Self-adaptive early warning method and device for oil and gas pipe network SCADA system

Abstract

The invention discloses an oil and gas pipe network SCADA system self-adaptive early warning method and device, and relates to the technical field of oil and gas pipe network early warning, and the method comprises the following steps: extracting the characteristic parameters of an oil and gas pipe network according to the historical oil and gas pipe network measurement data of an SCADA system; inputting the obtained characteristic parameters of the oil and gas pipe network into the established self-organizing characteristic mapping network for training and testing to obtain an oil and gas pipe network operation trend prediction model; inputting characteristic parameters of a to-be-detected oil and gas pipe network into the oil and gas pipe network operation trend prediction model, continuing monitoring if the result shows normal operation, and giving an alarm if the result shows abnormal operation; the self-adaptive early warning method and device for the oil and gas pipe network SCADA system have the advantages of being high in self-adaptability and intelligence, accurate in early warning, efficient in response, comprehensive in coverage, efficient in management and the like, and powerful technical support is provided for operation management of an oil and gas pipe network.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas pipeline network warning, and specifically relates to an adaptive warning method and device for an oil and gas pipeline network SCADA system. Background Art

[0002] Supervisory Control and Data Acquisition (SCADA) technology is an important industrial automation technology, which is widely used in various fields such as electric power, water supply, petrochemical industry, and transportation. This technology aims to monitor and control dispersed industrial processes in real time, helping operators effectively manage complex industrial systems. With the development of artificial intelligence technology, applying a mapping network to warning monitoring based on the SCADA system can effectively improve the early warning effect of faults.

[0003] Currently, with the continuous development of industrial automation, the SCADA system also faces some challenges. One of them is the adaptive emergency warning of oil and gas pipeline networks. Since the main way of transporting oil and gas resources is through pipeline networks, but the complex geographical conditions and climate, as well as seismic risks and vast areas make the predictability and safety of resource transportation a challenge. For example, the inability to effectively and timely predict seismic risks may cause damage to pipelines, and then lead to problems such as waste of resources.

[0004] Therefore, there is an urgent need to study a method for real-time adaptive emergency warning under complex natural conditions, which can effectively warn various faults occurring in the oil and gas pipeline network and avoid waste of resources. Summary of the Invention

[0005] To solve the problem that in the scenario of transporting oil and gas resources through pipeline networks under complex geographical conditions, climate, seismic risks and vast areas, various faults are likely to occur in the oil and gas pipeline network, and an effective adaptive process warning cannot be carried out on the pipeline network, resulting in waste of resources, the purpose of the present invention is to provide an adaptive warning method and device for an oil and gas pipeline network SCADA system.

[0006] The present invention realizes the above purpose through the following technical solutions:

[0007] An adaptive warning method and device for an oil and gas pipeline network SCADA system, including the following steps:

[0008] Step 1, extract the characteristic parameters of the oil and gas pipeline network according to the historical measurement data of the oil and gas pipeline network of the SCADA system;

[0009] Step 2, input the characteristic parameters of the oil and gas pipeline network obtained in Step 1 into the established self-organizing feature mapping network for training and testing to obtain an oil and gas pipeline network operation trend prediction model;

[0010] Step 3: Input the characteristic parameters of the oil and gas pipeline network to be measured into the oil and gas pipeline network operation trend prediction model described in Step 2. If the result shows normal operation, continue monitoring; if the result shows abnormal operation, give an alarm.

[0011] Preferably, the characteristic parameters of the oil and gas pipeline network in Step 1 are at least one of flow rate, pressure, temperature, liquid level, and valve status.

[0012] Preferably, Step 2 includes the following steps:

[0013] Step 2.1: Divide the characteristic parameters of the oil and gas pipeline network obtained in Step 1 into a training set and a test set.

[0014] Step 2.2: Use the training set to train the weights in the established self-organizing feature mapping network until the convergence condition is met, and obtain the oil and gas pipeline network operation trend prediction model to be tested.

[0015] Step 2.3: Use the test set to test the oil and gas pipeline network operation trend prediction model to be tested obtained in Step 2.2, and obtain the oil and gas pipeline network operation trend prediction model.

[0016] Preferably, Step 2.2 specifically includes the following steps:

[0017] Step 2.2.1: Calculate the Euclidean distance between the characteristic parameters of the oil and gas pipeline network and each neuron in the self-organizing feature mapping network.

[0018] Step 2.2.2: Identify the neuron with the minimum Euclidean distance from the characteristic parameters of the oil and gas pipeline network.

[0019] Step 2.2.3: Update all neurons and the weights of all neurons in the self-organizing feature mapping network according to the learning rule.

[0020] Step 2.2.4: Train the characteristic parameters of all oil and gas pipeline networks in the training set until the convergence condition is met, and obtain the oil and gas pipeline network operation trend prediction model to be tested.

[0021] Preferably, the convergence condition in Step 2.2.4 includes training the weights in the self-organizing feature mapping network using the training set until the number of training times is greater than 10 3 .

[0022] Preferably, before inputting the characteristic parameters of the oil and gas pipeline network to be measured into the oil and gas pipeline network operation trend prediction model described in Step 2, perform normalization processing on the characteristic parameters of the oil and gas pipeline network to be measured.

[0023] Preferably, Step 3 specifically includes the following steps:

[0024] Input the characteristic parameters of the oil and gas pipeline network to be measured into the oil and gas pipeline network operation trend prediction model described in step 2 to obtain the oil and gas pipeline network operation trend category; wherein, the oil and gas pipeline network operation trend category includes the normal operation trend of the oil and gas pipeline network and the abnormal operation trend of the oil and gas pipeline network;

[0025] If the prediction result is the normal operation trend of the oil and gas pipeline network, the SCADA system continues to monitor;

[0026] If the prediction result is the abnormal operation trend of the oil and gas pipeline network, the SCADA system outputs abnormal operation and alarms.

[0027] The present invention further includes an adaptive warning device for the oil and gas pipeline network SCADA system, including the following modules:

[0028] Parameter extraction module: used to obtain the characteristic parameters of the oil and gas pipeline network according to the historical measurement data of the oil and gas pipeline network of the SCADA system;

[0029] Model training module: used to input the characteristic parameters of the oil and gas pipeline network obtained by the parameter extraction module into the established self-organizing feature mapping network for training and testing to obtain the oil and gas pipeline network operation trend prediction model;

[0030] Prediction and alarm module: used to input the characteristic parameters of the oil and gas pipeline network to be measured by the SCADA system into the oil and gas pipeline network operation trend prediction model to obtain the prediction result. If the result shows normal operation, continue to monitor; if the result shows abnormal operation, alarm.

[0031] Preferably, an electronic device is used to run the above modules. The electronic device includes a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the adaptive warning method for the oil and gas pipeline network SCADA system described in any one of the above.

[0032] Further preferably, the electronic device further includes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, it implements the steps of the adaptive warning method for the oil and gas pipeline network SCADA system described in any one of the above.

[0033] The present invention has the following advantages compared with the prior art:

[0034] The adaptive warning method and device for the oil and gas pipeline network SCADA system of the present invention can solve the problem that in the scenarios of complex geographical conditions, climate, seismic risks, and vast areas for oil and gas resource transportation through pipeline networks, various faults are likely to occur in the oil and gas pipeline networks, and effective adaptive process warning cannot be carried out on the pipeline networks, resulting in resource waste.

[0035] By deeply mining the operation data of the pipeline network, the early warning method of the present invention can accurately identify potential fault signs, avoid false alarms and missed alarms, and improve the accuracy of early warning. When the early warning device detects a potential fault, it can immediately generate an early warning message and provide suggestions for emergency response strategies, helping the operation and maintenance personnel to take measures quickly and reduce the impact of the fault on the operation of the pipeline network.

[0036] The early warning method and device of the present invention are widely applicable, suitable for oil and gas pipeline networks under various complex geographical conditions and climate environments, as well as pipeline network facilities of different scales and types. The human-machine interaction interface provided by the early warning device is friendly and intuitive, facilitating the operation and maintenance personnel to monitor the pipeline network status in real time, view early warning information and historical data, and improve the efficiency and convenience of pipeline network operation management. Through accurate early warning and efficient response, the present invention can significantly reduce the incidence rate and impact degree of pipeline network faults, and reduce resource waste and environmental pollution caused by faults.

[0037] The adaptive early warning method and device for the oil and gas pipeline network SCADA system of the present invention have the advantages of high adaptability and intelligence, accurate early warning and efficient response, comprehensive coverage and efficient management, resource conservation and environmental protection, and easy integration and expansion, providing strong technical support for the operation management of the oil and gas pipeline network. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 It is a schematic flow chart of an adaptive early warning method for an oil and gas pipeline network SCADA system of the present invention. Figure 2 It is a self-organizing feature map network topology structure. Figure 3 It is a structural block diagram of an adaptive early warning device for an oil and gas pipeline network SCADA system of the present invention. Figure 4 It is a structural block diagram of an electronic device of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0038] The purpose of the present invention is to provide an adaptive early warning method and device for an oil and gas pipeline network SCADA system, which are realized through the following technical solutions:

[0039] At present, the long-distance oil and gas pipeline network SCADA system (Supervisory Control And Data Acquisition) consists of a central control system located in the dispatching control center, station control systems distributed along the line, RTUs (Remote Terminal Units) for monitoring (surveillance) valve chambers, and a communication system. Among them, the main instrument monitoring unit of the oil and gas pipeline network consists of temperature, pressure, flow rate, liquid level, valve status, etc. The main monitoring equipment of the oil and gas pipeline network consists of various valve actuators, pump units (oil pipelines), compressor units (gas pipelines), auxiliary systems, etc.

[0040] However, in the prior art, the dispatching control center usually conducts artificial centralized regulation of the whole line according to the process through dispatchers, and cannot timely give real-time and effective early warnings for the pipeline network. To achieve intelligent early warning in the monitoring process of the oil and gas pipeline network SCADA system, the present invention provides an adaptive early warning method for the oil and gas pipeline network SCADA system.

[0041] Embodiment 1

[0042] An adaptive early warning method for an oil and gas pipeline network SCADA system, as Figure 1 and Figure 2 shown, includes the following steps:

[0043] Step 1, according to the historical measurement data of the oil and gas pipeline network of the SCADA system, extract the characteristic parameters of the oil and gas pipeline network; the characteristic parameters of the oil and gas pipeline network are at least one of flow rate, pressure, temperature, liquid level, and valve state;

[0044] The characteristic parameters of the oil and gas pipeline network extracted from the historical measurement data of the oil and gas pipeline network in the SCADA (Supervisory Control And Data Acquisition) system are the key operating indicators of the oil and gas pipeline network SCADA (Supervisory Control And Data Acquisition) system, and they can reflect the current state and behavior pattern of the oil and gas pipeline network.

[0045] According to the historical measurement data of the oil and gas pipeline network of the SCADA system, select part of the oil and gas pipeline network as the research area, and collect the characteristic parameters with controllability and representativeness in this research area. As shown in Table 1 below, the value ranges of the characteristic parameters in Table 1 are obtained from multiple measurements by the corresponding sensors.

[0046] Table 1 Value ranges of the characteristic parameters extracted in the research area of this application;

[0047]

[0048] According to Table 1, in this embodiment, the characteristic parameters extracted in the research area include: flow rate, pressure, temperature, liquid level, and valve state. Among them, the value ranges of the above characteristic parameters are divided into Range A and Range B, where Range A is the value range of the characteristic parameters when the oil and gas pipeline network in the research area operates normally, and Range B is the value range of the characteristic parameters when the oil and gas pipeline network in the research area operates abnormally.

[0049] It can be seen from Table 1 that for the characteristic parameter: the unit of flow rate is (L / h), the value range when the oil and gas pipeline network operates normally is 0 - 1000 (L / h), and the value range when the oil and gas pipeline network operates abnormally is > 1000 (L / h);

[0050] Characteristic parameter: The unit of pressure is (Pa), and the value range during normal operation of the oil and gas pipeline network is 500 - 700 (Pa), while the value range during abnormal operation of the oil and gas pipeline network is < 500 or > 700;

[0051] Characteristic parameter: The unit of temperature is (°C), and the value range during normal operation of the oil and gas pipeline network is 20 - 50 (°C), while the value range during abnormal operation of the oil and gas pipeline network is < 20 or > 50;

[0052] Characteristic parameter: The unit of liquid level is (m), and the value range during normal operation of the oil and gas pipeline network is 0 - 10 (m), while the value range during abnormal operation of the oil and gas pipeline network is > 10;

[0053] Characteristic parameter: Valve status. During normal operation of the oil and gas pipeline network, the valve status can be open or closed, and during abnormal operation of the oil and gas pipeline network, the valve status is faulty.

[0054] Step 2: Input the characteristic parameters of the oil and gas pipeline network obtained in Step 1 into the established self-organizing feature mapping network for training and testing to obtain an oil and gas pipeline network operation trend prediction model;

[0055] The self-organizing feature mapping network is an unsupervised learning neural network used to generate a low-dimensional space of training samples, transform the complex non-linear statistical relationships between high-dimensional data into simple geometric relationships, and display them in a low-dimensional manner. After the training of the self-organizing feature mapping network converges, for any input pattern sample, the weights of the self-organizing feature mapping network can be adjusted by the self-organizing competition method according to the input training sample data, so as to effectively identify the input unit.

[0056] In this embodiment, the self-organizing feature mapping network can automatically discover the internal structure pattern of the input data and form the topological distribution of the operation status of the oil and gas pipeline network. In addition, during the training process of the self-organizing feature mapping network, the weights of its neurons will be continuously adjusted to minimize the error between the input data and the neurons, so as to obtain an oil and gas pipeline network operation trend prediction model to be tested, thereby realizing the prediction and early warning of abnormal situations occurring during the operation of the oil and gas pipeline network.

[0057] In this embodiment, the self-organizing feature mapping network learns the normal operation trend of the oil and gas pipeline network through training and constructs an oil and gas pipeline network operation trend prediction model to be tested.

[0058] Step 3: Input the characteristic parameters of the oil and gas pipeline network to be tested into the oil and gas pipeline network operation trend prediction model described in Step 2, predict the operation trend of the oil and gas pipeline network through the model. If the result shows normal operation, continue to monitor; if the result shows abnormal operation, give an alarm.

[0059] Table 2 shows the characteristic parameters of the oil and gas pipeline network to be measured in 20 time periods in the research area of this application, as well as the prediction results obtained by inputting these characteristic parameters into the trend prediction model.

[0060] Table 2

[0061]

[0062]

[0063] As can be seen from Table 2, the operating trends of the oil and gas pipeline network in this embodiment are divided into normal and abnormal, with normal represented by 1 and abnormal represented by 0. As shown in Table 2, the characteristic parameters of the oil and gas pipeline network in 20 time periods in the research area are extracted. Among them, in the 4th time period, the pressure of the oil and gas pipeline network in the research area is 800 (psi), and at this time, the operating trend of the oil and gas pipeline network is abnormal.

[0064] Reason for abnormality: The pressure value of the oil and gas pipeline network in the research area exceeds the value range under the normal operating state of the oil and gas pipeline network.

[0065] In this embodiment, when the SCADA system predicts an abnormal operating trend of the oil and gas pipeline network, it will remind the operator to adjust the equipment in time through sound (such as a beeping sound) and light (such as the flashing of an indicator light), so as to avoid failures in the operation of the oil and gas pipeline network. Among them, this alarm method of the SCADA system is intuitive and easy to attract attention, and is suitable for use in occasions that require immediate response.

[0066] Of course, when the SCADA system predicts an abnormal operating trend of the oil and gas pipeline network, it will display the abnormal information in text form on the display screen, including abnormal information parameters such as the type of abnormality, the location of the abnormality, and the time of the abnormality.

[0067] When the SCADA system predicts an abnormal operating trend of the oil and gas pipeline network, the SCADA system will provide an alarm list and list all current alarm information in this alarm list. Among them, the alarm list usually includes parameters such as the alarm number, the alarm time, the alarm level, and the alarm description, so as to facilitate the operator to quickly browse and locate problems.

