A water quality inversion-based corrosion pipe section identification and diagnosis method for a water supply network

Abstract

The application provides a water supply pipe network corrosion pipe section identification and diagnosis method based on water quality inversion, the method collects water quality data and pipe section attribute information in a water supply pipe network area, determines the topological water flow direction based on the residual chlorine decay characteristics, determines the appropriate diagnosis node and target independent pipe section, monitors the water quality parameter change characteristics in the pipe section, combines the water quality change amount and the quantitative evaluation model of the pipe section corrosion degree, realizes the target positioning of the corrosion pipe section and the rapid inversion diagnosis of the corrosion state, the input layer of the model is the water quality change characteristics and pipe section information between the pipe network diagnosis nodes, the operation layer adopts an algorithm based on the water quality decay characteristics and the corrosion state mapping relationship, and the output layer is the pipe section corrosion state score, when the diagnosis result is lower than the preset safety threshold, the warning information and the maintenance suggestion are generated, the application can realize the diagnosis effect with the determination coefficient exceeding 0.95, and effectively improves the safety and reliability of the operation management of the water supply pipe network.

Description

Technical Field

[0001] This invention belongs to the field of water supply network inspection and relates to a method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion. Background Technology

[0002] Drinking water safety is crucial to public health and socio-economic development, making water quality assurance paramount. Water supply networks are a vital component of urban water supply systems, primarily delivering treated drinking water from water plants to end-users. However, with increasing network age and the long-term effects of complex water environments, corrosion within water supply pipes is becoming increasingly prominent. Corrosion within the pipe walls not only leads to water quality deterioration, causing secondary pollution problems such as excessive heavy metals, increased turbidity, and increased color, seriously affecting the safety and quality of tap water, but the accumulation of corrosion products also impacts hydraulic transport performance, increases energy consumption and network operating costs, shortens pipe lifespan, and affects the stable operation of urban water supply systems.

[0003] Internal corrosion detection, pipeline cleaning, maintenance, and upgrades are crucial operational tasks for water supply companies. However, these tasks often suffer from high costs, low diagnostic efficiency, and untimely maintenance. In trenchless pipeline inspection, related technologies, such as a pressure pipeline internal corrosion detection device (publication number CN119246686A) and a water transmission pipeline internal wall inspection equipment and method (authorization announcement number CN118998514B), use ultrasonic and optical sensor technologies to detect the internal condition of pipelines. However, these technologies suffer from high equipment costs and the inability to achieve continuous monitoring. A pipeline internal detection method and system based on multi-sensor fusion (authorization announcement number CN119150175B) predicts pipeline status by fusing multi-sensor data and analyzing historical data, but it relies on a large amount of historical data, has high implementation and maintenance costs, and cannot accurately determine the pipeline condition. A method and device for monitoring corrosion of water-steam pipelines in supercritical units (publication number CN 119848752A) only monitors and simulates water quality at the inlet and outlet of the water-steam pipelines. It cannot achieve rapid location and corrosion status diagnosis of target pipe sections in water supply networks under multi-node and complex hydraulic conditions. Therefore, there is an urgent need for a method that can quickly and accurately quantify and dynamically assess the corrosion status of water supply networks and provide real-time early warning, ensuring the safety and reliability of network operation. Summary of the Invention

[0004] The purpose of this invention is to provide a method for rapid inversion diagnosis of corrosion status of the inner wall of a water supply network by monitoring the decay characteristics of water flow and water quality parameters in multiple nodes of a water supply network area, combining the network operation data to construct a corrosion degree evaluation model, quickly locating and accurately quantifying the corrosion status of the target pipe section.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion includes the following steps:

[0007] Step S1: Obtain water quality data and pipe segment attribute information for multiple nodes within the water supply network area;

[0008] Step S2: Determine the direction of topological flow by the direction of residual chlorine concentration decay, identify suitable diagnostic nodes based on diagnostic targets, eliminate branch pipe interference, and determine the target independent pipe segment;

[0009] Step S3: Extract features from the water quality data at the upstream and downstream points of the target independent pipe section to obtain water quality decay characteristics that reflect the corrosion state of the water supply pipe section.

