are consistent throughout the section. Water quality parameters refer to the water quality parameters at multiple detection locations, including the concentration, proportion, etc. of various substances. Due to multiple water inlets, there are water quality differences at each water inlet. For example, due to the differences in the water sources of different water inlet branches (such as industrial wastewater and natural water bodies), the water quality parameters (such as the concentrations of Cl⁻ and SO4²⁻) in each section of the main pipeline change dynamically with the position, which results in differences in the water quality parameters throughout the section of the water conveyance pipelines of multiple water inlet branches.

[0013] Preferably, the data acquisition example is described as follows: Obtain static data such as pipeline materials and thickness through engineering drawings or Internet of Things sensors; Deploy temperature and humidity sensors and soil monitoring equipment to verify the environmental consistency throughout the section (such as temperature fluctuation ≤ ±2°C); Install water quality sensors at multiple water inlet branches and key nodes of the main pipeline (such as every 100 meters) to detect the concentration of corrosive substances (such as Cl⁻ and dissolved oxygen) in real time.

[0014] S20: Calibrate the contribution degree of the corrosive substance list of the water quality parameters according to the pipeline material information of the environmental parameters and pipeline information, and obtain a corrosion contribution degree list; Furthermore, calibrate the contribution degree of the corrosive substance list of the water quality parameters according to the pipeline material information of the environmental parameters and pipeline information, and obtain a corrosion contribution degree list. Step S20 includes the steps: S21: Retrieve multiple corrosive substance arrays of the pipeline material information through a corrosion data table pre-built by the user. Among them, any one of the multiple corrosive substance arrays includes at least one corrosive substance and has a collaborative environmental parameter calibrated by a material corrosion chemical formula. Any environmental attribute of the collaborative environmental parameter has a deviation threshold identifier and an attribute weight identifier; S22: Compare the detected substances of the water quality parameters with the multiple corrosive substance arrays to obtain multiple selected corrosive substance arrays, and use the multiple selected corrosive substance arrays as multiple list elements to construct the corrosive substance list; S23: Calibrate the contribution degree of the corrosive substance list based on the environmental parameters and the collaborative environmental parameters to obtain a corrosion contribution degree list.

[0015] Further, based on the environmental parameters and the collaborative environmental parameters, calibrate the contribution degree of the corrosion substance list to obtain a corrosion contribution degree list. Step S23 includes the steps: S231: Obtain the first corrosion substance array of the corrosion substance list, and extract the first attribute deviation threshold and the first attribute weight from the deviation threshold identifier and the attribute weight identifier until the Nth attribute deviation threshold and the Nth attribute weight; S232: Calculate the first attribute environmental deviation of the environmental parameters and the collaborative environmental parameters until the Nth attribute environmental deviation; S233: Calculate the first attribute ratio of the first attribute deviation threshold and the first attribute environmental deviation until the Nth attribute ratio is calculated, and perform weighting according to the first attribute weight until the Nth attribute weight to obtain the contribution degree of the first corrosion substance array. Among them, when the ratio of the first attribute deviation threshold and the first attribute environmental deviation is greater than 1, the first attribute ratio is configured as 1, and when it is less than 1, the first attribute ratio is equal to the calculated ratio; S234: Add the contribution degree of the first corrosion substance array to the corrosion contribution degree list.

[0016] Specifically, the corrosion number table is a predefined database that records the chemical reaction relationships between different pipeline materials (such as carbon steel, cast iron) under different environmental parameters (temperature, humidity) and specific corrosion substances (such as Cl⁻, SO4²⁻), including data such as corrosion rate and corrosion mechanism (pitting corrosion, uniform corrosion); the collaborative environmental parameters refer to the combination of multiple environmental attributes on which the reaction between the corrosion substance and the pipeline material depends (for example, when the temperature ≥ 30°C and pH < 6, the corrosivity of Cl⁻ to stainless steel increases); the attribute deviation threshold identifier refers to the allowable deviation range between the actual value of the environmental parameter and the ideal value in the corrosion number table (such as a temperature deviation of ±5°C, and the contribution degree calculation needs to be adjusted if it exceeds); the attribute weight identifier: the influence weight of different environmental parameters on the corrosion contribution (such as a temperature weight of 0.6 and a pH weight of 0.4); the contribution degree calibration: quantify the contribution degree of the corrosion substance to the pipeline corrosion and dynamically adjust the weight in combination with the environmental and material characteristics.

