Blowout leakage risk processing method and device for polar region drilling platform

Abstract

The invention relates to the technical field of oil and gas development, and discloses a blowout leakage risk processing method and device for a polar drilling platform, which can take a blowout leakage accident as a top event, and divide the polar drilling platform into a plurality of subsystems associated with the top event; determining the fault events of the plurality of subsystems as a plurality of intermediate events corresponding to the top event, and determining a logical relationship between the top event and the plurality of intermediate events; determining a bottom event corresponding to each intermediate event, and determining a logical relationship between each intermediate event and the corresponding bottom event; constructing a fault tree model according to the top event, each intermediate event, each bottom event and the corresponding logical relationship; and according to the first Bayesian network corresponding to the fault tree model, identifying the bottom event having key influence on the blowout leakage accident, thereby effectively realizing treatment of the blowout leakage risk of the polar region, enriching the treatment modes of the blowout leakage risk of the polar region, and enhancing the diversity of the treatment modes of the blowout leakage risk of the polar region.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas development, and in particular to a method and device for handling blowout leakage risks of a polar drilling platform. Background Art

[0002] Well blowouts and leaks are relatively serious accidents during oil and gas exploration and development activities in polar regions, which may cause significant loss of life and property and serious environmental damage.

[0003] Related technologies can safely and effectively manage blowout risks at an acceptable risk level, such as risk identification, analysis and control of blowouts, which are crucial for oil and gas exploration and development. However, there are few related technologies for dealing with blowout risks in polar regions. Summary of the invention

[0004] The present invention provides a method and device for handling blowout leakage risks of a polar drilling platform, so as to solve the defect that related technologies have few methods for handling blowout leakage risks in the polar regions, and enrich the methods for handling blowout leakage risks in the polar regions.

[0005] In a first aspect, a method for handling blowout leakage risks of a polar drilling platform comprises:

[0006] Taking a blowout leakage accident of a polar drilling platform as a top event, and dividing the polar drilling platform into a plurality of subsystems associated with the top event;

[0007] Determine the fault events of the multiple subsystems as multiple intermediate events corresponding to the top event, and determine the logical relationship between the top event and the multiple intermediate events;

[0008] Determine a base event corresponding to each of the intermediate events, and determine a logical relationship between each of the intermediate events and the corresponding base event;

[0009] Constructing a fault tree model according to the top event, each of the intermediate events, each of the bottom events and corresponding logical relationships;

[0010] According to the first Bayesian network corresponding to the fault tree model, the bottom event having a critical impact on the blowout leakage accident is identified.

[0011] Optionally, constructing a fault tree model according to the top event, each of the intermediate events, each of the bottom events and corresponding logical relationships includes:

[0012] Creating a top event node corresponding to the top event, creating an intermediate event node corresponding to each intermediate event, and creating a bottom event node corresponding to each bottom event;

[0013] Based on the logical relationship between the top event and the plurality of intermediate events, a corresponding logic gate is created between the top event node and the intermediate event node, and based on the logical relationship between the intermediate event and the bottom event, a corresponding logic gate is created between the intermediate event node and the bottom event node, so as to construct the fault tree model;

[0014] The fault tree model includes the top event node, each of the intermediate event nodes, each of the bottom event nodes and corresponding logic gates.

[0015] Optionally, the identifying the bottom event having a critical impact on the blowout leakage accident according to the first Bayesian network corresponding to the fault tree model includes:

[0016] Mapping the fault tree model into the first Bayesian network;

[0017] The bottom event having a critical impact on the blowout leakage accident is identified according to the first Bayesian network.

[0018] Optionally, mapping the fault tree model to the first Bayesian network includes:

[0019] Taking each of the bottom event nodes in the fault tree model as a root node, taking each of the intermediate event nodes in the fault tree model as an intermediate node, and taking the top event node in the fault tree model as a leaf node;

[0020] Generate a conditional probability relationship between the leaf node and each of the intermediate nodes according to the logic gate between the top event node and each of the intermediate event nodes in the fault tree model; and generate a conditional probability relationship between each of the intermediate nodes and the corresponding root node according to the logic gate between each of the intermediate event nodes and the bottom event node in the fault tree model;

[0021] The root node, each of the intermediate nodes, the leaf nodes and the corresponding conditional probability relationships are taken as a whole as the first Bayesian network.

[0022] Optionally, the identifying the bottom event having a critical impact on the blowout leakage accident according to the first Bayesian network includes:

[0023] Obtaining the occurrence probability of each of the bottom events, and setting the occurrence probability of the bottom event as the prior probability corresponding to the root node in the first Bayesian network;

[0024] Determine the prior probability of each of the intermediate nodes and the leaf nodes based on the conditional probability relationship in the first Bayesian network and the prior probability of each of the root nodes;

[0025] Under the assumption that the top event must occur, the node state of the leaf node in the first Bayesian network is set accordingly, and based on the conditional probability relationship in the first Bayesian network, the prior probability of the leaf node and the prior probability of each of the intermediate nodes, the posterior probability of each of the intermediate nodes and each of the root nodes is determined in sequence;

[0026] Determine the probability change rate of each root node according to the posterior probability and the prior probability of each root node;

[0027] Comparing the probability change rate of each of the root nodes with a preset threshold value respectively to determine all target root nodes; wherein the probability change rate of the target root node is higher than the preset threshold value;

[0028] All target root nodes are determined as the bottom events having a critical impact on the blowout leakage accident.

[0029] Optionally, the method further includes:

[0030] Taking the blowout leakage accident as an initial event, and constructing an event tree model according to the initial event;

[0031] Converting the event tree model into a second Bayesian network;

[0032] The safety of the polar drilling platform is evaluated based on the second Bayesian network.

[0033] Optionally, constructing an event tree model according to the initial event includes:

[0034] Determine a multi-level safety barrier in the polar drilling platform for handling the initial event; wherein the first level of the safety barrier in the multi-level safety barrier is put into use when the initial event occurs, and the other levels of the safety barrier are put into use when the previous level of the safety barrier fails;

[0035] Determine the input consequences corresponding to each level of the safety barrier;

[0036] Creating an initial event node corresponding to the initial event, creating a multi-level safety node corresponding to the multi-level safety barrier, and creating a consequence node corresponding to the input consequence;

[0037] Establishing an event evolution link between the initial event node, the multi-level safety node and the consequence node as an event tree model;

[0038] The evaluating the safety of the polar drilling platform based on the second Bayesian network includes:

[0039] The effectiveness of each level of the safety barrier is evaluated according to the second Bayesian network.

