CN112441254B - Performance detection method and device of engine lubricating oil system, storage medium and terminal - Google Patents
Performance detection method and device of engine lubricating oil system, storage medium and terminal Download PDFInfo
- Publication number
- CN112441254B CN112441254B CN201910833892.6A CN201910833892A CN112441254B CN 112441254 B CN112441254 B CN 112441254B CN 201910833892 A CN201910833892 A CN 201910833892A CN 112441254 B CN112441254 B CN 112441254B
- Authority
- CN
- China
- Prior art keywords
- performance index
- lubricating oil
- engine
- oil system
- factor information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64F—GROUND OR AIRCRAFT-CARRIER-DECK INSTALLATIONS SPECIALLY ADAPTED FOR USE IN CONNECTION WITH AIRCRAFT; DESIGNING, MANUFACTURING, ASSEMBLING, CLEANING, MAINTAINING OR REPAIRING AIRCRAFT, NOT OTHERWISE PROVIDED FOR; HANDLING, TRANSPORTING, TESTING OR INSPECTING AIRCRAFT COMPONENTS, NOT OTHERWISE PROVIDED FOR
- B64F5/00—Designing, manufacturing, assembling, cleaning, maintaining or repairing aircraft, not otherwise provided for; Handling, transporting, testing or inspecting aircraft components, not otherwise provided for
- B64F5/60—Testing or inspecting aircraft components or systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Transportation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Lubrication Details And Ventilation Of Internal Combustion Engines (AREA)
Abstract
A performance detection method and device of an engine lubricating oil system, a storage medium and a terminal are provided, and the method comprises the following steps: obtaining a plurality of sample data from historical data of an engine lubricating oil system, wherein the sample data comprises performance index influence factor information and performance index values, and the performance index values are obtained by calculating the performance index influence factor information; training to obtain a lubricating oil system model by using the performance index influence factor information and the performance index value; acquiring to-be-detected data including performance index influence factor information in a preset time period; calculating a performance index actual value based on the performance index influence factor information of the data to be detected; calculating a performance index expected value by using the performance index influence factor information of the data to be detected and the lubricating oil system model; and calculating a deviation value of the actual value and the expected value of the performance index, and judging whether the performance of the engine lubricating oil system is abnormal in a preset time period based on the deviation value. The technical scheme of the invention can predict and detect the engine lubricating oil system.
Description
Technical Field
The invention relates to the technical field of vehicle health management, in particular to a method and a device for detecting the performance of an engine lubricating oil system, a storage medium and a terminal.
Background
The engine lubricating oil system is an important system influencing the flight safety of an airplane, and is mainly used for supplying lubricating oil to various friction surfaces of a gear box, a bearing and the like in an engine so as to reduce the friction of parts and lubricate and cool the parts, and meanwhile, supplying working fluid necessary for feathering to a propeller. The normal operation of the oil lubrication system is an important guarantee for ensuring the safe operation of the engine, which can lead to irreparable consequences in case of failure. In order to ensure safe and reliable operation of each system of the airplane, a large number of sensors with high precision are additionally arranged on the engine lubricating oil system to strictly monitor the working parameters of the engine lubricating oil system, and the engine lubricating oil system has certain diagnostic capability, can detect partial faults and automatically takes active safety measures. In addition, the daily maintenance of the civil passenger plane can also play a role in actively discovering and preventing various faults including the lubricating oil system to a certain extent.
However, at present, the state detection and daily maintenance of the lubricating oil system by each airline company mainly focuses on the faults which have already occurred, an applicable method and an effective technology for early detection and early warning of the faults are not available, the maintenance strategy is mainly timed maintenance and after-repair, and the requirements of improving the operation efficiency of the civil airliner and reducing the operation and maintenance cost cannot be met.
Similarly, the range from aircraft engine oil systems to other vehicle oil systems is extended, and similar technical problems and deficiencies exist with other vehicle oil systems. Therefore, in order to improve the operation efficiency of airplanes and other vehicles and reduce the operation cost, it is very necessary to perform performance detection on engine lubricating oil systems such as vehicles and the like and construct early warning analysis of the engine lubricating oil systems.
Disclosure of Invention
The invention solves the technical problem of how to detect the performance of an engine lubricating oil system.
In order to solve the technical problem, an embodiment of the present invention provides a performance detection method for an engine oil system, including: obtaining a plurality of sample data from historical data generated by normal operation of an engine lubricating oil system, wherein each sample data comprises performance index influence factor information and a performance index value related to the performance index influence factor information, and the performance index value is obtained by calculation of the performance index influence factor information; training to obtain a lubricating oil system model of the engine lubricating oil system by using the performance index influence factor information and the associated performance index value; acquiring data to be detected in a preset time period, wherein the data to be detected comprises performance index influence factor information; calculating to obtain an actual value of the performance index based on the performance index influence factor information in the data to be detected; calculating to obtain a performance index expected value by using performance index influence factor information in the data to be detected and the lubricating oil system model; and calculating a deviation value between the actual value of the performance index and the expected value of the performance index, and judging whether the performance of the engine lubricating oil system is abnormal in the preset time period or not based on the deviation value.
Optionally, the performance index influence factor information includes: a value of a lubricating oil pressure in the engine lubricating oil system, an engine speed of the engine lubricating oil system.
Optionally, the performance index value of the engine oil system refers to an oil pressure relative noise ratio in the engine oil system, and the oil pressure relative noise ratio refers to a quotient of an oil pressure signal-to-noise ratio and an engine speed signal-to-noise ratio of the engine oil system.
Optionally, the determining whether the performance of the engine oil system in the preset time period is abnormal based on the deviation value includes: and if the deviation value between the actual value of the performance index and the expected value of the performance index exceeds a preset threshold value, judging that the engine lubricating oil system has abnormal risks in the preset time period.
Optionally, the obtaining of the performance index value through calculating the performance index influence factor information includes: and performing wavelet transformation on the performance index influence factor information, and calculating to obtain a performance index value associated with the performance index influence factor information.
Optionally, the historical data includes a plurality of oil pressure values and engine speeds arranged according to time; the performing wavelet transform on the performance index influencing factor information, and calculating to obtain the performance index value associated with the performance index influencing factor information includes: extracting the lubricating oil pressure value from the historical data to construct a lubricating oil pressure original signal arranged according to time, and extracting the engine speed from the historical data to construct an engine speed original signal arranged according to time; respectively performing wavelet transformation and wavelet reconstruction on the original lubricating oil pressure signal and the original engine rotating speed signal to obtain a reconstructed lubricating oil pressure signal and a reconstructed engine rotating speed signal; respectively calculating the lubricating oil pressure signal-to-noise ratio and the engine rotating speed signal-to-noise ratio according to the signal-to-noise ratio principle; taking the quotient of the pressure signal-to-noise ratio of the lubricating oil and the rotating speed signal-to-noise ratio of the engine as a performance index expected value related to the performance index influence factor information; the lubricating oil pressure signal-to-noise ratio is the ratio of a lubricating oil pressure reconstruction error to the lubricating oil pressure original signal, and the engine rotating speed signal-to-noise ratio is the ratio of an engine rotating speed reconstruction error to the engine rotating speed original signal; the oil pressure reconstruction error is the difference between the original oil pressure signal and the reconstructed oil pressure signal, and the engine rotating speed reconstruction error is the difference between the original engine rotating speed signal and the reconstructed engine rotating speed signal.
Optionally, the performing wavelet transform and wavelet reconstruction on the lubricant pressure signal and the engine speed signal respectively to obtain a reconstructed lubricant pressure signal and a reconstructed engine speed signal includes: respectively carrying out wavelet transformation on the lubricating oil pressure signal and the engine rotating speed signal to obtain a wavelet coefficient and a scale coefficient; denoising the wavelet coefficient and the scale coefficient respectively to obtain a denoised wavelet coefficient and a denoised scale coefficient; and respectively performing wavelet reconstruction on the denoised wavelet coefficient and the denoised scale coefficient to obtain a reconstructed lubricating oil pressure signal and a reconstructed engine rotating speed signal.
In order to solve the above technical problem, an embodiment of the present invention further provides a performance detection apparatus for an engine oil system, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is suitable for acquiring a plurality of sample data from historical data generated by normal operation of an engine lubricating oil system, each sample data comprises performance index influence factor information and a performance index value related to the performance index influence factor information, and the performance index value is obtained by calculation of the performance index influence factor information; the training module is suitable for training to obtain a lubricating oil system model of the engine lubricating oil system by utilizing the performance index influence factor information and the associated performance index value; the second acquisition module is suitable for acquiring data to be detected in a preset time period, and the data to be detected comprises performance index influence factor information; the first calculation module is suitable for calculating to obtain an actual performance index value based on the performance index influence factor information in the data to be detected; the second calculation module is suitable for calculating to obtain a performance index expected value by utilizing the performance index influence factor information in the data to be detected and the lubricating oil system model; and the judging module is suitable for calculating a deviation value between the actual value of the performance index and the expected value of the performance index and judging whether the performance of the engine lubricating oil system is abnormal in the preset time period or not based on the deviation value.
To solve the above technical problem, an embodiment of the present invention further provides a storage medium having stored thereon computer instructions, where the computer instructions execute the steps of the above method when executed.
In order to solve the foregoing technical problem, an embodiment of the present invention further provides a terminal, including a memory and a processor, where the memory stores computer instructions executable on the processor, and the processor executes the computer instructions to perform the steps of the foregoing method.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides a performance detection method of an engine lubricating oil system, which comprises the following steps: obtaining a plurality of sample data from historical data generated by normal operation of an engine lubricating oil system, wherein each sample data comprises performance index influence factor information and a performance index value related to the performance index influence factor information, and the performance index value is obtained by calculation of the performance index influence factor information; training to obtain a lubricating oil system model of the engine lubricating oil system by using the performance index influence factor information and the associated performance index value; acquiring data to be detected in a preset time period, wherein the data to be detected comprises performance index influence factor information; calculating to obtain a performance index actual value based on the performance index influence factor information in the data to be detected; calculating to obtain a performance index expected value by using performance index influence factor information in the data to be detected and the lubricating oil system model; and calculating a deviation value between the actual value of the performance index and the expected value of the performance index, and judging whether the performance of the engine lubricating oil system in the preset time period is abnormal or not based on the deviation value. According to the embodiment of the invention, whether the engine lubricating oil system is in an abnormal state or not can be judged by analyzing the deviation condition between the actual value of the performance index when the engine lubricating oil system (such as an engine lubricating oil system of a vehicle like an airplane and the like) actually runs and the expected value of the performance index obtained based on the lubricating oil system model and the performance index influence factor information of the data to be detected, so that the early fault of the engine lubricating oil system can be detected. Furthermore, the embodiment of the invention can fully utilize the historical data generated by the normal operation of the engine lubricating oil system to judge and predict the performance of the engine lubricating oil system under the condition of not changing the existing equipment and detection conditions, is favorable for discovering the performance degradation and potential faults of the engine lubricating oil system in advance, can reduce the influence of the faults of the engine lubricating oil system on the normal operation of vehicles, and provides powerful support for the state maintenance of the engine lubricating oil system of the vehicles.
Further, the performance index influencing factor information includes: the performance index influencing factor information comprises: a value of a lubricating oil pressure in the engine lubricating oil system, an engine speed of the engine lubricating oil system. In the running process of the vehicle, the lubricating oil pressure value in the engine lubricating oil system and the engine rotating speed of the engine lubricating oil system are used as performance index influence factor information, the performance data is easily obtained by existing equipment, the performance prediction of the engine lubricating oil system can be completed without changing the existing equipment, and a feasible scheme is further provided for detecting the potential fault of the engine lubricating oil system.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting performance of an engine oil system according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for detecting the performance of an engine oil system in a typical application scenario according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for constructing a normal behavior model of pressure fluctuations of oil in a typical scenario according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a performance detection device of an engine lubricating oil system according to an embodiment of the present invention.
Detailed Description
As the technical background, the state detection and daily maintenance of the engine oil system of the current vehicles such as airplanes mainly focus on the faults which have already occurred, the early detection of the faults is lack of applicable methods and effective technologies, and the maintenance strategies are mainly timed maintenance and after-repair, so that the requirements of improving the operating efficiency of the vehicles and reducing the operating cost cannot be met.
The embodiment of the invention provides a performance detection method of an engine lubricating oil system, which comprises the following steps: obtaining a plurality of sample data from historical data generated by normal operation of an engine lubricating oil system, wherein each sample data comprises performance index influence factor information and a performance index value related to the performance index influence factor information, and the performance index value is obtained by calculation of the performance index influence factor information; training to obtain a lubricating oil system model of the engine lubricating oil system by using the performance index influence factor information and the associated performance index value; acquiring data to be detected in a preset time period, wherein the data to be detected comprises performance index influence factor information; calculating to obtain an actual value of the performance index based on the performance index influence factor information in the data to be detected; calculating to obtain a performance index expected value by using performance index influence factor information in the data to be detected and the lubricating oil system model; and calculating a deviation value between the actual value of the performance index and the expected value of the performance index, and judging whether the performance of the engine lubricating oil system is abnormal in the preset time period or not based on the deviation value.
According to the embodiment of the invention, whether the engine lubricating oil system is in an abnormal state can be judged by analyzing the deviation condition between the actual value of the performance index when the engine lubricating oil system (such as an engine lubricating oil system of a vehicle like an airplane and the like) actually runs and the expected value of the performance index obtained based on the engine lubricating oil system model and the performance index influence factor information of the data to be detected, so that the early failure of the engine lubricating oil system can be detected.
Furthermore, the embodiment of the invention can fully utilize the historical data generated by the normal operation of the engine lubricating oil system to judge and predict the performance of the engine lubricating oil system under the condition of not changing the existing equipment and detection conditions, is favorable for discovering the performance degradation and potential faults of the engine lubricating oil system in advance, can reduce the influence of the faults of the engine lubricating oil system on the normal operation of vehicles, and provides powerful support for the state maintenance of the engine lubricating oil system of the vehicles.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Fig. 1 is a schematic flow chart of a method for detecting performance of a vehicle engine oil system according to an embodiment of the present invention. The performance detection method may be used to detect or pre-check whether a vehicle engine oil system is operating properly, for example, to detect whether an aircraft engine oil system is operating properly.
Specifically, the performance detection method may include the steps of:
step S101, obtaining a plurality of sample data from historical data generated by normal operation of an engine lubricating oil system, wherein each sample data comprises performance index influence factor information and a performance index value related to the performance index information, and the performance index value is obtained by calculation of the performance index influence factor information;
step S102, training to obtain a lubricating oil system model of the engine lubricating oil system by using the performance index influence factor information and the associated performance index value;
step S103, acquiring data to be detected in a preset time period, wherein the data to be detected comprises performance index influence factor information;
step S104, calculating to obtain an actual value of the performance index based on the information of the performance index influence factors in the data to be detected;
step S105, calculating to obtain a performance index expected value by using performance index influence factor information in the data to be detected and the lubricating oil system model;
and step S106, calculating a deviation value between the actual value of the performance index and the expected value of the performance index, and judging whether the performance of the engine lubricating oil system is abnormal in the preset time period or not based on the deviation value.
More specifically, during the operation of a vehicle such as an aircraft, other operation data of an engine lubricating oil system and the vehicle can be recorded at a proper time, so that historical operation data arranged according to time can be formed. In a specific implementation, historical operation data generated when the engine lubricating oil system operates normally can be used as historical data. The historical data may refer to data obtained when the engine oil system is in good performance state, in normal operation, and without a performance fault.
The historical data may include a plurality of values of the lubricant pressure, the engine speed of the engine lubricant system, and the like, arranged in time.
In step S101, a plurality of sample data may be acquired from a set of historical data of the engine oil system. In one embodiment, each sample data may include performance index influencer information and its associated performance index value. The performance index influence factor information may be a value of a lubricating oil pressure in the engine lubricating oil system, and an engine speed of the engine lubricating oil system, and is obtained by measuring and monitoring through a sensor or other measuring tools. The performance index value may be obtained by calculating and transforming the performance index influence factor information by using wavelet transformation, and the functional relationship between the performance index value and the performance index influence factor information may be derived by mathematical operation.
Under normal conditions, the lubricating oil pressure value of the engine lubricating oil pressure changes along with the engine rotating speed, and when the engine rotating speed is stable, the lubricating oil pressure is basically unchanged, namely the lubricating oil pressure and the engine rotating speed basically keep the same change trend; when the lubricating oil pressure abnormally fluctuates, the lubricating oil pressure is in periodic fluctuation except the change in the same direction as the rotating speed of the engine, and the difference between the maximum value and the minimum value of the fluctuation can reach tens of Pounds per Square Inch (pound per Square Inch, PSI for short).
In step S102, a lubricating oil system model of the engine lubricating oil system may be obtained by training using the performance index influencing factor information and the associated performance index value in the sample data.
In an embodiment, the lubricant pressure value and the engine speed in the sample data of the engine lubricant system may be used to obtain a lubricant pressure original signal and an engine speed original signal, and then the performance index value associated with the performance index influencing factor information is obtained by performing wavelet transformation and wavelet reconstruction on the lubricant pressure original signal and the engine speed original signal, where a functional relationship between the performance index influencing factor information and the associated performance index value is a lubricant system model of the engine lubricant system. It should be noted that the raw oil pressure signal and the raw engine speed signal may be discrete raw signals.
And then substituting the parameters into the functional relation to obtain the lubricating oil system model of the engine lubricating oil system. For example, a lubricating oil system model of the engine lubricating oil system is obtained.
Specifically, the oil system model is as follows: n is a radical ofr＝f(Op,Es). Wherein N isrThe expected value of the relative noise ratio of the lubricating oil pressure is represented, namely the ratio of the signal-to-noise ratio of the lubricating oil pressure to the corresponding signal-to-noise ratio of the engine speed; o ispRepresents a value of oil pressure; esRepresenting engine speed; the f () function represents the oil system model to describe the overall condition of the oil pressure fluctuation.
Specifically, first, the performance index influencing factor information may be obtained from the sample data, and the original lubricating oil pressure signal and the corresponding original engine speed signal may be respectively constructed.
Secondly, a proper wavelet and a proper decomposition grade number can be selected, discrete wavelet transformation is respectively carried out on the original lubricating oil pressure signal and the corresponding original engine speed signal to obtain decomposed signals, and each decomposed signal comprises a wavelet coefficient and a scale coefficient.
Then, the decomposed signals, that is, the decomposed oil pressure signals and the corresponding engine speed signals, may be subjected to noise reduction processing, respectively, to obtain noise-reduced signals. In practice, modulo maximum or the like noise reduction may be employedProcessing mode, determining noise reduction threshold value delta1And respectively carrying out noise reduction treatment on the decomposed oil pressure signal and the corresponding engine speed signal, namely carrying out partial coefficient suppression on wavelet coefficients (high-frequency detail parts) of each layer in the decomposed signal, thereby obtaining the decomposed signal after the noise reduction treatment.
Further, wavelet reconstruction can be performed on the decomposed and denoised lubricating oil pressure signal and the engine rotating speed signal by combining with a wavelet transform method, so as to respectively obtain the lubricating oil pressure reconstruction signal and the corresponding engine rotating speed reconstruction signal. Further, according to the signal-to-noise ratio principle, the lubricating oil pressure signal-to-noise ratio and the engine rotating speed signal-to-noise ratio can be respectively calculated. In a specific implementation, the ratio of the reconstruction error of the oil pressure to its original signal can be determined as the signal-to-noise ratio of the oil pressure; and determining the ratio of the reconstruction error of the engine speed to the original signal thereof as the signal-to-noise ratio of the engine speed, thereby obtaining the normal noise ratio for describing the condition of the pressure fluctuation of the lubricating oil of the civil passenger aircraft.
Further, the quotient of the oil pressure signal-to-noise ratio and the engine speed signal-to-noise ratio may be used as the performance index value associated with the performance index influencing factor information, i.e., the relative noise ratio of the normal fluctuation of the oil pressure system.
In step S103, data to be detected within a preset time period may be acquired. The data to be detected at least comprises performance index influence factor information. The preset time period may be a time range or a time point.
In step S104, if the data to be detected is determined, wavelet transform may be performed on the performance index influencing factor information in the data to be detected to obtain an actual value of the performance index.
Specifically, the oil pressure values in the performance index influencing factor information may be arranged according to time to obtain an original oil pressure signal of the data to be detected. And the engine rotating speeds in the performance index influence factor information can be arranged according to time to obtain the original engine rotating speed signal of the data to be detected.
Further, wavelet transformation and wavelet reconstruction are carried out on the original lubricating oil pressure signal and the original engine speed signal of the data to be detected, so that a lubricating oil pressure signal-to-noise ratio and an engine speed signal-to-noise ratio of the data to be detected are obtained, and the quotient of the lubricating oil pressure signal-to-noise ratio and the engine speed signal-to-noise ratio of the data to be detected is used as the relative noise ratio of the data to be detected.
Then, in step S105, a performance index expected value may be calculated by using the performance index influencing factor information in the data to be detected and the lubricating oil system model. Specifically, the value of the lubricating oil pressure and the engine speed in the data to be detected can be used as the input of the lubricating oil system model, so as to calculate the expected value of the performance index of the data to be detected.
In step S106, a deviation value between the expected value and the actual value of the performance index may be calculated. Further, it may be determined whether there is an abnormal risk in the performance of the engine oil system according to the deviation value.
In one embodiment, the predetermined threshold may be an empirical value if the deviation value is less than a predetermined threshold, indicating that the oil pressure fluctuation is normal. In another embodiment, if the offset value is greater than or equal to the predetermined threshold value, indicating an abnormal oil pressure fluctuation, servicing, troubleshooting, or other factors may be required.
For example, assume that the relative noise ratio of the data to be detected is rn(ii) a The relative noise ratio of normal data obtained by the oil system model is rzThe deviation is Δ r, Δ r ═ rn-rzL. Suppose delta2Is said preset threshold value, if Δ r<δ2Then, the lubricating oil pressure fluctuation is normal without maintenance; if Δ r ≧ Δ2Then an oil pressure fluctuation anomaly is indicated, requiring servicing, troubleshooting, or other factors.
The following description will be made in detail with reference to an aircraft lubricating oil system as a specific example. Fig. 2 is a schematic flow chart of a method for detecting performance of an aircraft engine oil system in a typical scenario according to an embodiment of the present invention.
Referring to fig. 2, taking an aircraft as a civil passenger aircraft as an example, the method for detecting the performance of the engine lubricating oil system of the civil passenger aircraft includes the following steps:
first, operation s1 is performed, i.e., a performance metric is defined. The performance index is a ratio of a relative noise to a pressure of the oil, i.e., a quotient of a signal to noise ratio to a speed of the engine. Specifically, the quotient of the lubricating oil pressure signal-to-noise ratio and the engine rotating speed signal-to-noise ratio is defined by analyzing and summarizing the working principle and the working environment of the lubricating oil pressure fluctuation condition of the civil passenger aircraft and combining the relevant knowledge of signal processing, namely the lubricating oil pressure relative noise ratio is a detection index of the lubricating oil pressure fluctuation, and the overall condition of the lubricating oil pressure fluctuation of the civil passenger aircraft is described through the performance index.
Next, operation s2 is performed to define influencing factors, i.e., performance index influencing factor information. Specifically, by analyzing and summarizing the working principle and the working environment of the pressure fluctuation condition of the lubricating oil of the civil airliner, the performance index influence factor information can be determined to be the lubricating oil pressure and the engine rotating speed.
Again, operation s3 is performed to define a normal behavior model of civil aircraft lube pressure fluctuation, illustrated as a lube system model. Specifically, a functional relation between the performance index value and the performance index influence factor information is determined, and the functional relation is used for describing the overall situation of the lubricating oil pressure fluctuation of the civil passenger plane. In one embodiment, a normal behavior model of civil aircraft lube pressure fluctuations may be derived based on wavelet transforms.
The oil system model is noted as: n is a radical ofr＝f(Op,Es). Wherein N isrThe expected value of the relative noise ratio of the oil pressure is expressed, namely the ratio of the signal-to-noise ratio of the oil pressure to the corresponding signal-to-noise ratio of the engine speed; o ispRepresents a value of oil pressure; esRepresenting engine speed; the f (-) function represents the oil system model to describe the overall behavior of the oil pressure fluctuations.
Thereafter, operation s4 is performed, i.e. sample data and data to be detected are determined, and the sample data may be selected from the historical data.
Further, operation s51 is performed to train the relative noise ratio of the model of the oil system, and operation s52 is performed to calculate the relative noise ratio of the data to be detected.
Specifically, a training sample set and a testing sample set are constructed by selecting data when the civil passenger aircraft lubricating oil system has no faults and has no performance degradation, and the training sample set and the testing sample set are applied to a normal behavior model of the civil passenger aircraft lubricating oil pressure fluctuation for training and testing to obtain the relative noise ratio r of the lubricating oil system modelzAnd is used to describe the relative noise ratio of normal fluctuations in the lubricating oil pressure of a civil aircraft. For the data to be detected which needs to be subjected to the oil pressure fluctuation detection, the relative noise ratio r of the data to be detected can be calculated according to the calculation processn。
Fig. 3 is a schematic flow chart of a method for constructing a normal behavior model of oil pressure fluctuation in a typical scenario according to an embodiment of the present invention. Taking a normal behavior model of the lubricating oil pressure fluctuation of the civil passenger aircraft as an example, referring to fig. 3, the specific steps of the method for constructing the normal behavior model of the lubricating oil pressure fluctuation of the civil passenger aircraft may include the following steps:
step S301, constructing an original lubricating oil pressure signal S by adopting historical data of an engine lubricating oil systemoAnd a raw engine speed signal Se. In specific implementation, the raw oil pressure signal S can be constructed based on the performance index influence factor information in the historical dataoOriginal signal S of engine speede。
Step S302, selecting proper wavelets and decomposition levels to perform wavelet transformation to obtain decomposed signal SNo、SNe. In specific implementation, the original signal S of the oil pressure can be processed by selecting proper wavelets and decomposition levelsoEngine speed SeDiscrete wavelet transform is carried out to obtain the decomposed signal SNo、SNe。
Step S303, determining a noise reduction threshold value by adopting a modulus maximum value, and performing decomposition on the decomposed signal SNoAnd SNeTo make a noise reductionAnd obtaining the noise reduction signal. In specific implementation, the noise reduction threshold δ may be determined by a mode of noise reduction processing of a modulo maximum1Separately aligning the decomposed signals SNo、SNeAnd carrying out noise reduction treatment. For example, using a threshold value δ1For the decomposed signal SNo、SNeAnd screening the wavelet coefficients of each layer.
Step S304, reconstructing the noise reduction signal to obtain a reconstructed signal SCo，SCe. In specific implementation, the obtained wavelet coefficient can be used in combination with a wavelet transformation method to reconstruct the original signals of the lubricating oil pressure and the engine rotating speed respectively so as to obtain a reconstructed signal SCo、SCe。
Step S305, based on the reconstructed signal SCo、SCeAnd the original signal So、SeObtaining the pressure signal-to-noise ratio r of the lubricating oiloSignal to noise ratio r of enginee. In specific implementation, the oil pressure signal-to-noise ratio r can be respectively calculated according to the signal-to-noise ratio principleoEngine speed signal to noise ratio reTo obtain the relative noise ratio r of the oil system modelzFor describing the relative noise ratio of normal oil pressure fluctuations of the passenger aircraft. r iszIs the pressure signal-to-noise ratio r of the lubricating oil of the civil passenger planeoSignal-to-noise ratio r with engine speedeIs reflected in the pressure fluctuations of the oil under normal behavior of the oil system.
In step S306, r is calculatedo/reTo obtain rz。
Further, referring to fig. 2, an operation s6 may be performed to calculate a deviation value. I.e. the relative noise ratio rnModel relative noise ratio r to oil systemzComparing, calculating deviation value delta r ═ rn-rz|。
Further, operation s7 may be performed to determine whether the deviation value exceeds a predetermined threshold. Specifically, assume that the preset threshold is δ2. Δ r can then be analyzed: if Δ r<δ2Then operation s82 is performed with normal performance, indicating that the oil pressure fluctuation is normal; if Δ r ≧ Δ2Then operation s81 is performed to perform a performance flare warning indicating that the oil pressure fluctuation is abnormal and that servicing, troubleshooting, or other factors are required. Wherein, delta2Are empirical values.
Therefore, in the embodiment of the invention, the original signal of the lubricating oil pressure and the corresponding original signal of the engine rotating speed are subjected to noise reduction treatment by adopting a wavelet transform mode, and the lubricating oil pressure value with abnormal fluctuation is detected by comparing the signal-to-noise ratio of the two signals, so that the early fault of the lubricating oil pressure is identified. Moreover, the existing data of the vehicles such as the civil passenger plane and the like can be fully utilized under the condition of not changing the existing equipment and detection conditions of the vehicles, the early warning analysis is carried out on the lubricating oil pressure fluctuation, the lubricating oil pressure fluctuation abnormity is found in advance, and the influence of the lubricating oil pressure fluctuation abnormity on the normal operation of the civil passenger plane is further reduced.
Fig. 4 is a schematic structural diagram of a performance detection device of a vehicle engine oil system according to an embodiment of the present invention. The performance detection device 4 of the vehicle engine lubricating oil system (hereinafter referred to as the performance detection device 4) can predict the vehicle engine lubricating oil system by adopting the method shown in the above fig. 1 to 3, and can send out an early warning signal according to the prediction result.
Specifically, the performance detection device 4 may include: a first obtaining module 41, configured to obtain a plurality of sample data from historical data generated during normal operation of an engine oil system, where each sample data includes performance index influencing factor information, and the performance index value is obtained by calculating the performance index influencing factor information; a training module 42, configured to calculate, by using the information of the performance index impact factor, a lubricating oil system model of the engine lubricating oil system, where the lubricating oil system model includes a performance index expected value associated with the information of the performance index impact factor; a second obtaining module 43, configured to obtain data to be detected within a preset time period, where the data to be detected includes performance index influence factor information; the first calculation module 44 is configured to calculate an actual value of the performance index based on the information of the performance index influencing factors in the data to be detected; the second calculation module 45 is suitable for calculating to obtain a performance index expected value by using the data to be detected and the lubricating oil system model; and the judging module 46 is configured to calculate a deviation value between the actual value of the performance index and the expected value of the performance index, and judge whether the performance of the engine oil system is abnormal in the preset time period based on the deviation value.
In a specific implementation, the performance index influencing factor information may include: a value of a lubricating oil pressure in the engine lubricating oil system, an engine speed of the engine lubricating oil system.
In a specific implementation, the performance index value of the engine lubricating oil system refers to a lubricating oil pressure relative noise ratio in the engine lubricating oil system, and the lubricating oil pressure relative noise ratio refers to a quotient of a lubricating oil pressure signal-to-noise ratio and an engine speed signal-to-noise ratio of the engine lubricating oil system.
In a specific implementation, the determining module 46 may include: a decision sub-module 461. If the deviation value between the actual value of the performance index and the expected value of the performance index exceeds a preset threshold, the determining submodule 461 is configured to determine that there is an abnormal risk in the engine oil system in the preset time period.
In a specific implementation, the first obtaining module 41 includes: and the calculating submodule 411 is configured to perform wavelet transformation on the performance index influence factor information, and train to obtain a performance index expected value associated with the performance index influence factor information.
In a specific implementation, the historical data includes a plurality of oil pressure values and engine speeds arranged in time, and the calculation submodule 411 may include: an extracting unit 4111, configured to extract a lubricant pressure value from the plurality of data points to construct a raw lubricant pressure signal arranged in time, and extract an engine speed from the plurality of data points to construct a raw engine speed signal arranged in time; a constructing unit 4112, configured to perform wavelet transformation and wavelet reconstruction on the original lubricating oil pressure signal and the original engine speed signal respectively to obtain a reconstructed lubricating oil pressure signal and a reconstructed engine speed signal; a determining unit 4113 for calculating a signal-to-noise ratio of the pressure of the lubricating oil and a signal-to-noise ratio of the rotating speed of the engine respectively according to a signal-to-noise ratio principle; a generating unit 4114, configured to use a quotient of the oil pressure signal-to-noise ratio and the engine speed signal-to-noise ratio as a performance index expected value associated with the performance index influencing factor information; the lubricating oil pressure signal-to-noise ratio is the ratio of a lubricating oil pressure reconstruction error to the lubricating oil pressure original signal, and the engine rotating speed signal-to-noise ratio is the ratio of an engine rotating speed reconstruction error to the engine rotating speed original signal; the oil pressure reconstruction error is the difference between the original oil pressure signal and the reconstructed oil pressure signal, and the engine rotating speed reconstruction error is the difference between the original engine rotating speed signal and the reconstructed engine rotating speed signal.
In a specific implementation, the constructing unit 4112 may be configured to perform wavelet transform on the oil pressure signal and the engine speed signal to obtain a wavelet coefficient and a scale coefficient; the wavelet coefficient and the scale coefficient are subjected to denoising processing respectively to obtain a denoised wavelet coefficient and a denoised scale coefficient; and the wavelet reconstruction module is used for performing wavelet reconstruction on the denoised wavelet coefficient and the denoised scale coefficient respectively to obtain a reconstructed lubricating oil pressure signal and a reconstructed engine rotating speed signal.
For more details of the operation principle and the operation mode of the performance detection apparatus 4, reference may be made to the description in the embodiments shown in fig. 1 to fig. 3, and details are not repeated here.
Further, the embodiment of the present invention further discloses a storage medium, on which computer instructions are stored, and when the computer instructions are executed, the technical solutions of the methods in the embodiments shown in fig. 1 to fig. 3 are executed. Preferably, the storage medium may include a computer-readable storage medium such as a non-volatile (non-volatile) memory or a non-transitory (non-transient) memory. The computer readable storage medium may include ROM, RAM, magnetic or optical disks, and the like.
Further, an embodiment of the present invention further discloses a terminal, which includes a memory and a processor, where the memory stores a computer instruction capable of running on the processor, and the processor executes the technical solution of the method in the embodiment shown in fig. 1 to 3 when running the computer instruction. In particular, the terminal may be a vehicle having an engine oil system, such as an aircraft.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. A method for detecting performance of an engine oil system, comprising:
obtaining a plurality of sample data from historical data generated during normal operation of an engine lubricating oil system, wherein,
each sample data comprises performance index influence factor information and a performance index value related to the performance index influence factor information, and the performance index value is obtained through calculation of the performance index influence factor information;
training to obtain a lubricating oil system model of the engine lubricating oil system by using the performance index influence factor information and the associated performance index value;
acquiring data to be detected in a preset time period, wherein the data to be detected comprises performance index influence factor information;
calculating to obtain an actual value of the performance index based on the performance index influence factor information in the data to be detected;
calculating to obtain a performance index expected value by using performance index influence factor information in the data to be detected and the lubricating oil system model;
calculating a deviation value between the actual value of the performance index and the expected value of the performance index, and judging whether the performance of the engine lubricating oil system is abnormal in the preset time period or not based on the deviation value;
wherein the performance index influencing factor information comprises: a lubricating oil pressure value in the engine lubricating oil system, an engine speed of the engine lubricating oil system;
the performance index value of the engine lubricating oil system refers to a lubricating oil pressure relative noise ratio in the engine lubricating oil system, and the lubricating oil pressure relative noise ratio refers to a quotient of a lubricating oil pressure signal-to-noise ratio and an engine speed signal-to-noise ratio of the engine lubricating oil system.
2. The performance detection method according to claim 1, wherein the determining whether the performance of the engine oil system is abnormal in the preset time period based on the deviation value includes: and if the deviation value between the actual value of the performance index and the expected value of the performance index exceeds a preset threshold value, judging that the engine lubricating oil system has abnormal risks in the preset time period.
3. The performance detection method according to claim 1, wherein the performance index value obtained by the performance index influencing factor information calculation includes:
and performing wavelet transformation on the performance index influence factor information, and calculating to obtain a performance index value associated with the performance index influence factor information.
4. The performance detection method according to claim 3, characterized in that the history data includes a plurality of values of the oil pressure and the engine speed arranged in time; the performing wavelet transform on the performance index influencing factor information, and calculating to obtain the performance index value associated with the performance index influencing factor information includes:
extracting the lubricating oil pressure value from the historical data to construct a lubricating oil pressure original signal arranged according to time, and extracting the engine speed from the historical data to construct an engine speed original signal arranged according to time;
respectively performing wavelet transformation and wavelet reconstruction on the original lubricating oil pressure signal and the original engine rotating speed signal to obtain a reconstructed lubricating oil pressure signal and a reconstructed engine rotating speed signal;
respectively calculating the lubricating oil pressure signal-to-noise ratio and the engine rotating speed signal-to-noise ratio according to the signal-to-noise ratio principle;
taking the quotient of the lubricating oil pressure signal-to-noise ratio and the engine rotating speed signal-to-noise ratio as a performance index value related to the performance index influence factor information;
the lubricating oil pressure signal-to-noise ratio is the ratio of a lubricating oil pressure reconstruction error to the lubricating oil pressure original signal, and the engine rotating speed signal-to-noise ratio is the ratio of an engine rotating speed reconstruction error to the engine rotating speed original signal;
the oil pressure reconstruction error is the difference between the original oil pressure signal and the reconstructed oil pressure signal, and the engine rotating speed reconstruction error is the difference between the original engine rotating speed signal and the reconstructed engine rotating speed signal.
5. The performance detection method of claim 4, wherein the performing wavelet transform and wavelet reconstruction on the original oil pressure signal and the original engine speed signal to obtain a reconstructed oil pressure signal and a reconstructed engine speed signal comprises:
respectively carrying out wavelet transformation on the original lubricating oil pressure signal and the original engine speed signal to obtain a wavelet coefficient and a scale coefficient;
denoising the wavelet coefficient and the scale coefficient respectively to obtain a denoised wavelet coefficient and a denoised scale coefficient;
and respectively performing wavelet reconstruction on the denoised wavelet coefficient and the denoised scale coefficient to obtain a reconstructed lubricating oil pressure signal and a reconstructed engine rotating speed signal.
6. A performance detection device of an engine oil system, characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is suitable for acquiring a plurality of sample data from historical data generated by normal operation of an engine lubricating oil system, each sample data comprises performance index influence factor information and a performance index value related to the performance index influence factor information, and the performance index value is obtained by calculation of the performance index influence factor information;
the training module is suitable for training to obtain a lubricating oil system model of the engine lubricating oil system by utilizing the performance index influence factor information and the associated performance index value;
the second acquisition module is suitable for acquiring data to be detected in a preset time period, and the data to be detected comprises performance index influence factor information;
the first calculation module is suitable for calculating to obtain an actual value of the performance index based on the performance index influence factor information in the data to be detected;
the second calculation module is suitable for calculating to obtain a performance index expected value by utilizing the performance index influence factor information in the data to be detected and the lubricating oil system model;
the judging module is suitable for calculating a deviation value between the actual value of the performance index and the expected value of the performance index and judging whether the performance of the engine oil system is abnormal in the preset time period or not based on the deviation value;
wherein the performance index influence factor information includes: a lubricating oil pressure value in the engine lubricating oil system, an engine speed of the engine lubricating oil system;
the performance index value of the engine oil system refers to an oil pressure relative noise ratio in the engine oil system, and the oil pressure relative noise ratio refers to a quotient of an oil pressure signal-to-noise ratio and an engine speed signal-to-noise ratio of the engine oil system.
7. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, performing the steps of the method of any one of claims 1 to 5.
8. A terminal comprising a memory and a processor, the memory having stored thereon a computer program being executable on the processor, characterized in that the processor, when executing the computer program, performs the steps of the method according to any of the claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910833892.6A CN112441254B (en) | 2019-09-04 | 2019-09-04 | Performance detection method and device of engine lubricating oil system, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910833892.6A CN112441254B (en) | 2019-09-04 | 2019-09-04 | Performance detection method and device of engine lubricating oil system, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112441254A CN112441254A (en) | 2021-03-05 |
| CN112441254B true CN112441254B (en) | 2022-07-05 |
Family
ID=74733996
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910833892.6A Active CN112441254B (en) | 2019-09-04 | 2019-09-04 | Performance detection method and device of engine lubricating oil system, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112441254B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113008551B (en) * | 2021-03-31 | 2022-04-22 | 安徽江淮汽车集团股份有限公司 | Clutch performance evaluation method and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2487704A1 (en) * | 2004-11-18 | 2006-05-18 | R. Kyle Schmidt | Method and system for health monitoring of aircraft landing gear |
| FR2900745B1 (en) * | 2006-05-05 | 2008-10-10 | Eurocopter France | METHOD AND DEVICE FOR DIAGNOSING A MECHANISM |
| CN102092477B (en) * | 2010-11-30 | 2013-02-20 | 中国民航大学 | Device and method for automatic test and fault diagnosis of plane audio integrated system |
| CN104340372A (en) * | 2013-07-31 | 2015-02-11 | 上海杰之能信息科技有限公司 | Performance monitoring method and device and monitoring server of airborne auxiliary power unit (APU) |
| CN104343492B (en) * | 2013-08-02 | 2017-02-15 | 上海杰之能软件科技有限公司 | Monitoring method and system for lubricating oil of aircraft and engine of aircraft |
| CN108681817B (en) * | 2018-05-17 | 2021-08-06 | 中电普瑞电力工程有限公司 | Excitation system performance evaluation method and device and storage medium |
-
2019
- 2019-09-04 CN CN201910833892.6A patent/CN112441254B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112441254A (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | Wavelets for fault diagnosis of rotary machines: A review with applications | |
| CN108896299B (en) | Gearbox fault detection method | |
| CN111089726B (en) | Rolling bearing fault diagnosis method based on optimal dimension singular spectrum decomposition | |
| AU2010308514A1 (en) | System and method for selecting a maintenance operation | |
| Omar et al. | Dynamic wavelet-based tool for gearbox diagnosis | |
| Attoui et al. | Vibration-based bearing fault diagnosis by an integrated DWT-FFT approach and an adaptive neuro-fuzzy inference system | |
| Alkhadafe et al. | Condition monitoring of helical gears using automated selection of features and sensors | |
| Ma et al. | Subspace-based MVE for performance degradation assessment of aero-engine bearings with multimodal features | |
| Shao et al. | Gearbox vibration monitoring using extended Kalman filters and hypothesis tests | |
| Liu et al. | Application of EMD-WVD and particle filter for gearbox fault feature extraction and remaining useful life prediction | |
| Singh et al. | A review of vibration analysis techniques for rotating machines | |
| CN112441254B (en) | Performance detection method and device of engine lubricating oil system, storage medium and terminal | |
| Shi et al. | The VMD-scale space based hoyergram and its application in rolling bearing fault diagnosis | |
| Ayaz | Autoregressive modeling approach of vibration data for bearing fault diagnosis in electric motors | |
| KR20230102431A (en) | Oil gas plant equipment failure prediction and diagnosis system based on artificial intelligence | |
| Leoni et al. | A new comprehensive monitoring and diagnostic approach for early detection of mechanical degradation in helicopter transmission systems | |
| Tastimur et al. | Defect diagnosis of rolling element bearing using deep learning | |
| Byington et al. | False alarm mitigation of vibration diagnostic systems | |
| CN113221292A (en) | Predictive maintenance model and maintenance method for wave-activated generator | |
| Baqqar et al. | A general regression neural network model for gearbox fault detection using motor operating parameters | |
| CN111929044B (en) | Method, apparatus, computing device and storage medium for monitoring device status | |
| CN115420499B (en) | Gearbox fault diagnosis method and system based on Lyapunov exponent | |
| KR102654326B1 (en) | Fault diagnosis device and method of oil purifier | |
| CN110736615B (en) | Method for diagnosing spring defects | |
| Wang et al. | Kernel regression residual decomposition method to detect rolling element bearing faults |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |