Drainage pipe network evaluation method and system based on multi-factor analysis

Abstract

The invention discloses a drainage pipe network assessment method and system based on multi-factor analysis, and relates to the field of drainage pipe network management, and the method comprises a collection module which is used for collecting the historical operation data of a drainage pipe network and the real-time monitoring data of a to-be-assessed time period, and forming an original data set with a space-time label; the processing module is used for carrying out preprocessing of time alignment, space calibration and anomaly correction on the original data set, and generating a time-space correlation standardized data set comprising historical sample data and to-be-evaluated sample data; historical operation and real-time monitoring data of the drainage pipe network can be accurately integrated, deviation is corrected through data calibration, features are extracted by integrating structure, hydraulic power and environmental factors, evaluation weights are dynamically adjusted according to pipe network building, stable operation and aging stages, a current health level, a bearing threshold value and a future risk trend are accurately output, early warning is carried out when the value exceeds a limit, and the safety of the drainage pipe network is guaranteed. Hidden dangers can be checked in time, and stable operation of a pipe network is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of drainage network management technology, specifically to a drainage network evaluation method and system based on multi-factor analysis. Background Technology

[0002] Drainage networks are core urban infrastructure, consisting of pipes, pumping stations, inspection wells, etc. They mainly collect and transport domestic sewage, industrial wastewater and rainwater, which can prevent urban flooding, prevent sewage from polluting the soil and water bodies, and ensure the stability and normal operation of the urban water environment.

[0003] The invention patent application with application number 202510694138.4 discloses a method and system for assessing the operational safety of urban drainage pipe networks. The application aims to solve the problem that "sewage pipe networks have a wide service range, large pipe scale, and complex system, but lack scientific and reasonable connection channels. This makes it difficult to detect accidents in the sewage system in a timely manner, and can only take passive emergency measures, resulting in extremely low disposal efficiency, which seriously restricts the safe operation of the sewage system and may even have an adverse impact on the normal operation of the city."

[0004] However, in the existing drainage network assessment technology, in order to ensure the stable daily operation of the drainage network, it is necessary to monitor the drainage network itself and its related parameters in real time. This monitoring method requires attention to too many parameters, is not very convenient, and its accuracy is affected by the complexity of the drainage network itself.

[0005] To this end, we propose a method and system for evaluating drainage pipe networks based on multi-factor analysis. Summary of the Invention

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a drainage network evaluation method and system based on multi-factor analysis, which can effectively solve the problems of the existing technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions; This invention discloses a drainage network evaluation system based on multi-factor analysis, comprising: The system comprises the following modules: Acquisition module, which collects historical operational data of the drainage network and real-time monitoring data for the period to be evaluated, forming a raw dataset with spatiotemporal labels; Processing module, which preprocesses the raw dataset by performing time alignment, spatial calibration, and anomaly correction, generating a spatiotemporally correlated standardized dataset including historical sample data and data to be evaluated; Extraction module, which extracts structural, hydraulic, and environmental coupling features of historical samples and corresponding dynamic features of the samples to be evaluated from the spatiotemporally correlated standardized dataset, integrating them to form a categorized dynamic feature set; Construction module, which acquires historical sample features from the categorized dynamic feature set and constructs a full life-cycle assessment model based on these features, which automatically adjusts weights according to the operational phase; Assessment module, which inputs the features of the samples to be evaluated from the categorized dynamic feature set into the assessment model, outputting the current health level, carrying capacity threshold, and future risk evolution trend of the network to be evaluated; and Early Warning module, which categorizes and stores the output results of the assessment module and simultaneously triggers over-limit warnings based on preset thresholds. The acquisition module is interconnected with the processing module via a wireless network. The processing module is interconnected with the extraction module and the construction module via a wireless network. The extraction module and the construction module are interconnected with the evaluation module via a wireless network. The evaluation module is interconnected with the early warning module via a wireless network.

[0008] Furthermore, the historical operational data collected by the acquisition module includes structural foundation data of the drainage pipe network, historical hydraulic operation data, and historical environmental impact data; The structural data includes pipe material, pipe diameter, pipe laying years, interface type and pipe route; historical hydraulic operation data includes historical flow velocity, historical flow rate, historical pressure and historical liquid level at each monitoring point; historical environmental impact data includes soil corrosivity level around the pipeline, historical groundwater level changes, land use of surrounding plots and historical extreme weather impact records. The classification dimensions of the real-time monitoring data for the period to be evaluated are consistent with those of the historical operation data, and the collection frequency of the real-time monitoring data is no less than twice that of the historical operation data. The real-time monitoring data also records the actual spatial coordinates of each monitoring point.

[0009] Furthermore, the processing module performs time alignment operations based on the timestamps in the spatiotemporal tags; For historical sample data and sample data to be evaluated in the original dataset where timestamps do not match, supplementary data for the target alignment time is calculated using the following formula:

[0010] Furthermore, when the processing module performs anomaly correction on the original dataset, if the sample data of a certain dimension exceeds the normal mapping range between that dimension and other related dimensions, the correction value of the abnormal data is calculated based on the valid data of the related dimensions. For example, the anomaly correction for the flow velocity data in the hydraulic dimension is as follows:

[0011] Furthermore, when the processing module performs anomaly correction on the original dataset, if the sample data of a certain dimension exceeds the normal mapping range between that dimension and other related dimensions, the correction value of the abnormal data is calculated based on the valid data of the related dimensions. For example, the anomaly correction for the flow velocity data in the hydraulic dimension is as follows:

[0012] Furthermore, in the full life cycle assessment model constructed by the building module, the weights are automatically adjusted to adapt to the current operating stage of the pipeline network, and the operating stages are set as the new construction period, the stable operation period, and the aging period. The expression for the full life cycle assessment model is: The smaller end value.

[0013] Furthermore, the load-bearing threshold output by the evaluation module is calculated based on a comprehensive health index and historical extreme safety condition data:

[0014] On the other hand, a drainage network evaluation method based on multi-factor analysis includes: Historical operational data of the drainage network and real-time monitoring data for the period to be evaluated are collected to form a raw dataset with spatiotemporal labels. The raw dataset is then subjected to time alignment, spatial calibration, and anomaly correction to generate a spatiotemporally correlated standardized dataset containing historical samples and samples to be evaluated. From the spatiotemporally correlated standardized dataset, structural, hydraulic, and environmental coupling features of historical samples and corresponding dynamic features of samples to be evaluated are extracted and integrated to form a classified dynamic feature set. Based on the historical sample features in the classified dynamic feature set, a full life cycle assessment model is constructed. The features of samples to be evaluated from the classified dynamic feature set are input into the full life cycle assessment model, which outputs the current health level, carrying capacity threshold, and future risk evolution trend of the network to be evaluated. The assessment output results are classified and stored, and over-limit warnings are triggered simultaneously based on preset thresholds.

[0015] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects: This invention provides a method and system for evaluating drainage pipe networks based on multi-factor analysis. During execution, the method and system comprehensively collect historical operational data of the drainage pipe network and real-time monitoring data for the period to be evaluated. Through time alignment, spatial calibration, and anomaly correction preprocessing, a standardized spatiotemporal correlation dataset is generated, effectively ensuring data accuracy and correlation. Furthermore, historical sample structure, hydraulic and environmental coupling characteristics, and dynamic characteristics of the samples to be evaluated are extracted from this dataset, integrating them to form a categorized dynamic feature set. Based on these historical sample characteristics, a full life-cycle evaluation model is constructed that automatically adjusts weights according to the new construction period, stable operation period, and aging period of the pipe network, improving evaluation adaptability. Inputting the characteristics of the samples to be evaluated into the model accurately outputs the current health level, carrying capacity threshold, and future risk evolution trend. The evaluation results can also be categorized and stored, and over-limit warnings can be triggered based on preset thresholds, providing a scientific basis for pipe network operation and maintenance, helping to prevent potential risks in a timely manner, and ensuring the long-term stable operation of the pipe network. Attached Figure Description

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

[0017] Figure 1 This is a schematic diagram of a drainage network evaluation system based on multi-factor analysis. Figure 2 This is a flowchart illustrating a drainage network evaluation method based on multi-factor analysis. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0019] The present invention will be further described below with reference to embodiments. Example

[0020] This embodiment presents a drainage network evaluation system based on multi-factor analysis, such as... Figure 1 As shown, it includes: The data acquisition module is used to collect historical operational data of the drainage network and real-time monitoring data for the period to be evaluated, forming a raw dataset with spatiotemporal labels. The historical operational data collected by the acquisition module includes structural foundation data of the drainage network, historical hydraulic operation data, and historical environmental impact data. The structural data includes pipe material, pipe diameter, pipe laying years, interface type and pipe route; historical hydraulic operation data includes historical flow velocity, historical flow rate, historical pressure and historical liquid level at each monitoring point; historical environmental impact data includes soil corrosivity level around the pipeline, historical groundwater level changes, land use of surrounding plots and historical extreme weather impact records. The classification dimensions of the real-time monitoring data and the historical operation data during the evaluation period are consistent, and the collection frequency of the real-time monitoring data is no less than twice the collection frequency of the historical operation data. The real-time monitoring data also records the actual collection spatial coordinates of each monitoring point. The processing module is used to preprocess the original dataset by performing time alignment, spatial calibration and anomaly correction, and generate a spatiotemporally correlated standardized dataset including historical sample data and sample data to be evaluated. The processing module performs time alignment based on the timestamps in the spatiotemporal tags; For historical sample data and sample data to be evaluated in the original dataset where timestamps do not match, supplementary data for the target alignment time is calculated using the following formula:

[0021] Among them, the time interval of the time-aligned data is uniformly set to the collection period of the sample data to be evaluated; The above formula selects two original data acquisition times adjacent to the target alignment time and their corresponding data values, and uses the idea of ​​linear interpolation to calculate the supplementary data of the target time. This ensures that the data time interval after time alignment is uniformly the acquisition period of the sample data to be evaluated. This not only ensures the consistency of data in different time periods in the time dimension, but also reasonably fills in the missing information based on the existing real data, avoiding the impact of time dimension differences on the accuracy of subsequent feature extraction and model evaluation. When the processing module performs spatial calibration on the original dataset, it calculates the calibrated coordinates of the monitoring points to be calibrated using the calibrated benchmark monitoring points in the pipeline topology as a reference: When performing spatial calibration on the original dataset, the processing module calculates the calibrated coordinates of the monitoring points to be calibrated using the calibrated benchmark monitoring points in the pipeline topology as a reference:

[0022] The above formula takes the benchmark monitoring points already marked in the pipeline network topology as a reference, and combines the pipeline design length and pipeline design direction angle between the monitoring point to be calibrated and the benchmark monitoring point. It calculates the calibrated plane coordinates of the monitoring point to be calibrated through trigonometric function relationships to ensure the accuracy of the spatial location data of the monitoring point. In the case where there are no directly adjacent benchmark monitoring points, iterative calibration is performed through multiple benchmark monitoring points on the pipeline network topology link until the calibration deviation is less than the preset threshold. This method makes full use of the pipeline network's own topological relationship, significantly improves the reliability of spatial data, and lays the foundation for subsequent feature analysis based on spatial correlation. If a monitoring point has no directly adjacent benchmark monitoring point, iterative calibration is performed using multiple benchmark monitoring points on the pipeline topology link until the calibration deviation is less than a preset threshold. When the processing module performs anomaly correction on the original dataset, if the sample data of a certain dimension exceeds the normal mapping range between that dimension and other related dimensions, the correction value for the abnormal data is calculated based on the valid data of the related dimensions. For example, the anomaly correction for the flow velocity data in the hydraulic dimension is as follows: Normalized value; The above formula sets weight coefficients for structural, hydraulic, and environmental characteristics, and then sums the normalized values ​​of structural, hydraulic, and environmental characteristics by weighting them to obtain a coupling characteristic index. This achieves a comprehensive quantification of the multi-dimensional characteristics of historical samples. At the same time, the normalized values ​​of structural, hydraulic, and environmental characteristics are calculated by weighted average of the parameters under their respective dimensions. This takes into account the differences in importance of different characteristics and eliminates the influence of the dimensions of each parameter through standardization, thus achieving effective integration of multi-dimensional characteristics and providing comprehensive historical characteristic input for the life cycle assessment model.

