CN112036568B - Intelligent diagnosis method for damage faults of primary loop coolant system of nuclear power device - Google Patents
Intelligent diagnosis method for damage faults of primary loop coolant system of nuclear power device Download PDFInfo
- Publication number
- CN112036568B CN112036568B CN202010659408.5A CN202010659408A CN112036568B CN 112036568 B CN112036568 B CN 112036568B CN 202010659408 A CN202010659408 A CN 202010659408A CN 112036568 B CN112036568 B CN 112036568B
- Authority
- CN
- China
- Prior art keywords
- state
- meta
- proposition
- rule
- coolant system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- G—PHYSICS
- G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
- G21C—NUCLEAR REACTORS
- G21C17/00—Monitoring; Testing ; Maintaining
- G21C17/002—Detection of leaks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
- Y02E30/30—Nuclear fission reactors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Plasma & Fusion (AREA)
- High Energy & Nuclear Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Monitoring And Testing Of Nuclear Reactors (AREA)
Abstract
The invention discloses an intelligent diagnosis method for damage faults of a primary loop coolant system of a nuclear power device, which comprises the following steps: setting a failure diagnosis rule of a primary loop coolant system of the nuclear power device, and generating a knowledge matrix according to the diagnosis rule, wherein the knowledge matrix comprises a state vector P, an input transformation matrix I, an output transformation matrix O and a transfer trigger vector DT; and acquiring parameter signals corresponding to each element proposition in the diagnosis rules in real time according to the diagnosis rules, determining the state of each element proposition according to the parameter signals, assigning the state to a state vector P, performing fault diagnosis reasoning calculation according to a knowledge matrix, judging whether the obtained result is true, if so, indicating that the primary loop coolant system of the primary loop of the nuclear power device is damaged, and if not, indicating that the primary loop coolant system of the primary loop of the nuclear power device is not damaged. The invention realizes the parallel reasoning of the diagnosis process through matrix operation, thereby realizing the online intelligent diagnosis of the damage fault of the primary loop coolant system of the nuclear power device.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis of nuclear power devices, and particularly relates to an online intelligent diagnosis method for a primary loop main coolant system damage fault generated in the operation process of a pressurized water reactor nuclear power device.
Background
It is counted that more than half of the operation events occurring in the nuclear power stations in the world are related to misoperation and misjudgment of operators. The main reasons for causing misoperation and misjudgment of operators are the complexity of the nuclear power plant and the huge psychological stress generated by operators in the event of accidents. At present, the judgment of the operation fault of the nuclear power plant is mainly carried out by operators through observing operation parameters and changes thereof according to the mastered knowledge and experience. To reduce or even avoid misjudgment and misoperation, an effective technical means is to provide real-time online automatic diagnosis capability of operation faults for operators in a nuclear power plant instrument control system.
The failure of the primary coolant system of the primary loop refers to the accident that the pressure boundary of the primary coolant system of the primary loop is broken and the coolant leaks due to the damage of the pipeline of the primary coolant system of the primary loop of the pressurized water reactor nuclear power plant, the valves and the like. The accident has a high probability of occurrence, and if the accident cannot be found in time, serious consequences can be caused.
A nuclear power plant is a complex nonlinear, strongly coupled dynamic time-varying system. The fault on-line intelligent diagnosis system realizes the automatic analysis and processing of the change condition of the operation parameters of the nuclear power device, and assists an operator to accurately and timely judge the operation state of the nuclear power device and the occurrence of faults so as to take correct disposal measures. Common fault diagnosis techniques can be divided into three major categories, mechanism model-based, data-driven, and knowledge rule-based.
The fault diagnosis method based on the mechanism model needs to establish an accurate mechanism or mathematical model of the diagnosed object. However, the nuclear power plant is extremely complex, and the characteristics of the nuclear power plant can change to a certain extent along with the use and equipment aging, so that the establishment of an accurate and complete mechanism model or mathematical model under normal and accident working conditions is difficult, and the operation time is long, so that the method has a large gap from the requirements of practical application in terms of instantaneity and accuracy.
The implementation basis of the data-driven fault diagnosis method is to have a large amount of sample data under normal and fault states of the diagnosed equipment. Because the nuclear power plant has high risk in a fault state, an operation data sample in the fault state cannot be obtained through experiments, and the operation data sample can be obtained through analog simulation only, but the reality degree is limited. Therefore, although there are many theoretical research results in recent years, the data-driven fault diagnosis method has a large gap from the practical application requirements for the realizability and accuracy of the operation fault diagnosis of the nuclear power plant.
People accumulate rich operation experience in the long-term operation process of the nuclear power plant, and can form rich and complete fault judgment rules by combining theoretical analysis. Therefore, the adoption of an artificial intelligence technology based on knowledge, namely an expert system, for realizing the automatic diagnosis of the operation faults of the nuclear power plant is a practical and feasible technical approach. A practical fault on-line automatic diagnostic expert system is needed to solve two problems: firstly, how to convert the fault judgment rule in the form of natural language into an expression form suitable for computer program language; and secondly, the real-time performance of the fault judgment and reasoning process is effectively ensured.
