A pipeline safety evaluation method, system and equipment within the scope of a power plant boiler

By establishing a comprehensive evaluation index system for pipeline failure risk and a Bayesian network model, the problem of accurately evaluating the safety status of power plant boiler pipelines has been solved, enabling efficient and accurate detection and early warning of safety hazards, and supporting scientific maintenance and renovation decisions.

CN117875714BActive Publication Date: 2024-11-15CHINA SPECIAL EQUIP INSPECTION & RES INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410063121.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-16
Publication Date
2024-11-15
Estimated Expiration
2044-01-16

AI Technical Summary

Technical Problem

Existing technologies are insufficient for scientifically and accurately conducting hazard identification and safety assessment of pipelines within the boiler area of ​​power plants, resulting in difficulties in accurately assessing safety status and failing to meet the growing demand for safety supervision.

Method used

A comprehensive evaluation index system for pipeline failure risk is established, a pipeline failure risk accident tree model is constructed and mapped to a Bayesian network, and prior probabilities are assigned based on multi-source data fusion analysis to conduct pipeline failure probability inference analysis and safety status early warning.

Benefits of technology

It improves the efficiency and accuracy of pipeline hazard investigation and safety status monitoring within the power plant boiler area, promptly identifies major safety hazards, provides a scientific basis for maintenance and renovation plans, and achieves a balance between safety and economy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117875714B_ABST
    Figure CN117875714B_ABST
Patent Text Reader

Abstract

The present invention discloses a pipeline safety evaluation method, system and equipment within the scope of a power station boiler, and relates to the field of coal-fired power. The present invention first analyzes the dangerous factors affecting the safe operation of pipelines from three aspects: equipment intrinsic safety, external environment and human factors, and establishes a comprehensive evaluation index system for pipeline failure risk, including 7 major evaluation items and corresponding 35 small evaluation indicators; then, nodes at all levels are established based on the comprehensive evaluation index system for pipeline failure risk, and a pipeline failure risk accident tree model is constructed and mapped to a Bayesian network; prior probabilities of different evaluation indicators are assigned based on multi-source data fusion analysis; pipeline failure probability reasoning analysis is performed based on the Bayesian network and the prior probabilities of different evaluation indicators, the pipeline failure probability is calculated, and a pipeline safety status warning is performed, which improves the efficiency and accuracy of pipeline hidden danger inspection and current safety status detection, and provides a scientific and effective theoretical basis for the formulation of pipeline maintenance, transformation, replacement and other plans.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of coal power technology, and in particular to a pipeline safety evaluation method, system and equipment within a power station boiler range. Background Art

[0002] As the "ballast stone" of China's electricity, coal-fired power is an important infrastructure to promote economic development and safeguard people's livelihood. At present, although the proportion of coal-fired power installed capacity is less than 50%, the proportion of power generation is still 60%, and it undertakes 70% of the peak tasks. In the short and medium term, coal-fired power still occupies a dominant position in providing electricity and peak power generation. Among them, super (super) critical thermal power units are the main units in the power industry. The pipelines within the scope of their power station boilers, especially the main steam pipelines, reheat steam hot section pipelines and other high-temperature pipelines are basically made of P91 and P92 martensitic heat-resistant steel. With the increase in the service time of power station boilers, some problems in the inspection and maintenance and regular inspection of power plants have also been exposed, such as abnormal metallographic structure, low or uneven hardness distribution, cracking of welded joints, etc.

[0003] In order to prevent systemic risks and effectively eliminate safety hazards, it is necessary to further strengthen the safety supervision of pipelines within the scope of power plant boilers and entrust qualified inspection and testing institutions to conduct safety evaluations. However, there is currently no systematic discussion on how to scientifically and accurately carry out hidden danger inspections and safety evaluations of pipelines within the scope of power plant boilers. The relevant technical system and its core key technologies have yet to be established, which makes it difficult to meet the growing urgent needs of boiler users for the inspection of hidden dangers in pipelines within the scope of power plant boilers and the accurate identification of the current safety status. Therefore, in order to ensure the safe production of generator sets, a complete and reliable set of evaluation technologies for inspecting safety hazards in pipelines within the scope of power plant boilers and determining the current safety status needs to be established. Summary of the invention

