An oil and gas pipeline network sensor fault intelligent identification method and device and a storage device

Abstract

The application provides an oil and gas pipeline network sensor fault intelligent identification method, device and storage equipment, which comprises the following steps: determining a safety production process data threshold interval of a target oil and gas medium based on the physical parameters of the target oil and gas medium, obtaining an operating parameter, and determining a mutation time point when the operating parameter is located in the safety production process data threshold interval; determining an abnormal type of the sensor based on the mutation time point, and distinguishing between a sensor physical fault (such as natural aging, power depletion, etc.) and a network attack suffered by the sensor. The method of the application can judge whether a network attack occurs based on the size of the abnormal disturbance time difference of the sensor output data after analysis by the control core, identify the potential abnormal type of the sensor, is suitable for many application scenarios, improves the matching degree between the abnormal identification result and the application scenario, and thus realizes the distinction between the sensor network attack and the physical fault.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to an oil and gas pipeline network sensor fault intelligent identification method and device and a storage device. BACKGROUND

[0002] In a gas transmission system (such as an oil and gas pipeline network system), a sensor undertakes important functions such as data collection and information generation. Abnormal sensor or sensor under attack will cause risks such as data transmission anomaly and information leakage in the gas transmission system, thereby causing a huge impact on the current production node, and even possibly causing abnormality to other production nodes.

[0003] Related sensor fault detection methods (such as a distributed filter, a fusion algorithm based on historical measurement improvement, and an improved sensor network based on quasi-Newton) have the characteristics of single detection mode and dependence on external conditions such as sensor signals, and are difficult to be applied to actual application scenarios, so that the matching degree of the detection results in the above methods is not high, and there is still a safety problem that the gas transmission system is caused to have an accident due to sensor fault or attack. SUMMARY

[0004] The present application provides an oil and gas pipeline network sensor fault intelligent identification method and device and a storage device to solve the technical problem of low matching degree of detection results in related detection methods.

[0005] In a first aspect, the present application provides an oil and gas pipeline network sensor fault intelligent identification method, comprising:

[0006] Based on a physical parameter of a target oil and gas medium, a safety production process data threshold interval of the target oil and gas medium is determined;

[0007] An operating parameter is obtained, and when the operating parameter is located in the safety production process data threshold interval, a mutation time point is determined based on the operating parameter;

[0008] Based on the mutation time point, an abnormal type is determined; wherein the abnormal type includes sensor fault or sensor under network attack.

[0009] Optionally, the target oil and gas medium includes a first substance and a second substance; the physical parameter includes a first physical parameter of the first substance and a second physical parameter of the second substance; and the determination of the safety production process data threshold interval of the target oil and gas medium based on the physical parameter of the target oil and gas medium comprises:

[0010] Based on the first physical parameter and the second physical parameter, a mixed parameter of the target oil and gas medium is calculated;

[0011] Based on the mixed parameter, a relationship ratio of temperature and pressure is determined.

[0012] determining a safe production process data threshold interval of the target oil and gas medium when the relationship between the temperature and the pressure is less than a first threshold value; wherein the safe production process data threshold interval comprises at least one of a target temperature interval and a target pressure interval.

[0013] Optionally, the obtaining the running parameter, and determining the mutation time point based on the running parameter when the running parameter is located in the safe production process data threshold interval, comprises:

[0014] obtaining a running parameter;

[0015] calculating a log-likelihood ratio cumulative sum at each time point according to each of the running parameters in a preset time period when the running parameter is located in the safe production process data threshold interval;

[0016] determining the mutation time point based on the log-likelihood ratio cumulative sum at each time point.

[0017] Optionally, the running parameter comprises a first running parameter of a first device and a second running parameter of a second device; and the mutation time point comprises a first mutation time point of the first device and a second mutation time point of the second device.

[0018] The determining the abnormal type based on the mutation time point comprises:

[0019] calculating a time difference absolute value of the first mutation time point and the second mutation time point when the first mutation time point and the second mutation time point are not empty;

[0020] determining that the abnormal type is a sensor failure when the time difference absolute value is less than a second threshold value.

[0021] Or,

[0022] determining that the abnormal type is that the sensor is attacked by a network when the time difference absolute value is greater than or equal to the second threshold value.

[0023] Optionally, the determining the abnormal type based on the mutation time point further comprises:

[0024] determining that the sensor is in normal operation when the first mutation time point and the second mutation time point are empty.

[0025] Optionally, the safe production process data threshold interval comprises an upper boundary and a lower boundary; and after the obtaining the running parameter, the method further comprises:

[0026] When the operation parameter is less than the lower boundary or greater than the upper boundary, alarm information is generated; wherein the alarm information is used to indicate that the sensor is operating abnormally.

[0027] In a second aspect, the present application provides an oil and gas pipeline network sensor fault intelligent identification device, comprising:

[0028] A first determination module is configured to determine a safety production process data threshold interval of a target oil and gas medium based on a physical parameter of the target oil and gas medium.

[0029] A second determination module is configured to obtain an operation parameter, and determine a mutation time point based on the operation parameter when the operation parameter is within the safety production process data threshold interval.

[0030] A third determination module is configured to determine an abnormal type based on the mutation time point; wherein the abnormal type includes a sensor fault or a network attack on the sensor.

[0031] In a third aspect, the embodiments of the present application provide a storage device, comprising a processor and a memory connected with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, so that the processor executes the oil and gas pipeline network sensor fault intelligent identification method as described in the first aspect and various possible designs of the first aspect.

[0032] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions; when the processor executes the computer execution instructions, the oil and gas pipeline network sensor fault intelligent identification method as described in the first aspect and various possible designs of the first aspect is implemented.

[0033] In a fifth aspect, the embodiments of the present application provide a computer program product, comprising a computer program; when the computer program is executed by the processor, the oil and gas pipeline network sensor fault intelligent identification method as described in the first aspect and various possible designs of the first aspect is implemented.

[0034] The oil and gas pipeline network sensor fault intelligent identification method, device and storage equipment provided by the application can determine the safety production process data threshold interval of a target oil and gas medium based on the physical parameters of the target oil and gas medium, obtain an operating parameter, and determine a mutation time point when the operating parameter is located in the safety production process data threshold interval, determine the abnormal type of the sensor based on the mutation time point, such as sensor failure or network attack on the sensor, that is, whether a network attack occurs can be determined based on the size of the abnormal disturbance time difference after the sensor output data is analyzed in the control core, the potential sensor abnormal type is identified, the matching degree between the abnormal identification result and the application scenario is improved, the sensor network attack and physical failure are distinguished, and thus the precision of the abnormal identification result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0036] Figure 1 An architecture schematic diagram of an oil and gas pipeline network sensor fault intelligent identification system provided by an embodiment of the application;

[0037] Figure 2 One of flow schematic diagrams of an oil and gas pipeline network sensor fault intelligent identification method provided by an embodiment of the application;

[0038] Figure 3 The second flow schematic diagram of the oil and gas pipeline network sensor fault intelligent identification method provided by the embodiment of the application;

[0039] Figure 4 A sensor data transmission application schematic diagram provided by an embodiment of the application;

[0040] Figure 5 A monitoring schematic diagram of an operating parameter provided by an embodiment of the application;

[0041] Figure 6 The third flow schematic diagram of the oil and gas pipeline network sensor fault intelligent identification method provided by an embodiment of the application;

[0042] Figure 7 One of application scenario diagrams of the oil and gas pipeline network sensor fault intelligent identification method provided by an embodiment of the application;

[0043] Figure 8 The second application scenario diagram of the oil and gas pipeline network sensor fault intelligent identification method provided by an embodiment of the application;

[0044] Figure 9 The structure schematic diagram of the oil and gas pipeline network sensor fault intelligent identification device provided by an embodiment of the application;

[0045] Figure 10 The structural schematic diagram of the storage device provided in the embodiment of the present application is shown.

[0046] The specific embodiments of the present application have been shown by the above-mentioned drawings, and will be described in more detail hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0047] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The following description is made with reference to the accompanying drawings in which like reference numerals refer to like elements, unless otherwise indicated. The following exemplary embodiments described in the following detailed description are not meant to be limiting in terms of the scope of the application, but merely to be illustrative in terms of the various aspects of the application as detailed in the appended claims.

[0048] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in one or more embodiments of the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards, and provide corresponding operation portal for user to choose authorization or refusal.

[0049] In a gas transmission system (such as an oil and gas pipeline network system), sensors bear important functions such as data collection and information generation. Abnormal sensors or sensors under attack (e.g., fake, tampering, or replay routing information attacks, witch attacks, sinkhole attacks, flooding (Hello) attacks, denial of service (DoS) attacks, distributed denial of service (DDoS) attacks, etc.) can cause risks such as data transmission abnormalities and information leakage in the gas transmission system, and further cause great impact on the current production node, and even may cause abnormality to other production nodes.

[0050] Existing sensor fault detection methods (such as distributed filters, fusion algorithms improved based on historical measurements, and improved quasi-Newtonian sensor networks) typically utilize simulated sensor signals and employ devices like filters and state detectors for sensor attack detection. These methods are characterized by their reliance on a single detection approach and external conditions such as sensor signals and operation logs. Generally, operation logs consist mostly of alarm records and status parameter records, containing only discrete data, making them difficult to apply to real-world scenarios. This results in low accuracy of the detection results from the aforementioned methods, and the safety issue of gas transmission systems malfunctioning or being attacked still exists.

[0051] To address the aforementioned issues, this application proposes a method, apparatus, and storage device for intelligent identification of sensor faults in oil and gas pipeline networks. The method includes: determining a safety production process data threshold range for the target oil and gas medium based on its physical parameters; acquiring operating parameters; identifying abrupt change points when the operating parameters are within the safety production process data threshold range; and determining the sensor anomaly type based on these abrupt change points, such as physical sensor failure or sensor cyberattack. This allows for determining whether a sensor is malfunctioning based on the safety production process data threshold range, and identifying potential sensor anomaly types when operating parameters are within the safety production process data threshold range. It is applicable to numerous application scenarios, improves the matching degree between anomaly identification results and scenarios, and distinguishes between sensor cyberattacks and physical faults, thereby improving the accuracy of anomaly identification results.

[0052] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0053] Figure 1 This is a schematic diagram of the architecture of an intelligent identification system for sensor faults in an oil and gas pipeline network, provided as an embodiment of this application.

[0054] Taking the intelligent fault identification system for oil and gas pipeline network sensors as an example, and using pressure sensors as an example, see [link to relevant documentation]. Figure 1The intelligent fault identification system for oil and gas pipeline network sensors (model 101) includes a server and a control unit. The control unit comprises an electric valve, a pressure sensor, a data collection device, a first device, a second device, and a PI controller. The pressure sensor collects pressure data of the target oil and gas medium after passing through the filter separator and transmits this data to the first and second devices via the data collection device. During operation of the oil and gas pipeline network system, the first device acts as the operation control device, inputting the processed data to the PI controller. The PI controller generates feedback control commands (such as feedback adjustment increase commands, feedback adjustment decrease commands, or no adjustment commands) based on the pressure data transmitted by the first device to control the electric valve's transmission of the target oil and gas medium and regulate its pressure within the pipeline network system. The second device is used for control redundancy and monitoring for abnormal conditions.

[0055] The server communicates with the first and second devices in the control unit to acquire operating parameters (such as pressure or temperature data) from the first and second devices. Based on the comparison between the operating parameters and the safety production process data threshold range, it determines whether there is a system anomaly. If the operating parameters are not within the safety production process data threshold range, an alarm message is generated. If the operating parameters in the first and second devices are within the safety production process data threshold range, the time point of data mutation in the first and second devices is determined, thereby determining the type of sensor anomaly.

[0056] The control principle of the PI controller is shown in Figure 102. The control unit includes multiple electric valves ( Figure 1 Only two are shown, including Figure 1 (VLV-103 and VLV-104 are shown in Figure 102). PIC-100 is a pressure sensor controller (a sensor-control feedback integrated unit, which can be simply referred to as a controller), and LIC-100 is a level sensor controller (a sensor-control feedback integrated unit, which can be simply referred to as a controller).

[0057] PI controllers include splitters (such as...) Figure 1 As shown in Figure 102 (V-100), when the separator V-100 separates the target oil and gas medium, the pressure sensor controller PIC-100 (a sensor-control feedback system, which can be simply referred to as the pressure sensor controller) adjusts the pressure value through control valve VLV-104 to lower it if the pressure data is too high, and adjusts the pressure value through control valve VLV-103 to raise it if the pressure data is too low. Similarly, if the level sensor controller LIC-100 detects that the level data is too high, it adjusts the level value through control valve VLV-103 to lower it, and if the level data is too low, it adjusts the level value through control valve VLV-103 to raise it.

[0058] Taking stress data as an example, such as Figure 1 As shown in Figure 103: When the control valve VLV-104 receives the PV process value (also the pressure data after separation by the separator V-100), it compares it with the PID setpoint (the target value that the PID controller expects the regulated variable to reach) SP, and generates the corresponding OP output value (including but not limited to increasing or decreasing the value) based on the comparison result. Based on the OP output value, the pressure value is adjusted to increase or decrease.

[0059] Based on this, the output process of the intelligent fault identification system for oil and gas pipeline network sensors is as follows: Figure 1 As shown in Figure 104, the intelligent identification system for sensor faults in oil and gas pipeline networks includes mixer MIX-100, separator V-100, control valves VLV-100, VLV-101, VLV-102, VLV-103, VLV-104, compressor K-100, etc.

[0060] The target oil and gas medium is input to the mixer MIX-100 via control valve VLV-100, and then input to the separator V-100 via control valve VLV-104. After separation in separator V-100, the temperature, pressure and other data of the target oil and gas medium are regulated by control valves VLV-102, control valve VLV-103 and control valve VLV-104.

[0061] Optionally, when regulating the pressure of the target oil or gas medium, it can be achieved through compressor K-100, where Q-100 represents the heat energy required by the compressor.

[0062] Figure 2 This is a flowchart illustrating a method for intelligent fault identification of oil and gas pipeline network sensors, provided as an embodiment of this application. See also... Figure 2 The method includes the following steps:

[0063] S101. Based on the physical parameters of the target oil and gas medium, determine the data threshold range for the safe production process of the target oil and gas medium.

[0064] Optionally, the intelligent fault identification method for oil and gas pipeline network sensors provided in this embodiment can be applied to storage devices that are communicatively connected to the first device, the second device, etc. (e.g., Figure 1 The embodiments of this application are not limited to the servers shown in the examples.

[0065] Specifically, the physical parameters of the target oil and gas medium are obtained. The target oil and gas medium is used to indicate the oil and gas medium being transported in the gas transmission system (such as the oil and gas pipeline network system). The target oil and gas medium can be an oil and gas medium composed of a single substance (or component) or a mixed oil and gas medium composed of two or more substances.

[0066] The safe production process data threshold interval of the target oil and gas medium is determined based on the physical parameters of the target oil and gas medium. It can be understood that the safe production process data threshold interval of a single-substance oil and gas medium is directly determined by the physical parameters of the single substance, and the safe production process data threshold interval of a mixed oil and gas medium is determined by fusion of the physical parameters of each substance in the mixed oil and gas medium.

[0067] S102, an operating parameter is acquired, and when the operating parameter is located in the safe production process data threshold interval, a mutation time point is determined based on the operating parameter.

[0068] Specifically, the operating parameter of the target oil and gas medium is acquired, and the operating parameter is compared with the safe production process data threshold interval of the target oil and gas medium. When the operating parameter is less than or equal to the upper boundary of the safe production process data threshold interval and greater than or equal to the lower boundary of the safe production process data threshold interval, it is determined that the operating parameter is located in the safe production process data threshold interval, at this time, the sensor may not be abnormal, or the sensor is abnormal but the abnormality does not affect the normal operation of the gas transmission system, at this time, the data mutation time point in the operating parameter can be determined.

[0069] The mutation time point is used to indicate the time when the data in the operating parameter suddenly changes (such as suddenly increases and / or suddenly decreases).

[0070] S103, an abnormal type is determined based on the mutation time point; wherein the abnormal type includes a sensor failure or a sensor under a network attack.

[0071] Specifically, the abnormal type of the sensor is determined based on the data mutation time point in the operating parameter, wherein the abnormal type includes but is not limited to a sensor failure (or a sensor physical failure) or a sensor under a network attack.

[0072] It can be understood that the sensor under a network attack belongs to an abnormal type involving a wider range, greater potential harm, and higher maintenance difficulty. The vulnerabilities and failures at the physical level need certain conditions and time from the appearance of security vulnerabilities to accidents. Once the external attacker successfully attacks or intrudes when the sensor is under a network attack, the failure / abnormality will spread to the physical core device in the system. Based on this, when the operating parameter is located in the safe production process data threshold interval, the potential sensor failure or the abnormality that the sensor is under a network attack is efficiently and quickly identified, thereby improving the safety of the system.

[0073] In some embodiments, the target oil and gas medium comprises a first substance and a second substance; the physical parameters comprise a first physical parameter of the first substance and a second physical parameter of the second substance; and determining the safe production process data threshold interval of the target oil and gas medium based on the physical parameters of the target oil and gas medium comprises:

[0074] calculating a mixing parameter of the target oil and gas medium based on the first physical parameter and the second physical parameter;

[0075] determining a temperature and pressure relationship ratio based on the mixing parameter;

[0076] when the temperature and pressure relationship ratio is less than a first threshold value, determining the safe production process data threshold interval of the target oil and gas medium; wherein the safe production process data threshold interval comprises at least one of a target temperature interval and a target pressure interval.

[0077] Optionally, when the target oil and gas medium is a mixed oil and gas medium, the safe production process data threshold interval of the target oil and gas medium is determined by the physical parameters of each substance in the mixed oil and gas medium. In the embodiments of the present application, the determination method of the safe production process data threshold interval is mainly described for the target oil and gas medium which is a mixed oil and gas medium composed of two substances (such as a first substance and a second substance).

[0078] Specifically, when the target oil and gas medium comprises a first substance and a second substance, the physical parameters of the target oil and gas medium comprise a first physical parameter of the first substance and a second physical parameter of the second substance. The physical parameters include, but are not limited to, at least one of the critical temperature, the critical pressure, the gas relative temperature, etc.

[0079] Specifically, based on the first physical parameter and the second physical parameter, a mixing parameter of the target oil and gas medium is calculated, a temperature and pressure relationship ratio in the target oil and gas medium is determined based on the mixing parameter of the target oil and gas medium, when the temperature and pressure relationship ratio is less than a first threshold value, it is determined that the algorithm converges, and based on the equipment parameters in the gas transmission system and the temperature and pressure relationship ratio, a safe production process data threshold interval of the target oil and gas medium is determined.

[0080] The safe production process data threshold interval comprises at least one of a target temperature interval and a target pressure interval.

[0081] Optionally, the safe production process data threshold interval comprises an upper boundary and a lower boundary.

[0082] For example, the target temperature interval is [target temperature lower boundary, target temperature upper boundary], and the target pressure interval is [target pressure lower boundary, target pressure upper boundary].

[0083] For example Figure 1 The intelligent identification system for faults in oil and gas pipeline network sensors, taking a mixed oil and gas medium composed of two substances i and j as an example, uses the Peng-Robinson equation to determine the boundary values ​​of pressure data, as shown in formula (1):

[0084]

[0085] Where R represents the universal gas constant (taken as 8.314 J / (mol·K)), T represents the temperature of the target oil and gas medium, a represents the attraction constant of the target oil and gas medium, and b represents the volume constant of the target oil and gas medium. α represents a temperature-dependent factor used to adjust the attraction constant a. The attraction constant a and volume constant b of any substance (such as i or j) in the target oil and gas medium are calculated as follows:

[0086]

[0087] Among them, T c P represents the critical temperature. C T represents the critical pressure. r It represents the relative temperature of the target oil and gas medium, which is the ratio of the actual temperature to the critical temperature.

[0088] α represents the temperature-dependent factor used to adjust the attraction constant a, see the following formula:

[0089]

[0090] Based on this, the attraction constant a of the target oil and gas medium mix Volume constant b mix The calculation method is shown in the following formula:

[0091]

[0092] Where, x i a represents the mole fraction of the i-th substance in the target oil and gas medium in the mixture. i Let b represent the attraction constant of the i-th substance in the target oil and gas medium. i Let k represent the volume constant of the i-th substance in the target oil and gas medium. ij This represents the secondary interaction factor between substance i and substance j.

[0093] It can be understood that formula (1) can also be referred to as the relationship between the temperature and pressure of the target oil and gas medium, and the above formulas (1)-(6) are criteria for determining whether the simulation process conforms to the actual production. When the difference between the calculation results of the relationship between the temperature and pressure is less than the first threshold value, the simulation process converges and is determined. Based on the equipment parameters in the gas transmission system and the relationship between the temperature and pressure, the safety production process data threshold interval of the target oil and gas medium is determined, the valve dynamic condition is defined, and the liquid level, pressure and other controllers and control expressions (such as Figure 1 The first threshold value can be specifically set according to the actual situation. For example, the first threshold value is set to 0.01 or 0.001.

[0094] Optionally, the safety production process data threshold interval of the target oil and gas medium further includes upper and lower liquid level threshold values.

[0095] For example, the target pressure interval of the filter separator inlet is [7, 8.95], the target pressure interval of the filter separator outlet is [7, 11.8], the target temperature interval of the filter separator inlet is [11, 12], and the target temperature interval of the filter separator outlet is [11, 50].

[0096] In some embodiments, after the running parameter is obtained, the method further includes:

[0097] When the running parameter is less than the lower boundary or greater than the upper boundary, an alarm information is generated; wherein the alarm information is used to indicate that the sensor is running abnormally.

[0098] Specifically, when the running parameter of the target oil and gas medium is less than the lower boundary in the safety production process data threshold interval or the running parameter of the target oil and gas medium is greater than the upper boundary in the safety production process data threshold interval, it is determined that the sensor has a fault or is attacked and affects the normal operation of the oil and gas official system, and the alarm information is generated based on the running parameter of the target oil and gas medium; wherein the alarm information is used to indicate that the sensor is running abnormally.

[0099] Optionally, the alarm information includes at least one of the type of the running parameter in the target oil and gas medium, the numerical value of the running parameter, and the like.

[0100] Figure 3 Another flowchart of an oil and gas pipeline network sensor fault intelligent identification method provided by the embodiment of the present application is provided. Referring to Figure 3 The method includes the following steps:

[0101] S1021, obtaining a running parameter.

[0102] S1022、in the running parameter is located in the safety production process data threshold interval, according to each running parameter in the preset time period, the log likelihood ratio cumulative sum at each time is calculated.

[0103] Specifically, the running parameter of the target oil and gas medium is obtained, the running parameter of the target oil and gas medium is compared with the upper limit and the lower limit of the safety production process data threshold interval, when the running parameter of the target oil and gas medium is located in the upper limit and the lower limit of the safety production process data threshold interval, it is determined that the sensor does not exist abnormal or the sensor exists abnormal but the abnormal does not affect the normal operation of the gas transmission system. According to the running parameter in the preset time period, the log likelihood ratio cumulative sum at each time is calculated.

