Big data-based digital risk management and control analysis method and system, and medium

Abstract

The application relates to the technical field of pressure data processing, in particular to a digital risk management and control analysis method and system based on big data and a medium, the method comprising the following steps: acquiring initial pressure signals of an oil and gas pipeline to be detected at different preset positions, and determining fluctuation factors corresponding to each initial pressure signal; correcting each initial pressure signal; determining a sub-pipeline between each adjacent preset position as a target sub-pipeline, and performing pipeline leakage pressure change rule analysis and processing on each target sub-pipeline according to target pressure signals at the preset positions adjacent to each target sub-pipeline; and according to leakage risk signals corresponding to the target sub-pipeline, screening out leakage sub-pipelines from all target sub-pipelines, and determining leakage positions of each leakage sub-pipeline. Through data processing on the initial pressure signals, the application realizes leakage detection of the oil and gas pipeline, and improves the accuracy of leakage detection of the oil and gas pipeline.

Description

Technical Field

[0001] This invention relates to the field of pressure data processing technology, specifically to a digital risk management and control analysis method, system, and medium based on big data. Background Technology

[0002] With the development of technology, the application of digital risk management and analysis based on big data is becoming increasingly widespread. For example, it can be applied to the detection of leaks in oil and gas pipelines. Oil and gas pipeline media are flammable and explosive; once a large-scale leak occurs, it can easily trigger explosions and other accidents, causing casualties, property damage, and environmental pollution. Therefore, timely detection of oil and gas pipeline leaks and the implementation of effective measures are crucial.

[0003] Currently, the common method for detecting leaks in oil and gas pipelines is to use pressure sensors to collect pressure values ​​to determine whether there is a leak. Generally speaking, the lower the collected pressure value, the more likely there is a leak in the oil and gas pipeline.

[0004] However, when using pressure values ​​collected by pressure sensors to determine whether there is a leak in an oil or gas pipeline, the following technical problems often arise:

[0005] Since the ground along the route of oil and gas pipelines is often not flat, and the undulating terrain may cause local compression of the pipelines, resulting in increased pressure, even a small leak may not reduce the pressure. If only the pressure value is considered when detecting leaks in oil and gas pipelines, the leak may be overlooked, leading to poor accuracy in leak detection. Summary of the Invention

[0006] To address the technical problem of poor accuracy in detecting leaks in oil and gas pipelines, this invention proposes a digital risk management and control analysis method, system, and medium based on big data.

[0007] In a first aspect, the present invention provides a digital risk management and analysis method based on big data, the method comprising:

[0008] The initial pressure signals of the oil and gas pipeline to be inspected at different preset locations are obtained, and the fluctuation factor corresponding to each initial pressure signal is determined according to the height of the preset location corresponding to each initial pressure signal and its adjacent initial pressure signals. The height of different preset locations represents the height of different parts of the oil and gas pipeline to be inspected.

[0009] Based on the fluctuation factor corresponding to each initial pressure signal, each initial pressure signal is corrected to obtain the target pressure signal corresponding to each initial pressure signal.

[0010] The sub-pipes between each adjacent preset position are identified as target sub-pipes. Based on the target pressure signal at the preset position adjacent to each target sub-pipe, the leakage pressure change law of each target sub-pipe is analyzed and processed to obtain the leakage risk signal corresponding to each target sub-pipe.

[0011] Based on the leakage risk signal corresponding to the target sub-pipe, the leaking sub-pipe is selected from all the target sub-pipes, and the leakage location of each leaking sub-pipe is determined.

[0012] In conjunction with the first aspect above, in one possible implementation, determining the fluctuation factor corresponding to each initial pressure signal based on the height of a preset position corresponding to each initial pressure signal and its adjacent initial pressure signals includes:

[0013] The height of the preset position corresponding to each initial pressure signal and the variance of the height of the preset position corresponding to the adjacent initial pressure signals are determined as the initial fluctuation factor corresponding to each initial pressure signal.

[0014] Based on the initial fluctuation factor corresponding to each initial pressure signal, the fluctuation factor corresponding to each initial pressure signal is determined, wherein the initial fluctuation factor and the fluctuation factor are positively correlated.

[0015] In conjunction with the first aspect above, in one possible implementation, the step of correcting each initial pressure signal based on the fluctuation factor corresponding to each initial pressure signal to obtain the target pressure signal corresponding to each initial pressure signal includes:

[0016] If the fluctuation factor corresponding to the initial pressure signal is greater than the preset fluctuation threshold, the initial pressure signal is reduced according to the fluctuation factor corresponding to the initial pressure signal to obtain the target pressure signal corresponding to the initial pressure signal.

[0017] If the fluctuation factor corresponding to the initial pressure signal is less than or equal to the preset fluctuation threshold, then the initial pressure signal is determined as the target pressure signal.

[0018] In conjunction with the first aspect above, in one possible implementation, the step of analyzing the leakage pressure variation pattern of each target sub-pipe based on the target pressure signal at a preset location adjacent to each target sub-pipe to obtain a leakage risk signal corresponding to each target sub-pipe includes:

[0019] Each target pressure signal is divided into equal parts, and the sub-signals obtained from the division are used as window signals to obtain the window signal sequence corresponding to each target pressure signal, wherein the window signal sequence is a time series;

[0020] Based on the window signal at the same position in the window signal sequence corresponding to the target pressure signal at the preset position adjacent to each target sub-pipe, the pipeline leakage pressure change law is analyzed and processed to obtain the target risk signal sequence corresponding to each target sub-pipe;

[0021] The leakage risk signal for each target sub-pipeline is formed by combining all target risk signals in the target risk signal sequence.

