Intelligent pipeline supervision system based on Internet of Things

Abstract

The invention discloses a smart pipeline supervision system based on the Internet of Things, and relates to the technical field of smart pipeline supervision, and the system comprises the steps: deploying a plurality of sensors, and obtaining pipeline data; calculating a pipeline health value based on the pipeline data; based on the pipeline health value, performing preliminary analysis on pipeline health by using an edge computing technology, and performing preliminary processing; based on the preliminary analysis result, secondary analysis is carried out, potential fault points are identified, and response measures are executed; based on the response measures, an operation report is automatically generated. According to the method, multiple types of sensors are integrated, the pipeline state is comprehensively monitored in real time, health value abnormity is quickly responded through edge calculation, and fault diffusion is effectively prevented. The problem is accurately positioned through secondary analysis, and the maintenance strategy is optimized. On the whole, the intelligent monitoring level, the response speed and the maintenance efficiency of the pipeline system are remarkably improved, the operation risk and cost are greatly reduced, and the industry is promoted to be transformed to intelligent operation and maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of smart pipeline monitoring, and in particular to a smart pipeline monitoring system based on the Internet of Things. Background Art

[0002] As an important logistics method, pipeline transportation plays an indispensable role in the transportation of compressed air, oxygen, carbon dioxide, hydrogen and other gases. In recent years, with the rapid development of Internet of Things technology, more and more intelligent monitoring systems have been applied to the field of pipeline supervision. Traditional pipeline monitoring methods mainly rely on manual inspections and simple alarm devices, which have problems such as low monitoring efficiency and slow response speed. With the advancement of sensing technology and the improvement of data processing capabilities, the existing IoT-based pipeline supervision system still has some shortcomings, especially in the health monitoring and fault diagnosis of gas pipelines. Traditional methods often focus on the monitoring of a single parameter and lack a comprehensive assessment of the overall health of the pipeline. In addition, most systems fail to make full use of edge computing technology for real-time data analysis and response, resulting in delayed fault detection and delayed response measures. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides an intelligent pipeline monitoring system based on the Internet of Things to solve the problems of data processing delay and inaccurate fault prediction in the existing pipeline monitoring system.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides an IoT-based smart pipeline monitoring system, which includes a data acquisition module responsible for deploying a variety of sensors to obtain pipeline data;

[0007] The pipeline health calculation module is responsible for calculating the pipeline health value based on the pipeline data;

[0008] The preliminary analysis module is responsible for conducting preliminary analysis and processing of pipeline health based on pipeline health values ​​using edge computing technology;

[0009] The secondary analysis module is responsible for conducting secondary analysis based on the preliminary analysis results, identifying potential failure points, and taking corresponding measures;

[0010] The report generation module is responsible for automatically generating operation reports based on response measures.

[0011] As a preferred solution of the smart pipeline monitoring system based on the Internet of Things of the present invention, wherein: the multiple sensors include pressure sensors, temperature sensors, flow meters, vibration sensors and acoustic sensors;

[0012] The pipeline data includes pressure, temperature, flow rate, vibration frequency and sound.

[0013] As a preferred solution of the smart pipeline monitoring system based on the Internet of Things described in the present invention, the pipeline health value is calculated based on the pipeline data, including the following steps:

[0014] Perform Z-score standardization on pipeline data;

[0015] Based on the processed pipeline data, the pipeline health value is calculated and expressed as,

[0016]

[0017] Among them, A represents the pipeline health value, P represents the pressure after treatment, T represents the temperature after treatment, Q represents the flow rate after treatment, W represents the decibel value of the sound after treatment, V represents the vibration frequency after treatment, a represents the elastic sensitivity coefficient, b represents the reference offset, c represents the heat resistance index, φ represents the vibration frequency coefficient, α represents the pressure enhancement coefficient, and β represents the temperature enhancement coefficient.