[0010] Step S4: The water quality decay characteristics and the pipe segment attribute information are used as input data for the input layer. A regression model is constructed in the computation layer to characterize the mapping relationship between water quality decay characteristics and corrosion state. The corrosion state of the inner wall of the target pipe segment of the water supply network is inverted and calculated to obtain the evaluation score of the corrosion degree. The evaluation score is then output through the output layer.

[0011] Step S5: Based on the evaluation score, quickly diagnose the degree of corrosion of the water supply pipe section and issue early warnings or make maintenance decisions;

[0012] In step S2, the total chlorine concentration at each node in the water supply network topology satisfies the following equation: , in This is the vector of total chlorine concentration. This represents the vector of total chlorine concentration changes between nodes. Let the node water supply vector be... The flow vector of the pipe segment is used; the topological flow direction of the water supply network is determined based on the direction of the decay of residual chlorine concentration. Among them, the node with high residual chlorine concentration in the same pipe segment is determined to be upstream, and the node with low residual chlorine concentration is determined to be downstream.

[0013] In step S2, the distance range between the diagnostic nodes corresponding to the target pipe segment must meet the following conditions:

[0014] There should be no branch pipe confluence along the connection path between the two nodes to limit the maximum distance between them; the difference in total chlorine concentration between the two nodes must meet the following requirements. Where LOD is the detection limit for total chlorine concentration, and n is a coefficient determined according to the diagnostic accuracy requirements to limit the minimum distance between nodes;

[0015] In step S3, the water quality decay characteristic refers to the amount of water quality change per unit hydraulic residence time or per unit pipe length, which is calculated using the water quality index parameters of the diagnostic node and the attribute parameters of the corresponding target independent pipe segment, including time-decay variables. Variable decay along the way , decay variables along space ,in These are downstream water quality parameters, among which For upstream water quality parameters, L For the length of the pipe section, T The hydraulic residence time, D The diameter is the pipe diameter.

[0016] Preferably, in step S1, the water quality data includes conventional indicators and corrosion indicators, and the acquisition methods include collecting samples from fire hydrants and user taps for testing, as well as retrieving water quality monitoring data that is regularly uploaded and updated in the GIS system.

[0017] The conventional indicators include turbidity, total chlorine concentration, free chlorine concentration, pH value, ammonia nitrogen concentration, iron ion concentration, manganese ion concentration, total organic carbon (TOC), total nitrogen concentration (TN), and total trihalomethane concentration (THMs).

[0018] The corrosion indicators include calcium hardness, bicarbonate concentration, chloride concentration, sulfate concentration, Langeliier saturation index, Larson index, and calcium carbonate precipitation potential (CCPP).

[0019] The conventional indicators are those specified in the "Standards for Drinking Water Quality" GB5749; the corrosion indicators are those used to assist in assessing the water body's potential for metal corrosion and scale formation.

[0020] Preferably, in step S1, the target independent pipe segment attribute information is obtained through the water supply network GIS system, including pipe age, pipe diameter, pipe segment length, water flow velocity, and hydraulic residence time.

[0021] Preferably, in step S4, the algorithmic features of the inversion calculation's computational layer are as follows: , A regression model is used to establish the mapping relationship between the input independent variables and the output dependent variable, thereby achieving the inversion calculation of the corrosion state of the target independent pipe segment. Specific fitting methods include multinomial regression, multiple linear regression, random forest regression, and neural network regression. The multiple linear regression model is as follows: ,in For the input feature variable vector, For the intercept term, These are the regression coefficients; the regression coefficients are obtained using the least squares method. It is estimated that among themX For the input sample matrix, Y This is the column vector of observations for the corresponding sample.

[0022] Preferably, the corrosion status evaluation score of the output layer is used to reflect the physical and chemical properties and corrosion characteristics of the inner surface of the pipeline, including corrosion rate, corrosion product composition, pipeline remaining life and its impact on water quality.