[0040] Optionally, converting the event tree model into a second Bayesian network includes:

[0041] Creating a corresponding Bayesian initial event node according to the initial event node in the event tree model, and initializing the node state of the Bayesian initial event node; creating a corresponding multi-level Bayesian safety node according to the multi-level safety node in the event tree model, and initializing the node state of each Bayesian safety node;

[0042] Creating a corresponding Bayesian consequence node based on the consequence node, and initializing the node state of the Bayesian consequence node; wherein the node state of the Bayesian consequence node is used to identify each of the input consequences;

[0043] According to the event evolution link in the event tree model, a conditional probability relationship between the node state of the Bayesian initial event node, the node state of each level of the Bayesian safety node and the node state of the Bayesian consequence node is generated;

[0044] The conditional probability relationship among the Bayesian initial event node, the Bayesian safety node at each level, the Bayesian consequence node and the node state is taken as the second Bayesian network.

[0045] Optionally, the node state of the Bayesian initial event node is used to identify whether the initial event occurs, and the node state of each level of the Bayesian safety node is used to identify whether the corresponding safety barrier is valid or invalid;

[0046] The evaluating the effectiveness of each of the safety barriers according to the second Bayesian network comprises:

[0047] Obtaining the failure probability of the safety barrier at each level, and using the failure probability of the safety barrier at each level as the prior probability of the corresponding Bayesian safety node;

[0048] Under the assumption that the initial event must occur, correspondingly setting the node state of the Bayesian initial event node in the second Bayesian network;

[0049] For any of the Bayesian safety nodes, when the node state of the Bayesian safety node is set to failure, the first occurrence probability corresponding to the investment consequence is determined based on the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node; when the node state of the Bayesian safety node is set to success, the second occurrence probability corresponding to the investment consequence is determined based on the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node; the effectiveness of the safety barrier is evaluated based on the difference between the first occurrence probability and the second occurrence probability.

[0050] In a second aspect, the present invention provides a blowout leakage risk treatment device for a polar drilling platform, comprising:

[0051] As a unit, it is used to take the blowout and leakage accident of the polar drilling platform as the top event;

[0052] a dividing unit, for dividing the polar drilling platform into a plurality of subsystems associated with the top event;

[0053] A first determining unit, configured to determine the fault events of the multiple subsystems as multiple intermediate events corresponding to the top event;

[0054] A second determining unit, configured to determine a logical relationship between the top event and the plurality of intermediate events;

[0055] A third determining unit, configured to determine a bottom event corresponding to each of the intermediate events;

[0056] A fourth determining unit, used to determine the logical relationship between each of the intermediate events and the corresponding bottom event;

[0057] A first construction unit is used to construct a fault tree model according to the top event, each of the intermediate events, each of the bottom events and corresponding logical relationships;

[0058] An identification unit is used to identify the bottom event that has a critical impact on the blowout leakage accident according to the first Bayesian network corresponding to the fault tree model.

[0059] The method and device for handling blowout leakage risks of a polar drilling platform provided by the present invention can take a blowout leakage accident as a top event, divide the polar drilling platform into multiple subsystems associated with the top event; determine the fault events of multiple subsystems as multiple intermediate events corresponding to the top event, and determine the logical relationship between the top event and the multiple intermediate events; determine the bottom event corresponding to each intermediate event, and determine the logical relationship between each intermediate event and the corresponding bottom event; construct a fault tree model based on the top event, each intermediate event, each bottom event and the corresponding logical relationship; identify the bottom event that has a key impact on the blowout leakage accident based on the first Bayesian network corresponding to the fault tree model, which can effectively realize the handling of polar blowout leakage risks, enrich polar blowout leakage risk handling methods, and enhance the diversity of polar blowout leakage risk handling methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A flow chart of a method for handling blowout and leakage risks of a polar drilling platform provided by an embodiment of the present invention;

[0062] Figure 2 A schematic diagram of the structure of a fault tree model provided by an embodiment of the present invention;

[0063] Figure 3 An illustration of symbols in a fault tree model provided by an embodiment of the present invention;

[0064] Figure 4 A numerical mapping illustration diagram of a fault tree model mapping Bayesian network provided by an embodiment of the present invention;

[0065] Figure 5 A schematic diagram of the structure of a Bayesian network provided by an embodiment of the present invention;

[0066] Figure 6 A schematic diagram of a comparison between a priori probability and a posteriori probability of a key event of a polar offshore blowout provided by an embodiment of the present invention;

[0067] Figure 7 A schematic diagram of the structure of an event tree model provided by an embodiment of the present invention;

[0068] Figure 8 A structural diagram of a bow-tie model provided by an embodiment of the present invention

[0069] Fig. 9 An illustration of numerical mapping of an event tree mapping Bayesian network provided by an embodiment of the present invention;

[0070] Fig.10 A schematic structural diagram of a blowout leakage risk treatment device for a polar drilling platform provided by an embodiment of the present invention;

[0071] Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] In order to solve the problem that there are few methods for handling blowout leakage risks in related technologies, the blowout leakage risk handling method and device for polar drilling platforms provided in this embodiment can take the blowout leakage accident as the top event, divide the polar drilling platform into multiple subsystems associated with the top event; determine the fault events of multiple subsystems as multiple intermediate events corresponding to the top event, and determine the logical relationship between the top event and the multiple intermediate events; determine the bottom event corresponding to each intermediate event, and determine the logical relationship between each intermediate event and the corresponding bottom event; construct a fault tree model based on the top event, each intermediate event, each bottom event and the corresponding logical relationship; identify the bottom event that has a key impact on the blowout leakage accident based on the first Bayesian network corresponding to the fault tree model, effectively realize the handling of blowout leakage risks in polar regions, enrich the blowout leakage risk handling methods in polar regions, and enhance the diversity of blowout leakage risk handling methods in polar regions.

[0074] Combine the following Figure 1-Figure 9 The blowout leakage risk treatment method of the polar drilling platform of this embodiment is described.

[0075] like Figure 1 As shown, this embodiment proposes a first method for handling blowout leakage risks of a polar drilling platform, which may include the following steps:

[0076] S101. Take the blowout and leakage accident of the polar drilling platform as the top event.

[0077] The polar drilling platform may be a drilling platform located in a polar region. Further, the polar drilling platform may be a polar offshore drilling platform.

[0078] It should be noted that this embodiment can handle the blowout leakage risk of drilling platforms in different regions and environments. Specifically, this embodiment can handle the blowout leakage risk of polar drilling platforms. Furthermore, this embodiment can take the blowout leakage risk handling in polar offshore drilling platforms as an example to introduce the execution process in the relevant steps.

[0079] Specifically, the Arctic region is rich in oil and gas resources. With climate warming and melting glaciers in recent years, it has attracted increasing attention from academia and industry, especially in oil and gas exploration activities. However, the harsh environmental conditions and remote geographical location of the Arctic pose great risks to drilling operations. Effective risk management is essential to safely carry out these operations at an acceptable risk level, including risk identification, analysis and control of Arctic drilling.

[0080] Well blowouts are considered one of the most catastrophic events in oil and gas activities, including in the Arctic. Such accidents can cause significant loss of life and property, as well as serious environmental damage. The fragile Arctic environment is particularly vulnerable to damage, so environmental risks need to be minimized. Accidents in Arctic drilling operations occur from time to time, and effective risk management strategies are urgently needed.

[0081] Many risk assessment methods are used to identify and evaluate accident risks. Most of them are designed to deal with onshore and offshore accident scenarios, including deepwater operations. However, there are currently few accident risk assessment methods in the Arctic region. These risk assessment methods need to consider the characteristics of Arctic drilling operations before they are applied. Compared with onshore and offshore oil and gas activities, their characteristics are different. For example, low temperatures can make it difficult to deal with accidents. Heating measures are required before emergency operations are carried out. In addition, it is necessary to take into account the distance from the land, and the long distance may lead to a delay in controlling the risk. In the relevant technology, the research on the risk assessment methods of polar offshore blowouts and leaks is mostly focused on qualitative methods, and there is little research on quantitative risk assessment methods of polar offshore blowouts and leaks.

[0082] Specifically, this embodiment can take the blowout leakage accident of the polar offshore drilling platform as the top event, determine the corresponding intermediate events and bottom events based on the top event, and then construct the corresponding fault tree. According to the fault tree, the risk assessment of the polar offshore blowout leakage is performed to deal with the blowout leakage risk of the polar offshore drilling platform.

[0083] S102. Divide the polar drilling platform into a plurality of subsystems associated with top events.

[0084] Specifically, this embodiment can divide polar offshore drilling platforms into several subsystems according to their functions through data study and engineering research. When a subsystem fails, it may cause leakage or even blowout of the polar offshore drilling platform.

[0085] S103: Determine the fault events of the multiple subsystems as multiple intermediate events corresponding to the top event.

[0086] Specifically, in this embodiment, the fault event of each subsystem may be determined as an intermediate event that may cause the aforementioned top event to occur.

[0087] S104: Determine the logical relationship between the top event and multiple intermediate events.

[0088] Specifically, this embodiment can determine the logical relationship between the top event and different intermediate events. For example, when there are five intermediate events, the top event can have a certain logical relationship with two of the intermediate events, and can also have a certain logical relationship with the other three intermediate events.

[0089] S105: Determine the bottom event corresponding to each intermediate event.

[0090] Specifically, this embodiment can subdivide the factors that may cause failure of each subsystem based on the divided subsystems, and systematically identify risks through literature analysis and accident report analysis, determine the risk influencing factors that may cause subsystem failures, and use the determined risk influencing factors as the bottom event corresponding to the subsystem failure event, i.e., the intermediate event.

[0091] It should be noted that the main risks of polar drilling operations are low temperature, storms, long offshore distances, and equipment performance being greatly affected by the environment. Low temperature brings risks to daily and emergency operations. For example, a cold-proof structure needs to be designed to maintain a reasonable temperature during work. Once a leak occurs in this confined space structure, explosive gases will accumulate, increasing the risk of explosion during operation. In addition, low temperature will reduce the toughness of the steel structure of the offshore platform and reduce equipment availability. Therefore, in the emergency process of accidents in the Arctic region, it is necessary to use heaters to increase the temperature so that the emergency equipment can reach the expected capacity. Storms can increase the risks of Arctic operations. For example, storms can increase wave energy and cause damage to the platform. One of the accidents occurred in Norway, where the upper module of the semi-submersible platform was damaged by the storm. Another risk is the long distance in the Arctic region, and conventional resources are difficult to deliver to the platform. In addition, once an accident occurs, emergency disposal becomes difficult, both for personnel and equipment.

[0092] S106: Determine the logical relationship between each intermediate event and the corresponding bottom event.

[0093] Specifically, for each intermediate event, this embodiment can determine the logical relationship between the intermediate event and different bottom events. For example, when there are five bottom events corresponding to the intermediate event, the intermediate event can have a certain logical relationship with one of the bottom events and a certain logical relationship with the other four bottom events.

[0094] S107, constructing a fault tree model according to the top event, each intermediate event, each bottom event and the corresponding logical relationships.

[0095] It should be noted that, in this embodiment, the identified risk influencing factors can be used as the basic events of the fault tree, that is, the bottom events, the failure of the divided subsystems can be used as the intermediate events, and the polar offshore blowout leakage accident can be used as the top event to establish a polar offshore blowout leakage fault tree model.

[0096] Optionally, step S107 may include:

[0097] Create a top event node corresponding to the top event, create an intermediate event node corresponding to each intermediate event, and create a bottom event node corresponding to each bottom event;

[0098] Based on the logical relationship between the top event and multiple intermediate events, a corresponding logic gate is created between the top event node and the intermediate event node, and based on the logical relationship between the intermediate event and the bottom event, a corresponding logic gate is created between the intermediate event node and the bottom event node to construct a fault tree model;

[0099] The fault tree model includes a top event node, each intermediate event node, each bottom event node and corresponding logic gates.

[0100] Considering the process of Arctic offshore drilling and the above-mentioned risk factors, the most important event is the event that the system least wants to happen, that is, a blowout leakage accident. With reference to various literature related to blowout accidents, various factors that may cause blowout leakage accidents are listed in detail, and the logical relationship between each factor and the top event is organized. Starting from the top event, intermediate events and basic events are drawn to complete the construction of the fault tree model. In order to better illustrate the logical relationship between the top event, the intermediate event and the bottom event, as well as to illustrate the logic gates between the top event node, the intermediate event node and the bottom event node, this embodiment proposes and combines Figure 2 , Table 1 and Figure 3 For introduction. Figure 3 As shown, Figure 2 The middle rectangular box represents the top event node or the middle event node, and the circular box represents the basic event, i.e. the bottom event node. Figure 2 The logic symbols specifically include symbols corresponding to the logic AND gate and the logic OR gate, and the logic relationship includes the relationship of logic AND and logic OR. The letter codes in the rectangular box and the circular box represent the corresponding event names, as shown in Table 1.

[0101] Table 1 Event codes and failure probabilities of polar offshore well kick fault tree

[0102]

[0103]

[0104]

[0105] S108. Identify bottom events that have a critical impact on the blowout leakage accident according to the first Bayesian network corresponding to the fault tree model.