Traditional expert systems are based on production rules, which are consistent with the summary and expression modes of experience knowledge of people, are easy to understand, and are often complicated to express in a programming language. In addition, the inference engine of the traditional expert system performs serial inference according to rule combination, and when the rule is complex, the search efficiency is low and the inference speed is low. When knowledge rules are more, problems such as rule conflict and reasoning circulation can also occur.
The invention comprises the following steps:
in order to overcome the defects of the background technology, the invention provides a method which can convert the knowledge of the failure diagnosis rules of the primary coolant system of the primary loop of the pressurized water reactor nuclear power plant based on natural language into a knowledge matrix which is easy to store and express by a computer, and realize parallel reasoning of the diagnosis process through matrix operation, thereby realizing rapid and automatic diagnosis of the failure of the primary coolant system of the primary loop of the nuclear power plant.
The technical scheme adopted by the invention for solving the technical problems is as follows:
an intelligent diagnosis method for a damage fault of a primary loop coolant system of a nuclear power device, comprising the following steps:
setting a failure diagnosis rule of a primary loop coolant system of the nuclear power device, and generating a knowledge matrix according to the diagnosis rule, wherein the knowledge matrix comprises a state vector P, an input transformation matrix I, an output transformation matrix O and a transfer trigger vector DT; and acquiring parameter signals corresponding to each element proposition in the diagnosis rule in real time, determining the state of each element proposition according to the parameter signals, assigning the state to a state vector P, performing fault diagnosis reasoning calculation according to a knowledge matrix, and judging whether the obtained result is true, if so, indicating that the primary loop coolant system of the nuclear power device is damaged, and if not, indicating that the primary loop coolant system of the nuclear power device is not damaged.
Preferably, the primary circuit coolant system breakage fault diagnosis rules for the nuclear power plant include:
rule one, if p 1 and p 6 and p 5 then p 10 ；
Rule two, if rule one is satisfied and If p 9 and p 8 and p 4 and p 3 and p 2 and p 10 then p 11 ；
Rule III, if rule II is true or If p 7 then p 11 ；
Wherein, the meta proposition p 1 When the state of (1) is 1, the average temperature of a loop is not reduced, and the meta-proposition p is 1 Indicating a drop in average temperature of a loop when the state of (2) is 0;
meta proposition p 2 When the state of (1) is 1, the second-circuit water dosage is not out of standard, and the meta-proposition p 2 When the state of (2) is 0, the second-circuit water dosage exceeds the standard;
meta proposition p 3 When the state of (1) is 1, the safety valve of the voltage stabilizer is not opened, and the meta proposition p 3 When the state of (2) is 0, the safety valve of the voltage stabilizer is opened;
meta proposition p 4 When the state of (1) indicates that the release valve of the voltage stabilizer is not opened, meta proposition p 4 When the state of (2) is 0, the release valve of the voltage stabilizer is opened;
meta proposition p 5 When the state of (1) is 1, the water level of the voltage stabilizer is reduced, and the meta proposition p is that 5 When the state of (2) is 0, the water level of the voltage stabilizer is not reduced;
meta proposition p 6 When the state of (1) is 1, the primary proposition p indicates that the drainage valve of the loop is not opened 6 When the state of (2) is 0, the drainage valve of the primary circuit is opened;
meta proposition p 7 When the state of (1) is 1, the alarm indicates that the dosage of the containment is high, p 7 When the state of (2) is 0, the dose of the non-containment vessel is high, and an alarm is given;
meta proposition p 8 When the state of (1) is 1, the high alarm of the cooling water without equipment is shown, p 8 When the state of (1) is 0, indicating that the equipment cooling water agent is high, and giving an alarm;
meta proposition p 9 When the state of (1) is 1, the auxiliary system is alarmed without leakage, p 9 When the state of (2) is 0, the auxiliary system has leakage alarm;
meta proposition p 10 When the state of (1) is 1, the pressure boundary of a loop is broken, p 10 When the state of (2) is 0, the pressure boundary of the first circuit is not broken;
meta proposition p 11 When the state of (1) is 1, the failure of the primary coolant system of the primary circuit is indicated, p 11 When the state of (2) is 0, the primary coolant system of the primary circuit is not broken.
Preferably, the parameter signals corresponding to each meta-proposition in the diagnosis rule include: the device comprises a primary loop average temperature, a secondary loop water dosage high alarm signal, a safety valve discharge pipe temperature high alarm signal, a release valve discharge pipe temperature high alarm signal, a pressure stabilizer water level, a primary loop drain valve opening state signal, a safety shell dosage high alarm signal, a device cooling water dosage high alarm signal and other auxiliary system leakage alarm signals.
Preferably, the method for generating the state vector P includes: the elements of the state vector P correspond to the current state of all the meta-propositions in the rule, the meta-propositions being ordered in the order in which they appear in sequence in the three rules and not repeated, the final conclusion meta-propositions being arranged last in the vector P,
P＝[p 1 ，p 6 ，p 5 ，p 10 ，p 9 ，p 8 ，p 4 ，p 3 ，p 2 ，p 7 ，p 11 ]。
preferably, the method for generating the transition trigger vector DT includes:
element DT [ i ] in transition trigger vector DT]The value of (2) is the ith transition t i Corresponding condition element propositionThe number is a row vector, and the dimension corresponds to the number of transitions, i.e. the number of diagnostic rules; the number of conditional meta-propositions in rule one is 3, DT 1]=3; the number of conditional meta-propositions in rule two is 6, DT 2]=6; the number of conditional meta-propositions in rule three is 1, DT 3]=1; transfer trigger vector dt= [3,6,1]]。
Preferably, the method for generating the input transformation matrix I comprises:
the rows in the input transformation matrix I correspond to 11-element propositions in a primary coolant system breakage fault diagnosis rule for a circuit; the columns correspond to three of rule one, rule two and rule three; the ordering of the rows in the input transformation matrix I is exactly the same as the ordering of the meta-propositions in P. The ordering of the columns is exactly the same as the ordering of the branches.
Preferably, the method for generating the output transformation matrix o comprises:
the rows in the output transformation matrix O correspond to three transitions in rule one, rule two and rule three, and the columns correspond to 11 element propositions and are strictly consistent with the element propositions in P.
Preferably, according to the read input signal value of the corresponding parameter of each element proposition of the state vector P, the state of each element proposition in P is obtained, and is assigned to the state vector P, and the method for performing fault diagnosis reasoning calculation according to the knowledge matrix comprises the following steps:
(1) Acquiring the initial state of each element proposition in the state vector P according to the read input signals, and assigning the initial state to the initial state vector P 0 Let p=p 0 ；
(2) Calculating P×I, and correcting the P×I result according to DT to obtain T;
(3) Calculating T X O, correcting elements larger than 1 in the T X O result to be 1, and assigning the obtained result to S;
(4) Calculation of S+P 0 Will S+P 0 The result of (2) is assigned to S;
(5) If P is not equal to S, making P=S, and going to the step (2) for circulation; if P=S, the numerical value of the corresponding element P11 of the conclusion meta-proposition in P is obtained, if the numerical value is equal to 1, the result is expressed as true, and the failure of the damage of the loop coolant system is judged; otherwise, it is determined that no failure of the primary coolant system has occurred.
The invention has the beneficial effects that: the invention provides a practical, efficient and convenient fault diagnosis knowledge expression and reasoning method for diagnosing the damage faults of a primary coolant system of a primary loop of a nuclear power device. The fault diagnosis rule knowledge expression system based on the meta proposition and the knowledge matrix and the parallel reasoning algorithm based on the matrix operation are designed, so that the expression and storage of diagnosis rule knowledge in a computer are greatly facilitated, the speed of a diagnosis reasoning process can be greatly improved, the technical bottleneck that the reasoning speed is rapidly reduced due to the fact that a traditional expert system is increased along with the rule is overcome, and the instantaneity and the realizability of the online intelligent diagnosis system for the damaged faults of the primary coolant system of the primary loop of the nuclear power device are ensured.
The fault diagnosis knowledge matrix-based nuclear power plant primary loop coolant system failure fault diagnosis expert knowledge expression system is convenient for computer storage, calling and expansion, and convenient for rule conflict and dead cycle detection; the designed reasoning algorithm based on knowledge matrix operation can transform a complex logic reasoning process into simple matrix operation and has parallel reasoning capability. The method is applied to the fault diagnosis of the primary loop coolant system of the nuclear power device, can greatly facilitate the expression and storage of diagnosis knowledge, improve the operation efficiency of a fault diagnosis expert system, and realize the complete stripping of an inference algorithm and data, thereby being easy to continuously expand new knowledge rules in the use process, leading the capability of the fault diagnosis system to be continuously perfected and enhanced, and having good expandability.
Drawings
FIG. 1 is a schematic diagram of a pressurized water reactor nuclear power plant system;
FIG. 2 is a flow chart illustrating a primary loop coolant system breakage fault determination process in accordance with an embodiment of the present invention;
FIG. 3 is a knowledge matrix initialization process according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating the operation fault diagnosis of the nuclear power plant according to the embodiment of the invention;
FIG. 5 is a flowchart of an algorithm for fault diagnosis using the knowledge matrix according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and examples.
(1) Forming a primary coolant system breakage fault diagnosis rule knowledge matrix of a pressurized water reactor nuclear power plant primary loop
The pressurized water reactor nuclear power plant is shown in fig. 1, the primary coolant system breakage fault determination process of the primary loop is shown in fig. 2, and the diagnostic rules are generated as follows:
if ((average primary circuit temperature not lowered and primary circuit drain valve not opened and primary circuit drain valve continuously lowered and no equipment cooling water level high alarm and auxiliary system leak-free alarm and primary circuit drain valve not opened and primary circuit drain valve not exceeded) or containment case dosage high alarm) then primary circuit coolant system breakage.
A fault diagnosis expert knowledge expression system based on a knowledge matrix achieves the aim of easily expressing and storing a fault diagnosis knowledge computer of a primary coolant system failure of a primary loop of a nuclear power device by defining model elements and designing a knowledge matrix generation method, and lays a foundation for realizing automatic diagnosis of operation faults.
1) Definition of knowledge matrix constituent elements
a. Proposition of the element
The resulting rule-form of knowledge of a failure diagnosis of a primary circuit coolant system of a nuclear power plant can be expressed as:
If(p 1 and p 2 …)or(p 3 and p 4 …)……,then A
wherein p is 1 、p 2 、p 3 … …, etc. are conditional propositions, a is a conclusion proposition.
Proposition p i The structure of (a) is generally a condition that a certain parameter is greater than, less than or equal to a certain value (e.g., a circuit average temperature is not reduced), or whether a certain device state has a certain phenomenon, an attribute (e.g., a circuit drain valve is not opened), etc. These propositions are only "true"Or "false" two states, which are defined herein as "meta-propositions". Conclusion proposition a is also one of the meta propositions, being "primary coolant system breakage for one circuit".
"meta proposition" refers to the smallest logical judgment unit in the rule knowledge generated by fault diagnosis. It is no longer resolvable into a combination of two or more logical decisions. It can be input meta-proposition and conclusion meta-proposition (usually with specific physical meaning, such as that the average temperature of a loop is higher than 300 ℃, or the drain valve is opened, etc.), or can be intermediate result of logic reasoning (i.e. intermediate meta-proposition may not have specific physical meaning), p is used i And (3) representing.
The meta-proposition of the rules for generating the fault diagnosis knowledge of the primary coolant system breakage of the primary circuit of the nuclear power plant is determined as shown in table 1.
TABLE 1 definition table of primary loop coolant system breakage fault diagnosis rules meta proposition
In Table 1, p 10 Is an intermediate meta proposition, which has physical meaning here, namely: a break appears at the pressure boundary of the first circuit; p is p 11 Is a conclusion meta-proposition, and the others are input meta-propositions.
b. Diagnostic knowledge generation rules
Based on the meta-proposition definition of table 1, the rules for generating the primary coolant system breakage fault diagnosis knowledge for a loop can be symbolized as:
rule one: if p 1 and p 6 and p 5 then p 10 ；
Rule II: if p 9 and p 8 and p 4 and p 3 and p 2 and p 10 then p 11 ；
Rule III: or Ifp 7 then p 11 。
The above rules can be categorized into two categories, namely (1) if the rule head starts with an "or", it means that the rule is in an "or" relationship with other rules; (2) If the rule header starts directly with an "if," it indicates that the rule is an "AND" relationship with other rules.
For the three rules described above, it can be seen that each rule has an inference conclusion, i.e., contains a "then" character. In addition, each rule has at most one or operator, and if a plurality of or operators exist, the plurality of or operators can be split into a plurality of rules.
c. Status of
Judgment result of finger element proposition. The value of which adopts alpha (p i ) It is indicated that the values of 1 and 0 are two. When the judgment result of a meta proposition is true, the state value is 1, otherwise, the state value is 0. The state value of the condition element proposition depends on the judging result of the operation parameters (or the operation state of equipment and the like) of the nuclear power plant contained in the condition element proposition at the current moment, and the state value of the conclusion or intermediate element proposition depends on the logic operation result of the precursor element proposition.
d. State vector P
The elements of the state vector P correspond to the current state of all meta-propositions in the rule. The ranking is that other meta-propositions are ranked in order of appearance in the rule except that the conclusion meta-propositions are ranked at the end of the vector P. If there are meta-propositions that occur multiple times in each rule, then the elements in P are arranged in the order of the first occurrence and there are no duplicates.
An element value of 1 in the vector represents the meta-proposition p corresponding to the element i Is true, the state of the meta-proposition is activated (i.e., alpha (p i ) =1); the element value is 0, then the reverse (i.e., alpha (p) i ) =0). To simplify expression, p is used directly in subsequent definitions and calculations i State value alpha (p) representing its corresponding meta-proposition i )。
For a loop primary coolant system breakage fault diagnosis rule, there are 11 states of meta-propositions (states containing 9 input meta-propositions, 1 intermediate meta-propositions, and 1 conclusion meta-propositions). The state vector is:
P＝[p 1 ，p 6 ，p 5 ，p 10 ，p 9 ，p 8 ，p 4 ，p 3 ，p 2 ，p 7 ，p 11 ] (1)
e. transfer of
The transition represents a logical AND operation, which means that the state of a certain intermediate element proposition or conclusion element proposition changes in the diagnosis and reasoning process. A transition may have 1 or more conditional element propositions (inference logical conditions, which may be input element propositions, which may be intermediate element propositions), and 1 result element propositions (inference logical results, which may be intermediate element propositions, which may be final conclusion element propositions). When the state of all conditional meta-propositions of a certain transition is 1, the transition is triggered, and the state of the conclusion meta-propositions becomes 1, which indicates that the transition has occurred. Transfer uses t i And (3) representing.
The "then" in a rule represents a "state transition". For failure diagnosis of the primary coolant system of the primary circuit, 3 rules are provided, corresponding to three transfer t respectively 1 、t 2 、t 3 。
f. Transfer trigger vector DT
Element DT [ i ] in transition trigger vector DT]The value of (2) is the ith transition t i The number of corresponding input meta-propositions. Is a row vector, and the dimension corresponds to the number of branches, i.e., the number of diagnostic rules.
For a primary loop coolant system breakage fault diagnosis rule, the transition trigger vector DT is:
DT＝[3,6,1] (2)
g. input transformation matrix I
The rows in the input transformation matrix I correspond to 11-element propositions in a primary coolant system breakage fault diagnosis rule for a circuit; columns correspond to 3 branches in the inference rule. A certain element value in the matrix I is 1, which indicates that the element proposition corresponding to the row where the element is located is the transferred input element proposition corresponding to the column where the element is located; and if the value of a certain element is 0, the element proposition corresponding to the row of the element is not the transferred input element proposition corresponding to the column of the element.