[0023] Preferably, the regression model needs to meet the following conditions:

[0024] The coefficient of determination (R²) should be greater than 0.9, the residual distribution should satisfy the normality assumption and have no significant heteroscedasticity, the mean of the residuals should be close to zero, the variance inflation factor (VIF) should be less than 10, and the Durbin-Watson test (DW value) should be between 1.5 and 2.5. Among the candidate models that meet the above conditions, the model with the highest coefficient of determination (R²), the Durbin-Watson test (DW value) close to 2, and the smallest root mean square error (RMSE) and mean absolute error (MAE) should be selected as the optimal regression model.

[0025] Preferably, in step S5, the warning limit for the corrosion status evaluation score is 0. An evaluation score higher than 0 indicates that the pipe section is in good condition, and an evaluation score lower than 0 indicates that there is obvious corrosion on the inner wall of the pipe section. The lower the evaluation score, the more severe the corrosion.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] (1) Reduce waste of manpower and resources: This invention uses water quality monitoring and real-time data analysis to quickly identify corroded pipe sections based on water quality changes, and prioritizes the maintenance of high-corrosion-risk areas to achieve efficient resource allocation;

[0028] (2) Rapid diagnosis and accurate early warning: This invention adopts a regression model based on optimal parameters, combined with pipeline network attributes and water quality decay characteristics, to accurately determine the topological direction of water flow in the water supply network, locate the target pipe section of corrosion, diagnose the corrosion status of the pipeline and provide timely early warning, so as to ensure the safe operation of the pipeline network;

[0029] (3) Intelligent monitoring and management: This invention establishes an algorithm to invert the pipeline state by changing water quality parameters, thereby realizing intelligent perception, dynamic updating and refined management of the corrosion state of the water supply network, and improving the efficiency of pipeline corrosion prevention and control.

[0030] (4) Wide applicability and scalability: The method of the present invention can be integrated into the existing water supply network management system and can be flexibly adjusted for different water quality conditions and network structures, thus possessing good applicability and scalability.

[0031] The principle of this invention is to collect water quality data and pipe segment attribute information from multiple points within a water supply network area. Based on the residual chlorine decay characteristics, suitable diagnostic nodes and target independent pipe segments are identified. A quantitative evaluation model of water quality change and corrosion degree of the target pipe segment is constructed. The input layer of the model consists of water quality change characteristics and pipe segment attribute information between diagnostic nodes in the network. The computational layer uses an algorithm based on the mapping relationship between water quality decay characteristics and corrosion state. The output layer is the pipe corrosion state score. When the diagnostic result is lower than a preset safety threshold, early warning information and maintenance suggestions are generated. The constructed model can achieve a diagnostic effect with a determination coefficient exceeding 0.95, possessing dynamic assessment and precise early warning capabilities for the corrosion state of the water supply network, effectively improving the safety and reliability of water supply network operation and management. Attached Figure Description

[0032] Figure 1 A flowchart illustrating a method for identifying and diagnosing corroded pipe sections in a water supply network based on water quality inversion, provided as an embodiment of the present invention;

[0033] Figure 2 An embodiment of the present invention provides a method for identifying and diagnosing corroded pipe sections in a water supply network based on water quality inversion. This method is implemented using a preferred multiple linear regression model, with the coefficient of determination R0... 2 These are the evaluation indicators. Detailed Implementation

[0034] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0035] like Figure 1 As shown in this embodiment, a method for identifying and diagnosing corroded pipe sections in a water supply network based on water quality inversion is provided, including:

[0036] Step S1: Obtain water quality data and pipe segment attribute information for multiple nodes within the water supply network area; pipe segment attribute information includes pipe age, pipe diameter, water flow velocity, and hydraulic residence time;

[0037] Step S2: Determine the direction of topological flow by the direction of residual chlorine concentration decay, identify suitable diagnostic nodes based on diagnostic targets, eliminate branch pipe interference, and determine the target independent pipe segment;

[0038] Step S3: The variables are the pipe age, pipe diameter and other attribute information of the target pipe segment, as well as the water quality data of the upstream and downstream points of the target independent pipe segment and the water quality degradation characteristics obtained by solving the pipe segment attribute information.

[0039] Step S4: Computational Layer: Employing the preferred multiple linear regression model

[0040]

[0041] This model can achieve the coefficient of determination (R²) 2 The variance inflation factor (VIF) of each variable is less than 10, passing the F-test. The Durbin-Watson test (DW value) is within the range of 1.5 to 2.5. The output variable is the pipeline corrosion status evaluation score.

