Photothermal power station key equipment failure consequence evaluation method, device, equipment and medium

Abstract

The invention discloses a photo-thermal power station key equipment failure consequence assessment method, device and equipment and a medium, and relates to the technical field of risk assessment, and the method comprises the steps: collecting and integrating the historical accident data of a photo-thermal power station, building an accident scene model, and recognizing key nodes such as equipment failure factors, response measures and states. The model is converted into a Bayesian network, the device state is a child node, and the influence factor is a father node; and determining the weight and conditional probability of each factor according to expert opinions by applying an interval type-2 fuzzy logic reasoning model, and evaluating the severity of the equipment failure consequence. According to the method, the historical accident data of the photo-thermal power station are collected and integrated, and the Bayesian network and the interval type-2 fuzzy logic reasoning model are combined, so that the potential risk of equipment failure can be identified and evaluated more accurately, and a scientific basis is provided for safe operation of the power station.

Description

Technical Field

[0001] The present application relates to the technical field of risk assessment, and in particular to a method, device, equipment and medium for assessing the consequences of failure of key equipment in a solar thermal power station. Background Art

[0002] Solar thermal power generation has attracted much attention due to its stable power generation capacity and has become a key component of emerging energy supply. However, solar thermal power stations face environmental, safety and cost challenges brought about by high-temperature operation of equipment and continuous power generation. Once a safety accident occurs, it will cause serious economic losses and threats to personal safety.

[0003] At present, there are many methods in other fields to evaluate the consequences of equipment accidents, such as analytic hierarchy process, fault tree, risk matrix, fuzzy reasoning, bow tie model, reliability block diagram analysis, Petri net, accident scenario deduction, etc. However, these methods have certain limitations, resulting in inaccurate prediction of the consequences of equipment failure in CSP plants. Summary of the invention

[0004] The purpose of this application is to provide a method, device, equipment and medium for evaluating the consequences of failure of key equipment in a solar thermal power plant, which can accurately quantify the potential accident consequences of failure of equipment in a solar thermal power plant.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for evaluating the consequences of failure of key equipment in a solar thermal power station, including:

[0007] Obtain historical accident data of CSP plants; the historical accident data are typical accident cases of special equipment;

[0008] Summarize and integrate the historical accident data to obtain key nodes of the accident consequence scenario, and establish an accident scenario deduction model based on the key nodes; the key nodes include equipment failure influencing factors, equipment failure response measures, and equipment failure node status; the accident scenario deduction model is used to predict the consequences of equipment failure through equipment failure conditions;

[0009] The accident scenario deduction model is converted into a Bayesian network structure; in the Bayesian network structure, each device failure node state is set as a child node, and each device failure influencing factor is set as a parent node;

[0010] According to interval type-2 fuzzy set theory, the failure impact data of each key equipment to be evaluated is input into the interval type-2 fuzzy logic reasoning model to obtain the relative weight of each parent node and determine the conditional probability table; the interval type-2 fuzzy logic reasoning model is a model based on the best-worst method of interval type-2 fuzzy; the interval type-2 fuzzy number of the interval type-2 fuzzy is obtained by converting the obtained expert opinions according to the corresponding fuzzy probability language;

[0011] Based on the conditional probability table, the Bayesian network structure is updated, and the posterior probability of each child node is calculated to evaluate the severity of the consequences of equipment failure.

[0012] In a second aspect, the present application provides a device for evaluating the consequences of failure of key equipment in a solar thermal power station, comprising:

[0013] A data acquisition module is used to acquire historical accident data of a CSP plant; the historical accident data are typical accident cases of special equipment;

[0014] A model building module is used to summarize and integrate the historical accident data to obtain the key nodes of the accident consequence scenario, and to establish an accident scenario deduction model based on the key nodes; the key nodes include equipment failure influencing factors, equipment failure response measures, and equipment failure node status; the accident scenario deduction model is used to predict the consequences of equipment failure through equipment failure conditions;

[0015] A conversion module, used to convert the accident scenario deduction model into a Bayesian network structure; in the Bayesian network structure, each device failure node state is set as a child node, and each device failure influencing factor is set as a parent node;

[0016] The calculation module is used to input the failure impact data of each key equipment to be evaluated into the interval type-2 fuzzy logic reasoning model according to the interval type-2 fuzzy set theory, obtain the relative weight of each parent node, and determine the conditional probability table; the interval type-2 fuzzy logic reasoning model is a model based on the best-worst method of interval type-2 fuzzy; the interval type-2 fuzzy number of the interval type-2 fuzzy is obtained by converting the obtained expert opinions according to the corresponding fuzzy probability language;

[0017] The evaluation module is used to update the Bayesian network structure based on the conditional probability table, calculate the posterior probability of each child node, and evaluate the severity of the consequences of equipment failure.

[0018] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-mentioned methods for assessing the consequences of failure of key equipment in a solar thermal power station.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for evaluating the consequences of failure of key equipment in a solar thermal power station.

[0020] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0021] The present application provides a method, device, equipment and medium for evaluating the consequences of failure of key equipment in a solar thermal power station. By obtaining historical accident data of the solar thermal power station and summarizing and integrating them, the potential causes and consequences of accidents can be more accurately identified, thereby improving the safety management level of the power station; the accident scenario deduction model established based on key nodes can predict the consequences of equipment failure through equipment failure conditions; converting the accident scenario deduction model into a Bayesian network structure helps to more clearly represent the relationship between the factors affecting equipment failure and the consequences of equipment failure, and facilitates the analysis of the degree of influence of each factor on the consequences; the use of an interval type-2 fuzzy logic inference model can more accurately process uncertainty information and improve the reliability of the evaluation results. By updating the Bayesian network structure and calculating the posterior probability of each subnode, the severity of the consequences of equipment failure can be evaluated more comprehensively and meticulously. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is an application environment diagram of a method for evaluating the consequences of failure of key equipment in a solar thermal power station in one embodiment of the present application;

[0024] Figure 2 A flow chart of a method for evaluating the consequences of failure of key equipment in a solar thermal power station provided in one embodiment of the present application;

[0025] Figure 3 A schematic diagram of an accident scenario consequence assessment framework provided in one embodiment of the present application;

[0026] Figure 4 A flowchart of expert opinion aggregation steps provided for an embodiment of the present application;

[0027] Figure 5 A structural diagram of a consequence assessment model for a molten salt storage tank accident scenario provided in one embodiment of the present application;

[0028] Figure 6A typical interval type-2 fuzzy number result diagram provided in one embodiment of the present application;

[0029] Figure 7 A distribution diagram of accident consequence levels and level proportions provided in an embodiment of the present application;

[0030] Figure 8 A schematic diagram of functional modules of a device for evaluating the consequences of failure of key equipment in a solar thermal power station provided in one embodiment of the present application;

[0031] Fig. 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0034] The failure consequence assessment method for key equipment of a solar thermal power station provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the historical accident data to be processed to the server 104. After the server 104 receives the historical accident data to be processed, for the historical accident data to be processed, the server 104 obtains the historical accident data of the solar thermal power station; summarizes and integrates the historical accident data to obtain the key nodes of the accident consequence scenario, and establishes an accident scenario deduction model based on the key nodes; the key nodes include equipment failure influencing factors, equipment failure response measures, and equipment failure node status; the accident scenario deduction model is used to predict the consequences of equipment failure through equipment failure conditions; the accident scenario deduction model is converted into a Bayesian network structure; the Bayesian network In the structure, each device failure node state is set as a child node, and each device failure influencing factor is set as a parent node; according to the interval type-2 fuzzy set theory, the failure influencing data of each key device to be evaluated is input into the interval type-2 fuzzy logic reasoning model to obtain the relative weight of each parent node and determine the conditional probability table; the interval type-2 fuzzy logic reasoning model is a model based on the best-worst method of interval type-2 fuzzy; the interval type-2 fuzzy number of the interval type-2 fuzzy is obtained by converting the obtained expert opinions according to the corresponding fuzzy probability language; based on the conditional probability table, the Bayesian network structure is updated, and the posterior probability of each child node is calculated to evaluate the severity of the consequences of equipment failure. The server 104 can feedback the obtained evaluation results to the terminal 102. In addition, in some embodiments, the method for evaluating the consequences of failure of key equipment in a solar thermal power station can also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 can directly process the historical accident data to be processed, or the server 104 can obtain the historical accident data to be processed from the data storage system and process the historical accident data to be processed.

[0035] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0036] In an exemplary embodiment, Figure 2As shown, a method for evaluating the consequences of failure of key equipment in a solar thermal power station is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 205.

