CN113483764B - Intelligent aircraft task path planning method based on online sensing - Google Patents
Intelligent aircraft task path planning method based on online sensing Download PDFInfo
- Publication number
- CN113483764B CN113483764B CN202110767874.XA CN202110767874A CN113483764B CN 113483764 B CN113483764 B CN 113483764B CN 202110767874 A CN202110767874 A CN 202110767874A CN 113483764 B CN113483764 B CN 113483764B
- Authority
- CN
- China
- Prior art keywords
- aircraft
- damage state
- damage
- online
- sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
An intelligent aircraft task path planning method based on-line sensing; firstly, establishing simulation models of various damage states and typical working conditions under an offline condition to obtain corresponding sensing information, classifying and reducing the sensing information according to characteristics, and constructing an offline damage state library. Then, in flight, comprehensively constructing a likelihood function by using the on-line sensing information and the sensing information of each damage state in the off-line library; and simultaneously, giving prior probability of each damage state, and further giving the current damage state of the structure by utilizing Bayesian inference. And then, judging the reliability of the aircraft for executing various actions based on the damage state, and determining the optimal path in the selectable task paths based on an optimization method by taking a given reliability threshold as a constraint and the shortest task completion time as a target. The invention provides a complete method for reasoning from online sensing structural damage state to task path planning on line, and provides support for intelligent aircraft online path decision.
Description
Technical Field
The invention belongs to the field of aircraft path planning, and particularly relates to an intelligent aircraft task path planning method based on online sensing.
Background
The traditional aircraft flies according to a preset path, and under the conditions of sudden states such as bird collisions, hail, lightning strokes and the like, the damage state of a structure is difficult to evaluate quickly and accurately, so that potential risks are brought to the aircraft to continue to execute tasks. Meanwhile, the flight envelope of the traditional aircraft is conservative and is not beneficial to exerting the optimal performance of the structure, so that the development of the intelligent aircraft based on the online sensing self-adaptive task path adjustment is of great significance.
This means that the intelligent aircraft needs to complete real-time assessment of the structural damage state in a burst state, and also needs to give corresponding assessment of the structural damage state according to the aging and fatigue conditions of the intelligent aircraft, so as to realize online decision of requirements for task path planning and the like. Furthermore, if the structural damage status of the aircraft is better than expected based on past experience in real-time assessment, it may be possible to have it perform a task beyond the traditional design range to increase revenue. In the process, the damage state of the aircraft structure needs to be accurately inferred by data acquired by the sensors arranged on the aircraft in real time, meanwhile, the reliability of various realization paths of subsequent tasks is evaluated based on the damage state of the aircraft structure, and finally, the on-line planning of the paths is completed.
Therefore, in order to meet the requirement of task path planning of the intelligent aircraft based on online sensing, a method which can utilize multisource online sensing data to rapidly infer the structural damage state and evaluate the reliability of multiple possible paths of subsequent tasks so as to select the most suitable path is developed, which is very important.
Disclosure of Invention
The invention aims to solve the problems that the real-time assessment of the structural state of an aircraft is difficult and the planning of a mission route is conservative under the repeated use and the burst state of the aircraft, and provides an intelligent aircraft mission path planning method based on-line sensing.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
an intelligent aircraft task path planning method based on-line sensing is specifically as follows:
(1) constructing an offline damage state library;
(2) structure damage state online reasoning;
(3) a method for path selection based on reliability constraints.
Compared with the prior art, the invention has the beneficial effects that: the invention establishes a set of complete method from online sensing structural state reasoning to path planning, and provides support for the aircraft to realize online path decision.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a detailed flowchart of example 1.
FIG. 3 is a detailed flowchart of example 2.