[0004] In response to the problems raised in the above background technology, the present invention provides a pipeline safety evaluation method, system and equipment within the scope of a power plant boiler to improve the efficiency and accuracy of pipeline hidden danger inspection and current safety status detection within the scope of a power plant boiler.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] In one aspect, the present invention provides a pipeline safety evaluation method within a power plant boiler, comprising:

[0007] Analyze the risk factors that affect the safe operation of pipelines from three aspects: equipment intrinsic safety, external environment and human factors, and establish a comprehensive evaluation index system for pipeline failure risk; the comprehensive evaluation index system for pipeline failure risk includes 7 major evaluation items and corresponding 35 minor evaluation indicators;

[0008] Based on the comprehensive evaluation index system of pipeline failure risk, nodes at all levels are established to construct a pipeline failure risk accident tree model;

[0009] Map the pipeline failure risk fault tree model into a Bayesian network;

[0010] Assigning prior probabilities of different evaluation indicators based on multi-source data fusion analysis;

[0011] Based on the Bayesian network and the prior probabilities of different evaluation indicators, the pipeline failure probability is inferred and analyzed to calculate the pipeline failure probability;

[0012] Provide early warning of pipeline safety status based on pipeline failure probability.

[0013] Optionally, the seven major evaluation items constituting the comprehensive evaluation index system for pipeline failure risk include cracks / cracking, material degradation, quality defects, operating conditions, use management, pipe wall thinning and other problems; the seven sub-evaluation indicators corresponding to the cracks / cracking include branch pipeline cracks / cracking, weld surface cracks, weld buried defects / cracks, IV type cracks, thermal fatigue cracks, vibration fatigue cracks and parent material cracks / cracking; the three sub-evaluation indicators corresponding to material degradation include low hardness caused by operation, organizational aging and mechanical property degradation; the seven sub-evaluation indicators corresponding to quality defects include support and hanger defects, welding defects other than cracks, low hardness caused by post-weld heat treatment, high hardness, design The four evaluation indicators corresponding to the operating conditions include deep peak regulation and rapid load change, safety valve failure, overtemperature and overpressure; the nine evaluation indicators corresponding to the use management include special inspections not implemented as required, statutory inspections not carried out in accordance with regulations, missing technical data, missing quality control of imported products, abnormal valve control system, valves not maintained, fault records, personnel certification issues, and irregular emergency rescue and inspections; the four evaluation indicators corresponding to the pipe wall thinning include erosion thinning, steam oxidation thinning, water side corrosion thinning and outer wall corrosion thinning; the one evaluation indicator corresponding to the other problems is unqualified water quality or improper cleaning.

[0014] Optionally, the pipeline failure risk comprehensive evaluation index system is used to establish nodes at all levels and construct a pipeline failure risk accident tree model, specifically including:

[0015] The pipeline failure risk accident tree model is constructed by taking pipeline failure as the child node of the pipeline failure risk accident tree model, taking the seven major evaluation items as the intermediate nodes, and taking the evaluation indicators corresponding to the evaluation items as the parent nodes of the intermediate nodes.

[0016] Optionally, the prior probabilities of assigning different evaluation indicators based on multi-source data fusion analysis specifically include:

[0017] According to the evaluation levels of different evaluation indicators of the pipeline, combined with the possibility of event occurrence and running time, the prior probabilities of different evaluation indicators are determined based on multi-source data fusion analysis.

[0018] Optionally, the pipeline failure probability reasoning analysis based on the Bayesian network and the prior probabilities of different evaluation indicators to calculate the pipeline failure probability specifically includes:

[0019] Based on the Bayesian network and the prior probability of different evaluation indicators, the pipeline failure probability reasoning analysis is carried out using the formula Calculation evaluation item M j The probability of occurrence P(M j ); where X i represents the i-th evaluation index; k is the number of evaluation indicators; P(X i ) is the evaluation index X i The prior probability of j |X i ) indicates that in event X i In the event that event M j Conditional probability of occurrence;

[0020] According to the evaluation project M j The probability of occurrence P(M j ), using the formula Calculate the pipeline failure probability P(E); where K is the number of evaluation items; P(E|M j ) indicates that in event M j The conditional probability of pipeline failure E occurring when .