[0037] in:

[0038] Step 201, obtaining historical accident data of a CSP power station; the historical accident data is a typical accident case of special equipment;

[0039] Step 202, summarize and integrate the historical accident data to obtain key nodes of the accident consequence scenario, and establish an accident scenario deduction model based on the key nodes; the key nodes include equipment failure influencing factors, equipment failure response measures, and equipment failure node status; the accident scenario deduction model is used to predict the consequences of equipment failure through equipment failure conditions;

[0040] Step 203, converting the accident scenario deduction model into a Bayesian network structure; in the Bayesian network structure, each device failure node state is set as a child node, and each device failure influencing factor is set as a parent node;

[0041] Step 204, according to interval type-2 fuzzy set theory, input the failure impact data of each key equipment to be evaluated into the interval type-2 fuzzy logic reasoning model, obtain the relative weight of each parent node, and determine the conditional probability table; the interval type-2 fuzzy logic reasoning model is a model based on the best-worst method of interval type-2 fuzzy; the interval type-2 fuzzy number of the interval type-2 fuzzy is obtained by converting the obtained expert opinions according to the corresponding fuzzy probability language;

[0042] Step 205 , based on the conditional probability table, the Bayesian network structure is updated, and the posterior probability of each child node is calculated to evaluate the severity of the consequences of equipment failure.

[0043] In some specific embodiments, when executing step 201, the following contents may be included in detail:

[0044] like Figure 3As shown in the figure, based on the operating experience and literature of solar thermal enterprises, the evolution path of the accident scenario is summarized, and the causes of the accident are explored. These causes include the early factors of the design, installation, operation and maintenance stages of key equipment such as absorbers, salt pipelines, molten salt storage tanks, and molten salt heat exchangers. In view of the particularity of the operating conditions of the solar thermal system, the frequent and influential indirect cloud breaks and extreme weather are separately classified as natural factors. At the same time, the damage caused to the system by the molten salt medium is classified as a medium factor. After the accident, the response measures are included in the evolution path of the accident scenario, and the effects of these measures on preventing accidents and the effectiveness of the implementation of different measures on the evolution of the accident path are evaluated until the accident is completely eliminated or the power station function is paralyzed. Finally, the accidents are connected in series to establish an accident scenario deduction model, which is the evolution process from equipment failure to consequences.

[0045] Specifically, given that the existing historical data is insufficient to comprehensively study the operation of the system, a tower solar thermal power station accident scenario consequence assessment model was constructed by consulting relevant literature and seeking expert opinions. The model mainly analyzes the consequence factors of four special equipment: the absorber, salt pipeline, molten salt storage tank, and molten salt heat exchanger. Taking the molten salt storage tank as an example, the main types of failures include tank leakage and tank foundation failure. Among them, tank leakage involves five main influencing factors, including design, installation, operation, medium, and system failure. For details, please refer to Figure 4 .

[0046] In some embodiments, when executing step 202, the specific steps may be as follows:

[0047] This embodiment is based on the historical public data of scientific and technological literature related to solar thermal power plants, the experience of enterprise operation, and combined with expert opinions as the basic data for research. Through the comprehensive analysis and collation of these materials, the key nodes in the accident consequence scenario are determined. These nodes include the influencing factors of equipment failure, measures to deal with equipment failure, and the status of equipment failure. The setting of key nodes takes into account the influencing factors, which are the direct causes of equipment failure, covering the entire life cycle of key equipment from design, manufacturing, installation, operation to maintenance. When selecting the status of key nodes, attention was paid to four key equipment in solar thermal power plants: absorbers, salt pipelines, molten salt storage tanks, and molten salt heat exchangers. Based on the interrelationship of these key nodes, failures at the nodes may not only cause secondary accidents themselves, but may also cause accidents of other equipment.

[0048] Specifically, the steps for node settings are as follows:

[0049] The node is set as a binary model, that is, two states of occurrence and non-occurrence. Whether the response measures can take effect is used as the decisive measure for different path deductions. Since the response measures are not responded to or delayed, and the response only plays a weakening role, it does not play a role in curbing the occurrence of subsequent accidents, which makes the accident worse. Other factors are used as synergistic factors. Finally, the consequence failure evaluation standard is established. The consequence evaluation model taking the molten salt storage tank as an example is as follows Figure 5 The specific node codes and names are shown in Table 1:

[0050] Table 1 Node code and name

[0051]

[0052]

[0053] In some embodiments, when executing steps 203-204, the following may be specifically included:

[0054] According to interval type-2 fuzzy set theory, the failure impact data of each key equipment to be evaluated is input into the interval type-2 fuzzy logic reasoning model, and the relative weight of each parent node is obtained based on the interval type-2 fuzzy best-worst method (FBWM), and finally the corresponding equipment failure probability is obtained. The specific steps are as follows:

[0055] (1) The accident scenario model is transformed into a Bayesian network structure. The target events to be evaluated, such as freezing and cracking of the heat sink, are set as child nodes; the influencing factors, such as insufficient salt filling and drastic transient temperature fluctuations, are set as parent nodes. The nodes represented are connected to each other based on the causal relationship between the events.

