Simulation method for ground collapse induced by underground pipeline damage under multiple working conditions

Abstract

The invention relates to the technical field of simulation of ground collapse induced by underground pipeline damage. The invention relates to a method for simulating surface collapse induced by underground pipeline damage under multiple working conditions. The method comprises the following steps: S1, collecting pipeline related data of an underground pipeline needing to be simulated, performing data segmentation on the pipeline related data, and predicting the pipeline related data according to the pipeline related data after data segmentation; according to the method, by collecting multi-source data and conducting segmented prediction, the mastering capacity of the pipeline operation state is improved, geological exploration, pipeline parameters and field monitoring data are collected, future pipeline working condition data are predicted through a machine learning model after fluctuation analysis and data segmented processing are conducted, prediction data are screened through an effective time threshold value, and the prediction efficiency is improved. Data accuracy and effectiveness are guaranteed, a solid foundation is laid for subsequent analysis, pipeline pressure and temperature changes are accurately predicted, potential problems are perceived in advance, and sudden accidents are avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation of ground subsidence induced by underground pipeline damage, in particular to a simulation method of ground subsidence induced by underground pipeline damage under multiple working conditions. BACKGROUND

[0002] With the acceleration of urbanization, the development and utilization of underground space are increasing, and the safety and stability of underground pipeline systems, as an important part of urban infrastructure, are directly related to the operation efficiency of the city and the safety of residents' life and property. However, with the passage of time, many cities' underground pipeline systems are at risk of aging and damage, which not only increases the risk of urban waterlogging in the rainy season, but also can cause ground subsidence, causing serious economic losses and casualties.

[0003] At present, there are many deficiencies in the monitoring and early warning technology for ground subsidence induced by underground pipeline damage. The existing monitoring methods mostly rely on regular inspection and simple sensor monitoring, which is difficult to identify and locate the pipeline damage position in real time and accurately. The data processing and analysis means are relatively backward, which cannot effectively extract and utilize key features, resulting in insufficient warning accuracy and reliability. In addition, the existing researches are mostly concentrated on simulation under single working condition, lacking of systematic research on the mechanism of ground subsidence induced by underground pipeline damage under multiple working conditions, and the comprehensiveness of analysis is poor. Therefore, a simulation method of ground subsidence induced by underground pipeline damage under multiple working conditions is proposed. SUMMARY

[0004] The purpose of the present application is to provide a simulation method of ground subsidence induced by underground pipeline damage under multiple working conditions to solve the problems raised in the background.

[0005] To achieve the above purpose, a simulation method of ground subsidence induced by underground pipeline damage under multiple working conditions is provided, comprising the following steps:

[0006] S1, collecting pipeline related data of underground pipeline to be simulated, and segmenting the pipeline related data, and predicting the pipeline related data according to the segmented pipeline related data;

[0007] S2, collecting historical underground pipeline related events, and analyzing the damage form and damage characteristics according to the historical underground pipeline related events;

[0008] S3, establishing a damage identification and positioning model according to the damage form list and the corresponding damage characteristics, then inputting the predicted pipeline related data into the damage identification and positioning model to simulate the pipeline damage situation, and positioning the damage point of the underground pipeline;

[0009] S4, the soil parameters are extracted for the pipeline related data and the historical underground pipeline related events, and the soil parameters are combined with the damage points and the damage forms to calculate the collapse difference risk threshold value;

[0010] S5, the influence analysis on the ground collapse is performed according to the difference risk threshold value obtained in S4 in combination with the predicted pipeline related data, and the risk optimization suggestion for the underground pipeline under different working conditions is proposed according to the analysis result.

[0011] As a further improvement of the technical solution, S1 establishes a data transmission connection channel with the underground pipeline management end, then obtains the serial number of the underground pipeline to be simulated this time, and then extracts all pipeline related data of the underground pipeline from the underground pipeline management end according to the serial number of the underground pipeline through the data transmission connection channel;

[0012] The pipeline related data includes geological exploration data, pipeline parameter data and field monitoring data.

