Complex equipment fault diagnosis method based on causal belief rule base

Abstract

The invention discloses a complex equipment fault diagnosis method based on a causal belief rule base, and relates to the technical field of complex equipment fault diagnosis, and the method comprises the steps: obtaining a causal relationship between a fault and an index in complex equipment; based on the causal relationship between the fault and the index in the complex equipment, constructing a causal graph; constructing a rule based on a causal graph and initializing confidence to obtain a causal confidence rule base; based on the causal belief rule base, performing fault diagnosis on the complex equipment; the belief rule base is improved based on the causal relationship, and then the precision of complex equipment fault diagnosis is improved.

Description

Technical Field

[0001] The present application relates to the technical field of complex equipment fault diagnosis, and in particular to a complex equipment fault diagnosis method based on a causal confidence rule base. Background Art

[0002] Belief Rule Base (BRB) is a rule base modeling method based on fuzzy logic. In 2006, Yang et al. proposed a belief-base inference methodology using the evidential reasoning approach (RIMER), which introduced the belief framework into the traditional production rules. The RIMER method is developed based on Dempster-Shafer evidence theory, decision theory, fuzzy theory and traditional production rules. As an important part of the RIMER method, BRB is a generalization of the traditional fuzzy rule base (FRB) and can provide a more reliable description of knowledge in engineering systems. At present, the BRB model has been rapidly developed and has been applied in many fields such as fault detection, medicine, engineering system safety assessment, and complex system modeling. The BRB system consists of a series of rules. Its essence is an expert system that can effectively utilize various types of information and establish a nonlinear model between input and output. A basic rule base can be composed of many simple IF-THEN rules. If a confidence level is added to the result part and the premise attribute weight and rule weight are considered at the same time, the confidence rule can be obtained. A series of confidence rules combined together constitute a confidence rule base.

[0003] Confidence rule bases have been widely used in the field of complex equipment fault diagnosis. However, in the process of building BRB, some rules may have pseudo-correlations due to the neglect of the influence of potential third-party factors. Specifically, the limitations of expert experience, the lack of mechanism knowledge and the randomness of sample data will lead to pseudo-correlations between the premise attributes and conclusions of BRB rules, which will destroy the interpretability of BRB rules to a certain extent. The existing confidence rule base itself may have pseudo-correlations between its indicators and faults due to the limitations of expert experience, the lack of mechanism knowledge and the randomness of sample data when diagnosing complex equipment faults, which may only be a data-fitting pseudo-correlation, resulting in low accuracy in complex equipment fault diagnosis. Summary of the invention

[0004] The purpose of this application is to provide a complex equipment fault diagnosis method based on a causal confidence rule base, improve the confidence rule base based on causal relationships, and thus improve the accuracy of complex equipment fault diagnosis.

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

[0006] The present application provides a complex equipment fault diagnosis method based on a causal confidence rule base, comprising:

[0007] Obtain the cause-effect relationship between faults and indicators in complex equipment;

[0008] Construct a cause-effect diagram based on the cause-effect relationship between faults and indicators in complex equipment;

[0009] Building rules based on the causal graph and initializing confidence to obtain a causal confidence rule base;

[0010] Based on the causal confidence rule base, fault diagnosis is performed on complex equipment.

[0011] Optionally, the causal relationship includes causal relationships corresponding to multiple fault types;

[0012] The causal relationship corresponding to any fault type includes: a plurality of cause indicators and a plurality of effect indicators corresponding to the fault type; a change in the cause indicator causes the corresponding fault to occur; and the occurrence of the fault causes the corresponding plurality of effect indicators to change.

[0013] Optionally, based on the causal confidence rule base, fault diagnosis of complex equipment includes:

[0014] Let the first iteration number i=1;

[0015] Determine all rules corresponding to the i-th premise attribute in the causal confidence rule base as current rules; the premise attribute is a cause indicator or a result indicator;

[0016] Get the number M of current rules;

[0017] Let the second iteration number m=1;

[0018] Based on the reference value of the i-th premise attribute, determine the matching degree of the i-th premise attribute in the m-th current rule;

[0019] Increase the value of the second iteration number m by 1, and return to the step "determine the matching degree of the i-th premise attribute in the m-th current rule based on the reference value of the i-th premise attribute" until the value of the second iteration number m is equal to the number of current rules M, and obtain the matching degree of the i-th premise attribute in each corresponding rule;

[0020] Increase the value of the first iteration number i by 1, and return to the step of "determining all rules corresponding to the i-th premise attribute in the causal confidence rule base as current rules" until all premise attributes are traversed to obtain the matching degree of different premise attributes in each corresponding rule;

[0021] Based on the matching degree of different premise attributes in each corresponding rule, the activation weight of each rule is determined respectively;

[0022] Based on the activation weights of different rules, the confidence of each conclusion is determined respectively; the conclusion corresponds to the fault type one by one;

[0023] Based on the confidence levels of different conclusions, the fault diagnosis results are determined.

[0024] Optionally, the matching degree is:

[0025] in, is the matching degree of the i-th premise attribute in the m-th current rule; is the reference value of the i-th premise attribute in the n+1-th rule; is the reference value of the i-th premise attribute in the n-th rule; x i is the i-th premise attribute.

[0026] Optionally, the activation weight is:

[0027] Among them, w m is the activation weight of the mth rule; θ m is the rule weight of the mth rule; M1 is the number of premise attributes; δ i is the weight of the i-th premise attribute; N is the number of rules; θ n is the rule weight of the nth rule; is the matching degree of the i-th premise attribute in the n-th current rule.

[0028] Optionally, the confidence level of the conclusion is:

[0029]

[0030] B = DE;

[0031]

[0032] Among them, β l is the confidence level corresponding to the lth conclusion; A, B, C, D, E are all intermediate parameters; L is the number of conclusions; β l,m is the confidence level corresponding to the lth conclusion of the mth rule; β i,m is the confidence corresponding to the i-th conclusion of the m-th rule.

[0033] Optionally, the fault diagnosis result is:

[0034]

[0035] Among them, Output is the fault diagnosis result; D l This is the first conclusion.

[0036] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0037] The present application provides a complex equipment fault diagnosis method based on a causal confidence rule base, clarifies objects and indicators, constructs a causal graph, constructs rules and initial confidence through the causal graph, calculates the matching degree of premise attributes and reference values, calculates the activation weight of the rules, and uses the ER parsing algorithm to calculate the confidence of the final evaluation result to obtain the final result. A causal machine is added to the BRB, and the causal machine uses the causal graph to screen the rules to obtain rules with causal relationships, which effectively reduces the number of rules in the model and reduces the complexity of the model. The performance of the model is improved by reasonably improving the reference level of the premise attributes, and the interpretability of the confidence rule base is improved while reasonably reducing the number of rules to prevent combinatorial explosion. By constructing the causal graph, a new confidence rule base with causal relationships is obtained, which improves the interpretability of the model, and does not affect its performance while filtering the rules, thereby improving the accuracy, interpretability and efficiency of complex equipment fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 This is a flow chart of a complex equipment fault diagnosis method with a causal confidence rule base in one embodiment of the present application;

[0040] Figure 2 This is a basic structure diagram of a traditional trust rule library in an embodiment of the present application;

[0041] Figure 3 This is a basic structure diagram of a causal confidence rule base in one embodiment of the present application;

[0042] Figure 4 Schematic diagram of the reasoning process of the causal confidence rule base in one embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0045] In an exemplary embodiment, Figure 1 As shown, a complex equipment fault diagnosis method based on a causal confidence rule base is provided, comprising:

[0046] Step 101: Obtain the causal relationship between faults and indicators in complex equipment. The causal relationship includes causal relationships corresponding to multiple fault types. The causal relationship corresponding to any fault type includes: multiple cause indicators and multiple effect indicators corresponding to the fault type. The corresponding fault occurs when the cause indicator changes. After the fault occurs, the corresponding multiple effect indicators change.

[0047] Clearly define the object and index: Before diagnosing the fault of complex equipment, you first need to clarify the specific equipment, that is, the object; then select the index related to the occurrence of the fault or the index that changes due to the occurrence of the fault. Before building the database, you must first analyze the specific problem. For example, when diagnosing the looseness of the fiber optic flange interface, you must first determine the index that may cause the fault, or which indexes will change due to the occurrence of the fault, so as to facilitate subsequent analysis and processing.

[0048] Step 102: Construct a cause-effect diagram based on the cause-effect relationship between faults and indicators in complex equipment.

[0049] After clarifying the object and the indicator, the relationship between the indicator and the fault should be established. By analyzing the mechanism of the object and determining the causal relationship between the indicator and the fault based on the indicator obtained in step 1, the causal diagram is initially constructed using expert knowledge, and then the data is analyzed to improve the causal diagram.

[0050] Step 103: Construct rules based on the causal graph and initialize the confidence to obtain a causal confidence rule base. Construct rules based on the indicators screened by the causal graph and give an initial confidence. During the causal graph screening process, if the causal strength between some premise attributes and conclusions is less than a given threshold, delete such rules to obtain a filtered rule base (i.e., causal confidence rule base). The basic structure of the confidence rule base before screening (i.e., the traditional confidence rule base) is as follows: Figure 2 As shown; the basic structure of the causal confidence rule base is as follows Figure 3As shown in Figure 2, the reasoning process of the causal confidence rule base is as follows: Figure 4 shown.

[0051] Figure 2 In this example, x1 is the first premise attribute, x2 is the second premise attribute, and x M is the Mth premise attribute, δ1 is the weight of the first premise attribute, δ2 is the weight of the second premise attribute, δ M is the weight of the Mth premise attribute, R1 is the first rule, R2 is the second rule, R k is the kth rule, R L is the Lth rule, θ1 is the rule weight of the first rule, θ2 is the rule weight of the second rule, θ k is the rule weight of the kth rule, θ L is the rule weight of the Lth rule, D1 is the first conclusion, D2 is the second conclusion, D N is the Nth conclusion. In the causal machine, each node represents a premise attribute / evaluation result or a reference level of premise attribute / evaluation result, each directed edge represents a causal relationship, and the arrow represents the direction of the causal relationship, that is, the node pointed by the arrow represents the result of the causal relationship, the node where the arrow starts represents the cause of the causal relationship, and the weight on the edge represents the causal strength. Figure 3 In the above formula, R′1 represents the first rule with causal relationship after being screened by the causal machine, R′2 represents the second rule with causal relationship after being screened by the causal machine, and R′ j R′ represents the jth rule with causal relationship after being screened by the causal machine. p is the rule weight of the pth rule with causal relationship after screening by the causal machine; θ′1 is the rule weight of the first rule with causal relationship after screening by the causal machine; θ′2 is the rule weight of the second rule with causal relationship after screening by the causal machine; θ′ j is the rule weight of the jth rule with causal relationship after being screened by the causal machine; θ′ p is the rule weight of the pth rule with causal relationship after being screened by the causal machine; Figure 4 In the above example, c1 represents the first attribute (cause indicator), c2 represents the third attribute, and c m represents the mth cause attribute, e1 represents the first result attribute (result indicator), e2 represents the third result attribute, and e n represents the nth fruit attribute, p 11 represents the causal strength between the first cause attribute and the first effect attribute, p 12 represents the causal strength between the first cause attribute and the second effect attribute, p 1nrepresents the causal strength between the first cause attribute and the nth effect attribute, p 21 represents the causal strength between the second cause attribute and the first effect attribute, p 22 represents the causal strength between the second cause attribute and the second effect attribute, p 2n represents the causal strength between the second cause attribute and the nth effect attribute, p m1 represents the causal strength between the mth cause attribute and the first effect attribute, p m2 represents the causal strength between the mth cause attribute and the second effect attribute, p mn Represents the causal strength between the mth cause attribute and the nth effect attribute.

[0052] Step 104: Perform fault diagnosis on complex equipment based on the causal confidence rule base.

[0053] Step 104 includes:

[0054] Step 104 - 1 : Let the first iteration number i=1.

[0055] Step 104-2: Determine that all rules corresponding to the i-th premise attribute in the causal confidence rule base are current rules. The premise attribute is a cause indicator or a result indicator. The premise attribute corresponds to different things in different situations. If it is diagnosis, then the conclusion is the dependent variable. If it is prediction, then the premise attribute is the dependent variable: when diagnosing, the indicator changes because of the fault, so the fault corresponding to the conclusion is the cause, and the indicator corresponding to the premise attribute changes to the result. If it is prediction, then it is to judge what kind of fault may occur through the indicator.

[0056] Step 104 - 3: Obtain the number M of current rules.

[0057] Step 104 - 4 : Set the second iteration number m=1.

[0058] Step 104 - 5 : Based on the reference value of the ith premise attribute, determine the matching degree of the ith premise attribute in the mth current rule.

[0059] Step 104 - 6 : Increase the value of the second iteration number m by 1, and return to step 104 - 5 until the value of the second iteration number m is equal to the number M of current rules, and obtain the matching degree of the i-th premise attribute in each corresponding rule.

[0060] Step 104-7: Increase the value of the first iteration number i by 1, and return to step 104-2 until all premise attributes are traversed to obtain the matching degree of different premise attributes in each corresponding rule. The matching degree is:

[0061] in, is the matching degree of the i-th premise attribute in the m-th current rule. is the reference value of the i-th premise attribute in the n+1-th rule. is the reference value of the i-th premise attribute in the n-th rule. i is the i-th premise attribute.

[0062] Step 104-8: Based on the matching degree of different premise attributes in each corresponding rule, determine the activation weight of each rule. The activation weight is:

[0063] Among them, w m is the activation weight of the mth rule. m is the rule weight of the mth rule. M1 is the number of premise attributes. δ i is the weight of the i-th premise attribute. N is the number of rules. θ n is the rule weight of the nth rule. is the matching degree of the i-th premise attribute in the n-th current rule.

[0064] Step 104-9: Based on the activation weights of different rules, the confidence of each conclusion is determined. The conclusion corresponds to the fault type one by one. The confidence of the conclusion is:

[0065]

[0066] B=DE.

[0067]

[0068] Among them, β l is the confidence level corresponding to the lth conclusion. A, B, C, D, and E are all intermediate parameters. L is the number of conclusions. β l,m is the confidence level corresponding to the lth conclusion of the mth rule. i,m is the confidence corresponding to the i-th conclusion of the m-th rule.

[0069] Step 104-10: Determine the fault diagnosis result based on the confidence of different conclusions. The fault diagnosis result is:

[0070]

[0071] Among them, Output is the fault diagnosis result. l This is the first conclusion.

[0072] The present application adds a causal machine to the confidence rule base (BRB) fault diagnosis model. The causal machine uses a causal graph to screen the rules and obtain rules with causal relationships, thereby reasonably reducing the number of rules to prevent combinatorial explosion while improving the interpretability of the confidence rule base. The advantages are that the number of rules in the model is effectively reduced, the complexity of the model is reduced, and the performance of the model is improved by reasonably improving the reference level of the premise attributes; by constructing a causal graph, a new confidence rule base with causal relationships is obtained, the interpretability of the model is improved, and the performance of the model will not be affected while filtering the rules.

[0073] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a complex equipment fault diagnosis method of a causal confidence rule base is implemented.

[0074] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0075] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0076] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0077] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0078] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0079] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A complex equipment fault diagnosis method based on a causal confidence rule base, characterized in that: include: Obtain the cause-effect relationship between faults and indicators in complex equipment; Construct a cause-effect diagram based on the cause-effect relationship between faults and indicators in complex equipment; Building rules based on the causal graph and initializing confidence to obtain a causal confidence rule base; Based on the causal confidence rule base, fault diagnosis is performed on complex equipment.

2. The complex equipment fault diagnosis method based on the causal confidence rule base according to claim 1 is characterized in that: The causal relationship includes causal relationships corresponding to multiple fault types; The causal relationship corresponding to any fault type includes: a plurality of cause indicators and a plurality of effect indicators corresponding to the fault type; a change in the cause indicator causes the corresponding fault to occur; and the occurrence of the fault causes the corresponding plurality of effect indicators to change.

3. The complex equipment fault diagnosis method based on the causal confidence rule base according to claim 1 is characterized in that: Based on the causal confidence rule base, fault diagnosis of complex equipment is performed, including: Let the first iteration number i=1; Determine all rules corresponding to the i-th premise attribute in the causal confidence rule base as current rules; the premise attribute is a cause indicator or a result indicator; Get the number M of current rules; Let the second iteration number m=1; Based on the reference value of the i-th premise attribute, determine the matching degree of the i-th premise attribute in the m-th current rule; Increase the value of the second iteration number m by 1, and return to step "determine the matching degree of the i-th premise attribute in the m-th current rule based on the reference value of the i-th premise attribute" until the value of the second iteration number m is equal to the number of current rules M, and obtain the matching degree of the i-th premise attribute in each corresponding rule; Increase the value of the first iteration number i by 1, and return to the step of "determining all rules corresponding to the i-th premise attribute in the causal confidence rule base as current rules" until all premise attributes are traversed to obtain the matching degree of different premise attributes in each corresponding rule; Based on the matching degree of different premise attributes in each corresponding rule, the activation weight of each rule is determined respectively; Based on the activation weights of different rules, the confidence of each conclusion is determined respectively; the conclusion corresponds to the fault type one by one; Based on the confidence levels of different conclusions, the fault diagnosis results are determined.

4. The complex equipment fault diagnosis method based on the causal confidence rule base according to claim 3 is characterized in that: The matching degree is: in, is the matching degree of the i-th premise attribute in the m-th current rule; is the reference value of the i-th premise attribute in the n+1-th rule; is the reference value of the i-th premise attribute in the n-th rule; x i is the i-th premise attribute.

5. The complex equipment fault diagnosis method based on the causal confidence rule base according to claim 4 is characterized in that: The activation weight is: Among them, w m is the activation weight of the mth rule; θ m is the rule weight of the mth rule; M1 is the number of premise attributes; δ i is the weight of the i-th premise attribute; N is the number of rules; θ n is the rule weight of the nth rule; is the matching degree of the i-th premise attribute in the n-th current rule.

6. The complex equipment fault diagnosis method based on the causal confidence rule base according to claim 5 is characterized in that: The confidence level of the conclusion is: B = DE; Among them, β l is the confidence level corresponding to the lth conclusion; A, B, C, D, E are all intermediate parameters; L is the number of conclusions; β l,m is the confidence level corresponding to the lth conclusion of the mth rule; β i,m is the confidence corresponding to the i-th conclusion of the m-th rule.

7. The complex equipment fault diagnosis method based on the causal confidence rule base according to claim 6 is characterized in that: The fault diagnosis results are: Among them, Output is the fault diagnosis result; D l This is the first conclusion.

Images