[0056] (2) Establish an expert group and invite multiple experts in the CSP industry to participate in the model evaluation. Through the questionnaire survey method, collect the opinions of the experts on the possibility of occurrence of basic accident events such as thermal shock, thermal stress, and equipment control failure, that is, expert opinions. The weight of each expert is determined by the scoring method based on the professional level, years of work, education level, age, and familiarity with accidents.

[0057] Specifically, five experts from CSP companies and universities with different educational backgrounds and work experience were invited to evaluate the relevant parameters of the Bayesian network model. The scoring method was used according to the scoring details in Table 1, and the weights of each expert were obtained as 0.273, 0.273, 0.106, 0.197 and 0.152, respectively. The specific situation is shown in Table 2.

[0058] Table 2 Expert weight coefficients

[0059]

[0060] (3) Calculate the probability of the parent node of the Bayesian network model, and convert the expert opinions obtained through the questionnaire into interval type-2 fuzzy numbers based on the corresponding fuzzy probability language. In order to facilitate experts to judge the possibility of events, the present invention adopts seven levels of language terms: "very low (VL)", "low (L)", "generally low (ML)", "medium (M)", "generally high (MH)", "high (H)" and "very high (VH)". Subsequently, expert opinions are aggregated by the improved similarity aggregation method based on interval type-2 fuzzy sets (IT2FS-SAM). Calculate the consistency of each pair of expert opinions The weighted agreement WA(E i ), relative agreement RAD(E i ) and the consensus coefficient CDC(E i ), based on the summary of expert opinions, the defuzzification formula is used to obtain the type II fuzzy number The clarity value Obtain the probability of the parent node, and convert the clear value of the parent node into the failure probability (FAP). The specific process is as follows Figure 4 shown.

[0061] Specifically, we analyze the Concentrating Solar Power Best Practices Study database, An Evaluation of Molten-Salt Power Towers Including Results of the Solar Two Project, and the operating experience of related companies to collect statistics on the failure data of the solar thermal system and obtain the prior probabilities of some nodes. We use the improved SAM method to calculate the prior probabilities of other nodes. The steps are as follows:

[0062] The probability of a node in a certain state is divided into 7 levels. Expert opinions are obtained through questionnaires. In order to reduce the uncertainty and subjectivity of expert judgment, the corresponding fuzzy language is used to convert expert opinions into interval type-2 fuzzy numbers. Interval type-2 fuzzy sets (IT2FS) are often regarded as special cases of type-2 fuzzy sets with z=1, such as Figure 6 The specific language terms and interval type-2 fuzzy numbers are shown in Table 3.

[0063] Table 3 Linguistic terms and their corresponding interval type-2 fuzzy numbers

[0064] Language terminology Interval Type-2 Fuzzy Numbers Very Low (VL) ((0,0,0,0.1；1,1),(0,0,0,0.05；0.9,0.9)) Low (L) ((0,0.1,0.1,0.3；1,1),(0.05,0.1,0.1,0.2；0.9,0.9)) Generally low (ML) ((0.1,0.3,0.3,0.5；1,1),(0.2,0.3,0.3,0.4；0.9,0.9)) Medium (M) ((0.3,0.5,0.5,0.7；1,1),(0.4,0.5,0.5,0.6；0.9,0.9)) Normally high (MH) ((0.5,0.7,0.7,0.9；1,1),(0.6,0.7,0.7,0.8；0.9,0.9)) High (H) ((0.7,0.9,0.9,1；1,1),(0.8,0.9,0.9,1；0.9,0.9)) Very High (VH) ((0.9,1,1,1；1,1),(0.95,1,1,1；0.9,0.9))

[0065] In order to better integrate expert opinions, when there are differences in expert opinions, the expert weights are incorporated into the consistency calculation process through the improved similarity aggregation method (SAM), and the interval type-2 fuzzy numbers are used to reduce the uncertainty and subjectivity of expert opinions. The specific steps of aggregation are as follows: the consistency of different expert opinions is calculated to obtain the similarity matrix.

[0066] a) Randomly select two experts and assume their opinions of expert i and expert j to be Use the similarity metric function to calculate the consistency of each pair of expert opinions

[0067]

[0068] in, is the area of ​​the intersection of two UMFs, is the area of ​​the intersection of the two LMFs.

[0069] like is a set of interval type-2 fuzzy numbers, then it can be expressed as:

[0070]

[0071] In the formula, is the upper membership function (UMF), is the lower membership function (LMF), H1 and H2 represent expert 1 and expert 2 respectively. is the left boundary x value of the upper membership function, represents the x value of the upper membership function, is the right boundary x value of the membership function on the trapezoid, is the vertex y value of the upper membership function, is the left boundary x value of the lower membership function, represents the x-value of the lower membership function, is the right boundary x value of the trapezoidal lower membership function, is the vertex y value of the lower membership function, as shown in Figure 6 shown.