[0068] There are various ways for the SCADA system to output an abnormal operating trend and give an alarm, such as voice alarm, SMS, email alarm, etc., which will not be elaborated here.

[0069] As shown in Table 2, in this embodiment, the characteristic parameters of the oil and gas pipeline network include at least one of flow rate, pressure, temperature, liquid level, and valve status. An adaptive early warning method for an oil and gas pipeline network SCADA system provided by this application realizes the purpose of predicting whether the oil and gas pipeline network has an abnormal operation trend by inputting the characteristic parameters of the oil and gas pipeline network extracted in real time into a trained oil and gas pipeline network operation trend prediction model. If the prediction result is that the current operation trend of the oil and gas pipeline network is a normal operation trend, the system continues to run; if the prediction result is that the current oil and gas pipeline network has an abnormal operation trend, the system alarms.

[0070] It should be noted that, in this embodiment, the SCADA system monitors the flow measurement data in the oil and gas pipeline network through a flow meter, and this flow measurement data helps to understand the transportation capacity of the oil and gas pipeline network and timely discover and handle flow anomalies in the oil and gas pipeline network.

[0071] In this embodiment, the SCADA system monitors the pressure measurement data in the oil and gas pipeline network through a pressure meter, and this pressure measurement data helps to understand the operation status of the oil and gas pipeline network and timely discover and handle pressure anomalies in the oil and gas pipeline network.

[0072] In this embodiment, the SCADA system monitors the temperature measurement data in the oil and gas pipeline network through a temperature meter, and this pressure measurement data helps to understand the operation status of the oil and gas pipeline network and timely discover and handle temperature anomalies in the oil and gas pipeline network.

[0073] In addition, in this embodiment, the SCADA system can also monitor the liquid level measurement data of equipment such as storage tanks and separators through a liquid level meter, and the liquid level measurement data helps to prevent safety problems caused by too high or too low liquid levels.

[0074] Of course, in this embodiment, the SCADA system can directly monitor the operation status measurement data of the valve (open, closed, faulty), which helps to understand the control situation of the oil and gas pipeline network and timely discover and handle valve failures.

[0075] Input the obtained characteristic parameters of the oil and gas pipeline network into the established self-organizing feature mapping network for training and testing to obtain an oil and gas pipeline network operation trend prediction model, which specifically includes the following steps:

[0076] Step 2.1, divide the obtained characteristic parameters of the oil and gas pipeline network into a training set and a test set;

[0077] Step 2.2, use the training set to train the weights in the established self-organizing feature mapping network until the convergence condition is met to obtain an oil and gas pipeline network operation trend prediction model to be tested;

[0078] After testing the oil and gas pipeline network operation trend prediction model to be measured using the test set, the oil and gas pipeline network operation trend prediction model is obtained. Among them, the oil and gas pipeline network operation trend prediction model can calculate the prediction error between the two by comparing the prediction results of the model with the actual data in the test set, so as to evaluate the prediction performance of the oil and gas pipeline network operation trend prediction model;

[0079] Step 2.2.1, calculate the Euclidean distance between the characteristic parameters of the oil and gas pipeline network and each neuron in the self-organizing feature mapping network;

[0080] Step 2.2.2, identify the neuron with the smallest Euclidean distance from the characteristic parameters of the oil and gas pipeline network;

[0081] Step 2.2.3, update all neurons in the self-organizing feature mapping network and the weights of all the neurons according to the learning rule;

[0082] Step 2.2.4, train the characteristic parameters (flow rate, pressure, temperature, liquid level, valve state) of all oil and gas pipeline networks in the training set until the convergence condition is met, and obtain the oil and gas pipeline network operation trend prediction model to be tested;

[0083] The convergence condition in Step 2.2.4 includes training the weights in the self-organizing feature mapping network by the training set until the number of training times is greater than 10 3 ; Of course, the convergence condition in the self-organizing feature mapping network can be set according to needs, and this embodiment does not make specific limitations.

[0084] Step 2.3, use the test set to test the oil and gas pipeline network operation trend prediction model to be tested obtained in Step 2.2, and obtain the oil and gas pipeline network operation trend prediction model.

[0085] This application uses the trained self-organizing feature mapping network as the oil and gas pipeline network operation trend prediction model. The training process of the self-organizing feature mapping network is as follows:

[0086] (1) Randomly assign values in the interval [0, 1] to all connection weights W j (t o ) from the input layer unit to the output layer unit;

[0087] (2) Let the connection weight of the jth output unit be denoted as W j =(W j1 , W j2 , …, W jn ), and perform the following operations on any parameter (flow rate, pressure, temperature, liquid level, valve state) X k in the characteristic parameters:

[0088] a. Calculate the characteristic parameter X kThe Euclidean distance d j from each connection weight W j is:

[0089]

[0090] where is the i-th X K ; p is any positive integer greater than 1; n is any positive integer greater than 1; W ij is the j-th connection weight value of the i-th output unit.

[0091] b. Find the minimum Euclidean distance:

[0092]

[0093] (3) Define a neighborhood N c (t) centered at c with a radius of a certain γ(t), and perform weight adjustment

[0094] If:

[0095]

[0096]

[0097] R(t) = 1

[0098] where t is the time; ΔW ij is the increment of the i-th connection weight of the j-th output unit; η(t) is the gain function; is the input characteristic parameter; γ i (t) is the radius function; R(t) is the coefficient function; W ij (t) is the j-th connection weight of the i-th output unit at time t.

[0099] Furthermore:

[0100]

[0101]

[0102] W ij (t + 1) is the j-th connection weight of the i-th output unit at time t + 1;

[0103] η(t) is a gain function that decreases with time:

[0104]

[0105] (4) t = t + 1, where t ≤ 10 3 ;

[0106] When t > 10 is satisfied3 When the convergence requirement is met, the operation trend prediction model of the oil and gas pipeline network to be tested is output;

[0107] If the condition t > 10 is not satisfied 3 for the convergence requirement (i.e., when t ≤ 10 3 ), step (2) is continued to be repeated;

[0108] The connection weight W refers to the weight value connecting neurons, which reflects the signal strength from one neuron to another. The value range of the weight is a set of real numbers, and its magnitude and sign depend on the specific neural network structure and training task. In the input pattern, the input parameter X in the self-organizing feature neural network (for example, in this embodiment, X can be X k ), refers to a large amount of non-linear input data received by numerous neurons in the self-organizing feature neural network. The Euclidean distance d is a standard method for measuring the true distance between two points in an m-dimensional space.

[0109] The characteristic parameters (flow rate, pressure, temperature, liquid level, valve state) of the oil and gas pipeline network are input into the self-organizing feature mapping network, and the characteristic parameters are trained in sequence until the convergence condition is met, thereby obtaining the operation trend prediction model of the oil and gas pipeline network to be tested. Before inputting the characteristic parameters of the oil and gas pipeline network to be tested into the operation trend prediction model of the oil and gas pipeline network, the characteristic parameters of the oil and gas pipeline network to be tested are normalized, so as to ensure the quality and consistency of the input data.

[0110] In some embodiments, the characteristic parameters of the oil and gas pipeline network to be tested in the SCADA system are input into the operation trend prediction model of the oil and gas pipeline network, and the abnormal operation trend of the oil and gas pipeline network is obtained and an alarm is given, which specifically includes the following steps:

[0111] The characteristic parameters of the oil and gas pipeline network to be tested are input into the operation trend prediction model of the oil and gas pipeline network described in step 2, and the operation trend category of the oil and gas pipeline network is obtained; wherein, the operation trend category of the oil and gas pipeline network includes the normal operation trend of the oil and gas pipeline network and the abnormal operation trend of the oil and gas pipeline network;

[0112] If the prediction result is the normal operation trend of the oil and gas pipeline network, the SCADA system continues to monitor;

[0113] If the prediction result is the abnormal operation trend of the oil and gas pipeline network, the SCADA system outputs abnormal operation and gives an alarm.

[0114] The present invention provides an adaptive early warning method for an oil and gas pipeline network SCADA system, which can solve the problem of resource waste caused by various faults easily occurring in the oil and gas pipeline network and the inability to effectively perform an adaptive process early warning on the pipeline network in the scenarios of complex geographical conditions and climates, as well as seismic risks and vast regions for oil and gas resource transportation through the pipeline network.

[0115] Example 2

[0116] An adaptive early warning device for an oil and gas pipeline network SCADA system, as Figure 3 shown, includes the following modules:

[0117] Parameter extraction module 10: used to obtain the characteristic parameters of the oil and gas pipeline network according to the historical measurement data of the oil and gas pipeline network of the SCADA system;

[0118] Model training module 20: used to input the characteristic parameters of the oil and gas pipeline network obtained by the parameter extraction module into the established self-organizing feature mapping network for training and testing, and obtain an oil and gas pipeline network operation trend prediction model;

[0119] Prediction and alarm module 30: used to input the characteristic parameters of the oil and gas pipeline network to be measured of the SCADA system into the oil and gas pipeline network operation trend prediction model to obtain a prediction result. If the result shows normal operation, continue to monitor; if the result shows abnormal operation, alarm.

[0120] This embodiment provides an adaptive early warning device for an oil and gas pipeline network SCADA system. This adaptive early warning device for an oil and gas pipeline network SCADA system can solve the problem of resource waste caused by various faults that easily occur in the oil and gas pipeline network in scenarios of complex geographical conditions, climate, seismic risks, and vast areas where oil and gas resources are transported through the pipeline network, and the inability to effectively perform an adaptive process early warning on the pipeline network.

[0121] Example 3

[0122] An electronic device, as Figure 4 shown in the structural block diagram, the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0123] The memory 101 can be used to store the computer program 103. The processor 102 realizes the adaptive early warning method for the oil and gas pipeline network SCADA system in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0124] The memory 101 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the electronic device 100 (such as audio data, etc.). In addition, the memory 101 may include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0125] At least one processor 102 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or the processor 102 may also be any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and connects various parts of the entire electronic device 100 through various interfaces and lines.

[0126] In one example, the memory 101 in the electronic device 100 stores multiple instructions to implement an adaptive early warning method for an oil and gas pipeline network SCADA system. The processor 102 can execute the multiple instructions to implement:

[0127] Step 1: Obtain the characteristic parameters of the oil and gas pipeline network according to the historical measurement data of the oil and gas pipeline network of the SCADA system;

[0128] Step 2: Input the characteristic parameters into the established self-organizing feature mapping network for training and testing to obtain an oil and gas pipeline network operation trend prediction model;

[0129] Step 3: Input the characteristic parameters of the oil and gas pipeline network to be measured by the SCADA system into the oil and gas pipeline network operation trend prediction model to obtain the abnormal operation trend of the oil and gas pipeline network and give an alarm.

[0130] Embodiment 4

[0131] A computer-readable storage medium, wherein if the modules / units integrated in the electronic device 100 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0132] Based on such an understanding, all or part of the processes in the methods provided by the above embodiments of the present disclosure can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented.

[0133] Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory and read-only memory (ROM, Read-Only Memory).

[0134] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0136] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions in Figure 1 one process or multiple processes and / or blocksFigure 1 The functions specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 process or more processes and / or boxes Figure 1 or more boxes.

Claims

1. An adaptive early warning method for an oil and gas pipeline network SCADA system, characterized in that: It includes the following steps: Step 1: Extract the characteristic parameters of the oil and gas pipeline network according to the historical measurement data of the oil and gas pipeline network in the SCADA system; Step 2: Input the characteristic parameters of the oil and gas pipeline network obtained in Step 1 into the established self-organizing feature mapping network for training and testing to obtain an oil and gas pipeline network operation trend prediction model; Step 3: Input the characteristic parameters of the oil and gas pipeline network to be measured into the oil and gas pipeline network operation trend prediction model described in Step 2. If the result shows normal operation, continue to monitor; if the result shows abnormal operation, alarm.

2. The adaptive early warning method for the oil and gas pipeline network SCADA system according to claim 1, characterized in that: The characteristic parameters of the oil and gas pipeline network in Step 1 are at least one of flow rate, pressure, temperature, liquid level, and valve status.

3. The adaptive warning method for the oil and gas pipeline network SCADA system according to claim 1, characterized in that: Step 2 includes the following steps: Step 2.1: Divide the characteristic parameters of the oil and gas pipeline network obtained in Step 1 into a training set and a test set; Step 2.2: Use the training set to train the weights in the established self-organizing feature mapping network until the convergence condition is met to obtain an oil and gas pipeline network operation trend prediction model to be tested; Step 2.3: Use the test set to test the oil and gas pipeline network operation trend prediction model to be tested obtained in Step 2.2 to obtain an oil and gas pipeline network operation trend prediction model.

4. The adaptive warning method for the oil and gas pipeline network SCADA system according to claim 3, wherein: Step 2.2 specifically includes the following steps: Step 2.2.1: Calculate the Euclidean distance between the characteristic parameters of the oil and gas pipeline network and each neuron in the self-organizing feature mapping network; Step 2.2.2: Identify the neuron with the smallest Euclidean distance from the characteristic parameters of the oil and gas pipeline network; Step 2.2.3: Update all neurons and the weights of all neurons in the self-organizing feature mapping network according to the learning rule; Step 2.2.4: Train the characteristic parameters of all oil and gas pipeline networks in the training set until the convergence condition is met to obtain an oil and gas pipeline network operation trend prediction model to be tested.

5. The adaptive early warning method for the oil and gas pipeline network SCADA system according to claim 4, characterized in that: The convergence condition in step 2.2.4 includes training the weights in the self-organizing feature mapping network with the training set until the number of training times satisfies being greater than 10 3 .

6. The adaptive early warning method for the oil and gas pipeline network SCADA system according to claim 1, characterized in that: Before inputting the characteristic parameters of the oil and gas pipeline network to be measured into the oil and gas pipeline network operation trend prediction model described in Step 2, perform normalization processing on the characteristic parameters of the oil and gas pipeline network to be measured.

7. The adaptive early warning method for the oil and gas pipeline network SCADA system according to claim 1, wherein: Step 3 specifically includes the following steps: Input the characteristic parameters of the oil and gas pipeline network to be measured into the oil and gas pipeline network operation trend prediction model described in Step 2 to obtain the oil and gas pipeline network operation trend category; among them, the oil and gas pipeline network operation trend category includes the normal operation trend of the oil and gas pipeline network and the abnormal operation trend of the oil and gas pipeline network; If the prediction result is the normal operation trend of the oil and gas pipeline network, the SCADA system continues to monitor; If the prediction result is the abnormal operation trend of the oil and gas pipeline network, the SCADA system outputs abnormal operation and alarms.

8. An adaptive warning device for an oil and gas pipeline network SCADA system, characterized in that: It includes the following modules: Parameter extraction module: used to obtain the characteristic parameters of the oil and gas pipeline network according to the historical measurement data of the oil and gas pipeline network in the SCADA system; Model training module: used to input the characteristic parameters of the oil and gas pipeline network obtained by the parameter extraction module into the established self-organizing feature mapping network for training and testing to obtain an oil and gas pipeline network operation trend prediction model; Prediction and alarm module: used to input the characteristic parameters of the oil and gas pipeline network to be measured in the SCADA system into the oil and gas pipeline network operation trend prediction model to obtain a prediction result. If the result shows normal operation, continue to monitor; if the result shows abnormal operation, alarm.

9. An adaptive early warning device for an oil and gas pipeline network SCADA system according to claim 8, characterized in that: An electronic device operates the module described in claim 8. The electronic device includes a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the adaptive warning method for the oil and gas pipeline network SCADA system described in any one of claims 1 to 7.

10. An adaptive warning device for an oil and gas pipeline network SCADA system according to claim 9, characterized in that: The electronic device further includes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the steps of the adaptive warning method for the oil and gas pipeline network SCADA system described in any one of claims 1 to 7 are implemented.

Images