Detailed Description
The technical solutions of the present invention are further described below with reference to the drawings and the embodiments, but the present invention is not limited thereto, and modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
The method comprises the steps of firstly establishing simulation models of various damage states and typical working conditions under an offline condition to obtain corresponding sensing information, classifying and reducing the sensing information according to characteristics, and constructing an offline damage state library. Then, in flight, comprehensively constructing a likelihood function by using the on-line sensing information and the sensing information of each damage state in the off-line library; and simultaneously, giving prior probability of each damage state, and further giving the current damage state of the structure by using Bayesian inference. And then, judging the reliability of the aircraft for executing various actions based on the damage state, and determining the optimal path in the selectable task paths based on an optimization method by taking a given reliability threshold as a constraint and the shortest task completion time as a target. The invention provides a complete method for reasoning from online sensing structural damage state to task path planning on line, and provides support for intelligent aircraft online path decision.
The first embodiment is as follows: the embodiment describes an intelligent aircraft mission path planning method based on online sensing, and the method specifically comprises the following steps:
(1) constructing an offline damage state library;
(2) structure damage state online reasoning;
(3) a method for path selection based on reliability constraints.
The second embodiment is as follows: in a first embodiment, the method for planning a mission path of an intelligent aircraft based on online sensing includes:
step 1: establishing a simulation model of the structural response state of the aircraft under the action of flight load according to the structural characteristics of the aircraft;
step 2: according to the simulation model of the aircraft obtained in the step 1, dividing the aircraft structure into m regions R 1 ，R 2 ···R m Respectively establishing a simulation model containing n different damage states S in each region based on the typical failure characteristics of the conventional aircraft structure, wherein R i The simulation model contained by the region is denoted as M i,1 ，M i,2 ···M i,n ，i＝1～m；
And step 3: applying q types of typical flight working conditions F ═ F of aircrafts to each simulation model 1 ，f 2 ···f q Extracting sensing data information corresponding to the actual aircraft including the measuring points of each simulation model, classifying and reducing the sensing data information according to the acquired information type and magnitude difference and requirements, for example, classifying ultrasonic signals, electric signals and strain signals, and reducing the data dimension based on the strain information in a specific direction; the processed sensing information is represented as D, wherein R i The sensing information of the j damage state of the area under the k typical flight condition is represented as D i,j,k ；
And 4, step 4: and combining the damage state and the flight condition of each simulation model with corresponding sensing data information to form a database O ═ damage state S, flight condition F and sensing information D }.
The third concrete implementation mode: in a first embodiment, the method for planning a mission path of an intelligent aircraft based on online sensing includes:
step 1: when the aircraft executes a task, sensing information of the aircraft is acquired in real time, and the acquired sensing information is classified and reduced according to the storage characteristics of the sensing information in the off-line damage state library and is represented as D online ；
And 2, step: based on off-line damage state database O and on-line sensing information D online Constructing likelihoodsFunction L (S) i |D online ) In which S is i Representing the i-th damage state, and then given a priori probability P (S) according to each damage state i ) Therefore, the possible probability of various damage states is obtained based on Bayesian reasoning, as shown in formula (1), and the most possible damage state is selected to be inferred as the damage state of the current structure;
the fourth concrete implementation mode: in a first or third embodiment, the method for planning a mission path of an intelligent aircraft based on online sensing specifically includes:
step 1: based on the structural damage state obtained by inference in the step (2) and the total actions possibly executed by the aircraft, under the condition of considering load uncertainty in various actions, predicting the reliability probability P of each action executed by the aircraft based on the Monte Carlo method i ，i＝1，2···l；
Step 2: reliability threshold P for a given aircraft th At a reliability threshold P th And for constraint, determining the optimal task path by adopting an optimization method in the subsequent optional paths of the task by taking the minimum time for completing the task as an objective function.
Example 1:
based on the invention process of fig. 1, the present embodiment is described by strain information-based online sensing, state inference and path planning of an aircraft wing panel under layered damage, and the specific process is shown in fig. 2 and can be divided into the following stages: step one, constructing an offline layered damage state library; stage two, online reasoning of the structural layered damage state; and step three, a path selection method based on reliability constraint.
Wherein, the first stage comprises the following steps:
step 1: establishing a simulation model of the structural response state of the aircraft under the action of flight load according to the structural characteristics of the aircraft; in this embodiment, strain sensors in three directions of an array 6 x 6 on an aircraft wing panel, the structural features of the wing panel and the layout features of the sensors are shown in fig. 2, and a layered damage model of the structure under load is established.