[0017] Specifically, relevant corrosion substance arrays are screened from the corrosion number table according to the pipeline material (such as carbon steel). For example, the corrosion substance array of carbon steel may include Cl⁻, dissolved oxygen, SO4²⁻, and each array is associated with collaborative environmental parameters (such as for Cl⁻ corrosion, the temperature > 25°C and the flow rate < 1 m / s); the deviation threshold (such as the allowable temperature deviation of ±3°C) and the attribute weight (temperature weight of 0.7) in the array are extracted; the actual water quality parameters (such as detected Cl⁻ 300 ppm, SO4²⁻ 150 ppm) are matched with the arrays in the corrosion number table, and the matching corrosion substances (such as Cl⁻, SO4²⁻) are screened to form a corrosion substance list; the deviation between the actual environmental parameters and the collaborative environmental parameters is calculated (for example, the measured temperature of 28°C and the ideal temperature of 25°C, the deviation is +3°C); it is judged whether it exceeds the limit according to the deviation threshold (±5°C): when it does not exceed the limit, the ratio is calculated (3 / 5 = 0.6), and if it exceeds the limit, the ratio is set to 1; weighted summation: temperature ratio 0.6 × weight 0.7 + pH ratio 0.8 × weight 0.3 = comprehensive contribution degree of 0.66.

[0018] By comparing the environmental deviation with the threshold, it is avoided that the contribution degree is distorted due to local environmental fluctuations (such as a sudden short-term temperature rise). The collaborative environmental parameters comprehensively consider the interaction of multiple factors (such as high temperature + low pH aggravating Cl⁻ corrosion), which is closer to the actual corrosion scenario.

[0019] S30: According to the corrosion contribution degree list and the corrosion substance list, perform pipe segment clustering on the first water conveyance pipeline to obtain the water conveyance pipeline segmentation result; Further, according to the corrosion contribution degree list and the corrosion substance list, perform pipe segment clustering on the first water conveyance pipeline to obtain the water conveyance pipeline segmentation result. Step S0 includes the steps: S31: Extract the first-position corrosion contribution degree list and the first-position corrosion substance concentration list of the water quality parameters; S32: Weight the first-position corrosion substance concentration list with the first-position corrosion contribution degree list to construct the first-position space coordinate; S33: Extract the second-position corrosion contribution degree list and the second-position corrosion substance concentration list of the water quality parameters adjacent to the first position; S34: Weight the second-position corrosion substance concentration list with the second-position corrosion contribution degree list to construct the second-position space coordinate; S35: When the Euclidean distance between the first-position space coordinate and the second-position space coordinate is less than or equal to the clustering distance, add the first position and the second position to the same-segment position, otherwise, divide at the midpoint of the line connecting the first position and the second position into different segments; S36: Repeated analysis. When the Euclidean distance between any two adjacent positions is greater than the clustering distance, output the segmented result of the water conveyance pipeline.