[0106] Optionally, step S108 may include:

[0107] Mapping the fault tree model to a first Bayesian network;

[0108] The bottom events with key impact on the blowout leakage accident are identified based on the first Bayesian network.

[0109] Optionally, the above mapping of the fault tree model into a first Bayesian network includes:

[0110] Each bottom event node in the fault tree model is used as a root node, each intermediate event node in the fault tree model is used as an intermediate node, and the top event node in the fault tree model is used as a leaf node;

[0111] Generate a conditional probability relationship between a leaf node and each intermediate node according to a logic gate between a top event node and each intermediate event node in the fault tree model; and generate a conditional probability relationship between each intermediate node and a corresponding root node according to a logic gate between each intermediate event node and a bottom event node in the fault tree model;

[0112] The root node, each intermediate node, leaf node and the corresponding conditional probability relationship are taken as a whole as the first Bayesian network.

[0113] It should be noted that in the process of mapping the fault tree model to the first Bayesian network in this embodiment, graphic mapping and numerical mapping can be performed. For graphic mapping, this embodiment can equate the bottom event node, the intermediate event node, and the top event node in the fault tree model to the root node, the intermediate node, and the leaf node in the Bayesian network, respectively. For numerical mapping, a conditional probability table is assigned to each root node, each intermediate node, and each leaf node to replace the logic gate.

[0114] like Figure 4As shown, this embodiment uses a conditional probability table of 0 and 1 to represent the logical AND gate and the logical OR gate. In the Bayesian network, the node from which the arrow starts is called the parent node, and the node to which the arrow points is called the child node. For the logical AND gate, the conditional probability of the child node is 1 only when the conditional probability of the parent node is all 1, otherwise it is 0. For the logical OR gate, the conditional probability of the child node is 0 only when the conditional probability of the parent node is all 0, otherwise it is 1.

[0115] like Figure 5 The first Bayesian network shown may include Figure 5 Except for the nodes with letter codes A, B, C, D, E and the corresponding arrows, and all parts except the Bayesian consequence nodes and the corresponding arrows, and. Among them, the Bayesian consequence node is Figure 5 The text in the middle box is the node of the consequence. It should be noted that the arrows represent the relationship between related nodes.

[0116] Optionally, the above-mentioned identifying the bottom events having a key impact on the blowout leakage accident according to the first Bayesian network includes:

[0117] Obtain the occurrence probability of each bottom event, and set the occurrence probability of the bottom event as the prior probability of the corresponding root node in the first Bayesian network;

[0118] Determine the prior probability of each intermediate node and leaf node based on the conditional probability relationship in the first Bayesian network and the prior probability of each root node;

[0119] Under the assumption that the top event must occur, the node state of the leaf node in the first Bayesian network is set accordingly, and based on the conditional probability relationship in the first Bayesian network, the prior probability of the leaf node and the prior probability of each intermediate node, the posterior probability of each intermediate node and each root node is determined in turn;

[0120] According to the posterior probability and prior probability of each root node, determine the probability change rate of each root node;

[0121] The probability change rate of each root node is compared with a preset threshold value to determine all target root nodes; wherein the probability change rate of the target root node is higher than the preset threshold value;

[0122] All target root nodes are identified as bottom events that have a critical impact on the blowout leakage accident.

[0123] It should be noted that, in this embodiment, the bottom events having a critical impact on the blowout leakage accident can be determined by performing sensitivity analysis in the first Bayesian network.

[0124] Among them, sensitivity analysis can be used to verify the probability parameters of the Bayesian network and identify highly sensitive nodes, that is, risk factors that have a greater impact on accident consequences, by studying the impact of small changes in the model's numerical parameters on the output parameters. Identifying highly sensitive nodes can allocate limited safety resources in a targeted manner.

[0125] Specifically, in this embodiment, the prior probability of the root node obtained from relevant literature, accident reports and expert knowledge can be first filled into the Bayesian network. The Bayesian formula is:

[0126]

[0127] in,

[0128] P(X|Y) is the probability of event X occurring under the condition that event Y occurs, that is, the posterior probability.

[0129] P(Y|X) is the probability of event Y occurring given event X.

[0130] P(X) is the prior probability of event X, that is, the probability without any information about Y.

[0131] P(Y) is the probability of event Y occurring, regardless of whether it occurs or not.

[0132] Specifically, in this embodiment, the prior probabilities of the intermediate nodes and the leaf node "T" can be obtained through the Bayesian network, and the probability that the state of the node "T" is "yes" (that is, the prior probability of the node "T") is 8.76E-03, that is, the probability of occurrence of a polar offshore well kick event in the embodiment is 8.76E-03.

[0133] Specifically, in this embodiment, the top event can be set to occur, that is, the probability of the node "T" state taking "yes" is set to "1", and the probabilities of the intermediate nodes and the root node also change accordingly, and the probability after the change is the posterior probability. The prior probability and the posterior probability of the root node are compared, and the change rate of each root node from the prior probability to the posterior probability is calculated and compared. The node with a high change rate is identified as a highly sensitive node.

[0134] like Figure 6 As shown, this embodiment can determine the relative change rate of the prior / posterior probability of each root node by identifying the highly sensitive nodes in the Bayesian network, and determine the root node with a larger relative change rate, so as to obtain the key factors affecting the occurrence of the blowout leakage accident: X20 gate blowout preventer failure, X21 annular blowout preventer failure, X27 diverter seal failure, X28 diverter ball valve start failure, X29 diverter pipeline rupture, X30 diverter control failure. Among them, the prior probability and posterior probability of each node are shown in Table 2.

[0135] Table 2 Event codes and failure probabilities of polar offshore well kick fault tree

[0136]

[0137]

[0138]

[0139] It can be understood that in order to effectively reduce the probability of blowout leakage accidents, this embodiment takes risk control measures for the most sensitive nodes, that is, model verification is carried out on bottom events that have a key impact on blowout leakage accidents, and on this basis, risk control measures are taken to effectively control the evolution and escalation of leakage risks of blowouts in polar waters.

[0140] This embodiment can take risk control measures for bottom events that have a critical impact on blowout and leakage accidents, and put forward risk control suggestions for offshore blowouts in the Arctic region:

[0141] (1) Preventive maintenance of equipment can reduce the probability of accidents. System inspection, equipment testing and component replacement should be carried out before equipment failure occurs in the system;

[0142] (2) Install sensors to monitor equipment status. Since the causes of failures are complex, sensors can monitor changes in equipment operating status to determine the degree of aging or damage and perform corresponding maintenance;

[0143] (3) Strengthen personnel safety training. Operators should be proficient in emergency response skills to avoid secondary risks of accidents caused by human factors; maintenance personnel need to reach a level of proficiency in the inspection process and maintenance operations to ensure that the equipment is in a high-availability state.

[0144] The blowout leakage risk management method for polar drilling platforms proposed in this embodiment can effectively manage the blowout leakage risk in the polar regions, enrich the blowout leakage risk management methods in the polar regions, and enhance the diversity of the blowout leakage risk management methods in the polar regions.

[0145] based on Figure 1 This embodiment proposes a second method for handling blowout and leakage risks of a polar drilling platform, which may further include:

[0146] The blowout accident is taken as the initial event, and an event tree model is constructed based on the initial event;

[0147] Convert the event tree model into a second Bayesian network;

[0148] Evaluating the safety of polar drilling platforms based on the second Bayesian network.

[0149] Optionally, the event tree model is constructed based on the initial event, including:

[0150] Determine the multi-level safety barriers used in polar drilling platforms to handle initial events; wherein the first level of the multi-level safety barriers is put into use when an initial event occurs, and the other levels of safety barriers are put into use when the previous level of safety barriers fails;

[0151] Determine the input consequences corresponding to each level of safety barriers;

[0152] Creating an initial event node corresponding to the initial event, creating a multi-level safety node corresponding to the multi-level safety barrier, and creating a consequence node corresponding to the input consequence;

[0153] Establish event evolution links between initial event nodes, multi-level safety nodes, and consequence nodes, and use them as event tree models;

[0154] The above-mentioned safety assessment of polar drilling platforms based on the second Bayesian network includes:

[0155] The effectiveness of each level of safety barriers is evaluated based on the second Bayesian network.

[0156] Specifically, in order to reduce the consequences of accidents, this embodiment can add a safety barrier to the polar offshore blowout event tree model, establish an event tree, and connect the top event of the fault tree model with the initial event of the event tree model as a hub to form a bow-tie model.

[0157] Specifically, this embodiment can take the polar offshore blowout leakage accident as the initial event. Catastrophic accidents are usually caused by the failure of safety barriers. In order to reduce the consequences of the accident, a safety barrier is added to the polar offshore blowout event tree model.

[0158] It should be noted that accidents are usually caused by the failure of safety barriers. In order to reduce the consequences of accidents, five safety barriers are added to the polar offshore blowout event tree model, namely: (1) Level 1 well control barrier: It starts from the natural barrier at the bottom of the well, directly contacts the bottom hole pressure, and prevents formation fluid from flowing into the wellbore; (2) Level 2 well control barrier: It is an independent backup means. In the event of failure of the level 1 well control barrier, it provides an alternative solution to ensure the integrity of the wellbore; (3) Blowout control barrier: This barrier can prevent the escalation of accidents and prevent blowouts; (4) Fire and explosion barrier: When a blowout occurs, the first thing to pay attention to is fire and explosion prevention. The key lies in the control of ignition sources. The main ignition sources of polar offshore drilling platforms are open flames, chemical reaction heat, electric sparks, etc.; (5) Emergency response barrier: When a blowout is out of control, emergency response measures need to be taken to repair and rebuild the wellhead blowout prevention system to prevent the escalation of the blowout. The safety barrier codes and corresponding failure probabilities are shown in Table 3.

[0159] Table 3 Failure probability of safety barriers

[0160]

[0161] Specifically, this embodiment can create an initial event node corresponding to the initial event, create a multi-level safety node corresponding to the multi-level safety barrier, and create a consequence node corresponding to the input consequence. Then, starting from the initial event node, drawing from left to right, a branch is established under each level of safety node to represent the event development path. Different results are ultimately obtained along different development paths, and an event evolution link is established, thereby establishing an event tree model that characterizes the evolution process of polar offshore blowout and leakage accidents.

[0162] It should be noted that the event tree is a method of inductive reasoning analysis, which is generally binary and is divided into only two states: "success" or "failure". The possible consequences of the accident can be inferred based on the order in which the accident occurred. Due to the fragility of the polar ecology, major blowout accidents may have an impact on the natural environment. At the same time, due to the weak infrastructure in the cold polar waters, once an accident occurs, it is impossible to provide support as quickly as ordinary drilling platforms, which may lead to more casualties and economic losses.

[0163] Specifically, the event tree model can be Figure 7 As shown, Figure 7 C1, C2, C3, C4, C5 and C6 in the table represent the input consequences of the safety barriers, as shown in Table 4.

[0164] Table 4 Input consequences and probabilities corresponding to safety barriers

[0165]

[0166]

[0167] Specifically, Figure 8 As shown, this embodiment can combine the constructed fault tree model with the event tree model to obtain a bow-tie model. The bow-tie model can then be used to describe the risk process. This embodiment can use the top event of the fault tree model as the initial event of the event tree model to establish a bow-tie model. Afterwards, this embodiment can map the bow-tie model to the Bayesian network through the structure and probability migration rules, establish a Bayesian network model, and perform relevant processing on the risk of blowout leakage accidents based on the established Bayesian network model, such as determining the bottom events that have a key impact on the blowout leakage accident as described above.

[0168] From the event tree model of well blowout escalation in the Arctic, when the emergency response barrier fails, more serious pollution will occur, while the failure of fire and explosion barriers may lead to loss of personnel and damage to equipment. Combining the fault tree model and the event tree model, a bow-tie model of Arctic offshore blowout accidents is constructed to show the process of the potential factors leading to blowouts in Arctic oil and gas activities developing into the consequences of blowout accidents.

[0169] Optionally, the event tree model is converted into a second Bayesian network, including:

[0170] According to the initial event node in the event tree model, a corresponding Bayesian initial event node is created, and the node state of the Bayesian initial event node is initialized; according to the multi-level safety node in the event tree model, a corresponding multi-level Bayesian safety node is created, and the node state of each Bayesian safety node is initialized;

[0171] Creating a corresponding Bayesian consequence node based on the consequence node, and initializing the node state of the Bayesian consequence node; wherein the node state of the Bayesian consequence node is used to identify each input consequence;

[0172] According to the event evolution link in the event tree model, the conditional probability relationship between the node state of the Bayesian initial event node, the node state of each level of the Bayesian safety node and the node state of the Bayesian consequence node is generated;

[0173] The conditional probability relationship among the Bayesian initial event node, each level of Bayesian safety node, Bayesian consequence node and node state is taken as the second Bayesian network.

[0174] The node state of the Bayesian initial event node is used to identify whether the initial event occurs, and the node state of each level of Bayesian safety node is used to identify whether the corresponding safety barrier is valid or invalid.