[0042] Step S5: Based on the evaluation score, quickly diagnose the degree of corrosion of the water supply network and provide early warnings or maintenance decisions.

[0043] In steps S2 to S5, water quality monitoring and real-time data analysis are used to quickly identify the target pipe section for diagnosis and assess the corrosion status of the pipe network. After data acquisition, the computational layer automatically executes the entire process of feature calculation, model inference, and early warning determination, covering steps S2 to S5. The system can achieve rapid inversion assessment and response decision-making of the corrosion status of the water supply network, thereby realizing the immediate identification and dynamic management of corrosion risks, and significantly improving diagnostic efficiency and the accuracy of resource allocation. Example

[0044] This embodiment uses a water supply network in a certain area of ​​Southeast China as the implementation background. Based on the model established in the embodiment, it applies the following to a water supply network with pipe ages ranging from 5 to 50 years. Figure 1 The process involves screening diagnostic nodes and pipe sections, and assessing corrosion conditions. The model used in the computational layer is a multiple linear regression model. The model meets the following criteria: variance inflation factor (VIF) < 10, Durbin-Watson test (DW value) between 1.5 and 2.5, and coefficient of determination R0. 2 > 0.9.

[0045] The input variables include the pipe age, diameter, and length of the selected pipe section, as well as the decay characteristics of water quality parameters such as turbidity, total chlorine concentration, free chlorine concentration, pH value, ammonia nitrogen concentration, calcium hardness, bicarbonate concentration, chloride ion concentration, sulfate concentration, Langelier saturation index (LSI), Larson index, calcium carbonate precipitation potential (CCPP), iron ion concentration, manganese ion concentration, total organic carbon (TOC), and total nitrogen (TN). The decay characteristics are calculated based on the decay of water quality parameters per unit length of the pipe section.

[0046]

[0047] Using the aforementioned pipe section parameters and water quality degradation parameters as an input variable matrix, a stepwise regression method was employed for screening. One screening criterion was to use the variance inflation factor (VIF) to detect multicollinearity among the independent variables, requiring VIF < 10.

[0048]

[0049] The second screening criterion is to check the independence of the residuals using the Durbin-Watson test; a Durbin-Watson value in the range of 1.5 to 2.5 meets the requirements.

[0050]

[0051] Input the selected independent variables and perform calculations using a multiple linear regression model:

[0052]

[0053] Examine the coefficient of determination (R) 2 The obtained calculation results are shown in the figure. Figure 2 The calculations were performed by comparing the actual values ​​in the test dataset with the calculated values ​​from the model.

[0054]

[0055] Where y i This is the actual value of the corrosion score. This is the value calculated by the model. In this implementation method of the example, the coefficient of determination (R²) of the predicted result for the pipe section corrosion score in this embodiment is... 2 The value of 0.9545 (≥ 0.9) indicates that this embodiment can explain more than 95% of the variance of the calculated pipe section corrosion status, which is extremely close. Of the 18 pipe groups, 10 pipe sections were found to have corrosion based on the scoring threshold, consistent with the actual situation. This shows that the diagnostic accuracy of this embodiment for the internal wall corrosion of the 18 pipe sections is 100%. It can accurately diagnose the corrosion status of pipe sections based on the input pipe section parameters and water quality degradation characteristic parameters, avoiding the high costs and resource waste caused by blind excavation operations.

[0056] Example 2

[0057] This embodiment uses a water supply network in a certain area of ​​Southeast China as the implementation background. Based on the system established in this embodiment, the optimal multiple linear regression model is selected, and 0 is set as the corrosion warning limit. The pipe parameters of a 22-year-old, 1400mm diameter ductile iron pipe section in Southeast China, along with the water quality degradation characteristics at both ends, are substituted into the optimal regression model. Under this implementation method, the corrosion status score of this pipe section is calculated to be 2.09, which is higher than the set corrosion warning limit. Therefore, the pipe section is judged to be in good condition and does not require excavation for maintenance or replacement.