[0013] As a further improvement of the technical solution, the steps of S1 are as follows:

[0014] S1.1, the collected pipeline related data is combined with the collection time to perform fluctuation analysis, and the fluctuation frequency of the pipeline related data is obtained;

[0015] S1.2, the segmented time threshold value is set according to the fluctuation frequency obtained in S1.1, and then the pipeline related data is segmented according to the segmented time threshold value, so that the whole pipeline related data is divided into multiple segments of pipeline related data;

[0016] S1.3, the multiple segments of pipeline related data are combined to predict the working condition range of future pipeline related data, and the predicted pipeline related data is obtained according to the prediction result;

[0017] S1.4, the historical predicted pipeline related data is obtained, then the historical predicted pipeline related data is combined with the collected pipeline related data to perform effective time threshold value analysis, so as to obtain the effective time threshold value, and then the predicted pipeline related data obtained in S1.3 is intercepted according to the effective time threshold value, and only the predicted pipeline related data within the effective time threshold value is reserved.

[0018] As a further improvement of the technical solution, the steps of S2 are as follows:

[0019] S2.1, collect historical underground pipeline related events, and extract related events containing ground collapse in the historical underground pipeline related events;

[0020] S2.2, performing damage form and damage feature analysis on the extracted historical underground pipeline related events of S2.1, thereby obtaining the damage form and damage cause of each extracted historical underground pipeline related event, and taking the features of the damage cause as the damage features;

[0021] S2.3, collecting the damage form and damage features obtained in S2.2, thereby establishing a damage form list and damage features of each damage form.

[0022] As a further improvement of the technical solution, the steps of S3 are as follows:

[0023] S3.1, according to the analysis of the feature changes of different damage forms based on the damage form list and the corresponding damage features, identifying the key damage features, providing basic data for establishing a damage recognition model, and then using the extracted damage features to apply a support vector machine algorithm for pre-training, thereby establishing a damage recognition and positioning model, which can accurately recognize different types of pipeline damage and locate the damage point in combination with a multi-modal vibration signal processing algorithm;

[0024] S3.2, inputting the predicted pipeline related data into the damage recognition and positioning model to summarize the pipeline damage situation and locate the damage point, thereby obtaining the damage points contained in the underground pipeline and the corresponding damage form of each damage point.

[0025] As a further improvement of the technical solution, the damage simulation form of S3.2 includes longitudinal cracks, transverse cracks, pipeline connection water leakage and foreign object insertion.

[0026] As a further improvement of the technical solution, the steps of S4 are as follows:

[0027] S4.1, extracting pipeline soil parameters from pipeline related data;

[0028] S4.2, extracting event soil parameters from the damaged historical underground pipeline related events, thereby obtaining the event soil parameters of each damaged historical underground pipeline event before collapse;

[0029] S4.3, comparing the differences between each event soil parameter and the pipeline soil parameter of each damage point, obtaining the soil difference data of each damage point, and then extracting the damage form of each event soil parameter corresponding to the historical underground pipeline related event, combining each event soil parameter and the corresponding damage form with the soil difference data of each damage point to calculate the collapse difference risk threshold, thereby obtaining the collapse difference risk threshold of each damage point corresponding to different damage forms.