[0175] Specifically, a Bayesian safety node can represent a safety barrier, such as a node with letter codes A, B, C, D, E, and T. The node status of a Bayesian safety node can be two kinds, namely, valid and invalid. Valid means that the safety barrier corresponding to the Bayesian safety node successfully prevents the continued evolution of the blowout leakage accident, and invalid means that the safety barrier corresponding to the Bayesian safety node fails and fails to prevent the continued evolution of the blowout leakage accident.

[0176] Specifically, the Bayesian consequence node (i.e. Figure 5 The number of states of the Bayesian consequence node (shown in ) is the same as the number of event tree consequences, namely C1, C2, C3, C4, C5 and C6.

[0177] It should be noted that if Fig. 9As shown in the figure, when the probability of the Bayesian safety node state taking yes or no changes, the probability distribution of the consequence nodes C1 to C6 will also change accordingly. Among them, yes means that the node state of the Bayesian safety node is valid, and no means that the node state of the Bayesian safety node is invalid, which fails to prevent the continued evolution of the blowout leakage accident.

[0178] Optionally, the effectiveness of each safety barrier is evaluated according to the second Bayesian network, including:

[0179] Obtain the failure probability of each level of safety barrier, and use the failure probability of each level of safety barrier as the prior probability of the corresponding Bayesian safety node;

[0180] Under the assumption that the initial event is bound to occur, the node state of the Bayesian initial event node in the second Bayesian network is set accordingly. For any Bayesian safety node, when the node state of the Bayesian safety node is set to failure, the first occurrence probability of the corresponding input consequence is determined according to the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node. When the node state of the Bayesian safety node is set to success, the second occurrence probability of the corresponding input consequence is determined according to the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node. The effectiveness of the safety barrier is evaluated according to the difference between the first occurrence probability and the second occurrence probability.

[0181] Specifically, after constructing the second Bayesian network, this embodiment can use the failure probability of the safety barrier as the prior probability of the Bayesian safety node, and assign a conditional probability table to the Bayesian consequence node. The value of the data in the conditional probability table is "0" or "1", that is, when the Bayesian initial event node and the Bayesian safety node take different node states, different results are obtained, and the final result is "1", and the rest are "0". For example, when the initial event occurs and the first-level well control barrier is successful, that is, when the node "T" state is "yes" and the node "A" state is "yes", the result is "C1", then fill in "1" in "C1" in the conditional probability table, and fill in "0" for the rest of the results "C2-C6".

[0182] Optionally, the bow-tie model can also be mapped to a corresponding Bayesian network in this embodiment. After establishing the equivalent Bayesian network of the fault tree and the event tree, the embodiment can connect them to each other through the same top event node and the Bayesian initial event node as the pivot node to obtain the following: Figure 5 The Bayesian network shown.

[0183] In this embodiment, the Bayesian initial event node is connected to the Bayesian consequence node (such as Figure 5After the "T" shown in the figure is connected to the "Consequence" node by an arrow), considering the impact of the top event not occurring (that is, when the node "T" state is "no") on the Bayesian consequence node, another state (for example, a safe state) can be added to the Bayesian consequence node, that is, a "Safe" state is added to the original "C1-C6" state of the consequence node.

[0184] In this embodiment, since the consequence "C1" is already in a safe state, the "Safe" state is not added to the consequence node. Instead, the probability of the node "T" state taking "no" is incorporated into the "C1" state, that is, when the node "T" state is "no", "1" is filled in "C1" in the conditional probability table, and "0" is filled in the remaining results "C2-C6".

[0185] Specifically, this embodiment can evaluate the effectiveness of the safety barrier by assuming that the initial event occurs, and compare the changes in the consequence probabilities when the safety barriers take effect respectively as shown in Table 5, and then the model verification can be performed.

[0186] Table 5 The impact of safety barrier success on consequence probability

[0187]

[0188] From the results, it can be seen that increasing safety barriers can reduce the probability of serious accidents, effectively inhibit the further development of accidents, and reduce accident losses. Therefore, the risk management of polar offshore drilling platforms should focus on and ensure the availability of these five safety barriers.

[0189] This embodiment can more comprehensively and quantitatively evaluate the risk of blowout and leakage accidents on polar offshore drilling platforms, obtain key risk influencing factors and safety barriers, and then propose risk control measures to reduce the risk of blowout and leakage accidents on polar offshore platforms.

[0190] The blowout risk management method for polar drilling platforms proposed in this embodiment can identify the effectiveness of safety barriers based on the event tree model and the second Bayesian network, enhance fault monitoring and maintenance of effective safety barriers, and thus enhance the management and control of polar blowout risks.

[0191] like Fig.10 As shown, this embodiment proposes a third method for handling blowout leakage risk of polar drilling platforms, which can be applied to a corresponding blowout leakage risk handling device of a polar drilling platform, and the device can include a fault tree construction module, an event tree construction module, a Bayesian network module, and a risk assessment module. Specifically, the method can include the following steps:

[0192] S1. The fault tree construction module identifies risk influencing factors, derives logical relationships, and establishes a fault tree, i.e., a fault tree model.

[0193] S2, the event tree building module adds a safety barrier, builds an event tree model, and connects the fault tree model and the event tree model to form a bow-tie model.

[0194] S3, the Bayesian network module maps the bow-tie model to the Bayesian network through structural and probability migration rules.

[0195] S4. The risk assessment module identifies key risk influencing factors, conducts model verification, and proposes risk control measures.

[0196] The blowout leakage risk management method for polar drilling platforms proposed in this embodiment can perform blowout leakage risk management through fault tree models and event tree models, enrich the blowout leakage risk management methods in polar regions, and enhance the blowout leakage risk management and control in polar regions.

[0197] like Fig.11 As shown, this embodiment provides a blowout leakage risk treatment device for a polar drilling platform, which may include:

[0198] As a unit, it is used to take the blowout and leakage accident of the polar drilling platform as the top event;

[0199] A partitioning unit, for partitioning the polar drilling platform into a plurality of subsystems associated with the top event;

[0200] A first determining unit, configured to determine the fault events of the multiple subsystems as multiple intermediate events corresponding to the top event;

[0201] A second determining unit, used to determine the logical relationship between the top event and the plurality of intermediate events;

[0202] A third determining unit, used to determine a bottom event corresponding to each intermediate event;

[0203] A fourth determining unit, used to determine the logical relationship between each intermediate event and the corresponding bottom event;

[0204] A first construction unit is used to construct a fault tree model according to the top event, each intermediate event, each bottom event and the corresponding logical relationship;

[0205] The identification unit is used to identify the bottom event that has a key impact on the blowout leakage accident according to the first Bayesian network corresponding to the fault tree model.

