CN115982942A - Method, device, equipment and storage medium for predicting residual life of aviation precooler - Google Patents
Method, device, equipment and storage medium for predicting residual life of aviation precooler Download PDFInfo
- Publication number
- CN115982942A CN115982942A CN202211489610.3A CN202211489610A CN115982942A CN 115982942 A CN115982942 A CN 115982942A CN 202211489610 A CN202211489610 A CN 202211489610A CN 115982942 A CN115982942 A CN 115982942A
- Authority
- CN
- China
- Prior art keywords
- precooler
- data
- life
- residual life
- mlbf
- 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.)
- Granted
Links
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for predicting the residual life of an aviation precooler. The method comprises the following steps: acquiring current key parameter data of a precooler; determining whether the precooler currently belongs to a normal life cycle stage or not according to the key parameter data and a corresponding condition of a precooler life cycle stage acquired in advance; if not, fitting the key parameter data to obtain a fitting curve equation; and processing the fitting curve equation and the MLBF equation by using a multidimensional data updating correction model to obtain a predicted value of the residual life of the precooler. According to the method for predicting the residual life of the aviation precooler, the fitting curve equation and the MLBF equation are processed by utilizing the multidimensional data updating and correcting model, the predicted value of the residual life of the precooler is obtained, the prediction accuracy of the residual life of the precooler is improved, and the requirement of practical application can be well met.
Description
Technical Field
The application relates to the technical field of precoolers, in particular to a method, a device, equipment and a storage medium for predicting the residual life of an aviation precooler.
Background
The function of the aircraft bleed air system is to provide pressurized air of stable flow, pressure and temperature for user systems such as air conditioning systems, supercharging systems, anti-icing systems, aircraft engine starting systems, water tank supercharging systems, hydraulic oil tank supercharging systems and the like. Precoolers are important components of the bleed air system, which performance is degraded, directly affecting flight safety. Therefore, it is necessary to study the prediction of the remaining life of the precooler. The service life prediction result of the precooler in the related technology is not accurate enough, and the actual application requirements cannot be met.
Disclosure of Invention
The application aims to provide a method, a device, equipment and a storage medium for predicting the residual life of an aviation precooler, so as to improve the accuracy of predicting the residual life of the precooler. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to an aspect of an embodiment of the application, a method for predicting the residual life of an aviation precooler is provided, and comprises the following steps:
acquiring current key parameter data of a precooler;
determining whether the precooler currently belongs to a normal life cycle stage or not according to the key parameter data and a corresponding condition of a precooler life cycle stage acquired in advance;
if not, fitting the key parameter data to obtain a fitting curve equation;
and processing the fitting curve equation and the MLBF equation by utilizing the multidimensional data updating correction model to obtain the predicted value of the residual life of the precooler.
In some embodiments of the present application, the method further comprises:
and if the precooler currently belongs to the normal life cycle stage, acquiring the residual life value of the precooler by adopting an MLBF algorithm.
In some embodiments of the present application, the method for acquiring the corresponding condition of the precooler lifecycle stage includes:
acquiring preprocessing historical data of key parameters of a precooler;
determining a life cycle stage parameter threshold of the precooler according to the preprocessing historical data;
and determining the corresponding condition according to the life cycle stage parameter threshold.
In some embodiments of the present application, the obtaining pre-processing historical data of key parameters of a precooler includes:
acquiring historical data of key parameters of a precooler;
cleaning the historical data to obtain cleaned data;
and correcting the cleaned data to obtain the pre-processing historical data.
In some embodiments of the present application, the cleansing the historical data includes: and eliminating false data recorded due to the anomaly of the aircraft sensor in the historical data.
In some embodiments of the present application, the key parameters include precooler outlet temperature and precooler inlet pressure; the precooler lifecycle phases include a normal phase and an exception phase; the corresponding conditions for the normal phase include an MLBF value less than or equal to a first threshold, an outlet temperature less than or equal to a second threshold, and an inlet pressure less than or equal to a third threshold; the corresponding conditions for the abnormal phase include the MLBF value being greater than a first threshold and the outlet temperature being greater than a second threshold or the inlet pressure being greater than a third threshold.
In some embodiments of the application, the processing the fitted curve equation and the MLBF equation by using the multidimensional data update correction model to obtain the predicted value of the remaining life of the precooler includes:
and taking the fitted curve equation as a state equation of a multi-dimensional data updating and correcting algorithm, taking the MLBF equation as an observation equation of the multi-dimensional data updating and correcting algorithm, and predicting by using a multi-dimensional data updating and correcting model to obtain the optimal estimated residual life.
According to another aspect of the embodiments of the present application, there is provided an apparatus for predicting remaining life of an aircraft precooler, including:
the key parameter data acquisition module is used for acquiring the current key parameter data of the precooler;
the normal phase determining module is used for determining whether the precooler currently belongs to a normal life cycle phase according to the key parameter data and a corresponding condition of the precooler life cycle phase acquired in advance;
the fitting module is used for fitting the key parameter data to obtain a fitting curve equation if the key parameter data does not belong to the key parameter data;
and the residual life prediction module is used for processing the fitting curve equation and the MLBF equation by utilizing the multidimensional data updating and correcting model to obtain a predicted value of the residual life of the precooler.
According to another aspect of the embodiments of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement the method for predicting the remaining life of an aircraft precooler.
According to another aspect of an embodiment of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, the program being executed by a processor to implement the method for predicting the remaining life of an aircraft precooler described in any one of the above.
The technical scheme provided by one aspect of the embodiment of the application can have the following beneficial effects:
according to the method for predicting the remaining life of the aircraft precooler based on multi-dimensional data updating and correcting, whether the precooler belongs to the normal life cycle stage or not is determined according to key parameter data and corresponding conditions of the precooler life cycle stage obtained in advance, if not, the key parameter data is fitted to obtain a fitted curve equation, and the fitted curve equation and an MLBF equation are processed by using a multi-dimensional data updating and correcting model to obtain the predicted value of the remaining life of the precooler, so that the prediction accuracy of the remaining life of the precooler is improved, and the requirement of practical application can be well met.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application, or may be learned by the practice of the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 illustrates a flow chart of a method of predicting remaining life of an aircraft precooler, in accordance with an embodiment of the present application.