[0030] As a further improvement of the technical solution, the steps of S5 are as follows:

[0031] S5.1. Obtain the collapse differential risk threshold according to S4.2 and combine it with the predicted pipeline-related data to perform ground collapse risk analysis;

[0032] S5.2. When the corresponding damage point in the predicted pipeline-related data meets the collapse difference risk threshold, risk control suggestions are made to the underground pipeline management end based on the damage form corresponding to the collapse difference risk threshold. Conversely, when the corresponding damage point in the predicted pipeline-related data does not meet the collapse difference risk threshold, monitoring is continued.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. This method for simulating ground collapse induced by underground pipeline damage under multiple working conditions improves the ability to grasp the pipeline operation status by collecting multi-source data and performing segmented predictions. It collects geological exploration, pipeline parameters, and on-site monitoring data. After fluctuation analysis and data segmentation processing, it uses a machine learning model to predict future pipeline operating data. It also filters the predicted data through an effective time threshold to ensure data accuracy and effectiveness, laying a solid foundation for subsequent analysis, accurately predicting pipeline pressure and temperature changes, detecting potential problems in advance, and avoiding sudden accidents.

[0035] 2. In this method for simulating ground collapse induced by underground pipeline damage under multiple working conditions, in-depth analysis of historical events and construction of damage models enhance the ability to understand and respond to pipeline damage. Historical events are collected, ground collapse-related events are screened, and the damage forms and characteristics are analyzed. A damage form list and feature library are established. Combined with a multimodal vibration signal processing algorithm, a damage identification and positioning model is established to accurately identify the damage type and locate the damage point. When longitudinal or transverse cracks appear in the pipeline, the damage form can be quickly located and judged, providing accurate information for maintenance.

[0036] 3. This method of simulating ground collapse induced by underground pipeline damage under multiple working conditions provides a scientific basis for pipeline maintenance and risk control through analysis based on soil parameters and risk thresholds. Soil parameters are extracted to calculate the collapse difference risk threshold, and the ground collapse risk is evaluated in combination with the predicted data. Reasonable suggestions are made for different risk conditions. When the damage point in the predicted data meets the risk threshold, risk control suggestions such as emergency repair and enhanced monitoring are made according to the form of damage. If it is not met, monitoring is continued to achieve reasonable resource allocation and improve pipeline safety and management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is the overall flow chart of the present invention;

[0038] Figure 2 A flowchart of obtaining the fluctuation frequency of pipeline-related data according to the present invention;

[0039] Figure 3 Flow chart for collecting historical underground pipeline related events for the present application;

[0040] Figure 4 Flow chart for obtaining the damage points contained in the underground pipeline and the corresponding damage forms of each damage point for the present application;

[0041] Figure 5 Flow chart for extracting pipeline soil parameters from pipeline related data for the present application;

[0042] Figure 6 Flow chart for providing risk management and control recommendations to the underground pipeline management end according to the corresponding damage form of the collapse difference risk threshold for the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0044] Please refer to Figure 1 - Figure 6 The present embodiment aims to provide a method for simulating ground collapse induced by underground pipeline damage under multiple working conditions, which comprises the following steps:

[0045] S1, collect pipeline related data of the underground pipeline to be simulated, and segment the pipeline related data, and predict the pipeline related data according to the segmented pipeline related data;

[0046] S1 establishes a data transmission connection channel with the underground pipeline management end, then obtains the serial number of the underground pipeline to be simulated, and then extracts all pipeline related data of the underground pipeline from the underground pipeline management end according to the serial number of the underground pipeline through the data transmission connection channel;

[0047] The pipeline related data includes geological exploration data, pipeline parameter data, and field monitoring data, and the steps are as follows:

[0048] Establishing a data transmission connection channel: first, a stable communication channel needs to be established between the underground pipeline management end and the simulation system, which can be achieved through API interface, database connection or other transmission protocols (such as MQTT, HTTP, etc.). Through this channel, underground pipeline related data can be transmitted;

[0049] Obtaining the serial number of the underground pipeline: through the communication channel with the management end, the simulation system requests the serial number of the specified pipeline from the underground pipeline management end, each underground pipeline has a unique serial number, which ensures that the system can accurately locate the pipeline to be simulated, and the management end returns the unique serial number of the pipeline according to the request;

[0050] Extracting pipeline related data through pipeline serial number: using the obtained underground pipeline serial number, send a request to the underground pipeline management end through the data transmission channel to obtain all related data of the pipeline;

[0051] Data analysis and storage: the data received by the simulation system needs to be parsed, according to the data format (such as JSON), the data is converted into a structure suitable for simulation, the geological exploration data, pipeline parameter data and monitoring data will be parsed and stored into corresponding variables or data structures.