[0020] Specifically, spatial coordinate construction refers to combining the list of corrosion substance concentrations and the contribution degree list of each detection point to generate multi-dimensional vector coordinates. For example, if the corrosion substances are Cl⁻ and SO4²⁻, the coordinate dimension is the concentration of each substance × contribution degree (such as Cl⁻ concentration 300 ppm × contribution degree 0.7 = 210, SO4²⁻ concentration 150 ppm × contribution degree 0.5 = 75, and the coordinate vector is [210, 75]); Euclidean distance: measures the similarity of the spatial coordinates of two detection points in multi-dimensional space and is used to determine whether they belong to the same corrosion characteristic segment; clustering distance: a preset corrosion characteristic similarity threshold (such as distance ≤ 50), calibrated based on historical data or experiments, reflecting the tolerance of corrosion mechanism differences; different segment division: when the corrosion characteristics of two points are significantly different, the midpoint of the connection line is used as the demarcation point of the two different points, and then continue to loop and cluster until the clustering condition is met, that is, when the Euclidean distance between any two adjacent positions is greater than the clustering distance, stop to ensure that the corrosion characteristics within the segment are consistent.

[0021] Exemplarily, extract the corrosion contribution degree list (such as Cl⁻: 0.7, SO4²⁻: 0.5) and concentration list (Cl⁻: 300 ppm, SO4²⁻: 150 ppm) of the first position, and generate coordinate A by weighting: [300×0.7, 150×0.5] = [210, 75]; extract the contribution degree list (Cl⁻: 0.6, SO4²⁻: 0.4) and concentration list (Cl⁻: 280 ppm, SO4²⁻: 130 ppm) of the second position, and generate coordinate B: [280×0.6, 130×0.4] = [168, 52]. Calculate the Euclidean distance = 48. Assuming the clustering distance is 50, then the first position and the second position are grouped into the same segment. If the distance between the first position and the second position is 55 (exceeding the threshold), then the midpoint of the connection line between the second position and the first position is used as the demarcation line for dividing the first position and the second position.

[0022] Cluster the pipe segments with similar corrosion mechanisms (such as high Cl⁻ contribution areas) through the weighted coordinates of corrosion contribution degree and concentration, avoiding the redundancy of full inspection.

[0023] S40: Traverse the segmented result of the water conveyance pipeline, process the list of corrosion substance concentrations and the list of corrosion contribution degrees through a pre-trained pipeline thickness loss prediction model to generate a time series prediction value of pipeline thickness loss, and calibrate the pipeline failure prediction moment in combination with the pipeline thickness information of the pipeline information; Further, traverse the segmented results of the water conveyance pipeline, and process the list of corrosion substance concentrations and the list of corrosion contribution degrees through a pre-trained pipeline thickness loss prediction model to generate a time series prediction value of the pipeline thickness loss, including: Extract the first segmented corrosion substance concentration list and the first segmented corrosion contribution degree list of the first segmented result of the water conveyance pipeline segmented results; Process the first segmented corrosion substance concentration list and the first segmented corrosion contribution degree list through the pipeline thickness loss prediction model, output the time series prediction value of the first segmented pipeline thickness loss, and add it to the time series prediction value of the pipeline thickness loss.

[0024] Further, the pre-trained pipeline thickness loss prediction model includes: Configure a pipeline corrosion substance concentration record list, a pipeline corrosion contribution degree record list, and true time series information of the pipeline thickness loss record with a preset duration; Using the true time series information of the pipeline thickness loss record as supervision, and using the pipeline corrosion substance concentration record list and the pipeline corrosion contribution degree record list as inputs, train multiple pipeline thickness loss prediction base models; Configure an output mean calculation rule for the multiple pipeline thickness loss prediction base models to generate the pipeline thickness loss prediction model.

[0025] Specifically, the time series prediction value of the pipeline thickness loss: Based on the corrosion substance concentration and contribution degree, predict the pipeline thickness loss amount (unit: mm / year) at multiple future time points (such as every year) to form time series data; Base model (BaseModel): Refers to an independent prediction model (such as LSTM, random forest), and each model learns the corrosion kinetics law from different perspectives (for example, LSTM captures time series dependencies, and random forest processes non-linear relationships); Output mean calculation rule: Take the arithmetic mean or weighted mean of the prediction results of multiple base models to reduce the risk of overfitting and improve the generalization ability; Failure prediction moment: When the cumulative loss value of the predicted thickness exceeds the pipeline safety threshold (such as the original thickness of 10 mm → the remaining thickness ≤ 2 mm), it is determined as the failure moment.