FIG. 2 illustrates a flow chart of a method of predicting remaining life of an aircraft precooler, in accordance with another embodiment of the present application.
FIG. 3 illustrates a precooler performance lifecycle diagram in one embodiment of the present application.
FIG. 4 illustrates precooler pressure decay trends and precooler pressure data fitting trend lines in one embodiment of the present application.
FIG. 5 shows a fleet aircraft precooler pressure history QAR (in one embodiment of the present application
English: quick Access Recorder, chinese: fast access recorder) data analysis graph.
FIG. 6 shows a precooler outlet temperature maximum data fit in one embodiment of the present application.
FIG. 7 illustrates a graph of precooler remaining life prediction results corrected based on multidimensional data updates in one embodiment of the present application.
FIG. 8 shows a block diagram of an apparatus for predicting the remaining life of an aircraft precooler according to an embodiment of the present application.
Fig. 9 shows a block diagram of an electronic device according to an embodiment of the present application.
FIG. 10 shows a computer-readable storage medium of an embodiment of the present application.
The objects, features, and advantages of the present application will be further explained with reference to the accompanying drawings in which embodiments are shown.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Precoolers refer to heat exchangers or evaporative coolers used to reduce the temperature of the working fluid before it begins to be compressed. The precooler may be applied to an air conditioning system or to a bleed air system of an aircraft. Taking the bleed air system of an aircraft as an example, the precooler is the most important component for the bleed air system, and the service life of the precooler directly affects the service life of the bleed air system, so that for the bleed air system of an aircraft, predicting the remaining life of the precooler is crucial for the maintenance and upkeep of the bleed air system.
The inventors of the present application have found that the aircraft bleed air system precooler decays from early performance to failure, with a significant decay process as the wing ages. And predicting the remaining time from the current moment to the final failure by analyzing the historical performance degradation trend of the cable. Accurate life prediction may improve reliability of aircraft components or systems, reducing maintenance costs. One embodiment of the present application thus proposes a precooler remaining life prediction method based on multidimensional data update correction.
As shown in fig. 1, an embodiment of the present application provides a method for predicting the remaining life of an aircraft precooler, including the following steps:
acquiring key QAR data and operating data of a precooler; carrying out data acquisition and data correction processing; calculating the average service time Before Failure of the residual MLBF (English: mean Life Before Failure, abbreviated as MLBF), and defining the characteristics of the precooler in a normal period, a decay period and a Failure period aiming at the Failure mode of the precooler; synthesizing a precooler health index threshold and a calculated residual MLBF threshold, judging whether the precooler is in a decay period and a failure period, if not, continuously monitoring the performance, and if so, performing temperature, pressure and other key characteristic data fitting analysis on the precooler in the decay period and the failure period to obtain a state equation; obtaining a measurement equation by using the calculated residual MLBF; and executing a multi-dimensional data updating correction algorithm by using the state equation and the measurement equation.
In one possible embodiment, the estimated remaining life PV1 is calculated based on a key data fitting function of the aircraft component; in addition, based on the MLBF algorithm of the average service time before the fault, a corrected residual life value PV2 is calculated, a data fitting function, PV1 and PV2 are input into a calculation model of 'residual life prediction of multi-dimensional data correction updating', correction is carried out by utilizing PV2, iterative updating is carried out in the model, and finally the more accurate residual life of the precooler is obtained.
In one possible implementation, the precooler remaining life prediction method of the embodiment may include two parts, namely performance state evaluation and remaining life prediction. In the performance evaluation part, firstly, a model reflecting the health state of the precooler is established by utilizing the full life cycle data analysis of the precooler, and data fitting is carried out on the historical data of the performance attenuation of the precooler to evaluate the current performance of the precooler; meanwhile, the MLBF is introduced to obtain the average flight hours in the normal stage, and the state of the precooler is comprehensively judged: normal period, decay period, expiration period. In the residual life prediction part driven by data, discrete data fitting is facilitated, such as a data fitting formula is obtained by a least square method, a residual life data function of the precooler prediction, a residual life value PV1 and fitting reliability are obtained through historical QAR data analysis, and meanwhile, the predicted life PV2 is calculated through an MLBF algorithm; at the moment, a multi-dimensional data updating correction algorithm is introduced, and finally a predicted value of the remaining life is obtained.
In one possible implementation, the transfer relationship between the state equation at the time k and the state equation at the time k-1 can be obtained by fitting the critical data of the precooler, such as temperature and the like. The time series function of parameters such as the subsequent temperature of the precooler and the like is obtained through data fitting, the threshold value of complete failure is set based on the time series function and the precooler technical principle, and the residual life PV1 can be predicted, so that the estimated residual life is obtained.
And obtaining another residual life estimation value PV2 as residual life correction data based on the average service time before MLBF failure of the aircraft component manufacturer and the self-owned aircraft component, the week, the month and the year, and the residual life data of the historical unplanned replacement component.
The time updating process can be regarded as a predicted residual life process and is mainly used for calculating the state variable value and the predicted error of the current moment so as to determine the prior estimation value of the state variable of the next moment; the measurement update process of the actual usage data of a large number of aircraft components can be regarded as a correction process for comparing and correcting the new observed values and the prior estimated values to obtain improved posterior estimated values.
And taking the time series function, PV1 and PV2 as input calculation models, continuously updating by using the time series function, correcting iteration, and finally calculating the optimal residual life in a convergence manner.
As shown in fig. 2, another embodiment of the present application provides a method of predicting remaining life of an aircraft precooler, including steps S10-S40.
And S10, acquiring current key parameter data of the precooler.
The precooler current key parameter data may include, for example, a precooler outlet temperature and a precooler inlet pressure.
