A data analysis-based safety monitoring system and method for gas pipelines
By installing movable sensors at key nodes of gas pipelines, combined with data analysis and model optimization, real-time and accurate safety monitoring of gas pipelines has been achieved, solving the safety hazards and high costs of traditional methods and improving monitoring efficiency and reliability.
Patent Information
- Application Number
- CN202411198560.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2044-08-29
AI Technical Summary
Traditional gas pipeline monitoring methods are difficult to achieve real-time and accurate safety monitoring, posing safety hazards. Furthermore, they rely on manual inspections and fixed sensors, which are costly and have limited coverage.
A data-driven gas pipeline safety monitoring system is adopted. By installing mobile sensors at key nodes, pressure, temperature, flow rate and gas concentration data are collected in real time. Anomaly detection functions and time series analysis are used to establish a safety monitoring model for real-time monitoring and early warning. The monitoring parameters are optimized through model training.
It improves the real-time performance and accuracy of gas pipeline monitoring, reduces the probability of missed and false alarms, reduces human error, enhances the reliability and stability of the system, and reduces operational risks and costs.
Smart Images

Figure CN119202580B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of gas pipeline safety technology, and in particular to a gas pipeline safety monitoring system, method, electronic device, and non-transitory computer-readable storage medium based on data analysis. Background Technology
[0002] Currently, the safety monitoring of gas pipelines is a crucial aspect of ensuring public safety and stable energy supply. Traditional gas pipeline monitoring methods primarily rely on regular inspections, manual checks, and the installation of fixed sensors. These methods can detect external damage, corrosion, and leaks in the pipelines, and ensure their normal operation through manual inspections or regular maintenance. In addition, some regions have adopted buried sensors and gas detectors to monitor changes in gas concentration around the pipelines in real time, providing early warnings of potential safety hazards.
[0003] However, the frequency of regular inspections and manual checks is low, making it difficult to detect sudden leaks or damage in real time, posing significant safety hazards. Secondly, the installation and maintenance costs of fixed sensors are high, and their coverage is limited, making it difficult to comprehensively monitor all critical nodes in the pipeline. Finally, traditional methods rely on manual analysis and judgment, making them susceptible to human factors and hindering efficient and accurate safety monitoring. Summary of the Invention
[0004] This invention addresses the technical problems existing in the prior art by providing a data analysis-based gas pipeline safety monitoring system, method, electronic device, and non-transitory computer-readable storage medium that can improve the accuracy and efficiency of gas pipeline safety monitoring.
[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:
[0006] This invention provides a gas pipeline safety monitoring system based on data analysis, the system comprising:
[0007] The data acquisition module is used to install movable sensors at key nodes of the gas pipeline to collect the pressure, temperature, flow rate inside the gas pipeline and the gas concentration in the surrounding environment.
[0008] An anomaly identification module is used to analyze the pipeline data from the sensor in real time and identify abnormal conditions in the gas pipeline through an anomaly detection and discrimination function.
[0009] The model building module is used to predict future data of the gas pipeline through time series analysis and to build a safety monitoring model based on the historical and real-time data of the gas pipeline.
[0010] The data adjustment module is used to adjust the pipeline data of the gas pipeline after detecting an anomaly in the gas pipeline or predicting a potential risk.
[0011] The model training module is used to continue monitoring the gas pipeline to obtain monitoring data, and to adjust and optimize the parameters of the monitoring model based on the monitoring data to obtain an optimized safety monitoring model.
[0012] The safety monitoring module is used to perform safety monitoring on the gas pipeline based on the optimized safety monitoring model.
[0013] Optionally, the anomaly detection module is further configured to:
[0014] Obtain different pipeline data of the gas pipeline at preset times;
[0015] Based on the different pipeline data of the gas pipeline at the current time t, calculate the average value and standard deviation of the pipeline data for each type;
[0016] Obtain the weights of the covariance matrix among the pipeline data, and the corresponding adaptive weighting coefficients;
[0017] Based on the different pipeline data of the gas pipeline at the current time t, the average value and standard deviation of each type of pipeline data, the weight of the covariance matrix and the adaptive weighting coefficient, the anomaly detection discrimination function is constructed.
[0018] The abnormal detection value of the gas pipeline is determined according to the abnormal detection discrimination function, and the abnormal detection of the gas pipeline is performed based on the abnormal detection value.
[0019] Optionally, the anomaly detection function is expressed as:
[0020]
[0021] Among them, X i (t), X j (t), X k (t) represents the different pipeline data at time t, μ i μ j μ k These represent the average values of various pipeline data, σ i σ j σ k W represents the standard deviation of various pipeline data. ij δ represents the weights of the covariance matrix among the data from each pipeline. k These are adaptive weighting coefficients.
[0022] Optionally, the model building module is further configured to:
[0023] Obtain the pipeline data at the current time t, and the historical pipeline data up to time h;
[0024] Obtain the exogenous variables generated by external factors of the gas pipeline;
[0025] Obtain the hysteresis term of the pipeline data before time s;
[0026] Based on the pipeline data at the current time t, the historical pipeline data before time h, the exogenous variables, and the lag error term, a safety monitoring model is constructed to predict future data of the gas pipeline.
[0027] Optionally, the future data of the gas pipeline is represented as follows:
[0028]
[0029] in, These are the autoregressive coefficients, where t, h, and s are all time points, and Z is the autoregressive coefficient. v (t) is an exogenous variable, λ v These are the weighting coefficients of the exogenous variables, η1 is the acceleration coefficient, and θ is the weighting coefficient of the exogenous variables. s These are the moving average coefficients, and ∈(ts) is the lag error term. It is the second derivative, and γ is the velocity coefficient. It is the first derivative, ∈ t D(t) is the random error term, D(t) is the pipeline data at the current time t, and D(th) represents the historical pipeline data at the previous time h.
[0030] Optionally, the data adjustment module is further configured to:
[0031] Obtain the current value and set value of each of the pipeline data;
[0032] Calculate the first difference between the current value and the set value for each of the pipeline data;
[0033] Obtain the feedforward variable for each of the exogenous variables at a delay τ. j The variable value after time step;
[0034] The multiple first differences are summed, integrated, and differentiated respectively, and combined with each of the variable values to obtain the adjusted pipeline data.
