Gas pipe network monitoring method and system based on intelligent gas, medium and equipment

Abstract

The invention discloses a gas pipe network monitoring method and system based on intelligent gas, a medium and equipment. The method comprises the steps that pipeline pressure data, gas flow data and gas concentration data of a to-be-monitored gas pipe network are obtained in real time; preprocessing the pipeline pressure data, the gas flow data and the gas concentration data; and monitoring the preprocessed pipeline pressure data, gas flow data and gas concentration data in real time based on a trained gas pipe network monitoring model so as to identify whether the gas pipe network has an abnormal condition or not. According to the invention, whether the gas pipe network is abnormal or not can be accurately monitored.

Description

Technical Field

[0001] The present application belongs to the field of gas monitoring technology, and specifically relates to a gas pipeline network monitoring method, system, medium and equipment based on smart gas. Background Art

[0002] Traditional gas pipeline network monitoring often relies on manual inspections and regular maintenance, which is time-consuming and labor-intensive and difficult to detect safety hazards in a timely manner. With the development of Internet of Things technology, by deploying pressure sensors, flow sensors and gas concentration sensors on the gas pipeline network, status data can be obtained in real time to achieve dynamic monitoring. However, existing methods have deficiencies in data preprocessing, feature extraction and model generalization capabilities, resulting in low accuracy and efficiency in abnormal gas pipeline network monitoring. Summary of the invention

[0003] The main purpose of this application is to provide a gas pipeline network monitoring method, system, medium and equipment based on smart gas. This application aims to improve the efficiency of abnormal monitoring of the gas pipeline network.

[0004] To achieve the above objectives, this application provides the following technical solutions:

[0005] A gas pipeline network monitoring method based on smart gas, the method comprising: acquiring pipeline pressure data, gas flow data and gas concentration data of a gas pipeline network to be tested in real time; preprocessing the pipeline pressure data, gas flow data and gas concentration data; based on a trained gas pipeline network monitoring model, real-time monitoring of the preprocessed pipeline pressure data, gas flow data and gas concentration data is performed to identify whether there is an abnormality in the gas pipeline network, wherein the gas pipeline network monitoring model introduces multiple extraction functions to extract features of the pipeline pressure data, gas flow data and gas concentration data respectively and perform comprehensive calculations to evaluate the overall health status of the gas pipeline network to be tested.

[0006] Optionally, the pipeline pressure data, gas flow data and gas concentration data are preprocessed, including: cleaning the pipeline pressure data, gas flow data and gas concentration data; standardizing the cleaned pipeline pressure data, gas flow data and gas concentration data; extracting features from the standardized pipeline pressure data, gas flow data and gas concentration data; and denoising the pipeline pressure data, gas flow data and gas concentration data after feature extraction.

[0007] Optionally, the gas pipeline network monitoring model includes: an input layer, used to input the preprocessed pipeline pressure data, gas flow data and gas concentration data; a feature extraction layer, used to extract features from the preprocessed pipeline pressure data, gas flow data and gas concentration data; a nonlinear transformation layer, used to capture the nonlinear relationship between the extracted features; a feature interaction layer, used to evaluate the correlation between different features; and an output layer, used to output the anomaly detection score of the gas pipeline network.

[0008] Optionally, the feature extraction layer includes: a pipeline pressure change rate extraction function, used to extract features from pipeline pressure data; a gas flow rate change rate extraction function, used to extract features from gas flow data; and a gas concentration change rate extraction function, used to extract features from gas concentration data.

[0009] The present application also provides a gas pipeline network monitoring system based on smart gas, wherein the monitoring includes a management platform, a sensor network platform and an object platform that are communicatively connected in sequence, and the management platform includes: an acquisition module for acquiring pipeline pressure data, gas flow data and gas concentration data of the gas pipeline network in real time; a preprocessing module for preprocessing the pipeline pressure data, gas flow data and gas concentration data; an identification module for real-time monitoring of the preprocessed pipeline pressure data, gas flow data and gas concentration data based on a trained gas pipeline network monitoring model to identify whether there is any abnormality in the gas pipeline network.

[0010] Optionally, the preprocessing module includes: a cleaning submodule, used to clean the pipeline pressure data, gas flow data and gas concentration data; a standardization processing submodule, used to standardize the cleaned pipeline pressure data, gas flow data and gas concentration data; a feature extraction submodule, used to extract features from the standardized pipeline pressure data, gas flow data and gas concentration data; and a denoising submodule, used to denoise the pipeline pressure data, gas flow data and gas concentration data after feature extraction.

