An intelligent diagnosis expert system and method for aero-engine blade hole exploration damage

Abstract

This invention discloses an intelligent diagnostic expert system and method for borehole damage of aero-engine blades. The method constructs a structured data model of the engine blade, systematically encapsulating complex damage tolerance standards for different components, stages, and locations. This transforms the process of manually searching for diagnostic standards from massive maintenance manuals into automated data matching, significantly improving diagnostic efficiency. Through a mechanism that dynamically selects key evaluation parameters based on damage type, it ensures accurate judgment using the most relevant parameters for different damage modes, overcoming the misjudgment problem caused by improper parameter use in traditional methods. The method solidifies the expert experience of senior maintenance personnel and standard maintenance procedures into executable diagnostic rules, and uses rule-based reasoning to simulate expert thinking for automated reasoning, effectively reducing reliance on the personal experience of maintenance personnel and improving the consistency of diagnostic results.

Description

Technical Field

[0001] This invention relates to the field of aero-engine fault diagnosis, and more specifically, to an intelligent diagnostic expert system and method for borehole damage of aero-engine blades. Background Technology

[0002] As the core power component of an aircraft, the blades of an aero-engine operate in harsh environments for extended periods, making them highly susceptible to damage such as impacts, cracks, and ablation. This damage directly impacts engine performance, efficiency, and safety, and in severe cases, can lead to catastrophic consequences. Therefore, regularly conducting in-situ inspections of the engine's internal blades using borescopes, and accurately diagnosing and deciding on repairs for any damage discovered, is a crucial aspect of aviation maintenance and support.

[0003] Currently, in the field of aero-engine maintenance, the core step of structural damage diagnosis based on borehole images still heavily relies on manual interpretation by maintenance personnel. However, this traditional method faces several pressing challenges that need to be addressed: First, the damage tolerance standards vary greatly among different engine models, different components, and even different parts of the same blade. Maintenance personnel need to find the corresponding standards in the maintenance manual. The diagnostic process is not only extremely inefficient, but also highly susceptible to misdiagnosis due to fatigue, negligence, or misunderstanding of the manual.

[0004] Second, damage diagnosis requires maintenance personnel to make a comprehensive judgment based on multiple factors such as the shape, location, and size of the damage. Diagnostic conclusions rely on the personal experience of maintenance personnel and lack stable and uniform objective standards.

[0005] In summary, there is an urgent need in this field for a solution that can systematically encapsulate maintenance standards and the experience of technical experts, and can perform automated, standardized, and intelligent diagnostics. Summary of the Invention

[0006] In view of this, the present invention provides an intelligent diagnostic expert system and method for borehole damage of aero-engine blades, which solves the problems of excessive reliance on human experience, low efficiency and opaque decision-making process in existing aero-engine blade damage diagnosis methods.

[0007] To achieve the above objectives, the following solution is proposed: Intelligent diagnostic methods for borehole damage in aero-engine blades include: A structured data model of engine blades is constructed, which includes the hierarchical structure of engine blades and corresponding size and damage assessment parameters. Obtain damage parameters from borehole images of engine blades; Based on the preset evaluation parameter mapping relationship, key evaluation parameters are determined by the damage parameters of borehole images; The structured data model, borehole image damage parameters, and key assessment parameters are matched with diagnostic rules in the expert knowledge base, and the first diagnostic rule whose conditions are fully met is executed to generate the corresponding maintenance decision. Output maintenance decisions and generate inspection reports.

[0008] Preferably, it further includes: The structured data model of the engine blades is displayed in a hierarchical tree format for users to select components.

[0009] Preferably, in the hierarchical structure of the engine blades, the engine components to which the blades belong include: a low-pressure compressor, a high-pressure compressor, a high-pressure turbine, and a low-pressure turbine; The blade sub-assemblies include rotor blades and stator blades at each stage; The details of the blade parts include the inlet and outlet edges, the edge plate, the blade body, and the blade tip.

