Overflow analysis method and device, electronic equipment and storage medium
The method improves the accuracy of drilling fluid overflow analysis by integrating Bayesian network models and fault trees to assess dynamic interactions between hardware and non-hardware events, addressing the limitations of current static analysis methods.
Patent Information
- Application Number
- CN202411539019.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-03-14
AI Technical Summary
Current methods for analyzing drilling fluid overflow incidents in the petroleum industry lack accuracy, primarily focusing on static analysis of individual risk factors rather than dynamic interactions between hardware and non-hardware events.
The proposed method involves obtaining key event information, determining response failure cause chains, fault trees, and Bayesian network models to calculate the probabilities of non-hardware and hardware events, ultimately assessing the likelihood of overflow incidents through integrated analysis.
This approach enhances the accuracy of overflow analysis by considering dynamic interactions and probabilities, providing a comprehensive evaluation of incident risks.
Smart Images
Figure CN119624096A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of drilling safety, and in particular to an overflow analysis method, device, electronic equipment and storage medium. Background Art
[0002] With the continuous growth of global energy demand and the continuous advancement of mining technology, the mining industry has developed rapidly and the scale of mining has gradually expanded. However, the mining process is also accompanied by various potential risks, such as geological risks, technical risks, environmental risks, and man-made accident risks, which may lead to accidents such as wellhead overflow. Therefore, it is of great significance to analyze the occurrence of wellhead overflow.
[0003] At present, the existing wellhead overflow emergency response risk analysis and assessment are mainly carried out through methods such as fault tree and fuzzy comprehensive evaluation, which focus more on the static analysis of single fault points or risk factors, and mainly focus on identifying and evaluating independent and relatively fixed risk factors.
[0004] However, existing overflow analysis methods suffer from insufficient accuracy. Summary of the invention
[0005] The embodiments of the present application provide an overflow analysis method, an apparatus, an electronic device and a storage medium to solve the problem of insufficient accuracy of existing overflow analysis methods.
[0006] In a first aspect, an embodiment of the present application provides an overflow analysis method, comprising:
[0007] Obtain overflow key event information, which includes hardware key event information and non-hardware key event information;
[0008] According to the overflow key event information, determine the cause chain, fault tree and Bayesian network model of the response failure accident;
[0009] Determine the probability of occurrence of non-hardware critical events based on the Bayesian network model;
[0010] Determine the probability of occurrence of hardware critical events based on the fault tree and the probability of occurrence of non-hardware critical events;
[0011] Determine the probability of response failure based on the cause chain of response failure accidents, the probability of occurrence of non-hardware critical events, and the probability of occurrence of hardware critical events;
[0012] The overflow analysis results are determined based on the causal chain of the response failure accident and the probability of response failure.
[0013] In a possible implementation, based on the overflow key event information, determining the response failure accident cause chain, fault tree and Bayesian network model includes:
[0014] Determine the overflow emergency response sequence diagram based on the overflow key event information;
[0015] According to the overflow emergency response sequence diagram, determine the cause chain of response failure accidents;
[0016] Determine the fault tree based on overflow key event information, intermediate event information and basic event information;
[0017] The Bayesian network model is determined based on non-hardware key event information, basic influencing factor information and extended node information.
[0018] In a possible implementation, determining the probability of occurrence of a non-hardware critical event according to a Bayesian network model includes:
[0019] Acquire prior probability information of basic influencing factor information, conditional probability information of extended node information, and conditional probability information of non-hardware key event information;
[0020] Determine the posterior probability information of each node in the Bayesian network model according to the prior probability information of the basic influencing factor information, the conditional probability information of the extended node information and the conditional probability information of the non-hardware key event information;
[0021] According to the posterior probability information of each node in the Bayesian network model, the occurrence probability of non-hardware critical events is determined.
[0022] In a possible implementation, after determining the posterior probability information of each node in the Bayesian network model according to the prior probability information of the basic influencing factor information, the conditional probability information of the extended node information, and the conditional probability information of the non-hardware key event information, the method further includes:
[0023] Adjust the prior probability information of the basic influencing factor information to obtain the posterior probability information of each node target;
[0024] Determine the change rate of the posterior probability of each node according to the posterior probability information of the target of each node and the posterior probability information of each node;
[0025] According to the change rate of the posterior probability of each node, the sensitivity analysis results of the basic influencing factors are determined.
[0026] In a possible implementation, determining the probability of occurrence of a hardware critical event based on the fault tree and the probability of occurrence of a non-hardware critical event includes:
[0027] Determine the probability of occurrence of intermediate events based on the probability of occurrence of non-hardware critical events and the probability of occurrence of basic events;
[0028] According to the probability of occurrence of intermediate events, the probability of occurrence of hardware key events is determined.
[0029] In a possible implementation manner, after determining the probability of occurrence of a hardware critical event according to the fault tree and the probability of occurrence of a non-hardware critical event, the method further includes:
[0030] Determine the probability of occurrence of critical events based on the probability of occurrence of non-hardware critical events and the probability of occurrence of hardware critical events;
[0031] Determine the importance of key events based on overflow probability and the probability of occurrence of key events;
[0032] According to the importance of key events, determine the results of event importance analysis.
[0033] In a possible implementation, the importance of the key event is determined according to the overflow probability and the occurrence probability of the key event, including:
[0034] According to the overflow probability and the occurrence probability of the key event, the first conditional probability and the second conditional probability are determined. The first conditional probability is the probability of overflow under the condition that the key event occurs, and the second conditional probability is the probability of the key event and overflow occurring together.
[0035] The first conditional probability and the overflow probability are divided to obtain the first importance;
[0036] The second conditional probability and the overflow probability are divided to obtain the second importance;
[0037] The importance of the key event is determined based on the first importance and the second importance.
[0038] In a second aspect, an embodiment of the present application provides an overflow analysis device, comprising:
[0039] An acquisition module is used to acquire overflow key event information, where the overflow key event information includes hardware key event information and non-hardware key event information;
[0040] The first determination module is used to determine the response failure accident cause chain, fault tree and Bayesian network model according to the overflow key event information;
[0041] A second determination module is used to determine the probability of occurrence of non-hardware critical events according to a Bayesian network model;
[0042] A third determination module is used to determine the probability of occurrence of a hardware critical event based on the fault tree and the probability of occurrence of a non-hardware critical event;
[0043] A fourth determination module is used to determine the probability of response failure according to the cause chain of the response failure accident, the probability of occurrence of non-hardware key events and the probability of occurrence of hardware key events;
[0044] The fifth determination module is used to determine the overflow analysis result according to the cause chain of the response failure accident and the probability of response failure.
[0045] In a third aspect, an embodiment of the present application provides an overflow analysis device, including: a memory, a processor;
[0046] Memory stores computer-executable instructions;
[0047] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.
[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.
[0049] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.
[0050] The overflow analysis method, device, electronic device and storage medium provided in the embodiments of the present application obtain overflow key event information, which includes hardware key event information and non-hardware key event information; determine the response failure accident causal chain, fault tree and Bayesian network model according to the overflow key event information; determine the probability of occurrence of non-hardware key events according to the Bayesian network model; determine the probability of occurrence of hardware key events according to the fault tree and the probability of occurrence of non-hardware key events; determine the probability of response failure according to the response failure accident causal chain, the probability of occurrence of non-hardware key events and the probability of occurrence of hardware key events; determine the means of overflow analysis results according to the response failure accident causal chain and the probability of response failure, obtain the probability of occurrence of non-hardware key events in the fault tree from the Bayesian network model, and then obtain the probability of occurrence of hardware key events in the fault tree, further bring the probability of occurrence of all overflow key events in the sequence diagram into the response failure accident causal chain to obtain the probability of response failure, and analyze the overflow according to the response failure accident causal chain and the probability of response failure, so as to achieve the effect of improving the accuracy of the overflow analysis results. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0052] Figure 1 A schematic diagram of the flow chart of the overflow analysis method provided in the embodiment of the present application;
[0053] Figure 2 An overflow emergency response sequence diagram provided for an embodiment of the present application;
[0054] Figure 3 A fault tree diagram provided for an embodiment of the present application;
[0055] Figure 4 A schematic diagram of a Bayesian network model provided for an embodiment of the present application;
[0056] Figure 5 A schematic flow chart of another overflow analysis method provided in an embodiment of the present application;
[0057] Figure 6 A schematic diagram of the structure of the overflow analysis device provided in an embodiment of the present application;
[0058] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0059] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0060] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0061] First, the terms involved in this application are explained:
[0062] Bayesian network model: refers to a probabilistic graphical model consisting of nodes representing variables and directed edges connecting these nodes, which can handle data with uncertainty and complex dependencies;
[0063] Fault tree: refers to a logical tree diagram that uses event symbols, logic gate symbols, and transfer symbols to represent the causes of accidents or fault events and their logical relationships.
