Engine gas path fault detection method, system, equipment and medium

Abstract

The invention relates to the technical field of engine fault detection, in particular to an engine gas path fault detection method, system and device and a medium. The method comprises the following steps: firstly, preprocessing acquired engine state data to obtain multi-dimensional engine state data; then engine state features are extracted from the multi-dimensional engine state data, and dimension increasing is carried out; and finally, selecting a feature combination with distinction degree from the dimension-increased engine state features, and calling a support vector machine to analyze the feature combination to obtain an engine gas path fault detection result. Fault features are optimized in a dimension increasing mode, hidden fault information is obtained through mining, and the fault detection accuracy is improved; and fault point data is obtained through fitting positioning, so that interference of redundant features and noise in a dimension increasing process is eliminated, and the detection accuracy of fault detection on unbalanced data is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of aero-engine detection, and in particular to an engine gas path fault detection method, system, equipment and medium. Background Art

[0002] Aircraft engines are complex thermodynamic machines that provide propulsion for aircraft flight. During operation, many components are in a state of high speed, high stress, high temperature, and high pressure for a long time, which makes the time of engine failure uncertain. As an important part of the aircraft, the operating status of the engine directly affects its safe service. Therefore, timely and accurate engine fault detection and management can not only achieve condition-based maintenance and reduce maintenance costs, but also improve flight safety; by researching and developing accurate and reliable engine fault detection technology, the safety and economy of the aircraft operation process can be effectively enhanced.

[0003] The existing gas path fault detection methods are affected by sensor accuracy and environmental interference. Flight monitoring data often contains more redundant features and noise, which increases the burden of model training and reduces the fault detection accuracy. In addition, the number of normal samples in the monitoring data collected during actual engine operation is much larger than the number of fault samples. The extremely unbalanced sample distribution affects the learning process of the fault detection method and weakens the generalization ability of the model. Summary of the invention

[0004] Aiming at the problem that the existing gas path fault detection method is easily disturbed by redundant features and noise in flight monitoring data, resulting in reduced detection accuracy, the present invention proposes an engine gas path fault detection method, system, equipment and medium; the method first preprocesses the acquired engine status data to obtain multi-dimensional engine status data; then extracts engine status features from the multi-dimensional engine status data and increases the dimension; finally, selects a feature combination with discrimination from the engine status features after the dimension increase, calls a support vector machine to analyze the feature combination, and obtains the engine gas path fault detection result; the fault features are optimized by increasing the dimension, and the hidden fault information is mined, thereby improving the fault detection accuracy.

[0005] The specific implementation contents of the present invention are as follows:

[0006] An engine gas circuit fault detection method comprises the following steps: firstly, preprocessing the acquired engine status data to obtain multi-dimensional engine status data; then extracting engine status features from the multi-dimensional engine status data and increasing the dimension; finally, selecting a feature combination with discrimination from the increased-dimensional engine status features, calling a support vector machine to analyze the feature combination, and obtaining an engine gas circuit fault detection result.

[0007] In order to better implement the present invention, further, the engine gas path fault detection method specifically includes the following steps:

[0008] Step S1: Obtain engine status data from engine post-flight data and pre-process it;

[0009] Step S2: extracting engine state features from the multi-dimensional engine state data, and increasing the dimension of the engine state features according to a set increasing dimension type; the increasing dimension type includes exponential increasing dimension, logarithmic increasing dimension, differential increasing dimension and combined increasing dimension;

[0010] Step S3: performing feature selection on the dimension-increased engine state features to obtain a feature combination with discrimination, and analyzing the feature combination by calling a support vector machine to obtain an engine gas path fault detection result.

[0011] In order to better implement the present invention, further, the step S1 specifically includes the following steps:

[0012] Step S11: acquiring engine post-flight data, and extracting engine status data from the engine post-flight data;

[0013] Step S12: pre-process the engine state data to obtain multi-dimensional engine state data.

[0014] In order to better implement the present invention, further, the step S2 specifically includes the following steps:

[0015] Step S21: extracting engine state features from multi-dimensional engine state data;

[0016] Step S22: extracting the engine state features through linear combination, logarithmic transformation and exponential transformation to obtain expanded engine state features;

[0017] Step S23: Dimensionally expand the engine status characteristics according to the set dimension-increasing type.

[0018] In order to better implement the present invention, further, the step S3 specifically includes the following steps:

[0019] Step S31: calling the nearest component analysis algorithm to perform feature selection on the engine state features after dimension increase, and calculate the feature score;

[0020] Step S32: Calculate the feature weight vector according to the set regularization coefficient to obtain the feature ranking result;

[0021] Step S33: calling the principal component analysis method, combining the feature evaluation score and the feature sorting result analysis to obtain a feature combination with discrimination, and using it as the optimized engine state feature;

[0022] Step S34: calling the support vector machine to analyze the optimized engine state characteristics to obtain the engine gas path fault detection result.

[0023] In order to better implement the present invention, further, the engine gas path fault detection method also includes:

[0024] Step S4: Obtain fault data from the engine fault results, and fit the fault data in a normal distribution manner according to the set confidence interval to obtain expanded fault data, input the expanded fault data into the support vector machine, and obtain the fault point data in combination with the set dimension increase type.

[0025] Based on the above-mentioned engine gas path fault detection method, in order to better realize the present invention, further, an engine gas path fault detection system is proposed, which is used to execute the above-mentioned engine gas path fault detection method; it includes a preprocessing unit, a dimension increasing unit, and a detection unit;

[0026] The preprocessing unit is used to preprocess the acquired engine state data to obtain multi-dimensional engine state data;

[0027] The dimension increasing unit is used to extract engine state features from the multi-dimensional engine state data and increase the dimension;

[0028] The detection unit is used to select a feature combination with discrimination from the engine state features after dimension increase, call a support vector machine to analyze the feature combination, and obtain an engine gas path fault detection result.

[0029] In order to better implement the present invention, further, the engine gas path fault detection system also includes a positioning unit;

[0030] The positioning unit is used to obtain fault data from the engine fault results, and fit the fault data in a normal distribution manner according to a set confidence interval to obtain expanded fault data, input the expanded fault data into a support vector machine, and obtain fault point data in combination with a set dimensionality increase type.

[0031] Based on the above-proposed engine gas circuit fault detection method, in order to better realize the present invention, further, an electronic device is proposed, including a memory and a processor; a computer program is stored on the memory; when the computer program is executed on the processor, the above-proposed engine gas circuit fault detection method is implemented.

[0032] Based on the above-proposed engine gas circuit fault detection method, in order to better realize the present invention, further, a computer-readable storage medium is proposed, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned engine gas circuit fault detection method is implemented.

[0033] The present invention has the following beneficial effects:

[0034] (1) The present invention increases fault features by increasing dimensions, obtains a more discriminative feature combination, mines hidden information of fault features, and improves fault detection accuracy and computational efficiency.

[0035] (2) The present invention obtains fault point data by fitting, eliminates the interference of redundant features and noise in the dimensionality increase process, and improves the detection accuracy of fault detection on unbalanced data. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The present invention provides a schematic block diagram of the overall process of the engine gas circuit fault detection method. DETAILED DESCRIPTION

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be understood that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and therefore should not be regarded as limiting the scope of protection. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical personnel in this field without making creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "disposed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] Embodiment 1:

[0040] This embodiment proposes an engine gas path fault detection method, which first pre-processes the acquired engine state data to obtain multi-dimensional engine state data; then extracts engine state features from the multi-dimensional engine state data and increases the dimension; finally, selects a feature combination with discrimination from the increased-dimensional engine state features, calls a support vector machine to analyze the feature combination, and obtains an engine gas path fault detection result, which specifically includes the following steps:

[0041] Step S1: Obtain engine status data from engine post-flight data and pre-process it.

[0042] Furthermore, the step S1 specifically includes the following steps:

[0043] Step S11: acquiring engine post-flight data, and extracting engine status data from the engine post-flight data;

[0044] Step S12: pre-process the engine state data to obtain multi-dimensional engine state data.

[0045] Step S2: extracting engine state features from multi-dimensional engine state data, and increasing the dimension of the engine state features according to a set increasing dimension type; the increasing dimension type includes exponential increasing dimension, logarithmic increasing dimension, differential increasing dimension and combined increasing dimension.

[0046] Furthermore, the step S2 specifically includes the following steps:

[0047] Step S21: extracting engine state features from multi-dimensional engine state data;

[0048] Step S22: extracting the engine state features through linear combination, logarithmic transformation and exponential transformation to obtain expanded engine state features;

[0049] Step S23: Dimensionally expand the engine status characteristics according to the set dimension-increasing type.

[0050] Step S3: performing feature selection on the dimension-increased engine state features to obtain a feature combination with discrimination, and analyzing the feature combination by calling a support vector machine to obtain an engine gas path fault detection result.

[0051] Furthermore, the step S3 specifically includes the following steps:

[0052] Step S31: calling the nearest component analysis algorithm to perform feature selection on the engine state features after dimension increase, and calculate the feature score;

[0053] Step S32: Calculate the feature weight vector according to the set regularization coefficient to obtain the feature ranking result;

[0054] Step S33: calling the principal component analysis method, combining the feature evaluation score and the feature sorting result analysis to obtain a feature combination with discrimination, and using it as the optimized engine state feature;

[0055] Step S34: calling the support vector machine to analyze the optimized engine state characteristics to obtain the engine gas path fault detection result.

[0056] Step S4: Obtain fault data from the engine fault results, and fit the fault data in a normal distribution manner according to the set confidence interval to obtain expanded fault data, input the expanded fault data into the support vector machine, and obtain the fault point data in combination with the set dimension increase type.

[0057] Working principle: This embodiment first preprocesses the acquired engine status data to obtain multi-dimensional engine status data; then extracts engine status features from the multi-dimensional engine status data and increases the dimension; finally, selects a feature combination with discriminability from the engine status features after the dimension increase, calls a support vector machine to analyze the feature combination, and obtains the engine gas path fault detection result; optimizes the fault features by increasing the dimension, mines the hidden fault information, and improves the fault detection accuracy.

[0058] Embodiment 2:

[0059] This embodiment is based on the above embodiment 1. Figure 1 As shown, a specific embodiment is described in detail.

[0060] Step S1: Obtain engine status data from engine post-flight data and pre-process it.

[0061] Step S11: acquiring engine post-flight data, and extracting engine status data from the engine post-flight data;

[0062] Step S12: pre-process the engine state data to obtain multi-dimensional engine state data.

[0063] Step S2: extracting engine state features from multi-dimensional engine state data, and increasing the dimension of the engine state features according to a set increasing dimension type; the increasing dimension type includes exponential increasing dimension, logarithmic increasing dimension, differential increasing dimension and combined increasing dimension.

[0064] This embodiment performs feature dimension increase on the preprocessed post-flight engine data, including exponential, logarithmic, combination, etc. In order to obtain a distinguishing feature combination from the feature data after dimension increase, the nearest component analysis algorithm is called for feature analysis and extraction, and the principal component analysis method is used for feature optimization to obtain more distinguishing fault features for fault detection.

[0065] Step S3: performing feature selection on the dimension-increased engine state features to obtain a feature combination with discrimination, and analyzing the feature combination by calling a support vector machine to obtain an engine gas path fault detection result.

[0066] The neighbor component analysis algorithm adopted in this embodiment includes: first, calling the distance function to calculate the distance between features, then calling the similarity function to calculate the fault probability estimate between the feature and the neighbor feature, and finally calculating the weight vector according to the set regularization term and the calculated fault probability estimate, performing feature selection, and obtaining a more discriminative fault feature for fault detection.

[0067] Step S4: Obtain fault data from the engine fault results, and fit the fault data in a normal distribution manner according to the set confidence interval to obtain expanded fault data, input the expanded fault data into the support vector machine, and obtain the fault point data in combination with the set dimension increase type.

[0068] This embodiment takes into account the processing of unbalanced data sets. Most of the engine gas path failures are caused by the degradation of the engine gas path performance. For the engine gas path failure, if the fault point can be accurately located, the workload of fault detection will be greatly reduced. Therefore, after obtaining the test results, the fault data is obtained, and the fault data is fitted according to the set confidence interval normal distribution. The accurate positioning of the fault point is achieved by combining the dimensionality-increased features, which significantly improves the accuracy of fault detection.

[0069] The other parts of this embodiment are the same as those of the above-mentioned embodiment 1, and thus will not be described in detail.

[0070] Embodiment 3:

[0071] Based on any one of the above-mentioned embodiments 1-2, this embodiment proposes an engine gas path fault detection system for executing the above-mentioned engine gas path fault detection method; comprising a preprocessing unit, a dimension increasing unit, and a detection unit;

[0072] The preprocessing unit is used to preprocess the acquired engine state data to obtain multi-dimensional engine state data;

[0073] The dimension increasing unit is used to extract engine state features from the multi-dimensional engine state data and increase the dimension;

[0074] The detection unit is used to select a feature combination with discrimination from the engine state features after dimension increase, call a support vector machine to analyze the feature combination, and obtain an engine gas path fault detection result.

[0075] In order to better implement the present invention, further, the engine gas path fault detection system also includes a positioning unit;

[0076] The positioning unit is used to obtain fault data from the engine fault results, and fit the fault data in a normal distribution manner according to a set confidence interval to obtain expanded fault data, input the expanded fault data into a support vector machine, and obtain fault point data in combination with a set dimensionality increase type.

[0077] This embodiment also proposes an electronic device, including a memory and a processor; a computer program is stored in the memory; when the computer program is executed on the processor, the above-mentioned engine gas path fault detection method is implemented.

[0078] This embodiment further proposes a computer-readable storage medium, on which computer instructions are stored; when the computer instructions are executed on the above-mentioned electronic device, the above-mentioned engine gas circuit fault detection method is implemented.

[0079] The other parts of this embodiment are the same as any one of the above-mentioned embodiments 1-2, so they will not be repeated here.

[0080] The processor involved in the embodiments of the present application may be a chip. For example, it may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0081] The memory involved in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0082] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0083] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0085] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0086] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one device or distributed on multiple devices. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0087] In addition, each functional module in each embodiment of the present application may be integrated into one device, or each module may exist physically separately, or two or more modules may be integrated into one device.

[0088] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or may contain one or more servers, data centers and other data storage devices that can be integrated with a medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0089] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for detecting engine gas path faults, characterized in that: First, the acquired engine status data is preprocessed to obtain multi-dimensional engine status data; then, engine status features are extracted from the multi-dimensional engine status data and the dimensions are increased; finally, a feature combination with discriminability is selected from the engine status features after the dimension increase, and a support vector machine is called to analyze the feature combination to obtain the engine gas path fault detection result.

2. The engine gas path fault detection method according to claim 1, characterized in that: The engine gas path fault detection method specifically comprises the following steps: Step S1: Obtain engine status data from engine post-flight data and pre-process it; Step S2: extracting engine state features from the multi-dimensional engine state data, and increasing the dimension of the engine state features according to a set increasing dimension type; the increasing dimension type includes exponential increasing dimension, logarithmic increasing dimension, differential increasing dimension and combined increasing dimension; Step S3: performing feature selection on the dimension-increased engine state features to obtain a feature combination with discrimination, and analyzing the feature combination by calling a support vector machine to obtain an engine gas path fault detection result.

3. The engine gas path fault detection method according to claim 2, characterized in that: The step S1 specifically includes the following steps: Step S11: acquiring engine post-flight data, and extracting engine status data from the engine post-flight data; Step S12: pre-process the engine state data to obtain multi-dimensional engine state data.

4. The engine gas path fault detection method according to claim 2, characterized in that: The step S2 specifically includes the following steps: Step S21: extracting engine state features from multi-dimensional engine state data; Step S22: extracting the engine state features through linear combination, logarithmic transformation and exponential transformation to obtain expanded engine state features; Step S23: Dimensionally expand the engine status characteristics according to the set dimension-increasing type.

5. The engine gas path fault detection method according to claim 4, characterized in that: The step S3 specifically comprises the following steps: Step S31: calling the nearest component analysis algorithm to perform feature selection on the engine state features after dimension increase, and calculate the feature score; Step S32: Calculate the feature weight vector according to the set regularization coefficient to obtain the feature ranking result; Step S33: calling the principal component analysis method, combining the feature evaluation score and the feature sorting result analysis to obtain a feature combination with discrimination, and using it as the optimized engine state feature; Step S34: calling the support vector machine to analyze the optimized engine state characteristics to obtain the engine gas path fault detection result.

6. The engine gas path fault detection method according to claim 5, characterized in that: The engine gas path fault detection method further includes: Step S4: Obtain fault data from the engine fault results, and fit the fault data in a normal distribution manner according to the set confidence interval to obtain expanded fault data, input the expanded fault data into the support vector machine, and obtain the fault point data in combination with the set dimension increase type.

7. An engine gas path fault detection system, used to execute the engine gas path fault detection method as claimed in claim 1; characterized in that: It includes a pre-processing unit, a dimension increasing unit and a detection unit; The preprocessing unit is used to preprocess the acquired engine state data to obtain multi-dimensional engine state data; The dimension increasing unit is used to extract engine state features from the multi-dimensional engine state data and increase the dimension; The detection unit is used to select a feature combination with discrimination from the engine state features after dimension increase, call a support vector machine to analyze the feature combination, and obtain an engine gas path fault detection result.

8. An engine gas circuit fault detection system according to claim 7, characterized in that: The engine gas path fault detection system also includes a positioning unit; The positioning unit is used to obtain fault data from the engine fault results, and fit the fault data in a normal distribution manner according to a set confidence interval to obtain expanded fault data, input the expanded fault data into a support vector machine, and obtain fault point data in combination with a set dimensionality increase type.

9. An electronic device, characterized in that: It comprises a memory and a processor; the memory stores a computer program; when the computer program is executed on the processor, the engine gas path fault detection method as described in any one of claims 1-6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions; when the computer instructions are executed on the electronic device as claimed in claim 9, the engine gas path fault detection method as claimed in any one of claims 1-6 is implemented.

Images