The ordering of the rows in the input transformation matrix I should be exactly the same as the ordering of the meta-propositions in P. The ordering of the columns is exactly the same as the ordering of the branches.
For a broken fault diagnosis rule of a primary coolant system of a loop, the input transformation matrix I is as follows:
h. output transformation matrix O
The rows in the output transformation matrix o correspond to 3 transitions in the reasoning rules and the columns correspond to 11 meta-propositions in the reasoning rules. A certain element value is 1, which indicates that the element proposition corresponding to the column of the element is the transferred output element proposition corresponding to the row of the element; and when the value of a certain element is 0, the element proposition corresponding to the column of the element is not the transferred output element proposition corresponding to the row of the element.
The order of the columns in the output transformation matrix o should be exactly the same as the order of the meta-proposition in P. The ordering of the rows is exactly the same as the ordering of the branches.
For a failure diagnosis rule of a primary coolant system failure of a primary circuit, the output transformation matrix o is:
2) Knowledge matrix for diagnosing breakage fault of primary coolant system of one loop
Under the premise of the definition, the state vector P, the input transformation matrix I, the output transformation matrix O and the transfer trigger vector DT jointly form a knowledge matrix N= { P, I, O, DT } of the knowledge network model of the fault diagnosis rule, and the input condition and the reasoning logic of the knowledge of the fault diagnosis rule are completely expressed. The knowledge matrix expression mode only needs to store 4 vectors or matrices in a computer, so that the storage capacity requirement of the computer on diagnosis knowledge is greatly reduced, and a foundation is laid for a follow-up knowledge matrix-based reasoning algorithm.
In the implementation process of the diagnosis method, firstly, the knowledge matrix is generated according to the diagnosed nuclear power device constitution and the knowledge of a fault diagnosis expert of a loop main coolant system, and is stored in a knowledge base of a diagnosis system to finish the initialization work of the diagnosis system. The initialization flow is shown in fig. 3. This is typically done before the diagnostic system is put into service and a knowledge matrix of diagnostic rules for new fault types can be added continuously during use.
(2) Fault diagnosis reasoning process based on matrix operation
The operation fault diagnosis process of the nuclear power plant is to collect the required signals according to a certain time period, and perform repeated cycle of fault judgment through diagnosis and reasoning calculation, as shown in fig. 4.
The invention converts the fault diagnosis process which is inferred one by one according to the generated diagnosis rules into a simple and efficient processing process based on knowledge matrix operation, and can greatly improve the operation efficiency of a fault diagnosis expert system, thereby meeting the real-time requirement of the operation fault diagnosis of the nuclear power device.
After the knowledge matrix n= { P, I, O, DT } of the primary coolant system failure fault diagnosis of the primary circuit of the nuclear power plant is established, the steps of the reasoning algorithm for performing fault diagnosis by using the knowledge matrix n= { P, I, O, DT } are shown in fig. 5.
According to the definition of the primary coolant system breakage fault diagnosis rule meta proposition and the signals to be collected, which are determined in table 1, two test working conditions of fault occurrence and fault non-occurrence are respectively set for verifying the actual application effect. The initial state of each meta-proposition under both conditions is shown in table 2.
Table 2 initial state table of primary coolant system failure diagnosis meta-proposition for primary circuit under two conditions
As previously described.
For a broken fault of a primary coolant system of a loop, a knowledge matrix N= { P, I, O, DT } of a diagnosis rule is constructed in the initialization process, wherein the knowledge matrix N= { P, I, O, DT } is as follows:
state vector p= [ P ] 1 ，p 6 ，p 5 ，p 10 ，p 9 ，p 8 ，p 4 ，p 3 ，p 2 ，p 7 ，p 11 ]
Input transformation matrix:
outputting a transformation matrix:
transfer trigger vector dt= [3,6,1].
The following specifically describes the diagnosis, reasoning and calculation process in the implementation process of diagnosing the breakage fault of the primary coolant system in a loop under two test conditions:
step 1, reading the running parameters of the nuclear power plant, determining the initial activation state of each element proposition according to the values of the running parameters, and assigning an initial value to the state vector P, wherein the assignment method comprises the following steps: the first element of the P vector is meta-proposition P 1 I.e. "average temperature of the primary loop does not drop". During diagnosis, firstly, the average temperature of a loop at the current moment is read and compared with the value at the previous moment, if the average temperature is not reduced, the meta proposition p 1 If true, the first element of the P vector is assigned a value of 1; if it falls, meta-proposition p 1 For false, the first element of the P vector is assigned a value of 0. Other element assignment processes analogize:
assume the working condition is as follows: p= [1,1,1,0,1,1,1,1,1,1,0];
under the second working condition: p= [1,1,1,0,1,1,1,1,0,0,0];
and step 2, carrying out reasoning operation and outputting a reasoning conclusion.
a. Working condition one calculation step:
(1) based on the input signal as initial state vector P 0 Assignment, P 0 ＝[1，1，1，0，1，1，1，1，1，1，0]Let p=p 0 ；
(2) T=p×i= [3,5,1], corrected according to DT to t= [1,0,1];
③S＝T×O＝[0，0，0，1，0，0，0，0，0，0，1]calculate s=s+p 0 ＝[1，1，1，1，1，1，1，1，1，1，1]With S not equal to P, reasoning is incomplete, and intermediate node P is updated 10 Is a state of (2). Let p=s= [1,1,1,1,1,1,1,1,1,1,1 ]]Entering the next cycle;
(4) t=p×i= [3,6,1], corrected according to DT to t= [1, 1];
(5) s=txo= [0,0,0,1,0,0,0,0,0,0,2], for elements with values greater than 1, it means that there are multiple transitions occurring upstream of the node, and since an or operation occurs, there is a transition occurrence, and the state of the proposition of the downstream element changes, so the element with value greater than 1 in S is corrected to 1, and s= [0,0,0,1,0,0,0,0,0,0,1];
calculate s=s+p 0 ＝[1，1，1，1，1，1，1，1，1，1，1]There is s=p and reasoning is complete. Corresponding element P11 of conclusion meta-proposition in P]=1, output diagnostic conclusion: a circuit primary coolant system failure occurs.
b. And a working condition II calculating step:
(1) based on the input signal as initial state vector P 0 Assignment, P 0 ＝[1，1，1，0，1，1，1，1，0，0，0]Let p=p 0 ；
(2) T=p×i= [3,4,0], corrected according to DT to t= [1, 0];
③S＝T×O＝[0，0，0，1，0，0，0，0，0，0，0]calculate s=s+p 0 ＝[1，1，1，1，1，1，1，1，0，0，0]With S not equal to P, reasoning is incomplete, and intermediate node P is updated 10 Is a state of (2). Let p=s= [1,1,1,1,1,1,1,1,0,0,0 ]]Entering the next cycle;
(4) t=p×i= [3,5,0], corrected according to DT to t= [1, 0];
⑤S＝T×O＝[0，0，0，1，0，0，0，0，0，0，0]；
calculate s=s+p 0 ＝[1，1，1，1，1，1，1，1，0，0，0]There is s=p and reasoning is complete. Corresponding element P11 of conclusion meta-proposition in P]=0, outputting diagnostic conclusion: failure of the primary coolant system of the circuit did not occur.
It can be seen that the reasoning conclusion is consistent with the working condition preset conclusion.
This example verifies the correctness of the algorithm.
It will be understood that modifications and variations will be apparent to those skilled in the art from the foregoing description, and it is intended that all such modifications and variations be included within the scope of the following claims.
Claims (7)
1. An intelligent diagnosis method for a damage fault of a primary loop coolant system of a nuclear power device is characterized by comprising the following steps:
setting a failure diagnosis rule of a primary loop coolant system of a nuclear power device, and generating a knowledge matrix according to the diagnosis rule, wherein the knowledge matrix comprises a state vector P, an input transformation matrix I, an output transformation matrix O and a transfer trigger vector DT; acquiring parameter signals corresponding to each element proposition in the diagnosis rule in real time, determining the state of each element proposition according to the parameter signals, assigning the state to the state vector P, performing fault diagnosis reasoning calculation according to the knowledge matrix, and judging whether the obtained result is true, if so, indicating that the primary loop coolant system of the nuclear power plant is damaged, and if not, indicating that the primary loop coolant system of the nuclear power plant is not damaged;
the primary coolant system breakage fault diagnosis rule of the primary loop of the nuclear power plant comprises:
rule one: if p 1 and p 6 and p 5 then p 10 ；
Rule II: if rule one is satisfied and If p 9 and p 8 and p 4 and p 3 and p 2 and p 10 then p 11 ；
Rule III: if the rule two is satisfied or If p 7 then p 11 ；
Wherein, the meta proposition p 1 When the state of (1) is 1, the average temperature of a loop is not reduced, and the meta-proposition p is 1 Indicating a drop in average temperature of a loop when the state of (2) is 0;
meta proposition p 2 When the state of (1) is 1, the second-circuit water dosage is not out of standard, and the meta-proposition p 2 When the state of (2) is 0, the second-circuit water dosage exceeds the standard;
meta proposition p 3 When the state of (1) is 1, the safety valve of the voltage stabilizer is not opened, and the meta proposition p 3 When the state of (2) is 0, the safety valve of the voltage stabilizer is opened;
meta proposition p 4 When the state of (1) indicates that the release valve of the voltage stabilizer is not opened, meta proposition p 4 When the state of (2) is 0, the release valve of the voltage stabilizer is opened;
meta proposition p 5 When the state of (1) is 1, the water level of the voltage stabilizer is reduced, and the meta proposition p is that 5 When the state of (2) is 0, the water level of the voltage stabilizer is not reduced;
meta proposition p 6 When the state of (1) is 1, the primary proposition p indicates that the drainage valve of the loop is not opened 6 When the state of (2) is 0, the drainage valve of the primary circuit is opened;
meta proposition p 7 When the state of (1) is 1, the alarm indicates that the dosage of the containment is high, p 7 When the state of (2) is 0, the dose of the non-containment vessel is high, and an alarm is given;
meta proposition p 8 When the state of (1) is 1, the high alarm of the cooling water without equipment is shown, p 8 When the state of (1) is 0, indicating that the equipment cooling water agent is high, and giving an alarm;
meta proposition p 9 When the state of (1) is 1, the auxiliary system is alarmed without leakage, p 9 When the state of (2) is 0, the auxiliary system has leakage alarm;
meta proposition p 10 When the state of (1) is 1, the pressure boundary of a loop is broken, p 10 When the state of (2) is 0, the pressure boundary of the first circuit is not broken;
meta proposition p 11 When the state of (1) is 1, the failure of the primary coolant system of the primary circuit is indicated, p 11 The state of (2) is0 indicates that the primary coolant system of the primary circuit is unbroken.
