Urban underground pipeline life cycle safety monitoring method and system based on big data

Abstract

The invention discloses an urban underground pipeline life cycle safety monitoring method and system based on big data. The method comprises the following steps: acquiring full life cycle multi-source data of an urban underground pipeline; performing fusion preprocessing on the multi-source data, and constructing a pipeline digital twinborn model; performing real-time monitoring on the pipeline operation state by using a space-time correlation analysis algorithm, and extracting abnormal features; based on a pre-constructed deep learning risk assessment model, performing grading assessment on the pipeline safety state, and generating a risk grade; predicting the remaining service life of the pipeline through a service life prediction algorithm in combination with historical fault data and real-time monitoring data; and generating a maintenance decision suggestion according to the risk level and the remaining service life, and realizing full-life-cycle safety monitoring of the underground pipeline. A digital twinborn model is constructed through multi-source data fusion, and dynamic visual management of the whole life cycle of the underground pipeline is achieved. Through combination of time-space correlation analysis and a deep learning algorithm, pipeline abnormal features are accurately identified, and the risk assessment accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of urban public facility management, and in particular to a method and system for lifecycle safety monitoring of urban underground pipelines based on big data. Background Art

[0002] In the process of urban modernization, underground pipelines, as the lifeline of the city, play a critical supporting role in its normal operation. However, current urban underground pipeline management faces many challenges. Traditional underground pipeline safety monitoring methods mostly rely on single-point, decentralized monitoring, which makes it difficult to fully grasp the status changes of the pipeline throughout its life cycle. During the planning and design phase, a lack of forward-looking analysis of future urban development needs and potential risks has led to irrational pipeline layouts, interference between different pipelines, and insufficient reserved space. During the construction process, data recording is incomplete and non-standard, and construction information is disconnected from subsequent operations and maintenance, which poses hidden dangers to subsequent safety management.

[0003] In terms of operational monitoring, limited monitoring methods and low accuracy make it difficult to capture subtle changes in pipelines in real time. Most cities rely on only a small number of sensors or manual inspections, which are unable to detect early signs of failure. Furthermore, data from different departments and pipeline types is stored independently, with inconsistent data formats and standards. This creates data silos, severely hindering data fusion and analysis, and making it impossible to comprehensively assess the safety status of pipelines. Maintenance and inspection also present significant challenges. Due to the lack of accurate predictions of the remaining lifespan of pipelines, maintenance plans are often formulated based on experience. This can lead to either excessive maintenance, resulting in wasted resources, or insufficient maintenance, which can cause pipelines to operate with defects and cause safety accidents. Furthermore, in complex underground pipeline systems, once a failure occurs, it is difficult to quickly locate the root cause, resulting in low maintenance efficiency and a serious impact on urban operations. These issues urgently require an innovative, big data-based, full-lifecycle safety monitoring method and system to address them. Summary of the Invention

[0004] This application provides a method and system for monitoring the life cycle safety of urban underground pipelines based on big data, which is used to solve the technical problems of isolated traditional underground pipeline monitoring data and insufficient full life cycle safety assessment.

[0005] In one aspect, the present application provides a method for monitoring the lifecycle safety of urban underground pipelines based on big data, the method comprising the following steps: Step S1: Acquire multi-source data on the entire life cycle of urban underground pipelines; Step S2: performing fusion preprocessing on the multi-source data to construct a pipeline digital twin model; using a spatiotemporal correlation analysis algorithm to monitor the pipeline operation status in real time and extract abnormal features; Step S3: Perform a hierarchical assessment of the pipeline safety status based on a pre-built deep learning risk assessment model to generate a risk level; Step S4: Combine historical fault data with real-time monitoring data to predict the remaining service life of the pipeline through a life prediction algorithm; generate maintenance decision recommendations based on the risk level and remaining service life to achieve full life cycle safety monitoring of underground pipelines.

[0006] In one implementation of the present application, the multi-source data includes planning and design data, construction data, operation monitoring data, and maintenance and repair data.