[0072] The similarity of two interval type-2 fuzzy numbers is calculated using the area similarity measure function.

[0073]

[0074] In the formula, for The area of ​​the closed region formed by the UMF and the X-axis, for The area of ​​the closed region formed by the LMF and the X-axis.

[0075] b) Calculate the similarity measure function of each pair of experts and obtain the similarity matrix (CON):

[0076]

[0077] Among them, when i≠j, When i=j, con ij =1.

[0078] c) In order to make the consistency more reasonable, the expert weight is introduced to calculate the expert weighted consistency WA (E i ), and calculate the expert E i The relative agreement RAD(E i )(i=1,2,...,n) and consensus coefficient CDC(E i )(i=1,2,...,n).

[0079]

[0080] CDC(E i )=β·w(E i )+(1-β)·RAD(E i ).

[0081] Among them, β (0≤β≤1) represents the importance of expert agreement relative to relative agreement, usually β is 0.5, w(Ej) is the expert's own weight obtained in Table 2, CON(A i , A j ) represents the similarity between two expert opinions.

[0082] d) The fuzzy opinions of experts are summarized through the consensus coefficient to obtain the aggregated result expressed in the form of interval type-2 fuzzy numbers. The formula is as follows:

[0083]

[0084] e) Defuzzify the aggregation result to obtain a clear value, which represents the possibility of the node. The defuzzification formula is as follows:

[0085]

[0086] In the formula, Type-2 fuzzy number The clarity value, is the left boundary x value of the upper membership function, represents the x value of the upper membership function, is the right boundary x value of the membership function on the trapezoid, is the vertex y value of the upper membership function, is the left boundary x value of the lower membership function, represents the x-value of the lower membership function, is the right boundary x value of the trapezoidal lower membership function, is the vertex y value of the lower membership function, as shown in Figure 6 shown.

[0087] f) Finally, the failure possibility is converted into failure probability (FAP) through the improved conversion formula. The event probability obtained by the improved formula is closer to the probability area defined by the 7-level language variable. The formula is as follows:

[0088]

[0089] Finally, the aggregated fuzzy number, clear value and probability of basic events are obtained, taking the molten salt storage tank as an example, as shown in Table 4:

[0090] Table 4 Experts’ opinions on the parent node of molten salt storage tank damage

[0091]

[0092]

[0093] (4) The relative weight of each parent node is obtained based on the interval type-II fuzzy best-worst method (FBWM) to determine the conditional probability table: a set of standard criteria is established through literature summary and expert interviews, and the criteria with the strongest influence on the target factor is selected as the optimal criterion, and the criteria with the weakest influence is selected as the worst criterion; the optimal criterion is compared with other criteria, and other factors are compared with the worst criteria. Taking the molten salt tank leakage operation factor of expert i as an example, the optimal criterion is frequent start and stop, and the worst criterion is thermal stress. The score of comparing the optimal criterion (frequent start and stop) with other criteria (local overtemperature) is 3, and the score of comparing other factors (thermal shock) with the worst criterion (thermal stress) is 6. Among them, the comparison score level is 1 to 9, 1 means that the criterion is equally important as another criterion, and 9 means that the importance of this criterion and another criterion is at two extremes, which are represented by the corresponding interval type-II fuzzy numbers. In order to make the weighted sum method closer to reality when there are multiple state nodes, the "missing" node is used, and the missing-weighted sum algorithm is adopted to calculate the conditional probability table of the model.

[0094] Specifically, the calculation steps of conditional probability calculation are as follows:

[0095] Expert opinions were combined with the omission-weighted sum algorithm, and the fuzzy best-worst method (FBWM) was used to calculate the relative importance to complete the conditional probability table.

[0096] a) Establish a set of standard criteria through literature summary and expert interviews, and select the criterion with the strongest influence as the best criterion and the one with the weakest influence as the worst criterion for the target factor.

[0097] b) Compare the optimal criteria with other criteria to obtain the judgment matrix A B ; Compare other factors with the worst criteria to obtain the judgment matrix A W .

[0098] A B =(a B1 ,a B2 ,…,a Bn ).

[0099] A W =(a 1W ,a 2W ,…,a nW ) T .

[0100] In the formula, a Bj Indicates that the optimal criterion B is better than criterion j, a BB =1; a jW Indicates that criterion j is better than the worst criterion W, a WW =1. The score ranges from 1 to 9, 1 means that the criterion is equally important to another criterion, and 9 means that the importance of this criterion is at two extremes. Interval type-2 fuzzy numbers are used to represent this criterion, and the specific terms are shown in Table 5.