[0052] The steps of S1 are as follows:

[0053] S1.1, combine the collected pipeline related data with the collection time to perform fluctuation analysis, and obtain the fluctuation frequency of the pipeline related data;

[0054] S1.2, set a segmented time threshold according to the fluctuation frequency obtained in S1.1, and then segment the pipeline related data according to the segmented time threshold, so that the overall pipeline related data is divided into multiple segments of pipeline related data, the steps are as follows:

[0055] Setting a segmented time threshold according to the fluctuation frequency: through the analysis of the frequency spectrum, the main fluctuation frequency of the pipeline data is identified, which is closely related to the periodic changes in the pipeline operation (such as pressure fluctuation, temperature change, etc.), according to the obtained fluctuation frequency, the time period is selected as the segmented time threshold;

[0056] Data segmentation according to time threshold: by taking the time threshold analyzed by the fluctuation frequency as the standard, the time period of the pipeline data is divided, specifically, the data is divided according to each threshold time, ensuring that the data characteristics in each time period are consistent, which is convenient for subsequent analysis;

[0057] S1.3, combine the multiple segments of pipeline related data to predict the working condition range of future pipeline related data, and obtain predicted pipeline related data according to the prediction result;

[0058] S1.4, obtain historical predicted pipeline related data, and then perform effective time threshold analysis on the historical predicted pipeline related data combined with the collected pipeline related data, to obtain an effective time threshold, and then according to the effective time threshold, the predicted pipeline related data obtained in S1.3 is intercepted, only the predicted pipeline related data within the effective time threshold is retained, the steps are as follows:

[0059] Acquiring predicted pipeline-related data: Collect and integrate historical data of multiple pipeline sections, and fuse the data to provide a sufficient information base for subsequent prediction models. Then, based on the historical pipeline data, a machine learning prediction model is established to predict future pipeline operating condition data. The input of the model includes historical pipeline-related data, and the output is predicted pipeline-related data in the future;

[0060] Using the established prediction model, future pipeline operating condition data is predicted based on the input historical data. The output data includes pipeline pressure, temperature, strain, etc. in the future time period;

[0061] Effective time threshold analysis: Combine historical predicted pipeline data with real-time collected pipeline data for data comparison. Comparative analysis can reveal the differences between predicted data and actual collected data, and further help determine the key moment of pipeline operating condition change. The effective time threshold refers to the effective time period in which the predicted pipeline operating condition data is consistent with the actual collected data. In this time period, the predicted data has high accuracy and can be used for subsequent risk assessment and maintenance decision-making. The time threshold can be determined based on data trends, error ranges or other analysis methods, and the formula is as follows:

[0062] T threshold ={t||D pred (t)-D measured (t)≤α|};

[0063] Where T threshold is the effective time threshold, representing the effective time period of the data, t is the time point, D pred (t) is the value of the predicted pipeline-related data at time point t, D measured (t) is the value of the collected pipeline data at time point t, and a is the error threshold, representing the maximum difference between the predicted and actual data that can be accepted.

[0064] Cutting effective data range: According to the calculated effective time threshold, the predicted pipeline data is cut off, and only the predicted data within the effective time period is retained. The formula is as follows:

[0065] D valid ={D pred (t)t∈T threshold};

[0066] Where D valid is the effective pipeline prediction data set, representing the data within the effective time threshold.

[0067] S2, collect historical underground pipeline-related events, and analyze the damage form and damage characteristics based on the historical underground pipeline-related events;

[0068] The steps of S2 are as follows:

[0069] S2.1, collect historical underground pipeline related events, extract ground subsidence related events from the historical underground pipeline related events;

[0070] Collect all related events about underground pipelines from historical records, which are usually sourced from pipeline management departments, accident reports, monitoring systems, local governments, and emergency departments, etc. The event data includes the time, location, pipeline type, damage level, repair situation, etc. of the accident;

[0071] By analyzing historical data, all underground pipeline events related to ground subsidence are screened out. Ground subsidence events usually manifest as ground subsidence or collapse caused by pipeline rupture or damage. These events can be extracted by matching keywords in the event description (such as "ground subsidence", "subsidence", "excessive underground water", etc.), marking events containing ground subsidence, and storing them as a separate dataset. Each event will contain the following information: event ID, occurrence time, location, pipeline characteristics, damage, loss assessment, etc.

[0072] S2.2, analyze the damage form and damage characteristics of the historical underground pipeline related events extracted in S2.1, to obtain the damage form and cause of each extracted historical underground pipeline related event, and take the characteristics of the cause of the damage as the damage characteristics, as follows:

[0073] Classify the damage form: for each extracted event, classify according to the actual damage, the damage form of ground subsidence may include pipeline rupture, local deformation, corrosion aggravation, leakage, etc. By analyzing the monitoring data, reports and images of the accident site, the damage form can be determined, as follows:

[0074] F damage ={F PL ,F BX ,F FS ,F CK ,F QF ,F TJ ,F TL ,F AJ ,F CR ,F SL};

[0075] Where, F damage is the set of damage forms, F PL is pipeline rupture, F BX is pipeline deformation, F FS is pipeline corrosion damage, F CK is pipeline misalignment, F QF is pipeline heave, F TJ is pipeline disconnection, FTL F. for pipe interface material shedding, AJ F. for branch pipe hidden connection, CR F. for foreign matter penetration, SL F. for pipe leakage;

[0076] Extracting damage forms: According to the monitoring data of the event, the actual situation of ground subsidence, classify the damage form of each event, mark the damage mode of the pipeline, and form a damage form data set;

[0077] Analyzing damage causes and extracting damage characteristics: Analyze the causes of ground subsidence, which usually involves factors such as soil conditions around the pipeline, underground water level, pipeline material, pipeline burial depth, external load, etc. Based on the accident data, the relationship between these factors and the damage can be inferred, such as the soil type, underground water condition, rock structure, etc. around the underground pipeline, which will affect the stability of the pipeline, and the material, burial depth, diameter, etc. of the pipeline directly affect its compression resistance;

[0078] Extracting damage characteristics: By analyzing the damage causes, extract the key characteristics of each event, including soil moisture, pipeline material, burial depth, environmental temperature, load, etc. These characteristics will help predict the damage risk of the pipeline under similar conditions;

[0079] Summarizing and storing damage characteristics: By analyzing all relevant events, obtain the damage form and the cause of the damage and its characteristics of each event. The damage characteristics of each event will include damage form, soil condition, pipeline material, external pressure, etc.

[0080] S2.3, collect the damage form and damage characteristics obtained in S2.2, thereby establishing a damage form list and damage characteristics of each damage form.

[0081] Establishing a damage form list: classify all the collected damage forms to form a damage form list, each damage form is listed as an independent item, common damage forms include cracks, deformation, corrosion, leakage, etc.

[0082] Mapping damage forms and characteristics: For each damage form, identify and list all related damage characteristics, match by analyzing the characteristic factors appearing in historical events, each damage form will be associated with its specific damage characteristics, including soil type, pipeline material, burial depth, environmental temperature, underground water level, etc.

[0083] S3, according to the damage form list and the corresponding damage characteristics, establish a damage identification and positioning model, then input the predicted pipeline related data into the damage identification and positioning model to simulate the pipeline damage situation, and at the same time locate the damage point of the underground pipeline;

[0084] The steps of S3 are as follows:

[0085] S3.1, Analyze the characteristic changes under different damage forms according to the damage form list and corresponding damage characteristics, identify the key damage characteristics, provide basic data for establishing the damage identification model, then use the extracted damage characteristics to apply the support vector machine algorithm for pre-training, thereby establishing the damage identification and positioning model, and the damage identification and positioning model combined with the multi-modal vibration signal processing algorithm can accurately identify different types of pipeline damage and locate the damage point;

[0086] S3.2, input the predicted pipeline related data into the damage identification and positioning model to summarize the pipeline damage situation and locate the damage point, thereby obtaining the damage points contained in the underground pipeline and the corresponding damage form of each damage point, the steps are as follows:

[0087] Key damage feature extraction: for each damage form, use signal processing methods to extract its key features, including frequency domain analysis (such as FFT analysis), time domain analysis (such as peak and valley analysis), and time-frequency analysis (such as wavelet transform), the extracted key damage features will be used for subsequent model training as basic data for damage identification;

[0088] Data preparation and preprocessing: use the damage features obtained from historical data and experimental data as the training set. The training set should contain different types of damage forms and their corresponding feature data. Normalize the data to ensure that the scales of all features are relatively consistent and avoid the influence of dimensional differences between features on model training;

[0089] Support vector machine (SVM) training: use the extracted damage features to train the support vector machine (SVM) model. SVM is a supervised learning algorithm based on maximum interval classification, which can effectively distinguish different damage types. In the training process, SVM optimizes a hyperplane to maximize the interval between different damage categories, thereby achieving classification. Kernel functions (such as RBF kernel, polynomial kernel, etc.) can be selected to adapt to the distribution of data;

[0090] Model evaluation: use cross-validation and other techniques to evaluate the accuracy, precision, and recall rate of the SVM model to ensure that the model can accurately classify pipeline damage types;

[0091] Multi-modal vibration signal acquisition and preprocessing: install sensors on the pipeline to collect vibration signals in real time. These signals can come from different positions of the pipeline, including different frequency bands (such as low, medium, and high frequencies) and different directions (such as longitudinal and transverse directions). Perform time-frequency analysis on the collected vibration signals to extract time domain, frequency domain, and time-frequency domain features, and further analyze the trend of vibration signals;

[0092] Applying the pre-trained SVM model for damage recognition: input the processed seismic signal features into the trained SVM model to recognize the type of damage. The SVM model determines whether the pipeline has been damaged during this time period and classifies the specific type of damage.

[0093] Damage point localization: based on the analysis of multi-modal seismic signals, the location of the damage point is determined by combining the spatial distribution of the signals, including time difference positioning method, vibration propagation model, etc. Multiple sensors are installed at different positions of the pipeline. The precise location of the damage point is calculated by the difference in data from different sensors (such as signal propagation time difference).

[0094] Input predicted pipeline-related data: input the predicted pipeline-related data into the damage recognition and localization model. Through the damage recognition and localization model, simulate different types of pipeline damage. The model can predict whether the pipeline is likely to be damaged, the type and location of the damage, and the severity of the damage. The output of the damage recognition and localization model is used to determine the specific location of the pipeline damage and assess the severity of the damage, providing a basis for pipeline maintenance and safety assessment.

[0095] S3.2 Damage simulation forms include longitudinal cracks, transverse cracks, pipe connection leaks, and foreign object insertion.

[0096] S4, Extract soil parameters for both pipeline-related data and historical underground pipeline-related events. Combine the soil parameters with the damage points and damage forms to calculate the collapse difference risk threshold.

[0097] The steps of S4 are as follows:

[0098] S4.1 Extract pipeline soil parameters from pipeline-related data.

[0099] Extract soil-related parameters from pipeline-related data (such as geological exploration data), including soil moisture, soil type, soil density, etc. The specific extraction method depends on the storage format of the data.

[0100] S4.2 Extract event soil parameters from historical underground pipeline-related events that have been damaged. Obtain the event soil parameters of each historical underground pipeline event before it collapsed.

[0101] In the records of damaged historical underground pipeline-related events, extract the soil parameters of each damaged historical underground pipeline event before it collapsed. The extraction method depends on the recording format of the historical event data.

[0102] S4.3, combine each event soil parameter with the pipeline soil parameter of each damage point for difference comparison, obtain soil difference data of each damage point (compare each event soil parameter with the pipeline soil parameter of each damage point, calculate the difference between the two, obtain the soil difference data of each damage point), then extract the damage form occurred in the corresponding historical underground pipeline related event of each event soil parameter, combine each event soil parameter and the corresponding damage form with the soil difference data of each damage point for collapse difference risk threshold calculation, obtain the collapse difference risk threshold of each damage point corresponding to different damage forms, taking pipeline rupture as an example, the formula is as follows:

[0103]

[0104] wherein, is the collapse difference risk threshold corresponding to the damage form of pipeline rupture, which is a quantitative index for measuring the risk of ground collapse caused by pipeline rupture under the current soil difference and other related factors, e is a natural constant (about equal to 2.71828), β0 is a constant term, β1, β2, β3 are soil humidity difference data, soil type difference data, pipeline burial depth difference data respectively, corresponding regression coefficients, D humidity is the soil humidity difference data, D type is the soil type difference data, D depth is the pipeline burial depth difference data.

[0105] S5, according to the difference risk threshold calculated and obtained in S4, combine the predicted pipeline related data to analyze the influence on ground collapse, and at the same time, according to the analysis results, make risk optimization suggestions for underground pipeline under different working conditions.

[0106] S5 step is as follows:

[0107] S5.1, according to S4.2, obtain the collapse difference risk threshold and combine the predicted pipeline related data to analyze the risk of ground collapse;

[0108] S5.2, when the corresponding damage point in the predicted pipeline related data meets the collapse difference risk threshold, make risk control suggestions to the underground pipeline management end according to the damage form corresponding to the collapse difference risk threshold, otherwise, when the corresponding damage point in the predicted pipeline related data does not meet the collapse difference risk threshold, keep monitoring.

[0109] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Various changes and improvements can be made to the present application without departing from the spirit and scope of the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for simulating ground collapse induced by underground pipeline damage under multiple working conditions, characterized by: The following steps are involved: S1. Collect pipeline-related data for underground pipeline simulation, segment the pipeline-related data, and predict the pipeline-related data based on the segmented pipeline-related data; S2. Collect historical underground pipeline-related events and analyze the damage forms and characteristics based on these events; S3. Establish a damage identification and positioning model based on the damage form list and corresponding damage characteristics. Then, input the predicted pipeline-related data into the damage identification and positioning model to simulate the pipeline damage situation and locate the damage point of the underground pipeline. S4. Extract soil parameters from pipeline-related data and historical underground pipeline-related events, and calculate the collapse risk threshold based on the soil parameters and the damage point and damage form; S5. Based on the differential risk threshold obtained by calculation in S4 and combined with the predicted pipeline-related data, the impact of ground collapse is analyzed. At the same time, based on the analysis results, risk optimization suggestions for underground pipelines under different working conditions are proposed.

2. The method for simulating ground collapse caused by underground pipeline damage under multiple working conditions according to claim 1, characterized in that: The S1 establishes a data transmission connection channel with the underground pipeline management terminal, and then obtains the serial number of the underground pipeline to be simulated this time, and then extracts all pipeline-related data of the underground pipeline according to the underground pipeline serial number at the underground pipeline management terminal through the data transmission connection channel; Pipeline-related data include geological exploration data, pipeline parameter data, and field monitoring data.

3. The method for simulating ground collapse caused by underground pipeline damage under multiple working conditions according to claim 1, characterized in that: The steps of S1 are as follows: S1.

1. Perform fluctuation analysis on the collected pipeline-related data in combination with the collection time to obtain the fluctuation frequency of the pipeline-related data; S1.

2. Set a segmentation time threshold based on the fluctuation frequency obtained in S1.1, and then segment the pipeline-related data based on the segmentation time threshold, so that the overall pipeline-related data is divided into multiple segments of pipeline-related data; S1.

3. Combine the relevant data of multiple pipeline sections with the relevant data of future pipelines to predict the operating range, and obtain the predicted pipeline relevant data based on the prediction results; S1.

4. Obtain historical predicted pipeline-related data, and then perform effective time threshold analysis on the historical predicted pipeline-related data in combination with the collected pipeline-related data to obtain an effective time threshold. Then, the predicted pipeline-related data obtained in S1.3 is intercepted according to the effective time threshold, and only the predicted pipeline-related data within the effective time threshold is retained.

4. The method for simulating ground collapse caused by underground pipeline damage under multiple working conditions according to claim 1, characterized in that: The steps of S2 are as follows: S2.

1. Collect historical underground pipeline-related events and extract ground collapse-related events from these events. S2.

2. Analyze the damage forms and damage characteristics of the historical underground pipeline-related events extracted in S2.1, thereby obtaining the damage forms and causes of each extracted historical underground pipeline-related event, and using the characteristics of the causes of damage as damage characteristics; S2.

3. Collect the damage forms and damage characteristics obtained in S2.2, and thus establish a damage form list and the damage characteristics of each damage form.

5. The method for simulating ground collapse caused by underground pipeline damage under multiple working conditions according to claim 1 is characterized in that: The steps of S3 are as follows: S3.

1. Analyze the characteristic changes under different damage forms based on the damage form list and corresponding damage features, identify key damage features, and provide basic data for establishing a damage recognition model. Then, use the extracted damage features to pre-train the support vector machine algorithm to establish a damage recognition and location model. The damage recognition and location model, combined with a multimodal vibration signal processing algorithm, can accurately identify different types of pipeline damage and locate the damage point. S3.

2. The predicted pipeline-related data is input into the damage identification and positioning model to simulate the pipeline damage situation and locate the damage points, thereby obtaining the damage points contained in the underground pipeline and the damage form corresponding to each damage point.

6. The method for simulating ground collapse caused by underground pipeline damage under multiple working conditions according to claim 1, characterized in that: The S3.2 damage simulation forms include longitudinal cracks, transverse cracks, water leakage at pipe joints and insertion of foreign objects.

7. The method for simulating ground collapse caused by underground pipeline damage under multiple working conditions according to claim 1, characterized in that: The steps of S4 are as follows: S4.

1. Extract pipeline soil parameters from pipeline related data; S4.

2. Extract event soil parameters for historical underground pipeline damage-related events, obtaining event soil parameters for each historical underground pipeline damage event before collapse; S4.

3. Compare the soil parameters of each event with the pipeline soil parameters of each damage point to obtain soil difference data for each damage point. Then extract the damage form that occurred in historical underground pipeline-related events corresponding to each event soil parameter. Combine each event soil parameter and the corresponding damage form with the soil difference data of each damage point to calculate the collapse difference risk threshold, and obtain the collapse difference risk threshold corresponding to different damage forms at each damage point.

8. The method for simulating ground collapse caused by underground pipeline damage under multiple working conditions according to claim 1, characterized in that: The S5 step is as follows: S5.

1. Obtain the collapse differential risk threshold according to S4.2 and combine it with the predicted pipeline-related data to perform ground collapse risk analysis; S5.

2. When the corresponding damage point in the predicted pipeline-related data meets the collapse difference risk threshold, risk control suggestions are made to the underground pipeline management end based on the damage form corresponding to the collapse difference risk threshold. Conversely, when the corresponding damage point in the predicted pipeline-related data does not meet the collapse difference risk threshold, monitoring is continued.

Images