[0064] In the existing technology, the risk analysis and assessment of wellhead overflow emergency response are mainly carried out through methods such as fault tree and fuzzy comprehensive evaluation. There are technical problems that the corresponding processes of the well control system are not focused on and the impact of the interaction of multiple factors such as people and machines in the response process is not comprehensively considered.
[0065] The overflow analysis method, device, electronic device and storage medium provided in the present application obtain the probability of occurrence of non-hardware critical events in the fault tree from the Bayesian network model, and then obtain the probability of occurrence of hardware critical events in the fault tree, and further bring the probability of occurrence of all overflow critical events in the sequence diagram into the response failure accident causal chain to obtain the probability of response failure. The technical means of analyzing overflow according to the response failure accident causal chain and the probability of response failure solves the technical problem of insufficient accuracy of existing overflow analysis methods.
[0066] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0067] Figure 1 The flow chart of the overflow analysis method provided in the embodiment of the present application is shown in FIG. The execution subject of the method can be a server or other servers, and this embodiment is not particularly limited here. Figure 1 As shown, the method may include:
[0068] S101. Obtain overflow key event information, where the overflow key event information includes hardware key event information and non-hardware key event information.
[0069] Among them, overflow key event information may refer to information on a series of important operation nodes closely related to the overflow phenomenon during drilling or other related operations, hardware key event information may refer to information on key events mainly related to hardware facilities, and non-hardware key event information may refer to information on key events mainly related to the environment or human factors. For example, P1 to P10 in Table 1 are overflow key events, P6, P8 to P10 are non-hardware key events, and the others are hardware key events.
[0070]
[0071] Table 1: Key overflow events and descriptions
[0072] S102. Determine the response failure accident cause chain, fault tree and Bayesian network model based on the overflow key event information.
[0073] The response failure accident causal chain may refer to a series of links of events or factors that cause the wellhead intelligent control system to be unable to effectively respond to and control the wellhead overflow.
[0074] Among them, in the embodiment of the present application, according to the overflow key event information, the response failure accident cause chain, fault tree and Bayesian network model are determined, and the method may include:
[0075] Determine the overflow emergency response sequence diagram based on the overflow key event information;
[0076] According to the overflow emergency response sequence diagram, determine the cause chain of response failure accidents;
[0077] Determine the fault tree based on overflow key event information, intermediate event information and basic event information;
[0078] The Bayesian network model is determined based on non-hardware key event information, basic influencing factor information and extended node information.
[0079] The overflow emergency response sequence diagram may refer to a process sequence diagram used to describe how to respond to each overflow key event according to predetermined procedures and steps when overflow occurs during drilling operations, such as Figure 2 , IE can refer to the initiation of overflow, P1 to P10 can refer to key overflow events, END1 can refer to safety, the three major safety valves are closed in time, and END2 can refer to danger, the three major safety valves are not closed in time.
[0080] The response failure accident causal chain may refer to the response failure chain with the result END2 obtained according to the process in the overflow emergency response sequence diagram, such as Table 2.
[0081]
[0082] Table 2: Cause chain of response failure incidents
[0083] A fault tree can be composed of a top node, an intermediate node, and a basic node. The top node is the ultimate target in the fault tree analysis. For example, the event information in the top node is that the right wing safety valve is not closed in time. The intermediate node is a logical node located between the top node and the basic node. It is the cause of the top node and the result caused by the basic node. For example, the information in the intermediate node is various faults or abnormal conditions related to overflow, such as heating of the oil tank, failure of the oil pump to discharge oil or insufficient discharge of oil, etc. The basic node is the smallest unit that constitutes the fault tree, which is usually the most basic component failure or external event in the system. For example, the information in the basic node is the specific cause of the overflow fault such as insufficient oil, damaged cooler, wrong rotation direction of the motor, etc. In the embodiment of the present application, Figure 3, the top node T1 can be determined by hardware key event information, the intermediate nodes M1 to M7 can be determined by intermediate event information, and the basic nodes X1 to X11 can be determined by basic event information and non-hardware key event information.
[0084] The Bayesian network model can be composed of a root node and leaf nodes. The root node is a node without a parent node in the Bayesian network model and is the starting node in the Bayesian network model. The leaf node is other nodes in the Bayesian network model except the root node. In the embodiment of the present application, Figure 4 The root node can be determined by the basic influencing factor information, which can refer to the information of the core influencing factors of the wellhead overflow phenomenon, such as equipment status, environmental conditions and communication reliability. The leaf node can be determined by non-hardware key event information and extended node information, and the extended node information can refer to the information of other influencing factors of the wellhead overflow phenomenon.
