Petrochemical device protection layer failure times prediction method and system, electronic equipment and storage medium

Abstract

The application discloses a petrochemical device protection layer failure number prediction method, comprising the following steps: S110, acquiring key safety variables and protection layers of the device; S120, collecting real-time monitoring values of the key safety variables and protection layer trigger states of the device, and counting failure numbers of each protection layer in each period; S130, calculating joint likelihood distribution functions of all protection layers; S140, calculating posterior failure number distribution functions of each protection layer according to the Bayes theory; and S150, dynamically correcting the failure numbers of the protection layers in the next period by using a Markov chain method. The application further discloses a petrochemical device protection layer failure number prediction system, an electronic device and a storage medium. The application monitors fluctuation conditions of the protection layers of the key safety variables of the device in a period, counts the failure numbers of the protection layers in the period, and dynamically predicts the failure numbers of the protection layers in the next period based on the Bayes algorithm and the Markov chain method, thereby providing technical support for device-side dynamic risk early warning.

Description

Technical Field

[0001] This invention relates to the field of risk assessment technology for petrochemical plants, and in particular to a method, system, electronic device, and storage medium for predicting the number of protective layer failures in petrochemical plants. Background Technology

[0002] In the past decade or so, with the development of the chemical industry, many major industrial accidents have occurred globally, attracting widespread attention and concern. This has greatly promoted the research and development of process safety management. To achieve effective process safety management, it is necessary to quantitatively analyze the risks of the equipment. Layer protection analysis, as an effective risk analysis method for chemical process safety, has been widely used in the industry.

[0003] The protection layer analysis method is a simplified, procedural, and quantitative risk analysis approach that assesses the probability of initial events, the probability of protection layer failure, and the severity of consequences. However, current protection layer analysis methods are phased and static risk assessments, failing to dynamically reflect the real-time risk status of the device, and feedback on weaknesses in risk control is often delayed.

[0004] At present, there are the following problems in risk monitoring and early warning of petrochemical plants: (1) The identification of plant risks is based on static risk assessment technologies such as HAZOP, SIL, and risk checklists, which cannot reflect the real-time risks of the plant and predict the risks of the plant in the next cycle; (2) How to efficiently convert massive amounts of real-time plant data into effective abnormal event information and store it; (3) How to calculate the number of protection layer failures in the next cycle through various abnormal events, so as to calculate the risk value of the plant.

[0005] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] One of the objectives of this invention is to provide a method, system, electronic device, and storage medium for predicting the number of failures of the protective layer of a petrochemical plant, thereby improving the problems of existing technologies that cannot dynamically reflect the real-time risk status of the plant and have lag in feedback.

[0007] Another objective of this invention is to provide a method, system, electronic device, and storage medium for predicting the number of failures of the protective layer in petrochemical plants, thereby improving the problem of low prediction efficiency in the prior art.

[0008] To achieve the above objectives, according to a first aspect of the present invention, the present invention provides a method for predicting the number of failures of a protective layer in a petrochemical plant, comprising the following steps:

[0009] S110 acquires key safety variables and their protection layers of the acquisition device;

[0010] The S120 acquisition device collects real-time monitoring values ​​of key safety variables and protection layer trigger status, and counts the number of failures of each protection layer in each cycle.

[0011] S130 calculates the joint likelihood distribution function of all protective layers;

[0012] S140 calculates the posterior failure frequency distribution function of each protective layer based on Bayesian theory; and

[0013] S150 uses a Markov chain method to dynamically correct the number of failures of the protective layer in the next cycle.

[0014] Furthermore, in the above technical solution, the protection layer for key safety variables includes high / low alarms and personnel response, high-high / low-low alarms and personnel response, and emergency shutdown.

[0015] Furthermore, in the above technical solution, the key safety variables of the device are collected through the device's PLC, DCS / SIS, and / or SCADA system.

[0016] Furthermore, in the above technical solution, step S130 includes:

[0017] Calculate the average failure probability ε1 for each protective layer;

[0018] The likelihood function distribution of each protective layer follows a Gamma distribution, i.e.

[0019] Among them U w The number of prior failures of the protective layer within each cycle; and

[0020] Calculate the joint likelihood distribution function of all protective layers, i.e.

[0021] Where E x For the number of protective layers, F w and S w These represent the number of failures and successes of the protective layer within cycle w, respectively.

[0022] Furthermore, in the above technical solution, the number of prior failures of the protective layer U in each cycle w It follows a Poisson distribution, i.e.

[0023] U w ~Poisson(ε1).

[0024] Furthermore, in the above technical solution, the posterior failure frequency distribution function of the protective layer is the product of the joint prior distribution of the protective layer and the joint likelihood distribution function of the protective layer, i.e.

[0025]

[0026] Where Data represents the total number of events for each protection layer, and X is the correlation matrix representing the correlation between each protection layer.

[0027]

[0028] Furthermore, in the above technical solution, step S150 includes:

[0029] S151 uses the calculated number of protective layer failures in the next cycle as the initial value ε. (0) ;

[0030] S152 randomly selects parameters A and B based on the curves of the shape parameters a and b of the Gamma function;

[0031] S153 determines based on the selected A and B.

[0032] S154 will With initial value ε (0) In comparison;

[0033] in, If z ≥ 1, then take the original result as the result of this iteration and continue to the next iteration; if z < 1, then select a new result. As a result of this iteration, z-values ​​are defined by the formula in the Markov chain, V is the proposed distribution, which is related to the initial value and the shape parameter A; and

[0034] S155 Repeat steps S152 to S154 for the next iteration until the iteration ends. The final result is the corrected predicted number of protective layer failures in the next cycle.

[0035] Furthermore, the method for predicting the number of failures of the protective layer in petrochemical plants, as described above, also includes the following steps:

[0036] Risk value of accident caused by abnormal fluctuations in the protective layer of S160 computing device.

[0037] Furthermore, in the above technical solution, step S160 includes:

[0038] Calculate the accident risk value of abnormal fluctuations in each protective layer.

[0039] The risk of an accident due to abnormal fluctuations in the critical protection layer of the device is [value missing].

[0040] P=max(P(C1),P(C2),P(C3),...,P(C n )).

[0041] Furthermore, in the above technical solution, the key safety variables and their protection layers of the device are obtained by performing HAZOP analysis on the device.

[0042] According to a second aspect of the present invention, the present invention provides a petrochemical plant protective layer failure count prediction system, comprising: a data acquisition unit, which is used to acquire key safety variables of the plant and their protective layers, and collect real-time monitoring values ​​of key safety variables and protective layer triggering states, and count the failure count of each protective layer in each cycle; a data analysis unit, which is used to calculate the joint likelihood distribution function of all protective layers, and calculate the posterior failure count distribution function of each protective layer according to Bayesian theory; a correction unit, which is used to dynamically correct the failure count of the protective layer in the next cycle using the Markov chain method; and an output unit, which is used to output the corrected predicted failure count of the protective layer in the next cycle.

[0043] According to a third aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform a method for predicting the number of failures of a protective layer for a petrochemical plant as described in any of the above-described technical solutions.

[0044] According to a fourth aspect of the present invention, the present invention provides a non-transitory computer-readable storage medium storing computer-executable instructions for causing a computer to execute a method for predicting the number of failures of a protective layer in a petrochemical plant as described in any of the above-described technical solutions.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. Based on the real-time status of the protective layer, this invention predicts and dynamically corrects the number of failures of the protective layer in the next cycle, and can dynamically and accurately predict the real-time risks of the device.

[0047] 2. This invention monitors the fluctuation of the key safety variable protection layer of the monitoring device within a cycle. By statistically analyzing the number of protection layer failures within a cycle, it dynamically predicts the number of protection layer failures in the next cycle based on Bayesian algorithms and Markov chain methods. It can also calculate the device risk value in real time, providing technical support for dynamic risk early warning at the device end.

[0048] 3. This invention can use the historical initial failure count of the critical protective layer of the device to predict the failure count of each protective layer in the next cycle, which can be used for real-time monitoring and effective early warning of device risks.

[0049] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description

[0050] Figure 1 This is a flowchart illustrating a method for predicting the number of failures of a protective layer in a petrochemical plant according to an embodiment of the present invention.

[0051] Figure 2 This is a schematic diagram of a petrochemical plant protective layer failure prediction system according to an embodiment of the present invention.

[0052] Figure 3 This is a schematic diagram of the hardware structure of an electronic device for performing a method for predicting the number of failures of a protective layer in a petrochemical plant according to an embodiment of the present invention. Detailed Implementation

[0053] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0054] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprises" shall be understood to include the stated elements or components without excluding other elements or other components.

[0055] In this document, for ease of description, spatial relative terms such as “below,” “under,” “down,” “above,” “above,” “upper,” etc., are used to describe the relationship of one element or feature to another element or feature in the accompanying drawings. It should be understood that spatial relative terms are intended to encompass different orientations of an object in use or operation, in addition to those depicted in the figures. For example, if an object in the figure is flipped, an element described as “below” or “under” another element or feature would be oriented “above” that element or feature. Thus, the exemplary term “below” can encompass both the downward and upward orientations. An object may also have other orientations (rotated 90 degrees or other orientations), and the spatial relative terms used herein should be interpreted accordingly.

[0056] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.

[0057] like Figure 1As shown, the method for predicting the number of failures of the protective layer of a petrochemical plant according to a specific embodiment of the present invention includes the following steps:

[0058] S110 acquires key safety variables and their protection layers from the device.

[0059] Furthermore, in one or more exemplary embodiments of the present invention, key safety variables of the device and the protection layer for each key safety variable are determined by performing HAZOP analysis on the device.

[0060] The S120 acquisition device collects real-time monitoring values ​​of key safety variables and protection layer trigger status, and counts the number of failures of each protection layer in each cycle.

[0061] Furthermore, in one or more exemplary embodiments of the present invention, key safety variables in systems such as PLCs, DCS / SIS, and SCADA are collected in real time via a gateway protocol. Based on the real-time monitoring values ​​of the key safety variables and the trigger status of the protection layers, the number of abnormal events is recorded. The number of failures of each protection layer within each cycle is statistically analyzed.

[0062] S130 calculates the joint likelihood distribution function for all protective layers.

[0063] Furthermore, in one or more exemplary embodiments of the present invention, since the number of protective layer failures in one cycle is independent of the number of protective layer failures in the previous cycle, the number of prior protective layer failures U in each cycle is... w It follows a Poisson distribution, i.e., U w ~Poisson(ε1), where ε1 is the average failure probability of each protective layer.

[0064] The likelihood function data for each protective layer is obtained over the number of failures of all protective layers. Therefore, the likelihood function distribution for each protective layer follows a Gamma distribution, i.e.

[0065] Based on the likelihood function of each protective layer, the joint likelihood distribution function of all protective layers is obtained, i.e. Where E x For the number of protective layers, F w and S w These represent the number of failures and successes of the protective layer within cycle w, respectively.

[0066] S140 uses a Bayesian algorithm to calculate the posterior failure frequency distribution function for each protective layer.

[0067] Furthermore, in one or more exemplary embodiments of the present invention, according to the Bayesian algorithm, the posterior distribution is the product of the prior distribution and the likelihood function. The posterior failure frequency distribution function of each protection layer is the product of the joint prior distribution of the protection layers and the joint likelihood distribution function of the protection layers, i.e. Where Data represents the total number of events for each protection layer, and X is the correlation matrix representing the correlation between each protection layer (the following correlation matrix applies to cases with 5 or fewer protection layers; generally, devices have no more than 5 protection layers).

[0068]

[0069] S150 uses a Markov chain method to dynamically correct the number of failures of the protective layer in the next cycle.

[0070] Further, in one or more exemplary embodiments of the present invention, step S150 includes:

[0071] S151 uses the calculated number of protective layer failures in the next cycle as the initial value ε. (0) ;

[0072] S152 randomly selects parameters A and B based on the curves of the shape parameters a and b of the Gamma function;

[0073] S153 determines based on the selected A and B.

[0074] S154 will With initial value ε (0) In comparison,

[0075] in, If z≥1, then take the original result. As the result of this iteration, the next iteration continues. If z < 1, then a new [item] is selected. As a result of this iteration, the formula for the z-value is the same as that determined in the Markov chain, V is the proposed distribution, which is related to the initial value and the shape parameter A; and

[0076] S155 Repeat steps S152 to S154 for the next iteration until the iteration ends. The final result is the corrected predicted number of protective layer failures in the next cycle.

[0077] Risk value of accident caused by abnormal fluctuations in the protective layer of S160 computing device.

[0078] Furthermore, in one or more exemplary embodiments of the present invention, the risk value of an accident caused by abnormal fluctuations in the critical protective layer of the device is the location among the protective layers where the accident is most likely to occur. Step S160 includes:

[0079] Calculate the accident risk value of abnormal fluctuations in each protective layer. as well as

[0080] The risk of an accident due to abnormal fluctuations in the critical protection layer of the device is [value missing].

[0081] P=max(P(C1),P(C2),P(C3),...,P(C n )).

[0082] The method, system, electronic device, and storage medium for predicting the failure frequency of the protective layer of petrochemical equipment according to the present invention are described in more detail below by way of specific embodiments. It should be understood that the embodiments are merely exemplary and the present invention is not limited thereto.

[0083] Example 1

[0084] This embodiment uses the petrochemical plant protective layer failure prediction method of the present invention to predict the number of protective layer failures of a certain plant in real time.

[0085] HAZOP analysis was conducted on the device to determine its key safety variables and corresponding protection layers as C1, C2, ..., C n (In this embodiment, these are C1 to C5). The protection layers for the key safety variables of this device include high / low alarms and personnel response, high-high / low-low alarms and personnel response, and emergency shutdown.

[0086] The gateway protocol is used to collect key safety variables in systems such as PLC, DCS / SIS, and SCADA in real time. Based on the real-time monitoring values ​​of key safety variables and the trigger status of protection layers, the number of abnormal events is recorded. The number of failures of each protection layer in each cycle is statistically analyzed, as shown in Table 1.

[0087] Table 1. Number of failures of each protective layer in each cycle.

[0088] 1 137 116 75 2 0 2 146 107 68 3 0 3 128 114 69 2 1 4 133 120 80 1 0 5 139 121 71 2 0 …

[0089] Calculate the average failure probability ε for each protective layer. n ε1 represents the average failure probability of the protective layer C1, as shown in Table 2.

[0090] Table 2 Average failure probability of each protective layer

[0091] Average failure probability 0.418 0.354 0.223 0.006 0.0006

[0092] Assume U is the number of prior failures of the protective layer in each cycle. w It follows a Poisson distribution, i.e., U w~Poisson(ε1). The likelihood function data for each protective layer is obtained over the number of failures of all protective layers. Therefore, the likelihood function distribution of each protective layer follows a Gamma distribution, i.e.

[0093] Based on the likelihood function of each protective layer, the joint likelihood distribution function of all protective layers is obtained, i.e. Where E x For the number of protective layers, F w and S w These represent the number of failures and successes of the protective layer within cycle w, respectively.

[0094] According to the Bayesian algorithm, the posterior failure frequency distribution function of each protection layer is the product of the joint prior distribution of the protection layers and the joint likelihood distribution function of the protection layers, i.e.

[0095]

[0096] Where Data represents the total number of events for each protection layer, and X is the correlation matrix representing the correlation between each protection layer, with the specific values ​​as follows:

[0097]

[0098] The expected (predicted) number of failures for each protective layer can be obtained from the posterior failure number distribution function of the protective layer, E(C1)=ε1f(ε1)d(ε1)=139.753, as shown in Table 3.

[0099] Table 3 Predicted Failure Count for Each Protective Layer

[0100] Expected number of failures 139.753 115.376 71.208 2.016 0.0004

[0101] The Markov chain method is used to dynamically correct the failure count of the protective layer in the next cycle, including:

[0102] S151 uses the calculated number of next cycle protection layer failures as the initial value (taking C1 protection layer as an example, the initial value ε). (0) =139.753);

[0103] S152 randomly selects parameters A and B based on the shape parameters a and b curves of the Gamma function (i.e., the shape parameter and inverse scale parameter in the Gamma function), with initial parameters A = 0.3 and B = 0.4;

[0104] S153 determines based on the selected A and B.

[0105] S154 will With initial value ε (0) In comparison,

[0106] in, If z ≥ 1, then take the original result as the result of this iteration and continue to the next iteration; if z < 1, then select a new result. As a result of this iteration; and

[0107] S155 Repeat steps S152 to S154 for the next iteration until the iteration ends. The final result is the corrected predicted number of protective layer failures in the next cycle.

[0108] In this embodiment, a total of 1000 iterations were performed. Taking the protective layer C1 as an example, 95% of the results were distributed within the interval [135.781, 149.029], with an expected E(C1) = 142.624. The predicted number of protective layer failures in the next cycle after correction for each protective layer is shown in Table 4.

[0109] Table 4. Predicted number of protective layer failures in the next cycle after corrections for each protective layer.

[0110] Corrected expected number of failures 142.624 114.526 73.294 1.931 0.0003

[0111] Example 2

[0112] refer to Figure 2 As shown, this embodiment illustrates the petrochemical plant protective layer failure prediction system according to the present invention, which includes: a data acquisition unit 10, used to acquire the plant's key safety variables and their protective layers, and collect the real-time monitoring values ​​of the plant's key safety variables and the trigger status of the protective layers, and count the failure count of each protective layer in each cycle; a data analysis unit 20, used to calculate the joint likelihood distribution function of all protective layers, and calculate the posterior failure count distribution function of each protective layer according to Bayesian theory; a correction unit 30, used to dynamically correct the failure count of the protective layers in the next cycle using the Markov chain method; and an output unit 40, used to output the corrected predicted failure count of the protective layers in the next cycle.

[0113] Example 3

[0114] This embodiment provides a non-transitory (non-volatile) computer storage medium that stores computer-executable instructions that can execute the methods in any of the above method embodiments and achieve the same technical effect.

[0115] Example 4

[0116] This embodiment provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the methods described above and achieve the same technical effects.

[0117] Example 5

[0118] Figure 3 This is a schematic diagram of the hardware structure of the electronic device for executing the method for predicting the number of failures of the protective layer of a petrochemical plant according to this embodiment. The device includes one or more processors 610 and a memory 620. Taking one processor 610 as an example, the device may also include an input device 630 and an output device 640.

[0119] The processor 610, memory 620, input device 630, and output device 640 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0120] The memory 620, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 610 executes various functional applications and data processing of the electronic device by running the non-transitory software programs, instructions, and modules stored in the memory 620, thereby implementing the processing method of the above-described method embodiments.

[0121] The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data, etc. Furthermore, the memory 620 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 620 may optionally include memory remotely located relative to the processor 610, and these remote memories may be connected to the processing device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0122] Input device 630 can receive input digital or character information and generate signal input. Output device 640 may include display devices such as a display screen.

[0123] One or more modules are stored in memory 620 and, when executed by one or more processors 610, execute:

[0124] S110 acquires key safety variables and their protection layers of the acquisition device;

[0125] The S120 acquisition device collects real-time monitoring values ​​of key safety variables and protection layer trigger status, and counts the number of failures of each protection layer in each cycle.

[0126] S130 calculates the joint likelihood distribution function of all protective layers;

[0127] S140 uses a Bayesian algorithm to calculate the posterior failure frequency distribution function for each protective layer; and

[0128] S150 dynamically corrects the failure count of the protection layer in the next cycle based on the Markov chain method.

[0129] The above-described product can execute the methods provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in other embodiments of the present invention.

[0130] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general-purpose hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0132] The foregoing description of specific exemplary embodiments of the present invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of the invention, as well as various different choices and variations. Any simple modifications, equivalent changes, and alterations made to the foregoing exemplary embodiments should fall within the scope of protection of the present invention.

Claims

1. A method for predicting the number of failures of a protective layer in a petrochemical plant, characterized in that, The steps include the following: S110 acquires key safety variables and their protection layers of the acquisition device; The S120 acquisition device collects real-time monitoring values ​​of key safety variables and protection layer trigger status, and counts the number of failures of each protection layer in each cycle. S130 calculates the joint likelihood distribution function of all protective layers; step S130 includes: calculating the average failure probability of each protective layer. The likelihood function distribution of each protective layer follows a Gamma distribution, i.e. ,in The number of prior failures of the protective layer within each period; and the calculation of the joint likelihood distribution function of all protective layers, i.e. ,in For the number of protective layers, and These represent the number of failures and successes of the protective layer within cycle w, respectively. S140 uses a Bayesian algorithm to calculate the posterior failure frequency distribution function of each protection layer. The posterior failure frequency distribution function of each protection layer is the product of the joint prior distribution and the joint likelihood distribution function of the protection layers. S150 dynamically corrects the failure count of the protective layer in the next cycle based on the Markov chain method; step S150 includes: S151 uses the calculated number of protective layer failures in the next cycle as the initial value. ; S152 randomly selects parameters A and B based on the curves of the shape parameters a and b of the Gamma function; S153 determines based on the selected A and B. ; S154 will With initial value In comparison; ,in, , If z ≥ 1, then take the original result as the result of this iteration and continue to the next iteration; if z < 1, then select a new result. As a result of this iteration, z represents the formula determined in the Markov chain, and V is the proposed distribution; and S155 Repeat steps S152~S154 for the next iteration until the iteration ends. The final result is the corrected predicted number of protective layer failures in the next cycle.

2. The method for predicting the number of failures of the protective layer in a petrochemical plant according to claim 1, characterized in that, The protection layers for key safety variables include high / low alarms and personnel response, high-high / low-low alarms and personnel response, and emergency shutdown.

3. The method for predicting the number of failures of the protective layer in a petrochemical plant according to claim 1, characterized in that, Key safety variables of the device are collected through the device's PLC, DCS, SIS, and / or SCADA systems.

4. The method for predicting the number of failures of the protective layer in a petrochemical plant according to claim 1, characterized in that, Number of a priori failures of the protective layer in each cycle It follows a Poisson distribution, i.e. 。 5. The method for predicting the number of failures of the protective layer in a petrochemical plant according to claim 1, characterized in that, The product of the joint prior distribution of the protective layer and the joint likelihood distribution function of the protective layer, i.e. ， Where Data represents the total number of events for each protection layer, and X is the correlation matrix representing the correlation between each protection layer. 。 6. The method for predicting the number of failures of the protective layer in a petrochemical plant according to claim 1, characterized in that, It also includes the following steps: Risk value of accident caused by abnormal fluctuations in the protective layer of S160 computing device.

7. The method for predicting the number of failures of the protective layer in a petrochemical plant according to claim 1, characterized in that, Step S160 includes: Calculate the accident risk value of abnormal fluctuations in each protective layer. ; The risk of an accident due to abnormal fluctuations in the critical protection layer of the device is [value missing]. 。 8. The method for predicting the number of failures of the protective layer in a petrochemical plant according to claim 1, characterized in that, By performing HAZOP analysis on the device, the key safety variables and their protection layers were obtained.

9. A system for predicting the number of failures of a protective layer in a petrochemical plant, characterized in that, The method described in any one of claims 1 to 8 includes: The data acquisition unit is used to acquire the key safety variables of the device and their protection layers, and to collect the real-time monitoring values ​​of the key safety variables and the trigger status of the protection layers, and to count the number of failures of each protection layer in each cycle. The data analysis unit is used to calculate the joint likelihood distribution function of all protective layers and, based on Bayesian theory, to calculate the posterior failure frequency distribution function of each protective layer. The correction unit is used to dynamically correct the failure count of the protective layer in the next cycle using the Markov chain method; and The output unit is used to output the corrected predicted number of failures of the protective layer in the next cycle.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, causes the at least one processor to perform the petrochemical plant protective layer failure prediction method as described in any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer-executable instructions for causing the computer to execute the petrochemical plant protective layer failure prediction method as described in any one of claims 1 to 8.

Images