CN116754235A - Aeroengine reliability assessment method for competition failure - Google Patents
Aeroengine reliability assessment method for competition failure Download PDFInfo
- Publication number
- CN116754235A CN116754235A CN202210211317.4A CN202210211317A CN116754235A CN 116754235 A CN116754235 A CN 116754235A CN 202210211317 A CN202210211317 A CN 202210211317A CN 116754235 A CN116754235 A CN 116754235A
- Authority
- CN
- China
- Prior art keywords
- reliability
- data
- failure
- engine
- aero
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 230000004927 fusion Effects 0.000 claims abstract description 16
- 238000000265 homogenisation Methods 0.000 claims abstract description 6
- 238000006731 degradation reaction Methods 0.000 claims description 39
- 230000015556 catabolic process Effects 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 19
- 238000012423 maintenance Methods 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 13
- 238000005315 distribution function Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 claims description 7
- 238000013210 evaluation model Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000007423 decrease Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 239000000446 fuel Substances 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 239000010687 lubricating oil Substances 0.000 claims description 3
- 230000009469 supplementation Effects 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 12
- 238000012360 testing method Methods 0.000 abstract description 5
- 239000003016 pheromone Substances 0.000 description 6
- 230000002860 competitive effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000257303 Hymenoptera Species 0.000 description 1
- 238000013398 bayesian method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an aircraft engine reliability assessment method aiming at competition failure; the method comprises the following steps: on one hand, the collected monitoring data is optimized through an artificial intelligent algorithm, samples with higher homogenization degree are removed, the effectiveness of input fused samples is improved, the number of input samples is reduced, and therefore the accuracy of results is ensured, and meanwhile, the fusion calculation speed is improved; on the other hand, the fault data are expanded through a neural network algorithm, so that the problem that a large amount of reliability test data cannot be acquired due to fewer faults is solved. Therefore, the method and the device can improve the calculation accuracy while reducing redundant calculation data.
Description
Technical Field
The invention relates to the field of aeroengines, in particular to an aeroengine reliability assessment for competitive failure.
Background
Aeroengine technology relates to aerothermomechanics, combustion, heat transfer, structural strength, electronic control, materials and processes, etc., and has wide and deep expertise. Meanwhile, the working conditions are harsh, various requirements are harsh, and the requirements of the aircraft on the performance, the durability, the reliability, the cost reduction and the like of the aero-engine are increasingly improved, so that the aero-engine has the characteristics of long development period, high cost, high difficulty, high risk, intensive knowledge, intensive technology, intensive funds and the like.
Reliability management of an aeroengine is a very important link for aviation industry, so objective and scientific prediction of the reliability of an aeroengine is increasingly important.
According to the prior art, as an aero-engine reliability evaluation method for competitive failure provided by the patent application document of CN102567639A, two conditions of sudden failure and performance degradation failure are considered, an aero-engine reliability model based on the competitive failure is established, monitoring information is acquired for the performance degradation failure, and a Bayesian linear model is used for fusing the monitoring information, so that the information utilization efficiency is improved; aiming at the sudden failure, the event information is collected, a Bayesian method is applied, the sudden failure related information of different time sequence points is comprehensively utilized through the priori and posterior estimated information, and the information utilization efficiency is improved.
However, the prior art solutions in the above have the following drawbacks:
since a large amount of reliability test data cannot be acquired even if the number of faults is small for an aeroengine, only the middle region part of the probability distribution function can be evaluated at most, and for the capacity of a limited sample, there is a problem that the probability distribution function which is originally assumed is accepted but does not match the actual distribution in the fitting goodness test when fitting parameters. In addition, in the CN102567639a patent, the determined shape parameter is directly determined by the expected value of the degradation degree, and the exponential parameter is assumed to follow the gamma distribution, and the final fitting result cannot meet the actual situation due to the smaller data volume.
Disclosure of Invention
(one) solving the technical problems
In order to solve the technical problems and achieve the aim of the invention, the invention is realized by the following technical scheme:
on one hand, the collected monitoring data is optimized through an artificial intelligence algorithm, samples with higher homogenization degree are removed, the effectiveness of input fused samples is improved, the number of input samples is reduced, and therefore the fusion calculation speed is improved while the accuracy of results is ensured; on the other hand, the fault data are expanded through a neural network algorithm, so that the problem that a large amount of reliability test data cannot be acquired due to fewer faults is solved. Therefore, the method and the device can improve the calculation accuracy while reducing redundant calculation data.
(II) technical scheme
In order to solve the technical problems and achieve the aim of the invention, the invention is realized by the following technical scheme:
s1: acquiring monitoring information, fault information, maintenance information and inspection information;
s2: preprocessing the acquired monitoring information by adopting an artificial intelligence algorithm;
s3: establishing a performance degradation evaluation model of the multi-monitoring information fusion aero-engine;
s4: establishing an aeroengine burst failure reliability evaluation model based on the Weibull distribution of the neural network;
s5: and establishing a reliability model of the competition failure aero-engine system.
Further, step S2 includes: the method comprises the following steps of preprocessing a plurality of pieces of monitoring information by adopting an artificial intelligence algorithm: after the collected monitoring information is standardized, the input samples are subjected to sub-set division through an ant colony algorithm, the divided sub-sets are subjected to screening extraction, and the screening degree of the group is determined according to the homogenization degree of the samples in the group. The monitoring information comprises: engine exhaust temperature deviation, fuel consumption deviation, high-pressure rotor speed deviation, lubricating oil pressure deviation, low-pressure rotor vibration value deviation and high-pressure rotor vibration value deviation;
further, step S3 includes: the performance degradation degree of the aero-engine is evaluated by adopting a Bayesian model, and specifically comprises the following steps: describing a degradation process by adopting a gamma process, and setting degradation quantity w (t) to follow gamma distribution Ga (mu (t), lambda, and a density function of the degradation quantity w (t) to be:
wherein alpha and beta are respectively a shape parameter and a size parameter,
as a gamma function.
Establishing a reliability model based on performance degradation:
R 1 (t)＝P{T 1 t is P { w (t) < ε };
wherein R is 1 (T) is the reliability at time T, T 1 For the time that the aeroengine has passed from normal to a degraded failure state, w (t) And epsilon represents the degradation threshold value of the aeroengine, namely the performance failure threshold value, for the performance degradation degree of the aeroengine at the moment t. According to the prior art model, the expected value of the degradation is proportional to the power of time, namely:
α(t)＝kt v
the formula before the introduction can be obtained:
further, step S4 includes:
step S4.1: preprocessing and standardizing fault data;
step S4.2: establishing a neural network model;
the neural network is selected to input 3 layer neurons, one layer in the middle layer, the number of the neurons is 4, and the number of the neurons in the output layer is 1. The input layer neurons respectively correspond to fault information, maintenance information and degradation degree, and the output layer corresponds to failure reliability information. Setting the number of network training times, training targets and learning speed.
Step S4.3: training a neural network to obtain neural network parameters;
the acquired reliability statistical data is provided with N groups (N is an even number), the front N/2 groups of data are selected as training data, and the rear N/2 groups of data are selected as check data. The weight and threshold of the neural network are adjusted by inputting training sample data until the training sample data converges to a set range, and the neural network model is determined according to the final weight and threshold.
Step S4.4: obtaining prediction data through a neural network;
and expanding the data through the neural network model determined by the steps to obtain the predicted data. Specifically, based on the acquired aeroengine fault information, maintenance information and degradation degree, data supplementation is performed according to intervals between data, higher-density fault information, maintenance information and degradation degree are obtained, three pieces of input information are input into an input layer of a neural network, output layer data are obtained, and the data are supplemented into high-density aeroengine reliability statistical data.
Step S4.5: the measured data and the predicted data are used for establishing a failure reliability assessment model by adopting Weibull distribution.
Assuming that in the burst failure mode, the aero-engine reliability obeys a dual-parameter weibull distribution, the formula is as follows:
the reliability function is:
the density function is:
the failure rate function is:
the distribution function is:
where η is a scale parameter and β is a shape parameter.
It is a model that is easily resilient, which can be changed to different shapes as the shape parameters change, so that in actual use, it can better fit the reliability model due to its easy resiliency.
Setting:
the distribution function is transformed into:
y＝βx-βln(η)
and performing least square fitting on the known time and the unreliability, thereby obtaining estimated values beta and eta of the parameters.
Calculating the reliability of the burst failure according to the obtained parametersWherein T is 2 The time that it takes for the aeroengine to go from normal to a sudden failure condition.
Step S5 is further specifically:
in the competition mode, the reliability of the aero-engine at the moment t is as follows:
wherein Wn is the threshold for degradation failure; f (x, t) is a degradation amount distribution function, and the probability density function is F (x, t); rc (t) represents the reliability of the contention failure.
(III) beneficial effects
According to the invention, on one hand, aiming at the characteristic of more monitoring information, the collected monitoring data is optimized through an artificial intelligence algorithm, samples with higher homogenization degree are removed, the validity of the input fused samples is improved, the number of the input samples is reduced, and therefore, the fusion calculation speed is improved while the accuracy of the result is ensured; on the other hand, aiming at the problem of poor fault occurrence of the aeroengine, less fault data can be obtained, and the problem that a large amount of reliability test data cannot be obtained due to the fact that the faults are less frequently generated is solved by expanding the fault data through a neural network algorithm. Thereby realizing the improvement of calculation accuracy while reducing redundant calculation data.
Drawings
FIG. 1 is a flowchart of an aircraft engine reliability evaluation method for competitive failure provided by an embodiment of the present invention;
fig. 2 is a flowchart of an aeroengine data expansion method based on a neural network according to an embodiment of the present invention.
Detailed Description
The following description of the technical solutions in the embodiments of the present invention will be clear and complete, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The following describes the embodiments in detail with reference to the drawings, in order to describe the technical objects and effects achieved by the present invention in detail.
Referring to fig. 1, an aircraft engine reliability assessment method for a competing failure includes:
s1: acquiring monitoring information, fault information, maintenance information and inspection information;
s2: preprocessing the acquired monitoring information by adopting an artificial intelligence algorithm;
the method comprises the following steps of preprocessing a plurality of pieces of monitoring information by adopting an artificial intelligence algorithm: after the collected monitoring information is standardized, the input samples are subjected to sub-set division through an ant colony algorithm, the divided sub-sets are subjected to screening extraction, and the screening degree of the group is determined according to the homogenization degree of the samples in the group. The monitoring information comprises: engine exhaust temperature deviation, fuel consumption deviation, high-pressure rotor speed deviation, lubricating oil pressure deviation, low-pressure rotor vibration value deviation and high-pressure rotor vibration value deviation;
the specific steps of carrying out input sample space division by adopting an ant colony algorithm are as follows:
(1) Initializing parameters alpha, beta, hij, r and rho;
(2) Randomly selecting ant xi, calculating its food sourceAccording to the pheromone release mode, determining whether to release the pheromone, and calculating the heuristic function eta.
The pheromone release mode is as follows:
hij is the pheromone concentration; r (x) i ，x j ) Is the correlation between the two parameters; r is a correlation threshold.
The heuristic functions are:
wherein m is ant number, and is->
Correlation R (x) i ，x j ) The calculation method is as follows:
(3) Calculating the probability p of ants from xi to xj according to the following formula ij Setting probability threshold p, when p ij >p, put xi, and xj in the same set, otherwise not put in one set.
Where S is the set of possible paths from xi to xj, i.e. s= { x s ||R(x i ，x j )|>r,S＝1,2…n}；
(4) Adjusting the concentration of pheromone, updating mj to enableJ is the number of elements in the newly-placed class. The pheromone concentration was adjusted according to the following:
h ij (t′)＝(1-ρ)h ij (t)+Δh ij (t)；
(5) If there are uncategorized xi, then jump to step (2), otherwise end.
After the division of the vector space is completed, a plurality of sets with strong intra-group correlation and weak inter-group correlation or irrelevant are obtained.
The method has the advantages that data with higher homogeneity are removed, the calculated amount is reduced, meanwhile, the local characteristics of the input samples are better reflected, the effectiveness of the input fused samples is improved, the number of the input samples is reduced, the fusion calculation speed is improved, meanwhile, the calculation difficulty of the subsequent model establishment step is reduced, and the modeling time is shortened.
S3: establishing a performance degradation evaluation model of the multi-monitoring information fusion aero-engine;
the performance degradation degree of the aero-engine is evaluated by adopting a Bayesian model, and specifically comprises the following steps: describing a degradation process by adopting a gamma process, and setting degradation quantity w (t) to follow gamma distribution Ga (mu (t), lambda, and a density function of the degradation quantity w (t) to be:
wherein alpha and beta are respectively a shape parameter and a size parameter,
as a gamma function.
Establishing a reliability model based on performance degradation:
R l (t)＝P{T 1 t is P { w (t) < ε };
wherein R is 1 (T) is the reliability at time T, T 1 For the time that the aeroengine is normally converted into a decline failure state, w (t) is the decline degree of the performance of the aeroengine at the moment t, and epsilon represents the decline threshold value of the aeroengine, namely the performance failure threshold value. According to the prior art model, the expected value of the degradation is proportional to the power of time, namely:
α(t)＝kt v
the formula before the introduction can be obtained:
s4: establishing an aeroengine burst failure reliability evaluation model based on the Weibull distribution of the neural network;
the advantages of the artificial neural network algorithm in the field of data prediction are obvious, for the situation that the number of the fault data of the aero-engine is small, the data are predicted based on the neural network algorithm, the predicted data can be obtained, the parameters are obtained according to the predicted data by adopting Weibull distribution, and the method can effectively solve the problem of poor fault data in the field of reliability evaluation of the aero-engine.
The method comprises the following specific steps:
step S4.1: preprocessing and standardizing fault data;
step S4.2: establishing a neural network model;
step S4.3: training a neural network to obtain neural network parameters;
step S4.4: obtaining prediction data through a neural network;
step S4.5: the measured data and the predicted data are used for establishing a failure reliability assessment model by adopting Weibull distribution.
An effective neural network reliability model should satisfy sufficient connection among nodes, ensure classification capability of the network under nonlinear condition, and enable the network to have capability of reflecting variation of input characteristic information along with parameters, wherein the number of weight coefficients in the network is far smaller than that of training, so that the network has sufficient learning possibility.
Step S4.1 comprises the steps of counting fault data to obtain aeroengine fault information, maintenance information, degradation degree and sudden failure reliability information, analyzing the data, and carrying out standardized processing on the data to obtain a plurality of groups of aeroengine reliability statistic data.
When building a multi-layer neural network model, it is important to use an appropriate number of hidden layer nodes. If the number of hidden nodes is too small, the network can acquire too little information for solving the problem, and the network is difficult to handle the complex problem; if the number of hidden nodes is too large, the training time of the network is increased sharply, and too many hidden neurons easily cause the network to be trained excessively, namely the network has too much information processing capability, and even meaningless information in a training sample is remembered. In fact, factors affecting the number of hidden nodes include the size of the training samples, the size of the noise amount, and the complexity of the input/output function relationship to be network learned. Therefore, reasonable selection of parameters for building the neural network model is of great importance.
Step S4.2 comprises: the neural network is selected to input 3 layer neurons, one layer in the middle layer, the number of the neurons is 4, and the number of the neurons in the output layer is 1. The input layer neurons respectively correspond to fault information, maintenance information and degradation degree, and the output layer corresponds to failure reliability information. Setting the number of network training times, training targets and learning speed.
Step S4.3 includes: the acquired reliability statistical data is provided with N groups (N is an even number), the front N/2 groups of data are selected as training data, and the rear N/2 groups of data are selected as check data. The weight and threshold of the neural network are adjusted by inputting training sample data until the training sample data converges to a set range, and the neural network model is determined according to the final weight and threshold.
Step S4.4 includes: and expanding the data through the neural network model determined by the steps to obtain the predicted data. Specifically, based on the acquired aeroengine fault information, maintenance information and degradation degree, data supplementation is performed according to intervals between data, higher-density fault information, maintenance information and degradation degree are obtained, three pieces of input information are input into an input layer of a neural network, output layer data are obtained, and the data are supplemented into high-density aeroengine reliability statistical data.
As reliability statistics increase, reliability assessment becomes more accurate, and the result is closer to a true value.
Step S4.5 includes:
the weibull distribution is the most widely used model in reliability estimation in recent years, which reasonably models the reliability of many elements and makes it resilient in data fitting due to the shape parameters of the weibull model. And, it can be linearized after double logarithmic transformation, thus making it more convenient in computer processing.
Assuming that in the burst failure mode, the aero-engine reliability obeys a dual-parameter weibull distribution, the formula is as follows:
the reliability function is:
the density function is:
the failure rate function is:
the distribution function is:
where η is a scale parameter and β is a shape parameter.
It is a model that is easily resilient, which can be changed to different shapes as the shape parameters change, so that in actual use, it can better fit the reliability model due to its easy resiliency.
Setting:
the distribution function is transformed into:
y＝βx-βln(η)
and performing least square fitting on the known time and the unreliability, thereby obtaining estimated values beta and eta of the parameters.
Calculating reliability of aeroengine in sudden failure mode according to obtained parametersWherein T is 2 The time that it takes for the aeroengine to go from normal to a sudden failure condition.
S5: and establishing a reliability model of the competition failure aero-engine system.
The aero-engine has both degradation failure and burst failure in the operation process, and the degradation failure and the burst failure are in a competition failure relationship, so according to the characteristics of the aero-engine failure mode, a reliability evaluation method based on competition failure is provided, and the step S5 specifically comprises the following steps:
in the competition mode, the reliability of the aero-engine at the moment t is as follows:
wherein Wn is the threshold for degradation failure; f (x, t) is a degradation amount distribution function, and the probability density function is F (x, t); rc (t) represents the reliability of the contention failure.
The above examples are only illustrative of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention, and various modifications and improvements made by those skilled in the art to the technical solution of the present invention should fall within the scope of protection defined by the claims of the present invention without departing from the spirit of the present invention.
Claims (10)
1. An aircraft engine reliability assessment method aiming at competition failure is characterized in that: the method comprises the following steps:
s1: acquiring monitoring information, fault information, maintenance information and inspection information;
s2: preprocessing the acquired monitoring information by adopting an artificial intelligence algorithm;
s3: establishing a performance degradation evaluation model of the multi-monitoring information fusion aero-engine;
s4: establishing an aeroengine burst failure reliability evaluation model based on the Weibull distribution of the neural network;
s5: and establishing a reliability model of the competition failure aero-engine system.
2. The method for evaluating the reliability of an aircraft engine on wing based on the fusion of monitoring information according to claim 1, wherein the step S2 comprises: after the collected monitoring information is standardized, the input samples are subjected to sub-set division through an ant colony algorithm, the divided sub-sets are subjected to screening extraction, and the screening degree of the group is determined according to the homogenization degree of the samples in the group.
3. The method for evaluating the reliability of an aircraft engine in-wing based on the fusion of monitoring information according to claim 2, wherein the monitoring information comprises: engine exhaust temperature deviation, fuel consumption deviation, high-pressure rotor rotational speed deviation, lubricating oil pressure deviation, low-pressure rotor vibration value deviation and high-pressure rotor vibration value deviation.
4. The method for evaluating the reliability of an aircraft engine on wing based on the fusion of monitoring information according to claim 1, wherein the step S4 comprises:
step S4.1: preprocessing and standardizing fault data;
step S4.2: establishing a neural network model;
step S4.3: training a neural network to obtain neural network parameters;
step S4.4: obtaining prediction data through a neural network;
step S4.5: the measured data and the predicted data are used for establishing a failure reliability assessment model by adopting Weibull distribution.
5. The method for evaluating the on-wing reliability of the aero-engine based on the monitoring information fusion according to claim 4, wherein the method comprises the following steps of: step S4.2, selecting 3 neurons of an input layer of the neural network, wherein the number of the neurons of a middle layer is 4, and the number of the neurons of an output layer is 1; the input layer neurons respectively correspond to fault information, maintenance information and degradation degree, and the output layer corresponds to failure reliability information; setting the number of network training times, training targets and learning speed.
6. The method for evaluating the on-wing reliability of the aero-engine based on the monitoring information fusion according to claim 4, wherein the method comprises the following steps of: the step S4.3 comprises the steps of selecting the front N/2 groups of data of N groups of reliability statistical data as training data and the rear N/2 groups of data as check data; the weight and threshold of the neural network are adjusted by inputting training sample data until the training sample data converges to a set range, and the neural network model is determined according to the final weight and threshold.