[0101] Table 5 Linguistic terms and their corresponding interval type-2 fuzzy numbers

[0102] Language terminology Relative importance Interval Type-2 Fuzzy Numbers Equally Important (EI) 1 ((1,1,1,1；1,1),(1,1,1,1；0.9；0.9)) Intermediate value (IV) 2 ((1,2,2,3；1,1),(1.5,2,2,2.5；0.9,0.9)) More important (MMI) 3 ((2,3,3,4；1,1),(2.5,3,3,3.5；0.9,0.9)) Intermediate value (IV) 4 ((3,4,4,5；1,1),(3.5,4,4,4.5；0.9,0.9)) Significantly Important (SMI) 5 ((4,5,5,6；1,1),(4.5,5,5,5.5；0.9,0.9)) Intermediate value (IV) 6 ((5,6,6,7；1,1),(5.5,6,6,6.5；0.9,0.9)) Very important (VSMI) 7 ((6,7,7,8；1,1),(6.5,7,7,7.5；0.9,0.9)) Intermediate value (IV) 8 ((7,8,8,9；1,1),(7.5,8,8,8.5；0.9,0.9)) Extremely Important (EMI) 9 ((8,9,9,10；1,1),(8.5,9,9,9.5；0.9,0.9))

[0103] c) Solve the simultaneous equations to find the optimal solution for all criteria and obtain the relative weight of a single expert.

[0104] minmax{ω BE / ω jE -E BEj |,ω jE / ω EW -E jEW}.

[0105]

[0106] in,

[0107] ω BE represents the optimal criterion, ω EW represents the worst criterion; represents the upper membership function of the optimal criterion, represents the lower membership function; Respectively represent the upper membership function and the lower membership function boundary x value, Represents the boundary y value of the upper membership function; represents the boundary of the upper membership function, The lower membership function boundary.

[0108] d) Aggregate expert opinions to obtain the final conditional probability table.

[0109] After obtaining the weight of each node, the probability distribution of the parent node in the child node is determined by consulting the literature and asking experts for their opinions. In order to express the uncertain causal relationship, the missing node is added on the basis of the traditional weighted sum algorithm.

[0110] Assume that x is the parent node, y is the child node, there are i child nodes and each node has j states, the omission-weighted sum algorithm formula is as follows:

[0111]

[0112] In the formula, ω i Represents the weight of the parent node; ω L represents the weight of the missing node, used to express uncertainty, ω L The higher the value, the higher the uncertainty. S1, S2, ..., Sn represent the node status. The conditional probability table of the failure design factor of the tank foundation is shown in Table 6:

[0113] Table 6 Conditional probability table of tank foundation failure design factors

[0114]

[0115]

[0116] In some embodiments, when executing step 205, the following may be specifically included:

[0117] The constructed Bayesian network model is used for analysis. Through forward causal technology, the specific weight of the parent node influencing factors on the child node accidents can be clarified, and the inhibitory effect of the response measures in preventing accidents can be evaluated. In addition, the model can also calculate the failure probability of the equipment through forward reasoning, and put forward targeted protection suggestions based on this.

[0118] The accident consequence level is constructed using the standard and the actual operating cost of the CSP plant. Expert opinions are collected through questionnaire surveys to complete the accident consequence evaluation of different evolution paths. The expert opinions are fuzzy processed and summarized using interval type-2 fuzzy numbers to obtain the aggregated results expressed in the form of interval type-2 fuzzy numbers. The aggregated results are defuzzified to obtain a clear value for each accident consequence level. After normalization, the evaluation of different levels of accident consequences including direct economic losses, casualties, equipment damage, and environmental pollution can be obtained, thus completing the evaluation of accident consequences.

[0119] Specifically, the accident consequence calculation steps are as follows:

[0120] (1) The accident consequence levels are constructed using the standards and the actual operating costs of CSP plants, which mainly include four types of consequences: direct economic losses, casualties, equipment damage, and environmental pollution. The specific accident consequence levels are shown in Table 7:

[0121] Table 7 Classification of accident consequences

[0122]

[0123]

[0124] (2) Obtain expert opinions through questionnaire survey to complete the accident consequence level evaluation opinions of different evolution paths. Use interval type II fuzzy numbers to fuzzify expert opinions to reduce the uncertainty of evaluation opinions. Finally, summarize the expert fuzzy opinions to obtain the aggregated results expressed in the form of interval type II fuzzy numbers. Defuzzify the aggregated results to obtain clear values. After normalization, the accident consequences including direct economic losses, casualties, equipment damage and environmental pollution can be obtained. The different levels of evaluation are completed. The results are as follows: Figure 7 Using the fuzzy language list in Table 3, questionnaires were distributed to experts. The accident consequence levels, expert opinions and level proportions are shown in Table 8:

[0125] Table 8 Accident consequence levels, expert opinions and level proportions

[0126]

[0127] Based on the same inventive concept, the embodiment of the present application also provides a device for evaluating the consequences of failure of key equipment in a thermal power plant for implementing the above-mentioned method for evaluating the consequences of failure of key equipment in a thermal power plant. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more devices for evaluating the consequences of failure of key equipment in a thermal power plant provided below can refer to the limitations of the method for evaluating the consequences of failure of key equipment in a thermal power plant above, and will not be repeated here.

