A natural gas pipeline detection system based on optical fiber monitoring

Abstract

The present invention discloses a natural gas pipeline detection system based on optical fiber monitoring, which relates to the technical field of industrial pipeline monitoring. The monitoring trend prediction module of the system uses a global risk assessment algorithm combined with an abnormal scoring function A i The system calculates the cumulative risk factor Racc based on the comprehensive health status Htotal, and predicts the pipeline health prediction value Plongterm for a period of time in the future through time series analysis. By comparing it with the predicted health threshold Y, the system can automatically issue a risk warning. When the pipeline health prediction value Plongterm is greater than the health threshold Y, the system will issue an alarm and make maintenance recommendations for specific pipeline sections. This data-driven prediction and warning mechanism effectively reduces the occurrence of sudden pipeline accidents and improves the safety and reliability of natural gas pipeline management. By predicting potential problems in advance, the system can also optimize maintenance plans and reduce the number of emergency maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial pipeline monitoring, and in particular to a natural gas pipeline detection system based on optical fiber monitoring. Background Art

[0002] Industrial pipeline monitoring mainly involves the operation status monitoring and safety management of pipelines in industries such as petroleum, natural gas, and chemicals. In these industries, natural gas pipelines require special detection and safety assurance technologies due to their long-distance, high-pressure transmission characteristics. With the rapid development of fiber optic sensing technology, this technology has been gradually introduced into the field of pipeline monitoring.

[0003] In the existing technology, although the deep learning solution is innovative in feature extraction and signal classification, and improves the accuracy of detection, it relies on a large amount of training data, has high computational complexity, and may be insufficient in shielding interference signals and generalization in different environments. In order to solve these problems, in the future, we can consider optimizing the model architecture to improve computing efficiency, adding more types of data for training, and improving the ability to identify interference signals in different environments, thereby further enhancing the practicality and robustness of the system;

[0004] Furthermore, the shortcomings of existing natural gas pipeline detection methods are mainly due to the fact that pipelines in long-term operation may suffer minor damage due to environmental pressure, corrosion or mechanical stress accumulation, and these problems are often difficult to detect in the early stages, further increasing the risk of pipeline accidents. Based on this background, a pipeline detection system based on optical fiber monitoring is developed to effectively solve the above problems. Through real-time multi-parameter monitoring and data analysis, the safety and reliability of natural gas pipeline operation are greatly improved. Summary of the invention

[0005] Technical issues solved

[0006] In view of the deficiencies of the prior art, the present invention provides a natural gas pipeline detection system based on optical fiber monitoring, which solves the problems mentioned in the background technology.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: including an optical fiber monitoring module, a data processing module, an abnormality monitoring module, a spatiotemporal distribution analysis module and a monitoring trend prediction module;

[0009] The optical fiber monitoring module is used to deploy optical fiber sensors along the natural gas pipeline, collect optical signals in real time, and transmit the collected optical signals to the demodulation device, where the optical signals are demodulated into electrical signals, and then the electrical signals are converted into digital signals to obtain pipeline operation data, and then transmitted to the data processing module through relevant network protocols;

[0010] The data processing module is used to receive pipeline operation data in real time, and pre-process the pipeline operation data. After the pre-processing, the data is normalized to obtain a standard data set, and a time series database is constructed to store the obtained standard data set.

[0011] The anomaly monitoring module is used to construct a multi-parameter fusion algorithm formula, extract a standard data set from the time series database, input it into the multi-parameter fusion algorithm formula to calculate and output an anomaly scoring function A i , and preset the abnormal threshold Ath and the output abnormal scoring function A i Conduct preliminary comparative assessment and analysis of abnormal conditions in natural gas pipelines;

[0012] The spatiotemporal distribution analysis module is used to further conduct a comprehensive analysis based on the preliminary comparative evaluation and analysis, by constructing a time dimension anomaly algorithm formula and extracting anomaly scoring function A. i Input into the time dimension abnormal algorithm formula to calculate and output the health status score H at time t i (t), and then further calculate the comprehensive health status Htotal in the output natural gas pipeline space based on the health status score Hi(t) at time t;

[0013] The monitoring trend prediction module establishes a pipeline global risk assessment algorithm formula based on the abnormal scoring function A i , input into the pipeline global risk assessment algorithm formula, calculate and output the cumulative risk factor Racc, and combine it with the comprehensive health status Htotal to calculate and output the pipeline health prediction value Plongterm, and then preset the predicted health threshold Y and the pipeline health prediction value Plongterm for secondary comparative evaluation and analysis to predict the health status of the pipeline.

[0014] Preferably, the optical fiber monitoring module includes an optical fiber signal acquisition unit, an optical fiber signal demodulation unit and an electrical signal conversion and transmission unit;

[0015] The optical fiber signal acquisition unit sets a number of monitoring points inside the natural gas pipeline, each monitoring point is 50 meters apart, and a number of optical fiber sensor groups are laid continuously to collect the optical signal group in the natural gas pipeline in real time, and then the optical fiber sensor groups are connected in series and sorted according to the distance, and each optical fiber sensor in the optical fiber sensor group is marked as i, where i represents the i-th section of the optical fiber sensor, i={1,2,3,..,n}, and then integrated with the demodulation device;

[0016] The optical fiber sensor group includes optical fiber Brillouin sensor, optical fiber Bragg grating and distributed acoustic wave sensor;

[0017] The optical signal group includes a Brillouin scattering signal, a fiber grating reflection wavelength and a phase signal;

[0018] The optical fiber signal demodulation unit demodulates the optical signal groups collected by different optical fiber sensor groups into electrical signal groups through a demodulation device; the specific adjustment contents are as follows:

[0019] The demodulation equipment measures the stress and temperature changes at different locations in the optical fiber by analyzing the Brillouin scattering signal;

[0020] The demodulation equipment analyzes the stress and temperature of the environment in which the optical fiber is located by measuring the wavelength change of the wavelength reflected from the optical fiber grating;

[0021] The demodulation device analyzes and obtains the vibration signal by analyzing the phase change of the phase signal;

[0022] Integrate the different positions, stress and temperature changes in the optical fiber, the environment in which the optical fiber is located, stress, temperature and vibration signals into an electrical signal group;

[0023] The electrical signal conversion and transmission unit is used to convert the electrical signal group obtained after demodulation by the demodulation device into a numerical signal using an analog-to-digital converter ADC to obtain pipeline operation data. The pipeline operation data includes sound velocity Cs, soil moisture Ws and local stress S. The pipeline operation data is then transmitted to the data processing module through the optical fiber Ethernet and the TCP / IP network protocol.

[0024] Preferably, the data processing module includes a preprocessing unit and a storage unit;

[0025] The preprocessing unit is used to receive the pipeline operation data in real time, and after receiving the pipeline operation data, perform denoising on the pipeline operation data using a bandpass filter and wavelet transform technology, and perform standardization after denoising to obtain a standard data set, wherein the standard data set includes a sound velocity change rate △Cs, a soil moisture change rate △Ws, and a local stress gradient △S;

[0026] The sound velocity change rate △Cs, soil moisture change rate △Ws and local stress gradient △S are calculated and obtained by the following standardized calculation formula;

[0027] ; ; ;

[0028] In the formula, Cs t Represents the sound velocity acquisition value at time t, Ws t represents the soil moisture collected at time t, S t represents the local stress at time t, Cs t+1 Represents the sound velocity acquisition value at time t+1, Ws t+1represents the soil moisture collected at time t+1, S t+1 represents the local stress at time t+1;

[0029] The storage unit is used to build a time series database, and set a write port and a write port, write the standard data set into the time series database through the write port, and mark the written standard data set with a timestamp when writing, and store it in the real-time data table in the time series database. At the same time, the last stored standard data set is automatically transferred to the historical data table and stored in chronological order.

[0030] Preferably, the abnormality monitoring module includes an abnormality calculation unit and an abnormality analysis unit;

[0031] The abnormal calculation unit is used to construct a multi-parameter fusion algorithm formula, extract the standard data set obtained in real time through the write port of the time series database, input it into the multi-parameter fusion algorithm formula, and calculate and output the abnormal scoring function A i , conduct preliminary analysis to see if there are any abnormal changes in the natural gas pipeline;

[0032] The anomaly scoring function A i Obtained through calculation using the following multi-parameter fusion algorithm formula;

[0033] ;

[0034] In the formula, A i It represents the abnormal scoring function corresponding to the optical fiber sensor of the i-th section of the natural gas pipeline. a1, a2 and a3 represent the preset weight values ​​of the sound velocity change rate △Cs, the soil moisture change rate △Ws and the local stress gradient △S, respectively, and a1+a2+a3=1. The specific values ​​are set by the user.

[0035] Preferably, the abnormal analysis unit presets an abnormal threshold value Ath according to the normal index of the natural gas pipeline by the user, and then compares it with the acquired abnormal scoring function Ath. i Conduct a preliminary comparative assessment to analyze the status of the natural gas pipeline in different fiber optic sensor sections. The specific assessment contents are as follows;

[0036] When the anomaly scoring function A i > abnormal threshold Ath, it means that the natural gas pipeline safety of the optical fiber sensor section of the current section is in an abnormal state, and an early warning is triggered to maintain the natural gas pipeline of the current section;

[0037] When the anomaly scoring function A i When ≤ the abnormal threshold Ath, it means that the natural gas pipeline safety of the optical fiber sensor section of the current section is in normal state, and the health prediction of the natural gas pipeline is carried out at this time.

[0038] Preferably, the spatiotemporal distribution analysis module includes a time dimension analysis unit and a space dimension analysis unit;

[0039] The time dimension analysis unit is used to trigger when the natural gas pipeline safety is in a normal state at the preliminary comparative assessment, and extract the abnormal scoring function A of the current monitoring point by constructing the time dimension abnormal algorithm formula. i , input into the time dimension abnormal algorithm formula, calculate and output the health status score H at time t i (t), captures the changes in the health status of the natural gas pipeline within a period of time;

[0040] The health status score H at the time t i (t) The output is calculated by the following time dimension anomaly algorithm formula;

[0041] ;

[0042] In the formula, H i (t) represents the health status score of the fiber optic sensor in the i-th section of the natural gas pipeline at time t, T represents the time span, t1 represents the lower limit of time, t2 represents the upper limit of time, dt represents the time differential variable, and A i (t) represents the abnormal scoring function corresponding to the optical fiber sensor of the i-th section of the natural gas pipeline at time t.

[0043] Preferably, the spatial dimension analysis unit is used to calculate the health status scores H of multiple monitoring points. i (t) Combined with the spatial coupling effect, the comprehensive health status Htotal is calculated and output to further analyze the global health status of the pipeline;

[0044] The comprehensive health status Htotal is calculated and output by the following algorithm formula;

[0045] ;

[0046] Where N represents the total number of fiber optic sensors deployed, T xy It means that in space, the health status of the detection point is affected by the coupling of its spatial position coordinates x and y.

[0047] Preferably, the monitoring trend prediction module includes a cumulative risk analysis unit, a time series analysis and prediction unit, and a health assessment unit;

[0048] The data accumulation risk analysis unit extracts the comprehensive health status Htotal combined with the abnormal scoring function A by establishing a pipeline global risk assessment algorithm formula i , input into the global risk assessment algorithm formula to calculate and output the cumulative risk factor Racc, and quantify the overall risk accumulation of the pipeline;

[0049] The cumulative risk factor Racc is calculated and output by the following global risk assessment algorithm formula;

[0050] ;

[0051] Where Li represents the length of the pipeline covered by the i-th section of the optical fiber sensor, which is 50 meters, Ltotal represents the total length of the pipeline, k represents the risk correction factor for the entire area, and N represents the total number of optical fiber sensors deployed.

[0052] Preferably, the time series analysis and prediction unit extracts historical data through the write port of the time series database to calculate and output the abnormal scoring function A at the previous moment i (t-1), combined with the cumulative risk factor Racc and the comprehensive health status Htotal, and then using time series analysis to comprehensively calculate the output pipeline health prediction value Plongterm, to predict the risk development trend of the pipeline in the future;

[0053] The pipeline health prediction value Plongterm is calculated and output by the following algorithm formula;

[0054] ;

[0055] Where f represents the prediction function, and the prediction function f is a time series analysis algorithm, such as a decision tree, random forest, or neural network.

[0056] Preferably, the health assessment unit presets a predicted health threshold value Y through the average of the historical pipeline health prediction values ​​Plongterm, and then performs a secondary comparative assessment with the acquired pipeline health prediction value Plongterm to predict the health status of the natural gas pipeline. The specific assessment contents are as follows;

[0057] When the pipeline health prediction value Plongterm>predicted health threshold Y, it means that the future health status of the pipeline is abnormal. At this time, the secondary execution abnormality monitoring module is executed to locate the abnormal pipeline section and send maintenance prompt information;

[0058] When the pipeline health prediction value Plongterm ≤ the predicted health threshold Y, it means that the future health status of the pipeline is normal, and continuous monitoring is performed at this time.

[0059] Beneficial Effects

[0060] The present invention provides a natural gas pipeline detection system based on optical fiber monitoring. It has the following beneficial effects:

[0061] (1) The system uses optical fiber monitoring modules to deploy multiple sensor points along the natural gas pipeline to collect multiple physical parameters such as sound velocity, soil moisture, and stress in real time. These data are converted from optical signals into electrical signals through demodulation equipment, and then processed into digital signals through analog-to-digital conversion. They are transmitted to the data processing module for preprocessing and standardization, and stored in the time series database. Compared with traditional manual detection and single-parameter monitoring, the real-time data collection and processing of this system greatly improves the accuracy and efficiency of monitoring. In particular, through denoising and standardization processing, the accuracy and comparability of the data are ensured, providing a reliable data basis for subsequent abnormality detection and health status assessment.

[0062] (2) The system uses an anomaly monitoring module. The system uses a multi-parameter fusion algorithm formula to fuse and calculate the standardized data to generate an anomaly scoring function A. i The system uses the preset abnormal threshold Ath and the abnormal scoring function A i The comparison can initially identify potential anomalies in the natural gas pipeline. Subsequently, the spatiotemporal distribution analysis module further combines the analysis of the time dimension and the space dimension to calculate the health status score H at each time and location. i (t) and the comprehensive health status Htotal. This analysis method based on the dual dimensions of time and space effectively improves the sensitivity and detection accuracy of abnormal conditions, and can capture small changes and local hidden dangers in the early stage of the pipeline, thereby significantly reducing the occurrence rate of failures.

[0063] (3) The monitoring trend prediction module of the system uses a global risk assessment algorithm combined with anomaly scoring function A i The system calculates the cumulative risk factor Racc based on the comprehensive health status Htotal, and predicts the pipeline health prediction value Plongterm for a period of time in the future through time series analysis. By comparing with the predicted health threshold Y, the system can automatically issue risk warnings. When the pipeline health prediction value Plongterm is greater than the health threshold Y, the system will issue an alarm and make maintenance recommendations for specific pipeline sections. This data-driven prediction and warning mechanism enhances the system's foresight, effectively reduces the occurrence of sudden pipeline accidents, and improves the safety and reliability of natural gas pipeline management. By predicting potential problems in advance, the system can also optimize maintenance plans and reduce the number of emergency maintenance, thereby reducing operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 The present invention is a schematic diagram of a natural gas pipeline detection system based on optical fiber monitoring. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Example 1

[0067] See also Figure 1 The present invention provides a natural gas pipeline detection system based on optical fiber monitoring. To achieve the above purpose, the present invention is implemented through the following technical solutions: including an optical fiber monitoring module, a data processing module, an abnormality monitoring module, a spatiotemporal distribution analysis module and a monitoring trend prediction module;

[0068] The optical fiber monitoring module is used to deploy optical fiber sensors along the natural gas pipeline, collect optical signals in real time, and transmit the collected optical signals to the demodulation device, where the optical signals are demodulated into electrical signals, and then the electrical signals are converted into digital signals to obtain pipeline operation data, which are then transmitted to the data processing module through relevant network protocols;

[0069] The data processing module is used to receive pipeline operation data in real time and preprocess the pipeline operation data. After preprocessing, the data is normalized to obtain a standard data set, and a time series database is constructed to store the obtained standard data set.

[0070] The anomaly monitoring module is used to construct a multi-parameter fusion algorithm formula, extract the standard data set in the time series database, input the multi-parameter fusion algorithm formula to calculate and output the anomaly scoring function A i , and preset the abnormal threshold Ath and the output abnormal scoring function A i Conduct preliminary comparative assessment and analysis of abnormal conditions in natural gas pipelines;

[0071] The spatiotemporal distribution analysis module is used to conduct a comprehensive analysis based on the preliminary comparative evaluation and analysis, by constructing the time dimension anomaly algorithm formula and extracting the anomaly scoring function A. i Input into the time dimension abnormal algorithm formula to calculate and output the health status score H at time t i (t), and then further calculate the comprehensive health status Htotal in the output natural gas pipeline space based on the health status score Hi(t) at time t;

[0072] The monitoring trend prediction module establishes a pipeline global risk assessment algorithm formula based on the abnormal scoring function A i, input into the pipeline global risk assessment algorithm formula, calculate and output the cumulative risk factor Racc, and combine it with the comprehensive health status Htotal to calculate and output the pipeline health prediction value Plongterm, and then preset the predicted health threshold Y and the pipeline health prediction value Plongterm for secondary comparative evaluation and analysis to predict the health status of the pipeline.

[0073] In this embodiment, the system realizes real-time monitoring, data processing, anomaly detection, spatiotemporal analysis, and health status prediction of the pipeline through the collaborative work of five core modules. First, the optical fiber monitoring module collects the physical parameters of the pipeline operation in real time through the optical fiber sensors laid along the pipeline, and converts the optical signal into a digital signal to achieve efficient real-time monitoring. The data processing module preprocesses and normalizes the collected data to ensure the accuracy of the data, and effectively stores and manages it through a time series database. The anomaly monitoring module uses a multi-parameter fusion algorithm to analyze the standardized data and generate an anomaly score A. i By comparing it with the threshold Ath, potential risks can be identified in a timely manner. The spatiotemporal distribution analysis module further combines the time and space dimensions to generate a health status score H i (t) and the global health status Htotal, thereby achieving an in-depth analysis of the overall health of the pipeline. Finally, the monitoring trend prediction module is based on the risk assessment algorithm, combined with the cumulative risk factor Racc and the health status prediction value Plongterm, to perform long-term prediction and early warning of the health status, providing opportunities for early intervention. Compared with the current traditional detection methods, this system has greatly improved the real-time monitoring and detection accuracy. Through multi-parameter fusion and spatiotemporal distribution analysis, the system can more keenly capture early abnormalities of the pipeline, significantly improving the sensitivity of fault detection. At the same time, combined with the trend prediction function, the system can predict future pipeline operation risks, optimize maintenance plans, reduce the incidence of emergencies, and reduce maintenance costs. This pipeline detection system that integrates real-time monitoring, intelligent analysis, prediction and early warning has achieved significant improvements in safety, operating efficiency and economy.

[0074] Example 2

[0075] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the optical fiber monitoring module includes an optical fiber signal acquisition unit, an optical fiber signal demodulation unit and an electrical signal conversion and transmission unit;

[0076] The optical fiber signal acquisition unit sets up several monitoring points inside the natural gas pipeline, with each monitoring point spaced 50 meters apart, and continuously lays several optical fiber sensor groups to collect the optical signal group in the natural gas pipeline in real time. The optical fiber sensor groups are then connected in series and sorted by distance. Each optical fiber sensor in the optical fiber sensor group is marked as i, where i represents the i-th optical fiber sensor, i={1,2,3,..,n}, and then integrated with the demodulation equipment;

[0077] The fiber optic sensor group includes fiber optic Brillouin sensing, fiber optic Bragg grating and distributed acoustic wave sensing;

[0078] The optical signal group includes a Brillouin scattering signal, a fiber Bragg grating reflection wavelength and a phase signal;

[0079] The optical fiber signal demodulation unit demodulates the optical signal groups collected by different optical fiber sensor groups into electrical signal groups through the demodulation device; the specific adjustment contents are as follows:

[0080] The demodulation equipment measures the stress and temperature changes at different locations in the optical fiber by analyzing the Brillouin scattering signal;

[0081] The demodulation equipment analyzes the stress and temperature of the environment in which the optical fiber is located by measuring the wavelength change of the wavelength reflected from the optical fiber grating;

[0082] The demodulation device analyzes and obtains the vibration signal by analyzing the phase change of the phase signal;

[0083] Integrate the different positions, stress and temperature changes in the optical fiber, the environment in which the optical fiber is located, stress, temperature and vibration signals into an electrical signal group;

[0084] The electrical signal conversion and transmission unit is used to convert the electrical signal group obtained after demodulation by the demodulation device into a numerical signal using an analog-to-digital converter ADC to obtain pipeline operation data. The pipeline operation data includes sound velocity Cs, soil moisture Ws and local stress S. The pipeline operation data is then transmitted to the data processing module through optical fiber Ethernet and the TCP / IP network protocol.

[0085] In this embodiment, the optical fiber monitoring module realizes the refined and real-time monitoring of the natural gas pipeline through the integration of optical fiber signal acquisition, demodulation and electrical signal conversion and transmission. The module uses optical fiber Brillouin sensing, fiber Bragg grating and distributed acoustic wave sensing technology to collect multi-dimensional physical parameters such as stress, temperature, vibration, etc. from multiple monitoring points along the pipeline to form a comprehensive optical signal group. Through the processing of the demodulation equipment, the system can convert these optical signals into electrical signals, and then convert them into digital signals through the analog-to-digital converter ADC, so as to obtain pipeline operation data including sound velocity Cs, soil moisture Ws and local stress S. Through optical fiber Ethernet and TCP / IP protocol, these data are transmitted to the data processing module, ensuring efficient transmission and timely processing of data, and the real-time and high-precision of the module are significantly improved. Compared with the traditional method of relying on a single sensor or regular detection, the optical fiber sensor group can realize continuous and global monitoring of long-distance pipelines, and the comprehensive use of Brillouin scattering signals, fiber Bragg grating reflections and phase signals greatly enhances the system's sensitivity to changes in external parameters such as stress, temperature and vibration, and can accurately identify early abnormalities in pipelines. Through advanced signal processing and data transmission technology, the system improves the efficiency and stability of data processing, reduces detection delays and false alarm rates, and ultimately achieves a more efficient and safer pipeline monitoring effect, greatly reducing the risk of pipeline accidents and improving the reliability and safety of pipeline operations.

[0086] Example 3

[0087] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the data processing module includes a pre-processing unit and a storage unit;

[0088] The preprocessing unit is used to receive the pipeline operation data in real time. After receiving the pipeline operation data, the pipeline operation data is denoised using a bandpass filter and wavelet transform technology. After the denoising process, the data is standardized to obtain a standard data set. The standard data set includes the sound velocity change rate △Cs, the soil moisture change rate △Ws and the local stress gradient △S.

[0089] The sound velocity change rate △Cs, soil moisture change rate △Ws and local stress gradient △S are calculated and obtained by the following standardized calculation formula;

[0090] ; ; ;

[0091] In the formula, Cs t Represents the sound velocity acquisition value at time t, Ws t represents the soil moisture collected at time t, S t represents the local stress at time t, Cst+1 Represents the sound velocity acquisition value at time t+1, Ws t+1 represents the soil moisture collected at time t+1, S t+1 represents the local stress at time t+1;

[0092] The storage unit is used to build a time series database and set the write port and the write port. The standard data set is written into the time series database through the write port, and the written standard data set is timestamped when writing and stored in the real-time data table in the time series database. At the same time, the last stored standard data set is automatically transferred to the historical data table and stored in chronological order.

[0093] In this embodiment, the system first receives the real-time data transmitted from the optical fiber monitoring module through the preprocessing unit, and uses the bandpass filter and wavelet transform technology to denoise the data, remove environmental noise and interference signals, and ensure the accuracy of the data. The denoised data is standardized and converted into a standard data set, including the sound velocity change rate ΔCs, the soil moisture change rate ΔWs, and the local stress gradient ΔS. These parameters are calculated based on the acquisition values ​​at different times through a specific standardized calculation formula for the change rate, so as to facilitate subsequent analysis and abnormality detection. The storage unit is used to store the standardized data set in a time series database to ensure the continuity and traceability of the data. The storage unit stores the data set in a real-time data table through a write port, and marks a timestamp for each data, and automatically transfers the previous data to the historical data table to ensure the time order storage of the data. This time series database design can effectively manage a large amount of monitoring data and provide accurate historical basis for subsequent abnormal analysis, health status assessment, and trend prediction. Through these functions, the data processing module greatly improves the efficiency and accuracy of data management.

[0094] Example 4

[0095] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the anomaly monitoring module includes an anomaly computing unit and an anomaly analyzing unit;

[0096] The abnormal calculation unit is used to construct a multi-parameter fusion algorithm formula. Through the write port of the time series database, the standard data set obtained in real time is extracted and input into the multi-parameter fusion algorithm formula to calculate and output the abnormal scoring function A. i , conduct preliminary analysis to see if there are any abnormal changes in the natural gas pipeline;

[0097] Anomaly scoring function A i Obtained through calculation using the following multi-parameter fusion algorithm formula;

[0098] ;

[0099] In the formula, A i It represents the abnormal scoring function corresponding to the optical fiber sensor of the i-th section of the natural gas pipeline. a1, a2 and a3 represent the preset weight values ​​of the sound velocity change rate △Cs, the soil moisture change rate △Ws and the local stress gradient △S, respectively, and a1+a2+a3=1. The specific values ​​are set by the user.

[0100] The abnormal analysis unit is based on the user's preset abnormal threshold Ath according to the normal indicators of the natural gas pipeline, and then compared with the obtained abnormal scoring function A i Conduct a preliminary comparative assessment to analyze the status of the natural gas pipeline in different fiber optic sensor sections. The specific assessment contents are as follows;

[0101] When the anomaly scoring function A i > abnormal threshold Ath, it means that the natural gas pipeline safety of the optical fiber sensor section of the current section is in an abnormal state, and an early warning is triggered to maintain the natural gas pipeline of the current section;

[0102] When the anomaly scoring function A i When ≤ the abnormal threshold Ath, it means that the natural gas pipeline safety of the optical fiber sensor section of the current section is in normal state, and the health prediction of the natural gas pipeline is carried out at this time.

[0103] In this embodiment, the system extracts the standard data set acquired in real time through the time series database through the abnormal calculation unit, and calculates the abnormal scoring function Ai through the multi-parameter fusion algorithm, combined with the sound speed change rate ΔCs, soil moisture change rate ΔWs and local stress gradient ΔS, to achieve a preliminary evaluation of the status of each section of the pipeline. The weight of each parameter is set by the user according to the actual situation of the pipeline, so that the algorithm can flexibly adapt to different environmental conditions. Then, the abnormal analysis unit evaluates the abnormal score through the preset abnormal threshold Ath. When the abnormal scoring function Ai exceeds the abnormal threshold Ath, the system will immediately trigger an early warning and make maintenance suggestions to ensure that the problem can be handled in time at an early stage; when the abnormal scoring function Ai is lower than or equal to the abnormal threshold Ath, the system continues to monitor and predict the health status. This module improves the accuracy of abnormal detection through a multi-parameter fusion algorithm, and can simultaneously consider the changes in multiple important physical parameters to provide a more refined evaluation. In addition, the automated real-time early warning mechanism greatly shortens the response time and avoids delays caused by manual intervention.

[0104] Example 5

[0105] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the spatiotemporal distribution analysis module includes a time dimension ,analysis unit and a space dimension analysis unit;

[0106] The time dimension analysis unit is used to trigger when the natural gas pipeline safety is in a normal state at the preliminary comparative assessment. By constructing the time dimension abnormal algorithm formula, the abnormal score function A of the current monitoring point is extracted. i , input into the time dimension abnormal algorithm formula, calculate and output the health status score H at time t i (t), captures the changes in the health status of the natural gas pipeline within a period of time;

[0107] Health status score H at time t i (t) The output is calculated by the following time dimension anomaly algorithm formula;

[0108] ;

[0109] In the formula, H i (t) represents the health status score of the fiber optic sensor in the i-th section of the natural gas pipeline at time t, T represents the time span, t1 represents the lower limit of time, t2 represents the upper limit of time, dt represents the time differential variable, and A i (t) represents the abnormal scoring function corresponding to the optical fiber sensor of the i-th section of the natural gas pipeline at time t.

[0110] The spatial dimension analysis unit is used to score the health status of multiple monitoring points H i (t) Combined with the spatial coupling effect, the comprehensive health status Htotal is calculated and output to further analyze the global health status of the pipeline;

[0111] The comprehensive health status Htotal is calculated and output by the following algorithm formula;

[0112] ;

[0113] Where N represents the total number of fiber optic sensors deployed, T xy It means that in space, the health status of the detection point is affected by the coupling of its spatial position coordinates x and y.

[0114] In this embodiment, the system uses the time dimension analysis unit to extract the abnormal score A of the current monitoring point. i (t), and use the time dimension abnormal algorithm formula to calculate the health status score H in the time period t i (t), which can capture the health change trend of the pipeline in different time periods. Secondly, the spatial dimension analysis unit combines the health status scores H of multiple monitoring points i(t) and spatial coupling effects are used to calculate the comprehensive health status Htotal, thereby reflecting the health status of the entire pipeline system in the spatial dimension. This spatial analysis takes into account the interactions between the various monitoring points and the influence of the geographical location, further improving the analysis depth and accuracy of the system. The spatiotemporal distribution analysis module significantly improves the ability to capture changes in the health status of the pipeline by introducing dynamic analysis in the two dimensions of time and space. This module can not only analyze short-term abnormal fluctuations, but also identify potential health problems of the pipeline through long-term data analysis. In addition, the introduction of spatial coupling effects fully considers the correlation between different areas of the pipeline, which helps to discover global or regional problems. Compared with existing technologies, this module greatly improves the accuracy and foresight of health status assessment, realizes comprehensive and intelligent health monitoring of the pipeline system, thereby significantly reducing the risk of accidents and optimizing the maintenance and management strategy of the pipeline.

[0115] Example 6

[0116] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the monitoring trend prediction module includes the cumulative risk ,analysis unit, the time series analysis and prediction unit and the ,health assessment unit;

[0117] The data accumulation risk analysis unit extracts the comprehensive health status Htotal combined with the abnormal scoring function A by establishing a pipeline global risk assessment algorithm formula i , input into the global risk assessment algorithm formula to calculate and output the cumulative risk factor Racc, and quantify the overall risk accumulation of the pipeline;

[0118] The cumulative risk factor Racc is calculated and output by the following global risk assessment algorithm formula;

[0119] ;

[0120] Where Li represents the length of the pipeline covered by the i-th section of the optical fiber sensor, which is 50 meters, Ltotal represents the total length of the pipeline, k represents the risk correction factor for the entire area, and N represents the total number of optical fiber sensors deployed.

[0121] The time series analysis and prediction unit extracts historical data through the write port of the time series database to calculate and output the abnormal scoring function A at the previous moment. i (t-1), combined with the cumulative risk factor Racc and the comprehensive health status Htotal, and then using time series analysis to comprehensively calculate the output pipeline health prediction value Plongterm, to predict the risk development trend of the pipeline in the future;

[0122] The pipeline health prediction value Plongterm is calculated and output by the following algorithm formula;

[0123] ;

[0124] Where f represents the prediction function, and the prediction function f is a time series analysis algorithm, such as a decision tree, random forest, or neural network.

[0125] The health assessment unit presets the predicted health threshold Y through the average of the historical pipeline health prediction value Plongterm, and then performs a secondary comparative assessment with the obtained pipeline health prediction value Plongterm to predict the health status of the natural gas pipeline. The specific assessment contents are as follows;

[0126] When the pipeline health prediction value Plongterm>predicted health threshold Y, it means that the future health status of the pipeline is abnormal. At this time, the secondary execution abnormality monitoring module is executed to locate the abnormal pipeline section and send maintenance prompt information;

[0127] When the pipeline health prediction value Plongterm ≤ the predicted health threshold Y, it means that the future health status of the pipeline is normal, and continuous monitoring is performed at this time.

[0128] In this embodiment, the system uses the cumulative risk analysis unit to combine the comprehensive health status Htotal and the abnormal scoring function A i , using a global risk assessment algorithm to quantify and output the cumulative risk factor Racc, providing an accurate quantitative assessment of the overall risk status of the pipeline. Next, the time series analysis and prediction unit uses the historical data in the time series database, combined with Racc and Htotal, and calculates the long-term health prediction value Plongterm of the pipeline through time series analysis methods such as random forests or neural networks, which is used to predict future risk trends. Finally, the health assessment unit sets the predicted health threshold Y based on historical data, and compares Plongterm with the health threshold Y. When the prediction result exceeds the threshold, an early warning is triggered, and the abnormal pipeline section is accurately located and a maintenance prompt is issued to ensure that the problem can be handled at an early stage. By introducing time series analysis and deep learning algorithms, this module greatly improves the dynamics and foresight of pipeline status assessment, enabling the system to predict potential risks in advance and deploy maintenance measures in advance to avoid major accidents.

[0129] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A natural gas pipeline detection system based on optical fiber monitoring, characterized in that: It includes optical fiber monitoring module, data processing module, abnormal monitoring module, spatiotemporal distribution analysis module and monitoring trend prediction module; The optical fiber monitoring module is used to deploy optical fiber sensors along the natural gas pipeline, collect optical signals in real time, and transmit the collected optical signals to the demodulation device, where the optical signals are demodulated into electrical signals, and then the electrical signals are converted into digital signals to obtain pipeline operation data, and then transmitted to the data processing module through relevant network protocols; The data processing module is used to receive pipeline operation data in real time, and pre-process the pipeline operation data. After the pre-processing, the data is normalized to obtain a standard data set, and a time series database is constructed to store the obtained standard data set. The anomaly monitoring module is used to construct a multi-parameter fusion algorithm formula, extract a standard data set from the time series database, input it into the multi-parameter fusion algorithm formula to calculate and output an anomaly scoring function A i , and preset the abnormal threshold Ath and the output abnormal scoring function A i Conduct preliminary comparative assessment and analysis of abnormal conditions in natural gas pipelines; The spatiotemporal distribution analysis module is used to further conduct a comprehensive analysis based on the preliminary comparative evaluation and analysis, by constructing a time dimension anomaly algorithm formula and extracting anomaly scoring function A. i Input into the time dimension abnormal algorithm formula to calculate and output the health status score H at time t i (t), and then further calculate the comprehensive health status Htotal of the output natural gas pipeline space based on the health status score Hi(t) at time t; The spatiotemporal distribution analysis module includes a time dimension analysis unit and a space dimension analysis unit; The time dimension analysis unit is used to trigger when the natural gas pipeline safety is in a normal state at the preliminary comparative assessment, and extract the abnormal scoring function A of the current monitoring point by constructing the time dimension abnormal algorithm formula. i , input into the time dimension abnormal algorithm formula, calculate and output the health status score H at time t i (t), captures the changes in the health status of the natural gas pipeline within a period of time; The health status score H at the time t i (t) The output is calculated by the following time dimension anomaly algorithm formula; ； In the formula, H i (t) represents the health status score of the fiber optic sensor in the i-th section of the natural gas pipeline at time t, T represents the time span, t1 represents the lower limit of time, t2 represents the upper limit of time, dt represents the time differential variable, and A i (t) represents the abnormal scoring function corresponding to the optical fiber sensor of the i-th section of the natural gas pipeline at time t; The spatial dimension analysis unit is used to calculate the health status scores H of multiple monitoring points. i (t) Combined with the spatial coupling effect, the comprehensive health status Htotal is calculated and output to further analyze the global health status of the pipeline; The comprehensive health status Htotal is calculated and output by the following algorithm formula; ； Where N represents the total number of fiber optic sensors deployed, T xy It means that in space, the health status of the detection point is affected by the coupling of its spatial position coordinates x and y; The monitoring trend prediction module establishes a pipeline global risk assessment algorithm formula based on the abnormal scoring function A i , input into the pipeline global risk assessment algorithm formula, calculate and output the cumulative risk factor Racc, and combine it with the comprehensive health status Htotal to calculate and output the pipeline health prediction value Plongterm, and then preset the predicted health threshold Y and the pipeline health prediction value Plongterm for secondary comparative evaluation and analysis to predict the health status of the pipeline; The monitoring trend prediction module includes a cumulative risk analysis unit, a time series analysis and prediction unit, and a health assessment unit; The data accumulation risk analysis unit extracts the comprehensive health status Htotal combined with the abnormal scoring function A by establishing a pipeline global risk assessment algorithm formula i , input into the global risk assessment algorithm formula to calculate and output the cumulative risk factor Racc, and quantify the overall risk accumulation of the pipeline; The cumulative risk factor Racc is calculated and output by the following global risk assessment algorithm formula; ； In the formula, Li represents the length of the pipeline covered by the i-th section of the optical fiber sensor, which means 50 meters, Ltotal represents the total length of the pipeline, k represents the risk correction factor of the whole area, and N represents the total number of optical fiber sensors deployed; The time series analysis and prediction unit extracts historical data through the write port of the time series database to calculate and output the abnormal scoring function A at the previous moment. i (t-1), combined with the cumulative risk factor Racc and the comprehensive health status Htotal, and then using time series analysis to comprehensively calculate the output pipeline health prediction value Plongterm, to predict the risk development trend of the pipeline in the future; The pipeline health prediction value Plongterm is calculated and output by the following algorithm formula; ； In the formula, f represents the prediction function; The health assessment unit presets the predicted health threshold Y by the average of the historical pipeline health prediction values ​​Plongterm, and then performs a secondary comparative assessment with the obtained pipeline health prediction value Plongterm to predict the health status of the natural gas pipeline. The specific assessment contents are as follows; When the pipeline health prediction value Plongterm>predicted health threshold Y, it means that the future health status of the pipeline is abnormal. At this time, the secondary execution abnormality monitoring module is executed to locate the abnormal pipeline section and send maintenance prompt information; When the pipeline health prediction value Plongterm ≤ the predicted health threshold Y, it means that the future health status of the pipeline is normal, and continuous monitoring is performed at this time.

2. A natural gas pipeline detection system based on optical fiber monitoring according to claim 1, characterized in that: The optical fiber monitoring module includes an optical fiber signal acquisition unit, an optical fiber signal demodulation unit and an electrical signal conversion and transmission unit; The optical fiber signal acquisition unit sets a number of monitoring points inside the natural gas pipeline, each monitoring point is 50 meters apart, and a number of optical fiber sensor groups are laid continuously to collect the optical signal group in the natural gas pipeline in real time, and then the optical fiber sensor groups are connected in series and sorted according to the distance, and each optical fiber sensor in the optical fiber sensor group is marked as i, where i represents the i-th section of the optical fiber sensor, i={1,2,3,..,n}, and then integrated with the demodulation device; The optical fiber sensor group includes optical fiber Brillouin sensor, optical fiber Bragg grating and distributed acoustic wave sensor; The optical signal group includes a Brillouin scattering signal, a fiber grating reflection wavelength and a phase signal; The optical fiber signal demodulation unit demodulates the optical signal groups collected by different optical fiber sensor groups into electrical signal groups through a demodulation device; the specific adjustment contents are as follows: The demodulation equipment measures the stress and temperature changes at different locations in the optical fiber by analyzing the Brillouin scattering signal; The demodulation equipment analyzes the stress and temperature of the environment in which the optical fiber is located by measuring the wavelength change of the wavelength reflected from the optical fiber grating; The demodulation device analyzes and obtains the vibration signal by analyzing the phase change of the phase signal; The electrical signal conversion and transmission unit is used to convert the electrical signal group obtained after demodulation by the demodulation device into a numerical signal using an analog-to-digital converter ADC to obtain pipeline operation data. The pipeline operation data includes sound velocity Cs, soil moisture Ws and local stress S. The pipeline operation data is then transmitted to the data processing module through the optical fiber Ethernet and the TCP / IP network protocol.

3. A natural gas pipeline detection system based on optical fiber monitoring according to claim 2, characterized in that: The data processing module includes a preprocessing unit and a storage unit; The preprocessing unit is used to receive the pipeline operation data in real time, and after receiving the pipeline operation data, perform denoising on the pipeline operation data using a bandpass filter and wavelet transform technology, and perform standardization after denoising to obtain a standard data set, wherein the standard data set includes a sound velocity change rate △Cs, a soil moisture change rate △Ws, and a local stress gradient △S; The sound velocity change rate △Cs, soil moisture change rate △Ws and local stress gradient △S are calculated and obtained by the following standardized calculation formula; ； ； ； In the formula, Cs t Represents the sound velocity acquisition value at time t, Ws t represents the soil moisture collected at time t, S t represents the local stress at time t, Cs t+1 Represents the sound velocity acquisition value at time t+1, Ws t+1 represents the soil moisture collected at time t+1, S t+1 represents the local stress at time t+1; The storage unit is used to build a time series database, and set a write port and a write port, write the standard data set into the time series database through the write port, and mark the written standard data set with a timestamp when writing, and store it in the real-time data table in the time series database. At the same time, the last stored standard data set is automatically transferred to the historical data table and stored in chronological order.

4. A natural gas pipeline detection system based on optical fiber monitoring according to claim 3, characterized in that: The abnormality monitoring module includes an abnormality calculation unit and an abnormality analysis unit; The abnormal calculation unit is used to construct a multi-parameter fusion algorithm formula, extract the standard data set obtained in real time through the write port of the time series database, input it into the multi-parameter fusion algorithm formula, and calculate and output the abnormal scoring function A i , conduct preliminary analysis to see if there are any abnormal changes in the natural gas pipeline; The anomaly scoring function A i Obtained through calculation using the following multi-parameter fusion algorithm formula; ； In the formula, A i It represents the abnormal scoring function corresponding to the optical fiber sensor of the i-th section of the natural gas pipeline. a1, a2 and a3 represent the preset weight values ​​of the sound velocity change rate △Cs, the soil moisture change rate △Ws and the local stress gradient △S, respectively, and a1+a2+a3=1. The specific values ​​are set by the user.

5. A natural gas pipeline detection system based on optical fiber monitoring according to claim 4, characterized in that: The abnormal analysis unit presets an abnormal threshold value Ath according to the normal indicators of the natural gas pipeline by the user, and then compares it with the acquired abnormal scoring function Ath. i Conduct a preliminary comparative assessment to analyze the status of the natural gas pipeline in different fiber optic sensor sections. The specific assessment contents are as follows; When the anomaly scoring function A i > abnormal threshold Ath, it means that the natural gas pipeline safety of the optical fiber sensor section of the current section is in an abnormal state, and an early warning is triggered to maintain the natural gas pipeline of the current section; When the anomaly scoring function A i When ≤ the abnormal threshold Ath, it means that the natural gas pipeline safety of the optical fiber sensor section of the current section is in normal state, and the health prediction of the natural gas pipeline is carried out at this time.

Images