[0085] S103. Determine the probability of occurrence of non-hardware critical events according to the Bayesian network model.
[0086] The occurrence probability of a non-hardware critical event may refer to a numerical measurement of the likelihood of a critical event occurring under the influence of environmental or human factors.
[0087] Among them, in the embodiment of the present application, according to the Bayesian network model, the probability of occurrence of non-hardware critical events is determined, and the method may include:
[0088] Acquire prior probability information of basic influencing factor information, conditional probability information of extended node information, and conditional probability information of non-hardware key event information;
[0089] Determine the posterior probability information of each node in the Bayesian network model according to the prior probability information of the basic influencing factor information, the conditional probability information of the extended node information and the conditional probability information of the non-hardware key event information;
[0090] According to the posterior probability information of each node in the Bayesian network model, the occurrence probability of non-hardware critical events is determined.
[0091] Among them, the prior probability information of basic influencing factor information can refer to the probability estimates of these basic influencing factors obtained based on past experience, domain knowledge or analysis before observing specific samples or events. The conditional probability information of extended node information and the conditional probability information of non-hardware critical event information can refer to the probability of a node taking a specific value or an event occurring given the root node state or preconditions.
[0092] The method for obtaining the prior probability information of the basic influencing factor information is to obtain the probability score of the expert for the root node, and obtain the corresponding prior probability after fusing it through the evidence theory method, such as Table 3.
[0093]
[0094] Table 3: Expert Probability Fusion
[0095] The method for obtaining the conditional probability information of the extended node information and the conditional probability information of the non-hardware key event information can be determined based on fuzzy reasoning and triangular membership function. Furthermore, the nodes in the Bayesian network model can be scored according to actual conditions. The higher the score, the better the node status, such as Table 4.
[0096]
[0097] Table 4: Bayesian network model node score values
[0098] The posterior probability information of each node in the Bayesian network model can refer to a probability that is more in line with reality after correcting the probability of the node. The posterior probability of the node where the non-hardware critical event is located is the probability of occurrence of the non-hardware critical event.
[0099] Among them, in the embodiment of the present application, after determining the posterior probability information of each node in the Bayesian network model according to the prior probability information of the basic influencing factor information, the conditional probability information of the extended node information and the conditional probability information of the non-hardware key event information, the method may also include:
[0100] Adjust the prior probability information of the basic influencing factor information to obtain the posterior probability information of each node target;
[0101] Determine the change rate of the posterior probability of each node according to the posterior probability information of the target of each node and the posterior probability information of each node;
[0102] According to the change rate of the posterior probability of each node, the sensitivity analysis results of the basic influencing factors are determined.
[0103] Among them, the target posterior probability information of each node can refer to the posterior probability information obtained after adjusting the prior probability information of the basic influencing factor information. The adjustment operation can refer to reducing the probability of the basic influencing factor information to a certain threshold. At this time, the posterior probability information of each node is the target posterior probability information.
[0104] The change rate of the posterior probability of each node may refer to the ratio of the posterior probability information to the target posterior probability information, which represents the sensitivity of each node, as shown in Table 5.
[0105]
[0106] Table 5: Change rate of leaf node posterior probability
[0107] According to the above embodiment, the result of the sensitivity analysis of the basic influencing factor nodes can be that "equipment status" and "environmental status" have a significant impact on the overflow situation, among which "environmental status" has a higher degree of impact; and "communication reliability" has the highest degree of impact on the completion of emergency response by personnel in various positions. It can be preliminarily clarified that to improve the overflow situation at the wellhead, it is necessary to monitor the corresponding parameters of the surrounding environment in real time and respond promptly when abnormal conditions occur; to improve the reliability of personnel operations during the emergency response process, it is necessary to maintain good on-site communication conditions and conduct regular emergency training and drills.
[0108] S104: Determine the probability of occurrence of a hardware critical event based on the fault tree and the probability of occurrence of a non-hardware critical event.
[0109] The probability of occurrence of a hardware critical event may refer to a numerical measure of the likelihood of occurrence of a critical event under the influence of hardware facilities.
[0110] Among them, in the embodiment of the present application, according to the fault tree and the probability of occurrence of non-hardware critical events, the probability of occurrence of hardware critical events is determined, and the method may include:
[0111] Determine the probability of occurrence of intermediate events based on the probability of occurrence of non-hardware critical events and the probability of occurrence of basic events;
[0112] According to the probability of occurrence of intermediate events, the probability of occurrence of hardware key events is determined.