7. The method for evaluating the on-wing reliability of the aero-engine based on the monitoring information fusion according to claim 4, wherein the method comprises the following steps of: step S4.4 includes using the neural network obtained in step S4.3 to predict, specifically based on the obtained aero-engine fault information, maintenance information and degradation degree, performing data supplementation according to the interval between the data, obtaining higher-density fault information, maintenance information and degradation degree, inputting three input information into the input layer of the neural network, obtaining output layer data, and supplementing the output layer data into high-density aero-engine reliability statistical data.
8. The method for evaluating the on-wing reliability of the aero-engine based on the monitoring information fusion according to claim 4, wherein the method comprises the following steps of: the step S4.5 of establishing a failure reliability evaluation model by using the measured data and the predicted data and adopting Weibull distribution specifically comprises the following steps:
assuming that in the burst failure mode, the aero-engine reliability obeys a dual-parameter weibull distribution, the formula is as follows:
the reliability function is:
the density function is:
the failure rate function is:
the distribution function is:
wherein eta is a scale parameter, and beta is a shape parameter;
the model is easy to elasticity, and can be changed into different shapes along with the change of the shape parameters, so that in actual use, the reliability model can be better fitted due to the easy elasticity;
setting:
the distribution function is transformed into:
y＝βx-βln(η)
and performing least square fitting on the known time and the unreliability, thereby obtaining estimated values beta and eta of the parameters.
9. The method for evaluating the on-wing reliability of the aero-engine based on the monitoring information fusion according to claim 8, wherein the method comprises the following steps of:
the step S4.5 further comprises calculating the reliability of the burst failure according to the obtained parametersWherein T is 2 The time for the aeroengine to change from normal to the sudden failure state;
calculating the reliability of the burst failure according to the obtained parametersWherein T is 2 The time that it takes for the aeroengine to go from normal to a sudden failure condition.
10. The method for evaluating the on-wing reliability of the aero-engine based on the monitoring information fusion according to claim 1, wherein the method comprises the following steps of:
in the competition mode, the reliability of the aero-engine at the moment t is as follows:
wherein T is 1 The time that the aeroengine is in a failure state after being normally converted into the decline; t (T) 2 The time for the aeroengine to change from normal to the sudden failure state; w (t) is degradation amount, and Wn is degradation failure threshold; f (x, t) is a degradation amount distribution function, and the probability density function is F (x, t); r is R 2 Reliability in the burst failure mode; rc (t) represents the reliability of the contention failure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210211317.4A CN116754235A (en) | 2022-03-04 | 2022-03-04 | Aeroengine reliability assessment method for competition failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210211317.4A CN116754235A (en) | 2022-03-04 | 2022-03-04 | Aeroengine reliability assessment method for competition failure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116754235A true CN116754235A (en) | 2023-09-15 |
Family
ID=87957710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210211317.4A Pending CN116754235A (en) | 2022-03-04 | 2022-03-04 | Aeroengine reliability assessment method for competition failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116754235A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4707796A (en) * | 1983-10-19 | 1987-11-17 | Calabro Salvatore R | Reliability and maintainability indicator |
| CN102567639A (en) * | 2011-12-30 | 2012-07-11 | 南京航空航天大学 | Method for evaluating reliability of aircraft engine aiming at competing failure |
| RU2474804C1 (en) * | 2011-08-29 | 2013-02-10 | Открытое акционерное общество "Научно-производственное объединение "Сатурн" | Method of engine development |
| CN106125714A (en) * | 2016-06-20 | 2016-11-16 | 南京工业大学 | Failure Rate Forecasting Method in conjunction with BP neutral net Yu two parameters of Weibull |
| US20180284748A1 (en) * | 2017-04-03 | 2018-10-04 | General Electric Company | Control systems and methods for controlling power systems based on operational reliabilities and operational anomalies |