[0035] Optionally, the adjusted pipeline data is represented as follows:
[0036]
[0037] Among them, X i (t) is the current value of the i-th pipeline data, X i,setpoint It is Xi The set value of (t), K p,i K i,i K d,i These are the proportional, integral, and differential coefficients, respectively, τ. j At that moment, z j (t+τ j ) is the feedforward variable at a delay of τ j The value after f j It is the feedforward compensation coefficient, N is the total number of pipeline data, and X is the feedforward compensation coefficient. i (t)-X i,setpoint It is the first difference.
[0038] Optionally, the model training module is further configured to:
[0039] Calculate the mean and standard deviation of the Gaussian kernel in the safety monitoring model;
[0040] Construct the corresponding Gaussian kernel function based on the mean and the standard deviation;
[0041] Based on the monitoring data, the loss function of the safety monitoring model, and the Gaussian kernel function, gradient descent and Bayesian optimization are performed on the old parameters of the safety monitoring model to obtain the optimized safety monitoring model with updated parameters.
[0042] Optionally, the update parameters of the safety monitoring model are expressed as follows:
[0043]
[0044] Where η² is the learning rate, Q is the number of Gaussian kernels, and θ old These are the old parameters of the model, θ new These are the model's update parameters, L(θ) is the loss function, σ is the uncertainty, n is the current iteration number, and α is the model's update parameters. k It is the Bayesian optimization weight of the k-th Gaussian kernel, μ k σ k These are the mean and standard deviation of the k-th Gaussian kernel.
[0045] This invention also provides a data analysis-based method for safety monitoring of gas pipelines, the method comprising:
[0046] Movable sensors are installed at key nodes of the gas pipeline to collect data on the pressure, temperature, flow rate inside the gas pipeline, and the gas concentration in the surrounding environment.
[0047] The system analyzes the pipeline data from the sensors in real time and identifies abnormal conditions in the gas pipeline using an anomaly detection and discrimination function.
[0048] Predict future data of the gas pipeline through time series analysis, and establish a safety monitoring model based on the historical and real-time data of the gas pipeline;
[0049] After detecting an anomaly in the gas pipeline or predicting a potential risk, the pipeline data of the gas pipeline is adjusted.
[0050] The gas pipeline is monitored to obtain monitoring data, and the parameters of the monitoring model are adjusted and optimized based on the monitoring data to obtain an optimized safety monitoring model;
[0051] The gas pipeline is monitored for safety based on the optimized safety monitoring model.
[0052] Furthermore, to achieve the above objectives, the present invention also proposes an electronic device, comprising: a memory for storing computer software programs; and a processor for reading and executing the computer software programs, thereby realizing the data analysis-based gas pipeline safety monitoring method described above.
[0053] Furthermore, to achieve the above objectives, the present invention also proposes a non-transitory computer-readable storage medium storing a computer software program, which, when executed by a processor, implements a data analysis-based gas pipeline safety monitoring method as described above.
[0054] The beneficial effects of this invention are:
[0055] (1) By introducing mobile sensors and multivariate data analysis, this invention can monitor key parameters of gas pipelines (such as pressure, temperature, flow rate, etc.) in real time. Compared with traditional methods that rely on manual inspection and fixed sensors, this solution significantly improves the real-time performance of monitoring and effectively reduces the possibility of safety hazards.
[0056] (2) This invention employs a multivariate anomaly detection function, combined with higher-order moments, covariance matrices, and adaptive weighting, which enables more accurate detection of minute anomalies and reduces the probability of missed and false alarms. This high-precision detection method can promptly identify potential safety risks and improve the overall safety of the pipeline system.
[0057] (3) The present invention reduces the possibility of human error and judgment mistakes by using automated and intelligent monitoring and analysis methods, thereby improving the overall reliability and stability of the system.
[0058] In summary, this invention combines advanced technologies such as real-time monitoring, high-precision anomaly detection, intelligent prediction and early warning, automated response, self-learning and optimization, significantly improving the safety monitoring capabilities of gas pipelines, reducing the risks and costs of system operation, and providing a more effective guarantee for the safe operation of gas pipelines. Attached Figure Description
[0059] Figure 1 A scenario diagram illustrating a data analysis-based gas pipeline safety monitoring method provided by this invention;
[0060] Figure 2 A flowchart of a gas pipeline safety monitoring method based on data analysis provided by the present invention;
[0061] Figure 3 A schematic diagram of a gas pipeline safety monitoring system based on data analysis provided by the present invention;
[0062] Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;
[0063] Figure 5 This is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. Detailed Implementation
[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0065] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0066] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.
[0067] Please see Figure 1 , Figure 1 This is a scenario diagram illustrating a data analysis-based gas pipeline safety monitoring method provided by the present invention. (Example) Figure 1 As shown, the terminal and server are connected via a network, such as a wired or wireless network. The terminal can include, but is not limited to, portable devices such as mobile phones and tablets with various network platform applications installed, as well as fixed terminals such as computers, kiosks, and advertising machines. The server provides users with various business services, including service push servers and user recommendation servers.
[0068] It should be noted that, Figure 1 The scenario diagram of a gas pipeline safety monitoring method based on data analysis shown is merely an example. The terminals, servers, and application scenarios described in the embodiments of the present invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of the present invention, and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. As those skilled in the art will know, with the evolution of the system and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.
[0069] The terminal can be used for:
[0070] Movable sensors are installed at key nodes of the gas pipeline to collect data on the pressure, temperature, flow rate inside the gas pipeline, and the gas concentration in the surrounding environment.
[0071] The system analyzes the pipeline data from the sensors in real time and identifies abnormal conditions in the gas pipeline using an anomaly detection and discrimination function.
[0072] Predict future data of the gas pipeline through time series analysis, and establish a safety monitoring model based on the historical and real-time data of the gas pipeline;
[0073] After detecting an anomaly in the gas pipeline or predicting a potential risk, the pipeline data of the gas pipeline is adjusted.
[0074] The gas pipeline is monitored to obtain monitoring data, and the parameters of the monitoring model are adjusted and optimized based on the monitoring data to obtain an optimized safety monitoring model;
[0075] The gas pipeline is monitored for safety based on the optimized safety monitoring model.
[0076] Please see Figure 2 , Figure 2 This is a schematic diagram of a gas pipeline safety monitoring system based on data analysis provided by the present invention.
[0077] like Figure 2As shown in the figure, a gas pipeline safety monitoring system based on data analysis proposed in this embodiment of the invention includes:
[0078] The data acquisition module 201 is used to install movable sensors at key nodes of the gas pipeline to collect the pressure, temperature, flow rate inside the gas pipeline and the gas concentration in the surrounding environment.
[0079] This invention enables real-time and accurate monitoring of various parameters, i.e., pipeline data, both inside and around the gas pipeline, by installing movable sensors at key nodes of the pipeline. In some embodiments, the pipeline data includes internal pressure, temperature, and flow rate, as well as the gas concentration in the surrounding environment. By collecting and analyzing this data, the safety monitoring capabilities of gas pipelines can be effectively improved, preventing accidents from occurring.
[0080] In some embodiments, critical nodes in a gas pipeline typically refer to areas in the pipeline system that are prone to failure and require close monitoring, such as pipe connections, bends, pressure change points, and flow regulation points. The operational status of these nodes is crucial to the safety of the entire pipeline system and therefore requires special attention and monitoring.
[0081] Compared to fixed sensors, mobile sensors offer greater flexibility, allowing them to be moved and redeployed between different nodes as needed. This flexibility enables the monitoring system to respond quickly to new situations or emergencies that arise during pipeline operation.
[0082] By moving sensors between different key nodes, the monitoring coverage can be effectively expanded, ensuring that all critical parts of the pipeline system can be monitored in real time. This method reduces monitoring blind spots and improves overall monitoring efficiency.
[0083] Compared to installing fixed sensors in every possible location, using mobile sensors can significantly reduce the cost of sensor installation and maintenance. Extensive monitoring can be achieved with only a small number of sensors, thus saving costs while ensuring monitoring effectiveness.
[0084] The following details several types of pipeline data from this invention. Pressure: The internal pressure of a gas pipeline is one of the key parameters reflecting its operating status. Excessively high or low pressure can lead to safety hazards, such as pipeline rupture or gas leakage. By monitoring pressure changes in real time, the system can promptly detect anomalies and make adjustments.
[0085] Temperature: Temperature variations affect the flowability of natural gas and the structural stability of pipelines. Abnormal temperature fluctuations can lead to changes in gas flow rate or stress on pipeline materials, potentially causing safety issues. Real-time temperature monitoring can help identify potential risks.
[0086] Flow rate: The flow rate of natural gas directly affects the efficiency and safety of the pipeline system. Abnormal flow rates usually indicate potential leaks, blockages, or other malfunctions in the system. Therefore, real-time flow monitoring is crucial for ensuring the normal operation of the pipeline.
[0087] Gas concentration: Monitoring the gas concentration in the environment surrounding the pipeline, especially the concentration of combustible gases, can help detect signs of pipeline leaks early. By monitoring gas concentration, the system can provide early warnings and prevent leaks from occurring.
[0088] By installing movable sensors at key nodes of the gas pipeline using the above methods, this invention can construct a flexible and efficient safety monitoring system by collecting data on pressure, temperature, flow rate inside the pipeline, and gas concentration in the surrounding environment. This system can not only monitor the pipeline's operating status in real time but also provide timely warnings of potential safety hazards through data analysis and prediction, ultimately improving the safety and operational efficiency of the gas pipeline.
[0089] The anomaly identification module 202 is used to analyze the pipeline data of the sensor in real time and identify the abnormal situation of the gas pipeline through the anomaly detection discrimination function.
[0090] In some embodiments, the anomaly detection module 202 is further configured to:
[0091] Obtain different pipeline data of the gas pipeline at preset times;
[0092] Based on the different pipeline data of the gas pipeline at the current time t, calculate the average value and standard deviation of the pipeline data for each type;
[0093] Obtain the weights of the covariance matrix among the pipeline data, and the corresponding adaptive weighting coefficients;
[0094] Based on the different pipeline data of the gas pipeline at the current time t, the average value and standard deviation of each type of pipeline data, the weight of the covariance matrix and the adaptive weighting coefficient, the anomaly detection discrimination function is constructed.
[0095] The abnormal detection value of the gas pipeline is determined according to the abnormal detection discrimination function, and the abnormal detection of the gas pipeline is performed based on the abnormal detection value.
[0096] The anomaly detection function can be expressed as:
[0097]
[0098] Among them, X i (t), X j (t), X k (t) represents the different pipeline data at time t, μj μ j μ k These represent the average values of various pipeline data, σ i σ j σ k W represents the standard deviation of various pipeline data. ij δ represents the weights of the covariance matrix among the data from each pipeline. k These are adaptive weighting coefficients.
[0099] In specific implementation, F anomaly (t) is the anomaly detection value of the anomaly detection function.
[0100] X i (t), X j (t), X k (t) represents different pipeline data at time t, also known as pipeline parameters or monitoring data. It represents the actual observed values of different monitoring parameters (such as pressure, temperature, flow rate, etc.) at time t. These parameters can come from multiple sensors in the pipeline, and each parameter reflects a certain aspect of the pipeline system's state.
[0101] μ i μ j μ k These represent the average values of the data for each pipeline, and respectively represent the pipeline data X. i (t), X j (t), X k The historical average value of (t). The historical average value is usually obtained by statistical calculation of monitoring data over a period of time, reflecting the expected value of each parameter under normal operating conditions.
[0102] σ i σ j σ k The standard deviation represents the volatility and dispersion of the data for each pipeline. A larger standard deviation indicates greater volatility in the data.
[0103] W ij The weights W represent the weights of the covariance matrix between the parameters. The covariance matrix reflects the relationship between the two parameters. ij This indicates the relative importance of the relationship between two parameters in anomaly detection. The choice of weights affects the overall sensitivity of anomaly detection.
[0104] δ k These are adaptive weighting coefficients used to control the influence of higher-order moments (such as skewness) in anomaly detection. The adaptive weighting coefficients can be automatically adjusted according to actual conditions, ensuring that the formula maintains high detection accuracy under various environments.
[0105] Specifically, (X)i (t)-μ i ) and (X j (t)-μ j ) represents parameter X i (t), X j The deviation between (t) and their respective averages is calculated by multiplying the two parameters to determine the degree of simultaneous deviation from the average, revealing their coordinated change.
[0106] σ i σ j It is a standardization factor used to eliminate the influence of different dimensions of parameters, so that the covariances between different parameters can be directly compared.
[0107] W ij This assigns greater influence to certain parameters in anomaly detection. For example, if the correlation between certain parameters is considered very important in historical data, then W... ij The value will be higher, thus enhancing their ability to detect anomalies (F). anomaly The contribution of (t).
[0108] E[(X k )t)-μ k ) 3 ] represents parameter X k The third moment of (t), also known as skewness, reflects the asymmetry of the data. A large skewness indicates that the data distribution deviates significantly from the mean, potentially suggesting anomalies. This is a standardization factor used to make the third moment dimensionless for comparison with other parameters. δ k Used to control the impact of skewness on overall anomaly detection. For certain sensitive monitoring parameters, δ k They can be set higher to enhance their role in anomaly detection.
[0109] This formula, by combining the covariance-weighted component and the higher-order moment-weighted component, can simultaneously capture the linear correlation and asymmetry between parameters, making anomaly detection more comprehensive and accurate. Taking the square root is to ensure the anomaly detection value F... anomaly The result of (t) is consistent with the original data units, and it is also helpful to define a reasonable threshold to judge anomalies.
[0110] In summary, this invention provides an efficient anomaly detection method using multivariate analysis and higher-order moment analysis. Its advantage lies in its ability to simultaneously consider the correlation between multiple parameters and deviations in data distribution, thereby more accurately identifying potential anomalies during gas pipeline monitoring. This method is particularly suitable for real-time monitoring in multivariate, big data environments, significantly improving system safety and stability.
[0111] The model building module 203 is used to predict future data of the gas pipeline through time series analysis and to establish a safety monitoring model based on the historical and real-time data of the gas pipeline.
[0112] In some embodiments, the model building module 203 is further configured to:
[0113] Obtain the pipeline data at the current time t, and the historical pipeline data up to time h;
[0114] Obtain the exogenous variables generated by external factors of the gas pipeline;
[0115] Obtain the hysteresis term of the pipeline data before time s;
[0116] Based on the pipeline data at the current time t, the historical pipeline data before time h, the exogenous variables, and the lag error term, a safety monitoring model is constructed to predict future data of the gas pipeline.
[0117] In some embodiments, future data for gas pipelines are represented as follows:
[0118]
[0119] in, These are the autoregressive coefficients, where t, h, and s are all time points, and Z is the autoregressive coefficient. v (t) is an exogenous variable, λ v These are the weighting coefficients of the exogenous variables, η1 is the acceleration coefficient, and θ is the weighting coefficient of the exogenous variables. s These are the moving average coefficients, and ∈(ts) is the lag error term. It is the second derivative, and γ is the velocity coefficient. It is the first derivative, ∈ t D(t) is the random error term, D(t) is the pipeline data at the current time t, and D(th) represents the historical pipeline data at the previous time h.
[0120] In the specific implementation, These are autoregressive coefficients, used to describe the impact of historical data on current predictions. The autoregressive coefficients determine the weight of data from the previous h time points in the predicted value. Specifically, the magnitude of the coefficient reflects the degree to which historical data contributes to the future. t, h, and s are all time points.
[0121] Z v (t) is an exogenous variable, representing the impact of external factors (such as ambient temperature, pipeline load changes, etc.) at time t. These external factors may have a significant impact on the state of gas pipelines, and therefore need to be included in the prediction model.
[0122] λ vThese are the weighting coefficients of the exogenous variable, used to control for the exogenous variable Z. v (t) represents the degree of influence of exogenous variables on the prediction results. Different exogenous variables may have different impacts on the prediction results under different circumstances; the weighting coefficient λ... v The magnitude of these effects can be adjusted.
[0123] η1 is the acceleration coefficient, used to measure the contribution of the acceleration of data change (i.e., the second derivative) to the prediction.
[0124] θ s It is a moving average coefficient used to smooth the impact of the lag error term. It quantifies the contribution of the lag error term ∈ (ts) to the forecast result. The moving average coefficient can capture the impact of historical errors on the current forecast.
[0125] ∈(ts) is the lag error term, representing the prediction error at time s. The lag error term is used to adjust the prediction model to take into account the influence of historical prediction errors, thereby improving the robustness of the model.
[0126] It is the second derivative, representing the accelerating trend of data change. It reflects how the speed of data change changes over time and is a key factor in predicting rapidly changing scenarios.
[0127] γ is the velocity coefficient, used to measure the contribution of the rate of change of data (i.e., the first derivative) to the prediction. The velocity coefficient γ determines the magnitude of the influence of the first derivative on the predicted value.
[0128] It is the first derivative, representing the rate of change of data over time. This term is used to capture the linear trend of data and can predict how data will change steadily over time.
[0129] ∈ is the random error term, used to capture random fluctuations or unmodeled factors in the prediction. This term reflects the uncertainty in the model, which is usually unavoidable and must be taken into account for random errors in the prediction results.
[0130] D(th) represents the actual observation data at time h. By analyzing historical data over a period of time (i.e., multiple past measurements), the state at the current or future time can be estimated.
[0131] Specifically, The autoregressive part considers the observed data D(th) at historical time th and utilizes the autoregressive coefficients. This contributes to the prediction of the current time t+Δt. This part is responsible for making predictions based on historical trends. For example, if a parameter has shown a clear trend in the past few times, the autoregressive part can accurately reflect this trend and carry it into future predictions.
[0132] The moving average part considers the lag error term ∈(ts) at past time s and uses the moving average coefficient θ. s These errors are smoothed to adjust the current forecast values. This part corrects forecast bias by introducing historical errors, making the forecast model more robust.
[0133] The exogenous variable section introduces external factors Z that may affect the prediction results. v (t), through the weighting coefficient λ v This allows for adjustments to the impact of these external factors on the forecast values. This part is very important because the operation of gas pipelines is not only affected by internal conditions but may also be disturbed by changes in the external environment. The introduction of exogenous variables makes the forecast more comprehensive and accurate.
[0134] This part incorporates the first derivative of the data. and second derivative The system separately captures changes in velocity and acceleration. By using the velocity coefficient γ and acceleration coefficient η1, the impact of these rates of change on the predicted values can be flexibly adjusted, making it particularly suitable for handling nonlinear variations. This part can better capture the rapidly changing dynamic characteristics of the pipeline system, improving the accuracy of the prediction.
[0135] Through the above methods, this invention provides a complex and flexible time series forecasting model by combining autoregression, moving average, exogenous variable analysis, and derivative analysis. This model can fully consider the trends of historical data, changes in the external environment, and the dynamic characteristics of the data itself when predicting the future state of gas pipelines, thereby improving the accuracy and reliability of the prediction. This forecasting method is particularly suitable for the complex environment of gas pipeline systems, which are affected by multiple factors, and helps to provide timely warnings of potential risks, ensuring the safe operation of the pipeline.
[0136] The data adjustment module 204 is used to adjust the pipeline data of the gas pipeline after detecting an abnormality in the gas pipeline or predicting a potential risk.
[0137] In some embodiments, the data adjustment module 204 is further configured to:
[0138] Obtain the current value and set value of each of the pipeline data;
[0139] Calculate the first difference between the current value and the set value for each of the pipeline data;
[0140] Obtain the feedforward variable for each of the exogenous variables at a delay τ. j The variable value after time step;
[0141] The multiple first differences are summed, integrated, and differentiated respectively, and combined with each of the variable values to obtain the adjusted pipeline data.
[0142] In some embodiments, the adjusted pipeline data is represented as follows:
[0143]
[0144] Among them, X i (t) is the current value of the i-th pipeline data, X i,setpoint It is X i The set value of (t), K p,i K i,i K d,i These are the proportional, integral, and differential coefficients, respectively, τ. j At that moment, Z j (t+τ j ) is the feedforward variable at a delay of τ j The value after f j It is the feedforward compensation coefficient, N is the total number of pipeline data, and X is the feedforward compensation coefficient. i (t)-X i,setpoint It is the first difference.
[0145] In the specific implementation, X i (t) is the current value of the i-th control variable. The control variables are pipeline data, such as pressure, temperature, and flow rate. These variables directly reflect the real-time operating status of the pipeline system.
[0146] X i,setpoint It is X i The setpoint of (t) is the target setpoint of the i-th control variable. This value represents the ideal state or goal that the system is expected to achieve, and is usually determined based on safety, efficiency, or other key performance indicators.
[0147] K p,i K i,i K d,i These are the proportional, integral, and differential coefficients, respectively, where K p,i It is the proportional coefficient of the i-th control variable. The proportional control part is used to determine the current deviation, i.e., (X... i (t)-X i,setpoint The response of a linearly adjusted system. The proportional coefficient K. p,i This determines the direct impact of the current deviation on the adjustment amount.
[0148] K i,i It is the integral coefficient of the i-th control variable. The integral control part accumulates the deviation, that is, it controls the integral coefficient of (X). i (t)-X i,setpointThe system response is adjusted by time integration. This is particularly suitable for eliminating long-term deviations. The integral coefficient K... p,i This determines the impact of cumulative deviation on the adjustment amount.
[0149] K d,i This is the differential coefficient of the i-th control variable. The differential control part adjusts the system response by controlling the rate of change of the deviation (i.e., the time derivative of the deviation), helping to suppress rapidly changing disturbances or oscillations. Differential coefficient K p,i This determines the impact of the deviation change rate on the adjustment amount.
[0150] τ j It is a moment. Z j (t+τ j ) is the feedforward variable at a delay of τ j The value of the variable after the time delay τ is the j-th feedforward variable. j The value of the variable Z. Feedforward control is used to pre-adjust the system to respond to anticipated changes or disturbances. Feedforward variable Z j These may represent exogenous variables that represent external factors, such as ambient temperature and external pressure.
[0151] f j This is the feedforward compensation coefficient. It's used to adjust the contribution of the feedforward variable to the system response. Feedforward control incorporates known external influences and adjusts the compensation coefficient f using an appropriate factor. j This can effectively reduce the system's sensitivity to these disturbances.
[0152] N is the total number of control variables, representing the number of control variables involved in the formula. m is the total number of feedforward variables, representing the number of feedforward compensation variables involved in the formula.
[0153] K p,i ·(X i (t)-X i,setpoint The proportional control section is the foundation of PID control, using the current value X... i (t) and the set value X i,setpoint The system is adjusted based on the deviation between the two. This part of the adjustment is linear; that is, the greater the deviation, the greater the adjustment. The proportional coefficient K... p,i The size of this part determines its direct impact on the adjustment amount.
[0154] Integral control adjusts the system by accumulating the deviation, making it particularly suitable for eliminating static errors (i.e., long-term deviations). Integral control ensures that the system tends towards the setpoint over a long period. The integral coefficient k... i,i The magnitude of the cumulative deviation determines its contribution to the adjustment amount. It can help the system eliminate persistent small deviations, ensuring more precise control.
[0155] The differential control section adjusts the system based on the rate of change of the deviation. It can predict the trend of deviation change, thus making early corrections and suppressing rapid changes or oscillations in the system. The differential coefficient k... d,i The magnitude of this trend determines its impact on the adjustment amount, which helps improve the system's response speed and stability, especially in rapidly changing environments.
[0156] The feedforward compensation section takes into account the influence of external factors and delays them by τ. j The feedforward variable Z j (t+τ j This involves pre-tuning the system. This part can proactively address known external disturbances, thereby reducing their negative impact on the system. The feedforward compensation coefficient f... j This determines the strength of the influence of each feedforward variable on the system response.
[0157] This formula combines three classic control strategies—proportional, integral, and derivative—with advanced feedforward compensation to achieve precise automated regulation of gas pipeline systems. Proportional control: rapidly responds to current deviations and makes direct adjustments. Integral control: accumulates historical deviations to eliminate system errors over long periods. Derivative control: predicts deviation trends and prevents system oscillations. Feedforward control: pre-adjusts for external factors to reduce interference.
[0158] By comprehensively applying these control strategies, the system can precisely adjust key parameters in the gas pipeline, ensuring its safety and stability under various conditions. Feedforward compensation is particularly suitable for handling potentially delayed or anticipated disturbances, making the system response faster and more intelligent.
[0159] The model training module 205 is used to continue monitoring the gas pipeline to obtain monitoring data, and to adjust and optimize the parameters of the monitoring model based on the monitoring data to obtain an optimized safety monitoring model.
[0160] In some embodiments, the model training module 205 is further configured to:
[0161] Calculate the mean and standard deviation of the Gaussian kernel in the safety monitoring model;
[0162] Construct the corresponding Gaussian kernel function based on the mean and the standard deviation;
[0163] Based on the monitoring data, the loss function of the safety monitoring model, and the Gaussian kernel function, gradient descent and Bayesian optimization are performed on the old parameters of the safety monitoring model to obtain the optimized safety monitoring model with updated parameters.
[0164] In some embodiments, the update parameters of the security monitoring model are represented as follows:
[0165]
[0166] Where η² is the learning rate, Q is the number of Gaussian kernels, and θ old These are the old parameters of the model, θ new These are the model's update parameters, L(θ) is the loss function, σ is the uncertainty, n is the current iteration number, and α is the model's update parameters. k It is the Bayesian optimization weight of the k-th Gaussian kernel, μ k σ k These are the mean and standard deviation of the k-th Gaussian kernel.
[0167] In the implementation, η² is the learning rate, a hyperparameter that controls the step size of parameter updates. The learning rate determines how quickly the model parameters move towards the optimal value with each update. If the learning rate is too large, it may cause the parameters to fluctuate drastically, deviating from the optimal value; if it is too small, it may lead to a slow convergence speed.
[0168] Q represents the number of Gaussian kernels used in Bayesian optimization. A Gaussian kernel is a kernel function used to capture local information in the parameter space during Bayesian optimization.
[0169] θ old These are the old parameters of the model, calculated using historical data and previous iterations, representing the parameter settings of the model in previous states.
[0170] θ new These are the updated parameters of the model; the updated parameters are based on the old parameters θ. old Based on this, the adjustment results are combined with gradient descent and Bayesian optimization.
[0171] L(θ) is the loss function, representing the deviation between the model's prediction and the true value. A smaller loss function indicates higher accuracy in the model's predictions. By calculating the gradient of the loss function, the direction in which the model parameters need adjustment can be determined.
[0172] σ represents uncertainty, which characterizes the level of prediction uncertainty or noise in the model under the current conditions. Higher uncertainty indicates that the current model is less adaptable to the data and may require a larger adjustment step size.
[0173] n is the current iteration number. As the number of iterations increases, the step size of parameter adjustment usually decreases gradually to ensure convergence to the optimal value.
[0174] α k α is the Bayesian optimization weight of the k-th Gaussian kernel, representing the contribution of the k-th Gaussian kernel in parameter adjustment. kThis determines the impact of each Gaussian kernel on the final parameter update.
[0175] μ k σ k The mean and standard deviation of the k-th Gaussian kernel, μ k This indicates the location of the center point in the parameter space focused by the Gaussian kernel. Mean μ k This indicates the possible optimal region for the parameters. The standard deviation of the k-th Gaussian kernel represents the extent or influence of the Gaussian kernel in the parameter space. Standard deviation σ k The larger the value, the wider the parameter space covered by the Gaussian kernel.
[0176] Calculate the current old parameter θ old The gradient of the loss function, the sign and magnitude of which determine the direction and intensity of the adjustment. Taking into account the current iteration number n and the uncertainty σ, the step size is adjusted to gradually decrease as the iteration number increases, thereby avoiding parameter oscillations and promoting convergence.
[0177] Indicated by μ k Centered on σ, with standard deviation σ k Gaussian distribution with respect to old parameter θ old The influence of θ old The closer to μ k The larger the Gaussian kernel value, the greater its contribution to parameter tuning. The Bayesian optimization part combines the contributions of multiple Gaussian kernels, enabling it to identify the optimal parameter region in the parameter space and guide the parameters to be tuned in a more favorable direction.
[0178] This formula combines the global optimization capability of gradient descent with the local fine-tuning capability of Bayesian optimization, forming an efficient parameter update mechanism. The gradient descent part adjusts the parameters using the global loss function gradient, gradually reducing the loss function value. The Bayesian optimization part fine-tunes the parameters using a Gaussian kernel function, ensuring effective exploration within local optima. This combination maintains global stability while rapidly adapting to local changes during model training, thereby improving the model's prediction accuracy and adaptability. Especially in complex gas pipeline monitoring environments, this parameter update mechanism effectively addresses various uncertainties, ensuring the model's reliability and practicality.
[0179] The safety monitoring module 206 is used to perform safety monitoring on the gas pipeline according to the optimized safety monitoring model.
[0180] It is understandable that safety monitoring of gas pipelines is carried out based on the optimized safety monitoring model. On the basis of the previous data collection, analysis and model optimization, the optimized monitoring model is used to continuously monitor the real-time operating status of gas pipelines to ensure the safety, stability and efficient operation of the pipeline system.
[0181] The optimized safety monitoring model was developed through multiple iterations and continuous adjustments. It is based on a large amount of historical and real-time monitoring data and has been optimized and calibrated using various algorithms (such as autoregression, moving average, Bayesian optimization, and PID control). This model can more accurately reflect the operating status of gas pipelines, predict potential risks, and provide targeted early warning and automated response solutions.
[0182] The optimization process for the safety monitoring model will be described in detail below:
[0183] Data Acquisition and Preprocessing: Various data points, including pressure, temperature, flow rate, and gas concentration, are collected from key nodes of the gas pipeline. After noise filtering and normalization, this data is used as input to the model, helping it to monitor and predict more accurately.
[0184] Model training and tuning: The model is trained using historical data, and model parameters (such as autoregressive coefficients, moving average coefficients, PID control coefficients, etc.) are adjusted to enable the model to capture key features and abnormal patterns in the gas pipeline system.
[0185] Bayesian optimization: During model training, Bayesian optimization is used to further fine-tune the model parameters based on a Gaussian kernel function. This optimization method can find the optimal combination of parameters in the parameter space, enabling the model to maintain high accuracy and robustness under various operating environments.
[0186] Model evaluation and validation: The model is evaluated through cross-validation and real-world monitoring data to verify its predictive accuracy and reliability. Continuous feedback, adjustments, and iterations ensure the model has sufficient adaptability for real-world applications.
[0187] The specific safety monitoring process is as follows:
[0188] Real-time data input: Once the model optimization is complete, the system will continuously acquire real-time data from various key nodes of the gas pipeline and input this data into the optimized monitoring model.
[0189] Data analysis and anomaly detection: The model analyzes the input data to identify potential anomalies. Because the model has been optimized, it can detect anomalies more accurately and reduce the possibility of false positives or false negatives.
[0190] Risk Prediction and Early Warning: Through time series analysis and prediction algorithms, the model can predict potential risks in the pipeline system, such as excessive pressure, abnormal temperature, sudden flow changes, or gas leaks. The system will issue early warning signals based on the prediction results, prompting relevant personnel to take preventative measures.
[0191] Automated response and adjustment: When an anomaly is detected or a potential risk is predicted, the model will automatically generate a corresponding adjustment plan and automatically adjust the pipeline system through mechanisms such as PID control, such as adjusting the pressure in the pipeline and controlling the opening and closing of valves, to ensure the safe operation of the system.
[0192] It is understandable that the advantages of the optimized security monitoring model are as follows:
[0193] High accuracy: The optimized model can more accurately identify abnormalities in the gas pipeline system, reducing the possibility of false alarms and missed alarms.
[0194] Rapid Response: Through automated adjustment mechanisms, the system can quickly respond to potential risks and prevent accidents from occurring.
[0195] High predictability: The model combines historical and real-time data to predict risks in advance and issue early warnings, giving relevant personnel enough time to intervene.
[0196] Adaptability: The model can continuously adjust and optimize itself based on actual operating conditions, improving its adaptability to different environments and conditions.
[0197] Through the above methods, this invention enables efficient and accurate monitoring of gas pipelines based on an optimized safety monitoring model. By incorporating real-time data input, anomaly detection, risk prediction, and automated response, the system significantly improves the operational safety of gas pipelines, reduces the probability of accidents, and allows for timely and effective measures to ensure the stable operation of the pipeline system in the event of risks.
[0198] Please see Figure 3 The present invention provides a flowchart of a gas pipeline safety monitoring method based on data analysis, comprising the following steps:
[0199] Step 301: Install movable sensors at key nodes of the gas pipeline to collect data on the pressure, temperature, flow rate inside the gas pipeline and the gas concentration in the surrounding environment.
[0200] Step 302: Analyze the pipeline data from the sensor in real time, and identify abnormal conditions in the gas pipeline using an anomaly detection and discrimination function;
[0201] Step 303: Predict future data of the gas pipeline through time series analysis, and establish a safety monitoring model based on the historical and real-time data of the gas pipeline;
[0202] Step 304: After detecting an anomaly in the gas pipeline or predicting a potential risk, adjust the pipeline data of the gas pipeline;
[0203] Step 305: Continue to monitor the gas pipeline to obtain monitoring data, and adjust and optimize the parameters of the monitoring model based on the monitoring data to obtain an optimized safety monitoring model;
[0204] Step 306: Perform safety monitoring on the gas pipeline according to the optimized safety monitoring model.
[0205] It should be noted that the relevant content of the above steps has already been described in the section on data analysis-based gas pipeline safety monitoring systems, and will not be repeated here.
[0206] Please see Figure 4 , Figure 4 A schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, it performs the following steps:
[0207] Movable sensors are installed at key nodes of the gas pipeline to collect data on the pressure, temperature, flow rate inside the gas pipeline, and the gas concentration in the surrounding environment.
[0208] The system analyzes the pipeline data from the sensors in real time and identifies abnormal conditions in the gas pipeline using an anomaly detection and discrimination function.
[0209] Predict future data of the gas pipeline through time series analysis, and establish a safety monitoring model based on the historical and real-time data of the gas pipeline;
[0210] After detecting an anomaly in the gas pipeline or predicting a potential risk, the pipeline data of the gas pipeline is adjusted.
[0211] The gas pipeline is monitored to obtain monitoring data, and the parameters of the monitoring model are adjusted and optimized based on the monitoring data to obtain an optimized safety monitoring model;
[0212] The gas pipeline is monitored for safety based on the optimized safety monitoring model.
[0213] Please see Figure 5 , Figure 5 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. For example... Figure 5 As shown, this embodiment provides a computer-readable storage medium 500 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it performs the following steps:
[0214] Movable sensors are installed at key nodes of the gas pipeline to collect data on the pressure, temperature, flow rate inside the gas pipeline, and the gas concentration in the surrounding environment.
[0215] The system analyzes the pipeline data from the sensors in real time and identifies abnormal conditions in the gas pipeline using an anomaly detection and discrimination function.
[0216] Predict future data of the gas pipeline through time series analysis, and establish a safety monitoring model based on the historical and real-time data of the gas pipeline;
[0217] After detecting an anomaly in the gas pipeline or predicting a potential risk, the pipeline data of the gas pipeline is adjusted.
[0218] The gas pipeline is monitored to obtain monitoring data, and the parameters of the monitoring model are adjusted and optimized based on the monitoring data to obtain an optimized safety monitoring model;
[0219] The gas pipeline is monitored for safety based on the optimized safety monitoring model.
[0220] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0221] Those skilled in the art will understand that embodiments of the present invention can be provided as systems, methods, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0222] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.
[0223] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0224] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0225] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.
[0226] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A gas pipeline safety monitoring system based on data analysis, characterized in that, The system includes: The data acquisition module is used to install movable sensors at key nodes of the gas pipeline to collect the pressure, temperature, flow rate inside the gas pipeline and the gas concentration in the surrounding environment. An anomaly identification module is used to analyze the pipeline data from the sensor in real time and identify abnormal conditions in the gas pipeline through an anomaly detection and discrimination function. The model building module is used to predict future data of the gas pipeline through time series analysis and to build a safety monitoring model based on the historical and real-time data of the gas pipeline. The data adjustment module is used to adjust the pipeline data of the gas pipeline after detecting an anomaly in the gas pipeline or predicting a potential risk. The model training module is used to continue monitoring the gas pipeline to obtain monitoring data, and to adjust and optimize the parameters of the monitoring model based on the monitoring data to obtain an optimized safety monitoring model. The safety monitoring module is used to perform safety monitoring on the gas pipeline according to the optimized safety monitoring model. The anomaly detection module is further used for: Obtain different pipeline data of the gas pipeline at preset times; Based on the different pipeline data of the gas pipeline at the current time t, calculate the average value and standard deviation of the pipeline data for each type; Obtain the weights of the covariance matrix among the pipeline data, and the corresponding adaptive weighting coefficients; Based on the different pipeline data of the gas pipeline at the current time t, the average value and standard deviation of each type of pipeline data, the weight of the covariance matrix and the adaptive weighting coefficient, the anomaly detection discrimination function is constructed. The abnormal detection value of the gas pipeline is determined according to the abnormal detection discrimination function, and the abnormal detection of the gas pipeline is performed based on the abnormal detection value; The anomaly detection discriminant function is expressed as follows: in, These represent different pipeline data at time t. These are the average values for various types of pipeline data. The standard deviation of various pipeline data, The weights of the covariance matrix among the data from each pipeline. These are adaptive weighting coefficients; The model building module is also used for: Obtain the pipeline data at the current time t, and the historical pipeline data up to time h; Obtain the exogenous variables generated by external factors of the gas pipeline; Obtain the hysteresis term of the pipeline data before time s; Based on the pipeline data at the current time t, the historical pipeline data before time h, the exogenous variables, and the lag error term, a safety monitoring model is constructed to predict the future data of the gas pipeline. The future data for the gas pipeline is represented as follows: in, It is the autoregressive coefficient. All are times. It is an exogenous variable. These are the weighting coefficients of exogenous variables. It is the acceleration coefficient. It is the moving average coefficient. It is the lag error term. It is the second derivative. It is the speed coefficient. It is the first derivative. It is a random error term. This is the pipeline data at the current time t. This represents the historical pipeline data up to time h.
2. The gas pipeline safety monitoring system based on data analysis according to claim 1, characterized in that, The data adjustment module is also used for: Obtain the current value and set value of each of the pipeline data; Calculate the first difference between the current value and the set value for each of the pipeline data; Obtain the feedforward variable for each of the exogenous variables in the delay The variable value after time step; The multiple first differences are summed, integrated, and differentiated respectively, and combined with each of the variable values to obtain the adjusted pipeline data.
3. The gas pipeline safety monitoring system based on data analysis according to claim 2, characterized in that, The adjusted pipeline data is represented as follows: in, It is the current value of the i-th pipeline data. yes The set value, These are the proportional, integral, and differential coefficients, respectively. It was a moment. Is the feedforward variable delayed? The value after that, It is the feedforward compensation coefficient, and N is the total number of pipeline data. It is the first difference.
4. The gas pipeline safety monitoring system based on data analysis according to claim 3, characterized in that, The model training module is also used for: Calculate the mean and standard deviation of the Gaussian kernel in the safety monitoring model; Construct the corresponding Gaussian kernel function based on the mean and the standard deviation; Based on the monitoring data, the loss function of the safety monitoring model, and the Gaussian kernel function, gradient descent and Bayesian optimization are performed on the old parameters of the safety monitoring model to obtain the optimized safety monitoring model with updated parameters.
5. The gas pipeline safety monitoring system based on data analysis according to claim 4, characterized in that, The update parameters of the safety monitoring model are expressed as follows: in, Q is the learning rate, and Q is the number of Gaussian kernels. These are the old parameters of the model. These are the model's update parameters. It is a loss function. It is uncertain, where n is the current iteration number. It is the Bayesian optimization weight of the k-th Gaussian kernel. These are the mean and standard deviation of the k-th Gaussian kernel.
6. A data analysis-based method for gas pipeline safety monitoring, wherein the method uses the data analysis-based gas pipeline safety monitoring system according to any one of claims 1-5, characterized in that, The method includes: Movable sensors are installed at key nodes of the gas pipeline to collect data on the pressure, temperature, flow rate inside the gas pipeline, and the gas concentration in the surrounding environment. The system analyzes the pipeline data from the sensors in real time and identifies abnormal conditions in the gas pipeline using an anomaly detection and discrimination function. Predict future data of the gas pipeline through time series analysis, and establish a safety monitoring model based on the historical and real-time data of the gas pipeline; After detecting an anomaly in the gas pipeline or predicting a potential risk, the pipeline data of the gas pipeline is adjusted. The gas pipeline is monitored to obtain monitoring data, and the parameters of the monitoring model are adjusted and optimized based on the monitoring data to obtain an optimized safety monitoring model; The gas pipeline is monitored for safety based on the optimized safety monitoring model.
Citation Information
Patent Citations
Algorithm-based gas pipeline detection early warning system and method
CN116398823A
Combustible gas intelligent detection system and method based on big data
CN118482874A