[0113] Among them, according to the occurrence probability of non-hardware key events and the occurrence probability of basic events, the method for determining the occurrence probability of intermediate events may include first determining the relationship between the intermediate event and the underlying non-hardware key events and basic events. When the relationship is "occurs only when both occur", the occurrence probability of the intermediate event is the product of the occurrence probability of the underlying non-hardware key events and the occurrence probability of the basic events. When the relationship is "occurs when any one occurs", the occurrence probability of the intermediate event is the sum of the occurrence probability of the underlying non-hardware key events and the occurrence probability of the basic events. For example, Figure 3 , the probability of occurrence of M1 is the sum of the probabilities of occurrence of X1, X2 and X3, and the probability of occurrence of M3 is the product of the probabilities of occurrence of X4 and X5.
[0114] According to the probability of occurrence of the intermediate event, the method for determining the probability of occurrence of the hardware key event may include first determining the relationship between the hardware key event and the intermediate event below. When the relationship is "occurs only when both occur", the probability of occurrence of the hardware key event is the product of the probability of occurrence of the intermediate event below. When the relationship is "occurs when any one occurs", the probability of occurrence of the hardware key event is the sum of the probability of occurrence of the intermediate events below. For example, Figure 3 , the probability of occurrence of T1 is the sum of the probabilities of occurrence of M1 and M2.
[0115] In the embodiment of the present application, after determining the probability of occurrence of a hardware critical event according to the fault tree and the probability of occurrence of a non-hardware critical event, the method may further include:
[0116] Determine the probability of occurrence of critical events based on the probability of occurrence of non-hardware critical events and the probability of occurrence of hardware critical events;
[0117] Determine the importance of key events based on overflow probability and the probability of occurrence of key events;
[0118] According to the importance of key events, determine the results of event importance analysis.
[0119] Among them, the probability of occurrence of a critical event may refer to the probability of occurrence of an overflow critical event. Overflow critical events are composed of hardware critical events and non-hardware critical events. Therefore, the probability of occurrence of a critical event may be determined based on the probability of occurrence of non-hardware critical events and the probability of occurrence of hardware critical events.
[0120] The overflow probability may refer to the possibility of an overflow event occurring at the wellhead. Methods for obtaining the overflow probability may include collecting historical data of drilled wells, including geological data, drilling parameters, overflow event records, etc. For example, refer to the statistical data of overflows occurring at oil and gas wellheads in a certain region of China in 2021.
[0121] The importance of a key event can refer to the key position it occupies in a specific situation or process and the degree of its influence on the overall result or goal achievement. Methods for determining the importance of a key event can include structural importance analysis, probabilistic importance analysis, and critical importance analysis.
[0122] The results of event importance analysis can refer to the conclusions or summaries obtained after evaluating the importance of a series of key events. For example, according to the importance of key events in Table 6, the results of event importance analysis can be obtained as follows: although the risk increase factors of key events P7, P3, and P4 are relatively high, their importance factors are relatively low, and their impact on the overall risk of the system is relatively small. Key events P1 and P2 not only have high risk increase factors but also high importance factors. The failure of the overall emergency response of the system will largely come from the failure of key events P1 and P2.
[0123]
[0124] Table 6: Importance of key events
[0125] In the embodiment of the present application, the importance of the key event is determined according to the overflow probability and the occurrence probability of the key event. The method may include:
[0126] According to the overflow probability and the occurrence probability of the key event, the first conditional probability and the second conditional probability are determined. The first conditional probability is the probability of overflow under the condition that the key event occurs, and the second conditional probability is the probability of the key event and overflow occurring together.
[0127] The first conditional probability and the overflow probability are divided to obtain the first importance;
[0128] The second conditional probability and the overflow probability are divided to obtain the second importance;
[0129] The importance of the key event is determined based on the first importance and the second importance.
[0130] The first importance may refer to the node importance obtained by evaluating the increase in the overall failure probability of the system caused by the failure or failure of a single node, and the second importance may refer to the node importance obtained based on the part of the total failure probability of the system that includes the node failure.
[0131] The formula for obtaining the first importance can be:
[0132]
[0133] in, is the first conditional probability, is the overflow probability.
[0134] The formula for obtaining the second importance can be:
[0135]
[0136] in, is the second conditional probability, is the overflow probability.
[0137] According to the first importance and the second importance, the method of determining the importance of the key event may include averaging the first importance and the second importance, or making the first importance and the second importance constitute the importance of the key event.