| US20200184131A1 (en) * | 2018-06-27 | 2020-06-11 | Dalian University Of Technology | A method for prediction of key performance parameter of an aero-engine transition state acceleration process based on space reconstruction |
-
2022
- 2022-03-04 CN CN202210211317.4A patent/CN116754235A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4707796A (en) * | 1983-10-19 | 1987-11-17 | Calabro Salvatore R | Reliability and maintainability indicator |
| RU2474804C1 (en) * | 2011-08-29 | 2013-02-10 | Открытое акционерное общество "Научно-производственное объединение "Сатурн" | Method of engine development |
| CN102567639A (en) * | 2011-12-30 | 2012-07-11 | 南京航空航天大学 | Method for evaluating reliability of aircraft engine aiming at competing failure |
| CN106125714A (en) * | 2016-06-20 | 2016-11-16 | 南京工业大学 | Failure Rate Forecasting Method in conjunction with BP neutral net Yu two parameters of Weibull |
| US20180284748A1 (en) * | 2017-04-03 | 2018-10-04 | General Electric Company | Control systems and methods for controlling power systems based on operational reliabilities and operational anomalies |
| CN108710981A (en) * | 2017-04-03 | 2018-10-26 | 通用电气公司 | The control system and method for electric system are controlled based on operational reliability and operation exception |
| US20200184131A1 (en) * | 2018-06-27 | 2020-06-11 | Dalian University Of Technology | A method for prediction of key performance parameter of an aero-engine transition state acceleration process based on space reconstruction |
Non-Patent Citations (4)
| Title |
|---|
| ERWIN V. ZARETSKY: "Weibull-Based Design Methodology for Rotating Structures in Aircraft Engines", 《INTERNATIONAL JOURNAL OF ROTATING MACHINERY》, 31 December 2003 (2003-12-31), pages 313 - 325 * |
| 刘晓娟等: "考虑多退化失效和突发失效之间竞争失效的可靠性评估方法", 中国机械工程, vol. 28, no. 01, 15 January 2017 (2017-01-15) * |
| 李伟: "基于竞争失效的航空发动机可靠性评估研究", 《 CNKI优秀硕士学位论文全文库 工程科技Ⅱ辑》, no. 7, 15 July 2014 (2014-07-15) * |
| 王华伟等: "基于竞争失效的航空发动机剩余寿命预测", 《机械工程学报》, vol. 50, no. 6, 31 March 2014 (2014-03-31), pages 198 - 201 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7251582B2 (en) | Fault diagnosis | |
| Tang et al. | Transfer-learning based gas path analysis method for gas turbines | |
| Church et al. | Forecasting consumers' expenditure: A comparison between econometric and neural network models | |
| CN109766583A (en) | Based on no label, unbalanced, initial value uncertain data aero-engine service life prediction technique | |
| CN114997051A (en) | Aero-engine service life prediction and health assessment method based on transfer learning | |
| CN113722985B (en) | Method and system for evaluating health state and predicting residual life of aero-engine | |
| CN112116198B (en) | Data-driven process industrial state perception network key node screening method | |
| CN110348615B (en) | Cable line fault probability prediction method based on ant colony optimization support vector machine | |
| CN111814956B (en) | Multi-task learning air quality prediction method based on multi-dimensional secondary feature extraction | |
| CN111144552A (en) | Multi-index grain quality prediction method and device | |
| Liu et al. | Genetic programming model for software quality classification | |
| CN111192379A (en) | Comprehensive fault diagnosis method for complete aircraft | |
| CN112116002A (en) | Determination method, verification method and device of detection model | |
| CN111581831A (en) | Failure-related multi-state system reliability assessment method | |
| Chiachío et al. | Reduction of Petri net maintenance modeling complexity via Approximate Bayesian Computation | |
| CN115051929A (en) | Network fault prediction method and device based on self-supervision target perception neural network | |
| CN116754235A (en) | Aeroengine reliability assessment method for competition failure | |
| CN114154266B (en) | Gas turbine fault prediction method based on bias rank correlation flow causal structure learning | |
| CN115204463A (en) | Residual service life uncertainty prediction method based on multi-attention machine mechanism | |
| CN110889186A (en) | Consistency inspection method for degradation data of accelerated storage and natural storage based on equal degradation increment time interval gray correlation analysis | |
| Dui et al. | Reliability Evaluation and Prediction Method with Small Samples. | |
| Losi et al. | Autoregressive Bayesian hierarchical model to predict gas turbine degradation | |
| Yangyang et al. | Research on parallel lstm algorithm based on spark | |
| Escobar et al. | Evaluating temporal bias in time series event detection methods | |
| Li et al. | Application of Improved PSO-BP neural network in fault detection of liquid-propellant rocket engine |
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 |