[0104] Optionally, the running parameter includes but is not limited to at least one of temperature, gas pressure.

[0105] It can be understood that when the running parameter of the target oil and gas medium includes multiple types, when each type of running parameter is located in the upper limit and the lower limit of the safety production process data threshold interval, it is determined that the sensor does not exist abnormal or the sensor exists abnormal but the abnormal does not affect the normal operation of the gas transmission system. When one or more of the running parameters in each type of running parameter is not located in the corresponding safety production process data threshold interval, it is determined that the sensor exists abnormal, and the corresponding alarm information is generated.

[0106] For example, the running parameter of the target oil and gas medium includes running temperature and running gas pressure. When the running temperature is located in the upper limit and the lower limit of the target temperature interval, and the running gas pressure is located in the upper limit and the lower limit of the target gas pressure interval, it is determined that the sensor does not exist abnormal or the sensor exists abnormal but the abnormal does not affect the normal operation of the gas transmission system. When any one of the running temperature is greater than the upper limit of the target temperature interval, the running temperature is less than the lower limit of the target temperature interval, the running gas pressure is greater than the upper limit of the target gas pressure interval, and the running gas pressure is less than the lower limit of the target gas pressure interval, it is determined that the sensor exists abnormal, and the corresponding alarm information is generated.

[0107] As an example but not limited to, the number of running parameters in a unit time may include one or more, and the corresponding preset time period can be specifically set according to the number of running parameters in a unit time.

[0108] For example, the number of running parameters in 1s is 2, and the preset time period is set to 5s. According to 15 groups of running parameters in the preset time period, the log likelihood ratio cumulative sum of running parameters every 0.5s is calculated.

[0109] For example, there is one operating parameter per second, and the preset time period is set to 10 seconds. Based on the 10 sets of operating parameters within the preset time period, the cumulative sum of the log-likelihood ratios of the operating parameters per second is calculated.

[0110] S1023. Based on the cumulative sum of the log-likelihood ratios at each time point, determine the mutation time point.

[0111] Specifically, the data mutation time point is determined based on the changes in the cumulative sum of log-likelihood ratios at each time point.

[0112] Optionally, the abrupt change time point can be determined based on the difference between the cumulative sum of log-likelihood ratios at each time point and the cumulative sum of log-likelihood ratios at the previous time point.

[0113] For example, the log-likelihood ratio at time e is S. e The cumulative log-likelihood ratio at time e-1 is the cumulative log-likelihood ratio S. e-1 S was calculated e With S e-1 When the difference is greater than or equal to the second threshold, time e is determined as the data mutation point.

[0114] This application embodiment can determine the correlation rules between abnormal data and abnormal types by pre-determining the safety production process data threshold range of the target oil and gas medium, based on the temporal characteristics of different safety level controllers of the system (such as the application of the first device and the redundancy of the second device) under different abnormal data causes, monitor the operating parameters of the equipment in real time, detect sensor data deviation by using non-parametric cumulative summation, identify abrupt data that exceeds the safety production process data threshold range of the target oil and gas medium as abnormal data, and identify the abnormal type of the sensor efficiently, quickly and accurately based on the abrupt data time point and the correlation rules as the criterion.

[0115] In some embodiments, the operating parameters include first operating parameters of the first device and second operating parameters of the second device; the mutation time point includes first mutation time point of the first device and second mutation time point of the second device.

[0116] Specifically, sensors may malfunction or be attacked by networks, and the data they collect may not be accurate or may be erroneous. Therefore, the presence of sensor anomalies can be detected through the operating parameters of the first and second devices. These operating parameters include the first operating parameter of the first device and the second operating parameter of the second device. The corresponding abrupt change time points include the first abrupt change time point where the data in the first device changes, and the second abrupt change time point where the data in the second device changes.

[0117] by Figure 1The oil and gas pipeline network sensor fault intelligent identification system shown in Figure 101 is taken as an example, Figure 4 A sensor data transmission application schematic diagram is provided for the embodiment of the present application.

[0118] As Figure 4 shown, in the process of the sensor transmitting data to the first device, the sensor is attacked by a network attack and injected with false data, causing the first device to receive abnormal data, so that the PI controller issues an incorrect feedback control command. In the running process, the data collected by the second device is normal data.

[0119] Based on this, the real pressure data transmitted by the filter separator is taken as P real (t), the pressure data collected by the sensor is P sensor (t), the pressure data obtained by the first device is P feed (t), and the pressure data obtained by the second device is P monitor (t), respectively calculate the first mutation time point at which mutation occurs in the first device, and the second mutation time point at which data mutation occurs in the second device.

[0120] Optionally, a change point statistical (NP-CUSUM) algorithm is used to construct a sensor abnormal data real-time monitoring model to calculate the log-likelihood ratio cumulative sum at each time point in a preset time period, and identify the first mutation time point and the second mutation time point.

[0121] The running parameter sequence Y e collected in a preset time period is taken as y1, y2,..., y t , wherein y e represents the running parameter at time e. For each time point e, the upper and lower cumulative sums are calculated to detect the upper and lower fluctuations of the data transmission process in the preset time period. The calculation method of the upper and lower cumulative sums is as shown in the following formula.

[0122]

[0123] wherein, represents the upper cumulative sum, represents the lower cumulative sum, and h represents a decision value for determining the mutation time point, which can be specifically set according to actual conditions. μ0 represents the expected value (reference value) of the data transmission process, which can be specifically set according to actual conditions. If the offset is large, it is determined that the data has changed, and max(0, ·) represents the larger value between zero and the current value, so that the calculation result is not negative.

[0124] Optionally, the mutation time point is detected by a log likelihood ratio. Assuming H0, it indicates that no change occurs in the data transmission process, and the data conforms to normal distribution; assuming H1, it indicates that the data has changed in the data transmission process, and the distribution of the data appears to be offset, and the calculation method of the log likelihood ratio is as shown in the following formula:

[0125]

[0126] wherein, Λ(y e ) represents the log likelihood ratio of the e th data, Λ(y e ) is large, which indicates that the data is more consistent with the hypothesis H1, that is, the data has a significant offset. L(H1|y e ) represents the likelihood function of the data y e under the hypothesis H1, and L(H0|y e ) represents the likelihood function of the data y e under the hypothesis H0, and the normal distribution likelihood function is as shown in the following formula:

[0127]

[0128] wherein, μ represents the sample mean of the running parameter sequence collected in the preset time period, σ 2 represents the variance of the running parameter sequence collected in the preset time period, and Y represents the running parameter sequence collected in the preset time period.

[0129] The log likelihood ratio of each time data is calculated, and the cumulative sum S e of each data point is calculated, as shown in the following formula:

[0130] S e = max (0, S e-1 + Λ(y e )-h) (11) ;

[0131] In this way, the difference between the log likelihood ratio cumulative sum of t0 and the minimum value of the log likelihood ratio cumulative sum before t0 can be used to describe the change process of the running parameter sequence, that is is a judgment basis for judging whether the data change exceeds the threshold value, as shown in the following formula:

[0132]

[0133] wherein, represents the log likelihood ratio cumulative sum of t0.

[0134] It can be understood that when is greater than the decision value h, it indicates that the data of t0 in the running parameter sequence collected in the preset time period has changed. When Less than or equal to h, indicating that the preset time period is collected, the data in the operating parameter sequence does not change.

[0135] From the perspective of sensor abnormal data, while adapting to the field discrete process data, the data fitting function processing step is removed, the data-driven sensor abnormality identification method is adopted, the causes and corresponding abnormal types of sensor abnormal data are efficiently and timely identified, and the precision of sensor abnormality identification is improved, facilitating equipment maintenance.

[0136] Figure 5 A monitoring schematic diagram of an operating parameter is provided for the embodiments of the application.

[0137] As shown in Figure 5 , the abscissa represents time, unit: ms, and the ordinate represents pressure value, unit: Mpa. The pressure safety operation threshold of the target oil and gas medium is 0-11.8 Mpa. At 527 ms, the pressure of the target oil and gas medium is greater than the upper limit value 11.8 Mpa of the pressure safety operation, and the control unit can identify the abnormal data and issue an abnormal control instruction.

[0138] However, when the sensor fails or the sensor is subjected to a network attack, and the temperature and pressure of the target oil and gas medium collected at the same time do not exceed the corresponding upper limit value, the PI controller may not perform feedback control. At this time, the abnormal data has no physical impact on the system itself. At this time, the sensor failure cannot be detected, and the network attack on the sensor is not recognized as an invalid attack. In this way, with the change of time, the influence of abnormal data on the system itself may become greater and greater, thereby causing a safety accident to occur.

[0139] Considering the above problems, the sensor abnormal data time sequence features can be extracted, and the abnormal type is determined based on the abnormal data time sequence features. In the oil and gas pipeline network sensor fault intelligent identification system shown in 101 in Figure 1 , the data obtained by the second device is redundant of the data in the first device. In the process of the sensor being subjected to a network attack, the injected false data is executed in the process of the sensor transmitting data to the first device. Therefore, in the case that the sensor itself functions normally, the second device can output data similar to the real data when the sensor is subjected to a network attack, that is, obtain the real data. Based on this, the basis for distinguishing between sensor attack and sensor failure can be that when the sensor is subjected to a network attack, the first device obtains false data, and the second device obtains real data. When the sensor fails, the first device and the second device both obtain abnormal data. That is, the time point of abnormal data is a key factor for judging the abnormal type.

[0140] Figure 6 Another flowchart of an oil and gas pipeline network sensor fault intelligent identification method provided for the embodiments of the application. Referring toFigure 6 The method step S103 comprises the following steps:

[0141] S1031, when the first mutation time point and the second mutation time point are not empty, calculating the time difference absolute value between the first mutation time point and the second mutation time point.

[0142] Specifically, when the first mutation time point of the first device and the second mutation time point of the second device are not empty, it is determined that the sensor is abnormal, and the time difference absolute value between the first mutation time point and the second mutation time point is calculated.

[0143] S1032, when the time difference absolute value is less than a second threshold, determining that the abnormal type is a sensor failure.

[0144] Specifically, the time difference absolute value between the first mutation time point and the second mutation time point is compared with the second threshold, and when the above-mentioned time difference absolute value is less than the second threshold, it is determined that the abnormal type of the sensor is a sensor failure.

[0145] S1033, when the time difference absolute value is greater than or equal to the second threshold, determining that the abnormal type is that the sensor is attacked by a network.

[0146] Specifically, when the time difference absolute value between the first mutation time point and the second mutation time point is greater than or equal to the second threshold, it is determined that the abnormal type of the sensor is that the sensor is attacked by a network.

[0147] The system running time is set as T', the sampling frequency of the sensor is f, the running parameter of the first device is P feed (t), and the running parameter of the second device is P monitor (t). feed (t) and P monitor (t) are introduced into a change point statistical (NP-CUSUM) model, and the output log likelihood ratio accumulations of the first device and the second device are S feed (t) and S monitor (t), respectively. feed (t) and S monitor (t), the first mutation time point T1 and the second mutation time point T2 are determined, and the time difference absolute value δ between the first mutation time point and the second mutation time point is calculated, δ = |T1-T2|.

[0148] Specifically, the second threshold is set as σ, when the time difference absolute value δ < σ, it is determined that the abnormal type is a sensor failure; and when the time difference absolute value δ ≥ σ, it is determined that the abnormal type is that the sensor is attacked by a network. Wherein, σ can be set according to actual conditions. For example, the value of σ is set as 0.1T.

[0149] It can be understood that when there is no data mutation time point in the operating parameters of the first device and the second device, it is determined that there is no anomaly.

[0150] Each model simulation can obtain T' / f pressure transient values (also referred to as pressure operating parameters), when the sensor fails, the first device and the second device obtain abnormal data, the mutation time points T1 and T2 of the first device and the second device exist, and the difference δ between the mutation time points of the first device and the second device is not large. When the sensor is attacked by the network, the operating parameters of the second device can be identified as normal data, and the operating parameters of the first device will have a large mutation at a certain moment, so the difference δ between the first mutation time point T1 and the second mutation time point T2 is large.

[0151] The embodiments of the present application can model sensor attacks and failures, extract time sequence features of controller output data, and determine the intelligent identification of abnormal types based on real-time discrete operating parameters, further improving the information security of the gas transmission system and providing data basis for the maintenance of the sensor.

[0152] Figure 7 An application scenario diagram of the oil and gas pipeline network sensor failure intelligent identification method provided by the embodiments of the present application.

[0153] Referring to Figure 7 , the abscissa represents time, the unit is ms, and the ordinate represents pressure value, the unit is Mpa, and the pressure safe operation threshold is 0-11.8 MPa. At 527 ms, because the pressure value is greater than the pressure upper limit value 11.8 KPa, the log likelihood ratio cumulative sum S feed (t) has a mutation. At 589 ms, when the pressure value is greater than the pressure safe operation upper limit value 11.8 KPa, the log likelihood ratio cumulative sum S monitor (t) has a mutation. Based on the first mutation time point of the first device and the second mutation time point of the second device, it can be determined that the abnormal type is a sensor physical failure.

[0154] Figure 8 Another application scenario diagram of the oil and gas pipeline network sensor failure intelligent identification method provided by the embodiments of the present application.

[0155] Referring to Figure 8 , the abscissa represents time, the unit is ms, and the ordinate represents pressure value, the unit is Kpa, and the pressure safe operation threshold is 0-11.8 MPa. At 378 ms, because the pressure value is greater than the pressure upper limit value 11.8 KPa, the log likelihood ratio cumulative sum S feed(t) a mutation occurs. And the log likelihood ratio cumulative sum S feed (t) a mutation occurs immediately after the system starts, based on the first mutation time point of the first device and the second mutation time point of the second device, it can be determined that the abnormal type is that the sensor is attacked by the network.

[0156] In some embodiments, the determining of the abnormal type based on the mutation time points further comprises:

[0157] When the first mutation time point and the second mutation time point are both null, it is determined that the sensor is running normally.

[0158] Specifically, when the first mutation time point determined based on the first running parameter of the first device and the second mutation time point determined based on the second running parameter of the second device are both null, it is determined that the running parameter in the first device and the second device does not have a data mutation time, that is, the sensor is running normally.

[0159] Embodiments of the present application determine the cause of the abnormal type by identifying the timing characteristics of the abnormal sensor data, thereby quickly and accurately identifying the abnormal type of the sensor based on the difference between the data mutation time points of the two devices, and improving the security of the system.

[0160] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action order described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0161] It should be further noted that, although each step in the flowchart is displayed in sequence according to the arrow indication, these steps are not necessarily executed in sequence according to the arrow indication. Unless explicitly stated in this paper, the execution of these steps has no strict order limitation, and these steps can be executed in other order. Moreover, at least part of the steps in the flowchart can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed with at least part of other steps or other steps or stages of sub-steps or stages.

[0162] Figure 9 A structural schematic diagram of an oil and gas pipeline network sensor fault intelligent identification device provided by an embodiment of the present application. Referring to Figure 9An oil and gas pipeline network sensor fault intelligent identification device, comprising:

[0163] A first determination module 901 is configured to determine a safety production process data threshold interval of a target oil and gas medium based on a physical parameter of the target oil and gas medium.

[0164] A second determination module 902 is configured to obtain an operating parameter and determine a mutation time point based on the operating parameter when the operating parameter is located in the safety production process data threshold interval.

[0165] A third determination module 903 is configured to determine an abnormal type based on the mutation time point, wherein the abnormal type includes a sensor fault or a network attack on the sensor.

[0166] In some embodiments, the target oil and gas medium includes a first substance and a second substance; the physical parameter includes a first physical parameter of the first substance and a second physical parameter of the second substance; and the first determination module 901 includes:

[0167] A first calculation unit is configured to calculate a mixed parameter of the target oil and gas medium based on the first physical parameter and the second physical parameter.

[0168] A first determination unit is configured to determine a temperature and pressure relationship ratio based on the mixed parameter.

[0169] A second determination unit is configured to determine a safety production process data threshold interval of the target oil and gas medium when the temperature and pressure relationship ratio is less than a first threshold value, wherein the safety production process data threshold interval includes at least one of a target temperature interval and a target pressure interval.

[0170] Optionally, the second determination module 902 includes:

[0171] An obtaining unit is configured to obtain an operating parameter.

[0172] A second calculation unit is configured to calculate a log-likelihood ratio cumulative sum at each time point based on each operating parameter in a preset time period when the operating parameter is located in the safety production process data threshold interval.

[0173] A third determination unit is configured to determine the mutation time point based on the log-likelihood ratio cumulative sum at each time point.

[0174] Optionally, the operating parameter includes a first operating parameter of a first device and a second operating parameter of a second device; and the mutation time point includes a first mutation time point of the first device and a second mutation time point of the second device.

[0175] The third determination module 903 includes:

[0176] a third calculation unit, configured to calculate a time difference absolute value of the first mutation time point and the second mutation time point when the first mutation time point and the second mutation time point are not empty;

[0177] a fourth determination unit, configured to determine that the abnormal type is a sensor failure when the time difference absolute value is less than a second threshold value.

[0178] alternatively,

[0179] a fifth determination unit, configured to determine that the abnormal type is that the sensor is attacked by a network when the time difference absolute value is greater than or equal to the second threshold value.

[0180] Optionally, the third determination module 903 further includes:

[0181] a sixth determination unit, configured to determine that the sensor is in normal operation when the first mutation time point and the second mutation time point are empty.

[0182] Optionally, the safety production process data threshold interval includes an upper boundary and a lower boundary; and the second determination module 902 includes:

[0183] a generation unit, configured to generate an alarm information when the operation parameter is less than the lower boundary or greater than the upper boundary; wherein the alarm information is used to indicate that the sensor is in abnormal operation.

[0184] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be realized by other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and another division way can be used in actual implementation. For example, a plurality of units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0185] Figure 10 The structure of the storage device provided by the embodiment of the present application is shown in the figure. As shown in the figure, the storage device can include a transceiver 1001, a processor 1002 and a memory 1003. Figure 10

[0186] The processor 1002 executes the computer execution instructions stored in the memory, so that the processor 1002 executes the scheme in the above-mentioned embodiments. The processor 1002 can be a general-purpose processor, including a central processing unit CPU, a network processor NP, etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.​

[0187] The memory 1003 is connected to the processor 1002 via the system bus and completes communication between them. The memory 1003 is used to store computer program instructions.

[0188] The transceiver 1001 can be used to obtain the physical parameters and operating parameters of the target oil and gas medium.

[0189] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. Transceivers are used to enable communication between database access devices and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and may also include non-volatile memory.

[0190] This application also provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer performs the technical solution of the intelligent identification method for oil and gas pipeline sensor faults described in the above embodiments.

[0191] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the technical solution of the intelligent identification method for oil and gas pipeline network sensor faults in the above embodiments.

[0192] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0193] If the integrated units / modules are implemented in the form of hardware, the hardware can be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. Unless otherwise specified, the storage unit can be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0194] If the integrated units / modules are implemented in the form of software program modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the essential part or all or part of the technical solutions that make contributions to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0195] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application

[0196] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0197] It is to be understood that the application is not limited to the precise construction herein disclosed and shown in the drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application is limited only by the claims that follow.

Claims

1. A method for intelligent identification of sensor faults in oil and gas pipeline networks, characterized in that, include: Based on the physical parameters of the target oil and gas medium, the data threshold range for the safe production process of the target oil and gas medium is determined; The system acquires operating parameters, and when the operating parameters are within the threshold range of the safety production process data, it determines the mutation time point based on the operating parameters; the operating parameters include the first operating parameters of the first device and the second operating parameters of the second device; the mutation time point includes the first mutation time point of the first device and the second mutation time point of the second device. Based on the mutation time point, the anomaly type is determined; wherein, the anomaly type includes sensor failure or sensor being attacked by network. The determination of the anomaly type based on the mutation time point includes: When neither the first mutation time point nor the second mutation time point is empty, the absolute value of the time difference between the first mutation time point and the second mutation time point is calculated. When the absolute value of the time difference is less than the second threshold, the anomaly type is determined to be a sensor failure; or, When the absolute value of the time difference is greater than or equal to the second threshold, the anomaly type is determined to be a network attack on the sensor.

2. The method according to claim 1, characterized in that, The target oil and gas medium includes a first substance and a second substance; the physical parameters include the first physical parameters of the first substance and the second physical parameters of the second substance; The determination of the safety production process data threshold range for the target oil and gas medium based on its physical parameters includes: Based on the first physical parameter and the second physical parameter, the mixing parameters of the target oil and gas medium are calculated; Based on the aforementioned mixing parameters, the ratio of temperature to pressure is determined; When the ratio of temperature to pressure is less than a first threshold, a safety production process data threshold range for the target oil and gas medium is determined; wherein, the safety production process data threshold range includes at least one of a target temperature range and a target pressure range.

3. The method according to claim 1, characterized in that, The step of acquiring operating parameters, and determining the abrupt change time point based on the operating parameters when the operating parameters are within the threshold range of the safety production process data, includes: Obtain runtime parameters; When the operating parameters are within the threshold range of the safe production process data, the cumulative sum of the log-likelihood ratios at each time point is calculated based on the operating parameters within a preset time period. The mutation time point is determined based on the cumulative sum of the log-likelihood ratios at each time point.

4. The method according to claim 1, characterized in that, The determination of the anomaly type based on the mutation time point also includes: When both the first and second mutation time points are empty, the sensor is determined to be operating normally.

5. The method according to any one of claims 1-4, characterized in that, The safety production process data threshold range includes an upper boundary and a lower boundary; after obtaining the operating parameters, it includes: An alarm message is generated when the operating parameter is less than the lower boundary or greater than the upper boundary; wherein the alarm message is used to indicate that the sensor is operating abnormally.

6. An intelligent fault identification device for oil and gas pipeline network sensors, characterized in that, include: The first determining module is used to determine the safety production process data threshold range of the target oil and gas medium based on the physical parameters of the target oil and gas medium. The second determining module is used to acquire operating parameters and, when the operating parameters are within the threshold range of the safe production process data, determine the mutation time point based on the operating parameters; the operating parameters include the first operating parameters of the first device and the second operating parameters of the second device; the mutation time point includes the first mutation time point of the first device and the second mutation time point of the second device. The third determining module is used to determine the anomaly type based on the mutation time point; wherein, the anomaly type includes sensor failure or sensor being attacked by a network. The third determining module is specifically used for: When neither the first mutation time point nor the second mutation time point is empty, the absolute value of the time difference between the first mutation time point and the second mutation time point is calculated. When the absolute value of the time difference is less than the second threshold, the anomaly type is determined to be a sensor failure; or, When the absolute value of the time difference is greater than or equal to the second threshold, the anomaly type is determined to be a network attack on the sensor.

7. A storage device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-5.

Images