[0138] S105. Determine the probability of response failure according to the response failure accident cause chain, the occurrence probability of non-hardware key events and the occurrence probability of hardware key events.
[0139] Among them, the probability of response failure can refer to the probability of each response failure accident causal chain causing wellhead overflow. There are non-hardware critical events and hardware critical events in the corresponding failure accident causal chain. The method for obtaining the probability of response failure can include substituting the probability of occurrence of non-hardware critical events and the probability of occurrence of hardware critical events into the corresponding failure accident causal chain.
[0140] S106. Determine overflow analysis results based on the response failure accident causal chain and the probability of response failure.
[0141] Among them, according to the response failure accident causal chain and the probability of response failure, the method for determining the overflow analysis result may include combining each node in the response failure accident causal chain and the probability of response failure for comprehensive analysis. For example, the probability of response failure in two response failure accident causal chains is significantly higher than that of the remaining links. The failed nodes are P1, which discovers overflow and stops operation, P2, which continues to overflow and immediately shuts in the well, and P6, which shuts in the well by local ESD. Through the fault tree and Bayesian network model, it can be found that these three nodes are all nodes with high personnel uncertainty, and the participation of deterministic factors such as equipment and devices in the response failure accident causal chain is relatively low.
[0142] The overflow analysis method provided in the embodiment of the present application can obtain the occurrence probability of non-hardware critical events in the fault tree from the Bayesian network model, and then obtain the occurrence probability of hardware critical events in the fault tree, and further bring the occurrence probability of all overflow critical events in the sequence diagram into the response failure accident causal chain to obtain the probability of response failure, and analyze the overflow according to the response failure accident causal chain and the probability of response failure, so as to achieve the effect of improving the accuracy of the overflow analysis results.
[0143] Figure 5 A schematic diagram of another overflow analysis method provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the method includes:
[0144] S501. Construct the cause chain, fault tree and Bayesian network model of response failure accidents.
[0145] Among them, the response failure accident cause chain can refer to a series of links of events or factors that cause the wellhead intelligent control system to be unable to effectively respond and control the wellhead overflow.
[0146] S502: Determine the conditional probability of non-root nodes in the Bayesian network model according to the triangular membership function.
[0147] The non-root node conditional probability may refer to the probability of a node taking a specific value or an event occurring under a given root node state or precondition.
[0148] S503: Determine the posterior probability according to the prior probability of the root node and the conditional probability of the non-root nodes in the Bayesian network model.
[0149] The posterior probability may refer to a probability that is more in line with reality after correcting the probability of a node.
[0150] S504: Reduce the prior probability of the root node to 0.5, and obtain the state change information of the non-root nodes.
[0151] The state change information of the non-root node may refer to information about the changes of each node when the prior probability of the root node decreases to 0.5.
[0152] S505: Determine the top event probability according to the fault tree and the posterior probability.
[0153] The top event probability may refer to the occurrence probability of the event in the top node in the fault tree. The intermediate event probability is obtained according to the posterior probability, and then the top event probability is obtained from the intermediate event probability.
[0154] S506: Determine overflow analysis results according to the response failure accident cause chain, posterior probability, top event probability and state change information of non-root nodes.
[0155] The overflow analysis result may refer to the analysis result of the cause of the overflow phenomenon at the wellhead and the fault node.
[0156] Another overflow analysis method provided in an embodiment of the present application can determine the conditional probability of non-root nodes through a triangular membership function, and then reduce the prior probability of the root node to 0.5 after obtaining the posterior probability, clarify the impact of the root node on the status of other nodes, and then analyze the overflow in combination with the response failure accident causal chain, posterior probability, and top event probability, thereby improving the accuracy of the overflow analysis results.
[0157] Figure 6 This is a schematic diagram of the structure of the overflow analysis device provided in the embodiment of the present application. Figure 6 As shown, the overflow analysis device 60 includes: an acquisition module 601, a first determination module 602, a second determination module 603, a third determination module 604, a fourth determination module 605, and a fifth determination module 606. Among them:
[0158] An acquisition module 601 is used to acquire overflow key event information, where the overflow key event information includes hardware key event information and non-hardware key event information;
[0159] The first determination module 602 is used to determine the response failure accident cause chain, fault tree and Bayesian network model according to the overflow key event information;
[0160] The second determination module 603 is used to determine the probability of occurrence of non-hardware critical events according to the Bayesian network model;
[0161] The third determination module 604 is used to determine the probability of occurrence of the hardware critical event according to the fault tree and the probability of occurrence of the non-hardware critical event;
[0162] The fourth determination module 605 is used to determine the probability of response failure according to the response failure accident cause chain, the probability of occurrence of non-hardware key events and the probability of occurrence of hardware key events;
[0163] The fifth determination module 606 is used to determine the overflow analysis result according to the response failure accident cause chain and the probability of response failure.
[0164] In the embodiment of the present application, the first determining module 602 may also be used to:
[0165] Determine the overflow emergency response sequence diagram based on the overflow key event information;
[0166] According to the overflow emergency response sequence diagram, determine the cause chain of response failure accidents;
[0167] Determine the fault tree based on overflow key event information, intermediate event information and basic event information;
[0168] The Bayesian network model is determined based on non-hardware key event information, basic influencing factor information and extended node information.
[0169] In the embodiment of the present application, the second determining module 603 may also be used to:
[0170] Acquire prior probability information of basic influencing factor information, conditional probability information of extended node information, and conditional probability information of non-hardware key event information;
[0171] Determine the posterior probability information of each node in the Bayesian network model according to the prior probability information of the basic influencing factor information, the conditional probability information of the extended node information and the conditional probability information of the non-hardware key event information;
[0172] According to the posterior probability information of each node in the Bayesian network model, the occurrence probability of non-hardware critical events is determined.
[0173] In the embodiment of the present application, the second determining module 603 may also be used to:
[0174] Adjust the prior probability information of the basic influencing factor information to obtain the posterior probability information of each node target;
[0175] Determine the change rate of the posterior probability of each node according to the posterior probability information of the target of each node and the posterior probability information of each node;
[0176] According to the change rate of the posterior probability of each node, the sensitivity analysis results of the basic influencing factors are determined.
[0177] In the embodiment of the present application, the third determining module 604 may also be used to:
[0178] Determine the probability of occurrence of intermediate events based on the probability of occurrence of non-hardware critical events and the probability of occurrence of basic events;
[0179] According to the probability of occurrence of intermediate events, the probability of occurrence of hardware key events is determined.
[0180] In the embodiment of the present application, the third determining module 604 may also be used to:
[0181] Determine the probability of occurrence of critical events based on the probability of occurrence of non-hardware critical events and the probability of occurrence of hardware critical events;
[0182] Determine the importance of key events based on overflow probability and the probability of occurrence of key events;
[0183] According to the importance of key events, determine the results of event importance analysis.
[0184] In the embodiment of the present application, the third determining module 604 may also be used to:
[0185] According to the overflow probability and the occurrence probability of the key event, the first conditional probability and the second conditional probability are determined. The first conditional probability is the probability of overflow under the condition that the key event occurs, and the second conditional probability is the probability of the key event and overflow occurring together.
[0186] The first conditional probability and the overflow probability are divided to obtain the first importance;
[0187] The second conditional probability and the overflow probability are divided to obtain the second importance;
[0188] The importance of the key event is determined based on the first importance and the second importance.
[0189] As can be seen from the above, the overflow analysis device of the embodiment of the present application is composed of an acquisition module 601, which is used to acquire overflow key event information, and the overflow key event information includes hardware key event information and non-hardware key event information; a first determination module 602, which is used to determine the response failure accident causal chain, fault tree and Bayesian network model according to the overflow key event information; a second determination module 603, which is used to determine the occurrence probability of non-hardware key events according to the Bayesian network model; a third determination module 604, which is used to determine the occurrence probability of hardware key events according to the fault tree and the occurrence probability of non-hardware key events; a fourth determination module 605, which is used to determine the probability of response failure according to the response failure accident causal chain, the occurrence probability of non-hardware key events and the occurrence probability of hardware key events; a fifth determination module 606, which is used to determine the overflow analysis result according to the response failure accident causal chain and the probability of response failure. Therefore, the embodiment of the present application can obtain the occurrence probability of non-hardware critical events in the fault tree from the Bayesian network model, and then obtain the occurrence probability of hardware critical events in the fault tree, and further bring the occurrence probability of all overflow critical events in the sequence diagram into the response failure accident causation chain to obtain the probability of response failure, and analyze the overflow according to the response failure accident causation chain and the probability of response failure, so as to achieve the effect of improving the accuracy of the overflow analysis results.
[0190] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, the memory 702 and the communication component 703 are connected via a bus 704.
[0191] In a specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that at least one processor 701 executes the above method.
[0192] The specific implementation process of the processor 701 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0193] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.
[0194] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.
[0195] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.
[0196] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.
[0197] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.
[0198] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.
[0199] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
[0200] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.
[0201] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0202] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0203] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0204] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.
[0205] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. An overflow analysis method, characterized in that: Applied to a wellhead intelligent control system, the method comprises: Acquire overflow key event information, wherein the overflow key event information includes hardware key event information and non-hardware key event information; Determine the response failure accident cause chain, fault tree and Bayesian network model based on the overflow key event information; Determining the probability of occurrence of non-hardware critical events according to the Bayesian network model; Determining the probability of occurrence of a hardware critical event based on the fault tree and the probability of occurrence of the non-hardware critical event; Determine the probability of response failure according to the response failure accident causal chain, the occurrence probability of the non-hardware critical event and the occurrence probability of the hardware critical event; The overflow analysis result is determined based on the response failure accident causal chain and the probability of the response failure.
2. The method according to claim 1, characterized in that Determining the response failure accident cause chain, fault tree and Bayesian network model according to the overflow key event information includes: Determine an overflow emergency response sequence diagram based on the overflow key event information; Determine the cause chain of the response failure accident according to the overflow emergency response sequence diagram; Determining the fault tree according to the overflow key event information, the intermediate event information and the basic event information; The Bayesian network model is determined according to the non-hardware key event information, basic influencing factor information and extended node information.
3. The method according to claim 1, characterized in that Determining the probability of occurrence of non-hardware critical events according to the Bayesian network model includes: Acquire prior probability information of basic influencing factor information, conditional probability information of extended node information, and conditional probability information of the non-hardware key event information; Determine the posterior probability information of each node in the Bayesian network model according to the prior probability information of the basic influencing factor information, the conditional probability information of the extended node information and the conditional probability information of the non-hardware key event information; The occurrence probability of the non-hardware critical event is determined according to the posterior probability information of each node in the Bayesian network model.
4. The method according to claim 3, characterized in that After determining the posterior probability information of each node in the Bayesian network model according to the prior probability information of the basic influencing factor information, the conditional probability information of the extended node information and the conditional probability information of the non-hardware key event information, the method further includes: Adjusting the prior probability information of the basic influencing factor information to obtain the posterior probability information of each node target; Determining a posterior probability change rate of each node according to the posterior probability information of each node target and the posterior probability information of each node; According to the posterior probability change rate of each node, the sensitivity analysis result of the basic influencing factor node is determined.
5. The method according to claim 1, characterized in that Determining the probability of occurrence of a hardware critical event according to the fault tree and the probability of occurrence of the non-hardware critical event includes: Determining the probability of occurrence of an intermediate event according to the probability of occurrence of the non-hardware critical event and the probability of occurrence of the basic event; The occurrence probability of the hardware key event is determined according to the occurrence probability of the intermediate event.
6. The method according to claim 1, characterized in that After determining the probability of occurrence of a hardware critical event according to the fault tree and the probability of occurrence of the non-hardware critical event, the method further includes: Determining the probability of occurrence of the critical event according to the probability of occurrence of the non-hardware critical event and the probability of occurrence of the hardware critical event; Determining the importance of the key event according to the overflow probability and the occurrence probability of the key event; According to the importance of the key event, an event importance analysis result is determined.
7. The method according to claim 6, characterized in that Determining the importance of the key event according to the overflow probability and the occurrence probability of the key event includes: Determine a first conditional probability and a second conditional probability according to the overflow probability and the occurrence probability of the key event, wherein the first conditional probability is the probability of overflow under the condition that the key event occurs, and the second conditional probability is the probability of the key event and overflow occurring together; Taking a quotient of the first conditional probability and the overflow probability to obtain a first importance; Taking a quotient of the second conditional probability and the overflow probability to obtain a second importance; The importance of the key event is determined according to the first importance and the second importance.
8. An overflow analysis device, characterized in that: include: An acquisition module is used to acquire overflow key event information, wherein the overflow key event information includes hardware key event information and non-hardware key event information; A first determination module is used to determine the response failure accident cause chain, fault tree and Bayesian network model according to the overflow key event information; A second determination module is used to determine the probability of occurrence of non-hardware critical events according to the Bayesian network model; A third determination module, used to determine the probability of occurrence of a hardware critical event according to the fault tree and the probability of occurrence of the non-hardware critical event; A fourth determination module, configured to determine the probability of response failure according to the response failure accident cause chain, the occurrence probability of the non-hardware critical event and the occurrence probability of the hardware critical event; The fifth determination module is used to determine the overflow analysis result according to the response failure accident causal chain and the probability of the response failure.
9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.