[0018] As a preferred solution of the smart pipeline monitoring system based on the Internet of Things described in the present invention, the pipeline health is initially analyzed based on the pipeline health value using edge computing technology, including the following steps:

[0019] Set up edge computing devices on the pipeline and define preliminary analysis thresholds based on statistical analysis of historical data;

[0020] When the pipeline health value is greater than or equal to the preliminary analysis threshold, it indicates that the pipeline is safe;

[0021] When the pipeline health value is less than the preliminary analysis threshold, it indicates that there is an abnormality in the pipeline.

[0022] As a preferred solution of the smart pipeline monitoring system based on the Internet of Things described in the present invention, preliminary processing is performed based on the preliminary analysis results, including the following steps:

[0023] When the pipeline is safe, continue to monitor the pipeline health status;

[0024] When an abnormality is detected, the abnormal data is recorded, and the edge computing device immediately executes the gate control instructions to prevent dangers caused by potential ruptures, activates the emergency response plan, isolates the faulty section by closing the gates adjacent to the abnormal area, and reduces the impact on the entire pipeline network.

[0025] As a preferred solution of the IoT-based smart pipeline supervision system described in the present invention, the edge computing device marks the abnormal data and sends it to the cloud server through an encrypted connection, and uses encryption technology and blockchain to record the data transmission process.

[0026] As a preferred solution of the smart pipeline monitoring system based on the Internet of Things described in the present invention, a secondary analysis is performed based on the preliminary analysis results, including the following steps:

[0027] When an anomaly is found, the pipeline health value is mapped to the geographical layout of the pipeline network to create a heat map of the pipeline health value. The density of the data points around a given location is used to obtain the pipeline health value density estimate, which is expressed as,

[0028]

[0029] in, represents the pipeline health value density estimate at the position (x, y), A i represents the pipeline health value of the i-th observation point, (x, y) represents the geographical location x and y, n represents the number of observation points, (x i ,y i ) represents the position coordinates of the i-th observation point, i represents the index of the number of observation points, and σ represents the bandwidth;

[0030] The autoregressive moving average model is used to identify the regularity and abnormal trend of pipeline health value changes over time, expressed as,

[0031] φ(B)A t =θ(B)ε t -η t ;

[0032] Among them, B represents the backshift operator, A t represents the pipeline health value at time point t, φ(B) represents the autoregressive polynomial, φ(B)=1-φ1B-…-φ p B p , where p represents the order of the autoregressive term, φ1,…,φ p represents the linear coefficient of the autoregressive term, θ(B) represents the moving average polynomial, θ(B)=1+θ1B+…+θ q B q , where θ1,…,θq represent the linear coefficients of the moving average term, q represents the order of the moving average term, and ε t represents a white noise sequence, B q represents the qth power of the backshift operator, B p represents the p-th power of the backshift operator, η t represents the additional error value;

[0033] Spatial autocorrelation analysis is used to evaluate the spatial correlation between pipeline health values ​​at different locations, and the Moran index is calculated to quantify the degree of spatial autocorrelation, which is expressed as,

[0034]

[0035] Among them, I represents the Moran index, S represents the sum of all elements of the weight matrix, and A k represents the pipeline health value at position k, A m represents the pipeline health value at position m, w mk Represents the elements of the spatial weight matrix, k represents the index variable of the second position, m represents the index variable of the first position, Indicates the average of the pipeline health values ​​at all locations.

[0036] As a preferred solution of the IoT-based smart pipeline monitoring system of the present invention, the following steps are included to identify potential fault points based on the secondary analysis results:

[0037] Based on the secondary analysis results, the comprehensive pipeline health value abnormal scoring function is defined and expressed as:

[0038]

[0039]

[0040] Among them, S A (x, y, t) represents the comprehensive pipeline health value anomaly score at the location (x, y) and time point t, τ represents the threshold of pipeline health value density estimation, I e The threshold value representing the level of spatial autocorrelation, ΔA t Indicates the rate of change of pipeline health value, A t-1 Indicates the pipeline health value at the previous time point;

[0041] Based on the comprehensive pipeline health value anomaly scoring function, the areas where the pipeline health value anomaly score increases are located, marked as potential fault points, and a fault marking map is created.

[0042] As a preferred solution of the smart pipeline monitoring system based on the Internet of Things described in the present invention, the following steps are included: executing response measures according to the identification results:

[0043] Based on the fault marking map, the maintenance team is notified to enter the site, and the maintenance team performs repairs in a timely manner according to the location and nature of the fault point;

[0044] After the repair is completed, a quality inspection is carried out to ensure that the fault has been completely resolved without leaving any safety hazards, and the repair process is recorded.

[0045] As a preferred solution of the smart pipeline monitoring system based on the Internet of Things described in the present invention, the operation report is automatically generated based on the response measures, including the following steps:

[0046] Integrate fault marking maps and recorded maintenance processes to generate detailed reports for each fault point, and automatically generate operation reports by combining reports of all fault points.

[0047] The beneficial effects of the present invention are as follows: the present invention realizes all-round real-time monitoring of pipelines by integrating multiple sensors, ensuring rich and accurate data, and laying the foundation for intelligent monitoring. Advanced algorithms are used to convert pipeline data into health values, keenly capture state changes, quantify health conditions, assist early warning mechanisms, and significantly improve risk prediction capabilities. The application of edge computing technology greatly shortens response time, handles exceptions in real time, ensures data security through encryption and blockchain, and enhances system resilience. Secondary analysis deeply mines information in the time and space dimensions, accurately diagnoses faults, optimizes resource allocation, accelerates the maintenance process, and ensures stable system operation. Automatically generate operation reports, systematically sort out fault details and maintenance records, provide data support for decision-making, simplify management processes, and improve overall operation and maintenance efficiency. In summary, this innovative solution significantly enhances the intelligent monitoring, rapid response, and efficient management capabilities of pipeline systems, greatly reduces operational risks, and is a major advancement in the field of pipeline operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 This is a flow chart of the smart pipeline monitoring system based on the Internet of Things in Example 1.

[0050] Figure 2 This is the pipeline abnormality analysis discrimination diagram in Example 1. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a smart pipeline monitoring system based on the Internet of Things, comprising the following steps:

[0055] S1. Deploy various sensors to obtain pipeline data.

[0056] A variety of sensors including pressure sensors, temperature sensors, flow meters, vibration sensors, and acoustic sensors;

[0057] Pipeline data includes pressure, temperature, flow rate, vibration frequency and sound.

[0058] It should be noted that by deploying multiple types of sensors including pressure, temperature, flow, vibration and acoustics, comprehensive and real-time monitoring of pipeline operation status is achieved. This step can collect rich data, provide a basis for subsequent pipeline health analysis, ensure the diversity and accuracy of data, and thus improve the intelligence and reliability of the pipeline monitoring system.

[0059] S2. Calculate the pipeline health value based on the pipeline data.

[0060] Perform Z-score standardization on pipeline data;

[0061] Based on the processed pipeline data, the pipeline health value is calculated and expressed as,

[0062]

[0063] Among them, A represents the pipeline health value, which is used to quantify the health status of the pipeline, P represents the processed pressure, T represents the processed temperature, Q represents the processed flow rate, W represents the decibel value of the processed sound, V represents the processed vibration frequency, a represents the elastic sensitivity coefficient, which reflects the response of the material to pressure changes, b represents the reference offset, which is used to adjust the pressure measurement to make it closer to the true value, c represents the heat resistance index, which reflects the stability and life of the material at high temperature, φ' represents the vibration frequency coefficient, which affects the periodicity and energy distribution of the vibration, α represents the pressure enhancement coefficient, which represents the additional impact of the pressure increase on the pipeline health value, and β represents the temperature enhancement coefficient, which reflects the weighted impact of temperature changes on the pipeline health value.

[0064] Furthermore, the elastic sensitivity coefficient reflects the responsiveness of the pipeline material to pressure changes and is usually related to the elastic modulus of the material. It can be determined through laboratory testing, such as by applying different pressures and measuring the deformation of the pipeline material. This coefficient may also depend on the type of material, temperature, humidity and other environmental conditions. The heat resistance index reflects the stability and life of the material at high temperatures and can be determined through thermal cycling tests and long-term aging tests. These tests involve exposing material samples to different temperatures for a long time and then measuring the changes in their performance. By analyzing the relationship between temperature and performance degradation, an index suitable for inclusion in the formula can be obtained. The vibration frequency coefficient affects the periodicity and energy distribution of the vibration and may be related to the geometry of the pipeline, the supporting structure, the properties of the internal flow medium, and the external vibration source. Through vibration testing and spectrum analysis, the vibration response at different frequencies can be measured to determine a suitable coefficient. The pressure enhancement factor represents the additional effect of increased pressure on the pipeline health value. It can be obtained through experimental design to test the performance changes of the pipeline under known pressure conditions. This usually involves applying different pressures to the pipeline samples in a laboratory environment and monitoring their health indicators. The temperature enhancement factor reflects the weighted effect of temperature changes on the pipeline health value. This can also be determined through experimental testing, such as testing pipe samples over a range of temperatures to observe how temperature changes affect the pipe's mechanical properties, chemical stability and service life.

[0065] It should be noted that the formula for calculating pipeline health value is designed based on comprehensive consideration of the impact of pipeline physical characteristics and operating conditions on pipeline health, and quantification of these factors through mathematical models in order to objectively evaluate the health of the pipeline. Each parameter in the formula represents a specific physical quantity or environmental condition, and their contribution to the pipeline health value reflects their respective roles in pipeline performance and stability.

[0066] It should be noted that the standardized pipeline data is converted into pipeline health values ​​through complex mathematical models, effectively quantifying the health status of the pipeline. This quantification process can not only intuitively reflect the current status of the pipeline, but also capture subtle health change trends through the set formula, providing a scientific basis for the early warning mechanism. Through this quantitative analysis, dynamic monitoring of pipeline health can be achieved, potential risks can be predicted in advance, and the probability of sudden accidents can be reduced.

[0067] S3. Based on the pipeline health value, use edge computing technology to conduct preliminary analysis of pipeline health and perform preliminary processing.

[0068] Set up edge computing devices on the pipeline, which can directly access sensor data, reduce the latency and bandwidth requirements of data transmission to the central server, and define preliminary analysis thresholds based on historical data statistical analysis;

[0069] When the pipeline health value is greater than or equal to the preliminary analysis threshold, it indicates that the pipeline is safe;

[0070] When the pipeline health value is less than the preliminary analysis threshold, it indicates that there is an abnormality in the pipeline.

[0071] When the pipeline is safe, continue to monitor the pipeline health status;

[0072] When an abnormality is detected, the abnormal data is recorded, and the edge computing device immediately executes the gate control instructions to prevent dangers caused by potential ruptures and activate the emergency response plan, including starting the backup system, adjusting other parts of the pipeline network to maintain service, and isolating the faulty section by closing the gates adjacent to the abnormal area to reduce the impact on the entire pipeline network.

[0073] The edge computing device marks the abnormal data and sends it to the cloud server through an encrypted connection, using encryption technology and blockchain to record the data transmission process to ensure the integrity and tamper-proofness of the data.

[0074] It should be noted that the application of edge computing significantly reduces the delay of data transmission and improves the speed and efficiency of data processing. When the health value is lower than the threshold, the edge computing device can respond quickly, such as closing the gate, starting the backup system, etc., effectively preventing the fault from further expanding and reducing the impact on the environment and economy. In addition, the application of data encryption and blockchain technology ensures the security and integrity of the data and enhances the security of the system.

[0075] S4. Based on the preliminary analysis results, conduct secondary analysis, identify potential failure points, and implement corresponding measures.

[0076] When an anomaly is found, the pipeline health value is mapped to the geographical layout of the pipeline network to create a heat map of the pipeline health value. The density of the data points around a given location is used to obtain the pipeline health value density estimate, which is expressed as,

[0077]

[0078] in, represents the pipeline health value density estimate at the position (x, y), A i represents the pipeline health value of the i-th observation point, (x, y) represents the geographical location x and y, n represents the number of observation points, (x i ,y i ) represents the position coordinate of the ith observation point, i represents the index of the number of observation points, and σ represents the bandwidth, which determines the smoothness of the density estimation. It should be noted that the design of the pipeline health value density estimation formula is based on the fact that Gaussian kernel density estimation is used to smooth the observation point data to identify the distribution pattern and abnormally dense areas of pipeline health values ​​in geographic space.

[0079] The bandwidth σ can be calculated by Silverman's rule, and the formula is expressed as follows:

[0080]

[0081] Among them, s represents the standard deviation of the health value of the observation point;

[0082] It should be noted that the choice of bandwidth σ has a great impact on the results of density estimation. A larger σ will lead to a smoother estimate but may obscure details; a smaller σ will make the estimate more detailed but may introduce too much noise. Choosing the right bandwidth is one of the key steps in kernel density estimation.

[0083] The autoregressive moving average model is used to identify the regularity and abnormal trend of pipeline health value changes over time, expressed as,

[0084] φ(B)A t =θ(B)ε t -η t ;

[0085] Among them, B represents the backshift operator, A t represents the pipeline health value at time point t, φ(B) represents the autoregressive polynomial, capturing the autocorrelation of the time series, φ(B)=1-φ1V-…-φ p B p , where p represents the order of the autoregressive term, φ1,…,φ p represents the linear coefficient of the autoregressive term, θ(B) represents the moving average polynomial, reflecting the random fluctuations of the time series, θ(B)=1+θ1B+…+θ q B q , where θ1,…,θ q represents the linear coefficient of the moving average term, q represents the order of the moving average term, and ε t represents a white noise sequence, representing an unpredictable random disturbance, B q represents the qth power of the backshift operator, B p represents the p-th power of the backshift operator, η t Represents the additional error value, which is used to capture the part that cannot be explained by the model. The additional error value is determined by using the historical additional error value to fit the ARMA model, that is, to find the optimal autoregressive coefficients φ1,…,φ p and moving average coefficients θ1,…,θ q ; This is usually achieved by minimizing the residual sum of squares (RSS) or maximum likelihood estimation methods;

[0086] It should be noted that the ARMA model in time series analysis is used to identify the trend and periodicity of pipeline health values ​​over time and help predict future health status.

[0087] Spatial autocorrelation analysis is used to evaluate the spatial correlation between pipeline health values ​​at different locations, and the Moran index is calculated to quantify the degree of spatial autocorrelation, expressed as:

[0088]

[0089] Where I represents the Moran index, which is used to quantify the degree of spatial autocorrelation, S represents the sum of all elements of the weight matrix, and A k represents the pipeline health value at position k, A m represents the pipeline health value at position m, w mk Represents the elements of the spatial weight matrix, reflecting the spatial relationship between positions m and k, where k represents the index variable of the second position and m represents the index variable of the first position. Indicates the average of the pipeline health values ​​at all locations.

[0090] Furthermore, the weight matrix w mk The construction method of w is usually based on the spatial proximity and / or fluid dynamics relationship between different pipe segments in the pipeline network, quantifying the degree of mutual influence between each pipe segment. In short, w mk It reflects the strength of the interaction between pipe segments m and k, which can be defined by geographic adjacency, fluid connectivity or other engineering criteria.

[0091] It should be noted that the design of the Moran's index calculation formula is based on spatial autocorrelation analysis. The Moran's index is used to evaluate the spatial correlation of pipeline health values ​​at different locations, revealing the spatial clustering characteristics of health value distribution.

[0092] Based on the secondary analysis results, the comprehensive pipeline health value abnormal scoring function is defined and expressed as:

[0093]

[0094] Among them, S A (x, y, t) represents the comprehensive pipeline health value anomaly score at the location (x, y) and time point t, τ represents the threshold of pipeline health value density estimation, which is used to identify density anomalies, and I e The threshold representing the level of spatial autocorrelation, used to identify spatial autocorrelation anomalies, ΔA t Indicates the rate of change of pipeline health value, A t-1 Indicates the pipeline health value at the previous time point;

[0095] Furthermore, the threshold τ of pipeline health value density estimation is determined based on historical data and expert experience, aiming to distinguish normal health value density from abnormal density. e The determination is based on calculating the mean and standard deviation of the historical Moran index to form a baseline that reflects the spatial autocorrelation level of health values ​​under normal operating conditions. e Add several standard deviations to the baseline Moran's index.

[0096] It should be noted that the basis for designing the comprehensive pipeline health value anomaly scoring function formula is to quantify the anomaly score by integrating the health value density, time series anomaly and spatial autocorrelation anomaly to guide maintenance decisions.

[0097] Based on the comprehensive pipeline health value anomaly scoring function, the areas where the pipeline health value anomaly score increases are located, marked as potential fault points, and a fault marking map is created.

[0098] Based on the fault marking map, the maintenance team is notified to enter the site, and the maintenance team performs repairs in a timely manner according to the location and nature of the fault point;

[0099] After the repair is completed, a quality inspection is carried out to ensure that the fault has been completely resolved without leaving any safety hazards, and the repair process is recorded.

[0100] It should be noted that secondary analysis can accurately locate fault points and improve the accuracy of fault diagnosis through deep mining in spatial and temporal dimensions. Combining the heat map of geographical layout and time series analysis, it can reveal the law of pipeline health changes and assist the maintenance team to respond quickly. By defining the comprehensive pipeline health value abnormality scoring function, a quantitative evaluation of abnormal conditions is achieved, guiding the rational allocation of maintenance resources, and ensuring the efficiency and pertinence of maintenance work.

[0101] S5. Automatically generate operation reports based on response measures.

[0102] Integrate fault marking maps and recorded maintenance processes to generate detailed reports for each fault point, including a specific description of the fault, possible causes, recommended solutions and estimated repair time. Combine reports from all fault points to analyze fault frequencies and patterns, evaluate maintenance efficiency, and merge reports from all individual fault points into a comprehensive operation report, including a fault overview, key findings, overall maintenance efficiency, and recommendations for improvement. Use automated tools to automatically generate operation reports, which should clearly and accurately display the status of the fault point, maintenance activities, and overall system performance.

[0103] It should be noted that the automatically generated operation report summarizes the specific information of the fault point and the maintenance process, which facilitates the management to grasp the overall maintenance status of the pipeline, and also provides valuable historical data for future fault prediction and prevention. This function simplifies the report preparation process, saves human resources, and improves management efficiency.

[0104] In summary, the present invention realizes all-round real-time monitoring of pipelines by integrating multiple sensors, ensuring rich and accurate data, and laying the foundation for intelligent monitoring. Advanced algorithms are used to convert pipeline data into health values, keenly capture state changes, quantify health conditions, assist early warning mechanisms, and significantly improve risk prediction capabilities. The application of edge computing technology greatly shortens response time, handles exceptions in real time, ensures data security through encryption and blockchain, and enhances system resilience. Secondary analysis deeply mines information in the time and space dimensions, accurately diagnoses faults, optimizes resource allocation, accelerates the maintenance process, and ensures stable system operation. Automatically generate operation reports, systematically sort out fault details and maintenance records, provide data support for decision-making, simplify management processes, and improve overall operation and maintenance efficiency. In summary, this innovative solution significantly enhances the intelligent monitoring, rapid response, and efficient management capabilities of pipeline systems, greatly reduces operational risks, and is a major advancement in the field of pipeline operation and maintenance.

[0105] Example 2

[0106] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of a smart pipeline monitoring system based on the Internet of Things is provided.

[0107] In order to verify the effectiveness of the IoT-based smart pipeline monitoring system described in the present invention, a 10-kilometer compressed air pipeline was selected as the research object. The pipeline is divided into 10 monitoring sections, each 1 kilometer long, numbered S1 to S10. A variety of sensors including pressure sensors, temperature sensors, flow meters, vibration sensors, and acoustic sensors are deployed at key locations in each monitoring section. In addition, edge computing devices are set up along the pipeline to process data from sensors in real time and define preliminary analysis thresholds based on historical data.

[0108] During the experiment, the pipeline was continuously monitored for one month. During the monitoring process, hourly pressure, temperature, flow rate, vibration frequency and sound data were recorded, and these raw data were standardized. Then, the pipeline health value of each monitoring section was calculated based on the standardized data. When the pipeline health value of a monitoring section was detected to be lower than the set preliminary analysis threshold, the preliminary processing procedure was triggered, including recording abnormal data, closing the gates adjacent to the abnormal area, and other operations. Furthermore, the abnormal data was secondary analyzed to identify potential failure points and take corresponding response measures.

[0109] The details are shown in Table 1:

[0110] Table 1 Experimental record table

[0111]

[0112]

[0113]

[0114] From the data in Table 1, it can be observed that the pipeline health value varies with time and monitoring segments. For example, in the S1 monitoring segment, from August 1 to August 4, the pipeline health value showed a slight downward trend, from 0.87 to 0.85. Although this decline is small, it may still indicate potential problems. In addition, monitoring segments S2 to S4 also showed a similar trend of change.

[0115] It is worth noting that on the third day of the experiment (2024-08-03), the pipeline health value of the S4 monitoring section suddenly dropped to 0.86, indicating that the pipeline in this monitoring section may have an abnormal situation. Based on this, the edge computing device automatically triggered the preliminary processing procedure, recorded the abnormal data, and closed the gate adjacent to the S4 monitoring section to prevent possible rupture risks. At the same time, the abnormal data was sent to the cloud server for further analysis.

[0116] Subsequent secondary analysis revealed that the decline in pipeline health values ​​in the S4 monitoring section was related to the increase in vibration frequency in the area. Specifically, the vibration frequency increased from 0.11 mm / s on August 1 to 0.13 mm / s on August 2, a change that may have been caused by changes in the external environment of the pipeline. By defining a comprehensive pipeline health value anomaly scoring function and calculating the Moran index, the S4 monitoring section was identified as a potential fault point. A maintenance team was subsequently dispatched to the area, where repairs were carried out in a timely manner and the fault was completely resolved.

[0117] In summary, the IoT-based smart pipeline monitoring system of the present invention can effectively monitor the health status of pipelines and take prompt action when abnormalities are found, thus avoiding possible safety hazards. Compared with traditional manual monitoring methods, the present invention not only improves monitoring efficiency, but also enhances the ability to comprehensively assess the health status of pipelines, thereby significantly improving the safety and reliability of pipeline transportation. In addition, the present invention realizes real-time monitoring of pipeline health status and early warning of faults by combining edge computing technology with cloud data analysis, demonstrating its innovation and practicality in the field of pipeline monitoring.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A smart pipeline monitoring system based on the Internet of Things, characterized by: include, The data acquisition module is responsible for deploying various sensors to obtain pipeline data; The pipeline health calculation module is responsible for calculating the pipeline health value based on the pipeline data; The preliminary analysis module is responsible for conducting preliminary analysis and processing of pipeline health based on pipeline health values ​​using edge computing technology; The secondary analysis module is responsible for conducting secondary analysis based on the preliminary analysis results, identifying potential failure points, and taking corresponding measures; The report generation module is responsible for automatically generating operation reports based on response measures.

2. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 1, characterized in that: The multiple sensors include pressure sensors, temperature sensors, flow meters, vibration sensors and acoustic sensors; The pipeline data includes pressure, temperature, flow rate, vibration frequency and sound.

3. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 1, characterized in that: Based on the pipeline data, the pipeline health value is calculated, including the following steps: Perform Z-score standardization on pipeline data; Based on the processed pipeline data, the pipeline health value is calculated and expressed as, Among them, A represents the pipeline health value, P represents the pressure after treatment, T represents the temperature after treatment, Q represents the flow rate after treatment, W represents the decibel value of the sound after treatment, V represents the vibration frequency after treatment, a represents the elastic sensitivity coefficient, b represents the reference offset, c represents the heat resistance index, φ' represents the vibration frequency coefficient, α represents the pressure enhancement coefficient, and β represents the temperature enhancement coefficient.

4. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 3 is characterized by: Based on the pipeline health value, edge computing technology is used to conduct a preliminary analysis of pipeline health, including the following steps: Set up edge computing devices on the pipeline and define preliminary analysis thresholds based on statistical analysis of historical data; When the pipeline health value is greater than or equal to the preliminary analysis threshold, it indicates that the pipeline is safe; When the pipeline health value is less than the preliminary analysis threshold, it indicates that there is an abnormality in the pipeline.

5. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 4, characterized in that: Based on the preliminary analysis results, preliminary processing is carried out, including the following steps: When the pipeline is safe, continue to monitor the pipeline health status; When an abnormality is detected, the abnormal data is recorded, and the edge computing device immediately executes the gate control instructions to prevent dangers caused by potential ruptures, activates the emergency response plan, isolates the faulty section by closing the gates adjacent to the abnormal area, and reduces the impact on the entire pipeline network.

6. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 5, characterized in that: The edge computing device marks the abnormal data and sends it to the cloud server through an encrypted connection, using encryption technology and blockchain to record the data transmission process.

7. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 6, characterized in that: Based on the results of the preliminary analysis, a secondary analysis was conducted, including the following steps: When an anomaly is found, the pipeline health value is mapped to the geographical layout of the pipeline network to create a heat map of the pipeline health value. The density of the data points around a given location is used to obtain the pipeline health value density estimate, which is expressed as, in, represents the pipeline health value density estimate at the position (x, y), A i represents the pipeline health value of the i-th observation point, (x, y) represents the geographical location x and y, n represents the number of observation points, (x i ,y i ) represents the position coordinates of the i-th observation point, i represents the index of the number of observation points, and σ represents the bandwidth; The autoregressive moving average model is used to identify the regularity and abnormal trend of pipeline health value changes over time, expressed as, φ(B)A t =θ(B)ε t -or t ; Among them, B represents the backshift operator, A t represents the pipeline health value at time point t, φ(B) represents the autoregressive polynomial, φ(B)=1-φ1B-…-φ p B p , where p represents the order of the autoregressive term, φ1,…,φ p represents the linear coefficient of the autoregressive term, θ(B) represents the moving average polynomial, θ(B)=1+θ1B+…+θ q B q , where θ1,…,θ q represents the linear coefficient of the moving average term, q represents the order of the moving average term, and ε t represents a white noise sequence, B q represents the qth power of the backshift operator, B p represents the p-th power of the backshift operator, η t represents the additional error value; Spatial autocorrelation analysis is used to evaluate the spatial correlation between pipeline health values ​​at different locations, and the Moran index is calculated to quantify the degree of spatial autocorrelation, which is expressed as, Among them, I represents the Moran index, S represents the sum of all elements of the weight matrix, and A k represents the pipeline health value at position k, A m represents the pipeline health value at position m, w mk Represents the elements of the spatial weight matrix, k represents the index variable of the second position, m represents the index variable of the first position, Indicates the average of pipeline health values ​​at all locations.

8. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 7, characterized in that: Based on the secondary analysis results, identify potential failure points, including the following steps: Based on the secondary analysis results, the comprehensive pipeline health value abnormal scoring function is defined and expressed as: Among them, S A (x, y, t) represents the comprehensive pipeline health value anomaly score at the location (x, y) and time point t, τ represents the threshold of pipeline health value density estimation, I e The threshold value representing the level of spatial autocorrelation, ΔA t Indicates the rate of change of pipeline health value, A t-1 Indicates the pipeline health value at the previous time point; Based on the comprehensive pipeline health value anomaly scoring function, the areas where the pipeline health value anomaly score increases are located, marked as potential fault points, and a fault marking map is created.

9. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 8, characterized in that: Based on the identification results, response measures are implemented, including the following steps: Based on the fault marking map, the maintenance team is notified to enter the site, and the maintenance team performs repairs in a timely manner according to the location and nature of the fault point; After the repair is completed, a quality inspection is carried out to ensure that the fault has been completely resolved without leaving any safety hazards, and the repair process is recorded.

10. The smart pipeline monitoring system based on the Internet of Things as claimed in claim 9, characterized in that: Based on the response measures, an operation report is automatically generated, including the following steps: Integrate fault marking maps and recorded maintenance processes to generate detailed reports for each fault point, and automatically generate operation reports by combining reports of all fault points.

Images