[0011] The present application also provides a storage medium, which includes instructions, and when the instructions are executed on a computer, the computer executes the method as described in any of the preceding items.

[0012] The present application also provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any of the preceding items when executing the program.

[0013] This application can bring the following beneficial effects:

[0014] By constructing a gas pipeline network monitoring model, this application can effectively capture the key features in the gas pipeline network data and the relationships between them, so as to quickly and accurately identify potential problems in the gas pipeline network, thereby improving the speed and efficiency of gas pipeline network anomaly detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a gas pipeline network monitoring method based on smart gas provided by an embodiment of the present application;

[0016] Figure 2 It is a structural diagram of a gas pipeline network monitoring model provided by an embodiment of the present application;

[0017] Figure 3 is a structural schematic diagram of a gas pipeline network monitoring system based on smart gas provided in another embodiment of the present application;

[0018] Figure 4 is a schematic diagram of the structure of a storage medium provided by another embodiment of the present application;

[0019] Figure 5 It is a schematic diagram of the structure of an electronic device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0022] In this application, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0023] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0024] Figure 1 A flow chart of a gas pipeline network monitoring method based on smart gas according to an embodiment of the present application is shown as follows: Figure 1 As shown, the method includes:

[0025] S100: Setting pressure sensors, flow sensors and gas concentration sensors at key nodes (such as branch points, pressure regulating stations, valves, etc.) of the gas pipeline network to be tested, so as to obtain pipeline pressure data, gas flow data and gas concentration data of the gas pipeline network in real time;

[0026] S200: Preprocessing the pipeline pressure data, gas flow data and gas concentration data;

[0027] S300: Based on the trained gas pipeline network monitoring model, the pre-processed pipeline pressure data, gas flow data and gas concentration data are monitored in real time to identify whether there is an abnormality in the gas pipeline network.

[0028] This application can support multi-dimensional anomaly analysis by simultaneously collecting pipeline pressure data, gas flow data, and gas concentration data, so as to more comprehensively understand the nature of whether there are abnormal conditions in the gas pipeline network. In addition, this application can effectively capture the key features in the gas pipeline network data and the relationship between them by constructing a gas pipeline network monitoring model, so as to quickly and accurately identify potential problems in the gas pipeline network, thereby improving the speed and efficiency of gas pipeline network anomaly detection.

[0029] In another exemplary embodiment, in step S300, the pipeline pressure data, the gas flow data and the gas concentration data are preprocessed, including:

[0030] S301: Cleaning the pipeline pressure data, gas flow data and gas concentration data;

[0031] In this step, it is necessary to check whether there are invalid or erroneous data points in the data, such as missing values, outliers, etc. For missing values, nearest neighbor interpolation or linear interpolation can be used to fill them. For outliers, statistical methods (such as calculating the mean and standard deviation) can be used to identify them, and decide whether to delete or correct these outliers based on the actual situation.

[0032] S302: Standardizing the cleaned pipeline pressure data, gas flow data, and gas concentration data;

[0033] In this step, since the data collected by different types of sensors (such as pressure sensors, flow sensors, and gas concentration sensors) have different dimensions and ranges, the data collected by each sensor needs to be standardized through minimum-maximum scaling (Min-Max Scaling) or z-score normalization to eliminate the dimension effect so that all data are on the same scale, which is conducive to subsequent model training and analysis.

[0034] S303: extracting features from the pipeline pressure data, gas flow data and gas concentration data after the standardization process;

[0035] In this step, feature extraction can help the gas network monitoring model better understand and identify patterns. Specifically, feature extraction can include calculating statistical features (such as mean, variance, peak value, etc., trend analysis), or extracting features in signal processing (such as Fourier transform, wavelet transform, etc.).

[0036] S304: performing noise reduction processing on the pipeline pressure data, gas flow data and gas concentration data after feature extraction.

[0037] In this step, since there is inevitably a certain amount of noise interference in the collected data, it is necessary to take noise reduction measures to reduce the impact of noise. Common noise reduction methods include smoothing filtering, median filtering, etc.

[0038] In another exemplary embodiment, Figure 2 As shown, the gas network monitoring model includes the following connected in sequence:

[0039] An input layer, used to input the pre-processed pipeline pressure data, gas flow data and gas concentration data;

[0040] A feature extraction layer, used for extracting features from the preprocessed pipeline pressure data, gas flow data and gas concentration data;

[0041] Nonlinear transformation layer, used to capture the nonlinear relationship between the extracted features;

[0042] The feature interaction layer is used to evaluate the correlation between different features;

[0043] The output layer is used to output the anomaly detection score of the gas pipeline network.