[0058] The above-mentioned diagnosis and maintenance of corrosion in a single pipe section does not require excavation. It only requires testing eight water quality parameters at two points on the pipe section. Combined with the GIS system, the total operating cost is about 1,000 yuan, and the diagnosis can be completed in 2 hours, which is far less than the cost required for excavation. This can save the waste of manpower and material resources caused by excavating pipelines for inspection.

[0059] Comparative Example 1

[0060] A method based on pipe age for direct pipeline maintenance was selected as a comparative example. Other application conditions remained the same as in the aforementioned embodiments. Corrosion diagnosis was performed on the pipe segment data from Embodiment 1 using the corrosion diagnosis process of this embodiment, with a pipe age exceeding 30 years as the screening criterion. The optimal regression model was used for calculation, with 0 set as the corrosion warning limit. The calculation results are shown in Table 1. Of the six pipe segments, those exceeding 50 years of age were directly replaced, while those less than 50 years old were not replaced. Three of these pipes underwent unreasonable treatment, exhibiting both failure to promptly replace corroded pipes and the replacement of unnecessary pipes, resulting in a waste of human and material resources.

[0061] Table 1 compares the actual treatment of pipe sections with an age of 30 years or more with the calculation results.

[0062] Table 1

[0063]

[0064] Comparative Example 2

[0065] Two methods, endoscopic inspection and direct excavation for pipeline maintenance and replacement, were selected as comparative examples to compare the cost, time, and applicability of the three methods, as shown in Table 2. Maintaining other application conditions identical to the aforementioned examples, endoscopic inspection was performed on the same 480m long, DN1400 ductile iron pipe section in Example 2. Beforehand, high-pressure water jets or mechanical pipe cleaners were used to remove sediment from the pipe. The inspection equipment was then placed into the pipeline through a manhole or pre-reserved opening. The probe advanced at a constant speed and transmitted data, which was then marked and analyzed by engineers. Direct costs included equipment rental fees, labor costs, and material costs. Indirect costs included lane occupancy, minor dust, and noise. The construction period was approximately 3 days, and the inspection cost was approximately 60,000 RMB / km, depending on the use of the endoscopic equipment and the operation by professional personnel. The direct costs of excavating the pipeline include equipment, labor, material, trenching, backfilling, compaction, and waste transportation costs incurred during earthwork excavation, transportation, and backfilling. Indirect costs include social costs such as traffic congestion and damage to existing facilities, as well as environmental costs such as noise, dust, and rainwater erosion of the construction site soil. The construction period was approximately 60 days, and the total pipeline maintenance cost was approximately 5 million yuan / km. After the actual excavation and replacement, it was found that the original pipeline did not show obvious corrosion, resulting in a large waste of resources.

[0066] Table 2 compares the cost of this embodiment with commonly used water supply pipeline inspection technologies.

[0067] Table 2

[0068]

[0069] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0070] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0071] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for identifying and diagnosing corroded pipe sections in a water supply network based on water quality inversion, characterized in that, Includes the following steps: Step S1: Obtain water quality data and pipe segment attribute information for multiple nodes within the water supply network area; Step S2: Determine the direction of topological flow by the direction of residual chlorine concentration decay, identify suitable diagnostic nodes based on diagnostic targets, eliminate branch pipe interference, and determine the target independent pipe segment; Step S3: Extract features from the water quality data at the upstream and downstream points of the target independent pipe section to obtain water quality decay characteristics that reflect the corrosion state of the water supply pipe section. Step S4: The water quality decay characteristics and the pipe segment attribute information are used as input data for the input layer. A regression model is constructed in the computation layer to characterize the mapping relationship between water quality decay characteristics and corrosion state. The corrosion state of the inner wall of the target pipe segment of the water supply network is inverted and calculated to obtain the evaluation score of the corrosion degree. The evaluation score is then output through the output layer. Step S5: Based on the evaluation score, quickly diagnose the degree of corrosion of the water supply pipe section and issue early warnings or make maintenance decisions; In step S2, the total chlorine concentration at each node in the water supply network topology satisfies the following equation: , ,in This is the vector of total chlorine concentration. This represents the vector of total chlorine concentration changes between nodes. Let the node water supply vector be... The flow vector of the pipe segment is used; the topological flow direction of the water supply network is determined based on the direction of the decay of residual chlorine concentration. Among them, the node with high residual chlorine concentration in the same pipe segment is determined to be upstream, and the node with low residual chlorine concentration is determined to be downstream. In step S2, the distance range between the diagnostic nodes corresponding to the target pipe segment must meet the following conditions: There should be no branch pipe confluence along the connection path between the two nodes to limit the maximum distance between them; the difference in total chlorine concentration between the two nodes must meet the following requirements. Where LOD is the detection limit for total chlorine concentration, and n is a coefficient determined according to the diagnostic accuracy requirements to limit the minimum distance between nodes; In step S3, the water quality decay characteristic refers to the amount of water quality change per unit hydraulic residence time or per unit pipe length, which is calculated using the water quality index parameters of the diagnostic node and the attribute parameters of the corresponding target independent pipe segment, including time-decay variables. Variable decay along the way , decay variables along space in These are downstream water quality parameters, among which For upstream water quality parameters, For the length of the pipe section, The hydraulic residence time, The diameter is the pipe diameter.