[0023]

[0024] The module is used to obtain historical sample features from the dynamic feature set of classification, and based on the historical sample features, to build a full life cycle evaluation model that can automatically adjust weights as the operation progresses. In the full life cycle assessment model built by the module, the weights are automatically adjusted to adapt to the current operating stage of the pipeline network, and the operating stages are set as the new construction period, stable operation period and aging period. The expression for the full life cycle assessment model is:

[0025] The above formula comprehensively considers the characteristic differences of different operating stages of the pipeline network and designs an evaluation model that can automatically adjust the weights. The core inputs are the coupled characteristic index and the normalized value of the dynamic characteristic. The weighted fusion of the two is achieved through the weight coefficient to obtain the comprehensive health index of the pipeline network. This model fully adapts to the performance change law of the pipeline network throughout its entire life cycle and avoids the evaluation deviation of the fixed weight model at different operating stages, thereby realizing the dynamic and accurate evaluation of the health status of the pipeline network.

[0026]

[0027] Defect Comprehensive Impact Index The calculation method is as follows:

[0028]

[0029]

[0030]

[0031] (3) The graded setting of the weight coefficient of the defect type reflects the difference in the impact of different defects on the bearing capacity. Structural defects directly threaten the integrity of the pipeline structure and the pressure bearing capacity, and are given the highest weight; functional defects mainly affect the transportation function and have a relatively small impact on the structural bearing capacity, and are given a medium weight; minor defects have a limited impact and are given a lower weight.

[0032] When defect detection data is temporarily missing or incomplete, the following two strategies can be adopted: Strategy 1: Based on historical defect statistics, and considering factors such as pipe network material, service life, and operating environment, set default values ​​for the typical defect impact index of this type of pipe network. For example, for metal pipes that have exceeded 70% of their design life,

[0033] The early warning module is used to classify and store the output results of the evaluation module, and simultaneously trigger over-limit warnings based on preset thresholds; The acquisition module is interconnected with the processing module via a wireless network. The processing module is interconnected with the extraction module and the construction module via a wireless network. The extraction module and the construction module are interconnected with the evaluation module via a wireless network. The evaluation module is interconnected with the early warning module via a wireless network.

[0034] In this embodiment, the acquisition module collects historical operational data of the drainage network and real-time monitoring data of the period to be evaluated, forming a raw dataset with spatiotemporal labels. The processing module then performs preprocessing on the raw dataset, including time alignment, spatial calibration, and anomaly correction, generating a spatiotemporally correlated standardized dataset that includes historical sample data and sample data to be evaluated. The extraction module then extracts the structural, hydraulic, and environmental coupling features of the historical samples and the corresponding dynamic features of the sample to be evaluated from the spatiotemporally correlated standardized dataset, integrating them to form a classified dynamic feature set. The construction module further obtains the historical sample features from the classified dynamic feature set. Based on the historical sample features, a full life cycle assessment model that can automatically adjust weights according to the operational stage is constructed. The assessment module inputs the sample features to be evaluated from the classified dynamic feature set into the assessment model, outputting the current health level, carrying capacity threshold, and future risk evolution trend of the network to be evaluated. Finally, the early warning module classifies and stores the output results of the assessment module and simultaneously triggers over-limit warnings based on preset thresholds.

