A method and system for monitoring steady-state operation of a gas pipeline
Through multi-scale analysis and significance value calculation, the problem of inaccurate pressure detection of gas pipelines is solved, accurate monitoring and abnormal detection of internal pressure changes in pipelines is achieved, and the monitoring efficiency and accuracy of gas pipeline operation status is improved.
Patent Information
- Application Number
- CN202410788210.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-19
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-06-19
AI Technical Summary
There is a problem of inaccurate pressure detection results during the gas pipeline during the transportation process, which is mainly due to the fact that the external inspection noise of the pipeline affects the authenticity of the data.
By using multi-scale analysis method, by obtaining pressure data and flow data in the gas pipeline, the extension rules of pressure data are determined, the degree of mutation and chaos of the target data segment are calculated, and the Pearson correlation coefficient and the number of extreme points of the flow data are combined. , calculate the significance value of the pressure data and perform abnormal detection to improve detection accuracy.
Through multi-scale analysis and significance value calculation, we can have a more comprehensive understanding of the pressure changes in the pipeline, capture the sudden pressure situation, improve the efficiency and accuracy of gas pipeline operation status monitoring, and reduce the impact of noise interference.
Smart Images

Figure CN118606863B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing. The present invention relates to a method and system for monitoring the steady-state operation of a gas pipeline. Background Art
[0002] Gas is flammable and explosive, so its safety during transportation is extremely important, which places high demands on the reliability of gas pipelines. Gas pipelines may have certain safety risks when transporting flammable gases such as natural gas. For example, accidents such as leakage and explosion can cause serious harm to personnel and the environment. In order to ensure the safe operation of gas pipelines, effective monitoring methods and measures must be adopted.
[0003] The patent application document with publication number CN116480955A discloses a system for monitoring and accurately locating leaks in underground gas pipelines. A laser remote sensing detector is installed on a track robot outside the pipeline to patrol around the pipeline. The change in methane gas concentration is monitored to accurately locate the gas pipeline leak. The pressure and flow signals of the gas pipeline are monitored inside the pipeline. The leak of the gas pipeline network is identified by comparing the real-time monitoring value with the simulation value. A leak location model is established to solve the leak position and accurately determine the location of the leak. The fusion of outside-pipe monitoring and inside-pipe monitoring is used to work together to accurately locate the leak point regardless of whether the leak is small or serious.
[0004] Although the above operation can accurately locate the leakage point of the underground gas pipeline, the pipeline is also inspected outside during the internal monitoring, which may generate certain noise and affect the authenticity of the relevant data collected internally, resulting in inaccurate pressure detection results of the gas pipeline. Summary of the invention
[0005] In order to solve the above-mentioned technical problem of how to improve the accuracy of gas pipeline pressure detection results, the present invention provides solutions in the following aspects.
[0006] In a first aspect, a method for monitoring steady-state operation of a gas pipeline comprises:
[0007] Collect pressure data and flow data in the gas pipeline at multiple sampling times to obtain a pressure data set and a flow data set;
[0008] Determine an extension rule for any pressure data in the pressure data set, wherein the extension rule is to define multiple scales, and at each scale, obtain a corresponding target data segment with each pressure data as the center;
[0009] Obtaining the mutation degree of the target data segment; the mutation degree of the target data segment for: , It indicates that in a pressure data set, in one scale, in addition to the corresponding target data segment, the number of reference data segments with the same length as the target data segment is selected. Indicates the degree of confusion of the target data segment. Indicates the degree of confusion of the reference data segment, represents the information entropy of the target data segment, is a normalized function; the degree of chaos is used to characterize the fluctuation within the data segment;
[0010] The mean of the sum of the differences between the mutation degrees of the target data segment and all the reference data segments is taken as the significance value of the pressure data at the corresponding scale, and then the final significance value of the pressure data is obtained, and then the final significance value of all the pressure data is obtained;
[0011] Anomaly detection is performed on the pressure data in the gas pipeline based on the final significance value.
[0012] Beneficial effects: By determining the extension rules in the pressure data set and obtaining the target data segment of each pressure data at multiple scales, the pressure changes inside the pipeline can be analyzed at multiple scales, so as to have a more comprehensive understanding of the operation status of the pipeline. The corresponding mutation degree is calculated for the target data segment and all reference data segments, which can effectively capture the mutation of the pressure inside the pipeline. The mean of the sum of the differences between the mutation degree of the target data segment and the mutation degree of all reference data segments is taken as the significance of the pressure data, so as to quantify the importance of each pressure data at multiple scales and better reflect the authenticity of the pressure data. Based on the final significance value of all pressure data, anomaly detection can be automatically performed to timely discover abnormal conditions inside the pipeline, thereby improving the efficiency and accuracy of pipeline operation status monitoring.
[0013] In one embodiment, defining a plurality of scales comprises:
[0014] For any pressure data, multiple pressure data are selected from the corresponding sampling time forward as the initial scale;
[0015] Starting from an initial scale corresponding to any pressure data, a set number of pressure data is sequentially added until the extended scale reaches the set number of scales, thereby obtaining different scales.
[0016] Beneficial effects: Multiple scales can reflect changes in pressure data. Smaller scales may be more likely to capture fluctuations and mutations in pressure data in the short term, while larger scales are more suitable for observing long-term trends. Therefore, multi-scale analysis can help determine the rate and period of change of pressure data.
[0017] In one embodiment, the degree of confusion of the target data segment is:
[0018]
[0019] In the formula, Indicates the degree of confusion of the target data segment. represents the total number of valid pressure data in the target data segment, which is equal to the total pressure data in the target data segment minus the pressure data at the first and last ends thereof. Indicates the first The cosine value of the angle between a data point and the lines connecting the data points on both sides. represents the kurtosis in the target data segment, is the normalization function, Expressed as a natural constant e The exponential function of base .
[0020] Beneficial effects: The local characteristics of the pressure data are considered and the results are made more comparable through normalization. When the degree of confusion of a data segment is significantly higher than that of other data segments, it may indicate that the data segment is abnormal and requires further attention and analysis.
[0021] In one embodiment, after obtaining the significance value of the pressure data at the corresponding scale, the method further includes:
[0022] Calculate the weight of the significance value of the pressure data at each scale;
[0023] The weight of the significance for: ; Indicates the weight factor corresponding to the pressure data at each scale, Indicates the total number of all scales corresponding to the pressure data.
[0024] Beneficial effects: The importance of stress data at multiple scales is quantified by weighting the significance values, and it is ensured that stress data at each scale is appropriately considered in the comprehensive analysis.
[0025] In one embodiment, the weight factor is:
[0026]
[0027] In the formula, represents the weight factor, The Pearson correlation coefficient of the pressure data set and the flow data set at the sampling time corresponding to the target data segment of the pressure data at any scale, Indicates the mutation degree of the target data segment, , They represent the number of extreme points of the pressure data set and the number of extreme points of the flow data set at the corresponding sampling time in the target data segment of the pressure data at the corresponding scale, respectively. is the normalization function, Expressed as a natural constant e The exponential function of base .
[0028] Beneficial effect: The introduction of weight factors helps to emphasize or weaken the impact of pressure data at certain scales.
[0029] In one embodiment, the final significance value is:
[0030]
[0031] In the formula, represents the significance value of the pressure data at the corresponding scale, represents the final significance value of the pressure data, The weight representing the significance value of the pressure data at each scale.
[0032] In one embodiment, anomaly detection of pressure data in the gas pipeline based on the final significance value of all pressure data includes: presetting a threshold, comparing all final significance values with the threshold respectively, and when the final significance value exceeds the threshold, the pressure data in the gas pipeline is abnormal.
[0033] In a second aspect, a gas pipeline steady-state operation monitoring system includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the gas pipeline steady-state operation monitoring method according to the first aspect of the present invention is implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:
[0035] Figure 1 It is a method flow chart of steps S1-S5 in a method for monitoring steady-state operation of a gas pipeline in an embodiment of the present invention. DETAILED DESCRIPTION
[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0037] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
[0038] Reference Figure 1 A method for monitoring the steady-state operation of a gas pipeline includes steps S1-S5, which are as follows:
[0039] S1: Collect pressure data and flow data in the gas pipeline at multiple sampling times to obtain a pressure data set and a flow data set.
[0040] When collecting pressure data and flow data in the gas pipeline, it is necessary to ensure that the data are collected in the same time period and start at the same time. In an embodiment of the present invention, a pressure sensor and a turbine flowmeter can be used to collect pressure data and flow data respectively. The collection time for these two types of data is 30 minutes, and the collection frequency is once per second. The collected pressure data and flow data are digitized using an analog-to-digital conversion device to obtain a pressure data set and a flow data set.
[0041] S2: Determine an extension rule for any pressure data in the pressure data set, wherein the extension rule is to define multiple scales, and at each scale, obtain a corresponding target data segment with each pressure data as the center.
[0042] In the embodiment of the present invention, the CA algorithm is used to perform significance detection on the pressure data in the gas pipeline, and the data is observed and analyzed at multiple scales. Considering the influence of the data changes at these different scales on determining whether the pressure data is significant, an extension rule is determined.
[0043] Specifically, in the embodiment of the present invention, determining the extension rule includes:
[0044] For each pressure data, as the endpoint at the end of its corresponding scale, 100 pressure data are selected as the initial scale at the corresponding sampling time, and significance detection is performed on this scale. For the data at the starting end of the initial scale, if the amount of data before it is not enough to constitute a scale of 100 data, data extension can be used to supplement part of the data for subsequent analysis. The means of data extension is to collect pressure data before selecting the data segment for analysis. The amount of data extended between adjacent scales for each pressure data is 100 data, and the upper limit of the extended scale is 5 scales.
[0045] Exemplarily, an initial scale of one pressure data is taken as an example for smoothing, and 100 adjacent data are taken to obtain the second scale. The number of data of the second scale is 200, and so on to obtain the fifth scale.
[0046] Taking the initial scale selected above as an example, with its corresponding pressure data as the center, 50 data are selected to the left and right to form a data segment, and it is used as the target data segment of the pressure data at the corresponding scale for subsequent analysis.
[0047] S3: Obtain the mutation degree of the target data segment.
[0048] After determining the extension rules for each pressure data, it is necessary to analyze the mutations of the target data segments corresponding to each pressure data at multiple scales.
[0049] In the embodiment of the present invention, the disorder degree of the target data segment is obtained according to the data fluctuation of the target data segment corresponding to each pressure data at multiple scales.
[0050] Specifically, a rectangular coordinate system is established according to the pressure data set, wherein the abscissa is the sampling time and the ordinate is the value corresponding to the pressure data.
[0051] Randomly select The pressure data is in The target data segment at each scale is selected from the target data segment. Y The pressure data is used to calculate the cosine value of the angle between it and the adjacent two data. Since the data at the beginning and end of the target data segment do not have this indicator, the two data at the beginning and end need to be excluded when selecting. The cosine value of the angle between a data point and the line connecting the data points on both sides. Count the number of values of different sizes that appear in the target data segment. Each value is recorded as a class and counted as , and then calculate the first The frequency of occurrence of class values, as well as the mean and standard deviation of the frequency of occurrence of all classes in the target data segment.
[0052] The calculation formula for the degree of confusion of the above target data segment is as follows:
[0053]
[0054] In the formula, Indicates the degree of confusion of the target data segment. Indicates the total number of valid pressure data in the target data segment. Indicates the first The cosine value of the angle between a data point and the lines connecting the data points on both sides. represents the kurtosis in the target data segment, is the normalization function, Expressed as a natural constant e An exponential function with a base of , wherein the total number of valid pressure data is equal to the total pressure data in the target data segment minus the pressure data at its first and last ends.
[0055] Among them, the kurtosis The specific calculation formula is:
[0056]
[0057] In the formula, Indicates the first The probability of the class value appearing, and They represent the mean and standard deviation of the occurrence probability of all classes in the data segment.
[0058] The angle The value range of is between 0 and 360 degrees, and the value range of its cosine is The larger the value is, the sharper the shape of the angle is. The more data with drastic changes exist in the target data segment, and the more the kurtosis value in the target data segment deviates from 3, the greater the degree of confusion is.
[0059] The above calculation formula can be used to obtain the degree of confusion of the target data segment corresponding to each pressure data at multiple scales. However, when analyzing the mutation of the target data segment corresponding to each pressure data at multiple scales, it may be affected by local data, resulting in a deviation in the accuracy of the assessment of its degree of confusion. Therefore, it is also necessary to analyze the differences in the degree of confusion between multiple data segments to obtain the degree of mutation of the target data segment corresponding to each pressure data at multiple scales.
[0060] Specifically, in the pressure data set, for each target data segment, multiple reference data segments of the same length are selected at the same scale, and the total number of reference data segments is recorded as .
[0061] Similarly, the disorder degree of the reference data segment can be obtained according to the method of obtaining the disorder degree of the target data segment.
[0062] Then the mutation degree of the target data segment is:
[0063]
[0064] In the formula, Indicates the mutation degree of the target data segment, Indicates the degree of confusion of the target data segment. Indicates the degree of confusion of the reference data segment, represents the information entropy of the target data segment, is the normalization function.
[0065] in, The specific calculation formula is as follows:
[0066]
[0067] In the formula, Indicates e The logarithmic function with base .
[0068] The greater the difference between the degree of chaos of the target data segment and the degree of chaos of all reference data segments, and the greater the value of the information entropy, the more chaotic the numerical distribution in the corresponding target data segment is. The greater the degree of chaos in the target data segment, the higher the credibility is, and the greater the corresponding mutation degree is.
[0069] After obtaining the mutation degree of the target data segment, the mutation degree of the reference data segment can be obtained similarly.
[0070] S4: taking the mean of the sum of the differences in the mutation degrees between the target data segment and all the reference data segments as the significance value of the pressure data at the corresponding scale, and then obtaining the final significance value of the pressure data, and then obtaining the final significance value of all the pressure data.
[0071] The mean of the sum of the differences in the mutation degrees between the target data segment and all reference data segments is taken as the significance value at the corresponding scale of the pressure data, and then the abnormality of the pressure data at multiple scales is evaluated.
[0072] The calculation formula for the significance value under the above corresponding scale is:
[0073]
[0074] In the formula, Indicates the significance value of the pressure data at the corresponding scale, Indicates the mutation degree of the target data segment, Indicates the degree of mutation of the reference data segment.
[0075] However, in the actual process of collecting pressure data in the gas pipeline, pressure noise data will be generated due to factors such as the external environment, which is numerically very similar to the actual abnormal pressure data. Therefore, the mutation degree of the target data segment corresponding to any pressure data obtained at multiple scales cannot accurately reflect the abnormal situation of a pressure data at multiple scales.
[0076] The relationship between pressure and flow in a gas pipeline is determined by a variety of factors, including the geometry of the pipeline, the material of the pipeline, the properties of the fluid, and the operating conditions of the pipeline. Generally speaking, there is a certain correlation between pressure and flow, which can be understood through the basic fluid mechanics principles of gas pipelines. Generally speaking, the higher the pressure in the gas pipeline, the greater the corresponding resistance, resulting in a decrease in the speed of the fluid flowing through the pipeline, thereby reducing the flow.
[0077] Therefore, in this embodiment, by analyzing the correlation between each pressure data and its flow data corresponding to the same sampling time at multiple scales, the mutation degree of the target data segment of each pressure data at multiple scales is adjusted to obtain the weight of the significance value of each pressure data at multiple scales.
[0078] First, calculate the Pearson correlation coefficient of the pressure data set and flow data set at the sampling time corresponding to the data segment of any pressure data at multiple scales. The calculation formula of the Pearson correlation coefficient is as follows:
[0079]
[0080] In the formula, The Pearson correlation coefficient of the pressure data set and the flow data set at the sampling time corresponding to the target data segment, represents the covariance of the pressure data set and the flow data set in the sampling period, Represents the standard deviation product of the pressure dataset and the flow dataset in the sampling period.
[0081] Secondly, the number of extreme points of the pressure data set and the flow data set at the sampling time corresponding to the target data segment are obtained respectively, and the difference value of the number of extreme points of the pressure data set and the flow data set is obtained. The weight factor of the significance value of each pressure data at multiple scales is obtained by combining the above-mentioned Pearson correlation coefficient and the mutation degree of the target data segment.
[0082] The calculation formula for the weight factor of the significance value of each of the above pressure data at multiple scales is as follows:
[0083]
[0084] In the formula, represents the weight factor, The Pearson correlation coefficient of the pressure data set and the flow data set at the sampling time corresponding to the target data segment of the pressure data at any scale, Indicates the mutation degree of the target data segment, , They represent the number of extreme points of the pressure data set and the number of extreme points of the flow data set at the corresponding sampling time in the target data segment of the pressure data at the corresponding scale, respectively. is the normalization function, Expressed as a natural constant e The exponential function of base .
[0085] After obtaining the weight factors of the significance values of each pressure data at multiple scales, they can be introduced to obtain the weights of the corresponding significance values, thereby emphasizing or weakening the influence of the pressure data at certain scales.
[0086] Among them, the weight of the corresponding significance value is:
[0087]
[0088] In the formula, Represents the weight of the significance value corresponding to the pressure data at multiple scales, Indicates the weight factor corresponding to the pressure data at each scale, Indicates the total number of all scales corresponding to the pressure data.
[0089] The closer the value of the Pearson correlation coefficient is to -1, the stronger the negative correlation between the two data sets is. The greater the possibility that the mutation degree in the data segment at this scale is caused by the real anomaly generated by the pressure data itself, the more real the data is, and the greater the weight that this scale should receive. The greater the difference in the number of extreme points, the stronger the negative correlation between the two data is, and the greater the credibility is. It can also prove that the data is more real, and the greater the weight that this scale should receive.
[0090] It should be noted that, in other embodiments, when a pressure data contains multiple significance values, the method that may need to integrate these values to obtain a final significance value may be to directly calculate the arithmetic mean of all significance values, or to select the median of all significance values as the final significance value.
[0091] In the embodiment of the present invention, after obtaining the weights of the significance corresponding to the pressure data at multiple scales, the final significance value of the pressure data may be calculated.
[0092] The calculation formula for the final significance value of the above pressure data is as follows:
[0093] In the formula, Indicates the significance value of the pressure data at the corresponding scale, represents the final significance value of the pressure data, The weight representing the significance value of pressure data at each scale.
[0094] S5: Perform anomaly detection on the pressure data in the gas pipeline based on the final significance value.
[0095] Specifically, a threshold is set in advance, and all final significance values are compared with the threshold. In the embodiment of the present invention, the threshold is set to 0.7, and the significance values of all pressure data are compared with the set threshold. Pressure data exceeding 0.7 are regarded as abnormal points. These abnormal points may indicate abnormal conditions in the pipeline, such as leakage, blockage or other faults.
[0096] For the detected abnormal points, appropriate measures can be taken to deal with the abnormalities, such as repairing the pipeline, adjusting operating parameters, or taking emergency measures to ensure the safety of the pipeline.
[0097] The present invention can help improve the robustness of the significance detection algorithm by obtaining the mutation degree of the data segment corresponding to each pressure data at multiple scales and calculating the weight information of the pressure data and the flow data, so as to obtain a more accurate significance value for each pressure data, and can perform comprehensive anomaly detection on the pressure data in the entire pipeline, thereby obtaining a more accurate pressure data anomaly detection result, thereby avoiding the situation where the accuracy of the pressure detection result of the gas pipeline is reduced due to noise data generated by interference from the external environment.
[0098] The system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for monitoring the steady-state operation of a gas pipeline according to the first aspect of the present invention is implemented.
[0099] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.
[0100] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.
[0101] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly defined.
[0102] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.
Claims
1. A method for monitoring steady-state operation of a gas pipeline, characterized in that: include: Collect pressure data and flow data in the gas pipeline at multiple sampling times to obtain a pressure data set and a flow data set; Determine an extension rule for any pressure data in the pressure data set, wherein the extension rule is to define multiple scales, and at each scale, obtain a corresponding target data segment with each pressure data as the center; Obtaining the mutation degree of the target data segment; the mutation degree of the target data segment for: , It indicates that in a pressure data set, in one scale, in addition to the corresponding target data segment, the number of reference data segments with the same length as the target data segment is selected. Indicates the degree of confusion of the target data segment. Indicates the degree of confusion of the reference data segment, represents the information entropy of the target data segment, is a normalization function; the chaos degree is used to characterize the fluctuation within the data segment; the mean of the sum of the differences between the mutation degrees of the target data segment and all the reference data segments is taken as the significance value of the pressure data at the corresponding scale, the weights of the significance values of the pressure data at multiple scales are calculated, and then the final significance value of the pressure data is obtained, and then the final significance value of all the pressure data is obtained; Anomaly detection is performed on the pressure data in the gas pipeline based on the final significance value.
2. A gas pipeline steady-state operation monitoring method according to claim 1, characterized in that: Defining multiple scales includes: For any pressure data, multiple pressure data are selected from the corresponding sampling time forward as the initial scale; Starting from an initial scale corresponding to any pressure data, a set number of pressure data is sequentially added until the extended scale reaches the set number of scales, thereby obtaining different scales.
3. A gas pipeline steady-state operation monitoring method according to claim 2, characterized in that: The degree of confusion of the target data segment is: ; In the formula, Indicates the degree of confusion of the target data segment. represents the total number of valid pressure data in the target data segment, which is equal to the total pressure data in the target data segment minus the pressure data at the first and last ends thereof. Indicates the first The cosine value of the angle between a data point and the lines connecting the data points on both sides. represents the kurtosis in the target data segment, is the normalization function, Indicated by natural constant e The exponential function of base .
4. A gas pipeline steady-state operation monitoring method according to claim 3, characterized in that: Calculating the weights of the significance values of the pressure data at multiple scales, including: Calculate the weight of the significance value of the pressure data at each scale; The weight of the significance for: ; Indicates the weight factor corresponding to the pressure data at each scale, Indicates the total number of all scales corresponding to the pressure data.
5. A gas pipeline steady-state operation monitoring method according to claim 4, characterized in that: The weighting factor is: ; In the formula, represents the weight factor, The Pearson correlation coefficient of the pressure data set and the flow data set at the sampling time corresponding to the target data segment of the pressure data at any scale, Indicates the mutation degree of the target data segment, , They represent the number of extreme points of the pressure data set and the number of extreme points of the flow data set at the corresponding sampling time in the target data segment of the pressure data at the corresponding scale, respectively. is the normalization function, Indicated by natural constant e The exponential function of base .
6. A gas pipeline steady-state operation monitoring method according to claim 5, characterized in that: The final significance value is: ; In the formula, represents the significance value of the pressure data at the corresponding scale, represents the final significance value of the pressure data, The weight representing the significance value of the pressure data at each scale.
7. A gas pipeline steady-state operation monitoring method according to claim 6, characterized in that: Anomaly detection of pressure data in the gas pipeline according to the final significance value of all pressure data includes: presetting a threshold, comparing all final significance values with the threshold respectively, and when the final significance value exceeds the threshold, the pressure data in the gas pipeline is abnormal.
8. A gas pipeline steady-state operation monitoring system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the gas pipeline steady-state operation monitoring method according to any one of claims 1 to 7 is implemented.