[0007] In one implementation of the present application, in step S2, the spatiotemporal correlation analysis algorithm specifically performs the following process: The operation monitoring data is decomposed into time series to extract trend items, period items, and abnormal fluctuation items. A correlation matrix is constructed based on the spatial topology of the pipeline to calculate the spatiotemporal impact factors of each monitoring point. The spatial propagation range of abnormal characteristics is predicted using the spatiotemporal impact factors. The spatiotemporal impact factor calculation formula is:

[0008] Among them, SIF ij W represents the spatiotemporal impact factor of monitoring point i on monitoring point j, which is used to quantify the degree of influence of monitoring point i on monitoring point j in the spatiotemporal dimension; ij is the spatial distance weight, which reflects the association weight between monitoring point i and monitoring point j due to the spatial distance factor. Different distances usually have different weights, which is used to describe the role of spatial relationships on the impact; T ij is the time delay coefficient, which reflects the time delay characteristics of the process in which monitoring point i affects j. The time delay between different monitoring points can be reflected by this coefficient; W ik is the spatial distance weight between monitoring point i and adjacent monitoring point k, T ik is the time delay coefficient of monitoring point i to the adjacent monitoring point k, k is the index of the adjacent monitoring point, k = 1, 2, ..., n is the number of adjacent monitoring points, that is, the total number of monitoring points adjacent to monitoring point i, which is used to determine the range of the summation operation.

[0009] In one implementation of the present application, the deep learning risk assessment model specifically performs the following process: inputting the preprocessed multi-source data into the convolution layer for spatial feature extraction; processing the time series features through the long short-term memory network layer; using the attention mechanism to weight key features and output the risk level probability distribution. The risk level assessment formula is:

[0010] Where R is the risk level vector, X is the input data matrix, Conv is the convolution operation, is the hyperbolic tangent function, LSTM is the long short-term memory operation, W1, W2, W3 are weight matrices, b2, b3 are bias vectors, is the activation function.

[0011] In one implementation of the present application, step S4 specifically performs the following process: fitting the pipeline performance degradation trajectory based on the Weibull degradation model to calculate the degradation rate; using the Bayesian update method to fuse real-time monitoring data and update the remaining life probability distribution; generating a life prediction interval based on the updated distribution. The Weibull degradation model expression is:

[0012] Where, L(t) is the remaining life at time t, L0 is the initial life parameter, is the degradation rate coefficient, is the shape parameter.

[0013] In one implementation of the present application, in step S2, the multi-source data fusion preprocessing includes spatial coordinate unification and data quality assessment, and the steps are as follows: Convert planning and design data and construction data into a unified geographic coordinate system; Establish a data quality assessment indicator system, including completeness, consistency, and timeliness indicators; eliminate invalid data through quality scoring and generate a standardized data set; the data quality scoring formula is:

[0014] In the formula, Q is the data quality score, I is the completeness index, C is the consistency index, and T is the timeliness index. 、 、 is the weight coefficient.

[0015] In one implementation of the present application, in step S4, the process of generating a maintenance decision suggestion is specifically as follows: Taking maintenance cost, safety benefit and social impact as optimization goals, a multi-objective function is constructed; Generate Pareto optimal solution set using non-dominated sorting genetic algorithm; The optimal solution set is adaptively modified through the expert knowledge base to generate an executable maintenance plan; the multi-objective function expression is: F(x)={f1(x),f2(x),f3(x)} Where F(x) is the target vector, f1(x) is the maintenance cost function, f2(x) is the safety benefit function, f3(x) is the social impact function, and x is the maintenance plan parameter vector.

[0016] In one implementation of the present application, the method further includes: When an anomaly is detected, the abnormal feature vector is extracted; Infer the possible area of the anomaly source through the spatiotemporal correlation algorithm; The historical fault pattern library is used to match abnormal features and generate a traceability probability matrix. The most likely location of the abnormal source is determined based on the traceability probability matrix. The calculation formula for the abnormal source traceability probability is:

[0017] Where P(s|a) is the probability that anomaly a originates from s, P(a|s) is the conditional probability that s generates a, P(s) is the prior probability of s occurring, and n is the number of anomaly sources.

[0018] In one implementation of the present application, the method further includes: Based on pipeline risk level and importance index, a monitoring point coverage model is constructed; Use simulated annealing algorithm to optimize monitoring point locations and maximize risk coverage; The coverage model is updated based on real-time monitoring data, and the monitoring point layout is dynamically adjusted. The monitoring point coverage model is:

[0019] Where C is the total coverage, w i is the weight of the i-th pipeline segment, cou i is the coverage of the i-th pipeline segment, and n is the number of pipeline segments.