[0026] Specifically, the model pre-training process is as follows: Collect historical data: records of Cl⁻ and SO4²⁻ concentrations (sampled monthly) of a certain carbon steel pipeline over the past 10 years, a list of corrosion contribution degrees (dynamically calculated), and true thickness measurement values (annual inspection data); Align time series: Cut the input (concentration + contribution degree) and output (thickness loss) into training samples according to a time window (such as 3 years); Train the base model: LSTM model: The input is a time series concentration and contribution degree matrix, and the output is a thickness loss sequence (such as predicting the loss in the next 5 years); Random forest model: The input is the moving window mean (such as annual average concentration and contribution degree), and the output is the annual loss value; Generate the integrated model: Take the mean of the prediction results of LSTM and random forest.

[0027] Exemplarily, an example of time series prediction: The current thickness of the first segment is 8 mm, and the predicted thickness loss values for the next 5 years are [0.15, 0.18, 0.20, 0.22, 0.25] mm / year; Cumulative loss: The total loss at the end of the 5th year = 1.0 mm, and the remaining thickness = 7.0 mm (assuming the safety threshold is 5 mm); Failure determination: According to linear or non-linear regression extrapolation, the corresponding time (for example, the 15th year) when the remaining thickness ≤ 5 mm is the failure prediction time.

[0028] The integrated model takes into account both time series characteristics and static features, avoiding the bias of a single model (such as LSTM being sensitive to noise); Dynamic warning: Combine real-time data to update the predicted value and dynamically adjust the detection plan (such as when the predicted failure time of a certain segment is shortened from 10 years to 8 years, it is necessary to detect in advance).

[0029] S50: Send the pipeline failure prediction time to the water conservancy project quality inspection end for detection task allocation.

[0030] Furthermore, sending the pipeline failure prediction time to the water conservancy project quality inspection end for detection task allocation includes: Construct a detection task allocation urgency coefficient function: , where x represents the pipeline segment, t represents time, represents the detection task allocation urgency coefficient of pipeline segment x at time, represents the contribution degree threshold of the i-th attribute corrosion substance preset by the user, represents the corrosion contribution degree of the i-th attribute corrosion substance, Q represents the number of corrosion substances, represents the pipeline failure prediction time, represents the smoothing constant; According to the detection task allocation urgency coefficient function, obtain the detection task allocation urgency coefficient of any pipeline segment, and arrange the detection resource priorities from large to small to perform pipeline quality inspection.

[0031] Specifically, the urgency coefficient function is a mathematical expression that characterizes the detection priority of pipeline segments, integrating the proportion of the contribution degree of corrosive substances exceeding the threshold and the proximity to the failure time. The formula is: , and according to the detection task assignment urgency coefficient function, the detection task assignment urgency coefficient of any pipeline segment is obtained, and the detection resource priorities are arranged from large to small based on the detection task assignment urgency coefficient to perform pipeline quality detection.

[0032] The corrosion risk and time urgency are reflected in real time through the detection task assignment urgency coefficient function, avoiding the lag of fixed-cycle detection, concentrating limited resources (such as high-precision detection equipment) on high-risk pipeline segments, and reducing the probability of missed detection.

[0033] A water conservancy project quality detection method provided by an embodiment of the present invention has at least the following technical effects: 1. By collecting the pipeline information, environmental parameters, and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches, and then using the pipeline material and environmental parameters to calibrate the contribution degree of the corrosive substance list to obtain a corrosion contribution degree list; further, according to the corrosion contribution degree lists at multiple positions and the corrosive substance list, pipe segment clustering is performed to obtain the segmentation result of the first water conveyance pipeline; for each segment, the pipeline thickness loss prediction model is used to process the corrosive substance concentration list and the corrosion contribution degree list to obtain the predicted value of the pipeline thickness loss time series; furthermore, the pipeline thickness information is extracted, and the thickness reduction can be carried out according to the time series, thereby calibrating the predicted time of pipeline failure as the resource allocation for the subsequent quality detection tasks. The spatial positioning of pipe segments is realized by segmentation, and the time domain positioning of pipe segments is realized by predicting the failure time, realizing targeted quality detection and achieving the technical effect of improving the quality detection efficiency.

[0034] 2. The corrosion risk and time urgency are reflected in real time through the detection task assignment urgency coefficient function, avoiding the lag of fixed-cycle detection, concentrating limited resources (such as high-precision detection equipment) on high-risk pipeline segments, and reducing the probability of missed detection.

[0035] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the water conservancy project quality detection method provided in Embodiment 1, an embodiment of the present invention further provides a water conservancy project quality detection system, including: A data acquisition module, configured to obtain the pipeline information, environmental parameters, and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches, wherein the environmental parameters of the first water conveyance pipeline are consistent throughout the section, and the water quality parameters of the first water conveyance pipeline vary throughout the section; A contribution degree calibration module, configured to calibrate the contribution degree of the corrosion substance list of the water quality parameters according to the environmental parameters and the pipeline material information of the pipeline information, so as to obtain a corrosion contribution degree list; A pipe segment clustering module, configured to perform pipe segment clustering on the first water conveyance pipeline according to the corrosion contribution degree list and the corrosion substance list, so as to obtain a water conveyance pipeline segmentation result; A pipeline failure calibration module, configured to traverse the water conveyance pipeline segmentation result, process the corrosion substance concentration list and the corrosion contribution degree list through a pre-trained pipeline thickness loss prediction model, generate a time series prediction value of the pipeline thickness loss, and combine the pipeline thickness information of the pipeline information to calibrate the pipeline failure prediction time; A detection task allocation module, configured to send the pipeline failure prediction time to a water conservancy project quality detection end for detection task allocation.

[0036] Further, the steps executed by the contribution degree calibration module include: Retrieve multiple corrosion substance arrays of the pipeline material information through a corrosion data table pre-built by the user, wherein any one of the multiple corrosion substance arrays includes at least one corrosion substance and has a collaborative environmental parameter calibrated by a material corrosion chemical formula, and any environmental attribute of the collaborative environmental parameter has a deviation threshold identifier and an attribute weight identifier; Compare the detected substances of the water quality parameters with the multiple corrosion substance arrays to obtain multiple selected corrosion substance arrays, and use the multiple selected corrosion substance arrays as multiple list elements to construct the corrosion substance list; Based on the environmental parameters and the collaborative environmental parameters, calibrate the contribution degree of the corrosion substance list to obtain a corrosion contribution degree list.

[0037] Further, the steps executed by the contribution degree calibration module include: Obtain a first corrosion substance array of the corrosion substance list, and extract a first attribute deviation threshold and a first attribute weight from the deviation threshold identifier and the attribute weight identifier until the Nth attribute deviation threshold and the Nth attribute weight; Calculate the first attribute environmental deviation of the environmental parameters and the collaborative environmental parameters until the Nth attribute environmental deviation; Calculate a first attribute ratio of the first attribute deviation threshold and the first attribute environmental deviation until calculating the Nth attribute ratio, and perform weighting according to the first attribute weight until the Nth attribute weight to obtain a contribution degree of the first corrosion substance array, wherein when the ratio of the first attribute deviation threshold to the first attribute environmental deviation is greater than 1, configure the first attribute ratio to 1, and when it is less than 1, the first attribute ratio is equal to the calculated ratio; Add the contribution degree of the first corrosion substance array to the corrosion contribution degree list.

[0038] Further, the steps executed by the pipe segment clustering module include: Extract the first position corrosion contribution degree list and the first position corrosion substance concentration list of the water quality parameters; Weight the first position corrosion substance concentration list with the first position corrosion contribution degree list to construct the first position space coordinates; Extract the second position corrosion contribution degree list and the second position corrosion substance concentration list of the water quality parameters adjacent to the first position; Weight the second position corrosion substance concentration list with the second position corrosion contribution degree list to construct the second position space coordinates; When the Euclidean distance between the first position space coordinates and the second position space coordinates is less than or equal to the clustering distance, add the first position and the second position to the same segment position, otherwise, divide the midpoint of the line connecting the first position and the second position into different segments; Repeat the analysis. When the Euclidean distance between any two adjacent positions is greater than the clustering distance, output the water conveyance pipeline segmentation result.

[0039] Further, the steps executed by the pipeline failure calibration module include: Extract the first segment corrosion substance concentration list and the first segment corrosion contribution degree list of the first segmentation result of the water conveyance pipeline segmentation result; Process the first segment corrosion substance concentration list and the first segment corrosion contribution degree list through the pipeline thickness loss prediction model, output the first segment pipeline thickness loss time series prediction value, and add it to the pipeline thickness loss time series prediction value.

[0040] Further, the steps executed by the pipeline failure calibration module include: Configure a pipeline corrosion substance concentration record list, a pipeline corrosion contribution degree record list, and pipeline thickness loss record true value time series information with a preset duration; Using the pipeline thickness loss record true value time series information as supervision and the pipeline corrosion substance concentration record list and the pipeline corrosion contribution degree record list as inputs, train multiple pipeline thickness loss prediction base models; Configure an output mean calculation rule for the multiple pipeline thickness loss prediction base models to generate the pipeline thickness loss prediction model.

[0041] Further, the steps executed by the detection task allocation module include: Construct a detection task allocation urgency coefficient function: , where x represents a pipeline segment, and t represents time. represents the urgency coefficient of the detection task assignment for pipeline segment x at time t. represents the contribution threshold of the i-th attribute corrosion substance preset by the user. represents the corrosion contribution of the i-th attribute corrosion substance, and Q represents the quantity of the corrosion substance. represents the predicted pipeline failure time. represents the smoothing constant. According to the detection task assignment urgency coefficient function, obtain the detection task assignment urgency coefficient of any pipeline segment, and arrange the detection resource priorities from large to small based on the detection task assignment urgency coefficient to perform pipeline quality detection.

[0042] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0043] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0045] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the process Figure 1 a process or processes and / or blocks Figure 1 steps for the functions specified in a block or blocks.

[0047] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept.

[0048] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for detecting the quality of a water conservancy project, characterized in that, Including: Obtaining pipeline information, environmental parameters, and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches, wherein the environmental parameters of the first water conveyance pipeline are consistent throughout the section, and the water quality parameters of the first water conveyance pipeline vary throughout the section; Calibrating the contribution degree of the corrosion substance list of the water quality parameters according to the environmental parameters and the pipeline material information of the pipeline information, and obtaining a corrosion contribution degree list; Performing pipe section clustering on the first water conveyance pipeline according to the corrosion contribution degree list and the corrosion substance list, and obtaining a water conveyance pipeline segmentation result; Traversing the water conveyance pipeline segmentation result, processing the corrosion substance concentration list and the corrosion contribution degree list through a pre-trained pipeline thickness loss prediction model, generating a time series prediction value of the pipeline thickness loss, and calibrating the pipeline failure prediction time in combination with the pipeline thickness information of the pipeline information; Sending the pipeline failure prediction time to the water conservancy project quality inspection end for detection task allocation.