And S20, determining whether the precooler currently belongs to a normal life cycle stage according to the key parameter data and the corresponding condition of the precooler life cycle stage acquired in advance.
The precooler lifecycle includes a normal phase and an abnormal phase. The normal phase is a normal period, and the abnormal phase includes a decline period and an expiration period, which can be specifically referred to fig. 3.
In some embodiments, the method for acquiring the corresponding condition of the precooler life cycle stage comprises the following steps: acquiring preprocessing historical data of key parameters of a precooler; determining a life cycle stage parameter threshold of the precooler according to the preprocessing historical data; and determining the corresponding condition according to the life cycle stage parameter threshold.
Specifically, the obtaining of the preprocessing history data of the key parameters of the precooler may include: acquiring historical data of key parameters of a precooler; cleaning the historical data to obtain cleaned data; and correcting the cleaned data to obtain historical correction data, wherein the historical correction data is preprocessing historical data. Cleansing historical data may include: and eliminating false data in the historical data recorded by the sensor, thereby avoiding influencing the subsequent processing steps.
Illustratively, the key parameters may include precooler outlet temperature and precooler inlet pressure; the precooler lifecycle phases include a normal phase and an abnormal phase; the corresponding conditions of the normal phase include an MLBF value less than or equal to a first threshold, an outlet temperature less than or equal to a second threshold, and an inlet pressure less than or equal to a third threshold; the corresponding conditions for the abnormal phase include the MLBF value being greater than a first threshold and the outlet temperature being greater than a second threshold or the inlet pressure being greater than a third threshold. For example, in one specific example, the first threshold is 90%, the second threshold is 235 ℃, and the third threshold is 40PSI. The first threshold, the second threshold and the third threshold can be set according to actual needs.
Illustratively, through two data acquisition modes of WQAR (wireless rapid storage recorder) and ACARS (aircraft communication addressing and reporting system), representative key performance parameters are locked, and parameter data of precooler temperature, pressure, PRV (Pressure Regulating Valve) upstream Pressure, PRV actuation duration, runtime external altitude and temperature (TAT) of the bleed air system in the whole life cycle of a wing are acquired.
Because the temperature and the altitude of the work of the precooler of the bleed air system of the airplane are different when the precooler operates in the air and on the ground, the parameters such as the outlet temperature and the like can be influenced by the external temperature and the altitude air pressure. In order to realize the evaluation of the condition of each operation of the precooler, the influence of temperature and altitude on the key parameters of the precooler is eliminated by a mathematical method, the key parameters of the precooler are converted into the condition of uniform external temperature and altitude (such as standard atmospheric pressure sea level), and the corrected parameter values of the key parameters are obtained.
For example, the precooler modified outlet temperature PRE-T cor The formula:
wherein, the Precool outlet temp is the outlet temperature of the precooler, theta is the correction factor, K is the external interference factor, TAT is the total temperature, T is 0 Is the absolute temperature, T, of the atmosphere at sea level in the standard state 0 =288.15 degrees kelvin, K is the ambient temperature interference factor.
In some embodiments, the life cycle of the precooler is divided into a plurality of phases based on the historical correction data. And analyzing historical correction data of the precooler, and carrying out stage division on the life cycle of the precooler.
By way of example, it is known from analytical bleed air system technical principles that the fan bleed air flap always maintains the engine bleed air temperature at 200 ℃. The air pressure of an outlet of the engine is adjusted to be 8-36 PSI by an engine bleed valve; when the engine is in a high rotating speed, the air pressure of an outlet of the engine is adjusted to 44PSI by an engine bleed valve; the bleed air temperature downstream of the precooler is limited by means of a temperature controller of a bleed air pressure regulating valve control solenoid valve (CTS). When the temperature rises to 235 deg.c the bleed air pressure regulating flap (PRV) starts to control its downstream bleed air pressure to fall in an accelerated manner.
And analyzing historical QAR data of the precooler of the bleed air system to acquire performance life cycle data of the precooler. The life cycle division concept will be described in detail below by taking the data of the B-8XXX airplane on the wing from 2016 to 2022.
As shown in fig. 3, the machine is installed 10 months in 2015, and the running-in period data is removed. During the period from 4 months in 2016 to 6 months in 2019, the pressure and temperature data of the precooler tend to be stable, the temperature and the pressure normally fluctuate within the handbook range, and in addition, the temperature and the pressure are in the initial stage of the use of the component installation (such as the first 30% of the MLBF time interval), and the interval is set as the normal period through comprehensive judgment. During the period from 7 months in 2019 to 2 months in 2021, the outlet temperature data of the precooler of the bleed air system shows an ascending trend, the pressure shows a descending trend, and the interval (namely the time from 7 months in 2019 to 2 months in 2021) is set as a decline period through comprehensive judgment.
During the period from 3 months to 4 months in 2021, the temperature data of the outlet of the right-leading gas precooler shows an ascending trend, the temperature of a plurality of continuous flights exceeds 235 ℃, and faults occur frequently. And at 26 days after 4 months, the air leakage phenomenon is detected at bases of 7170HM2 and 10HA2 through post-aviation inspection of A city, the sealing ring is replaced, and the performance is recovered through subsequent monitoring and data result display. And 7/4/2021, checking whether the left HPV valve on the ECAM page is indicated to be not in a closed position by passing the station, and replacing the left HPV valve. 31/03/2021, and left PRV was changed after the second voyage. And subsequent monitoring and data result display performance recovery. The data shows that the left-hand precooler pressure exhibits a significant downward trend. Comprehensively judging and setting the interval as the expiration date.
And in the failure stage, the temperature of a plurality of continuous flights exceeds 235 ℃, the maximum value of the pressure of the precooler is lower than 42PSI, and the deviation from the normal interval shows that the precooler has obvious performance attenuation characteristics, which corresponds to the theoretical basis in the aircraft maintenance manual.
The service life of the precooler can be divided into 3 stages, namely a normal period, a decaying period and a failure period. When the precooler is out of date, it cannot work reliably and must be maintained or replaced in time. Thus, the first 2 stages of operating condition monitoring are of practical interest, while the remaining life prediction is estimated from the time the precooler enters the decline period.