[0020] On the other hand, the present application also provides a big data-based urban underground pipeline lifecycle safety monitoring system, which is applied to the aforementioned big data-based urban underground pipeline lifecycle safety monitoring method. The system includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can complete the aforementioned big data-based urban underground pipeline lifecycle safety monitoring method.

[0021] The method and system for monitoring the lifecycle safety of urban underground pipelines based on big data provided by this application have the following beneficial effects: (1) The digital twin model was constructed by fusion of multi-source data, which improved data consistency and realized dynamic visualization management of the entire life cycle of underground pipelines.

[0022] (2) By combining spatiotemporal correlation analysis with deep learning algorithms, pipeline abnormalities can be accurately identified, improving the real-time and accuracy of risk assessment.

[0023] (3) Generate maintenance decisions through life prediction algorithms and multi-objective optimization to avoid excessive or insufficient maintenance, reduce safety accident rates and operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flow chart of a method for monitoring the lifecycle safety of urban underground pipelines based on big data provided in an embodiment of the present application; Figure 2 Schematic diagram of the urban underground pipeline lifecycle safety monitoring system based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] The embodiment of the present application provides a method and system for monitoring the life cycle safety of urban underground pipelines based on big data. The technical solution proposed in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0027] Figure 1 This is a flow chart of the urban underground pipeline life cycle safety monitoring method based on big data provided in the embodiment of this application. Figure 1 As shown, the method mainly includes the following steps: Step S1: Obtain multi-source data on the entire life cycle of urban underground pipelines.

[0028] In an embodiment of the present application, the multi-source data includes planning and design data, construction data, operation monitoring data, and maintenance and repair data.

[0029] Step S2: Perform fusion preprocessing on the multi-source data to construct a pipeline digital twin model; use the spatiotemporal correlation analysis algorithm to monitor the pipeline operation status in real time and extract abnormal features.

[0030] In the embodiment of the present application, the spatiotemporal correlation analysis algorithm specifically performs the following process: The operation monitoring data is decomposed into time series to extract trend items, period items, and abnormal fluctuation items. A correlation matrix is constructed based on the spatial topology of the pipeline to calculate the spatiotemporal impact factors of each monitoring point. The spatial propagation range of abnormal characteristics is predicted using the spatiotemporal impact factors. The spatiotemporal impact factor calculation formula is:

[0031] Among them, SIF ij W represents the spatiotemporal impact factor of monitoring point i on monitoring point j, which is used to quantify the degree of influence of monitoring point i on monitoring point j in the spatiotemporal dimension; ij is the spatial distance weight, which reflects the association weight between monitoring point i and monitoring point j due to the spatial distance factor. Different distances usually have different weights, which is used to describe the role of spatial relationships on the impact; T ij is the time delay coefficient, which reflects the time delay characteristics of the process in which monitoring point i affects j. The time delay between different monitoring points can be reflected by this coefficient; W ik is the spatial distance weight between monitoring point i and adjacent monitoring point k, T ik is the time delay coefficient of monitoring point i to the adjacent monitoring point k, k is the index of the adjacent monitoring point, k = 1, 2, ..., n is the number of adjacent monitoring points, that is, the total number of monitoring points adjacent to monitoring point i, which is used to determine the range of the summation operation.

[0032] In the embodiment of the present application, multi-source data fusion preprocessing includes spatial coordinate unification and data quality assessment, and the steps are as follows: Convert planning and design data and construction data into a unified geographic coordinate system; Establish a data quality assessment indicator system, including completeness, consistency, and timeliness indicators; eliminate invalid data through quality scoring and generate a standardized data set; the data quality scoring formula is:

[0033] In the formula, Q is the data quality score, I is the completeness index, C is the consistency index, and T is the timeliness index. 、 、 is the weight coefficient.

[0034] Step S3: Perform a hierarchical assessment of the pipeline safety status based on the pre-built deep learning risk assessment model to generate a risk level.

[0035] In the embodiment of the present application, the deep learning risk assessment model specifically performs the following process: inputting the preprocessed multi-source data into the convolution layer for spatial feature extraction; processing the time series features through the long short-term memory network layer; using the attention mechanism to weight the key features and output the risk level probability distribution. The risk level assessment formula is:

[0036] Where R is the risk level vector, X is the input data matrix, Conv is the convolution operation, is the hyperbolic tangent function, LSTM is the long short-term memory operation, W1, W2, W3 are weight matrices, b2, b3 are bias vectors, is the activation function.

