A method, apparatus, equipment, and storage medium for detecting defects in engine blades.

Abstract

This invention discloses a method, apparatus, device, and storage medium for detecting defects in engine blades. The method includes: acquiring apparent attribute data of the engine blade to be tested; mapping the apparent attribute data to a preset standard model to obtain mapped data; calculating the difference signal between the mapped data and the preset standard model; comparing the difference signal with a preset threshold; and determining whether the engine blade to be tested has a defect based on the comparison result. The technical solution provided by this invention, by employing statistical analysis of apparent attributes and mapping to a standard model, can more stably, efficiently, accurately, and cost-effectively detect abnormal outlier features of engine blades, thereby promptly identifying potential defects in engine blades and ensuring the safe and stable operation of the engine.

Description

Technical Field

[0001] The present invention relates to the field of engine technology, and in particular to a method, apparatus, device and storage medium for detecting defects in engine blades. Background Technology

[0002] Engine blades are a crucial component of an engine, and their performance and quality directly impact the engine's safety and reliability. Therefore, regular defect inspection of engine blades is essential. Currently, commonly used methods for engine blade defect inspection include ultrasonic testing, eddy current testing, and magnetic particle testing. While these methods can detect surface and internal defects in blades, they also have drawbacks, such as complex operation, expensive equipment, low inspection efficiency, and stringent environmental requirements. Furthermore, traditional defect inspection methods often rely on manual inspection or pre-defined models of specific defects, which are both time-consuming and prone to missed defects. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and storage medium for detecting defects in engine blades, enabling stable, efficient, accurate, and low-cost defect detection of engine blades.

[0004] In a first aspect, embodiments of the present invention provide a method for detecting defects in engine blades, the method comprising:

[0005] Obtain the apparent property data of the engine blades under test;

[0006] The apparent attribute data is mapped to a preset standard model to obtain mapped data;

[0007] Calculate the difference signal between the mapped data and the preset standard model;

[0008] The differential signal is compared with a preset threshold, and the test engine blade is determined to have defects based on the comparison result.

[0009] Optionally, acquiring the apparent attribute data of the engine blade under test includes:

[0010] Acquire image data of the engine blades under test;

[0011] The apparent features of the engine blade under test are extracted based on the image data;

[0012] The appearance attribute data is generated based on the appearance features.

[0013] Optionally, the appearance features include at least one of a color histogram, a texture orientation field, a shape profile, and a reflectance distribution map.

[0014] Optionally, before extracting the apparent features of the engine blade under test based on the image data, the method further includes:

[0015] The image data is preprocessed, and the preprocessing includes at least one of denoising, enhancement, and correction.

[0016] Optionally, before mapping the apparent attribute data to a preset standard model to obtain mapped data, the method further includes:

[0017] Construct the preset specification model;

[0018] Obtain sample data of the apparent attributes of normal leaves;

[0019] The preset standard model is trained using the apparent attribute sample data.

[0020] Optionally, mapping the apparent attribute data to a preset standardized model to obtain mapped data includes:

[0021] A mapping algorithm is used to map the apparent attribute data to the same dimensional space of the preset standard model. The mapping algorithm includes linear mapping or nonlinear mapping.

[0022] Optionally, calculating the difference signal between the mapped data and the preset standard model includes:

[0023] The differential signal is calculated using Euclidean distance, Mahalanobis distance, or cosine distance.

[0024] Secondly, embodiments of the present invention also provide a defect detection device for engine blades, the device comprising:

[0025] The apparent data acquisition module is used to acquire the apparent attribute data of the engine blades under test.

[0026] The appearance data mapping module is used to map the appearance attribute data to a preset standard model to obtain mapped data.

[0027] The differential signal calculation module is used to calculate the differential signal between the mapping data and the preset standard model;

[0028] The blade defect determination module is used to compare the differential signal with a preset threshold and determine whether the engine blade under test has a defect based on the comparison result.

[0029] Thirdly, embodiments of the present invention also provide a computer device, the computer device comprising:

[0030] One or more processors;

[0031] Memory, used to store one or more programs;

[0032] When the one or more programs are executed by the one or more processors, the one or more processors implement the engine blade defect detection method provided in any embodiment of the present invention.

[0033] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the defect detection method for engine blades provided in any embodiment of the present invention.

[0034] This invention provides a method for detecting defects in engine blades. First, the apparent attribute data of the engine blade to be tested is acquired. Then, the obtained apparent attribute data is mapped onto a preset standard model to obtain mapped data. Next, the difference signal between the mapped data and the preset standard model is calculated. Finally, the obtained difference signal is compared with a preset threshold, thereby determining whether the engine blade to be tested has defects based on the comparison result. The engine blade defect detection method provided by this invention, by employing apparent attribute statistics and standard model mapping, can more stably, efficiently, accurately, and cost-effectively detect abnormal outlier features of engine blades, thereby timely identifying potential defects in engine blades and ensuring the safe and stable operation of the engine. Attached Figure Description

[0035] Figure 1 This is a flowchart of a defect detection method for engine blades provided in Embodiment 1 of the present invention;

[0036] Figure 2 This is a schematic diagram of the defect detection device for engine blades provided in Embodiment 2 of the present invention;

[0037] Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. Detailed Implementation

[0038] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0039] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. The process can be terminated when its operation is complete, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0040] Example 1

[0041] Figure 1 This is a flowchart of a defect detection method for engine blades provided in Embodiment 1 of the present invention. This embodiment is applicable to defect detection of blades at various stages in an engine, and also to defect detection of other types of mechanical components with measurable apparent properties and definable standard models. This method can be executed by the engine blade defect detection device provided in this embodiment of the invention. This device can be implemented in hardware and / or software, and is generally integrated into a computer device, specifically, an engine blade defect detection device. Figure 1 As shown, the specific steps include the following:

[0042] S11. Obtain the apparent attribute data of the engine blades to be tested.

[0043] Specifically, apparent attributes refer to the characteristics of light reflection on an object's surface under specific light source conditions, such as color, texture, shape, and reflectivity. Optionally, acquiring the apparent attribute data of the engine blade under test includes: acquiring image data of the engine blade under test; extracting apparent features of the engine blade under test based on the image data; and generating the apparent attribute data based on the apparent features. Specifically, image data of the engine blade under test can be acquired using sensors or high-precision imaging devices, such as high-precision cameras, laser scanners, or borescopes, thereby acquiring detailed apparent attribute information of the engine blade under test. This information can be used as part of the apparent attributes of the engine blade under test, providing a data basis for subsequent defect detection. After obtaining the image data of the engine blade under test, apparent features can be extracted from the image data, thereby generating the required apparent attribute data based on the extracted apparent features. Optionally, the apparent features include at least one of color histogram, texture direction field, shape contour, and reflectivity distribution map. When there is only one appearance feature, the extracted appearance feature can be directly used as the required appearance attribute data. When there are multiple appearance features, multiple appearance features can be combined to generate the required appearance attribute data.

[0044] Optionally, before extracting the apparent features of the engine blade under test from the image data, the method further includes: preprocessing the image data, wherein the preprocessing includes at least one of denoising, enhancement, and correction. By first preprocessing the acquired image data, the subsequent processing results can be made more accurate and reliable.

[0045] S12. Map the apparent attribute data to a preset standard model to obtain mapped data.

[0046] Specifically, a pre-defined standard model can be used to represent the common apparent attributes of normal blades, which can be obtained by statistically analyzing the color distribution, texture arrangement patterns, and shape contours of normal blades. After obtaining the apparent attribute data of the engine blade under test, the apparent attribute data can first be mapped to the pre-defined standard model to obtain corresponding mapped data, which can then be compared with the pre-defined standard model. Optionally, mapping the apparent attribute data to the pre-defined standard model to obtain mapped data includes: using a mapping algorithm to map the apparent attribute data to the same dimensional space of the pre-defined standard model, where the mapping algorithm includes linear mapping or nonlinear mapping.

[0047] Optionally, before mapping the apparent attribute data to a preset standard model to obtain mapped data, the method further includes: constructing the preset standard model; obtaining apparent attribute sample data of normal leaves; and training the preset standard model using the apparent attribute sample data. The preset standard model can also be established using algorithms such as deep learning and neural networks to improve the model's accuracy and robustness.

[0048] S13. Calculate the difference signal between the mapping data and the preset standard model.

[0049] Specifically, after mapping is completed, the difference signal between the obtained mapped data and the preset standard model can be calculated. Optionally, calculating the difference signal between the mapped data and the preset standard model includes using Euclidean distance, Mahalanobis distance, or cosine distance. The magnitude of the difference signal represents the degree of deviation between the actual apparent properties of the tested engine blade and its normal state, i.e., the strength of the outlier characteristic. The calculation of the difference signal can be automatically completed using machine learning algorithms to improve the accuracy and speed of detection.

[0050] S14. Compare the differential signal with a preset threshold, and determine whether the engine blade under test has a defect based on the comparison result.

[0051] Specifically, after calculating the differential signal, it can be compared with a preset threshold. If the differential signal exceeds the preset threshold, it can be determined that the engine blade under test may have a defect, and the blade can be marked so that maintenance personnel can be advised to conduct further inspections. The preset threshold can be set according to actual needs and experience, or it can be automatically completed using machine learning algorithms to improve the accuracy and speed of detection. Furthermore, based on the selected appearance attributes and the final comparison results, the defect type, defect location, defect severity, and specific inspection recommendations for the engine blade under test can be determined.

[0052] Based on the above technical solution, multiple engine blade defect detection devices can be used to simultaneously detect defects in multiple levels of blades on the engine. Each engine blade defect detection device can detect one level of blades. The apparent attribute data of each level of blade can be acquired separately and mapped to a preset standard model to obtain corresponding mapping data. Then, the difference signal between the mapping data of each level of blade and the preset standard model is calculated, and a preset threshold is used to determine whether each difference signal exceeds the normal range. This marks blades at each level that may have defects. The specific process can be found in the above description. Furthermore, each engine blade defect detection device can locally display the detection results of the corresponding level of blades and can also upload the detection results to a central server for aggregation, analysis, and storage. The central server can also communicate with a remote online terminal to monitor the working status and detection results of each engine blade defect detection device in real time.

[0053] The technical solution provided in this invention first acquires the apparent attribute data of the engine blade under test, then maps the obtained apparent attribute data to a preset standard model to obtain mapped data, then calculates the difference signal between the mapped data and the preset standard model, and finally compares the obtained difference signal with a preset threshold to determine whether there are defects in the engine blade under test based on the comparison result. By using apparent attribute statistics and standard model mapping, abnormal outlier characteristics of engine blades can be detected more stably, efficiently, accurately, and at low cost, thereby timely discovering potential defects in engine blades and ensuring the safe and stable operation of the engine.

[0054] Example 2

[0055] Figure 2 This is a schematic diagram of the engine blade defect detection device provided in Embodiment 2 of the present invention. This device can be implemented in hardware and / or software, and is generally integrated into a computer device to execute the engine blade defect detection method provided in any embodiment of the present invention. Figure 2As shown, the device includes:

[0056] Appearance data acquisition module 21 is used to acquire the appearance attribute data of the engine blade under test;

[0057] The appearance data mapping module 22 is used to map the appearance attribute data to a preset standard model to obtain mapped data.

[0058] Differential signal calculation module 23 is used to calculate the differential signal between the mapping data and the preset standard model;

[0059] The blade defect determination module 24 is used to compare the differential signal with a preset threshold and determine whether the engine blade under test has a defect based on the comparison result.

[0060] The technical solution provided in this invention first acquires the apparent attribute data of the engine blade under test, then maps the obtained apparent attribute data to a preset standard model to obtain mapped data, then calculates the difference signal between the mapped data and the preset standard model, and finally compares the obtained difference signal with a preset threshold to determine whether there are defects in the engine blade under test based on the comparison result. By using apparent attribute statistics and standard model mapping, abnormal outlier characteristics of engine blades can be detected more stably, efficiently, accurately, and at low cost, thereby timely discovering potential defects in engine blades and ensuring the safe and stable operation of the engine.

[0061] Based on the above technical solution, optionally, the apparent data acquisition module 21 includes:

[0062] An image data acquisition unit is used to acquire image data of the engine blade under test.

[0063] The appearance feature extraction unit is used to extract the appearance features of the engine blade under test based on the image data.

[0064] The appearance data generation unit is used to generate the appearance attribute data based on the appearance features.

[0065] Based on the above technical solution, optionally, the appearance features include at least one of color histogram, texture direction field, shape profile and reflectance distribution map.

[0066] Based on the above technical solution, optionally, the apparent data acquisition module 21 also includes:

[0067] An image data preprocessing unit is configured to preprocess the image data before extracting the apparent features of the engine blade under test from the image data, wherein the preprocessing includes at least one of denoising, enhancement, and correction.

[0068] Based on the above technical solution, optionally, the defect detection device for the engine blade also includes:

[0069] The standard model construction module is used to construct the preset standard model before mapping the appearance attribute data to the preset standard model to obtain the mapped data;

[0070] The sample data acquisition module is used to acquire sample data of the apparent attributes of normal leaves;

[0071] The standardized model training module is used to train the preset standardized model using the apparent attribute sample data.

[0072] Based on the above technical solution, optionally, the apparent data mapping module 22 is specifically used for:

[0073] A mapping algorithm is used to map the apparent attribute data to the same dimensional space of the preset standard model. The mapping algorithm includes linear mapping or nonlinear mapping.

[0074] Based on the above technical solution, optionally, the differential signal calculation module 23 is specifically used for:

[0075] The differential signal is calculated using Euclidean distance, Mahalanobis distance, or cosine distance.

[0076] The engine blade defect detection device provided in this embodiment of the invention can execute the engine blade defect detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0077] It is worth noting that in the embodiments of the above-mentioned defect detection device for engine blades, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0078] Example 3

[0079] Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention, showing a block diagram of an exemplary computer device suitable for implementing the embodiments of the present invention. Figure 3 The computer device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. Figure 3 As shown, the computer device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the computer device can be one or more. Figure 3Taking a processor 31 as an example, the processor 31, memory 32, input device 33, and output device 34 in a computer device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0080] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the engine blade defect detection method in this embodiment of the invention (e.g., the apparent data acquisition module 21, apparent data mapping module 22, differential signal calculation module 23, and blade defect determination module 24 in the engine blade defect detection device). The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 32, thereby realizing the aforementioned engine blade defect detection method.

[0081] The memory 32 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 32 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, the memory 32 may further include memory remotely located relative to the processor 31, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0082] The input device 33 can be used to acquire apparent attribute data of the engine blades under test, and to generate key signal inputs related to user settings and function control of the computer equipment. The output device 34 may include a display screen for displaying the final test results, etc. This device can be widely used in industrial production, greatly improving the operating safety and efficiency of engines.

[0083] Example 4

[0084] Embodiment 4 of the present invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a defect detection method for engine blades, the method comprising:

[0085] Obtain the apparent property data of the engine blades under test;

[0086] The apparent attribute data is mapped to a preset standard model to obtain mapped data;

[0087] Calculate the difference signal between the mapped data and the preset standard model;

[0088] The differential signal is compared with a preset threshold, and the test engine blade is determined to have defects based on the comparison result.

[0089] Storage media can be any type of memory device or storage device. The term "storage media" is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements. Storage media may also include other types of memory or combinations thereof. Furthermore, storage media may reside in a computer system in which the program is executed, or may reside in a different second computer system connected to the computer system via a network (such as the Internet). The second computer system can provide program instructions to the computer for execution. The term "storage media" can include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). Storage media may store program instructions (e.g., specifically implemented as a computer program) that can be executed by one or more processors.

[0090] Of course, the computer-executable instructions provided in the embodiments of the present invention are not limited to the method operations described above, but can also perform related operations in the defect detection method for engine blades provided in any embodiment of the present invention.

[0091] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0092] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0093] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0094] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for detecting defects in engine blades, characterized in that, include: Obtain the apparent property data of the engine blades under test; The apparent attribute data is mapped to a preset standard model to obtain mapped data; Calculate the difference signal between the mapped data and the preset standard model; The differential signal is compared with a preset threshold, and the presence of defects in the engine blade under test is determined based on the comparison result. The step of mapping the apparent attribute data to a preset standardized model to obtain mapped data includes: A mapping algorithm is used to map the apparent attribute data to the same dimensional space of the preset standard model. The mapping algorithm includes linear mapping or nonlinear mapping. The calculation of the difference signal between the mapped data and the preset standard model includes: The differential signal is calculated using Euclidean distance, Mahalanobis distance, or cosine distance.

2. The defect detection method for engine blades according to claim 1, characterized in that, The acquisition of apparent attribute data of the engine blade under test includes: Acquire image data of the engine blades under test; The apparent features of the engine blade under test are extracted based on the image data; The appearance attribute data is generated based on the appearance features.

3. The defect detection method for engine blades according to claim 2, characterized in that, The apparent features include at least one of color histogram, texture orientation field, shape profile, and reflectance distribution map.

4. The defect detection method for engine blades according to claim 2, characterized in that, Before extracting the apparent features of the engine blade under test based on the image data, the method further includes: The image data is preprocessed, and the preprocessing includes at least one of denoising, enhancement, and correction.

5. The defect detection method for engine blades according to claim 1, characterized in that, Before mapping the apparent attribute data to a preset standard model to obtain the mapped data, the method further includes: Construct the preset specification model; Obtain sample data of the apparent attributes of normal leaves; The preset standard model is trained using the apparent attribute sample data.

6. A defect detection device for engine blades, characterized in that, include: The apparent data acquisition module is used to acquire the apparent attribute data of the engine blades under test. The appearance data mapping module is used to map the appearance attribute data to a preset standard model to obtain mapped data. The differential signal calculation module is used to calculate the differential signal between the mapping data and the preset standard model; The blade defect determination module is used to compare the differential signal with a preset threshold and determine whether the engine blade under test has a defect based on the comparison result. The apparent data mapping module is specifically used for: A mapping algorithm is used to map the apparent attribute data to the same dimensional space of the preset standard model. The mapping algorithm includes linear mapping or nonlinear mapping. The differential signal calculation module is specifically used for: The differential signal is calculated using Euclidean distance, Mahalanobis distance, or cosine distance.

7. A computer device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the defect detection method for engine blades as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the defect detection method for engine blades as described in any one of claims 1-5.

Images