2. The intelligent diagnosis method for failure of a primary circuit coolant system of a nuclear power plant according to claim 1, wherein the parameter signals corresponding to the meta-propositions in the diagnosis rules comprise: the device comprises a primary loop average temperature, a secondary loop water dosage high alarm signal, a safety valve discharge pipe temperature high alarm signal, a release valve discharge pipe temperature high alarm signal, a pressure stabilizer water level, a primary loop drain valve opening state signal, a safety shell dosage high alarm signal, a device cooling water dosage high alarm signal and an auxiliary system leakage alarm signal.
3. The intelligent diagnostic method for a failure of a primary circuit coolant system of a nuclear power plant according to claim 1, wherein the method for generating the state vector P comprises: the elements of the state vector P correspond to the current state of all the meta-propositions in the rule, the meta-propositions being ordered in the order in which they appear in sequence in the three rules and not repeated, the final conclusion meta-propositions being arranged last in the vector P,
P＝[p 1 ，p 6 ，p 5 ，p 10 ，p 9 ，p 8 ，p 4 ，p 3 ，p 2 ，p 7 ，p 11 ]。
4. the intelligent diagnosis method for failure of a primary circuit coolant system of a nuclear power plant according to claim 1, wherein the method for generating the transfer trigger vector DT comprises:
element DT [ i ] in transition trigger vector DT]The value of (2) is the ith transition t i The corresponding number of the condition element propositions is a row vector, and the dimension corresponds to the number of transfers, namely the number of diagnostic rules; the number of conditional meta-propositions in rule one is 3, DT 1]=3; the number of conditional meta-propositions in rule two is 6, DT 2]=6; the number of conditional meta-propositions in rule three is 1, DT 3]=1; transfer trigger vector dt= [3,6,1]]。
5. The intelligent diagnosis method for failure of a primary circuit coolant system of a nuclear power plant according to claim 1, wherein the method for generating the input transformation matrix I comprises:
the rows in the input transformation matrix I correspond to 11-element propositions in a primary coolant system breakage fault diagnosis rule for a circuit; columns correspond to three transitions in the first rule, the second rule and the third rule; the ordering of the rows in the input transformation matrix I is strictly consistent with the ordering of the meta-propositions in P, and the ordering of the columns is strictly consistent with the ordering of the transitions.
6. The intelligent diagnosis method for failure of a primary circuit coolant system of a nuclear power plant according to claim 1, wherein the method for generating the output transformation matrix o comprises:
the rows in the output transformation matrix O correspond to three transitions in the rule I, the rule II and the rule III, and the columns correspond to 11 element propositions and are consistent with the order of the element propositions in P.
7. The intelligent diagnosis method for the damage faults of the primary circuit coolant system of the nuclear power plant according to claim 4, wherein the intelligent diagnosis method is characterized by comprising the following steps of: according to the read input signal value of the corresponding parameter of each element proposition of the state vector P, the state of each element proposition in P is determined, and the state is assigned to the state vector P, and the fault diagnosis reasoning calculation method according to the knowledge matrix comprises the following steps:
(1) Determining initial state of each element proposition in state vector P according to read input signal, and assigning value to initial state vector P 0 Let p=p 0 ；
(2) Calculating P×I, and correcting the P×I result according to DT to obtain T;
(3) Calculating T X O, correcting elements larger than 1 in the T X O result to be 1, and assigning the obtained result to S;
(4) Calculation of S+P 0 Will S+P 0 The result of (2) is assigned to S;
(5) If P is not equal to S, making P=S, and going to the step (2) for circulation; if P=S, the numerical value of the corresponding element P11 of the conclusion meta-proposition in P is obtained, if the numerical value is equal to 1, the result is true, and the failure of the primary coolant system of the primary loop is judged; otherwise, judging that the breakage fault of the primary coolant system of the primary loop does not occur.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010659408.5A CN112036568B (en) | 2020-07-09 | 2020-07-09 | Intelligent diagnosis method for damage faults of primary loop coolant system of nuclear power device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010659408.5A CN112036568B (en) | 2020-07-09 | 2020-07-09 | Intelligent diagnosis method for damage faults of primary loop coolant system of nuclear power device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112036568A CN112036568A (en) | 2020-12-04 |
| CN112036568B true CN112036568B (en) | 2023-10-17 |
Family