[0037] Step S4: Combine historical fault data with real-time monitoring data to predict the remaining service life of the pipeline through a life prediction algorithm; generate maintenance decision recommendations based on the risk level and remaining service life to achieve full life cycle safety monitoring of underground pipelines.

[0038] In the embodiment of the present application, the pipeline performance degradation trajectory is fitted based on the Weibull degradation model to calculate the degradation rate; the Bayesian update method is used to integrate the real-time monitoring data to update the remaining life probability distribution; and the life prediction interval is generated based on the updated distribution. The Weibull degradation model expression is:

[0039] Where, L(t) is the remaining life at time t, L0 is the initial life parameter, is the degradation rate coefficient, is the shape parameter.

[0040] In the embodiment of the present application, the process of generating maintenance decision recommendations is specifically as follows: constructing a multi-objective function with maintenance cost, safety benefit, and social impact as optimization objectives; generating a Pareto optimal solution set using a non-dominated sorting genetic algorithm; and adaptively modifying the optimal solution set using an expert knowledge base to generate an executable maintenance plan. The multi-objective function expression is: F(x)={f1(x),f2(x),f3(x)} Where F(x) is the target vector, f1(x) is the maintenance cost function, f2(x) is the safety benefit function, f3(x) is the social impact function, and x is the maintenance plan parameter vector.

[0041] In the embodiment of the present application, when an anomaly is detected, an abnormal feature vector is extracted; the possible area of the abnormal source is inferred through a spatiotemporal correlation algorithm; the abnormal features are matched using a historical fault pattern library to generate a traceability probability matrix; the most likely location of the abnormal source is determined based on the traceability probability matrix; wherein, the abnormal source traceability probability calculation formula is:

[0042] Where P(s|a) is the probability that anomaly a originates from s, P(a|s) is the conditional probability that s generates a, P(s) is the prior probability of s occurring, and n is the number of anomaly sources.

[0043] In the embodiment of the present application, a monitoring point coverage model is constructed based on the pipeline risk level and importance index; the simulated annealing algorithm is used to optimize the monitoring point locations to maximize the risk coverage; the coverage model is updated according to real-time monitoring data, and the monitoring point layout is dynamically adjusted; wherein, the monitoring point coverage model is:

[0044] Where C is the total coverage, w i is the weight of the i-th pipeline segment, cou i is the coverage of the i-th pipeline segment, and n is the number of pipeline segments.

[0045] The above is a method for monitoring the lifecycle safety of urban underground pipelines based on big data provided by an embodiment of the present application. Based on the same inventive concept, an embodiment of the present application also provides a system for monitoring the lifecycle safety of urban underground pipelines based on big data. Figure 2 A schematic diagram of the composition of the urban underground pipeline life cycle safety monitoring system based on big data provided in the embodiment of the present application is shown in FIG. Figure 2 As shown, the system mainly includes: at least one processor 201; and a memory 202 communicatively connected to the at least one processor 201; wherein the memory 202 stores instructions that can be executed by the at least one processor 201, and the instructions are executed by the at least one processor 201 so that the at least one processor 201 can complete the aforementioned big data-based urban underground pipeline life cycle safety monitoring method.

[0046] The following specifically shows examples of the solution provided by this application in specific application scenarios.

[0047] Ten pressure and vibration sensors (numbered P1-P10) were deployed on a 500-meter-long section of a ductile iron water supply main in a certain city (buried at a depth of 1.8 meters, with a diameter of DN400 and a service life of 15 years). The system monitors operating status in real time and predicts maintenance strategies. The specific process is as follows: 1. Multi-source data fusion preprocessing.

[0048]

[0049] Data quality score calculation: Completeness (I): The planning and design data lacks the thickness of the anti-corrosion layer (I=0.8). Consistency (C): The construction coordinate system has a deviation of 200 meters (C=0.7). Timeliness (T): Sensor data delay is ≤ 2 seconds (T=0.95). Q = 0.4 × 0.8 + 0.3 × 0.7 + 0.3 × 0.95 = 0.815 Result: Q>0.8, the data is valid; the coordinate system is converted to CGCS2000.

[0050] 2. Anomaly detection based on spatiotemporal correlation analysis.

[0051] Pressure mutation event: The pressure at monitoring point P5 suddenly dropped by 0.3 MPa (time t0). The pressure at monitoring point P4 dropped by 0.2 MPa at t0+8 seconds, and the pressure at monitoring point P6 dropped by 0.1 MPa at t0+12 seconds.

[0052] Calculation of spatiotemporal impact factors:

[0053] Conclusion: The contribution rate of P5 to the propagation of P4 is 31.8%. Combined with the topological inversion, the anomaly source is located 30 meters upstream of P5.

[0054] 3. Deep learning risk assessment.

[0055] Input features: Spatial features (convolutional layer output): The area of corrosion plaques in the pipe section accounts for 12%; Temporal features (LSTM output): The pressure fluctuation frequency increases by 40%; Attention weights: Corrosion feature weight 0.7, vibration feature weight 0.3.

[0056] Risk level output: 𝑅=Softmax([0.1,1.2,0.3])=[0.15,0.67,0.18] R =Softmax([0.1,1.2,0.3])=[0.15,0.67,0.18] Risk level: low = 0, medium = 1, high = 2.

[0057] Result: Risk level is "medium" (probability 67%), and requires priority investigation.

[0058] 4. Remaining life prediction and maintenance decision-making.

[0059] Weibull degradation model parameters: Initial life L0 = 40 years, λ = 0.008, β = 1.5 (typical values for ductile iron).

[0060] The current service time is t=15 years.

[0061] L (15)=40×exp(−0.008×151.5)=11.3 years.

[0062] Life span after Bayesian update: The real-time corrosion rate exceeded the expected value by 20% → Corrected λ=0.0096.

[0063] L Update (15) = 40 × exp(−0.0096 × 151.5) = 9.1 years.

[0064] Prediction interval: [7.2, 11.0] years (95% confidence level).

[0065] 5. Multi-objective maintenance decision optimization.

[0066] Optimization objective function:

[0067] Pareto optimal solution set (output by NSGA-II algorithm):

[0068] Expert revision: Although Option 2 is costly, it has low social impact and outstanding safety benefits → recommended for implementation.

[0069] 6. Dynamic monitoring point optimization.

[0070] Coverage model parameters:

[0071] C=0.9×1.0+0.7×0.6+1.0×0.8=2.12.

[0072] After simulated annealing optimization: P11 is added at the midpoint of segment X2 → cou2 increases to 0.9. Total coverage C = 2.35 (↑10.8%), with 100% coverage of the high-risk segment.

[0073] Effect summary: Abnormal location efficiency: The time from alarm to traceability and location is ≤3 minutes (traditional methods take 2 hours); Maintenance cost savings: Accurate life prediction avoids excessive maintenance and reduces annual costs.

[0074] The various embodiments in this application are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the partial description of the method embodiments.

[0075] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0076] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for monitoring the life cycle safety of urban underground pipelines based on big data, characterized in that: The method comprises the following steps: Step S1: Acquire multi-source data on the entire life cycle of urban underground pipelines; Step S2: performing fusion preprocessing on the multi-source data to construct a pipeline digital twin model; using a spatiotemporal correlation analysis algorithm to monitor the pipeline operation status in real time and extract abnormal features; Step S3: Perform a hierarchical assessment of the pipeline safety status based on a pre-built deep learning risk assessment model to generate a risk level; Step S4: Combine historical fault data with real-time monitoring data to predict the remaining service life of the pipeline through a life prediction algorithm; generate maintenance decision recommendations based on the risk level and remaining service life to achieve full life cycle safety monitoring of underground pipelines.

2. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: The multi-source data includes planning and design data, construction data, operation monitoring data and maintenance and repair data.

3. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: In step S2, the spatiotemporal correlation analysis algorithm specifically performs the following process: The operation monitoring data is decomposed into time series to extract trend items, period items, and abnormal fluctuation items. A correlation matrix is constructed based on the spatial topology of the pipeline to calculate the spatiotemporal impact factors of each monitoring point. The spatial propagation range of abnormal characteristics is predicted using the spatiotemporal impact factors. The spatiotemporal impact factor calculation formula is: Among them, SIF ij W represents the spatiotemporal impact factor of monitoring point i on monitoring point j, which is used to quantify the degree of influence of monitoring point i on monitoring point j in the spatiotemporal dimension; ij is the spatial distance weight, which reflects the association weight between monitoring point i and monitoring point j due to the spatial distance factor. Different distances usually have different weights, which is used to describe the role of spatial relationships on the impact; T ij is the time delay coefficient, which reflects the time delay characteristics of the process in which monitoring point i affects j. The time delay between different monitoring points can be reflected by this coefficient; W ik is the spatial distance weight between monitoring point i and adjacent monitoring point k, T ik is the time delay coefficient of monitoring point i to the adjacent monitoring point k, k is the index of the adjacent monitoring point, k = 1, 2, ..., n is the number of adjacent monitoring points, that is, the total number of monitoring points adjacent to monitoring point i, which is used to determine the range of the summation operation.

4. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: The deep learning risk assessment model specifically performs the following process: pre-processed multi-source data is input into the convolution layer for spatial feature extraction; time series features are processed through the long short-term memory network layer; key features are weighted using the attention mechanism, and the risk level probability distribution is output. The risk level assessment formula is: Where R is the risk level vector, X is the input data matrix, Conv is the convolution operation, is the hyperbolic tangent function, LSTM is the long short-term memory operation, W1, W2, W3 are weight matrices, b2, b3 are bias vectors, is the activation function.

5. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: The step S4 specifically performs the following process: fitting the pipeline performance degradation trajectory based on the Weibull degradation model and calculating the degradation rate; fusing the real-time monitoring data using the Bayesian update method to update the remaining life probability distribution; generating the life prediction interval based on the updated distribution. The Weibull degradation model expression is: Where, L(t) is the remaining life at time t, L0 is the initial life parameter, is the degradation rate coefficient, is the shape parameter.

6. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: In step S2, multi-source data fusion preprocessing includes spatial coordinate unification and data quality assessment, and the steps are as follows: Convert planning and design data and construction data into a unified geographic coordinate system; Establish a data quality assessment indicator system, including completeness, consistency, and timeliness indicators; eliminate invalid data through quality scoring and generate a standardized data set; the data quality scoring formula is: In the formula, Q is the data quality score, I is the completeness index, C is the consistency index, and T is the timeliness index. 、 、 is the weight coefficient.

7. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: In step S4, the process of generating maintenance decision suggestions is specifically as follows: Construct a multi-objective function with maintenance cost, safety benefit and social impact as optimization goals; Generate Pareto optimal solution set using non-dominated sorting genetic algorithm; The optimal solution set is adaptively modified through the expert knowledge base to generate an executable maintenance plan; the multi-objective function expression is: F(x)={f1(x),f2(x),f3(x)} Where F(x) is the target vector, f1(x) is the maintenance cost function, f2(x) is the safety benefit function, f3(x) is the social impact function, and x is the maintenance plan parameter vector.

8. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: The method further comprises: When an anomaly is detected, the abnormal feature vector is extracted; Infer the possible area of the anomaly source through the spatiotemporal correlation algorithm; The historical fault pattern library is used to match abnormal features and generate a traceability probability matrix. The most likely location of the abnormal source is determined based on the traceability probability matrix. The calculation formula for the abnormal source traceability probability is: Where P(s|a) is the probability that anomaly a originates from s, P(a|s) is the conditional probability that s generates a, P(s) is the prior probability of s occurring, and n is the number of anomaly sources.

9. The urban underground pipeline life cycle safety monitoring method based on big data according to claim 1 is characterized in that: The method further comprises: Based on pipeline risk level and importance index, a monitoring point coverage model is constructed; Use simulated annealing algorithm to optimize monitoring point locations and maximize risk coverage; The coverage model is updated based on real-time monitoring data, and the monitoring point layout is dynamically adjusted. The monitoring point coverage model is: Where C is the total coverage, w i is the weight of the i-th pipeline segment, cou i is the coverage of the i-th pipeline segment, and n is the number of pipeline segments.

10. A big data-based urban underground pipeline lifecycle safety monitoring system, applied to the big data-based urban underground pipeline lifecycle safety monitoring method according to any one of claims 1 to 9, characterized in that: The system includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete the urban underground pipeline life cycle safety monitoring method based on big data as described in any one of claims 1-9.

Images