2. The method according to claim 1, characterized in that, Calibrating the contribution degree of the corrosion substance list of the water quality parameters according to the environmental parameters and the pipeline material information of the pipeline information, and obtaining a corrosion contribution degree list, including: Retrieving multiple corrosion substance arrays of the pipeline material information through a corrosion number table pre-built by the user, wherein any one of the multiple corrosion substance arrays includes at least one corrosion substance and has a collaborative environmental parameter calibrated by a material corrosion chemical formula, and any environmental attribute of the collaborative environmental parameter has a deviation threshold identifier and an attribute weight identifier; Comparing the detected substances of the water quality parameters with the multiple corrosion substance arrays, obtaining multiple selected corrosion substance arrays, and constructing the corrosion substance list with the multiple selected corrosion substance arrays as multiple list elements; Calibrating the contribution degree of the corrosion substance list based on the environmental parameters and the collaborative environmental parameters, and obtaining a corrosion contribution degree list.

3. The method according to claim 2, wherein Calibrating the contribution degree of the corrosion substance list based on the environmental parameters and the collaborative environmental parameters, and obtaining a corrosion contribution degree list, including: Obtaining the first corrosion substance array of the corrosion substance list, and extracting the first attribute deviation threshold and the first attribute weight from the deviation threshold identifier and the attribute weight identifier until the Nth attribute deviation threshold and the Nth attribute weight; Calculating the first attribute environmental deviation until the Nth attribute environmental deviation between the environmental parameters and the collaborative environmental parameters; Calculating the first attribute ratio of the first attribute deviation threshold to the first attribute environmental deviation until calculating the Nth attribute ratio, and performing weighting according to the first attribute weight until the Nth attribute weight to obtain the contribution degree of the first corrosion substance array, wherein when the ratio of the first attribute deviation threshold to the first attribute environmental deviation is greater than 1, the first attribute ratio is configured as 1, and when it is less than 1, the first attribute ratio is equal to the calculated ratio; Adding the contribution degree of the first corrosion substance array to the corrosion contribution degree list.

4. The method according to claim 1, characterized in that Performing pipe section clustering on the first water conveyance pipeline according to the corrosion contribution degree list and the corrosion substance list, and obtaining a water conveyance pipeline segmentation result, including: Extract the first position corrosion contribution degree list and the first position corrosion substance concentration list of the water quality parameters; Weight the first position corrosion substance concentration list with the first position corrosion contribution degree list to construct the first position space coordinates; Extract the second position corrosion contribution degree list and the second position corrosion substance concentration list of the water quality parameters adjacent to the first position; Weight the second position corrosion substance concentration list with the second position corrosion contribution degree list to construct the second position space coordinates; When the Euclidean distance between the first position space coordinates and the second position space coordinates is less than or equal to the clustering distance, add the first position and the second position to the same segment position, otherwise, divide them into different segments at the midpoint of the line connecting the first position and the second position; Repeat the analysis. When the Euclidean distance between any two adjacent positions is greater than the clustering distance, output the water conveyance pipeline segmentation result.

5. The method according to claim 1, wherein Traverse the water conveyance pipeline segmentation result, and process the corrosion substance concentration list and the corrosion contribution degree list through a pre-trained pipeline thickness loss prediction model to generate the pipeline thickness loss time series prediction value, including: Extract the first segment corrosion substance concentration list and the first segment corrosion contribution degree list of the first segmentation result of the water conveyance pipeline segmentation result; Process the first segment corrosion substance concentration list and the first segment corrosion contribution degree list through the pipeline thickness loss prediction model, output the first segment pipeline thickness loss time series prediction value, and add it to the pipeline thickness loss time series prediction value.

6. The method according to claim 5, wherein Pre-train the pipeline thickness loss prediction model, including: Configure the pipeline corrosion substance concentration record list, the pipeline corrosion contribution degree record list and the pipeline thickness loss record true value time series information with a preset duration; Using the pipeline thickness loss record true value time series information as the supervision, and using the pipeline corrosion substance concentration record list and the pipeline corrosion contribution degree record list as the input, train multiple pipeline thickness loss prediction base models; Configure an output mean calculation rule for the multiple pipeline thickness loss prediction base models to generate the pipeline thickness loss prediction model.