Through historical data analysis, the output result is as follows:
1) Relevant parameters of a normal period, a decay period and a failure period of the precooler; the normal stage is a normal period, and the abnormal stage comprises a decline period and an expiration period;
2) Meanwhile, through historical QAR data analysis, a degradation model (relationship between observable data and hidden states) of precooler performance attenuation is determined, and a general precooler attenuation fitting curve formula is obtained, wherein pressure attenuation is linear trend, and temperature attenuation is curve trend;
3) And obtaining the threshold value of the performance attenuation of the precooler through technical principle analysis and historical fault data verification.
And judging the current life cycle stage of the precooler according to the currently acquired key parameter data. And judging the stage of the precooler according to the generated data such as the temperature and the like. According to the data such as the temperature generated by the precooler, the output result of historical data analysis is used as a judgment standard to judge the current life cycle stage of the precooler, and the output result is as follows:
case 1: a normal-period precooler; case 2: a decline period precooler; case 3: a failure period precooler.
When the temperature triggering threshold value appears, the existing temperature data fitting curve is similar to the failure period, and the service time of the precooler reaches more than 90 percent of the MLBF (mean service time before failure) (for example, the MLBF reaches 95 percent). For example, if the temperature at the outlet of a precooler exceeds a threshold of 235 degrees celsius and the data fit equation is close to the precooler equation for the expiration date, then the precooler may be determined to be in the expiration date.
And S30, if the data do not belong to the normal stage, fitting the key parameter data to obtain a fitting curve equation.
And if the precooler is in the decay period or the expiration period, fitting the key parameter discrete data of the corresponding period stage to obtain a fitting curve equation.
For the precooler below in fig. 4 in the degeneration phase, a discrete data fit is performed, y = f (x) to reflect the dependency between the quantities x and y. The method can realize curve fitting such as linear type, waterfall type attenuation curve, parabolic type attenuation curve and the like, and takes pressure data fitting as an example: the preliminary precooler pressure is judged to be linear with time, and y = bx + a is set. The least square method (also called the least square method) is applied to find the optimal function matching of the data by minimizing the sum of squares of errors, and the formula is as follows
According to the above formula, data fitting is performed to solve the best estimated values of the straight-line functions a and b. As shown in FIG. 4, a linear fit function y = -0.001x +45.199 is obtained, where x is the flight number after performance decay (which can also be converted to flight hours by flight number flight time), and the R square value R of the trend line 2 ＝0.7395，R 2 A closer to 1 indicates a better fit, setting the confidence level to 0.74.
Example of residual life prediction with pressure data fit: according to the historical QAR precooler pressure data analysis, as shown in fig. 5, if the precooler performance attenuation early warning threshold is set to 41PSI, it can be predicted that the precooler will trigger performance attenuation warning when the 4199 th flight is executed, obtain the flight hours of each flight, assume that the fleet daily utilization rate is 9.5FH, and estimate according to 6 flights every day, the remaining life can be calculated, and also the remaining flight hours can be estimated. A remaining life value PV1 based on precooler data fit is obtained.
Similarly, the precooler temperature curve can be fitted and fleet data analysis operations are repeated, with the results shown in fig. 6.
And S40, processing the fitted curve equation and the MLBF equation by utilizing a multidimensional data updating and correcting model to obtain a predicted value of the residual service life of the precooler.
In one embodiment, step S40 may include steps S401 to S404:
s401, based on the key data fitting function of the airplane component, the estimated residual life is calculated.
S402, calculating a corrected residual life value based on an MLBF algorithm of the average service time before the fault.
And S403, fitting a function with the data, estimating the residual life and correcting the residual life value, and inputting the multi-dimensional data to update the correction model.
S404, correcting by using the corrected residual life value, and performing iterative updating in a multidimensional data updating and correcting model to obtain the predicted residual life value of the precooler.
The MLBF is calculated by using a large amount of accumulated use data in the actual use process of the aircraft component, and the obtained average use time before the failure of the aircraft component reflects the reliability state of the component in a certain time period. An MLBF (mean time to failure) calculation method is adopted, and threshold values of key parameters such as temperature and pressure of an aircraft precooler are combined to serve as judgment conditions. If the precooler currently belongs to the normal life cycle stage, the MLBF is less than 60% or the MLBF is less than 80%, and a proper threshold value is set according to different principles of different airplane components; if the precooler currently belongs to the decay or failure stage of the life cycle, then the MLBF is greater than 80% or the MLBF is greater than 90%, and the threshold value is determined according to the situation.
Specifically, the remaining life value PV2 of the precooler may be obtained by using an MLBF algorithm, whose detailed algorithm steps are as follows:
the set aircraft component calculation is as follows:
the aircraft components are divided into MLBF =10000FH (flight hours) in different cases (average time of use before MLBF failure), and detailed calculation methods are set as follows:
1. the calculation mode that the MLBF of an airplane part of a certain model or part number is less than 10000FH is as follows:
A. first calculation
B. Subsequent calculation mode
MLBF = (cumulative flight hours of a component since last calculation of a fleet reaches 3 times MLBF and is not less than 3 calendar months)/(number of failure replacements in that period);
the minimum time interval for calculating the MLBF cannot be smaller than the part, the accumulated flight hours of the part are more than 3 times of the MLBF since the last calculation, and the accumulated flight hours are not smaller than 3 calendar months, otherwise, the calculated MLBF value is too large due to the fact that the time interval is too small, and the MLBF calculation loses practical significance.
2. When the MLBF of an airplane part of a certain model or part number is more than or equal to 10000FH, the calculation mode is as follows:
A. first calculation
B. Subsequent calculation mode
The minimum time interval for calculating the MLBF cannot be smaller than the part, the MLBF which is 1 time of the accumulated flying hours of the part since the last calculation is not smaller than 6 calendar months, otherwise, the calculated MLBF value is too large due to the fact that the time interval is too small, and the MLBF calculation loses practical significance.
Based on the MLBF calculation method, the system automatically acquires the Installation dates of the left-handed precooler and the right-handed precooler (for example, the Installation date of the B-8XXX aircraft precooler is 2015, 10 months), the self-Installation Time of the TSI (Time sine insertion), 19741.099FH, the number of fault replacements and other data, the automatic operation is realized according to the MLBF calculation logic, the average use Time before the MLBF fault is obtained, the used Time is subtracted, and therefore the residual life value PV2 is obtained, meanwhile, the data of the real temperature and Time of the fault precooler can be recorded, for example, when the residual 46 flight cycles (residual 115 FH) exist, the outlet temperature of the fault precooler is 230 ℃, and the real data points can be used for correcting the subsequent predicted values.
A prediction algorithm for updating and correcting multidimensional data is introduced by taking prediction of precooler temperature as an example. When a precooler temperature fitting data curve is obtained, the time required when the future temperature reaches the threshold value temperature can be predicted, the time is the residual life, and meanwhile, the temperature data points of a real fault precooler are used for correcting to obtain more accurate estimated residual life PV1.
The outlet temperature of a certain aircraft precooler at the moment is 216 ℃, and a predicted temperature equation based on a time sequence can be obtained by fitting according to precooler temperature data:
T(t)＝0.5*0.004*t 2 +200
setting the predicted temperature as X (k), Z (k) as the temperature value calculated by the data fitting function,
i.e. Z (k) =0.5 x 0.004 x k 2 +200
Then Z (k + 1) = Z (k) +0.004k +0.002
To implement the update correction function, the following formula is proposed:
X(k)＝X(k-1)+(Z(k)-X(k-1))*K(k)+(V(k)-X(k-1))(1-K(k))
P k ＝(1-K k-1 )P k-1
K k ＝P k /(P k +W)
P k in order to estimate the temperature error, X (K) is the predicted temperature, K (K) is a compensation coefficient, W is set to be consistent with Gaussian distribution noise, and V (K) represents the temperature value of the precooler with a real fault.
The above formula contains two information updating processes: a time update procedure and a correction update procedure. The time updating process is an estimation process of the temperature value and is used for calculating the temperature variable value at the current moment and the error of the estimated value so as to determine the prior estimated juice value of the state variable at the next moment. The other is a correction process for comparing and correcting the predicted value calculated by the new time series fitting function and the real value of the real fault aircraft component at the moment with the prior estimated value to obtain an improved posterior estimated value. Updating iteration is carried out through the equation, the correction is continuously carried out, and finally the predicted temperature value is obtained, and the detailed steps are as follows:
in the first step, a certain initial state of the failure precooler is set, namely k = 0:
T(0)＝200℃
W＝0.2
from the temperature data of the historical real fault precooler, a data set V (0) =201 ℃, V (53) can be obtained
＝206℃、V(10)＝210℃…V(87)＝216℃…
P 1 ＝1
K 1 ＝P 1 /(P 1 +0.2)
Then K is 1 ＝0.833
Then substituting into the formula can result:
P 2 ＝(1-K 1 )P 1 ＝(1-0.833)*1＝0.167
K 2 ＝P 2 /(P 2 +0.2)
K 2 ＝0.166/(0.166+0.2)＝0.454
X(2)＝200+(200.008-200)*0.454+(201.008-200)*0.546＝200.554
step 3, when k = 3:
3 ＝(1-K 2 )P 2
K 3 ＝P 3 /(P 3 +0.2)＝0.313
X(3)＝200.554+(200.018-200.554)*0.313+(201.019-200.554)*0.687＝200.706
…
and 87, when k =87, repeating the steps:
X(87)＝X(86)+(Z(87)-X(86))*K(87)+(V(87)-X(86))*(1-K(87))X(87)＝216.509+(215.138-216.509)*0.013+(216.895-216.509)*0.987＝216.872
…
step 143, when k =143, repeating the steps:
X(143)＝X(142)+(Z(143)-X(142))*K(143)+(V(143)-X(142))*(1-K(143))
X(143)＝243.321+(240.898-243.321)*0.008+(243.943-243.321)*0.992＝243.919
at this time, the precooler temperature is 216 ℃, and when the failure threshold value is set to 243 ℃, the estimated residual life of the precooler is 56 flight cycles, and the estimated residual life is 140FH when calculated according to the average 2.5FH of each flight of the fleet.
…
And step 170, when k =170, repeating the steps:
X(154)＝X(153)+(Z(154)-X(153))*K(153)+(V(153)-X(152))*(1-K(153))
X(154)＝250.779
at this time, the precooler temperature is 216 ℃, and when the failure threshold value is set to be 250 ℃, the predicted residual life of the precooler is 70 flight cycles, and the predicted residual life PV1 is 175FH according to the flight hours of the average flight of the fleet, such as 2.5 FH.
And substituting the PV1, PV2, corresponding temperature and other data into the following formula to carry out correction and update calculation so as to obtain more accurate estimated residual life:
setting Z (k) as the residual life PV1 obtained based on temperature data fitting, setting V (k) as the residual life PV2 based on MLBF, and setting the initial residual life X (0) as the predicted value based on MLBF, and calculating according to the following formula:
PV(k+1)＝PV(k)+(PV1(k+1)-PV(k))*K(k)+(PV2(k+1)-PV(k))(1-K(k))
K k ＝P k /(P k +W)
P k ＝(1-K k )P k-1
namely, the predicted optimal residual life is equal to the last predicted value, and deviation correction of the residual life is obtained based on MLBF and data fitting, so that a more accurate predicted value of the residual life is obtained. And in the residual life estimation process, the state variable value at the current moment and the estimated error are used for calculating the state variable prior estimated juice value at the next moment. In addition, the actual remaining life value PV2 of the actual fault aircraft component at the moment is corrected by using the remaining life value PV1. And the residual life can be predicted by utilizing the automatic calculation of the system. The calculation results are shown in fig. 7.
Examples of applications in aircraft air conditioning systems are as follows:
and fitting key data in the air conditioning system, such as the outlet temperature of the air compressor and other data to obtain a state equation of the outlet temperature of the air compressor in time, and obtaining a transfer relation between the state equation at the time k and the state equation at the time k-1.
For example, when the performance of a certain airplane is monitored, the maximum value of the outlet temperature of the air compressor shows an ascending trend, the system warns that the outlet temperature of the air compressor is abnormal, and the data fitting function of the maximum value of the outlet temperature of the air compressor in the failure period is as follows:
T(t)＝0.002*t 2 +200
wherein, when entering the expiration date, the initial temperature T (0) =200 ℃, and T is time; let the temperature T (T) and T (T-1) have the following relationship:
T(t)＝T(t-1)+0.004t+0.002
the outlet temperature T (T) of the air compressor entering the expiration date is more than 200 ℃, 250 ℃ or 230 ℃ can be set as a threshold, for example, if 250 ℃ is the threshold of complete failure of the air compressor, the estimated residual life equation is as follows:
the derivation process of the estimated residual life equation based on the time series is as follows:
and T (T) =0.5 x 0.004 x T 2 +200
T(t+1)＝0.002*(t+1) 2 +200
＝0.002*(t 2 +2t+1)+200
＝(0.002*t 2 +200)+(0.002*(2t+1))
T(t+1)＝T(t)+0.004t+0.002
Deducing:
obtaining:
while
Finally, the following components are obtained:
and obtaining the t moment and the t +1 moment, and predicting the transfer relationship of the PV1 residual life equation. In addition, the residual service life PV2 of the air compressor of the air conditioning system is obtained through an MLBF algorithm, and meanwhile data of the outlet temperature of the real fault air compressor are obtained and used as correction data.
The following formula is repeatedly calculated:
P k ＝(1-K k )P k-1
K k ＝P k /(P k +W)
PV(k+1)＝PV(k)+(PV1(k+1)-PV1(k))*K(k)+(Z(k+1)-PV(k))*(1-K(k))
PV (k) is residual life PV1 obtained based on temperature data fitting, Z (k) is residual life PV2 based on MLBF, corresponding failure temperature thresholds are set according to different types and different numbers of compressors, and the calculation process is the same as the precooler residual life prediction thought, so that the optimal residual life estimation value can be obtained.
According to the method for predicting the residual life of the aviation precooler, whether the precooler belongs to the normal life cycle stage or not is determined according to key parameter data and corresponding conditions of the precooler life cycle stage acquired in advance, if not, the key parameter data is fitted to obtain a fitting curve equation, the fitting curve equation and an MLBF equation are processed by using a multidimensional data updating and correcting model to obtain the predicted value of the residual life of the precooler, the key parameter data of different life cycle stages are comprehensively adopted, the respective advantages of the residual life prediction based on the MLBF and the residual life prediction based on data fitting are comprehensively integrated, and the theory of multidimensional data updating and correcting is adopted, so that the prediction accuracy of the residual life of the precooler is improved, and the requirement of practical application can be well met.
As shown in fig. 8, another embodiment of the present application provides an apparatus for predicting remaining life of an aircraft precooler, including:
the key parameter data acquisition module is used for acquiring the current key parameter data of the precooler;
the normal phase determining module is used for determining whether the precooler currently belongs to a normal life cycle phase according to the key parameter data and a corresponding condition of the precooler life cycle phase acquired in advance;
the fitting module is used for fitting the key parameter data to obtain a fitting curve equation if the key parameter data does not belong to the key parameter data;
and the residual life prediction module is used for processing the fitting curve equation and the MLBF equation by utilizing the multidimensional data updating and correcting model to obtain a predicted value of the residual life of the precooler.
In some embodiments, the remaining life prediction module is further configured to:
and if the precooler currently belongs to the normal life cycle stage, acquiring the residual life value of the precooler by adopting an MLBF algorithm.
In some embodiments, the method for acquiring the corresponding condition of the life cycle stage of the precooler comprises the following steps:
acquiring preprocessing historical data of key parameters of a precooler;
determining a life cycle stage parameter threshold of the precooler according to the preprocessing historical data;
and determining the corresponding condition according to the life cycle stage parameter threshold.
In some embodiments, the obtaining pre-processing historical data of key parameters of a precooler comprises:
acquiring historical data of key parameters of a precooler;
cleaning the historical data to obtain cleaned data;
and correcting the cleaned data to obtain the pre-processing historical data.
In some embodiments, the cleansing the historical data comprises: and eliminating false data in the historical data.
In some embodiments, the key parameters include precooler outlet temperature and precooler inlet pressure; the precooler lifecycle phases include a normal phase and an abnormal phase; the corresponding conditions of the normal phase include an MLBF value less than or equal to a first threshold, an outlet temperature less than or equal to a second threshold, and an inlet pressure less than or equal to a third threshold; the corresponding conditions for the abnormal phase include the MLBF value being greater than a first threshold and the outlet temperature being greater than a second threshold or the inlet pressure being greater than a third threshold.
In some embodiments, the processing the fitted curve equation and the MLBF equation using the multidimensional data update correction model to obtain the predicted value of the remaining life of the precooler includes: and taking the fitted curve equation as a state equation of a multi-dimensional data updating and correcting algorithm, taking the MLBF equation as an observation equation of the multi-dimensional data updating and correcting algorithm, and predicting by using a multi-dimensional data updating and correcting model to obtain the optimal estimated residual life.
The device for predicting the remaining life of the aviation precooler determines whether the precooler belongs to the normal life cycle stage or not according to key parameter data and corresponding conditions of the precooler life cycle stage acquired in advance, if not, the key parameter data is fitted to obtain a fitting curve equation, the fitting curve equation and an MLBF equation are processed by utilizing a multidimensional data updating and correcting model to obtain the predicted value of the remaining life of the precooler, the key parameter data of different life cycle stages are comprehensively adopted, the prediction accuracy of the remaining life of the precooler is improved, and the requirement of practical application can be well met.