[0010] Preferably, the preset evaluation parameter mapping relationship is as follows: The depth of damage to low-pressure compressor blades and high-pressure compressor blades is selected as a key evaluation parameter. For high-pressure compressor blades, the depth and length of pitting damage are selected as key evaluation parameters. The area of ​​ablation damage and coating peeling damage of turbine blades is selected as the key evaluation parameter. Crack damage in turbine blades is evaluated using length and number as key parameters. The depth of notch damage on turbine blades is selected as a key evaluation parameter.

[0011] Preferably, the diagnostic rules stored in the expert knowledge base adopt the "IF-THEN" production rule representation. The condition part consists of a logical combination of structural level, damage type, size type and numerical range, and the conclusion part distinguishes between compressor blades and turbine blades.

[0012] Preferably, the inspection report includes: structural location information, damage parameters, key assessment parameters, and maintenance decisions.

[0013] An intelligent diagnostic expert system for borehole damage of aero-engine blades includes: The data modeling module constructs a structured data model of the engine blades, which includes the hierarchical structure of the engine blades and the corresponding dimensions and damage assessment parameters. The damage parameter input module acquires the damage parameters of the borehole images of the engine blades. The parameter dynamic selection module determines key evaluation parameters based on the preset evaluation parameter mapping relationship and the damage parameters of the borehole image. The rule-based reasoning and diagnosis module matches the structured data model, borehole image damage parameters, and key assessment parameters with the diagnostic rules in the expert knowledge base, and executes the first diagnostic rule whose conditions are fully met to generate the corresponding maintenance decision. The results output module outputs maintenance decisions and generates inspection reports.

[0014] Preferably, it further includes: The human-machine interface displays the structured data model of the engine blades in a hierarchical tree format, allowing users to select components, display maintenance decisions, and generate inspection reports.

[0015] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: The present invention provides an intelligent diagnostic method for borehole damage in aero-engine blades. This method constructs a structured data model of the engine blade, including its hierarchical structure and corresponding dimensions and damage assessment parameters. By constructing this structured data model, the invention systematically encapsulates complex damage tolerance standards for different components, levels, and locations, transforming the process of manually searching for diagnostic standards from massive maintenance manuals into automated data matching, thus greatly improving diagnostic efficiency.

[0016] This invention acquires damage parameters from borehole images of engine blades; based on a preset evaluation parameter mapping relationship, it determines key evaluation parameters using the borehole image damage parameters. By dynamically selecting key evaluation parameters based on damage type, it ensures accurate judgment using the most relevant parameters for different damage modes, overcoming the misjudgment problem caused by improper parameter use in traditional methods.

[0017] This invention matches structured data models, borehole image damage parameters, and key evaluation parameters with diagnostic rules in an expert knowledge base, executes the first diagnostic rule whose conditions are fully met, generates a corresponding maintenance decision, outputs the maintenance decision, and generates a test report. By solidifying the expert experience of senior maintenance personnel and standard maintenance procedures into executable diagnostic rules, and utilizing rule-based reasoning to simulate expert thinking through automated reasoning, this invention effectively reduces reliance on the personal experience of maintenance personnel and significantly improves the consistency of diagnostic results.

[0018] The entire diagnostic process of this invention is transparent and interpretable. The generated test report fully records all information from structural location and damage parameters to decision-making schemes, ensuring the traceability of the decision-making process. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 A flowchart of an intelligent diagnostic method for borehole damage on aero-engine blades provided in an embodiment of the present invention; Figure 2 A flowchart illustrating the dynamic parameter selection logic provided in this embodiment of the invention; Figure 3 This is a schematic diagram of the layout of the human-computer interaction interface provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an intelligent diagnostic expert system for borehole damage of aero-engine blades provided in an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] First, combined Figure 1 The present invention provides an intelligent diagnostic method for borehole damage of aero-engine blades, which includes the following methods: Step S01: Construct a structured data model of the engine blades.

[0023] Specifically, the structured data model defines the hierarchical structure of the engine component to which the blade belongs, the blade sub-component, and the details of the blade part, and associates them with the corresponding dimensions and damage assessment parameters.

[0024] The structured data model of engine blades is displayed in a hierarchical tree format, allowing users to select components and providing an input interface for damage parameters. In the hierarchical structure of engine blades, the engine components to which the blades belong include: Low-Pressure Compressor (LPC), High-Pressure Compressor (HPC), High-Pressure Turbine (HPT), and Low-Pressure Turbine (LPT). Blade sub-components include rotor blades and stator blades at various stages. Blade part details include inlet and exhaust edges, rim plates, blade body, and blade tip. By selecting the hierarchical structure in the structured data model, users can obtain information including component names, sub-component names, and part details.

[0025] Step S02: Obtain the damage parameters of the borehole image of the engine blade.

[0026] Specifically, such as Figure 3 As shown, the device receives damage parameters input by the user after interpreting the borehole image, including the damage type and the corresponding measurement value.

[0027] Step S03: Based on the preset evaluation parameter mapping relationship, key evaluation parameters are determined through borehole image damage parameters.

[0028] Specifically, the evaluation parameter mapping relationship includes a mapping between component-damage type-evaluation parameter, such as... Figure 2 As shown, one or more key evaluation parameters are dynamically assigned to the current diagnostic scenario based on the selected component and the input damage type.

[0029] For low-pressure and high-pressure compressor blades, depth is selected as the key evaluation parameter for injury damage; for high-pressure compressor blades, depth and length are selected as key evaluation parameters for dent damage; for turbine blades, area is selected as the key evaluation parameter for ablation and peel damage; for turbine blades, length and number of cracks are selected as key evaluation parameters; and for turbine blades, depth is selected as the key evaluation parameter for dent and gap damage. Furthermore, for high-pressure compressor blades, the determination of tear, crack, and scratch damage types is not based on specific dimensional measurement parameters.

[0030] Step S04: Match the structured data model, borehole image damage parameters, and key evaluation parameters with the diagnostic rules in the expert knowledge base, and execute the first diagnostic rule whose conditions are fully met to generate the corresponding maintenance decision.

[0031] Specifically, the expert knowledge base stores multiple diagnostic rules built upon maintenance procedures and expert experience. These rules are then used to perform matching and reasoning based on priority, generating maintenance decisions.

[0032] The expert knowledge base covers diagnostic rules for low-pressure compressor (LPC) blades, high-pressure compressor (HPC) blades, high-pressure turbine (HPT) blades, and low-pressure turbine (LPT) blades. The diagnostic rules stored in the expert knowledge base use an "IF-THEN" production rule notation. The condition part consists of a logical combination of structural level, damage type, size type, and numerical range, while the conclusion part distinguishes between compressor blades and turbine blades. Specifically, diagnostic decisions for compressor blades can be represented by A, B, and C, while diagnostic decisions for turbine blades can be represented by A and B.

[0033] The diagnostic decision for compressor blades is as follows: A indicates the damage is within the specified range, allowing continued engine use without excluding the damage; B indicates the damage is within the specified range, but repair is required before engine use; C indicates the damage exceeds the damage tolerance, and the blade is scrapped and returned to the factory. The diagnostic decision for turbine blades is as follows: A indicates the damage is within the specified range, allowing continued engine use without excluding the damage; B indicates the damage exceeds the damage tolerance, and the blade is scrapped and returned to the factory.

[0034] The structural hierarchy information, damage parameters, and key assessment parameters are matched with the diagnostic rules in the expert knowledge base. The diagnostic rules in the expert knowledge base are traversed in descending order of preset rule priority, and the first diagnostic rule whose conditions are fully met is executed to generate the corresponding maintenance decision.

[0035] Step S05: Output maintenance decision and generate inspection report.

[0036] Specifically, it outputs maintenance decisions and generates, for example, Figure 3 The inspection report shown is in a standardized text or table format and includes structural location information, damage parameters, key assessment parameters, and maintenance decisions.

[0037] The intelligent diagnostic method for borehole damage of aero-engine blades in this invention solidifies expert knowledge and maintenance procedures into executable rules, realizing the automation and standardization of borehole damage diagnosis. It effectively overcomes the shortcomings of traditional methods, such as excessive reliance on human experience, low efficiency, and opaque decision-making process, and significantly improves the accuracy and reliability of diagnosis.

[0038] Next, this embodiment of the invention uses a crack at the tip of a high-pressure turbine (HPT) rotor blade of a certain type of twin-shaft gas turbine engine as an example to verify the feasibility of the intelligent diagnostic method for borehole damage of aero-engine blades of the present invention. The process is as follows: S01: Load the engine model according to the predefined hierarchical structure. For example... Figure 3 As shown, users can select sequentially in the hierarchy tree through the human-computer interaction interface: Component: High Pressure Turbine (HPT); Sub-component: First Stage Rotor Blade; Location Details: Blade Tip.

[0039] At this point, the structured data model automatically associates the permissible damage types (such as cracks, pits, notches, etc.) of the part with their corresponding standard evaluation parameters (such as length, depth, area, etc.).

[0040] S02: Inspectors manually interpret the observed borehole images and then input damage information into the human-machine interface, such as... Figure 3 As shown: Damage type: Select "crack"; Measurement values: Length = 2.3 mm, Quantity = 1.

[0041] S03: Based on the determined "HPT" component and "crack" damage type, automatically trigger the preset dynamic selection rules (parameter dynamic selection logic as follows). Figure 2 (As shown).

[0042] Rule determination: For HPT crack damage, length and number are selected as key evaluation parameters. "Length = 2.3mm, Number = 1" is locked as the core parameter for subsequent rule reasoning.

[0043] S04: Traverse all diagnostic rules related to "HPT-Crack" in the expert knowledge base in descending order of priority according to preset rules. Some examples of rules in the expert knowledge base are as follows: Rule 1: if (component == "HPT" and subcomponent == "rotor blade" and damage type == "crack" and length <= 2mm and quantity <= 3): decision = "A"; Rule 2: if (component == "HPT" and subcomponent == "rotor blade" and damage type == "crack" and length > 2mm or quantity > 3): decision = "B"; The parameters of this embodiment (HPT, crack, length = 2.3 mm, quantity = 1) are matched with the above rules. First, the condition of rule 1 (length ≤ 2 mm and quantity ≤ 3) is not met; then, the condition of rule 2 (length > 2 mm or quantity > 3) is fully met. According to the "first match" principle, the diagnostic module immediately executes rule 2 and generates maintenance decision: B.

[0044] S05, Output maintenance decision and generate as follows: Figure 3 The test report shown.

[0045] The intelligent diagnostic expert system for borehole damage of aero-engine blades provided in the embodiments of the present invention is described below. The intelligent diagnostic expert system for borehole damage of aero-engine blades described below can be referred to in correspondence with the intelligent diagnostic method for borehole damage of aero-engine blades described above.

[0046] First, combine Figure 4 This paper introduces an intelligent diagnostic expert system for borehole damage in aero-engine blades, such as... Figure 4 As shown, the intelligent diagnostic expert system for borehole damage of aero-engine blades may include: The data modeling module 101 constructs a structured data model of the engine blades, which includes the hierarchical structure of the engine blades and the corresponding dimensions and damage assessment parameters. Damage parameter input module 102 acquires damage parameters from borehole images of engine blades; The parameter dynamic selection module 103 determines key evaluation parameters based on the preset evaluation parameter mapping relationship and the borehole image damage parameters. The expert knowledge base 104 stores multiple diagnostic rules built based on maintenance procedures and expert experience; The rule reasoning and diagnosis module 105 matches the structured data model, borehole image damage parameters and key evaluation parameters with the diagnosis rules in the expert knowledge base, and executes the first diagnosis rule whose conditions are fully met to generate the corresponding maintenance decision. The output module 106 outputs maintenance decisions and generates a test report.

[0047] Furthermore, expert systems also include: The human-machine interface displays the structured data model of the engine blades in a hierarchical tree format, allowing users to select components, make maintenance decisions, and generate inspection reports.

[0048] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0049] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0050] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent diagnosis of borehole damage in aero-engine blades, characterized in that, include: A structured data model of engine blades is constructed, which includes the hierarchical structure of engine blades and corresponding size and damage assessment parameters. Obtain damage parameters from borehole images of engine blades; Based on the preset evaluation parameter mapping relationship, key evaluation parameters are determined by the damage parameters of borehole images; The structured data model, borehole image damage parameters, and key assessment parameters are matched with diagnostic rules in the expert knowledge base, and the first diagnostic rule whose conditions are fully met is executed to generate the corresponding maintenance decision. Output maintenance decisions and generate inspection reports.

2. The intelligent diagnostic method for borehole damage of aero-engine blades according to claim 1, characterized in that, Also includes: The structured data model of the engine blades is displayed in a hierarchical tree format for users to select components.

3. The intelligent diagnostic method for borehole damage of aero-engine blades according to claim 1, characterized in that, In the hierarchical structure of the engine blades, the engine components to which the blades belong include: low-pressure compressor, high-pressure compressor, high-pressure turbine, and low-pressure turbine. The blade sub-assemblies include rotor blades and stator blades at each stage; The details of the blade parts include the inlet and outlet edges, the edge plate, the blade body, and the blade tip.

4. The intelligent diagnostic method for borehole damage of aero-engine blades according to claim 3, characterized in that, The preset evaluation parameter mapping relationship is as follows: The depth of damage to low-pressure compressor blades and high-pressure compressor blades is selected as a key evaluation parameter. For high-pressure compressor blades, the depth and length of pitting damage are selected as key evaluation parameters. The area of ​​ablation damage and coating peeling damage of turbine blades is selected as the key evaluation parameter. Crack damage in turbine blades is evaluated using length and number as key parameters. The depth of notch damage on turbine blades is selected as a key evaluation parameter.

5. The intelligent diagnostic method for borehole damage of aero-engine blades according to claim 1, characterized in that, The diagnostic rules stored in the expert knowledge base adopt the "IF-THEN" production rule notation. The condition part consists of a logical combination of structural level, damage type, size type and numerical range, and the conclusion part distinguishes between compressor blades and turbine blades.

6. The intelligent diagnostic method for borehole damage of aero-engine blades according to claim 1, characterized in that, The inspection report includes: structural location information, damage parameters, key assessment parameters, and maintenance decisions.

7. An intelligent diagnostic expert system for borehole damage of aero-engine blades, characterized in that, include: The data modeling module constructs a structured data model of the engine blades, which includes the hierarchical structure of the engine blades and the corresponding dimensions and damage assessment parameters. The damage parameter input module acquires the damage parameters of the borehole images of the engine blades. The parameter dynamic selection module determines key evaluation parameters based on the preset evaluation parameter mapping relationship and the damage parameters of the borehole image. The rule-based reasoning and diagnosis module matches the structured data model, borehole image damage parameters, and key assessment parameters with the diagnostic rules in the expert knowledge base, and executes the first diagnostic rule whose conditions are fully met to generate the corresponding maintenance decision. The results output module outputs maintenance decisions and generates inspection reports.

8. The aero-engine blade damage diagnosis system based on borehole images according to claim 7, characterized in that, Also includes: The human-machine interface displays the structured data model of the engine blades in a hierarchical tree format, allowing users to select components, display maintenance decisions, and generate inspection reports.

Images