[0022] In conjunction with the first aspect mentioned above, in one possible implementation, the formula for the target risk signal in the target risk signal sequence corresponding to the target sub-pipeline is:

[0023] E jt =norm(E jt1 ×E jt2 );

[0024]

[0025] Among them, E jt It is the target risk signal between the t-th window signals in the window signal sequence corresponding to the target pressure signals at two preset positions adjacent to the j-th target sub-pipe, denoted as the t-th target risk signal in the target risk signal sequence corresponding to the j-th target sub-pipe; j is the sequence number of the target sub-pipe; t is the sequence number of the target risk signal in the target risk signal sequence or the sequence number of the window signal in the window signal sequence; norm() is the normalization function; E jt1 It is the first risk signal between the t-th window signals in the window signal sequence corresponding to the target pressure signals at two preset positions adjacent to the j-th target sub-pipe; E jt2 It is the second risk signal between the t-th window signals in the window signal sequence corresponding to the target pressure signals at two preset positions adjacent to the j-th target sub-pipe; μ jt It is the t-th window signal in all window signal sequences, except for and The mean of all window signals except those in the window; It is the t-th window signal in the window signal sequence corresponding to the first target pressure signal among the target pressure signals at two preset positions adjacent to the j-th target sub-pipe; It is the t-th window signal in the window signal sequence corresponding to the second target pressure signal among the target pressure signals at two preset positions adjacent to the j-th target sub-pipe; exp() is the natural exponential function; || is the absolute value function; It is the t-th window signal in the window signal sequence corresponding to the first target pressure signal among the target pressure signals at the two preset positions closest to the j-th target sub-pipe; It is the t-th window signal in the window signal sequence corresponding to the second target pressure signal among the two preset positions closest to the j-th target sub-pipe.

[0026] In conjunction with the first aspect above, in one possible implementation, the step of selecting the leaking sub-pipe from all target sub-pipes based on the leakage risk signal corresponding to the target sub-pipe includes:

[0027] If there are elements in the leakage risk signal corresponding to the target sub-pipe that are greater than the preset risk threshold, then the target sub-pipe will be identified as a leaking sub-pipe.

[0028] In conjunction with the first aspect above, in one possible implementation, determining the leak location of each leaking sub-pipe includes:

[0029] Based on the target pressure signal at a preset location adjacent to the target sub-pipe, and the length of the target sub-pipe, the formula corresponding to the pressure change rate of the target sub-pipe is determined as follows:

[0030] Where v is the pressure change rate corresponding to the target sub-pipe; L is the length of the target sub-pipe; || is the absolute value function; a1 is the average of all pressure values ​​in the first target pressure signal among the target pressure signals at two preset positions adjacent to the target sub-pipe; a2 is the average of all pressure values ​​in the second target pressure signal among the target pressure signals at two preset positions adjacent to the target sub-pipe.

[0031] Based on the pressure change rate of the target sub-pipe adjacent to the leaking sub-pipe and the length of the leaking sub-pipe, the formula for evaluating the overall leakage pressure corresponding to the leaking sub-pipe is as follows:

[0032] Where, x k v is the overall leakage pressure corresponding to the k-th leaking sub-pipe; k is the sequence number of the leaking sub-pipe; k1 It is the rate of pressure change corresponding to the target sub-pipe preceding the k-th leaking sub-pipe; v k2 It is the rate of pressure change corresponding to the next target sub-pipe after the k-th leaking sub-pipe; a k,1 It is the average of all pressure values ​​in the target pressure signal at a preset position between the k-th leaking sub-pipe and its preceding target sub-pipe; a k,2 It is the average of all pressure values ​​in the target pressure signal at the preset position between the k-th leaking sub-pipe and the next target sub-pipe; L k It is the length of the k-th leaking sub-pipe;

[0033] The leakage location of each leaking sub-pipe is determined based on the overall leakage pressure corresponding to the leaking sub-pipe, the pressure change rate corresponding to the previous target sub-pipe, and the target pressure signal at a preset position between the leaking sub-pipe and its previous target sub-pipe.

[0034] In conjunction with the first aspect mentioned above, in one possible implementation, the formula corresponding to the leakage location of the leaking sub-pipe is:

[0035] p k =v k1 ×(a k,1 -x k ); where p k It represents the leak location corresponding to the kth leaking sub-pipe, indicating the distance from the leak point on the kth leaking sub-pipe to the front end of the kth leaking sub-pipe.

[0036] Secondly, the present invention provides a digital risk management and analysis system based on big data. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When executed by the processor, the computer program implements the method described in the first aspect or any possible implementation thereof. The system includes the following modules:

[0037] The acquisition and determination module is used to acquire the initial pressure signals of the oil and gas pipeline to be detected at different preset positions, and to determine the fluctuation factor corresponding to each initial pressure signal based on the height of the preset position corresponding to each initial pressure signal and its adjacent initial pressure signals. The height of different preset positions represents the height of different parts of the oil and gas pipeline to be detected.

[0038] The signal correction module is used to correct each initial pressure signal according to the fluctuation factor corresponding to each initial pressure signal, so as to obtain the target pressure signal corresponding to each initial pressure signal.

[0039] The analysis and processing module is used to identify the sub-pipes between each adjacent preset position as target sub-pipes, and to analyze the leakage pressure change pattern of each target sub-pipe based on the target pressure signal at the preset position adjacent to each target sub-pipe, so as to obtain the leakage risk signal corresponding to each target sub-pipe.

[0040] The location determination module is used to filter out the leaking sub-pipes from all target sub-pipes based on the leakage risk signal corresponding to the target sub-pipe, and determine the leakage location of each leaking sub-pipe.

[0041] Thirdly, a server is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the device to perform the methods of the first aspect or any possible implementation thereof.

[0042] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0043] Fifthly, a digital risk management and analysis medium based on big data is provided, which stores computer program code. When the computer program code is run on a computer, it causes the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0044] The present invention has the following beneficial effects:

[0045] This invention presents a big data-based digital risk management and analysis method for detecting leaks in oil and gas pipelines. By processing initial pressure signals, it achieves leak detection and solves the technical problem of poor accuracy in oil and gas pipeline leak detection, thereby improving the accuracy of leak detection. Compared to oil and gas pipeline leak detection that only considers the magnitude of the collected pressure values, this invention comprehensively considers the height of each initial pressure signal and the preset position corresponding to adjacent initial pressure signals. It quantifies the fluctuation factor, which characterizes the ground undulation at the preset position corresponding to each initial pressure signal, and corrects the initial pressure signal based on the fluctuation factor. This can reduce the impact of pressure increases caused by ground undulation to a certain extent, thereby improving the accuracy of subsequent leak detection of the oil and gas pipelines to be detected. Furthermore, it analyzes and processes the pipeline leakage pressure change law of each target sub-pipeline, quantifies the leakage risk signal characterizing the leakage risk of each target sub-pipeline, thereby improving the accuracy of leak sub-pipeline selection and realizing the location of the leak in the leak sub-pipeline. Secondly, compared to collecting pressure signals only at the end of the oil and gas pipeline and detecting leaks based on the pressure signals at the end of the oil and gas pipeline, this invention collects pressure signals at multiple preset locations, thereby obtaining the pressure conditions at different parts of the oil and gas pipeline, making its pressure information richer. Therefore, leak detection based on pressure signals at multiple preset locations improves the accuracy of leak detection in oil and gas pipelines, thus facilitating the subsequent location of the leak point. Attached Figure Description

[0046] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart of the big data-based digital risk management and analysis method of the present invention;

[0048] Figure 2 This is a schematic diagram showing the different preset position distributions of the present invention;

[0049] Figure 3 This is a schematic diagram of the target sub-pipeline of the present invention;

[0050] Figure 4 This is a schematic diagram of the composition structure of the big data-based digital risk management and analysis system of the present invention;

[0051] Figure 5 This is a schematic diagram of the structure of a computer device according to the present invention.

[0052] The reference numerals in the attached drawings include: a first solid dot 301, a second solid dot 302, a first dashed line 303, and a second dashed line 304. Detailed Implementation

[0053] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the technical solution proposed according to the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0055] refer to Figure 1 The flowchart illustrates some embodiments of the big data-based digital risk management and analysis method of the present invention. This big data-based digital risk management and analysis method includes the following steps:

[0056] Step S1: Obtain the initial pressure signals of the oil and gas pipeline to be detected at different preset locations, and determine the fluctuation factor corresponding to each initial pressure signal based on the height of the preset location corresponding to each initial pressure signal and its adjacent initial pressure signals.

[0057] The oil and gas pipeline to be detected can be the pipeline for which leak detection is performed. An oil and gas pipeline refers to a pipeline used to transport oil or natural gas resources. The initial pressure signal can be a pressure signal collected by a pressure sensor installed at a preset location. The preset location can be a pre-defined position on the same external surface of the pipeline for installing the pressure sensor, and the first and last preset locations can be two endpoints on the same external surface of the pipeline, respectively. For example, different preset locations can represent different positions on the upper external surface of the oil and gas pipeline to be detected, and the endpoints of the upper external surface of the oil and gas pipeline to be detected can also be recorded as preset locations. The distance between adjacent preset locations can be equal. For example, a section of the pipeline constituting the oil and gas pipeline to be detected can be as follows: Figure 2 As shown, Figure 2 The area formed by the two straight lines can represent a section of the pipeline that constitutes the oil and gas pipeline to be inspected. Figure 2 Different solid dots can represent different preset positions. The height of different preset positions can represent the height of different parts of the oil and gas pipeline to be tested, that is, the height of different sub-pipes that constitute the oil and gas pipeline to be tested. Here, the sub-pipes can be small segments of pipeline obtained by dividing the oil and gas pipeline to be tested.

[0058] In reality, the ground where oil and gas pipelines are located is often not entirely on the same horizontal line. Some areas of the ground where oil and gas pipelines are located often have certain undulations, so the elevation of different locations on the ground where the pipelines are located often varies. Therefore, the elevation of different parts of the oil and gas pipeline can be characterized by the elevation of different parts of the pipeline. In the embodiments of this invention, the elevation can be represented by altitude.

[0059] As an example, this step may include the following steps:

[0060] The first step is to obtain the initial pressure signals of the oil and gas pipeline to be tested at different preset locations.

[0061] For example, a pressure sensor installed at a preset location can collect pressure values ​​every second within the current time period. These collected pressure values ​​form a pressure signal, which serves as the initial pressure signal for that preset location. The preset location can be the location corresponding to this initial pressure signal. The current time period can be a time period ending at the current moment. The duration of the current time period can be 10 minutes.

[0062] It should be noted that the pressure sensor can transmit real-time pressure data to the cloud, where it can perform the corresponding complex calculations. The sampling frequency of the pressure sensor at different preset locations remains consistent, and the height information of the pressure sensor's installation location is also recorded.

[0063] The second step is to determine the initial fluctuation factor corresponding to each initial pressure signal by the height of the preset position corresponding to each initial pressure signal and the variance of the height of the preset positions corresponding to adjacent initial pressure signals.

[0064] The third step is to determine the fluctuation factor corresponding to each initial pressure signal based on the initial fluctuation factor corresponding to each initial pressure signal.

[0065] Among them, the initial volatility factor can be positively correlated with the fluctuation volatility factor.

[0066] For example, the formula for determining the fluctuation factor corresponding to the initial pressure signal can be:

[0067] Among them, w i σ is the fluctuation factor corresponding to the i-th initial pressure signal. i is the index of the initial pressure signal. i σ is the initial fluctuation factor corresponding to the i-th initial pressure signal, which is the variance of the height of the preset position corresponding to the i-th initial pressure signal and the height of the preset positions corresponding to its adjacent initial pressure signals. For example, if there are two initial pressure signals adjacent to the i-th initial pressure signal, then σ is... i It can be the variance of the height of the preset position corresponding to the (i-1)th initial pressure signal, the height of the preset position corresponding to the ith initial pressure signal, and the height of the preset position corresponding to the (i+1)th initial pressure signal. σ is the variance of the height of all preset positions. These are pre-set factors greater than 0, mainly used to prevent the denominator from being 0, such as... It can be 0.01.

[0068] It should be noted that in reality, undulating ground can cause localized compression of oil and gas pipelines, leading to increased pressure. Secondly, when the ground is uneven, some heavy hydrocarbon components in the fossil fuels transported in the pipeline are more prone to deposition, resulting in poorer fluidity. Consequently, the corresponding pressure measurements are often higher than normal. i It can characterize the ground unevenness of the road segment where the preset location for collecting the i-th initial pressure signal is located. σ can characterize the overall unevenness of the road segment where the oil and gas pipeline to be detected is located. When w iA higher value often indicates that the road segment where the preset location for collecting the i-th initial pressure signal is located is relatively more uneven than the overall road segment. This often indicates that the road segment where the preset location for collecting the i-th initial pressure signal is located is more likely to be uneven. This often indicates that the i-th initial pressure signal is more likely to be higher. This often indicates that even if there is a leak, the pressure may not be low. This often indicates that it is easier to overlook the leak.

[0069] Step S2: Based on the fluctuation factor corresponding to each initial pressure signal, correct each initial pressure signal to obtain the target pressure signal corresponding to each initial pressure signal.

[0070] As an example, this step may include the following steps:

[0071] The first step is to determine the initial pressure signal as the target pressure signal if the fluctuation factor corresponding to the initial pressure signal is less than or equal to the preset fluctuation threshold.

[0072] The preset fluctuation threshold can be a pre-set threshold. For example, the preset fluctuation threshold can be 0.

[0073] It should be noted that the preset locations for collecting initial pressure signals with fluctuation factors less than or equal to the preset fluctuation threshold are typically located on relatively flat road sections. Conversely, the preset locations for collecting initial pressure signals with fluctuation factors greater than the preset fluctuation threshold are typically located on relatively uneven road sections.

[0074] The second step involves adjusting the initial pressure signal based on its fluctuation factor, if the fluctuation factor is greater than a preset threshold. The formula for obtaining the target pressure signal corresponding to the initial pressure signal is as follows:

[0075] in, This is the target pressure signal corresponding to the initial pressure signal. s is the initial pressure signal. w is the fluctuation factor corresponding to the initial pressure signal. w×s represents multiplying each pressure value in s by w. sw×s represents subtracting the pressure values ​​at the same time in s and w×s.

[0076] It should be noted that a larger w often indicates that the road section where the preset location for collecting the initial pressure signal is located is more likely to be uneven, the initial pressure signal is more likely to be higher, even if a leak exists, the pressure may not be low, the leak is more likely to be overlooked, and the initial pressure signal should be reduced. Therefore, It can characterize s after adaptive reduction.

[0077] Step S3: Determine the sub-pipes between each adjacent preset position as target sub-pipes, and analyze the leakage pressure change pattern of each target sub-pipe based on the target pressure signal at the preset position adjacent to each target sub-pipe to obtain the leakage risk signal corresponding to each target sub-pipe.

[0078] As an example, this step may include the following steps:

[0079] The first step is to identify the sub-pipes between each adjacent preset position as the target sub-pipes.

[0080] like Figure 3 As shown, the first solid dot 301 and the second solid dot 302 can represent adjacent preset positions, and the area between the first dashed line 303 and the second dashed line 304 can represent the sub-pipe between the first solid dot 301 and the second solid dot 302. Therefore, the area between the first dashed line 303 and the second dashed line 304 can represent the target sub-pipe, and the preset position adjacent to the target sub-pipe can include: the preset position represented by the first solid dot 301 and the preset position represented by the second solid dot 302.

[0081] The second step is to divide each target pressure signal into equal parts, and use the sub-signals obtained from the division as window signals to obtain the window signal sequence corresponding to each target pressure signal.

[0082] The window signal sequence can be a time series. The duration of the window signal can be 1 minute.

[0083] The third step involves analyzing the pipeline leakage pressure variation pattern based on the window signal at the same position in the window signal sequence corresponding to the target pressure signal at the preset position adjacent to each target sub-pipeline, thereby obtaining the target risk signal sequence corresponding to each target sub-pipeline.

[0084] Among them, the window signals at the same position in different window signal sequences can be window signals with the same sequence number in different window signal sequences.

[0085] For example, the formula for determining the target risk signal in the target risk signal sequence corresponding to the target sub-pipeline can be:

[0086] E jt =norm(E jt1 ×E jt2 );

[0087]

[0088] Among them, E jtThis is the target risk signal between the t-th window signals in the window signal sequence corresponding to the target pressure signals at two preset positions adjacent to the j-th target sub-pipe, denoted as the t-th target risk signal in the target risk signal sequence corresponding to the j-th target sub-pipe. j is the index of the target sub-pipe, and the value of j can range from {2, 3, ..., N-1}, where N is the number of target sub-pipes. t is the index of the target risk signal in the target risk signal sequence or the index of the window signal in the window signal sequence. norm() is the normalization function. E jt1 It is the first risk signal between the t-th window signals in the window signal sequence corresponding to the target pressure signals at two preset positions adjacent to the j-th target sub-pipe. jt2 It is the second risk signal between the t-th window signals in the window signal sequence corresponding to the target pressure signals at two preset positions adjacent to the j-th target sub-pipe. jt1 ×E jt2 E represents jt1 and E jt2 Multiply the elements at the same time. μ jt It is the t-th window signal in all window signal sequences, except for and The mean of all window signals other than the mean of the window signals is obtained by averaging the elements at the same time in all window signals. These averages at the same time constitute the mean of all window signals. It is the t-th window signal in the window signal sequence corresponding to the first target pressure signal among the target pressure signals at two preset positions adjacent to the j-th target sub-pipe. It is the t-th window signal in the window signal sequence corresponding to the second target pressure signal among the target pressure signals at two preset positions adjacent to the j-th target sub-pipe. express and The elements at the same time point are added together. 2×μ jt Indicates μ jt Multiply each element in by 2. Represents 2×μ jt and Subtract elements at the same time from each other. `exp()` is the natural exponential function. `||` is the absolute value function. It is the t-th window signal in the window signal sequence corresponding to the first target pressure signal among the target pressure signals at the two preset positions closest to the j-th target sub-pipe. It is the t-th window signal in the window signal sequence corresponding to the second target pressure signal among the two preset positions closest to the j-th target sub-pipe. Indicates will Each element in the expression is replaced with its corresponding opposite number. Indicates to and The absolute value of the difference between elements at the same time is calculated. Indicates to and The absolute value of the difference between elements at the same time is calculated. Indicates to Each element in the expression is calculated using the natural exponential function.

[0089] It should be noted that in actual situations, when a pipeline leaks, the pressure at the release point drops. At this time, a negative pressure wave often propagates in a fluctuating manner from the release point in both directions, and can often be detected by the installed pressure sensor. Therefore, the pressure value collected by the pressure sensor closer to the leak point is usually smaller. The release point is also called the leak point. When E jt1 A larger value in the value indicates that the pressure at the preset location adjacent to the j-th target sub-pipe is relatively lower than the overall pressure. This often suggests that the preset location adjacent to the j-th target sub-pipe may be closer to the leak point, and therefore indicates a greater risk of a leak on the j-th target sub-pipe. Generally, the negative pressure wave extends from the leak point along both sides of the pipe, and the pressure values ​​collected by pressure sensors at the same distance from the leak point tend to be quite similar. The smaller the element in the value, the more similar the pressure conditions at the two preset locations adjacent to the j-th target sub-pipe are, the more the pressure conditions at the two preset locations adjacent to the j-th target sub-pipe conform to the pressure change pattern at the leak point, and the more likely a leak point exists on the j-th target sub-pipe. The smaller the element in E, the more similar the pressure conditions at the two preset locations closest to the j-th target sub-pipe tend to be. This often indicates that the pressure conditions at these two preset locations more closely match the pressure change pattern at the leak point, and therefore, a leak point is more likely to exist on the j-th target sub-pipe. Therefore, when E... jt The larger the element in the value, the more likely there is a leak point on the j-th target sub-pipe.

[0090] Optionally, instead of calculating the leakage risk signal corresponding to the target sub-pipeline located at the end of the oil and gas pipeline to be detected, it is also unnecessary to calculate the target risk signal sequence corresponding to the target sub-pipeline located at the end of the oil and gas pipeline to be detected. Therefore, the method for determining whether the target sub-pipeline located at the end of the oil and gas pipeline to be detected is a leaking sub-pipeline can be as follows: The target sub-pipeline located at the end of the oil and gas pipeline to be detected is identified as a candidate sub-pipeline. If the target pressure signal at a preset location adjacent to the candidate sub-pipeline contains a pressure value lower than a preset pressure threshold, then the candidate sub-pipeline is determined to be a leaking sub-pipeline. The preset pressure threshold can be a pre-set minimum pressure allowed when the pipeline does not leak.

[0091] The fourth step is to combine all the target risk signals in the target risk signal sequence corresponding to each target sub-pipeline to form the leakage risk signal corresponding to each target sub-pipeline.

[0092] Step S4: Based on the leakage risk signal corresponding to the target sub-pipe, filter out the leaking sub-pipe from all the target sub-pipes and determine the leakage location of each leaking sub-pipe.

[0093] As an example, this step may include the following steps:

[0094] The first step is to identify the target sub-pipe as a leaking sub-pipe if there are elements in the leakage risk signal that are greater than the preset risk threshold.

[0095] The preset risk threshold can be a pre-set threshold. For example, the preset risk threshold can be 0.7.

[0096] The second step involves determining the formula corresponding to the pressure change rate of the target sub-pipe based on the target pressure signal at a preset location adjacent to the target sub-pipe and the length of the target sub-pipe:

[0097] Where v is the rate of pressure change corresponding to the target sub-pipe. L is the length of the target sub-pipe. || is the absolute value function. a1 is the average of all pressure values ​​in the first target pressure signal among two preset locations adjacent to the target sub-pipe. a2 is the average of all pressure values ​​in the second target pressure signal among two preset locations adjacent to the target sub-pipe.

[0098] It should be noted that v can characterize the average pressure change rate within the target sub-pipe.

[0099] The third step involves evaluating the overall leakage pressure of the leaking sub-pipe based on its pressure change rate and length, using the following formula:

[0100] Where, x k This is the overall leakage pressure corresponding to the k-th leaking sub-pipe. k is the sequence number of the leaking sub-pipe. k1 v is the pressure change rate corresponding to the target sub-pipe preceding the k-th leaking sub-pipe. k2 is the pressure change rate corresponding to the next target sub-pipe after the k-th leaking sub-pipe. k,1 It is the average of all pressure values ​​in the target pressure signal at a preset position between the k-th leaking sub-pipe and its preceding target sub-pipe. k,2 L is the average of all pressure values ​​in the target pressure signal at a preset location between the k-th leaking sub-pipe and its subsequent target sub-pipe. k It is the length of the k-th leaking sub-pipe.

[0101] It should be noted that when a leak occurs in a sub-pipeline, negative pressure waves are often generated along the pipeline from the leak point to both sides. Since one side of the pipeline is typically an output end and the other an input end, leaks often cause different pressure change rates on both sides. However, within a short period, the pressure change rates at close range on the same side tend to be relatively consistent. Therefore, the pressure change rate at close range on the same side of the leaking sub-pipeline tends to be relatively consistent. Thus, the average pressure change rate of the preceding target sub-pipeline can be used to characterize the average pressure change rate in the region before the leak point within the leaking sub-pipeline. Similarly, the average pressure change rate of the following target sub-pipeline can be used to characterize the average pressure change rate in the region after the leak point within the leaking sub-pipeline. Therefore, the length L of the k-th leaking sub-pipeline... k The formula that satisfies this condition can be: L k =v k1 ×(a k,1 -x k )+v k2 ×(a k,2 -x k ); the length L of the k-th leaking sub-pipe k The formula that satisfies x k By solving this problem, we can obtain... Therefore, x k It can represent the pressure at the leak point of the k-th leaking sub-pipe within the current time period.

[0102] The fourth step involves determining the leakage location of each leaking sub-pipe using the following formula: based on the overall leakage pressure of the leaking sub-pipe, the pressure change rate of the preceding target sub-pipe, and the target pressure signal at a preset position between the leaking sub-pipe and its preceding target sub-pipe.

[0103] p k =vk1 ×(a k,1 -x k ); where p k This represents the leak location corresponding to the k-th leaking sub-pipe, indicating the distance from the leak point on the k-th leaking sub-pipe to its front end. k1 is the pressure change rate corresponding to the target sub-pipe preceding the k-th leaking sub-pipe. k,1 It is the average of all pressure values ​​in the target pressure signal at a preset position between the k-th leaking sub-pipe and its preceding target sub-pipe. k It is the overall leakage pressure corresponding to the kth leaking sub-pipe.

[0104] It should be noted that the above method for determining the leak location is for locating the leak point of a leaking sub-pipe that is not adjacent to the leaking sub-pipe and is not located at the end of the oil and gas pipeline to be inspected. For other leaking sub-pipes, the method for obtaining the leak location can be: to determine the leak location of other leaking sub-pipes through manual inspection and then carry out repairs.

[0105] refer to Figure 4 Based on the same inventive concept as the above-described method embodiments, this invention provides a big data-based digital risk management and analysis system. This system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of a big data-based digital risk management and analysis method, specifically including:

[0106] The acquisition and determination module 401 is used to acquire the initial pressure signals of the oil and gas pipeline to be detected at different preset positions, and determine the fluctuation factor corresponding to each initial pressure signal based on the height of the preset position corresponding to each initial pressure signal and its adjacent initial pressure signals. The height of different preset positions represents the height of different parts of the oil and gas pipeline to be detected.

[0107] The signal correction module 402 is used to correct each initial pressure signal according to the fluctuation factor corresponding to each initial pressure signal to obtain the target pressure signal corresponding to each initial pressure signal.

[0108] The analysis and processing module 403 is used to determine the sub-pipe between each adjacent preset position as the target sub-pipe, and to analyze and process the pipeline leakage pressure change law of each target sub-pipe according to the target pressure signal at the preset position adjacent to each target sub-pipe, so as to obtain the leakage risk signal corresponding to each target sub-pipe.

[0109] The location determination module 404 is used to filter out the leaking sub-pipes from all target sub-pipes based on the leakage risk signal corresponding to the target sub-pipe, and determine the leakage location of each leaking sub-pipe.

[0110] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. For example, as shown... Figure 5 As shown, the computer device 500 includes: a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502. When the processor 502 executes the computer program 503, the computer device can execute any of the aforementioned big data-based digital risk management and analysis methods.

[0111] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server, including a memory and a processor. The memory stores executable program code, and the processor retrieves and runs the executable program code from the memory, enabling the device to execute any of the above-described big data-based digital risk management and analysis methods.

[0112] Based on the same inventive concept as the above-described method embodiments, the present invention provides a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform any of the above-described big data-based digital risk management and analysis methods.

[0113] Based on the same inventive concept as the above-described method embodiments, the present invention provides a digital risk management and analysis medium based on big data. This digital risk management and analysis medium based on big data stores computer program code. When the computer program code is run on a computer, the computer executes any of the above-described digital risk management and analysis methods based on big data.

[0114] In summary, the real-time leakage risk of each segment of the oil and gas pipeline was calculated, and the risk was normalized and a corresponding threshold was set. If the risk threshold is reached, an oil and gas leak is confirmed. Simultaneously, based on big data from GPS (Global Positioning System) or GIS (Geographic Information System) systems, the presence of regulating valves or oil pumps at the corresponding locations is determined. If no valves or pumps are operating, the corresponding leak location is calculated, an oil and gas leak warning is issued, and risk warning information is transmitted to relevant personnel via mobile phones and other media. This can quickly help safety personnel locate the leak point and prevent safety accidents. Compared to simply considering the magnitude of the collected pressure values ​​for oil and gas pipeline leak detection, this invention comprehensively considers the height of each initial pressure signal and the corresponding preset positions of adjacent initial pressure signals. It quantifies the fluctuation factor, characterizing the ground undulations at each preset position corresponding to the initial pressure signal, and corrects the initial pressure signal based on this fluctuation factor. This reduces the impact of pressure increases caused by ground undulations, thereby improving the accuracy of subsequent leak detection in the oil and gas pipelines under test. Furthermore, it analyzes the pressure variation patterns of each target sub-pipeline, quantifying the leakage risk signal characterizing the leakage risk of each target sub-pipeline, thus improving the accuracy of sub-pipeline selection and locating the leak position. Secondly, compared to collecting pressure signals only at the pipeline endpoints and performing leak detection based on these endpoint pressure signals, this invention collects pressure signals at multiple preset positions, obtaining pressure information from different parts of the oil and gas pipeline, thus enriching the pressure data. Therefore, leak detection based on pressure signals from multiple preset positions improves the accuracy of oil and gas pipeline leak detection.

[0115] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A digital risk management and analysis method based on big data, characterized in that, Includes the following steps: The initial pressure signals of the oil and gas pipeline to be inspected at different preset locations are obtained, and the fluctuation factor corresponding to each initial pressure signal is determined according to the height of the preset location corresponding to each initial pressure signal and its adjacent initial pressure signals. The height of different preset locations represents the height of different parts of the oil and gas pipeline to be inspected. Based on the fluctuation factor corresponding to each initial pressure signal, each initial pressure signal is corrected to obtain the target pressure signal corresponding to each initial pressure signal. The sub-pipes between each adjacent preset position are identified as target sub-pipes. Based on the target pressure signal at the preset position adjacent to each target sub-pipe, the leakage pressure change law of each target sub-pipe is analyzed and processed to obtain the leakage risk signal corresponding to each target sub-pipe. Based on the leakage risk signal corresponding to the target sub-pipe, the leaking sub-pipe is selected from all the target sub-pipes, and the leakage location of each leaking sub-pipe is determined. The step of determining the fluctuation factor corresponding to each initial pressure signal based on the height of each initial pressure signal and the height of the preset positions corresponding to its adjacent initial pressure signals includes: determining the initial fluctuation factor corresponding to each initial pressure signal by the variance of the height of the preset position corresponding to each initial pressure signal and the height of the preset positions corresponding to its adjacent initial pressure signals; and determining the fluctuation factor corresponding to each initial pressure signal based on the initial fluctuation factor corresponding to each initial pressure signal, wherein the initial fluctuation factor and the fluctuation factor are positively correlated. The step of correcting each initial pressure signal according to the fluctuation factor corresponding to each initial pressure signal to obtain the target pressure signal corresponding to each initial pressure signal includes: if the fluctuation factor corresponding to the initial pressure signal is greater than a preset fluctuation threshold, then the initial pressure signal is reduced according to the fluctuation factor corresponding to the initial pressure signal to obtain the target pressure signal corresponding to the initial pressure signal; if the fluctuation factor corresponding to the initial pressure signal is less than or equal to the preset fluctuation threshold, then the initial pressure signal is determined as the target pressure signal. The step of analyzing the leakage pressure variation pattern of each target sub-pipe based on the target pressure signal at a preset location adjacent to each target sub-pipe to obtain a leakage risk signal corresponding to each target sub-pipe includes: dividing each target pressure signal into equal parts, using the sub-signals as window signals to obtain a window signal sequence corresponding to each target pressure signal, wherein the window signal sequence is a time series; analyzing the leakage pressure variation pattern of the window signals at the same location in the window signal sequence corresponding to the target pressure signal at the preset location adjacent to each target sub-pipe to obtain a target risk signal sequence corresponding to each target sub-pipe; and constructing a leakage risk signal corresponding to each target sub-pipe from all the target risk signals in the target risk signal sequence corresponding to each target sub-pipe.

2. The digital risk management and control analysis method based on big data according to claim 1, characterized in that, The formula for the target risk signal in the target risk signal sequence corresponding to the target sub-pipeline is: ； ； ;in, Is with the first j The window signal sequence corresponding to the target pressure signal at two adjacent preset positions of the target sub-pipeline is the first... t The target risk signal between the signals of the first window is denoted as the first window signal. j In the target risk signal sequence corresponding to the target sub-pipeline, the first... t One target risk signal; j It is the sequence number of the target sub-pipe; t It is the sequence number of the target risk signal in the target risk signal sequence or the sequence number of the window signal in the window signal sequence; It is a normalization function; Is with the first j The window signal sequence corresponding to the target pressure signal at two adjacent preset positions of the target sub-pipeline is the first... t The first risk signal between window signals; Is with the first j The window signal sequence corresponding to the target pressure signal at two adjacent preset positions of the target sub-pipeline is the first... t The second risk signal between window signals; It is the first of all window signal sequences t In the window signals, besides and The mean of all window signals except those in the window; Is with the first j Among the target pressure signals at two preset locations adjacent to the target sub-pipe, the first target pressure signal corresponds to the window signal sequence of the first target pressure signal. t One window signal; Is with the first j Among the target pressure signals at two adjacent preset positions of the target sub-pipe, the second target pressure signal corresponds to the window signal sequence of the first... t One window signal; It is a natural exponential function; It is an absolute value function; It is the distance from the first j Among the target pressure signals at the two nearest preset positions of the target sub-pipe, the first target pressure signal corresponds to the window signal sequence of the first target pressure signal. t One window signal; It is the distance from the first j Among the target pressure signals at the two preset positions closest to the second target sub-pipe, the first target pressure signal in the window signal sequence corresponding to the second target pressure signal... t A window signal.

3. The digital risk management and control analysis method based on big data according to claim 1, characterized in that, The step of selecting leaking sub-pipes from all target sub-pipes based on the leakage risk signal corresponding to the target sub-pipe includes: If there are elements in the leakage risk signal corresponding to the target sub-pipe that are greater than the preset risk threshold, then the target sub-pipe will be identified as a leaking sub-pipe.

4. The digital risk management and control analysis method based on big data according to claim 1, characterized in that, Determining the leak location of each leaking sub-pipe includes: Based on the target pressure signal at a preset location adjacent to the target sub-pipe, and the length of the target sub-pipe, the formula corresponding to the pressure change rate of the target sub-pipe is determined as follows: Where v is the rate of pressure change corresponding to the target sub-pipe; L is the length of the target sub-pipe; It is an absolute value function; It is the average of all pressure values ​​in the first target pressure signal among the target pressure signals at two preset locations adjacent to the target sub-pipe; It is the average of all pressure values ​​in the second target pressure signal among the target pressure signals at two preset locations adjacent to the target sub-pipe; Based on the pressure change rate of the target sub-pipe adjacent to the leaking sub-pipe and the length of the leaking sub-pipe, the formula for evaluating the overall leakage pressure corresponding to the leaking sub-pipe is as follows: ;in, It is the overall leakage pressure corresponding to the k-th leaking sub-pipe; k is the sequence number of the leaking sub-pipe. It is the rate of pressure change corresponding to the target sub-pipe preceding the k-th leaking sub-pipe; It is the rate of pressure change corresponding to the next target sub-pipe after the k-th leaking sub-pipe; It is the average of all pressure values ​​in the target pressure signal at the preset position between the kth leaking sub-pipe and its previous target sub-pipe; It is the average of all pressure values ​​in the target pressure signal at the preset position between the kth leaking sub-pipe and its next target sub-pipe; It is the length of the k-th leaking sub-pipe; The leakage location of each leaking sub-pipe is determined based on the overall leakage pressure corresponding to the leaking sub-pipe, the pressure change rate corresponding to the previous target sub-pipe, and the target pressure signal at a preset position between the leaking sub-pipe and its previous target sub-pipe.

5. The digital risk management and control analysis method based on big data according to claim 4, characterized in that, The formula corresponding to the leakage location of the leaking sub-pipe is: ;in, It represents the leak location corresponding to the kth leaking sub-pipe, indicating the distance from the leak point on the kth leaking sub-pipe to the front end of the kth leaking sub-pipe.

6. A digital risk management and analysis system based on big data, characterized in that, It includes a processor and a memory, the processor being used to process instructions stored in the memory to implement a big data-based digital risk management and analysis method according to any one of claims 1-5.

7. A digital risk management and analysis medium based on big data, characterized in that, The big data-based digital risk management and analysis medium stores computer program code. When the computer program code is run on a computer, it causes the computer to execute any one of the big data-based digital risk management and analysis methods according to claims 1-5.

Images