A vibration detection method based on hemispherical resonator
By setting temperature and airflow velocity sensors on the aircraft engine and correcting the data of the hemispherical resonant gyroscope using compensation model, the problem of reduced vibration detection accuracy in high-temperature and high-speed airflow environments is solved, and the accuracy of aircraft engine vibration monitoring is improved and efficiency.
Patent Information
- Application Number
- CN202411451314.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2024-12-17
- Estimated Expiration
- 2044-10-17
AI Technical Summary
When the aircraft engine is used in high temperature and high-speed airflow environments, the measurement accuracy of the hemispherical resonant gyroscope is affected, resulting in a decrease in the accuracy of the vibration detection results.
By setting temperature sensors and airflow velocity sensors outside the gyroscope, collecting environmental data and correcting them according to the set temperature threshold and airflow velocity threshold, and using the temperature compensation and airflow velocity compensation neural network model to correct the angular velocity to improve vibration detection accuracy.
Effectively eliminate or reduce the impact of high temperature and airflow on gyroscope data acquisition, and improve the accuracy and efficiency of aircraft engine vibration monitoring.
Smart Images
Figure CN118980424B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of aircraft engine testing, and in particular to a vibration detection method based on a hemispherical resonator. Background Art
[0002] Hemispherical resonator gyroscope (HRG) is a kind of vibrating gyroscope that uses the oscillator vibration standing wave to move in the annular direction under the action of Coriolis force to sense the external angular velocity. It has the advantages of high measurement accuracy, high stability and high reliability. The HRG includes two working modes: force balance mode and full angle mode. The Hemispherical Shell Resonator (HSR) is the core component of the HRG.
[0003] Hemispherical resonant gyroscopes are widely used in industry due to their high detection accuracy. For example, they can be used to measure the angular velocity and vibration of the object to be measured. In terms of vibration detection, the gyroscope can detect vibration by measuring the angular velocity and transmit the data to the control system for analysis and processing. When the equipment vibrates, the gyroscope can accurately detect the vibration value by measuring the angular velocity.
[0004] Aircraft engines are very complex high-speed rotating mechanical structures, and their operating speed is often higher than the critical speed. The imbalance of the rotor and the instability of the airflow can easily lead to omnidirectional periodic vibration and complex random vibration of the engine. Therefore, to ensure the safety of aircraft flight, it is very important to monitor the vibration state of the aircraft engine in real time. Although the hemispherical resonant gyroscope has the advantage of high detection accuracy, when the aircraft engine is in use, it is in a high temperature environment and there may be a situation where the airflow velocity is very high. The high temperature environment and / or high-speed airflow will affect the measurement accuracy of the hemispherical resonant gyroscope. In order to improve the detection accuracy of the aircraft engine vibration, when using the hemispherical resonant gyroscope to measure the vibration, it is necessary to consider the high temperature and high-speed airflow in the environment. Summary of the invention
[0005] The purpose of the present invention is to provide a vibration detection method based on a hemispherical resonator, which fully considers the influence of temperature and airflow in the environment where the aircraft engine is located on the data collected by a gyroscope containing a hemispherical resonator, and corrects the collected results to improve the accuracy of vibration monitoring of the aircraft engine in use by the gyroscope containing the hemispherical resonator.
[0006] The present invention is achieved through the following technical solutions:
[0007] A vibration detection method based on a hemispherical resonator comprises the following steps:
[0008] S1. Using a temperature sensor to collect the temperature of the environment where the hemispherical resonator is located, and using an airflow velocity sensor to collect the airflow velocity of the environment where the hemispherical resonator is located;
[0009] S2, collecting the angular velocity of the aircraft engine based on a gyroscope containing a hemispherical resonator;
[0010] S3, arranging a plurality of vibration sensors outside the gyroscope, judging whether the gyroscope is faulty based on the detection results of the plurality of vibration sensors, if the gyroscope is faulty, using the detection results of the plurality of vibration sensors as the vibration detection results of the aircraft engine; if the gyroscope is not faulty, proceeding to the next step;
[0011] S4. Setting a temperature threshold and an airflow velocity threshold at which the gyroscope starts to generate errors; comparing the collected temperature with the temperature threshold, and comparing the collected airflow velocity with the airflow velocity threshold; judging whether to correct the angular velocity output by the gyroscope based on the comparison result, and if correction is required, using the corrected angular velocity to analyze the vibration value of the aircraft engine.