[0128] In an exemplary embodiment, Figure 8 As shown, a device for evaluating the consequences of failure of key equipment in a solar thermal power station is provided, comprising:

[0129] Data acquisition module 801, used to acquire historical accident data of the CSP plant;

[0130] The model building module 802 is used to summarize and integrate the historical accident data to obtain the key nodes of the accident consequence scenario, and to establish an accident scenario deduction model based on the key nodes; the key nodes include equipment failure influencing factors, equipment failure response measures, and equipment failure node status; the accident scenario deduction model is used to predict the equipment failure consequence through the equipment failure situation;

[0131] A conversion module 803 is used to convert the accident scenario deduction model into a Bayesian network structure; in the Bayesian network structure, each device failure node state is set as a child node, and each device failure influencing factor is set as a parent node;

[0132] The calculation module 804 is used to input the failure impact data of each key equipment to be evaluated into the interval type-2 fuzzy logic reasoning model according to the interval type-2 fuzzy set theory, obtain the relative weight of each parent node, and determine the conditional probability table; the interval type-2 fuzzy logic reasoning model is a model based on the best-worst method of interval type-2 fuzzy; the interval type-2 fuzzy number of the interval type-2 fuzzy is obtained by converting the obtained expert opinions according to the corresponding fuzzy probability language;

[0133] The evaluation module 805 is used to update the Bayesian network structure based on the conditional probability table, calculate the posterior probability of each child node, and evaluate the severity of the consequences of equipment failure.

[0134] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store evaluation results. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for evaluating the consequences of failure of key equipment in a solar thermal power station is implemented.

[0135] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0136] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0137] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0138] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0139] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0140] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, 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 this application.

Claims

1. A method for evaluating the consequences of failure of key equipment in a solar thermal power station, characterized in that: include: Obtain historical accident data of CSP plants; the historical accident data are typical accident cases of special equipment; Summarize and integrate the historical accident data to obtain key nodes of the accident consequence scenario, and establish an accident scenario deduction model based on the key nodes; the key nodes include equipment failure influencing factors, equipment failure response measures, and equipment failure node status; The accident scenario deduction model is used to predict the consequences of equipment failure through equipment failure conditions; Converting the accident scenario deduction model into a Bayesian network structure; According to interval type-2 fuzzy set theory, the failure impact data of each key equipment to be evaluated is input into the interval type-2 fuzzy logic reasoning model to obtain the relative weight of each parent node and determine the conditional probability table; the interval type-2 fuzzy logic reasoning model is a model based on the best-worst method of interval type-2 fuzzy; the interval type-2 fuzzy number of the interval type-2 fuzzy is obtained by converting the obtained expert opinions according to the corresponding fuzzy probability language; Based on the conditional probability table, the Bayesian network structure is updated, and the posterior probability of each child node is calculated to evaluate the severity of the consequences of equipment failure.

2. A method for evaluating the consequences of failure of key equipment in a CSP plant according to claim 1, characterized in that: The equipment failure influencing factors are the direct causes of equipment failure, and the equipment failure influencing factors include key equipment design factors, key equipment manufacturing factors, key equipment installation factors, key equipment operation factors and full life cycle factors of key equipment maintenance.

3. A method for evaluating the consequences of failure of key equipment in a CSP plant according to claim 1, characterized in that: Special equipment includes absorbers, salt pipelines, molten salt storage tanks and molten salt heat exchangers.

4. The method for evaluating the consequences of failure of key equipment in a CSP power station according to claim 1, characterized in that: The accident scenario deduction model is converted into a Bayesian network structure, specifically including: The target events that need to be evaluated in the accident scenario deduction model are determined as child nodes, and the influencing factors in the accident scenario deduction model are taken as parent nodes to construct a Bayesian network structure; the target events that need to be evaluated include freezing and cracking of the absorber; and the influencing factors include small salt filling amount and large transient temperature fluctuations.