ID=73579085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010659408.5A Active CN112036568B (en) | 2020-07-09 | 2020-07-09 | Intelligent diagnosis method for damage faults of primary loop coolant system of nuclear power device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112036568B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699117A (en) * | 2013-12-18 | 2014-04-02 | 中广核核电运营有限公司 | Method and system for diagnosing failure based on actual working conditions of nuclear power plant and simulation system |
| CN106597965A (en) * | 2016-12-07 | 2017-04-26 | 中国船舶重工集团公司第七〇九研究所 | Nuclear power apparatus running state monitoring system and monitoring method |
| CN107301884A (en) * | 2017-07-24 | 2017-10-27 | 哈尔滨工程大学 | A kind of hybrid nuclear power station method for diagnosing faults |
| CN109445411A (en) * | 2018-10-24 | 2019-03-08 | 西华大学 | A kind of Substation fault diagnosis |
| CN109491816A (en) * | 2018-10-19 | 2019-03-19 | 中国船舶重工集团公司第七六研究所 | Knowledge based engineering method for diagnosing faults |
| CN110289112A (en) * | 2019-06-14 | 2019-09-27 | 清华大学 | Nuclear power unit health status diagnostic method based on step analysis and fuzzy evaluation |
| CN110738274A (en) * | 2019-10-26 | 2020-01-31 | 哈尔滨工程大学 | nuclear power device fault diagnosis method based on data driving |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101766583B1 (en) * | 2016-04-27 | 2017-08-09 | 숭실대학교산학협력단 | Ontology-based reasoning apparatus and method using the knowledge of expert |
-
2020
- 2020-07-09 CN CN202010659408.5A patent/CN112036568B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699117A (en) * | 2013-12-18 | 2014-04-02 | 中广核核电运营有限公司 | Method and system for diagnosing failure based on actual working conditions of nuclear power plant and simulation system |
| CN106597965A (en) * | 2016-12-07 | 2017-04-26 | 中国船舶重工集团公司第七〇九研究所 | Nuclear power apparatus running state monitoring system and monitoring method |
| CN107301884A (en) * | 2017-07-24 | 2017-10-27 | 哈尔滨工程大学 | A kind of hybrid nuclear power station method for diagnosing faults |
| CN109491816A (en) * | 2018-10-19 | 2019-03-19 | 中国船舶重工集团公司第七六研究所 | Knowledge based engineering method for diagnosing faults |
| CN109445411A (en) * | 2018-10-24 | 2019-03-08 | 西华大学 | A kind of Substation fault diagnosis |
| CN110289112A (en) * | 2019-06-14 | 2019-09-27 | 清华大学 | Nuclear power unit health status diagnostic method based on step analysis and fuzzy evaluation |
| CN110738274A (en) * | 2019-10-26 | 2020-01-31 | 哈尔滨工程大学 | nuclear power device fault diagnosis method based on data driving |
Non-Patent Citations (2)
| Title |
|---|
| 核动力装置运行故障诊断系统设计研究;王天舒;余刃;刘笑凡;;核动力工程(第02期);180-183 * |
| 模糊Petri网专家系统及其在核动力装置故障诊断中的应用;彭俏;余刃;;核动力工程(第S1期);73-76 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112036568A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111337768A (en) | Deep parallel fault diagnosis method and system for dissolved gas in transformer oil | |
| JPH0522241B2 (en) | ||
| CN109472097B (en) | Fault diagnosis method for online monitoring equipment of power transmission line | |
| Kim et al. | Reactor vessel water level estimation during severe accidents using cascaded fuzzy neural networks | |
| WO2021114320A1 (en) | Wastewater treatment process fault monitoring method using oica-rnn fusion model | |
| CN114519382B (en) | Nuclear power plant key operation parameter extraction and abnormality monitoring method | |
| US11120350B2 (en) | Multilevel pattern monitoring method for industry processes | |
| CN106525397A (en) | Fault diagnosis method for nuclear power high-voltage heater | |
| Liu et al. | Improvement of fault diagnosis efficiency in nuclear power plants using hybrid intelligence approach | |
| Wu et al. | Research on rapid source term estimation in nuclear accident emergency decision for pressurized water reactor based on Bayesian network | |
| Liu et al. | Diagnosis of break size and location in LOCA and SGTR accidents using support vector machines | |
| Park et al. | Leak flow prediction during loss of coolant accidents using deep fuzzy neural networks | |
| CN112036568B (en) | Intelligent diagnosis method for damage faults of primary loop coolant system of nuclear power device | |
| Zhang et al. | Power grid fault diagnosis model based on the time series density distribution of warning information | |
| Do Koo et al. | Prediction of nuclear reactor vessel water level using deep neural networks | |
| Cheon et al. | Development strategies of an expert system for multiple alarm processing and diagnosis in nuclear power plants | |
| CN115564247A (en) | Intelligent identification and decision-making method and system for nuclear power plant accidents | |
| CN114580549A (en) | Nuclear power plant fault diagnosis method and device based on CNN-LSTM | |
| Santoso et al. | Nuclear plant fault diagnosis using probabilistic reasoning | |
| CN108830323B (en) | Nuclear reactor accident pattern recognition and safety parameter estimation method and estimation system | |
| Zavisca et al. | A bayesian network approach to accident management and estimation of source terms for emergency planning | |
| Lee et al. | Concept of robust AI with meta-learning for accident diagnosis | |
| Sun et al. | Research on Fault Diagnosis of Reactor Coolant Accident in Nuclear Power Plant Based on Radial Basis Function and Fuzzy Neural Network | |
| Yuan et al. | Data Driven Methods for Break Size and Location Estimation in LOCA Based on Deep Learning | |
| Park et al. | An experimental analysis on the CNS simulator comparing human performance between operators and students |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |