CN112036568B - Intelligent diagnosis method for damage faults of primary loop coolant system of nuclear power device - Google Patents

Abstract

The invention discloses an intelligent diagnosis method for damage faults of the primary coolant system of a nuclear power plant, which includes: setting damage fault diagnosis rules for the main coolant system of the primary circuit of the nuclear power plant, and generating a knowledge matrix based on the diagnosis rules. The knowledge matrix includes a state vector. P, input transformation matrix I, output transformation matrix O and transfer trigger vector DT; obtain the parameter signal corresponding to each element proposition in the diagnosis rule in real time according to the diagnosis rule, determine the state of each element proposition accordingly and assign it to the state vector P, according to The knowledge matrix performs fault diagnosis reasoning and calculation to determine whether the obtained result is true. If so, it means that the main coolant system of the primary circuit of the nuclear power plant is damaged. If not, it means that the main coolant system of the primary circuit of the nuclear power plant is not damaged. The invention realizes parallel reasoning of the diagnosis process through matrix operations, thereby realizing online intelligent diagnosis of damage faults of the primary circuit coolant system of the nuclear power plant.

Description

An intelligent diagnosis method for damage to the primary circuit coolant system of a nuclear power plant

Technical field

The invention belongs to the technical field of nuclear power plant fault diagnosis, and specifically relates to an online intelligent diagnosis method for primary loop main coolant system damage faults that occur during the operation of a pressurized water reactor nuclear power plant.

Background technique

According to statistics, more than half of the operational incidents that occur in nuclear power plants in the world are related to misoperation and misjudgment by operators. The main reasons for misoperation and misjudgment by operators are the complexity of nuclear power plants and the huge psychological pressure on operators when accidents occur. At present, the judgment of nuclear power plant operating faults is mainly made by operators by observing operating parameters and their changes, based on their knowledge and experience. To reduce or even avoid the occurrence of misjudgments and misoperations, an effective technical means is to provide operators with real-time, online automatic diagnosis capabilities for operating faults in the nuclear power plant instrumentation and control system.

Primary-circuit main coolant system damage failure refers to an accident in which the pipes of the primary-circuit main coolant system of a pressurized water reactor nuclear power plant and the valves in them are damaged, causing the pressure boundary of the primary-circuit main coolant system to be destroyed and the coolant to leak. . This accident has a high probability of occurring, and if it is not discovered in time, it may cause serious consequences.

Nuclear power plant is a complex nonlinear, strongly coupled dynamic time-varying system. The fault online intelligent diagnosis system can automatically analyze and process changes in the operating parameters of the nuclear power plant, assisting operators to accurately and timely determine the operating status and faults of the nuclear power plant, so as to take corrective measures. Commonly used fault diagnosis technologies can be divided into three categories: mechanism model-based, data-driven and knowledge rule-based.

Fault diagnosis methods based on mechanism models need to establish an accurate mechanism or mathematical model of the object to be diagnosed. However, nuclear power plants are extremely complex, and their characteristics will change to a certain extent as they are used and equipment ages. It is difficult to establish accurate and complete mechanism models or mathematical models under normal and accident conditions, and the calculations are computationally expensive. It takes a long time, so this type of method still has a large gap from the requirements of practical applications in terms of real-time performance and accuracy.

The basis for the implementation of data-driven fault diagnosis methods is to have a large amount of sample data in normal and fault conditions of the equipment to be diagnosed. Due to the high risk of nuclear power plant failure, it is usually impossible to obtain operating data samples during failure through experiments. It can often only be obtained through simulation, but its degree of reality is limited. Therefore, although there have been many theoretical research results based on data-driven fault diagnosis methods in recent years, the achievability and accuracy of operational fault diagnosis of nuclear power plants are still far from the requirements of practical applications.

People have accumulated rich operating experience during the long-term operation of nuclear power plants. Combined with theoretical analysis, rich and relatively complete fault determination rules can be formed. Therefore, it is a realistic and feasible technical approach to use knowledge-based artificial intelligence technology-expert system to realize automatic diagnosis of nuclear power plant operating faults. A practical online automatic fault diagnosis expert system needs to solve two problems: first, how to convert the fault judgment rules in the form of natural language into an expression form suitable for computer program language; second, how to effectively ensure the real-time nature of the fault judgment reasoning process .

Traditional expert systems are based on production rules, which is consistent with people's way of summarizing and expressing empirical knowledge and is easy to understand, but it is often cumbersome to express it in programming language. In addition, the reasoning engines of traditional expert systems perform serial reasoning according to a combination of rules. When the rules are complex, the search efficiency is low and the reasoning speed is slow. When there are many knowledge rules, problems such as rule conflicts and reasoning loops may also occur.

Contents of the invention:

In order to overcome the shortcomings of the above background technology, the present invention provides a set of knowledge that can convert the natural language-based knowledge of damage diagnosis rules of the main coolant system of the primary circuit of the pressurized water reactor nuclear power plant into a knowledge matrix that is easy to store and express by computers, and through the matrix The calculation realizes parallel reasoning of the diagnosis process, thereby realizing a method for rapid and automatic diagnosis of damage to the main coolant system of the primary circuit of the nuclear power plant.

In order to solve the above technical problems, the technical solutions adopted by the present invention are:

An intelligent diagnosis method for damage to the primary circuit coolant system of a nuclear power plant, including:

Set the damage fault diagnosis rules of the main coolant system of the primary circuit of the nuclear power plant, and generate a knowledge matrix based on the diagnosis rules. The knowledge matrix includes the state vector P, the input transformation matrix I, the output transformation matrix O and the transfer trigger vector DT; obtain the diagnosis rules in real time Based on the parameter signal corresponding to each element proposition, the state of each element proposition is determined and assigned to the state vector P. Based on the knowledge matrix, fault diagnosis reasoning calculation is performed to determine whether the obtained result is true. If so, it means that the nuclear power plant has The main coolant system of the loop is damaged. If not, it means that the main coolant system of the primary loop of the nuclear power plant is not damaged.

Preferably, the fault diagnosis rules for damage to the main coolant system of the primary circuit of the nuclear power plant include:

Rule 1, If p ₁ and p ₆ and p ₅ then p ₁₀ ;

Rule 2, if rule 1 is true and If p ₉ and p ₈ and p ₄ and p ₃ and p ₂ and p ₁₀ thenp ₁₁ ;

Rule three, if rule two is true or If p ₇ then p ₁₁ ;

Among them, when the state of meta-proposition p ₁ is 1, it means that the average temperature of the primary circuit has not dropped; when the state of meta-proposition p ₁ is 0, it means that the average temperature of the primary circuit has dropped;

When the status of meta-proposition p ₂ is 1, it means that the secondary circuit water dosage does not exceed the standard; when the status of meta-proposition p ₂ is 0, it means that the secondary circuit water dosage exceeds the standard;

When the state of meta-proposition p ₃ is 1, it means that the safety valve of the voltage regulator is not open; when the state of meta-proposition p ₃ is 0, it means that the safety valve of the voltage regulator is open;

When the state of meta-proposition p ₄ is 1, it means that the regulator release valve is not open; when the state of meta-proposition p ₄ is 0, it means that the regulator release valve is open;

When the state of meta-proposition p ₅ is 1, it means that the water level of the voltage regulator has dropped; when the state of meta-proposition p ₅ is 0, it means that the water level of the voltage regulator has not dropped;

When the status of meta-proposition p ₆ is 1, it means that the primary circuit drain valve is not open; when the status of meta-proposition p ₆ is 0, it means that the primary circuit drain valve is open;

When the status of meta-proposition p ₇ is 1, it means there is a high containment dose alarm; when the status of p ₇ is 0, it means there is no high containment dose alarm;

When the status of meta-proposition p ₈ is 1, it means that there is no equipment high cooling water dosage alarm; when the status of p ₈ is 0, it means there is equipment high cooling water dosage alarm;

When the status of meta-proposition p ₉ is 1, it means that there is no leakage alarm in the auxiliary system; when the status of p ₉ is 0, it means that there is a leakage alarm in the auxiliary system;

When the state of meta-proposition p ₁₀ is 1, it means that there is a breach in the pressure boundary of the primary circuit; when the state of p ₁₀ is 0, it means that there is no breach in the pressure boundary of the primary circuit;

When the status of meta-proposition p ₁₁ is 1, it means that the main coolant system of the primary circuit is damaged. When the status of p ₁₁ is 0, it means that the main coolant system of the primary circuit is not damaged.

Preferably, the parameter signals corresponding to each element proposition in the diagnostic rule include: primary circuit average temperature, secondary circuit water dosage high alarm signal, safety valve discharge pipe temperature high alarm signal, release valve discharge pipe temperature high alarm signal, voltage stabilization The water level of the equipment, the opening status signal of the primary circuit drain valve, the alarm signal of high dose of containment vessel, the alarm signal of high dose of equipment cooling water and the leakage alarm signal of other auxiliary systems.

Preferably, the method of generating the state vector P includes: the elements of the state vector P correspond to the current status of all meta-propositions in the rules, each meta-proposition is sorted in the order in which it appears in the three rules without repetition, and the final conclusion element is The proposition is 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 of generating the transfer trigger vector DT includes:

The value of element DT[i] in the transfer trigger vector DT is the number of conditional element propositions corresponding to the i-th transfer t _i , which is a row vector. The dimension corresponds to the number of transfers, that is, the number of diagnostic rules; rules The number of conditional propositions in Rule 1 is 3, DT[1]=3; the number of conditional propositions in Rule 2 is 6, DT[2]=6; the number of conditional propositions in Rule 3 is 1, DT [3]=1; transfer trigger vector DT=[3,6,1].

Preferably, the method of generating the input transformation matrix I includes:

The rows in the input transformation matrix I correspond to the 11 meta-propositions in the primary circuit main coolant system damage fault diagnosis rules; the columns correspond to the three transitions in the rules one, two and three; the rows in the input transformation matrix I correspond to The ordering is strictly consistent with the ordering of meta-propositions in P. The ordering of columns is strictly consistent with the ordering of transfers.

Preferably, the method of generating the output transformation matrix O includes:

The rows in the output transformation matrix Ο correspond to the three transitions in Rule 1, Rule 2 and Rule 3, and the columns correspond to 11 meta-propositions, and are strictly consistent with the ordering of meta-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 assigned to the state vector P. The method of performing fault diagnosis inference calculation based on the knowledge matrix includes:

(1) Obtain the initial state of each element proposition in the state vector P according to the read input signal, and assign it to the initial state vector P ₀ , let P=P ₀ ;

(2) Calculate P×I, correct the result of P×I according to DT, and obtain T;

(3) Calculate T×O, correct the elements greater than 1 in the result of T×O to 1, and assign the result to S;

(4) Calculate S+P ₀ and assign the result of S+P ₀ to S;

(5) If P≠S, let P=S and go to step (2) to loop; if P=S, get the value of the element P[11] corresponding to the conclusion element proposition in P. If it is equal to 1, then If the result is true, it is judged that the primary circuit coolant system is damaged; otherwise, it is judged that the primary circuit coolant system is not damaged.

The beneficial effects of the present invention are that: the present invention provides a practical, efficient, and convenient fault diagnosis knowledge expression and reasoning method for computer storage and calculation for damage fault diagnosis of the primary coolant system of the nuclear power plant. A fault diagnosis rule knowledge expression system based on meta-propositions and knowledge matrices, as well as a parallel reasoning algorithm based on matrix operations, are designed, which greatly facilitates the expression and storage of diagnostic rule knowledge in the computer and greatly improves the diagnostic reasoning process. speed, overcoming the technical bottleneck of traditional expert systems that cause the reasoning speed to drop sharply as the number of rules increases, thereby ensuring the real-time and achievability of the online intelligent diagnosis system for damage to the main coolant system of the primary circuit of the nuclear power plant.

The expert knowledge expression system for fault diagnosis of damage to the main coolant system of the nuclear power plant's primary circuit designed based on the fault diagnosis knowledge matrix is convenient for computer storage, call and expansion, and is convenient for the detection of rule conflicts and infinite loops; the designed system is based on The reasoning algorithm of knowledge matrix operation can transform the complex logical reasoning process into simple matrix operation and has parallel reasoning capabilities. Used in the diagnosis of damage to the primary circuit coolant system of nuclear power plants, it can greatly facilitate the expression and storage of diagnostic knowledge, improve the operating efficiency of the fault diagnosis expert system, and achieve the complete separation of reasoning algorithms and data, making it easier to use during use. New knowledge rules are continuously expanded in the system, so that the capabilities of the fault diagnosis system are continuously improved and enhanced, and it has good scalability.

Description of the drawings

Figure 1 is a schematic diagram of the pressurized water reactor nuclear power plant system;

Figure 2 is a flow chart of the primary loop main coolant system damage fault determination process according to the embodiment of the present invention;

Figure 3 is the knowledge matrix initialization process according to the embodiment of the present invention;

Figure 4 is the operation fault diagnosis process of the nuclear power plant according to the embodiment of the present invention;

Figure 5 is a flow chart of an algorithm for fault diagnosis using the knowledge matrix according to an embodiment of the present invention.

Detailed ways

The present invention will be further described below in conjunction with the accompanying drawings and examples.

(1) Form a knowledge matrix of fault diagnosis rules for damage to the main coolant system of the primary circuit of a pressurized water reactor nuclear power plant

The pressurized water reactor nuclear power plant is shown in Figure 1. The primary loop main coolant system damage fault determination process is shown in Figure 2. The generated diagnosis rules are as follows:

If(((The average temperature of the primary circuit has not dropped and the primary circuit drain valve has not been opened and the water level of the pressure stabilizer has continued to fall and there is no equipment high cooling water dosage alarm and the auxiliary system has no leakage alarm and the pressure stabilizer release valve has not been opened and the pressure stabilizer is safe The valve is not opened and the secondary circuit water dosage does not exceed the standard) or there is a high containment dosage alarm) then the primary circuit main coolant system is damaged.

A fault diagnosis expert knowledge expression system based on knowledge matrix. Through the definition of model elements and the design of knowledge matrix generation method, it can achieve the purpose of easy computer expression and storage of fault diagnosis knowledge of damage to the main coolant system of the primary circuit of nuclear power plant. It provides It lays the foundation for automatic diagnosis of operating faults.

1) Definition of the elements of the knowledge matrix

a. meta-proposition

The production rule form of the damage diagnosis knowledge of the primary loop coolant system of the nuclear power plant can be expressed as:

If(p ₁ and p ₂ …)or(p ₃ and p ₄ …)……,then A

Among them, p ₁ , p ₂ , p ₃ , etc. are conditional propositions, and A is the conclusion proposition.

The structure of proposition p _i is usually a conditional judgment, such as a certain parameter is greater than, less than or equal to a certain value (for example: the average temperature of the primary circuit has not dropped), or whether a certain equipment state has a certain phenomenon or attribute ( For example: the primary circuit drain valve is not opened), etc. These propositions have only two states: "established (true)" or "not established (false)", and are defined here as "meta-propositions". Conclusion proposition A is also one of the meta-propositions, which is "the primary circuit main coolant system is damaged".

"Meta-proposition" refers to the smallest logical judgment unit in fault diagnosis production rule knowledge. It cannot be broken down into a combination of two or more logical judgments. It can be an input meta-proposition and a conclusion meta-proposition (usually with specific physical meanings, such as: the average temperature of the primary circuit is greater than 300°C, or the drain valve is open, etc.), or it can be an intermediate result of logical reasoning (i.e., an intermediate meta-proposition, possibly has no specific physical meaning), represented by _pi .

Aiming at the production rules for diagnosis knowledge of damage to the main coolant system of the primary circuit of a nuclear power plant, the meta-propositions are determined as shown in Table 1.

Table 1 Element proposition definition table of primary circuit main coolant system damage diagnosis rules

In Table 1, p ₁₀ is an intermediate meta-proposition, which has physical meaning here, that is: there is a breach in the pressure boundary of the primary circuit; p ₁₁ is a conclusion meta-proposition, and the others are all input meta-propositions.

b.Diagnostic knowledge production rules

On the basis of the pairwise proposition definitions in Table 1, the production rules of primary circuit main coolant system damage fault diagnosis knowledge can be expressed symbolically as:

Rule 1: If p ₁ and p ₆ and p ₅ then p ₁₀ ;

Rule 2: If p ₉ and p ₈ and p ₄ and p ₃ and p ₂ and p ₁₀ then p ₁₁ ;

Rule 3: or Ifp ₇ then p ₁₁ .

The above rules can be divided into two categories, namely (1) if the rule header starts with "or", it means that the rule has an "OR" relationship with other rules; (2) if the rule header starts directly with "if", then Indicates that this rule has an "AND" relationship with other rules.

For the above three rules, it can be seen that each rule will have an inference conclusion, which contains a "then" character. In addition, each rule has at most one "or" operator. If there are multiple "or" operators, it can be split into multiple rules.

c.Status

Refers to the judgment result of the proposition. Its value is represented by α( _pi ), which has two values: 1 and 0. When the judgment result of a certain meta-proposition is true, its status value is 1, otherwise it is 0. The state value of the conditional element proposition depends on the judgment result of the nuclear power plant operating parameters (or equipment operating status, etc.) contained in it at the current moment. The state value of the conclusion or intermediate element proposition depends on the logic of its preceding element proposition. Operation result.

d.State vector P

The elements of the state vector P correspond to the current states of all meta-propositions in the rule. Except for the conclusion meta-proposition which is at the end of the vector P, other meta-propositions are sorted in the order in which they appear in the rules. If an elemental proposition appears multiple times in each rule, it will be arranged in the order of its first appearance, and there will be no repetition of elements in P.

If the value of an element in the vector is 1, it means that the state of the meta-proposition p _i corresponding to the element is true, and the state of the meta-proposition is activated (i.e. α(pi ₎ =1); if the element value is 0, the opposite is true (i.e. α (p _i )=0). In order to simplify the expression, in subsequent definitions and calculations, p _i is directly used to represent the state value α( _pi ) of its corresponding meta-proposition.

For the primary loop main coolant system damage fault diagnosis rule, there are 11 meta-proposition states (including 9 input meta-propositions, 1 intermediate meta-proposition and 1 conclusion meta-proposition). Its 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

Transfer represents the logical "AND" operation, which refers to the change in the state of an intermediate proposition or conclusion proposition during the diagnostic reasoning process. A transition can have one or more conditional meta-propositions (inference logical conditions, which can be input meta-propositions or intermediate meta-propositions), and one result meta-proposition (inference logical results, which can be intermediate meta-propositions or intermediate meta-propositions). is the final conclusion meta-proposition). When the status of all conditional propositions of a transition is 1, the transition is triggered, and the status of its conclusion proposition becomes 1, indicating that the transition has occurred. The transfer is represented by _ti .

The "then" in a rule represents a "state transition". For the diagnosis of damage to the primary circuit main coolant system, there are three rules, corresponding to the three transfers t ₁ , t ₂ , and t ₃ .

f. Transfer trigger vector DT

The value of element DT[i] in the transfer trigger vector _DT is the number of input element propositions corresponding to the i-th transfer ti. is a row vector, and its dimension corresponds to the number of transitions, that is, the number of diagnostic rules.

For the primary loop main coolant system damage fault diagnosis rule, the transfer 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 meta-propositions in the primary circuit main coolant system damage fault diagnosis rule; the columns correspond to 3 transitions in the inference rule. The value of an element in matrix I is 1, which means that the meta-proposition corresponding to the row of the element is the input meta-proposition of the transfer corresponding to the column of the element; the value of an element is 0, which means that the meta-proposition corresponding to the row of the element is not The input meta-proposition of the transition corresponding to the column in which this element is located.

The ordering of the rows in the input transformation matrix I should be strictly consistent with the ordering of the meta-propositions in P. The ordering of columns is strictly consistent with the ordering of transfers.

For the primary loop main coolant system damage fault diagnosis rule, the input transformation matrix I is:

h. Output transformation matrix Ο

The rows in the output transformation matrix Ο correspond to the three transitions in the inference rule, and the columns correspond to the 11 meta-propositions in the inference rule. If the value of an element is 1, it means that the meta-proposition corresponding to the column where the element is located is the output meta-proposition of the transfer corresponding to the row where the element is located; when the value of an element is 0, it means that the meta-proposition corresponding to the column where the element is located is not the meta-proposition corresponding to the row where the element is located. The output meta-proposition of the corresponding transfer.

The ordering of columns in the output transformation matrix Ο should be strictly consistent with the ordering of meta-propositions in P. The ordering of rows is exactly the same as the ordering of transfers.

For the primary loop main coolant system damage fault diagnosis rule, the output transformation matrix Ο is:

2) Primary circuit main coolant system damage fault diagnosis knowledge matrix

Under the premise of the above definition, the state vector P, the input transformation matrix I, the output transformation matrix Ο and the transfer trigger vector DT together constitute the knowledge matrix N = {P, I, O, DT} of the fault diagnosis rule knowledge network model, which fully expresses Input conditions and reasoning logic of fault diagnosis rule knowledge. This knowledge matrix expression method only needs to store four vectors or matrices in the computer, which greatly reduces the storage capacity requirements of the computer for diagnostic knowledge and lays the foundation for subsequent reasoning algorithms based on the knowledge matrix.

During the implementation of this diagnostic method, first, the above-mentioned knowledge matrix is generated based on the diagnosed nuclear power plant composition and the primary circuit main coolant system damage fault diagnosis expert knowledge, and is stored in the knowledge base of the diagnostic system to complete the initialization of the diagnostic system. . The initialization process is shown in Figure 3. This work is usually completed before the diagnostic system is put into use, and the diagnostic rule knowledge matrix for new fault types can be continuously added during use.

(2) Fault diagnosis reasoning process based on matrix operations

The process of fault diagnosis of nuclear power plant operation is a repeated cycle process of collecting required signals according to a certain time period, performing fault judgment through diagnostic reasoning and calculation, as shown in Figure 4.

The present invention converts the fault diagnosis process of line-by-line reasoning based on production diagnosis rules into a simple and efficient processing process based on knowledge matrix operations, which can greatly improve the operating efficiency of the fault diagnosis expert system, thereby meeting the real-time requirements of nuclear power plant operation fault diagnosis. sexual requirements.

After establishing the knowledge matrix N = {P, I, O, DT} for damage diagnosis of the primary coolant system of the nuclear power plant, the inference algorithm steps for fault diagnosis using it are shown in Figure 5.

According to the element proposition definition of the primary loop main coolant system damage fault diagnosis rule and the required collected signals determined in Table 1, in order to verify the actual application effect, two test conditions of fault occurrence and failure are set respectively. The initial states of each element proposition under the two working conditions are shown in Table 2.

Table 2 Initial state table of the element proposition for damage diagnosis of the main coolant system of the first loop under two working conditions

As mentioned before.

For the damage fault of the main coolant system of the primary circuit, the knowledge matrix N = {P, I, O, DT} of the diagnostic rules is constructed during the initialization process as:

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:

Output transformation matrix:

Transfer trigger vector DT=[3,6,1].

The following is a detailed explanation of the diagnostic reasoning and calculation process during the implementation of primary-circuit main coolant system damage fault diagnosis under two test conditions:

Step 1: Read the operating parameters of the nuclear power plant, determine the initial activation state of each element proposition based on the operating parameter value, and assign an initial value to the state vector P. The method of assignment is: the first element of the P vector is the element proposition p ₁ , that is, "the average temperature of the primary circuit has not dropped." When diagnosing, first read the average temperature of the primary circuit at the current moment and compare it with the value at the previous moment. If it does not drop, then the element proposition p ₁ is true, and the first element of the P vector is assigned a value of 1; if it drops, the element The proposition p ₁ is false, and the first element of the P vector is assigned the value 0. The assignment process of other elements is analogous:

Assume the working conditions: P = [1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0];

Assume working condition 2: P=[1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0];

Step 2: Perform inference operations and output inference conclusions.

a. Calculation steps for working condition 1:

①Assign a value to the initial state vector P ₀ according to the input signal, P ₀ =[1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0], and let P = P ₀ ;

②T=P×I=[3, 5, 1], corrected according to DT to get 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], there is S≠P, the reasoning is not completed, and the status of the intermediate node P ₁₀ is updated. Let P=S=[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] and enter the next cycle;

④T=P×I=[3, 6, 1], corrected according to DT to get T=[1, 1, 1];

⑤S=T×O=[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 2]. For elements with a value greater than 1, it means that there are multiple transfers occurring upstream of the node. Since In the OR operation, if a transition occurs, the state of the downstream element proposition can change. Therefore, the elements in S with a value greater than 1 are 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], S = P, and the reasoning is completed. The conclusion element proposition in P corresponds to element P[11]=1, and the diagnostic conclusion is output: the main coolant system of the primary circuit is damaged.

b. Calculation steps for working condition 2:

①Assign a value to the initial state vector P ₀ according to the input signal, P ₀ =[1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0], and let P = P ₀ ;

②T=P×I=[3, 4, 0], corrected according to DT to get T=[1, 0, 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], there is S≠P, the reasoning is not completed, and the status of the intermediate node P ₁₀ is updated. Let P=S=[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0] and enter the next cycle;

④T=P×I=[3, 5, 0], corrected according to DT to get T=[1, 0, 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], S=P, and the reasoning is completed. The conclusion element proposition in P corresponds to the element P[11]=0, and the diagnostic conclusion is output: the primary circuit main coolant system damage failure has not occurred.

It can be seen that the reasoning conclusion is consistent with the preset conclusion of the working conditions.

This example verifies the correctness of the algorithm.

It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should fall within the protection scope of the appended claims of the present invention.

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.