[0206] It should be noted that the processing processes of the serving unit, the dividing unit, the first determining unit, the second determining unit, the third determining unit, the fourth determining unit, the first constructing unit and the identifying unit and the beneficial effects thereof can be respectively referred to in Figure 1 Steps S101 to S105 in the above are not described in detail.

[0207] Optionally, the first construction unit is further used to: create a top event node corresponding to the top event, create an intermediate event node corresponding to each intermediate event, and create a bottom event node corresponding to each bottom event; based on the logical relationship between the top event and multiple intermediate events, create corresponding logic gates between the top event node and the intermediate event nodes, and based on the logical relationship between the intermediate event and the bottom event, create corresponding logic gates between the intermediate event node and the bottom event node to construct a fault tree model; wherein the fault tree model includes a top event node, each intermediate event node, each bottom event node and the corresponding logic gates.

[0208] Optionally, the identification unit is further used to: map the fault tree model into a first Bayesian network; and identify bottom events that have a critical impact on the blowout leakage accident based on the first Bayesian network.

[0209] Optionally, the identification unit is also used to: take each bottom event node in the fault tree model as a root node, take each intermediate event node in the fault tree model as an intermediate node, and take the top event node in the fault tree model as a leaf node; generate a conditional probability relationship between a leaf node and each intermediate node according to a logic gate between the top event node and each intermediate event node in the fault tree model; and, generate a conditional probability relationship between each intermediate node and the corresponding root node according to a logic gate between each intermediate event node and the bottom event node in the fault tree model; and take the root node, each intermediate node, the leaf node and the corresponding conditional probability relationship as a whole as a first Bayesian network.

[0210] Optionally, the identification unit is also used to:

[0211] Obtain the occurrence probability of each bottom event, and set the occurrence probability of the bottom event as the prior probability of the corresponding root node in the first Bayesian network; determine the prior probability of each intermediate node and leaf node based on the conditional probability relationship in the first Bayesian network and the prior probability of each root node; under the assumption that the top event must occur, set the node state of the leaf node in the first Bayesian network accordingly, and determine the posterior probability of each intermediate node and each root node in turn based on the conditional probability relationship in the first Bayesian network, the prior probability of the leaf node and the prior probability of each intermediate node; determine the probability change rate of each root node based on the posterior probability and the prior probability of each root node; compare the probability change rate of each root node with a preset threshold value to determine all target root nodes; wherein the probability change rate of the target root node is higher than the preset threshold; determine all target root nodes as bottom events that have a key impact on the blowout leakage accident.

[0212] Optionally, the above device further comprises:

[0213] The second construction unit is used to take the blowout leakage accident as the initial event and construct an event tree model according to the initial event;

[0214] An evaluation unit is used to convert the event tree model into a second Bayesian network; and evaluate the safety of the polar drilling platform based on the second Bayesian network.

[0215] Optionally, the second building block is further used for:

[0216] Determine the multi-level safety barriers for handling initial events in the polar drilling platform; wherein the first level of the multi-level safety barriers is put into use when the initial event occurs, and the other levels of safety barriers are put into use when the previous level of safety barriers fails; determine the input consequences corresponding to each level of safety barriers; create an initial event node corresponding to the initial event, create a multi-level safety node corresponding to the multi-level safety barriers, and create a consequence node corresponding to the input consequences; establish an event evolution link between the initial event node, the multi-level safety node and the consequence node, and use it as an event tree model;

[0217] Evaluation unit, also used for:

[0218] The effectiveness of each level of safety barriers is evaluated based on the second Bayesian network.

[0219] Optionally, the evaluation unit is also used to:

[0220] According to the initial event node in the event tree model, a corresponding Bayesian initial event node is created, and the node state of the Bayesian initial event node is initialized; according to the multi-level safety node in the event tree model, a corresponding multi-level Bayesian safety node is created, and the node state of each Bayesian safety node is initialized; based on the consequence node, a corresponding Bayesian consequence node is created, and the node state of the Bayesian consequence node is initialized; wherein the node state of the Bayesian consequence node is used to identify each input consequence; according to the event evolution link in the event tree model, a conditional probability relationship between the node state of the Bayesian initial event node, the node state of each level of the Bayesian safety node and the node state of the Bayesian consequence node is generated; the conditional probability relationship between the Bayesian initial event node, each level of the Bayesian safety node, the Bayesian consequence node and the node state is taken as a second Bayesian network as a whole.

[0221] Optionally, the node state of the Bayesian initial event node is used to identify whether the initial event occurs, and the node state of each level of the Bayesian safety node is used to identify whether the corresponding safety barrier is valid or invalid.

[0222] Evaluation unit, also used for:

[0223] Obtain the failure probability of each level of safety barrier, and use the failure probability of each level of safety barrier as the prior probability of the corresponding Bayesian safety node; assuming that the initial event must occur, set the node state of the Bayesian initial event node in the second Bayesian network accordingly;

[0224] For any Bayesian safety node, when the node state of the Bayesian safety node is set to failure, the first occurrence probability of the corresponding input consequence is determined according to the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node. When the node state of the Bayesian safety node is set to success, the second occurrence probability of the corresponding input consequence is determined according to the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node. The effectiveness of the safety barrier is evaluated according to the difference between the first occurrence probability and the second occurrence probability.

[0225] The blowout leakage risk management device for the polar drilling platform proposed in this embodiment can effectively manage the blowout leakage risk in the polar regions, enrich the blowout leakage risk management methods in the polar regions, and enhance the diversity of the blowout leakage risk management methods in the polar regions.

[0226] The blowout risk treatment device for the polar drilling platform in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions. The embodiment of the present invention also provides a computer device having the above Fig.11 The blowout leakage risk treatment device of the polar drilling platform is shown.

[0227] See also Fig.11 , a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.11 A processor 10 is taken as an example.

[0228] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0229] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0230] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function. The data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0231] The memory 20 may include a volatile memory, such as a random access memory. The memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive. The memory 20 may also include a combination of the above-mentioned types of memory.

[0232] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0233] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0234] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for handling blowout and leakage risks of a polar drilling platform, characterized in that: include: Taking a blowout leakage accident of a polar drilling platform as a top event, and dividing the polar drilling platform into a plurality of subsystems associated with the top event; Determine the fault events of the multiple subsystems as multiple intermediate events corresponding to the top event, and determine the logical relationship between the top event and the multiple intermediate events; Determine a base event corresponding to each of the intermediate events, and determine a logical relationship between each of the intermediate events and the corresponding base event; Constructing a fault tree model according to the top event, each of the intermediate events, each of the bottom events and corresponding logical relationships; According to the first Bayesian network corresponding to the fault tree model, the bottom event having a critical impact on the blowout leakage accident is identified.

2. The method according to claim 1, characterized in that The constructing of a fault tree model according to the top event, each of the intermediate events, each of the bottom events and the corresponding logical relationships includes: Creating a top event node corresponding to the top event, creating an intermediate event node corresponding to each intermediate event, and creating a bottom event node corresponding to each bottom event; Based on the logical relationship between the top event and the plurality of intermediate events, a corresponding logic gate is created between the top event node and the intermediate event node, and based on the logical relationship between the intermediate event and the bottom event, a corresponding logic gate is created between the intermediate event node and the bottom event node, so as to construct the fault tree model; The fault tree model includes the top event node, each of the intermediate event nodes, each of the bottom event nodes and corresponding logic gates.

3. The method according to claim 2, characterized in that The identifying the bottom event having a critical impact on the blowout leakage accident according to the first Bayesian network corresponding to the fault tree model includes: Mapping the fault tree model into the first Bayesian network; The bottom event having a critical impact on the blowout leakage accident is identified according to the first Bayesian network.

4. The method according to claim 3, characterized in that Mapping the fault tree model to the first Bayesian network includes: Taking each of the bottom event nodes in the fault tree model as a root node, taking each of the intermediate event nodes in the fault tree model as an intermediate node, and taking the top event node in the fault tree model as a leaf node; Generate a conditional probability relationship between the leaf node and each of the intermediate nodes according to the logic gate between the top event node and each of the intermediate event nodes in the fault tree model; and generate a conditional probability relationship between each of the intermediate nodes and the corresponding root node according to the logic gate between each of the intermediate event nodes and the bottom event node in the fault tree model; The root node, each of the intermediate nodes, the leaf nodes and the corresponding conditional probability relationships are taken as a whole as the first Bayesian network.

5. The method according to claim 4, characterized in that The identifying the bottom event having a critical impact on the blowout leakage accident according to the first Bayesian network includes: Obtaining the occurrence probability of each of the bottom events, and setting the occurrence probability of the bottom event as the prior probability corresponding to the root node in the first Bayesian network; Determine the prior probability of each of the intermediate nodes and the leaf nodes based on the conditional probability relationship in the first Bayesian network and the prior probability of each of the root nodes; Under the assumption that the top event must occur, the node state of the leaf node in the first Bayesian network is set accordingly, and based on the conditional probability relationship in the first Bayesian network, the prior probability of the leaf node and the prior probability of each of the intermediate nodes, the posterior probability of each of the intermediate nodes and each of the root nodes is determined in sequence; Determine the probability change rate of each root node according to the posterior probability and the prior probability of each root node; Comparing the probability change rate of each of the root nodes with a preset threshold value respectively to determine all target root nodes; wherein the probability change rate of the target root node is higher than the preset threshold value; All target root nodes are determined as the bottom events having a critical impact on the blowout leakage accident.

6. The method according to claim 1, characterized in that The method further comprises: Taking the blowout leakage accident as an initial event, and constructing an event tree model according to the initial event; Converting the event tree model into a second Bayesian network; The safety of the polar drilling platform is evaluated based on the second Bayesian network.

7. The method according to claim 6, characterized in that The step of constructing an event tree model according to the initial event includes: Determine a multi-level safety barrier in the polar drilling platform for handling the initial event; wherein the first level of the safety barrier in the multi-level safety barrier is put into use when the initial event occurs, and the other levels of the safety barrier are put into use when the previous level of the safety barrier fails; Determine the input consequences corresponding to each level of the safety barrier; Creating an initial event node corresponding to the initial event, creating a multi-level safety node corresponding to the multi-level safety barrier, and creating a consequence node corresponding to the input consequence; Establishing an event evolution link between the initial event node, the multi-level safety node and the consequence node as an event tree model; The evaluating the safety of the polar drilling platform based on the second Bayesian network includes: The effectiveness of each level of the safety barrier is evaluated according to the second Bayesian network.

8. The method according to claim 7, characterized in that The converting the event tree model into a second Bayesian network comprises: Creating a corresponding Bayesian initial event node according to the initial event node in the event tree model, and initializing the node state of the Bayesian initial event node; creating a corresponding multi-level Bayesian safety node according to the multi-level safety node in the event tree model, and initializing the node state of each Bayesian safety node; Creating a corresponding Bayesian consequence node based on the consequence node, and initializing the node state of the Bayesian consequence node; wherein the node state of the Bayesian consequence node is used to identify each of the input consequences; According to the event evolution link in the event tree model, a conditional probability relationship between the node state of the Bayesian initial event node, the node state of each level of the Bayesian safety node and the node state of the Bayesian consequence node is generated; The conditional probability relationship among the Bayesian initial event node, the Bayesian safety node at each level, the Bayesian consequence node and the node state is taken as the second Bayesian network.

9. The method according to claim 8, characterized in that The node state of the Bayesian initial event node is used to identify whether the initial event occurs, and the node state of each level of the Bayesian safety node is used to identify whether the corresponding safety barrier is valid or invalid; The evaluating the effectiveness of each of the safety barriers according to the second Bayesian network comprises: Obtaining the failure probability of the safety barrier at each level, and using the failure probability of the safety barrier at each level as the prior probability of the corresponding Bayesian safety node; Under the assumption that the initial event must occur, correspondingly setting the node state of the Bayesian initial event node in the second Bayesian network; For any of the Bayesian safety nodes, when the node state of the Bayesian safety node is set to failure, the first occurrence probability corresponding to the investment consequence is determined based on the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node; when the node state of the Bayesian safety node is set to success, the second occurrence probability corresponding to the investment consequence is determined based on the conditional probability relationship in the second Bayesian network and the failure probability of the Bayesian safety node; the effectiveness of the safety barrier is evaluated based on the difference between the first occurrence probability and the second occurrence probability.

10. A blowout leakage risk treatment device for a polar drilling platform, characterized in that: include: As a unit, it is used to take the blowout and leakage accident of the polar drilling platform as the top event; a dividing unit, for dividing the polar drilling platform into a plurality of subsystems associated with the top event; A first determining unit, configured to determine the fault events of the multiple subsystems as multiple intermediate events corresponding to the top event; A second determining unit, configured to determine a logical relationship between the top event and the plurality of intermediate events; A third determining unit, configured to determine a bottom event corresponding to each of the intermediate events; A fourth determining unit, used to determine the logical relationship between each of the intermediate events and the corresponding bottom event; A first construction unit is used to construct a fault tree model according to the top event, each of the intermediate events, each of the bottom events and corresponding logical relationships; An identification unit is used to identify the bottom event that has a critical impact on the blowout leakage accident according to the first Bayesian network corresponding to the fault tree model.

Images