Another embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement a method for predicting remaining life of an aircraft precooler according to any one of the above embodiments.
As shown in fig. 9, the electronic device 10 may include: the system comprises a processor 100, a memory 101, a bus 102 and a communication interface 103, wherein the processor 100, the communication interface 103 and the memory 101 are connected through the bus 102; the memory 101 stores a computer program that can be executed on the processor 100, and the processor 100 executes the computer program to perform the method provided by any of the foregoing embodiments.
The Memory 101 may include a high-speed Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The bus 102 may be an ISA bus, a PCI bus, an EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 101 is used for storing a program, and the processor 100 executes the program after receiving an execution instruction, and the method disclosed in any of the foregoing embodiments of the present application may be applied to the processor 100, or implemented by the processor 100.
The electronic equipment provided by the embodiment of the application and the method provided by the embodiment of the application are based on the same inventive concept, and have the same beneficial effects as the method adopted, operated or realized by the electronic equipment.
Another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement a method for predicting remaining life of an aircraft precooler according to any one of the above embodiments. Referring to fig. 10, a computer readable storage medium is shown as an optical disc 20, on which a computer program (i.e. a program product) is stored, which when executed by a processor, performs the method provided by any of the foregoing embodiments.
It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory, or other optical and magnetic storage media, which are not described in detail herein.
The computer-readable storage medium provided by the above-mentioned embodiments of the present application and the method provided by the embodiments of the present application have the same advantages as the method adopted, executed or implemented by the application program stored in the computer-readable storage medium.
It should be noted that:
the term "module" is not intended to be limited to a particular physical form. Depending on the particular application, a module may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same component. There may or may not be clear boundaries between the various modules.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may also be used with examples based on this disclosure. The required structure for constructing an arrangement of this type will be apparent from the description above. Moreover, this application is not intended to refer to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and any descriptions of specific languages are provided above to disclose the best modes of the present application.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless otherwise indicated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The above-mentioned embodiments only express the embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method for predicting the residual life of an aviation precooler is characterized by comprising the following steps:
acquiring current key parameter data of a precooler;
determining whether the precooler currently belongs to a normal life cycle stage or not according to the key parameter data and a pre-acquired corresponding condition of the life cycle stage of the precooler;
if not, fitting the key parameter data to obtain a fitting curve equation;
and processing the fitting curve equation and the MLBF equation by using a multidimensional data updating correction model to obtain a predicted value of the residual life of the precooler.
2. The method of claim 1, further comprising:
and if the precooler currently belongs to the normal life cycle stage, acquiring the residual life value of the precooler by adopting an MLBF algorithm.
3. The method according to claim 1, wherein the method for acquiring the corresponding condition of the precooler lifecycle stage comprises:
acquiring preprocessing historical data of key parameters of a precooler;
determining a life cycle stage parameter threshold of the precooler according to the preprocessing historical data;
and determining the corresponding condition according to the life cycle stage parameter threshold.
4. The method of claim 3, wherein the obtaining pre-processed historical data of pre-cooler key parameters comprises:
acquiring historical data of key parameters of a precooler;
cleaning the historical data to obtain cleaned data;
and correcting the cleaned data to obtain the pre-processing historical data.
5. The method of claim 4, wherein the cleansing the historical data comprises: and eliminating false data in the historical data.
6. The method of claim 1, wherein the key parameters include a precooler outlet temperature and a precooler inlet pressure; the precooler lifecycle phases include a normal phase and an abnormal phase; the corresponding conditions of the normal phase include an MLBF value less than or equal to a first threshold, an outlet temperature less than or equal to a second threshold, and an inlet pressure less than or equal to a third threshold; the corresponding conditions for the abnormal phase include the MLBF value being greater than a first threshold and the outlet temperature being greater than a second threshold or the inlet pressure being greater than a third threshold.
7. The method of claim 1, wherein the processing the fitted curve equation and the MLBF equation using the multi-dimensional data update correction model to obtain the predicted value of the remaining life of the precooler comprises:
based on a key data fitting function of the aircraft component, the estimated residual life is calculated;
calculating a corrected residual life value based on an MLBF algorithm of the average service time before the fault;
inputting a data fitting function, estimated residual life and corrected residual life values into a multidimensional data updating correction model;
and correcting by using the corrected residual life value, and performing iterative updating in the multidimensional data updating and correcting model to obtain the predicted residual life value of the precooler.
8. An apparatus for predicting the remaining life of an aircraft precooler, comprising:
the key parameter data acquisition module is used for acquiring the current key parameter data of the precooler;
the normal phase determining module is used for determining whether the precooler currently belongs to a normal life cycle phase according to the key parameter data and a corresponding condition of the precooler life cycle phase acquired in advance;
the fitting module is used for fitting the key parameter data to obtain a fitting curve equation if the key parameter data does not belong to the key parameter data;
and the residual life prediction module is used for processing the fitting curve equation and the MLBF equation by utilizing the multidimensional data updating and correcting model to obtain a predicted value of the residual life of the precooler.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of predicting remaining life of an aircraft precooler according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor to implement the method of prediction of the residual life of an aircraft precooler according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211489610.3A CN115982942B (en) | 2022-11-25 | 2022-11-25 | Method, device, equipment and storage medium for predicting residual life of aviation precooler |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211489610.3A CN115982942B (en) | 2022-11-25 | 2022-11-25 | Method, device, equipment and storage medium for predicting residual life of aviation precooler |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115982942A true CN115982942A (en) | 2023-04-18 |
| CN115982942B CN115982942B (en) | 2023-07-14 |
Family
ID=85972770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211489610.3A Active CN115982942B (en) | 2022-11-25 | 2022-11-25 | Method, device, equipment and storage medium for predicting residual life of aviation precooler |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115982942B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109460574A (en) * | 2018-10-09 | 2019-03-12 | 南京航空航天大学 | A kind of prediction technique of aero-engine remaining life |
| US20190228594A1 (en) * | 2018-01-23 | 2019-07-25 | Massoud Nakhkoob Niasar | Aircraft maintenance and aircraft reliability engineering software system |
| US10814883B1 (en) * | 2018-10-18 | 2020-10-27 | Northrop Grumman Systems Corporation | Prognostics for improved maintenance of vehicles |
| CN112100865A (en) * | 2019-11-04 | 2020-12-18 | 中国人民解放军国防科技大学 | Method for predicting remaining life of aircraft engine based on parallel CNN model |
| CN113051839A (en) * | 2021-05-12 | 2021-06-29 | 中国人民解放军海军航空大学 | Deep learning-based equipment residual life prediction model construction method |
| EP3876134A1 (en) * | 2020-03-05 | 2021-09-08 | Siemens Aktiengesellschaft | System, apparatus and method for predicting life of a component |
| CN113537643A (en) * | 2021-08-20 | 2021-10-22 | 诺博特数据信息科技(南京)有限公司 | Internet-based power equipment life prediction algorithm |
| CN113779882A (en) * | 2021-09-10 | 2021-12-10 | 中国石油大学(北京) | Method, device, equipment and storage medium for predicting residual service life of equipment |
| CN113987704A (en) * | 2021-10-28 | 2022-01-28 | 重庆大学 | Aero-engine service life prediction method based on automatic multi-differential learning deep network |
| CN114429249A (en) * | 2022-04-06 | 2022-05-03 | 杭州未名信科科技有限公司 | Method, system, equipment and storage medium for predicting service life of steel pipe bundle production equipment |
-
2022
- 2022-11-25 CN CN202211489610.3A patent/CN115982942B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190228594A1 (en) * | 2018-01-23 | 2019-07-25 | Massoud Nakhkoob Niasar | Aircraft maintenance and aircraft reliability engineering software system |
| CN109460574A (en) * | 2018-10-09 | 2019-03-12 | 南京航空航天大学 | A kind of prediction technique of aero-engine remaining life |
| US10814883B1 (en) * | 2018-10-18 | 2020-10-27 | Northrop Grumman Systems Corporation | Prognostics for improved maintenance of vehicles |
| CN112100865A (en) * | 2019-11-04 | 2020-12-18 | 中国人民解放军国防科技大学 | Method for predicting remaining life of aircraft engine based on parallel CNN model |
| EP3876134A1 (en) * | 2020-03-05 | 2021-09-08 | Siemens Aktiengesellschaft | System, apparatus and method for predicting life of a component |
| CN113051839A (en) * | 2021-05-12 | 2021-06-29 | 中国人民解放军海军航空大学 | Deep learning-based equipment residual life prediction model construction method |
| CN113537643A (en) * | 2021-08-20 | 2021-10-22 | 诺博特数据信息科技(南京)有限公司 | Internet-based power equipment life prediction algorithm |
| CN113779882A (en) * | 2021-09-10 | 2021-12-10 | 中国石油大学(北京) | Method, device, equipment and storage medium for predicting residual service life of equipment |
| CN113987704A (en) * | 2021-10-28 | 2022-01-28 | 重庆大学 | Aero-engine service life prediction method based on automatic multi-differential learning deep network |
| CN114429249A (en) * | 2022-04-06 | 2022-05-03 | 杭州未名信科科技有限公司 | Method, system, equipment and storage medium for predicting service life of steel pipe bundle production equipment |
Non-Patent Citations (2)
| Title |
|---|
| CHAO DENG等: "Study on Health Assessment and Residual Useful Life Prediction of Wind Turbine", 《2018 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS》, pages 1112 - 1117 * |
| 丁世来等: "多源试验数据重构与融合存储技术研究", 《电子产品可靠性与环境试验》, vol. 40, no. 1, pages 11 - 15 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115982942B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107111311B (en) | Gas turbine sensor fault detection using sparse coding methods | |
| US9176926B2 (en) | Monitoring of an aircraft engine for anticipating maintenance operations | |
| EP1926001B1 (en) | Reducing gas turbine performance tracking estimation non-repeatability | |
| US7062370B2 (en) | Model-based detection, diagnosis of turbine engine faults | |
| CN109033499B (en) | Multi-stage consistency inspection method for predicting residual life of aircraft engine | |
| US8682616B2 (en) | Identifying failures in an aeroengine | |
| US7072797B2 (en) | Trending system and method using monotonic regression | |
| EP1950634B1 (en) | Process for adapting measurement suite configuration for gas turbine performance diagnostics | |
| US9555903B2 (en) | Method for diagnosing a bleed air system fault | |
| US8417410B2 (en) | Operations support systems and methods with power management | |
| CN108732962B (en) | Compressor wash planning | |
| CN108363844B (en) | Method for predicting exhaust temperature in starting process of aircraft engine | |
| US20040172228A1 (en) | System and method for diagnosing faults utilizing baseline modeling techniques | |
| US20220242592A1 (en) | System and method for monitoring an aircraft engine | |
| CA2848087A1 (en) | Method for predicting a bleed air system fault | |
| US7801695B2 (en) | Operations support systems and methods with model-based torque estimates | |
| CN113053171A (en) | Civil aircraft system risk early warning method and system | |
| CN113343364A (en) | Aviation big data analysis method and tool | |
| Côme et al. | Aircraft engine fleet monitoring using self-organizing maps and edit distance | |
| CN115982942B (en) | Method, device, equipment and storage medium for predicting residual life of aviation precooler | |
| CN116362142B (en) | Method, device, equipment and storage medium for predicting lubricating oil quantity of aero-engine | |
| EP3742359A1 (en) | Systems and methods for auxiliary power unit health indicator computation | |
| EP1927915B1 (en) | State initialization for gas turbine engine performance diagnogtics | |
| CN105718620A (en) | Modeling method for reliability statistic analysis of key component of converter valve cooling system | |
| Borguet et al. | Regression-based modelling of a fleet of gas turbine engines for performance trending |
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 |