2. The method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion according to claim 1, characterized in that, In step S1, the water quality data includes conventional indicators and corrosion indicators. The acquisition methods include collecting samples from fire hydrants and user taps for testing, as well as retrieving water quality monitoring data that is regularly uploaded and updated in the GIS system. The conventional indicators include turbidity, total chlorine concentration, free chlorine concentration, pH value, ammonia nitrogen concentration, iron ion concentration, manganese ion concentration, total organic carbon (TOC), total nitrogen concentration (TN), and total trihalomethane concentration (THMs). The corrosion indicators include calcium hardness, bicarbonate concentration, chloride concentration, sulfate concentration, Langeliier saturation index, Larson index, and calcium carbonate precipitation potential (CCPP). The conventional indicators are those specified in the "Standards for Drinking Water Quality" GB5749; the corrosion indicators are those used to assist in assessing the water body's potential for metal corrosion and scale formation.

3. The method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion according to claim 1, characterized in that, In step S1, the target independent pipe segment attribute information is obtained through the water supply network GIS system, including pipe age, pipe diameter, pipe segment length, water flow velocity, and hydraulic residence time.

4. The method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion according to claim 1, characterized in that, In step S4, the algorithmic characteristics of the inversion calculation's computational layer are as follows: , A regression model is used to establish the mapping relationship between the input independent variables and the output dependent variable, thereby achieving the inversion calculation of the corrosion state of the target independent pipe segment. Specific fitting methods include multinomial regression, multiple linear regression, random forest regression, and neural network regression. The multiple linear regression model is as follows: ,in , which is the input feature variable vector. For the intercept term, These are the regression coefficients; The regression coefficients were obtained using the least squares method. It is estimated that among them X Input sample matrix, Y The column vector of observations corresponding to the sample.

5. The method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion according to claim 4, characterized in that, The corrosion status evaluation score of the output layer is used to reflect the physical and chemical properties and corrosion characteristics of the inner surface of the pipeline, including corrosion rate, corrosion product composition, pipeline remaining life and its impact on water quality.

6. The method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion according to claim 4, characterized in that, The regression model must meet the following conditions: The coefficient of determination (R²) should be greater than 0.9, the residual distribution should satisfy the normality assumption and have no significant heteroscedasticity, the mean of the residuals should be close to zero, the variance inflation factor (VIF) should be less than 10, and the Durbin-Watson test (DW value) should be between 1.5 and 2.

5. Among the candidate models that meet the above conditions, the model with the highest coefficient of determination (R²), the Durbin-Watson test (DW value) close to 2, and the smallest root mean square error (RMSE) and mean absolute error (MAE) should be selected as the optimal regression model.

7. The method for identifying and diagnosing corroded pipe sections in water supply networks based on water quality inversion according to claim 1, characterized in that, In step S5, the warning limit for the corrosion status evaluation score is 0. An evaluation score higher than 0 indicates that the pipe section is in good condition, while an evaluation score lower than 0 indicates that there is obvious corrosion on the inner wall of the pipe section. The lower the evaluation score, the more severe the corrosion.

Images