Self-adaptive weak feature extraction method for liquid rocket engine and related device

Abstract

The invention discloses a self-adaptive weak feature extraction method for a liquid rocket engine and a related device. The method comprises the following steps: constructing a combined function D based on a hyperelliptic function D1, a rectangular function, an exponential function D2 and a sign function; performing second-order synchronous compression transformation on the acquired signal to obtain a second-order synchronous compression transformation result; performing product operation on the combined function D and a second-order synchronous compression transformation result to obtain an energy function U; and according to the energy function U, the weak characteristics of the liquid rocket engine under the weak impact working condition are extracted. The method and the related device can extract the weak characteristics of the liquid rocket engine under the weak impact working condition.

Description

Technical Field

[0001] The invention belongs to the technical field of liquid aero-engine fault diagnosis, and relates to an adaptive weak feature extraction method and related devices for liquid rocket engines. Background Art

[0002] Liquid rocket engines are crucial for space travel. The successful full-scale test run of a 500tf liquid oxygen / kerosene rocket engine marks a new milestone in liquid propulsion technology for spaceflight, but also presents new challenges for the safety and reliability of rocket launches. The new generation of high-thrust liquid rocket engines boasts not only greater power but also more complex structures and more extreme operating conditions. Accidents often result in severe economic losses and casualties. Therefore, the importance of rocket engine fault diagnosis is self-evident. However, liquid rocket engines generate a large amount of signal data during operation, such as vibration, pressure, and temperature. These signals are often accompanied by complex noise and nonlinear characteristics. Furthermore, extensive test runs and rocket flight tests of high-pressure staged-fire liquid oxygen / kerosene engines have demonstrated that potential danger points in engine operation often occur during turbopump startup and operating condition adjustment, a critical stage for the initiation and propagation of many liquid rocket engine faults. These fault signatures often exist amidst strong interference, making them difficult to detect. Therefore, effectively extracting these subtle fault signatures presents a key technical challenge.

[0003] Advanced time-frequency analysis methods are an excellent way to accurately and quickly detect fault characteristics of signals from large equipment, such as liquid rocket engines, under complex operating conditions. However, current time-frequency analysis methods (such as synchronous compression transform and its improved method) are not ideal for extracting the rapidly varying weak harmonics and their changing characteristics in strong interfering vibration signals. In practical applications, large-scale mechanical equipment often undergoes complex rapid startup and shutdown processes and operating condition changes, which often leads to the neglect of subtle anomalies and operating state changes in the mechanical system. Even with the use of these advanced time-frequency analysis methods, the diagnostic effect on large equipment such as liquid rocket engines remains unsatisfactory, and the instantaneous frequency and its changing patterns of these complex rapidly varying signals cannot be effectively characterized. Therefore, it is necessary to develop more advanced time-frequency analysis methods that target the characteristics and changing patterns of weak rapidly varying harmonics in complex signals to meet the fault diagnosis needs of large equipment. Summary of the Invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide an adaptive weak feature extraction method and related device for liquid rocket engines, which can extract the weak features of liquid rocket engines under weak impact conditions.

[0005] To achieve the above object, the present invention discloses an adaptive weak feature extraction method for a liquid rocket engine, comprising:

[0006] Construct a combined function D based on the superelliptic function D1, the rectangular function, the exponential function D2 and the sign function;

[0007] Performing a second-order synchronous compression transformation on the collected signal to obtain a second-order synchronous compression transformation result;

[0008] Perform a product operation on the combination function D and the result of the second-order synchronous compression transformation to obtain an energy function U;

[0009] According to the energy function U, the weak characteristics of the liquid rocket engine under weak impact conditions are extracted.

[0010] The further improvement of the adaptive weak feature extraction method for liquid rocket engines described in the present invention is:

[0011] Furthermore, the collected signal is subjected to a second-order synchronous compression transformation to achieve time-frequency rearrangement and obtain the second-order synchronous compression transformation result. for:

[0012]

[0013] Furthermore, the superelliptic function D1 is:

[0014]

[0015] Where T0 is the selected first threshold parameter, T(u,ξ) is the second-order synchronous compression transform, is the abbreviation of , α and m are parameters.

[0016] Furthermore, the rectangular function Rect(T0, T1) is:

[0017]

[0018] Wherein, T1 is the selected second threshold parameter.

[0019] Furthermore, the exponential function D2 is:

[0020]

[0021] Among them, β and k are parameters.

[0022] Furthermore, the energy function U is:

[0023]

[0024] in, Represents a symbolic function.

[0025] Furthermore, the process of extracting the weak characteristics of the liquid rocket engine under weak impact conditions according to the energy function U is as follows:

[0026] The threshold parameters T0 and T1 are selected and substituted into the energy function U to obtain the weak characteristics of the liquid rocket engine under weak impact conditions.

[0027] The present invention discloses an adaptive weak feature extraction system for a liquid rocket engine, comprising:

[0028] A construction module for constructing a combination function D based on a superelliptic function D1, a rectangular function, an exponential function D2, and a sign function;

[0029] A transformation module is used to perform a second-order synchronous compression transformation on the collected signal to obtain a second-order synchronous compression transformation result;

[0030] An operation module, configured to perform a product operation on the combination function D and a result of the second-order synchronous compression transformation to obtain an energy function U;

[0031] The extraction module is used to extract the weak characteristics of the liquid rocket engine under weak impact conditions according to the energy function U.

[0032] The present invention discloses a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the adaptive weak feature extraction method for a liquid rocket engine are implemented.

[0033] The present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the adaptive weak feature extraction method for a liquid rocket engine are implemented.

[0034] The present invention has the following beneficial effects:

[0035] The adaptive weak feature extraction method and related device for liquid rocket engines described in the present invention, during operation, constructs a combination of a superelliptic function, a rectangular function, and an exponential function to obtain a law of function value variation, thereby achieving adaptive feature extraction of weak amplitude-frequency modulation signals from strong interfering vibration signals. Specifically, the method enhances low-energy features below a selected first threshold, maintains medium-energy features between the first and second thresholds, and suppresses high-energy features above the second threshold. Furthermore, the present invention introduces a sign function to transform the sign of the original high-energy features, distinguishing them from the enhanced energy features after conversion, thus avoiding confusion between the energy features before and after conversion.

[0036] Furthermore, the present invention satisfies the enhancement requirements of characteristic frequencies of different energies by setting an adjustable threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which constitute part of the present invention, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0038] Figure 1 Schematic diagram of the time domain characteristics of the example signal;

[0039] Figure 2 It is the time-frequency feature map of the example signal based on the second-order synchrosqueezing transform (SST2);

[0040] Figure 3 is a time-frequency characteristic diagram of an example signal based on the method of the present invention;

[0041] Figure 4 FIG. 4 is a frequency slice diagram of an example signal near the startup time based on the method of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0043] In the description of the present invention, it is to be understood that the terms “include” and “comprise” indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0044] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0045] It should be further understood that the term "and / or" as used in the present specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0046] It should be understood that although the terms "first," "second," and "third" may be used to describe preset ranges in embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are merely used to distinguish one preset range from another. For example, without departing from the scope of embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0047] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, 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. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0049] The accompanying drawings illustrate various schematic diagrams of structures according to embodiments disclosed herein. These figures are not drawn to scale; for clarity, some details are exaggerated and some details may be omitted. The shapes of the various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art may design regions / layers with different shapes, sizes, and relative positions as needed.

[0050] Example 1

[0051] To address the current situation where weak fault features of liquid rocket engines are not obvious and cannot be quickly and accurately extracted, the vibration signal contains complex and rapidly changing amplitude and frequency modulation features and weak features. Even with the most advanced time-frequency analysis method - synchronous compression transform and its improved methods (such as FSST and FSST2), it is still difficult to effectively characterize the instantaneous frequency and its changing law of the complex and rapidly changing signals. The present invention proposes a weak feature adaptive extraction method. First, the collected signal is subjected to a second-order synchronous compression transform based on short-time Fourier transform to achieve time-frequency rearrangement and preliminarily improve energy concentration. Secondly, a combination function of superelliptic function, rectangular function and exponential function is constructed to obtain the function value change law, and a sign function is introduced to distinguish high-energy features before and after the transformation. Then, the specific value or value range of the parameter is obtained by the restriction condition of the combination function. Finally, the constructed combination function is multiplied by the result of the second-order synchronous compression transform to obtain an energy function, which further realizes the enhancement and sharpening of the time-frequency features of the non-stationary signal. By setting a threshold, the adaptive change effect of enhancing low-energy features, maintaining medium-energy features and suppressing high-energy features is achieved.

[0052] Specifically, the adaptive weak feature extraction method for a liquid rocket engine according to the present invention comprises the following steps:

[0053] 1) Perform second-order synchronous compression transformation on the collected signal to achieve time-frequency rearrangement and obtain the characteristic expression of the signal for:

[0054]

[0055] 2) In order to increase the function value and thus achieve energy enhancement, based on the characteristic expression of the signal Construct the superelliptic function D1 as:

[0056]

[0057] in,

[0058]

[0059] Where T0 is the selected first threshold parameter, T(u,ξ) is the second-order synchronous compression transform, is the abbreviation of , α and m are parameters.

[0060] 3) In order to keep the function value unchanged and thus achieve energy conservation, a rectangular function Rect(T0, T1) is constructed:

[0061]

[0062] Wherein, T1 is the selected second threshold parameter.

[0063] 4) In order to make the value of the rectangular function Rect(T0, T1) approach 0, thereby achieving energy suppression, an exponential function D2 is constructed:

[0064]

[0065] Among them, β and k are parameters.

[0066] 5) For the original high energy features and energy enhanced features, by introducing the sign function To distinguish the two, the sign function is:

[0067]

[0068] 6) To achieve adaptive changes in function values, combine the above functions into a combined function D, and we get:

[0069]

[0070] 7) Pass the following conditions:

[0071] 7a) When T=0, the function D1 has a value of 0;

[0072] 7b) When T=T0, the function D1 has a value of 1, that is: Find the parameters α and m.

[0073] 8) Pass the following conditions:

[0074] 8a) When T=0, the function D2 has a value of 0;

[0075] 8b) When T=T1, the function D2 has a value of 1, that is: Find the parameters β and k.

[0076] 9) Multiply the combined function D with the result of the second-order synchronous compression transformation to obtain the energy function U:

[0077]

[0078] By selecting the threshold parameters T0 and T1 and substituting them into the energy function U, the extraction of adaptive weak features is finally achieved.

[0079] Example 2

[0080] The adaptive weak feature extraction system for a liquid rocket engine according to the present invention comprises:

[0081] A construction module for constructing a combination function D based on a superelliptic function D1, a rectangular function, an exponential function D2, and a sign function;

[0082] A transformation module is used to perform a second-order synchronous compression transformation on the collected signal to obtain a second-order synchronous compression transformation result;

[0083] An operation module, configured to perform a product operation on the combination function D and a result of the second-order synchronous compression transformation to obtain an energy function U;

[0084] The extraction module is used to extract the weak characteristics of the liquid rocket engine under weak impact conditions according to the energy function U.

[0085] In this embodiment, the collected signal is subjected to a second-order synchronous compression transformation to achieve time-frequency rearrangement, and a second-order synchronous compression transformation result is obtained. for:

[0086]

[0087] In this embodiment, the superelliptic function D1 is:

[0088]

[0089] Where T0 is the selected first threshold parameter, T(u,ξ) is the second-order synchronous compression transform, is the abbreviation of , α and m are parameters.

[0090] In this embodiment, the rectangular function Rect(T0, T1) is:

[0091]

[0092] Wherein, T1 is the selected second threshold parameter.

[0093] In this embodiment, the exponential function D2 is:

[0094]

[0095] Among them, β and k are parameters.

[0096] In this embodiment, the energy function U is:

[0097]

[0098] in, Represents a symbolic function.

[0099] In this embodiment, the process of extracting the weak characteristics of the liquid rocket engine under weak impact conditions according to the energy function U is as follows:

[0100] The threshold parameters T0 and T1 are selected and substituted into the energy function U to obtain the weak characteristics of the liquid rocket engine under weak impact conditions.

[0101] The division of modules in the embodiments of the present application is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the present application may be integrated into a single processor, or may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0102] Example 3

[0103] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the adaptive weak feature extraction method for a liquid rocket engine are implemented. For example, the steps include: constructing a combination function D based on a hyperelliptic function D1, a rectangular function, an exponential function D2, and a sign function; performing a second-order synchronous compression transform on the acquired signal to obtain a second-order synchronous compression transform result; multiplying the combination function D with the second-order synchronous compression transform result to obtain an energy function U; and extracting the weak features of the liquid rocket engine under weak shock conditions based on the energy function U. The memory may include a memory, such as a high-speed random access memory (RAM), or may also include a non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which may be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard architecture bus, etc. The bus may be classified as an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the programs may include program code, and the program code includes computer operating instructions. The memory may include internal memory and nonvolatile memory and provides instructions and data to the processor.

[0104] Example 4

[0105] A computer-readable storage medium stores a computer program. When executed by a processor, the computer program implements the steps of the adaptive weak feature extraction method for a liquid rocket engine, including: constructing a combination function D based on a superelliptic function D1, a rectangular function, an exponential function D2, and a sign function; performing a second-order synchronous compression transformation on the collected signal to obtain a second-order synchronous compression transformation result; multiplying the combination function D with the second-order synchronous compression transformation result to obtain an energy function U; and extracting the weak features of the liquid rocket engine under weak impact conditions based on the energy function U. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0106] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0110] Those skilled in the art will readily identify other embodiments of the present invention after considering the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0111] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0112] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An adaptive weak feature extraction method for liquid rocket engines, characterized in that: include: Construct a combined function D based on the superelliptic function D1, the rectangular function, the exponential function D2 and the sign function; Performing a second-order synchronous compression transformation on the collected signal to obtain a second-order synchronous compression transformation result; Perform a product operation on the combination function D and the result of the second-order synchronous compression transformation to obtain an energy function U; According to the energy function U, the weak characteristics of the liquid rocket engine under weak impact conditions are extracted.

2. The method for extracting adaptive weak features from liquid rocket engines according to claim 1, wherein: Perform second-order synchronous compression transformation on the collected signal to achieve time-frequency rearrangement and obtain the second-order synchronous compression transformation result for:

3. The adaptive weak feature extraction method for liquid rocket engines according to claim 1, characterized in that: The superelliptic function D1 is: Where T0 is the selected first threshold parameter, T(u,ξ) is the second-order synchronous compression transform, is the abbreviation of , α and m are parameters.

4. The method for extracting adaptive weak features of a liquid rocket engine according to claim 1, wherein: The rectangular function Rect(T0, T1) is: Wherein, T1 is the selected second threshold parameter.

5. The method for extracting adaptive weak features of liquid rocket engines according to claim 1, wherein: The exponential function D2 is: Among them, β and k are parameters.

6. The method for extracting adaptive weak features of a liquid rocket engine according to claim 1, wherein: The energy function U is: in, Represents a symbolic function.

7. The method for extracting adaptive weak features of a liquid rocket engine according to claim 1, wherein: The process of extracting the weak characteristics of the liquid rocket engine under weak impact conditions according to the energy function U is as follows: The threshold parameters T0 and T1 are selected and substituted into the energy function U to obtain the weak characteristics of the liquid rocket engine under weak impact conditions.

8. An adaptive weak feature extraction system for liquid rocket engines, characterized in that: include: A construction module for constructing a combination function D based on a superelliptic function D1, a rectangular function, an exponential function D2, and a sign function; A transformation module is used to perform a second-order synchronous compression transformation on the collected signal to obtain a second-order synchronous compression transformation result; An operation module, configured to perform a product operation on the combination function D and a result of the second-order synchronous compression transformation to obtain an energy function U; The extraction module is used to extract the weak characteristics of the liquid rocket engine under weak impact conditions according to the energy function U.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the adaptive weak feature extraction method for a liquid rocket engine as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the adaptive weak feature extraction method for a liquid rocket engine as claimed in any one of claims 1 to 7 are implemented.

Images