[0044] In this embodiment, the feature extraction layer is used to extract features from pipeline pressure data, gas flow data and gas concentration data using pipeline pressure change rate extraction function, gas flow change rate extraction function and gas concentration change rate extraction function respectively. In addition, the comprehensive change rate extraction function and the average value calculation within the time window are used to enhance the feature expression capability.

[0045] The specific representation of each extraction function is as follows:

[0046] Pipeline pressure change rate extraction function:

[0047]

[0048] Gas flow rate change rate extraction function:

[0049]

[0050] Gas concentration change rate extraction function:

[0051]

[0052] Comprehensive change rate extraction function:

[0053]

[0054] Average value within a time window:

[0055]

[0056] Wherein, P(t) represents the pipeline pressure data at time t, P(t-1) represents the pipeline pressure data at time t-1, F(t) represents the gas flow data at time t, F(t-1) represents the gas flow data at time t-1, C(t) represents the gas concentration data at time t, C(t-1) represents the gas concentration data at time t-1, Δt represents the time interval, ΔP(t) represents the pressure change rate, ΔF(t) represents the gas flow change rate, ΔC(t) represents the gas concentration change rate, represents the average pipeline pressure at time t, represents the average gas flow rate at time t, represents the average value of gas concentration at time t, ω represents the length of the time window of gas concentration change rate, P(ti) represents the pipeline pressure data at time ti, F(ti) represents the gas flow data at time ti, and C(ti) represents the gas concentration data at time ti.

[0057] Among the above characteristics, the pipeline pressure change rate reflects the change of the pressure in the gas pipeline over time. The change of pipeline pressure may be caused by many factors, such as changes in gas consumption, adjustments to the gas supply system, etc. By calculating the change rate of pipeline pressure, abnormal pressure fluctuations can be discovered in time, and then it can be inferred whether there is a leak or other fault.

[0058] The gas flow rate of change can also reflect changes in gas usage or pipeline conditions. Calculating the flow rate of change helps to detect flow anomalies, such as sudden increases or decreases, which may be caused by changes in user usage habits or pipeline damage.

[0059] The rate of change of gas concentration can reveal the possibility of gas leakage. When the gas concentration rises rapidly in a closed space, it may mean that a gas leak has occurred. Therefore, monitoring the changes in gas concentration is very important for preventing accidents.

[0060] In addition, there is an interdependence between the three features of pipeline pressure change rate, gas flow change rate, and gas concentration change rate. Among them, the change of pipeline pressure is often accompanied by the change of gas flow. For example, when the gas consumption increases, the pipeline pressure may drop, and the gas flow will increase at the same time. Therefore, the change rates of these two features need to be considered comprehensively to more accurately judge the status of the pipeline network. In addition, abnormal changes in gas flow will lead to changes in gas concentration. For example, if the gas flow in a certain area suddenly increases, and the gas concentration in that area also increases, this indicates that there is a risk of gas leakage. Therefore, it is necessary to conduct a comprehensive analysis of the change rates of these two features.

[0061] The comprehensive change rate is a comprehensive consideration of the above three change rates. This feature can provide a more comprehensive perspective on the state changes of the entire gas pipeline network. By calculating the combined value of the pipeline pressure change rate, gas flow change rate and gas concentration change rate, the overall health status of the pipeline network can be more accurately assessed.

[0062] The average value within the time window can help filter out the interference caused by short-term fluctuations and more clearly see the long-term trend changes in the gas pipeline network.

[0063] The above features are selected in this application because they can reflect the working status of the gas network from different angles, which helps the gas network monitoring model learn the feature distribution under the normal operation mode, and can also effectively identify abnormal situations that deviate from the normal mode. Through in-depth analysis of these features, the accuracy and reliability of the gas network monitoring model in identifying abnormal situations in the gas network can be improved, thereby ensuring the safety and stability of gas supply.