[0012] The present invention is a vibration detection method designed for the particularity of the environment in which the aircraft engine is working. First, the operating temperature of the aircraft engine is 1700-2000°C, and the temperature of the aircraft engine casing is usually between 50-600°C, basically between 150-200°C; when the aircraft engine is used normally in a closed space, the vibration detection of the aircraft engine is less affected by the airflow, but when the aircraft fails, it may be that the aircraft engine is exposed to the atmosphere, at this time, the vibration detection of the aircraft engine will be affected by the airflow.
[0013] Among them, the gyroscope containing a hemispherical resonator has the advantages of high acquisition accuracy and high sensitivity. Therefore, compared with directly using a vibration sensor, the use of a gyroscope containing a hemispherical resonator to detect the vibration of an aircraft engine when it is working has a higher sensitivity and has the advantage of high sensitivity.
[0014] Although the gyroscope containing a hemispherical resonator has the advantages of high acquisition accuracy and high sensitivity, when it is used to detect the vibration of an aircraft engine during operation, the gyroscope is installed on the aircraft engine casing. The gyroscope is affected by the temperature and airflow of the environment in which it is located, which will reduce the accuracy of the output results of the gyroscope containing the hemispherical resonator. For example, the more suitable operating temperature of a gyroscope containing a hemispherical resonator (hemispherical resonant gyroscope) is 20~50℃, although there are also some hemispherical resonant gyroscopes with operating temperatures limited to -20~80℃. The hemispherical resonant gyroscope can be used within the range of -20~20℃ and 50~80℃, but its measurement accuracy will be reduced. When the hemispherical resonant gyroscope is used at a higher temperature (greater than 80℃), it will lead to greater measurement errors. Therefore, the hemispherical resonant gyroscope error caused by the high temperature environment (150-200℃) where the gyroscope is working cannot be ignored.
[0015] First, the present invention takes into account the temperature of whether a gyroscope containing a hemispherical resonator is faulty, and first uses the detection results of multiple vibration sensors to determine whether the gyroscope is faulty. If the gyroscope is faulty, the data collected by it is unreliable, so as a fallback, the data collected by the vibration sensor is used to analyze the vibration of the aircraft engine.
[0016] Secondly, the present invention sets a temperature threshold and an airflow velocity threshold at which the gyroscope begins to generate errors, and determines whether to correct the data collected by the gyroscope based on a comparison between the collected temperature and the temperature threshold, and a comparison between the collected airflow velocity and the airflow velocity threshold, so as to reduce unnecessary corrections and improve the efficiency of data output.
[0017] Thirdly, the present invention corrects the angular velocity collected by the gyroscope, thereby eliminating or reducing the influence of the high temperature and airflow in the environment where the gyroscope is located when the aircraft engine is working on the angular velocity collected by the gyroscope, thereby improving the accuracy of the results of the gyroscope detecting the vibration of the aircraft engine when working.
[0018] In a preferred embodiment, in step S1, multiple temperature sensors are evenly arranged outside the gyroscope containing the hemispherical resonator, and the average temperature collected by the multiple temperature sensors is taken as the temperature of the environment where the hemispherical resonator is located, so as to improve the accuracy of the temperature collected by the temperature sensor.
[0019] In a preferred embodiment, in step S1, multiple air flow velocity sensors are evenly arranged on the outside of a gyroscope containing a hemispherical resonator, and the average value of the air flow velocities collected by the multiple air flow velocity sensors is taken as the air flow velocity of the environment where the hemispherical resonator is located, so as to improve the accuracy of the air flow velocity collected by the air flow velocity sensor in the environment.
[0020] In a preferred embodiment, in step S4, the process of obtaining the temperature threshold is:
[0021] The gyroscope is fixed on the turntable, and the turntable is controlled to rotate at a set angular velocity. At the same time, the ambient temperature is controlled to gradually rise between 25 and 200°C. By comparing the set angular velocity of the turntable and the angular velocity output by the gyroscope at different temperatures, when the absolute value of the difference between the angular velocity output by the gyroscope and the set angular velocity of the turntable is equal to the set error, the corresponding temperature is the temperature threshold.
[0022] Experiments have shown that as the temperature increases, the error in the gyroscope's angular velocity measurement increases.
[0023] In the process of designing the test to obtain the temperature threshold, the present invention fully considers that the temperature of the aircraft engine casing is usually between 50-600°C, basically between 150-200°C. Therefore, when conducting the test, the angular velocity of 25-200°C is collected.
[0024] The present invention sets a temperature threshold value and can judge by comparison whether the current temperature needs to modify the acquisition result of the gyroscope, so as to reduce unnecessary corrections. At the same time, the accuracy of the output result of the gyroscope can be ensured through correction.
[0025] In a preferred embodiment, the temperature is increased step by step with a temperature difference of 10°C.
[0026] In a preferred embodiment, in step S4, the process of obtaining the airflow velocity threshold is as follows:
[0027] An aircraft engine with a known vibration fault is used as a test object. A gyroscope is installed on the outer casing of the aircraft engine. The aircraft engine is driven to generate airflow, and the airflow velocity gradually increases. An airflow velocity sensor is used to collect the airflow velocity. The measured vibration result obtained by analyzing the angular velocity collected by the gyroscope is compared with the known vibration result. When the absolute value of the difference between the measured vibration result and the known vibration result is equal to the set error, the corresponding gas flow rate is the airflow velocity threshold.
[0028] Experiments have shown that as the air flow speed increases, the error in the gyroscope's angular velocity measurement increases.
[0029] Among them, the vibration results are expressed in vibration speed (mm / s).
[0030] Among them, the set error can be understood as the lowest error threshold set manually. Vibration displacement, vibration velocity (mm / s), and vibration acceleration (m / s²) are all measurement parameters for vibration measurement. Vibration analysis is usually performed with vibration acceleration. For example: an aircraft engine with a vibration value of 1.0 mm / s fails, and the vibration value becomes 4.0 mm / s after the failure. Then, the known vibration result of the aircraft engine with a known vibration failure is 4.0 mm / s. When the measured vibration result obtained by the angular velocity analysis collected by the gyroscope is 4.1 mm / s, then the absolute value of the difference between the measured vibration result and the known vibration result is 0.1 mm / s. If the set error is 0.1 mm / s, then when the measured vibration result obtained by the angular velocity analysis collected by the gyroscope is 4.1 mm / s, the corresponding gas flow rate is the air flow velocity threshold.
[0031] Furthermore, the theoretical angular velocity output by the gyroscope when detecting the aircraft engine can be inferred from the vibration value of the aircraft engine.
[0032] The present invention uses an aircraft engine with a known vibration fault as a test object, that is, the vibration parameters (vibration acceleration) of the test object are known. Through a test object with a known vibration fault (vibration acceleration), the error of data collected by a gyroscope under different gas flow rates can be measured.
[0033] By setting the airflow velocity threshold, the present invention can judge by comparison whether the acquisition result of the gyroscope needs to be modified under the current gas flow rate, so as to reduce unnecessary corrections. At the same time, the accuracy of the gyroscope output result can be ensured through correction.
[0034] In a preferred embodiment, in step S4, the specific correction process is:
[0035] If the temperature is less than the temperature threshold and the airflow velocity is less than the airflow velocity threshold, the angular velocity collected by the gyroscope is directly used to analyze the vibration value of the aircraft engine;
[0036] If the temperature is greater than or equal to the temperature threshold and the airflow velocity is less than the airflow velocity threshold, the temperature compensation neural network model is used to correct the angular velocity collected by the gyroscope;
[0037] If the temperature is less than the temperature threshold and the airflow velocity is greater than or equal to the airflow velocity threshold, the airflow velocity compensation neural network model is used to correct the angular velocity collected by the gyroscope;
[0038] If the temperature is greater than or equal to the temperature threshold and the airflow velocity is greater than or equal to the airflow velocity threshold, the temperature compensation neural network model and the airflow velocity compensation neural network model are used to correct the angular velocity in turn; the corrected angular velocity is used to analyze the vibration value of the aircraft engine.
[0039] The present invention fully considers the uncertainty of the environment in which the aircraft engine is located and reasonably designs the correction process. For example: the temperature of the aircraft engine casing is usually between 50-600°C, basically between 150-200°C, that is, the temperature of the aircraft engine casing is a variable value, and the temperature of the aircraft engine casing will change according to the temperature of different regions where the aircraft flies and different aircraft altitudes, and the temperature of the aircraft engine casing will change according to the temperature of the environment in which the aircraft is located, and will also change according to the length of time the aircraft engine is used. Therefore, during the entire flight of the aircraft, the temperature of the aircraft engine casing is changing. For example: the airflow in the environment in which the aircraft engine is located is also changing: when the aircraft is in normal flight, the gyroscope is not affected by the airflow; when the aircraft encounters strong airflow turbulence during flight, or a serious fault occurs during the flight of the aircraft, causing the airflow to enter the environment in which the aircraft engine is located, and the environment in which the gyroscope is located generates airflow. At this time, the output result of the gyroscope is affected by the airflow.
[0040] That is, during the flight of the aircraft, a gyroscope containing a hemispherical resonator is used to collect data. The gyroscope has the following working conditions: 1) not affected by temperature and airflow; 2) affected by temperature but not affected by airflow; 3) affected by airflow but not affected by temperature; 4) affected by both temperature and airflow.
[0041] In a preferred embodiment, the construction process of the temperature compensation neural network model is as follows:
[0042] The gyroscope is fixed on a turntable, and the turntable is controlled to rotate at a set angular velocity. At the same time, the ambient temperature is controlled to gradually rise between 25 and 200°C, and the angular velocity errors corresponding to several groups of different temperatures are measured as temperature compensation training sample sets. The temperature compensation training sample sets are input into the MLP neural network model for training and learning, and a temperature compensation neural network model that can be used to predict the angular velocity error corresponding to the ambient temperature of the gyroscope is obtained.
[0043] In a preferred embodiment, the construction process of the airflow velocity compensation neural network model is as follows:
[0044] An aircraft engine with a known vibration fault is taken as a test object. A gyroscope is installed on the outer casing of the aircraft engine. The aircraft engine is driven to generate airflow, and the airflow velocity gradually increases. An airflow velocity sensor is used to collect the airflow velocity, and several groups of angular velocity errors corresponding to different airflow velocities are obtained as airflow velocity compensation training sample sets. The airflow velocity compensation training sample sets are input into the MLP neural network model for training and learning, and an airflow velocity compensation neural network model that can be used to predict the angular velocity error corresponding to the airflow velocity in the environment where the gyroscope is located is obtained.
[0045] In a preferred embodiment, in step S3, the vibration sensor is calibrated or corrected before use.
[0046] Compared with the prior art, the present invention has the following advantages and beneficial effects:
[0047] 1. The present invention is aimed at the particularity of the environment in which the aircraft engine is working. The environment in which the aircraft engine is working, i.e., the environment in which the gyroscope is located, has high temperature and / or high-speed airflow, and the high temperature and high-speed airflow have an impact on the output result of the gyroscope containing a hemispherical resonator. Therefore, in order to improve the angular velocity collected by the gyroscope containing a hemispherical resonator to analyze the vibration of the aircraft engine, the present invention is based on collecting the temperature and gas flow rate of the environment in which the gyroscope containing the hemispherical resonator is located, and by comparing with the set temperature threshold and gas flow rate threshold respectively, it is determined whether to make corrections to improve the output efficiency. At the same time, the present invention can correct the collected results to improve the accuracy of the gyroscope containing the hemispherical resonator in monitoring the vibration of the aircraft engine in use.
[0048] 2. The present invention fully considers the uncertainty of the environment in which the aircraft engine is located and reasonably designs the correction process. According to the following working states of the gyroscope: 1) not affected by temperature and airflow; 2) affected by temperature but not affected by airflow; 3) affected by airflow but not affected by temperature; 4) affected by temperature and airflow at the same time, four output modes of the gyroscope are designed accordingly. According to the collected temperature and airflow velocity, they are compared with the set temperature threshold and gas flow velocity threshold respectively to determine which specific method to select for correction. This not only improves the output efficiency of the gyroscope, but also can improve the accuracy of the gyroscope output result. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:
[0050] Figure 1 Flow chart of the vibration detection method of the present invention. DETAILED DESCRIPTION
[0051] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the embodiments. The schematic implementation mode of the present invention and its description are only used to explain the present invention and are not intended to limit the present invention. The embodiments described below are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention.
[0052] In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is apparent to those of ordinary skill in the art that these specific details do not have to be employed to practice the present invention. In other embodiments, in order to avoid confusing the present invention, known structures, materials or methods are not specifically described. The materials, instruments and reagents used in the following examples, unless otherwise specified, can be obtained from commercial sources. The technical means used in the examples, unless otherwise specified, are conventional means well known to those skilled in the art.
[0053] Embodiment 1:
[0054] When the aircraft engine is working, the angular velocity collected by the gyroscope containing a hemispherical resonator can be used to analyze the vibration of the engine. When the angular velocity of the aircraft engine is collected by the gyroscope containing a hemispherical resonator, the output result of the gyroscope will be affected by the temperature and gas flow rate. When the aircraft engine is working, the environment where the gyroscope is located will be uncertain according to the flight environment and flight status of the aircraft. The environment temperature and airflow are suitable, the environment is high temperature but the airflow is suitable, the environment temperature is suitable but there is high-speed airflow, and the environment is high temperature and there is high-speed airflow. Therefore, the gyroscope has the following working states: 1) not affected by temperature and airflow; 2) affected by temperature but not affected by airflow; 3) affected by airflow but not affected by temperature; 4) affected by both temperature and airflow.
[0055] In order to improve the accuracy of the gyroscope containing a hemispherical resonator in collecting the angular velocity of the aircraft engine when it is working, this embodiment provides a vibration detection method based on a hemispherical resonator, such as Figure 1 As shown, the following steps are included:
[0056] S1. Using a temperature sensor to collect the temperature of the environment where the hemispherical resonator is located, and using an airflow velocity sensor to collect the airflow velocity of the environment where the hemispherical resonator is located; wherein the temperature sensor and the airflow velocity sensor are both prior art. Preferably, a plurality of temperature sensors are evenly arranged on the outside of the gyroscope containing the hemispherical resonator, and the average value of the temperatures collected by the plurality of temperature sensors is taken as the temperature of the environment where the hemispherical resonator is located. For example, with the center of the hemispherical resonator, four temperature sensors are evenly arranged in the circumferential direction of the outside of the hemispherical resonator, the temperatures collected by the four temperature sensors are T1, T2, T3 and T4 respectively, and the temperature of the environment where the hemispherical resonator is located is (T1+T2+T3+T4) / 4; Preferably, a plurality of airflow velocity sensors are evenly arranged on the outside of the gyroscope containing the hemispherical resonator, and the average value of the airflow velocities collected by the plurality of airflow velocity sensors is taken as the airflow velocity of the environment where the hemispherical resonator is located. For example, with the center of the hemispherical resonator, four airflow velocity sensors are evenly arranged in the circumferential direction of the outside of the hemispherical resonator, the temperatures collected by the four airflow velocity sensors are V1, V2, V3 and V4 respectively, and the gas flow velocity of the environment where the hemispherical resonator is located is (V1+V2+V3+V4) / 4.
[0057] S2. The angular velocity of the aircraft engine is collected based on a gyroscope containing a hemispherical resonator. The gyroscope containing a hemispherical resonator is a hemispherical resonator gyroscope, which is a prior art and has the advantages of high measurement accuracy and high sensitivity.
[0058] S3. Multiple vibration sensors are arranged outside the gyroscope, and whether the gyroscope is faulty is determined based on the detection results of the multiple vibration sensors. If the gyroscope is faulty, the detection results of the multiple vibration sensors are used as the vibration detection results of the aircraft engine; if the gyroscope is not faulty, the next step is performed; the vibration sensor is a prior art. Preferably, the vibration sensor is calibrated or corrected before use. Preferably, four vibration sensors are evenly arranged in the circumferential direction outside the hemispherical resonator with the center of the hemispherical resonator, and the measurement average value of the four vibration sensors is used as the vibration detection result of the aircraft engine. Although the detection accuracy of the vibration sensor is lower than that of the gyroscope containing the hemispherical resonator, it can be known that when the gyroscope fails, the vibration condition of the aircraft engine can be roughly determined, which is used as a supplement to the gyroscope for vibration detection of the aircraft engine.
[0059] S4. Setting a temperature threshold and an airflow velocity threshold at which the gyroscope starts to generate errors; comparing the collected temperature with the temperature threshold, and comparing the collected airflow velocity with the airflow velocity threshold; judging whether to correct the angular velocity output by the gyroscope based on the comparison result, and if correction is required, using the corrected angular velocity to analyze the vibration value of the aircraft engine.
[0060] The process of obtaining the temperature threshold is as follows:
[0061] The gyroscope is fixed on a turntable, and the turntable is controlled to rotate at a set angular velocity. At the same time, the ambient temperature is controlled to gradually rise between 25 and 200°C. Specifically, the temperature can be raised step by step with a temperature difference of 10°C. By comparing the set angular velocity of the turntable and the angular velocity output by the gyroscope at different temperatures, when the absolute value of the difference between the angular velocity output by the gyroscope and the set angular velocity of the turntable is equal to the set error, the corresponding temperature is the temperature threshold.
[0062] The process of obtaining the airflow velocity threshold is as follows:
[0063] An aircraft engine with a known vibration fault is used as a test object. A gyroscope is installed on the outer casing of the aircraft engine. The aircraft engine is driven to generate airflow, and the airflow velocity gradually increases. An airflow velocity sensor is used to collect the airflow velocity. The measured vibration results obtained by analyzing the angular velocity and acceleration collected by the gyroscope are compared with the known vibration results. When the absolute value of the difference between the measured vibration result and the known vibration result is equal to the set error, the corresponding gas flow rate is the airflow velocity threshold.
[0064] For example, an aircraft engine with a vibration value of 1.0 mm / s fails. After the failure, the vibration value becomes 4.0 mm / s. The set error is set to 0.1 mm / s. When the measured vibration result obtained by analyzing the angular velocity collected by the gyroscope is 4.1 mm / s, the absolute value of the difference between the measured vibration result and the known vibration result is 0.1 mm / s. At this time, the corresponding airflow velocity is the airflow velocity threshold.
[0065] In a preferred case, in order to adapt to the uncertainty of the environment in which the aircraft engine is working, the specific correction process of the angular velocity collected by the gyroscope in this embodiment is:
[0066] If the temperature is less than the temperature threshold and the airflow velocity is less than the airflow velocity threshold, the angular velocity collected by the gyroscope is directly used to analyze the vibration value of the aircraft engine;
[0067] If the temperature is greater than or equal to the temperature threshold and the airflow velocity is less than the airflow velocity threshold, the temperature compensation neural network model is used to correct the angular velocity collected by the gyroscope;
[0068] If the temperature is less than the temperature threshold and the airflow velocity is greater than or equal to the airflow velocity threshold, the airflow velocity compensation neural network model is used to correct the angular velocity collected by the gyroscope;
[0069] If the temperature is greater than or equal to the temperature threshold and the airflow velocity is greater than or equal to the airflow velocity threshold, the temperature compensation neural network model and the airflow velocity compensation neural network model are used to correct the angular velocity in turn; the corrected angular velocity is used to analyze the vibration value of the aircraft engine.
[0070] Among them, the construction process of the temperature compensation neural network model is as follows:
[0071] The gyroscope is fixed on a turntable, and the turntable is controlled to rotate at a set angular velocity. At the same time, the ambient temperature is controlled to gradually rise between 25 and 200°C, and the angular velocity errors corresponding to several groups of different temperatures are measured as temperature compensation training sample sets. The temperature compensation training sample sets are input into the MLP neural network model for training and learning, and a temperature compensation neural network model that can be used to predict the angular velocity error corresponding to the ambient temperature of the gyroscope is obtained.
[0072] The above angular velocity error is the difference between the angular velocity collected by the gyroscope and the angular velocity of the turntable.
[0073] The MLP neural network model is an existing technology. Specifically, the MLP neural network model includes an input layer-hidden layer calculation subunit for calculating the output of the hidden layer. The specific calculation method is as follows:
[0074] ;
[0075] in, h 1 represents the output of the hidden layer, represents the angular velocity error, represents the activation function, 1 represents a column vector, which is the current temperature. W 1 represents the weight matrix from the input layer to the hidden layer, b 1 Represents the bias vector.
[0076] The process of correcting the angular velocity collected by the gyroscope using the temperature compensation neural network model is as follows:
[0077] The above temperature compensation neural network model outputs an angular velocity error h 1 Based on the principle that the higher the temperature, the greater the error in the angular velocity output by the gyroscope, the angular velocity output by the gyroscope at the current temperature is subtracted from the angular velocity error output by the temperature compensation neural network model. h 1 , and obtain the modified angular velocity.
[0078] Among them, the construction process of the airflow velocity compensation neural network model is as follows:
[0079] An aircraft engine with a known vibration fault is taken as a test object. A gyroscope is installed on the outer casing of the aircraft engine. The aircraft engine is driven to generate airflow, and the airflow velocity gradually increases. An airflow velocity sensor is used to collect the airflow velocity, and several groups of angular velocity errors corresponding to different airflow velocities are obtained as airflow velocity compensation training sample sets. The airflow velocity compensation training sample sets are input into the MLP neural network model for training and learning, and an airflow velocity compensation neural network model that can be used to predict the angular velocity error corresponding to the airflow velocity in the environment where the gyroscope is located is obtained.
[0080] The vibration value of an aircraft engine with a known vibration fault is known, and the theoretical angular velocity output by the gyroscope when detecting the aircraft engine can be inferred. That is, the angular velocity error mentioned above refers to the difference between the angular velocity actually output by the gyroscope and the theoretical angular velocity.
[0081] Specifically, the MLP neural network model includes an input layer-hidden layer calculation subunit, which is used to calculate the output of the hidden layer. The specific calculation method is as follows:
[0082] ;
[0083] in, h 2 It represents the output of the hidden layer and the angular velocity error; represents the activation function; 2 represents a column vector, which is the current gas flow rate; W 2 Represents the weight matrix from the input layer to the hidden layer; b 2 Represents the bias vector.
[0084] The process of correcting the angular velocity collected by the gyroscope using the airflow velocity compensation neural network model is as follows:
[0085] The above airflow velocity compensation neural network model outputs an angular velocity error h 2 Based on the principle that the greater the airflow speed, the greater the error of the angular velocity output by the gyroscope, the angular velocity error output by the neural network model is compensated by subtracting the airflow speed from the angular velocity output by the gyroscope at the current airflow speed. h 2 , and obtain the modified angular velocity.
[0086] This embodiment is aimed at the particularity of the environment in which the aircraft engine is working. At the same time, this embodiment fully considers the uncertainty of the environment in which the aircraft engine is located and reasonably designs the correction process. According to the following working states of the gyroscope: 1) not affected by temperature and airflow; 2) affected by temperature but not affected by airflow; 3) affected by airflow but not affected by temperature; 4) affected by temperature and airflow at the same time, therefore, this embodiment is based on collecting the temperature and gas flow rate of the environment in which the gyroscope containing the hemispherical resonator is located, and correspondingly designs four output modes of the gyroscope. According to the collected temperature and airflow rate, they are compared with the set temperature threshold and gas flow rate threshold respectively to determine which specific method to select for correction. This not only improves the output efficiency of the gyroscope, but also improves the accuracy of the gyroscope output result to improve the accuracy of the vibration monitoring of the aircraft engine in use by the gyroscope containing the hemispherical resonator.
[0087] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A vibration detection method based on a hemispherical resonator, It is characterized in that The following steps are involved: S1. collecting the temperature of the environment where the hemispherical resonator is located using a temperature sensor, and collecting the airflow velocity of the environment where the hemispherical resonator is located using an airflow velocity sensor; S2, collecting the angular velocity of the aircraft engine based on the gyroscope containing the hemispherical resonator; S3, arranging a plurality of vibration sensors outside the gyroscope, judging whether the gyroscope is faulty based on the detection results of the plurality of vibration sensors, and if the gyroscope is faulty, using the detection results of the plurality of vibration sensors as the vibration detection results of the aircraft engine; If the gyroscope is not faulty, proceed to the next step; S4, setting a temperature threshold and an airflow velocity threshold at which the gyroscope starts to generate an error; comparing the collected temperature with the temperature threshold, and comparing the collected airflow velocity with the airflow velocity threshold; It is determined whether to correct the angular velocity output by the gyroscope based on the comparison result. If correction is required, the corrected angular velocity is used to analyze the vibration value of the aircraft engine.
2. A vibration detection method based on a hemispherical resonator according to claim 1, It is characterized in that In step S1, a plurality of the temperature sensors are evenly arranged outside the gyroscope including the hemispherical resonator, and an average value of the temperatures collected by the plurality of temperature sensors is taken as the temperature of the environment where the hemispherical resonator is located.
3. A vibration detection method based on a hemispherical resonator according to claim 1, It is characterized in that In step S1, a plurality of the airflow velocity sensors are evenly arranged outside the gyroscope containing the hemispherical resonator, and the airflow velocities collected by the plurality of the airflow velocity sensors are averaged as the airflow velocity of the environment where the hemispherical resonator is located.
4. A vibration detection method based on a hemispherical resonator according to claim 1, It is characterized in that In step S4, the process of obtaining the temperature threshold is as follows: The gyroscope is fixed on a turntable, and the turntable is controlled to rotate at a set angular velocity. At the same time, the ambient temperature is controlled to gradually rise between 25 and 200°C. By comparing the set angular velocity of the turntable and the angular velocity output by the gyroscope at different temperatures, when the absolute value of the difference between the angular velocity output by the gyroscope and the set angular velocity of the turntable is equal to a set error, the corresponding temperature is the temperature threshold.
5. A vibration detection method based on a hemispherical resonator according to claim 4, It is characterized in that The temperature was increased step by step with a temperature difference of 10 °C.
6. A vibration detection method based on a hemispherical resonator according to claim 1, It is characterized in that In step S4, the process of obtaining the airflow velocity threshold is as follows: An aircraft engine with a known vibration fault is used as a test object, the gyroscope is installed on the outer casing of the aircraft engine, the aircraft engine is driven to generate airflow, and the airflow velocity gradually increases, and an airflow velocity sensor is used to collect the airflow velocity, and the measured vibration result obtained by analyzing the angular velocity and acceleration collected by the gyroscope is compared with the known vibration result. When the absolute value of the difference between the measured vibration result and the known vibration result is equal to the set error, the corresponding gas flow rate is the airflow velocity threshold.
7. A vibration detection method based on a hemispherical resonator according to claim 1, It is characterized in that In step S4, the specific correction process is: If the temperature is less than the temperature threshold and the airflow velocity is less than the airflow velocity threshold, directly using the angular velocity collected by the gyroscope to analyze the vibration value of the aircraft engine; If the temperature is greater than or equal to the temperature threshold and the airflow velocity is less than the airflow velocity threshold, a temperature compensation neural network model is used to correct the angular velocity collected by the gyroscope; If the temperature is less than the temperature threshold and the airflow velocity is greater than or equal to the airflow velocity threshold, the angular velocity collected by the gyroscope is corrected using an airflow velocity compensation neural network model; If the temperature is greater than or equal to the temperature threshold and the airflow velocity is greater than or equal to the airflow velocity threshold, the temperature compensation neural network model and the airflow velocity compensation neural network model are used to correct the angular velocity in turn; the corrected angular velocity is used to analyze the vibration value of the aircraft engine.
8. A vibration detection method based on a hemispherical resonator according to claim 7, It is characterized in that The construction process of the temperature compensation neural network model is as follows: The gyroscope is fixed on a turntable, and the turntable is controlled to rotate at a set angular velocity. At the same time, the ambient temperature is controlled to gradually rise between 25 and 200°C, and the angular velocity errors corresponding to several groups of different temperatures are measured as temperature compensation training sample sets. The temperature compensation training sample sets are input into the MLP neural network model for training and learning, so as to obtain a temperature compensation neural network model that can be used to predict the angular velocity error corresponding to the ambient temperature of the gyroscope.
9. A vibration detection method based on a hemispherical resonator according to claim 7, It is characterized in that The construction process of the airflow velocity compensation neural network model is as follows: An aircraft engine with a known vibration fault is used as a test object, the gyroscope is installed on the outer casing of the aircraft engine, the aircraft engine is driven to generate airflow, and the airflow velocity gradually increases, and an airflow velocity sensor is used to collect the airflow velocity, and several groups of angular velocity errors corresponding to different airflow velocities are obtained as airflow velocity compensation training sample sets; the airflow velocity compensation training sample sets are input into the MLP neural network model for training and learning, and an airflow velocity compensation neural network model that can be used to predict the angular velocity error corresponding to the airflow velocity of the environment where the gyroscope is located is obtained.
10. A vibration detection method based on a hemispherical resonator according to any one of claims 1 to 9, It is characterized in that In step S3, the vibration sensor is calibrated or corrected before use.