5. The method for evaluating the consequences of failure of key equipment in a CSP power station according to claim 1, characterized in that: According to the interval type-2 fuzzy set theory, the failure impact data of each key equipment to be evaluated is input into the interval type-2 fuzzy logic reasoning model to obtain the relative weight of each parent node and determine the conditional probability table, which specifically includes: For each expert, the expert opinions are converted into interval type-2 fuzzy numbers according to fuzzy probability language; Based on the similarity aggregation method of interval type-2 fuzzy sets, the experts' opinion consistency, weighted consistency, relative consistency and consensus coefficient are aggregated to obtain the summary result of expert opinions; The summary results of expert opinions were combined with the omission-weighted sum algorithm, and the relative importance was calculated using the fuzzy best-worst method to complete the conditional probability table.

6. A method for evaluating the consequences of failure of key equipment in a CSP power station according to claim 5, characterized in that: The expert opinions are converted into interval type-2 fuzzy numbers according to fuzzy probability language, including: The probability of an event occurring is described as very low, low, generally low, medium, generally high, high and very high interval type-2 fuzzy numbers ((0, 0, 0, 0.1; 1, 1), (0, 0, 0, 0.05; 0.9, 0.9)), ((0, 0.1, 0.1, 0.3; 1, 1), (0.05, 0.1, 0.1, 0.2; 0.9, 0.9)), ((0.1, 0.3, 0.3, 0.5; 1, 1), (0.2, 0.3, 0.3, 0.4; 0.9, 0.9)), ((0.3, 0.5, 0.5, 0.7; 1, 1), (0.4, 0.5, 0.5, 0.6; 0.9, 0.9)), ((0.5, 0.7, 0.7, 0.9; 1, 1), (0.6, 0.7, 0.7, 0.8; 0.9, 0.9)), ((0.7, 0.9, 0.9, 1; 1, 1), (0.8, 0.9, 0.9, 1; 0.9, 0.9)) and ((0.9, 1, 1, 1; 1, 1), (0.95, 1, 1, 1; 0.9, 0.9)).

7. The method for evaluating the consequences of failure of key equipment in a CSP power station according to claim 1, characterized in that: The expert opinions are converted into interval type-2 fuzzy numbers based on fuzzy probability language, including: The linguistic terms of equal importance, intermediate value, relatively important, intermediate value, obviously important, intermediate value, very important, intermediate value and extremely important are described one by one as interval type-2 fuzzy numbers ((1,1,1,1; 1,1), (1,1,1,1; 0.9; 0.9)), ((1,2,2,3; 1,1), (1.5,2,2,2.5; 0.9, 0.9)), ((2,3,3,4; 1,1), (2.5,3,3,3.5; 0.9, 0.9)), ((3,4,4,5; 1,1), (3.5,4,4,4.5; 0.9, 0.9)). .9, 0.9)), ((4,5,5,6; 1,1), (4.5,5,5,5.5; 0.9, 0.9)), ((5,6,6,7; 1,1), (5.5,6,6,6.5; 0.9, 0.9)), ((6,7,7,8; 1,1), (6.5,7,7,7.5; 0.9, 0.9)), ((7,8,8,9; 1,1), (7.5,8,8,8.5; 0.9, 0.9)), and ((8,9,9,10; 1,1), (8.5,9,9,9.5; 0.9, 0.9)).

8. A device for evaluating the consequences of failure of key equipment in a solar thermal power station, characterized in that: include: A data acquisition module is used to acquire historical accident data of a CSP plant; the historical accident data are typical accident cases of special equipment; A model building module is used to summarize and integrate the historical accident data, obtain the key nodes of the accident consequence scenario, and establish an accident scenario deduction model based on the key nodes; the key nodes include equipment failure influencing factors, equipment failure response measures, and equipment failure node status; The accident scenario deduction model is used to predict the consequences of equipment failure through equipment failure conditions; A conversion module, used to convert the accident scenario deduction model into a Bayesian network structure; in the Bayesian network structure, each device failure node state is set as a child node, and each device failure influencing factor is set as a parent node; The calculation module is used to input the failure impact data of each key equipment to be evaluated into the interval type-2 fuzzy logic reasoning model according to the interval type-2 fuzzy set theory, obtain the relative weight of each parent node, and determine the conditional probability table; the interval type-2 fuzzy logic reasoning model is a model based on the best-worst method of interval type-2 fuzzy; the interval type-2 fuzzy number of the interval type-2 fuzzy is obtained by converting the obtained expert opinions according to the corresponding fuzzy probability language; The evaluation module is used to update the Bayesian network structure based on the conditional probability table, calculate the posterior probability of each child node, and evaluate the severity of the consequences of equipment failure.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for evaluating the consequences of failure of key equipment in a solar thermal power station as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a method for evaluating the consequences of failure of key equipment in a solar thermal power station according to any one of claims 1 to 7 is implemented.

Images