[0021] Optionally, the pipeline safety assessment method within the power plant boiler range also includes:

[0022] Iterative calculation of posterior probability is performed based on pipeline failure probability P(E) and Bayesian formula;

[0023] The evaluation index with large posterior probability is determined as the key factor leading to pipeline failure.

[0024] On the other hand, the present invention also provides a pipeline safety evaluation system within the scope of a power plant boiler, comprising:

[0025] A comprehensive evaluation index system establishment module is used to analyze the risk factors that affect the safe operation of pipelines from three aspects: equipment intrinsic safety, external environment and human factors, and establish a comprehensive evaluation index system for pipeline failure risks; the comprehensive evaluation index system for pipeline failure risks includes 7 major evaluation items and corresponding 35 minor evaluation indicators;

[0026] The accident tree model construction module is used to establish nodes at all levels based on the comprehensive evaluation index system of pipeline failure risk and construct the pipeline failure risk accident tree model;

[0027] Bayesian networking module, used to map the pipeline failure risk accident tree model into a Bayesian network;

[0028] Prior probability assignment module, used to assign prior probabilities of different evaluation indicators based on multi-source data fusion analysis;

[0029] The pipeline failure probability calculation module is used to perform pipeline failure probability reasoning analysis based on the Bayesian network and the prior probabilities of different evaluation indicators to calculate the pipeline failure probability;

[0030] The pipeline safety status early warning module is used to provide early warning of pipeline safety status based on the probability of pipeline failure.

[0031] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the pipeline safety evaluation method within the scope of a power plant boiler when executing the computer program.

[0032] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0033] The present invention provides a pipeline safety evaluation method, system and equipment within the scope of a power plant boiler. First, the dangerous factors affecting the safe operation of the pipeline are analyzed from three aspects: the intrinsic safety of the equipment, the external environment and human factors, and a comprehensive evaluation index system for pipeline failure risk is established. The comprehensive evaluation index system includes 7 major evaluation items and corresponding 35 small evaluation indicators; then, nodes at all levels are established based on the comprehensive evaluation index system for pipeline failure risk, and a pipeline failure risk accident tree model is constructed; the pipeline failure risk accident tree model is mapped into a Bayesian network; the prior probability of assigning different evaluation indicators is analyzed based on multi-source data fusion; the pipeline failure probability is reasoned and analyzed based on the Bayesian network and the prior probability of different evaluation indicators, and the pipeline failure probability is calculated; and the pipeline safety status is warned according to the pipeline failure probability. By applying the method of the present invention, the pipeline safety status within the scope of the power plant boiler can be mastered, major safety hazards can be discovered in time, and a scientific and effective theoretical basis can be provided for the formulation of maintenance, transformation, replacement and other plans, so as to solve the industry bottleneck technical problem that the safety status of the pipeline within the scope of the power plant boiler is difficult to accurately evaluate and quickly warn, so as to achieve both safety and economy, and improve the efficiency and accuracy of pipeline hidden danger investigation and current safety status detection within the scope of the power plant boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only 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.

[0035] Figure 1 A flow chart of a pipeline safety evaluation method within a power plant boiler according to the present invention;

[0036] Figure 2 A schematic diagram of a pipeline failure risk accident tree model constructed by the present invention;

[0037] Figure 3 A schematic diagram of a pipeline Bayesian network established for the present invention;

[0038] Figure 4 A schematic diagram of the Bayesian network calculation results provided by an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of the Bayesian network posterior probability calculation results provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0041] The present invention aims to analyze the risk factors that affect the safe operation of pipelines within the scope of power plant boilers (hereinafter referred to as "pipelines") from three aspects: equipment intrinsic safety, external environment and human factors, establish a pipeline failure risk accident tree model, map it into a Bayesian network by establishing nodes, combine multi-source data fusion analysis to assign prior probabilities of different evaluation indicators of pipelines, and perform pipeline failure probability reasoning analysis, and finally form a pipeline safety evaluation method, system and equipment within the scope of power plant boilers, so as to improve the efficiency and accuracy of pipeline hidden danger inspection and current safety status detection within the scope of power plant boilers.

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] See also Figure 1 The present invention provides a pipeline safety evaluation method within the scope of a power plant boiler, comprising:

[0044] Step 1: Analyze the risk factors that affect the safe operation of pipelines from three aspects: equipment intrinsic safety, external environment and human factors, and establish a comprehensive evaluation index system for pipeline failure risks.

[0045] The present invention analyzes the risk factors affecting the safe operation of pipelines within the scope of power plant boilers from three aspects: equipment intrinsic safety, external environment and human factors, and establishes a comprehensive evaluation index system for pipeline failure risk, specifically including crack (cracking) M 1 、Material Deterioration M 2 、Quality defect M 3 , operating condition M 4 、Use Management 5 , wall thinning M 6 And other issues 7 7 major evaluation items and corresponding 35 small evaluation indicators X 1 , X 2 ,……X 35 , as shown in Table 1.

[0046] Table 1 Comprehensive evaluation index system for pipeline failure risk and on-site inspection form

[0047]

[0048]

[0049]

[0050]

[0051]

[0052]

[0053]

[0054]

[0055]

[0056]

[0057]

[0058]

[0059]

[0060]

[0061]

[0062]

[0063]

[0064]

[0065] Where crack / cracking (symbol “ / ” means or) M 1 、Material Deterioration M 2 、Quality defect M 3 , wall thinning M 6 And other issues 7 The evaluation indicators of the five major items and their sub-items belong to the intrinsic safety of equipment; 4 Operating conditions belong to the external environment; M 5 Usage management belongs to the human factor aspect. Among them, crack / cracking 1 The corresponding 7 small evaluation indicators include branch pipeline crack / cracking X 1 、Weld surface cracks X 2 , weld buried defects / cracks X 3 、IV crack X 4 , thermal fatigue crack X 5 , vibration fatigue crack X 6 And cracks / cracking of base material X 7 ; The material deterioration M 2 The corresponding three small evaluation indicators include low hardness caused by operation X 8 、Tissue agingX 9 And mechanical properties decreased 10 ; The quality defect M 3 The corresponding 7 small evaluation indicators include support and hanger defect X 11 、Welding defects other than cracks X 12 , low hardness caused by post-weld heat treatment 13 , high hardness X 14 、Design defectX 15 , Improper processing technology 16 And the quality of the original material is not up to standard X 17 ; The operating condition M 4 The corresponding four sub-items of evaluation indicators include deep peak regulation and rapid load change X 18 、Safety valve failureX 19 , Overtemperature X 20 And overpressure X 21 ; The use management M 5 The corresponding 9 sub-items of evaluation indicators include special inspections that have not been implemented as required. 22 , statutory inspections not carried out in accordance with regulations X 23 、Missing technical informationX 24, Lack of quality control of imported products X 25 , valve control system abnormalityX 26 , The valve has not been maintained. 27 , Fault Record X 28 , Personnel certification issues 29 And emergency rescue and inspection are not standardized 30 The tube wall is thinned M 6 The corresponding four evaluation indicators include scour thinning X 31 , Steam oxidation thinning X 32 、Water side corrosion thinning X 33 And external wall corrosion thinning X 34 ; Other issues M 7 The corresponding evaluation index is unqualified water quality or improper cleaning X 35 .

[0066] Step 2: Establish nodes at all levels based on the comprehensive evaluation index system of pipeline failure risk and construct a pipeline failure risk accident tree model.

[0067] Specifically, the pipeline failure E is taken as a sub-node of the pipeline failure risk accident tree model, and the seven major evaluation items M are 1 ~M 7 As an intermediate node, the evaluation index corresponding to each evaluation item is used as the parent node of the intermediate node to construct a pipeline failure risk accident tree model.

[0068] Step 3: Map the pipeline failure risk accident tree model into a Bayesian network.

[0069] The accident tree model can identify and evaluate the dangers of various systems. It can not only analyze the direct cause of the accident, but also deeply reveal the potential cause of the accident. It is intuitive and logical to describe the cause and effect relationship of the accident. The schematic diagram is as follows: Figure 2 shown. Figure 2 In, X 1 , X 2 , ... are the specific evaluation indicators in Table 1, corresponding to the parent node in the Bayesian network; M 1 、M 2 、M 3 , ... are the evaluation items in Table 1, corresponding to the intermediate nodes in the Bayesian network; E is the pipeline failure (Pipe Failure), corresponding to the child node in the Bayesian network. By establishing nodes at all levels (parent node, child node, intermediate node), the pipeline failure risk accident tree model is mapped to the Bayesian network, such as Figure 3As shown, the Bayesian network of the accident tree model is realized. The pipeline failure risk accident tree model in the present invention is similar to the Bayesian network structure, except that the accident tree analysis performs logical operations (yes and no), focusing on cause analysis and indicator system establishment, while the Bayesian network assigns probability values ​​at the nodes, which is conducive to quantitative calculation.

[0070] Step 4: Assign prior probabilities of different evaluation indicators based on multi-source data fusion analysis.

[0071] The evaluation levels of different evaluation indicators of pipelines are determined by combining the fusion analysis of multi-source data such as inspection, detection, and monitoring. Combined with the possibility of event occurrence and operating time, typical prior probability values ​​of different evaluation indicators are selected in Table 2.

[0072] Table 2 Typical prior probability values ​​of different pipeline evaluation indicators

[0073]

[0074]

[0075] Step 5: Perform pipeline failure probability reasoning analysis based on the Bayesian network and the prior probabilities of different evaluation indicators to calculate the pipeline failure probability.

[0076] The pipeline failure probability is calculated based on the total probability formula. The specific calculation formulas are shown in formulas (1) and (2):

[0077]

[0078]

[0079] Where E represents pipeline failure, and P(E) represents the probability of pipeline failure. j and the i-th evaluation index X i The probability of occurrence is expressed as P(M j ) and P(X i ); where P(X i ) is the typical prior probability value selected in step 4. k is the number of evaluation indicators; K is the number of evaluation items. i In the event that event M j The conditional probability of occurrence is expressed as P(M j |X i ), which is usually set based on expert experience. Then P(E|M j ) indicates that in event M j The conditional probability of pipeline failure E occurring when .

[0080] The conditional probability calculation process is shown in Table 3 and Figure 4 As shown, through node X1 , Node X 2 The prior probability and node M 1 The conditional probability (Table 3) is set, and the calculation node M 1 The probability of occurrence is calculated to be 39.4% (0.394). Where Y indicates that the event has occurred, and N indicates that the event has not occurred.

[0081] Table 3 Node M 1 The conditional probability of setting

[0082] <![CDATA[X 1 ]]> <![CDATA[X 2 ]]> <![CDATA[P(M 1 =Y)]]> <![CDATA[P(M 1 =N)]]> Y Y 0.7 0.3 Y N 0.6 0.4 N Y 0.4 0.6 N N 0.1 0.9

[0083] Step 6: Provide early warning of pipeline safety status based on pipeline failure probability.

[0084] The present invention establishes a comprehensive evaluation index system for pipeline failure risk within the scope of power plant boilers based on multi-source data fusion analysis, and comprehensively uses the Bayesian network risk evaluation method to quantitatively analyze the pipeline failure probability P(E) within the scope of power plant boilers. When the calculated pipeline failure probability P(E) exceeds a certain threshold, it can be determined that the pipeline is currently in a dangerous state and an early warning is required.

[0085] By applying the method of the present invention, the safety status of pipelines within the scope of power plant boilers can be mastered, major safety hazards can be discovered in time, and a scientific and effective theoretical basis can be provided for the formulation of maintenance, transformation, replacement and other plans, thereby solving the industry bottleneck technical problem of difficult accurate evaluation and rapid warning of the safety status of pipelines within the scope of power plant boilers, and achieving a balance between safety and economy.

[0086] Furthermore, in practical applications, the pipeline safety evaluation method within the power plant boiler range described in the present invention may also include: performing iterative calculation of the posterior probability based on the pipeline failure probability P(E) and the Bayesian formula; and determining the evaluation index with a large posterior probability as the key factor leading to pipeline failure.

[0087] Specifically, the posterior probability is iteratively calculated based on the Bayesian formula, and its calculation formula is shown in formula (3) and formula (4):

[0088] P(M j |E)={P(M j )P(E|M j )} / P(E) (3)

[0089] P(X i |M j )={P(X i )P(M j |X i )} / P(M j ) (4)

[0090] P(Mj |E) indicates that in the case of pipeline failure E, event M j The posterior probability of occurrence. P(X i |M j ) indicates event M j In the event that event X occurs i The basic principle of iterative calculation of posterior probability is different from the forward analysis method of "from cause to effect". It is to analyze the cause from the result, that is, assuming that the result occurs (pipeline failure), analyze which factors dominate and their probability of occurrence (posterior probability), and then compare them with the prior probability to iteratively optimize the evaluation model. In this example, X 1 The prior probability is 30%, and the posterior probability is 50.3%; X 2 The prior probability is 60% and the posterior probability is 74.6%. In the actual calculation process, due to the large number of evaluation indicators and the complex network constructed, special software is generally used for analysis. The calculation results are as follows: Figure 5 shown.

[0091] On the one hand, the present invention can realize the quantitative evaluation of pipeline safety risks within the scope of power plant boilers; on the other hand, it can put forward opinions or suggestions for improving the safety status of pipelines within the scope of power plant boilers. Specifically, the risk factors (evaluation indicators) can be sorted from large to small according to the failure probability (characterized by posterior probability), such as X 3 >X 1 >X 8 >X 3 >X 6 …. It can be seen from this that the three key factors that affect pipeline failure are buried defects (cracks) in welds, cracks (cracking) in branch pipelines, and low hardness caused by operation. Controlling these three key factors can effectively reduce the probability of pipeline failure risk.

[0092] Based on the method of the present invention, the present invention also provides a pipeline safety evaluation system within the scope of a power plant boiler, including: a comprehensive evaluation index system establishment module, which is used to analyze the dangerous factors affecting the safe operation of pipelines from three aspects of equipment intrinsic safety, external environment and human factors, and establish a comprehensive evaluation index system for pipeline failure risk; the comprehensive evaluation index system for pipeline failure risk includes 7 major evaluation items and corresponding 35 minor evaluation indicators; an accident tree model construction module, which is used to establish nodes at all levels based on the comprehensive evaluation index system for pipeline failure risk, and construct a pipeline failure risk accident tree model; a Bayesian networking module, which is used to map the pipeline failure risk accident tree model into a Bayesian network; a priori probability assignment module, which is used to assign priori probabilities of different evaluation indicators based on multi-source data fusion analysis; a pipeline failure probability calculation module, which is used to perform pipeline failure probability reasoning analysis based on the Bayesian network and the priori probabilities of different evaluation indicators, and calculate the pipeline failure probability; a pipeline safety status early warning module, which is used to perform pipeline safety status early warning according to the pipeline failure probability.

[0093] Furthermore, the present invention also provides an electronic device, which may include: a processor, a communication interface, a memory and a communication bus. The processor, the communication interface and the memory communicate with each other via the communication bus. The processor may call a computer program in the memory to execute a pipeline safety assessment method within the scope of a power plant boiler.

[0094] In addition, when the computer program in the above-mentioned memory is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-transitory 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, which is stored in a storage medium and includes 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 method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks or optical disks.

[0095] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0096] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A pipeline safety evaluation method within the scope of a power plant boiler, characterized in that: include: The risk factors affecting the safe operation of pipelines are analyzed from three aspects: equipment intrinsic safety, external environment and human factors, and a comprehensive evaluation index system for pipeline failure risk is established; the comprehensive evaluation index system for pipeline failure risk includes 7 major evaluation items and 35 corresponding small evaluation indicators, namely, cracks / cracking M1, material degradation M2, quality defects M3, operating conditions M4, use management M5, pipe wall thinning M6 and other problems M7; the 7 small evaluation indicators corresponding to cracks / cracking M1 include branch pipeline cracks / cracking X1, weld surface cracks X2, weld buried defects / cracks X3, IV type cracks X4, thermal fatigue cracks X5, vibration fatigue cracks X6 and parent material cracks / cracking X7; the 3 small evaluation indicators corresponding to material degradation M2 include low hardness caused by operation X8, tissue aging X9 and mechanical property degradation X10. 10 The seven evaluation indicators corresponding to the quality defect M3 include the support and hanger defect X 11 、Welding defects other than cracks X 12 , low hardness caused by post-weld heat treatment 13 , high hardness X 14 、Design defectX 15 , Improper processing technology 16 And the quality of the original material is not up to standard X 17 The four evaluation indicators corresponding to the operating condition M4 include deep peak regulation and rapid load change X 18 、Safety valve failureX 19 , Overtemperature X 20 And overpressure X 21 ; The 9 evaluation indicators corresponding to the use management M5 include special inspections that have not been implemented as required X 22 , statutory inspections not carried out in accordance with regulations X 23 、Missing technical informationX 24 , Lack of quality control of imported products X 25 , valve control system abnormalityX 26 , The valve has not been maintained. 27 , Fault Record X 28 , Personnel certification issues 29 And emergency rescue and inspection are not standardized 30 The four evaluation indicators corresponding to the pipe wall thinning M6 include erosion thinning X 31 , Steam oxidation thinning X 32 、Water side corrosion thinning X 33 And external wall corrosion thinning X 34 ; The other problem M7 corresponds to a small evaluation index of unqualified water quality or improper cleaning X 35 ; Based on the comprehensive evaluation index system of pipeline failure risk, nodes at all levels are established to construct a pipeline failure risk accident tree model; Map the pipeline failure risk fault tree model into a Bayesian network; Assigning prior probabilities of different evaluation indicators based on multi-source data fusion analysis; The evaluation levels of different evaluation indicators of pipelines are determined by combining the fusion analysis of multi-source data from inspection, detection, and monitoring. Then, the typical prior probability values ​​of different evaluation indicators are selected in Table 2 in combination with the possibility of event occurrence and operation time. Table 2 Typical prior probability values ​​of different pipeline evaluation indicators Based on the Bayesian network and the prior probabilities of different evaluation indicators, the pipeline failure probability is inferred and analyzed to calculate the pipeline failure probability, including: Based on the Bayesian network and the prior probability of different evaluation indicators, the pipeline failure probability reasoning analysis is carried out using the formula Calculation evaluation item M j The probability of occurrence P(M j ); where X i represents the i-th evaluation index; k is the number of evaluation indicators; P(X i ) is the evaluation index X i The prior probability of j |X i ) indicates that in event X i In the event that event M j Conditional probability of occurrence; According to the evaluation project M j The probability of occurrence P(M j ), using the formula Calculate the pipeline failure probability P(E); where K is the number of evaluation items; P(E|M j ) indicates that in event M j The conditional probability of pipeline failure E occurring if it occurs; Provide early warning of pipeline safety status based on pipeline failure probability P(E); Based on the pipeline failure probability P(E) and the Bayesian formula, the posterior probability is iteratively calculated to determine the evaluation index with a large posterior probability as the key factor leading to pipeline failure; Specifically, the calculation formula for iterative calculation of the posterior probability based on the Bayesian formula is as follows: P(M j |E)={P(M j )P(E|M j )} / P(E) P(X i |M j )={P(X i )P(M j |X i )} / P(M j ) P(M j |E) indicates that in the case of pipeline failure E, event M j The posterior probability of occurrence; P(X i |M j ) indicates event M j In the event that event X occurs i The posterior probability of occurrence.

2. The pipeline safety evaluation method within the scope of a power plant boiler according to claim 1 is characterized in that: The pipeline failure risk comprehensive evaluation index system is used to establish nodes at all levels and construct a pipeline failure risk accident tree model, which specifically includes: The pipeline failure risk accident tree model is constructed by taking pipeline failure as the child node of the pipeline failure risk accident tree model, taking the seven major evaluation items as the intermediate nodes, and taking the evaluation indicators corresponding to the evaluation items as the parent nodes of the intermediate nodes.

3. A pipeline safety assessment system within the scope of a power plant boiler, characterized in that: include: The module for establishing a comprehensive evaluation index system is used to analyze the risk factors that affect the safe operation of pipelines from three aspects: equipment intrinsic safety, external environment and human factors, and to establish a comprehensive evaluation index system for pipeline failure risks; the comprehensive evaluation index system for pipeline failure risks includes seven major evaluation items and 35 corresponding evaluation indicators, namely, cracks / cracking M1, material degradation M2, quality defects M3, operating conditions M4, use management M5, pipe wall thinning M6 and other problems M7; the seven evaluation indicators corresponding to cracks / cracking M1 include branch pipeline cracks / cracking X1, weld surface cracks X2, weld buried defects / cracks X3, IV type cracks X4, thermal fatigue cracks X5, vibration fatigue cracks X6 and parent material cracks / cracking X7; the three evaluation indicators corresponding to material degradation M2 include low hardness caused by operation X8, tissue aging X9 and mechanical property degradation X10. 10 The seven evaluation indicators corresponding to the quality defect M3 include the support and hanger defect X 11 、Welding defects other than cracks X 12 , low hardness caused by post-weld heat treatment 13 , high hardness X 14 、Design defectX 15 , Improper processing technology 16 And the quality of the original material is not up to standard X 17 The four evaluation indicators corresponding to the operating condition M4 include deep peak regulation and rapid load change X 18 、Safety valve failureX 19 , Overtemperature X 20 And overpressure X 21 ; The 9 evaluation indicators corresponding to the use management M5 include special inspections that have not been implemented as required X 22 , statutory inspections not carried out in accordance with regulations X 23 、Missing technical informationX 24 , Lack of quality control of imported products X 25 , valve control system abnormalityX 26 , The valve has not been maintained. 27 , Fault Record X 28 , Personnel certification issues 29 And emergency rescue and inspection are not standardized 30 The four evaluation indicators corresponding to the pipe wall thinning M6 include erosion thinning X 31 , Steam oxidation thinning X 32 、Water side corrosion thinning X 33 And external wall corrosion thinning X 34 ; The other problem M7 corresponds to a small evaluation index of unqualified water quality or improper cleaning X 35 ; The accident tree model construction module is used to establish nodes at all levels based on the comprehensive evaluation index system of pipeline failure risk and construct the pipeline failure risk accident tree model; Bayesian networking module, used to map the pipeline failure risk accident tree model into a Bayesian network; Prior probability assignment module, used to assign prior probabilities of different evaluation indicators based on multi-source data fusion analysis; The evaluation levels of different evaluation indicators of pipelines are determined by combining the fusion analysis of multi-source data from inspection, detection, and monitoring. Then, the typical prior probability values ​​of different evaluation indicators are selected in Table 2 in combination with the possibility of event occurrence and operation time. Table 2 Typical prior probability values ​​of different pipeline evaluation indicators The pipeline failure probability calculation module is used to perform pipeline failure probability reasoning analysis based on the Bayesian network and the prior probabilities of different evaluation indicators to calculate the pipeline failure probability, including: Based on the Bayesian network and the prior probability of different evaluation indicators, the pipeline failure probability reasoning analysis is carried out using the formula Calculation evaluation item M j The probability of occurrence P(M j ); where X i represents the i-th evaluation index; k is the number of evaluation indicators; P(X i ) is the evaluation index X i The prior probability of j |X i ) indicates that in event X i In the event that event M j Conditional probability of occurrence; According to the evaluation project M j The probability of occurrence P(M j ), using the formula Calculate the pipeline failure probability P(E); where K is the number of evaluation items; P(E|M j ) indicates that in event M j The conditional probability of pipeline failure E occurring if it occurs; The pipeline safety status early warning module is used to provide early warning of the pipeline safety status based on the pipeline failure probability P(E); Based on the pipeline failure probability P(E) and the Bayesian formula, the posterior probability is iteratively calculated to determine the evaluation index with a large posterior probability as the key factor leading to pipeline failure; Specifically, the calculation formula for iterative calculation of the posterior probability based on the Bayesian formula is as follows: P(M j |E)={P(M j )P(E|M j )} / P(E) P(X i |M j )={P(X i )P(M j |X i )} / P(M j ) P(M j |E) indicates that in the case of pipeline failure E, event M j The posterior probability of occurrence; P(X i |M j ) indicates event M j In the event that event X occurs i The posterior probability of occurrence.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for evaluating pipeline safety within a power plant boiler as described in any one of claims 1 to 2 is implemented.

5. The electronic device according to claim 4, characterized in that: The memory is a non-transitory computer-readable storage medium.