[0035] In the above embodiments, the system can accurately integrate historical operation and real-time monitoring data of drainage pipe networks, correct deviations through data calibration, extract features by comprehensively considering structural, hydraulic, and environmental factors, dynamically adjust evaluation weights according to the pipe network's new construction, stable operation, and aging stages, accurately output the current health level, bearing capacity threshold, and future risk trends, and issue early warnings when limits are exceeded, which can promptly identify hidden dangers, ensure stable operation of the pipe network, extend its service life, and reduce failure losses. Example

[0036] At the implementation level, based on Example 1, this example refers to... Figure 2 A further detailed description of the drainage network evaluation system based on multi-factor analysis in Example 1 is provided below: A drainage network evaluation method based on multi-factor analysis includes: Historical operational data of the drainage network and real-time monitoring data for the period to be evaluated are collected to form a raw dataset with spatiotemporal labels; The original dataset is sequentially aligned in time, calibrated in space, and corrected for anomalies to generate a standardized dataset containing the spatiotemporal correlation of historical samples and samples to be evaluated. From the spatiotemporally correlated standardized dataset, the structural, hydraulic, and environmental coupling features of historical samples and the corresponding dynamic features of the samples to be evaluated are extracted and integrated to form a classification dynamic feature set; Based on the historical sample features in the classification dynamic feature set, a full life cycle assessment model is constructed; Input the features of the samples to be evaluated from the classification dynamic feature set into the full life cycle assessment model, and output the current health level, carrying capacity threshold and future risk evolution trend of the pipeline network to be evaluated; The evaluation output results are categorized and stored, and over-limit warnings are triggered simultaneously based on preset thresholds.

[0037] In summary, the system and method in the above embodiments generate a spatiotemporally correlated standardized dataset through time alignment, spatial calibration, and anomaly correction preprocessing, effectively ensuring data accuracy and correlation. Furthermore, historical sample structure, hydraulic and environmental coupling features, and dynamic features of the samples to be evaluated are extracted from this dataset and integrated to form a classified dynamic feature set. Based on the historical sample features, a full life-cycle assessment model is constructed that can automatically adjust weights according to the pipeline network's new construction period, stable operation period, and aging period, improving assessment adaptability. Inputting the features of the samples to be evaluated into the model accurately outputs the current health level, carrying capacity threshold, and future risk evolution trend. The assessment results can also be classified and stored, and over-limit warnings can be triggered based on preset thresholds, providing a scientific basis for pipeline network operation and maintenance, helping to prevent potential risks in a timely manner, and ensuring the long-term stable operation of the pipeline network.

[0038] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A sewer network assessment system based on a multi-factor analysis, characterized in that, The application relates to a sewage pipe network health evaluation method and device. The sewage pipe network health evaluation method comprises the following steps: A collection module is used to collect historical operation data of a sewage pipe network and real-time monitoring data of a to-be-evaluated period, and form an original data set with a time-space label; A processing module is used to perform time alignment, space calibration and abnormal correction preprocessing on the original data set, and generate a time-space correlation standardized data set comprising historical sample data and to-be-evaluated sample data; An extraction module is used to extract structure, hydraulic, environment coupling features of historical samples and corresponding dynamic features of to-be-evaluated samples from the time-space correlation standardized data set, and integrate to form a classification dynamic feature set; A construction module is used to obtain historical sample features in the classification dynamic feature set, and construct a full life cycle evaluation model which can automatically adjust weights according to an operation stage based on the historical sample features; An evaluation module is used to input to-be-evaluated sample features in the classification dynamic feature set into the evaluation model, and output a current health level, a bearing threshold and a future risk evolution trend of the to-be-evaluated pipe network; 2. A sewer network assessment system based on multi-factor analysis according to claim 1, characterized in that, An early warning module is used to classify and store the output results of the evaluation module, and simultaneously trigger an overrun early warning according to a preset threshold. The historical operation data collected by the collection module comprises structure basic data, historical hydraulic operation data and historical environment influence data of the sewage pipe network; The structure basic data comprises pipe material, pipe diameter, pipe laying age, interface type and pipe route; the historical hydraulic operation data comprises historical flow rate, historical flow, historical pressure and historical liquid level of each monitoring point; and the historical environment influence data comprises pipe surrounding soil corrosion grade, historical underground water level change, surrounding land use property and historical extreme weather influence record.

3. The sewer network evaluation system based on multi-factor analysis of claim 1, wherein, The classification dimensions of the real-time monitoring data of the to-be-evaluated period and the historical operation data are consistent, the collection frequency of the real-time monitoring data is not lower than 2 times the collection frequency of the historical operation data, and the real-time monitoring data also synchronously records actual collection space coordinates of each monitoring point. For the historical sample data and the sample data to be evaluated in the original data set with timestamp mismatch, the supplementary data at the target alignment time is calculated by the following formula:

4. The sewer network evaluation system based on multi-factor analysis of claim 1, wherein, The processing module performs a time alignment operation based on a time stamp in the time-space label; 5. The sewer network evaluation system based on multi-factor analysis of claim 1, wherein, When the processing module performs space calibration on the original data set, a calibrated coordinate of a to-be-calibrated monitoring point is calculated with reference to a calibrated reference monitoring point in a pipe network topological structure:

6. The sewer network evaluation system based on multi-factor analysis of claim 1, wherein, When the processing module performs abnormal correction on the original data set, when sample data in a certain dimension exceeds a normal mapping range of the certain dimension and other associated dimensions, a correction value of the abnormal data is calculated based on effective data of the associated dimensions, wherein abnormal correction of flow rate data in a hydraulic dimension is:

7. The sewer network evaluation system based on multi-factor analysis of claim 1, wherein, The extraction module extracts structure, hydraulic, environment coupling features of historical samples in compliance with: The expression of the full life cycle assessment model is:

8. The sewer network evaluation system based on multi-factor analysis of claim 1, wherein, In the full life cycle evaluation model constructed by the construction module, the weight automatically adjusts and adapts to a current operation stage of the pipe network, and the operation stage is set as a new construction period, a stable operation period and an aging period; wherein the preset threshold applied in the early warning module is 1.

9. The sewer network evaluation system based on multi-factor analysis of claim 1, wherein, The bearing threshold output by the evaluation module is calculated based on a comprehensive health index and historical limit safety working condition data:

10. A method for sewer network assessment based on multi-factor analysis, the method being a method for implementing a sewer network assessment system based on multi-factor analysis according to any one of claims 1-9, characterized in that, The collection module is connected with the processing module through wireless network interaction, the processing module is connected with the extraction module and the construction module through wireless network interaction, the extraction module and the construction module are connected with the evaluation module through wireless network interaction, and the evaluation module is connected with the early warning module through wireless network interaction. The application relates to a sewage pipe network health evaluation method and device. Collect historical operation data of the drainage pipe network and real-time monitoring data of the to-be-evaluated period to form an original data set with time and space labels; Perform time alignment, space calibration and anomaly correction on the original data set in sequence to generate a time and space associated standardized data set containing historical sample and to-be-evaluated sample data; From the time and space associated standardized data set, extract the structure, hydraulic and environment coupling characteristics of the historical samples and the corresponding dynamic characteristics of the to-be-evaluated samples, and integrate them to form a classification dynamic characteristic set; Based on the historical sample characteristics in the classification dynamic characteristic set, a full life cycle evaluation model is constructed; The to-be-evaluated sample characteristics in the classification dynamic characteristic set are input into the full life cycle evaluation model, and the current health level, bearing threshold and future risk evolution trend of the to-be-evaluated pipe network are output; The evaluation output results are classified and stored, and the preset threshold is triggered to trigger an out-of-limit warning.

Images