[0064] The nonlinear transformation layer includes multiple nonlinear transformation functions, such as hyperbolic tangent transformation, sigmoid transformation, polynomial transformation and exponential transformation, to capture the complex nonlinear relationship between features. The nonlinear transformation functions specifically include:

[0065] Hyperbolic tangent transformation:

[0066] g1(x1)=tanh(α1x1+β1)

[0067] Sigmoid transformation:

[0068] g2(x2)=σ(α2x2+β2)

[0069] Polynomial transformation:

[0070] g3(x3)=α3x3 3 +β3x3 2 +γ3x3+δ3

[0071] Exponential transformation:

[0072]

[0073] Among them, α1 represents the first slope control parameter, β1 represents the first offset, x1 represents the input pipeline pressure change rate, α2 represents the second slope control parameter, β2 represents the second offset, σ represents the sigmoid function, x2 represents the input gas flow change rate, α3 represents the cubic term coefficient, β3 represents the quadratic term coefficient, γ3 represents the linear term coefficient, δ3 represents the constant term, x3 represents the input gas concentration change rate, α4 represents the amplitude control parameter, β4 represents the parameter for controlling the exponential growth rate, and x4 represents the comprehensive change rate of the input.

[0074] In the above nonlinear transformation, the hyperbolic tangent function is an S-shaped function with an output range of (-1,1), which can compress the input data into this interval. This transformation helps the gas pipeline network monitoring model to better handle extreme values ​​in the data while keeping the relative proportion of the data unchanged, and is suitable for processing data with a large range of changes.

[0075] The Sigmoid function is also an S-shaped function with an output range of (0,1). It is mainly used to map data between 0 and 1. This transformation is particularly suitable for probability estimation tasks and can convert any real value into a probability value.

[0076] The polynomial transformation can capture the high-order interaction effects between features, that is, the complex relationship between different features. By introducing square terms and cubic terms of features, the transformation can model more complex nonlinear relationships and improve the fitting ability of the gas pipeline network monitoring model.

[0077] The exponential transformation can amplify or reduce the difference in data, especially for data with long-tail distribution or slight changes. The exponential transformation can highlight the slight changes in the data, which helps the gas pipeline network monitoring model to identify important features.

[0078] It should be noted that since the data of the gas pipeline network often contains complex nonlinear relationships, a single linear model is difficult to accurately capture these relationships. The present application uses a variety of nonlinear transformation functions to make the gas pipeline network monitoring model more flexibly adapt to different types of data, thereby better capturing the complex relationships between features. Furthermore, by introducing a variety of nonlinear transformations, the gas pipeline network monitoring model can better handle noise and outliers in the data, thereby improving the robustness of the gas pipeline network monitoring model, and further improving the anomaly detection capability of the gas pipeline network monitoring model.

[0079] It should also be noted that the above nonlinear transformation functions are not simply superimposed, and there is considerable complementarity between the transformation functions. Among them, the hyperbolic tangent transformation is suitable for processing data with a large range of changes, while the sigmoid transformation is suitable for processing data that needs to be normalized. The combination of the two can provide effective transformations within different data ranges. In gas pipeline network monitoring, pipeline pressure data often has a large range of changes, and gas concentration data needs to be normalized. By combining the hyperbolic tangent transformation and the sigmoid transformation, the gas pipeline network monitoring model can process these data more flexibly. In addition, the polynomial transformation is suitable for capturing high-order interaction effects, while the exponential transformation is suitable for amplifying subtle changes in the data. The combination of the two can provide effective transformations at different feature levels. For example, in gas pipeline network monitoring, gas flow data often has complex nonlinear relationships, and gas concentration data often has subtle changes. By combining the polynomial transformation and the exponential transformation, the gas pipeline network monitoring model can capture these features more comprehensively, thereby improving the accuracy of anomaly detection.

[0080] The feature interaction layer includes a first feature interaction module and a second feature interaction module. The two feature interaction modules evaluate the interaction between different features through different algorithms to improve the recognition ability of the gas pipeline network monitoring model for abnormal situations. The first feature interaction module and the second feature interaction module are respectively expressed as:

[0081] First feature interaction module:

[0082] h1(x1,x2)=sin(γ1x1+δ1x2)

[0083] h2(x2,x3)=cos(γ2x2+δ2x3)

[0084] Among them, x1 represents the input pressure change rate, x2 represents the input gas flow change rate, γ1 represents the first parameter for controlling the pressure change rate frequency, δ1 represents the first parameter for controlling the gas flow change rate frequency, γ2 represents the second parameter for controlling the pressure change rate frequency, and δ2 represents the second parameter for controlling the gas flow change rate frequency.

[0085] Second feature interaction module:

[0086] h3(x1,x4)=sin(γ3x1+δ3x4)cos(γ4x1+δ4x4)

[0087] h4(x2,x4)=log(γ5x2+δ5x4+ε)

[0088] Among them, x3 represents the input gas concentration change rate, x4 represents the input comprehensive change rate, γ3 represents the first parameter for controlling the frequency of the gas concentration change rate, δ3 represents the first parameter for controlling the frequency of the comprehensive change rate, γ4 represents the second parameter for controlling the frequency of the gas concentration change rate, δ4 represents the second parameter for controlling the frequency of the comprehensive change rate, γ5 represents the parameter of the linear combination of the gas concentration change rate, δ5 represents the parameter of the linear combination of the comprehensive change rate, and ε represents a constant to prevent negative numbers and zero values ​​from appearing in the logarithmic function.

[0089] The feature interaction layer described in the present application adopts two feature interaction modules, wherein the first feature interaction module is mainly used to preliminarily evaluate the basic relationship between different features. The first feature interaction module can capture the linear relationship and simple nonlinear relationship between features through simple interactive operations to quickly screen out significantly related feature combinations. The second feature interaction module is used to further evaluate more complex feature relationships based on the first feature interaction module. This module can capture the deep nonlinear relationship between features by adopting a more advanced interaction algorithm to deeply explore the complex interaction patterns between features.

[0090] In summary, the present application can enhance the expressive power of the gas pipeline network monitoring model by setting two feature interaction modules, so that it can more accurately capture and model complex patterns in the data. The use of a single feature interaction module can only capture part of the feature relationship, while the use of two feature interaction modules can evaluate the relationship between features from multiple angles and levels, thereby providing richer information. In addition, abnormal situations often manifest themselves as complex changes and abnormal patterns in the data. By setting two feature interaction modules, the gas pipeline network monitoring model can more comprehensively evaluate the relationship between features, thereby more accurately identifying these abnormal patterns. For example, the change of a feature may not be obvious when considered alone, but may exhibit abnormal behavior in interaction with other features.

[0091] Exemplarily, this application obtains a set of gas network data in real time, specifically including:

[0092] Pipeline pressure data: 100kPa, 102kPa, 98kPa, 101kPa, 103kPa

[0093] Gas flow data: 200m 3 / h,205m 3 / h,195m 3 / h,202m 3 / h,204m 3 / h

[0094] Gas concentration data: 95%, 97%, 93%, 96%, 98%

[0095] When considering the features individually:

[0096] Pipeline pressure data

[0097] Data changes: 100kPa→102kPa→98kPa→101kPa→103kPa

[0098] Change rate: +2kPa, -4kPa, +3kPa, +2kPa

[0099] Judging from the individual pressure data, the changes in pressure fluctuate within the normal range and there are no obvious abnormalities.

[0100] Gas flow data

[0101] Data change: 200m 3 / h→205m 3 / h→195m 3 / h→202m 3 / h→204m 3 / h

[0102] Rate of change: +5m 3 / h,-10m 3 / h,+7m 3 / h,+2m 3 / h

[0103] Judging from the individual traffic data, the changes in traffic also fluctuate within the normal range, with no obvious abnormalities.

[0104] Gas concentration data

[0105] Data changes: 95% → 97% → 93% → 96% → 98%

[0106] Change rate: +2%, -4%, +3%, +2%

[0107] Judging from the individual concentration data, the changes in concentration also fluctuated within the normal range, with no obvious abnormalities.

[0108] Feature Interaction

[0109] First feature interaction module

[0110] In the first feature interaction module, the product between the pipeline pressure change rate and the gas flow change rate is calculated:

[0111] Pressure change rate × flow rate change rate:

[0112] (+2kPa)×(+5m 3 / h)=+10kPa·m 3 / h

[0113] (-4kPa)×(-10m 3 / h)=+40kPa·m 3 / h

[0114] (+3kPa)×(+7m 3 / h)=+21kPa·m 3 / h

[0115] (+2kPa)×(+2m 3 / h)=+4kPa·m 3 / h

[0116] From these products, most results are within reasonable range, but there is a significant positive value (+40 kPa·m 3 / h), which may indicate that simultaneous changes in pressure and flow over a certain period of time may be a signal that needs attention.

[0117] Second feature interaction module

[0118] In the second feature interaction module, the present application further calculates the product between the above product and the gas concentration change rate:

[0119] (pressure change rate × flow rate change rate) × concentration change rate:

[0120] (+10kPa·m 3 / h)×(+2%)=+0.2kPa·m 3 / h %

[0121] (+40kPa·m 3 / h)×(-4%)=-1.6 kPa·m 3 / h %

[0122] (+21kPa·m 3 / h)×(+3%)=+0.63kPa·m 3 / h %

[0123] (+4kPa·m 3 / h)×(+2%)=+0.08kPa·m 3 / h %

[0124] From these quadratic products, there is a significant negative value (-1.6 kPa·m 3 / h·%), which indicates that the combined changes of pressure, flow rate and concentration show abnormal behavior within a certain period of time.

[0125] In the above examples, no obvious abnormality was found when considering the changes of each feature separately. However, through the calculation of the feature interaction layer, this application found a significant abnormal signal (-1.6 kPa·m 3 / h·%), which indicates that the combined changes in pressure, flow and concentration over a certain period of time may indicate a potential problem. This interactive relationship cannot be discovered when considering each feature separately. Only through the calculation of the feature interaction layer can this complex abnormal behavior be captured.

[0126] In summary, it is not difficult to see that the feature interaction layer can help the gas pipeline network monitoring model to more comprehensively evaluate the relationship between features through two layers of interaction, thereby improving the accuracy of the model for gas pipeline network anomaly detection.

[0127] The output layer outputs the final gas network anomaly detection score based on the results of the previous layers through the comprehensive scoring function shown below:

[0128] S=w1·g1(ΔP(t))+w2·g2(ΔF(t))+w3·g3(ΔC(t))+w4·g4(ΔI(t))+w5·h1(ΔP(t),ΔF(t))

[0129] +w6·h2(ΔF(t),ΔC(t))+w7·h3(ΔP(t),ΔI(t))+w8·h4(ΔF(t),ΔI(t))

[0130] Among them, w1, w2, w3, w4, w5, w6, w7, and w8 represent weight parameters respectively.

[0131] Below, in order to better understand how the gas pipeline network monitoring model works, this application still takes the above data as an example to gradually demonstrate the analysis process of the gas pipeline network monitoring model and the final anomaly score calculation.

[0132] The data collected includes:

[0133] Pipeline pressure data: 100kPa, 102kPa, 98kPa, 101kPa, 103kPa

[0134] Gas flow data: 200m 3 / h,205m 3 / h,195m 3 / h,202m 3 / h,204m 3 / h

[0135] Gas concentration data: 95%, 97%, 93%, 96%, 98%

[0136] First, the above data is cleaned and standardized by minimum and maximum value scaling. The processed data is expressed as:

[0137] Standardized pipeline pressure data: 0.4, 0.8, 0, 0.6, 1

[0138] Standardized gas flow data: 0.5, 1, 0, 0.7, 0.9

[0139] Standardized gas concentration data: 0.4, 0.8, 0, 0.6, 1

[0140] Secondly, the preprocessed data is subjected to feature extraction through the feature extraction layer, which is specifically expressed as follows:

[0141] Pipeline pressure change rate: 0.02, -0.0392, 0.0306, 0.0198

[0142] Gas flow rate change rate: 0.025, -0.0488, 0.0359, 0.0099

[0143] Gas concentration change rate: 0.0211, -0.0412, 0.0323, 0.0208

[0144] Average value in the time window: 100.8kPa, 200.4m 3 / h, 95.8%

[0145] Secondly, the features are transformed nonlinearly. For example, the sigmoid function is used to transform the features nonlinearly, and the following is obtained:

[0146] Pipeline pressure change rate: 0.505, 0.485, 0.508, 0.505

[0147] Gas flow rate change rate: 0.506, 0.484, 0.509, 0.502

[0148] Gas concentration change rate: 0.505, 0.484, 0.508, 0.505

[0149] Secondly, the feature interaction layer is used to capture the relationship between different features. The result after interaction is:

[0150] First feature interaction result: 0.130, 0.115, 0.132, 0.128

[0151] Second feature interaction results: 1.516, 1.453, 1.525, 1.512

[0152] Finally, the anomaly detection score is calculated through the comprehensive scoring function, and we can get:

[0153] S=0.814.

[0154] According to the statistical analysis of historical data, the anomaly detection threshold is set to twice the standard deviation of the historical data, and the final threshold is determined to be 0.6. Since the above anomaly detection score is greater than 0.814, the model can determine that there is an abnormality in the gas pipeline network to be monitored, and further inspection and maintenance of the gas pipeline network to be monitored is required.

[0155] In another exemplary embodiment, in step S300, the gas network monitoring model is trained by the following steps:

[0156] S301: Obtain and preprocess historical data of the gas pipeline network, and divide the preprocessed historical data into a training set and a validation set in a ratio of 7:3;

[0157] In this step, the historical data is preprocessed according to the above-mentioned preprocessing method, which will not be described in detail here.

[0158] S302: Setting training parameters, for example, setting the learning rate to 0.01, setting the maximum number of iterations to 300, and training the model using the training set. During the model training process, when the number of model iterations meets the preset value, the model training is completed;

[0159] S303: Use the validation set to validate the trained model. During the validation process, if the mean absolute error (MAE), mean square error (MSE) and root mean square error (RMSE) as the model performance evaluation indicators are all less than the threshold (in this model validation, the MAE threshold is set to a more tolerable 0.05, and the MSE threshold is set to a more stringent 0.001), the model validation is passed; otherwise, adjust the training parameters or expand the training set samples to retrain the model. For example, the learning rate can be adjusted to 0.005, and then the model is retrained until the model validation is passed.

[0160] In another exemplary embodiment, Figure 3 As shown, the present application also provides a gas pipeline network monitoring system based on smart gas, the monitoring system includes a management platform, a sensor network platform and an object platform that are communicatively connected in sequence, the management platform includes: an acquisition module 100, used to acquire pipeline pressure data, gas flow data and gas concentration data of the gas pipeline network in real time; a preprocessing module 200, used to preprocess the pipeline pressure data, gas flow data and gas concentration data; an identification module 300, used to monitor the preprocessed pipeline pressure data, gas flow data and gas concentration data in real time based on a trained gas pipeline network monitoring model, so as to identify whether there is any abnormality in the gas pipeline network.

[0161] In another exemplary embodiment, the preprocessing module includes: a cleaning submodule, used to clean the pipeline pressure data, gas flow data and gas concentration data; a standardization processing submodule, used to standardize the cleaned pipeline pressure data, gas flow data and gas concentration data; a feature extraction submodule, used to extract features from the standardized pipeline pressure data, gas flow data and gas concentration data; and a denoising submodule, used to denoise the pipeline pressure data, gas flow data and gas concentration data after feature extraction.

[0162] Based on the above embodiments, Figure 4 , for an explanation of the computer-readable storage medium of the exemplary embodiment of the present application, please refer to Figure 4 , the computer-readable storage medium shown is a CD 40, on which a computer program (i.e., a program product) is stored. When the computer program is executed by the processor, each step recorded in the above method implementation will be implemented, for example, a pressure sensor, a flow sensor, and a gas concentration sensor are set at the key nodes of the gas pipeline network to obtain the pipeline pressure data, gas flow data, and gas concentration data of the gas pipeline network in real time; the pipeline pressure data, gas flow data, and gas concentration data are preprocessed; the preprocessed pipeline pressure data, gas flow data, and gas concentration data are monitored in real time based on the trained gas pipeline network monitoring model to identify whether there is an abnormality in the gas pipeline network. The specific implementation method of each step is not repeated here.

[0163] It should be noted that the computer-readable storage medium includes but is not limited to phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0164] Based on the above embodiments, the present application also provides an electronic device, as shown below: Figure 5 An electronic device for downloading a file according to an exemplary embodiment of the present application is described.

[0165] Figure 5 A block diagram of an exemplary electronic device 50 suitable for implementing the embodiments of the present application is shown, and the electronic device 50 may be a computer system or a cloud server. Figure 5 The electronic device 50 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0166] like Figure 5 As shown, the electronic device 50 includes but is not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 connecting different system components (including the system memory 502 and the processing unit 501).

[0167] The electronic device 50 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 50, including volatile and non-volatile media, removable and non-removable media.

[0168] The system memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 5021 and / or cache memory 5022. The electronic device 50 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the ROM 5023 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 is not shown in the Figure 5 As shown in FIG. 5 , a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 503 via one or more data medium interfaces. System memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of each embodiment of the present application.

[0169] A program / utility 5025 having a set (at least one) of program modules 5024 may be stored, for example, in system memory 502, and such program modules 5024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 5024 generally perform the functions and / or methods of the embodiments described herein.

[0170] The electronic device 50 may also communicate with one or more external devices 504 (e.g., a keyboard, a pointing device, a display, etc.). Such communication may be performed via an input / output (I / O) interface 505. Furthermore, the electronic device 50 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 506. Figure 5 As shown, the network adapter 506 communicates with other modules (such as the processing unit 501, etc.) of the electronic device 50 via the bus 503. It should be understood that although Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 50 .

[0171] The processing unit 501 executes various functional applications and data processing by running the program stored in the system memory 502, for example, obtaining the pipeline pressure data, gas flow data and gas concentration data of the gas pipeline network in real time; preprocessing the pipeline pressure data, gas flow data and gas concentration data; and monitoring the preprocessed pipeline pressure data, gas flow data and gas concentration data in real time based on the trained gas pipeline network monitoring model to identify whether there is an abnormality in the gas pipeline network. The specific implementation of each step is not repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the file concurrent downloading device are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be concretized in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be concretized.

[0172] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0173] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0174] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0175] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0177] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that can be executed by a processor. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a cloud server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0178] The above embodiments are only for illustrating the technical concept and features of the present application, and their purpose is to enable people familiar with the technology to understand the content of the present application and implement it accordingly, and they cannot be used to limit the protection scope of the present application. Any equivalent changes or modifications made according to the spirit of the present application should be included in the protection scope of the present application.

Claims

1. A gas pipeline network monitoring method based on smart gas, characterized in that: The method is applied to a gas pipe network monitoring system, wherein the gas pipe network monitoring system comprises a management platform, a sensor network platform and an object platform which are sequentially connected in communication, and the method comprises: Obtain pipeline pressure data, gas flow data and gas concentration data of the gas pipeline network to be tested in real time; Preprocessing the pipeline pressure data, gas flow data and gas concentration data; Based on the trained gas pipeline network monitoring model, the pre-processed pipeline pressure data, gas flow data and gas concentration data are monitored in real time to identify whether there are abnormal conditions in the gas pipeline network. The gas pipeline network monitoring model introduces multiple extraction functions to extract features of the pipeline pressure data, gas flow data and gas concentration data and perform comprehensive calculations to evaluate the overall health status of the gas pipeline network to be tested.

2. The gas pipeline network monitoring method based on smart gas according to claim 1 is characterized in that: Preprocessing the pipeline pressure data, gas flow data and gas concentration data includes: Cleaning the pipeline pressure data, gas flow data and gas concentration data; Standardizing the pipeline pressure data, gas flow data and gas concentration data after cleaning; Performing feature extraction on the pipeline pressure data, gas flow data and gas concentration data after the standardization process; The pipeline pressure data, gas flow data and gas concentration data after feature extraction are subjected to noise reduction processing.

3. The gas pipeline network monitoring method based on smart gas according to claim 1 is characterized in that: The gas network monitoring model includes: An input layer, used to input the pre-processed pipeline pressure data, gas flow data and gas concentration data; A feature extraction layer, used for extracting features from the preprocessed pipeline pressure data, gas flow data and gas concentration data; Nonlinear transformation layer, used to capture the nonlinear relationship between the extracted features; The feature interaction layer is used to evaluate the correlation between different features; The output layer is used to output the anomaly detection score of the gas pipeline network.

4. The gas pipeline network monitoring method based on smart gas according to claim 3 is characterized in that: The feature extraction layer comprises: Pipeline pressure change rate extraction function, used to extract features from pipeline pressure data; Gas flow rate change rate extraction function, used to extract features from gas flow data; The gas concentration change rate extraction function is used to extract features from gas concentration data.

5. A gas pipeline network monitoring system based on smart gas, characterized in that: The monitoring system includes a management platform, a sensor network platform and an object platform which are communicatively connected in sequence, and the management platform includes: An acquisition module, used for acquiring pipeline pressure data, gas flow data and gas concentration data of the gas pipeline network in real time; A preprocessing module, used for preprocessing the pipeline pressure data, gas flow data and gas concentration data; The identification module is used to perform real-time monitoring of the pre-processed pipeline pressure data, gas flow data and gas concentration data based on the trained gas pipeline network monitoring model to identify whether there is an abnormality in the gas pipeline network, wherein the gas pipeline network monitoring model introduces multiple extraction functions to extract features of the pipeline pressure data, gas flow data and gas concentration data respectively and perform comprehensive calculations to evaluate the overall health status of the gas pipeline network to be tested.

6. A gas pipeline network monitoring system based on smart gas according to claim 5, characterized in that: The preprocessing module comprises: A cleaning submodule, used for cleaning the pipeline pressure data, gas flow data and gas concentration data; A standardization processing submodule, used for standardizing the pipeline pressure data, gas flow data and gas concentration data after cleaning; A feature extraction submodule, used for extracting features from the pipeline pressure data, gas flow data and gas concentration data after standardization; The denoising submodule is used to perform denoising on the pipeline pressure data, gas flow data and gas concentration data after feature extraction.

7. A storage medium, characterized in that: The method comprises instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 4.

8. An electronic device, characterized in that: The electronic device comprises: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

Images