7. The method according to claim 1, characterized in that, Send the pipeline failure prediction moment to the water conservancy project quality inspection end for inspection task allocation, including: Construct a detection task allocation urgency coefficient function: ， where x represents a pipeline segment and t represents time, represents the urgency coefficient of the detection task assignment for pipeline segment x at time t, represents the contribution threshold of the i-th attribute corrosion substance preset by the user, represents the corrosion contribution of the i-th attribute corrosion substance, and Q represents the number of corrosion substances, represents the pipeline failure prediction time, represents the smoothing constant; According to the detection task allocation urgency coefficient function, obtain the detection task allocation urgency coefficient of any pipeline segment, and arrange the detection resource priorities from large to small according to the detection task allocation urgency coefficient to perform pipeline quality inspection.

8. A water conservancy project quality inspection system, characterized in that, Including: A data acquisition module for obtaining the pipeline information, environmental parameters and water quality parameters of the first water conveyance pipeline of a water conservancy project with multiple water inlet branches. Among them, the environmental parameters of the first water conveyance pipeline are the same throughout the section, and the water quality parameters of the first water conveyance pipeline vary throughout the section; A contribution degree calibration module for calibrating the contribution degree of the corrosion substance list of the water quality parameters according to the environmental parameters and the pipeline material information of the pipeline information to obtain the corrosion contribution degree list; A pipe segment clustering module for clustering the first water conveyance pipeline according to the corrosion contribution degree list and the corrosion substance list to obtain the water conveyance pipeline segmentation result; The pipeline failure calibration module is used to traverse the segmented results of the water conveyance pipeline, process the corrosion substance concentration list and the corrosion contribution degree list through a pre-trained pipeline thickness loss prediction model, generate the time series prediction value of the pipeline thickness loss, and calibrate the pipeline failure prediction time in combination with the pipeline thickness information of the pipeline information; The detection task assignment module is used to send the pipeline failure prediction time to the water conservancy project quality detection end for detection task assignment.

9. The system according to claim 8, wherein The steps executed by the contribution degree calibration module include: Retrieve multiple corrosion substance arrays of the pipeline material information through a corrosion number table pre-built by the user, where any one of the multiple corrosion substance arrays includes at least one corrosion substance and has a collaborative environment parameter calibrated by a material corrosion chemical formula, and any environmental attribute of the collaborative environment parameter has a deviation threshold identifier and an attribute weight identifier; Compare the detected substances of the water quality parameters with the multiple corrosion substance arrays to obtain multiple selected corrosion substance arrays, and use the multiple selected corrosion substance arrays as multiple list elements to construct the corrosion substance list; Based on the environmental parameters and the collaborative environment parameters, calibrate the contribution degree of the corrosion substance list to obtain the corrosion contribution degree list.

10. The system according to claim 9, characterized in that The steps executed by the contribution degree calibration module include: Obtain the first corrosion substance array of the corrosion substance list, and extract the first attribute deviation threshold and the first attribute weight from the deviation threshold identifier and the attribute weight identifier until the Nth attribute deviation threshold and the Nth attribute weight; Calculate the first attribute environmental deviation of the environmental parameters and the collaborative environment parameters until the Nth attribute environmental deviation; Calculate the first attribute ratio of the first attribute deviation threshold and the first attribute environmental deviation until the Nth attribute ratio is calculated, and perform weighting according to the first attribute weight until the Nth attribute weight to obtain the contribution degree of the first corrosion substance array, where when the ratio of the first attribute deviation threshold to the first attribute environmental deviation is greater than 1, the first attribute ratio is configured to 1, and when it is less than 1, the first attribute ratio is equal to the calculated ratio; Add the contribution degree of the first corrosion substance array to the corrosion contribution degree list.

Images