Step 2: according to the simulation model of the aircraft obtained in the step 1, dividing the aircraft structure into m regions R 1 ，R 2 ···R m Based on the typical failure characteristics of the conventional aircraft structure, a simulation model containing n different damage states S is respectively established in each region, wherein R is i The simulation model contained in the region is represented as M i,1 ，M i,2 ···M i,n (ii) a In the present embodiment, the aircraft wing panel is regarded as 1 region as a whole, i.e., m is 1. Considering only the layered damage state as a typical failure feature, a total of 20 different layered damage states are modeled, i.e., n is 20. Different layered damage states are generated by changing the damage center position (x, y), the damage depth h, the damage length a and width b and the damage area A, and the finally obtained simulation model is M 1,1 ，M 1,2 ···M 1,20 。
And step 3: applying typical flight conditions F ═ F of q aircrafts to each simulation model 1 ，f 2 ···f q Extracting sensing data information corresponding to the actual aircraft including the measuring points of each simulation model, classifying and reducing the sensing data information according to the acquired information type and magnitude difference, for example, classifying ultrasonic signals, electric signals and strain signals, and reducing the data dimension based on the strain information in a specific direction; the processed sensing information is represented as D, wherein R i The sensing information of the jth damage state of the area under the kth typical flight condition is represented as D i,j,k (ii) a In the present embodiment, the load conditions of the aircraft on the strake under 4 speeds v and 4 turning radii r, i.e. q 4 x 16, are considered. Strain information of 3 directions of 36 measuring points at different turning speeds is extracted by adopting a strain sensor, the strain is classified according to the strain direction, namely the classification number is 3, then principal component analysis is carried out on the obtained strain information in each direction to extract main features, the obtained feature value lambda and the feature vector g are used for distinguishing the strain in a subsequent database, and the integral characterization is D ═ lambda, g }.
Step 4: combining the damage state and the flight condition of each simulation model with corresponding sensing data information to form a database O ═ damage state S, flight condition F and sensing information D }; in the present embodiment, the damage state S is { x, y, a, b, h }, and the flight condition F is { F ═ F 1 ，f 2 ···f 16 And in the case of the damage state, the damage state library O is set to { S, F, D }.
The second stage comprises the following steps:
and 5: when the aircraft executes a task, acquiring sensing information of the aircraft in real time, classifying and reducing the acquired sensing information according to the storage characteristics of the sensing information in the off-line damage state library, and expressing the classification as D online (ii) a In the embodiment, the sensing data of each strain site in the wing plate online flight process is acquired, classified according to the strain direction, and the characteristic value lambda is acquired through principal component analysis online And feature vector g online Overall characterized by D online ＝{λ online ，g online }。
Step 6: based on off-line damage state database O and on-line sensing information D online Constructing a likelihood function L (S) i |D online ) In which S is i Representing the i-th damage state. Then given a priori probabilities P (S) according to the respective injury states i ) Therefore, the possible probability of various damage states is obtained based on Bayesian reasoning, as shown in formula (1), and the most possible damage state is selected to be inferred as the damage state of the current structure; in the present embodiment, information D is sensed online using a wing plate online And constructing a likelihood function L (S) according to strain characteristics in the off-line database D i |D online ) And assuming that the prior probability of different damage states S of the wing plate is P (S) i ) 1/20, i is 1,2 · 20, the probability of the structure being in different damage states can be inferred by bayesian formula (1):
and 7: and deducing the obtained structural damage state and possible execution of the aircraft based on the step 6In the total of l actions, the reliability probability P of the aircraft to execute each action is predicted based on the Monte Carlo method under the condition that the load uncertainty in each action is considered i I 1,2 · l; in the present embodiment, after the stratified damage state of the front fender is obtained, it is determined whether or not the load conditions (6 speed and 6 radius combinations) to which the 36 turning speed and radius combinations are subjected cause further stratified expansion of the fender. The calculation method adopts a Monte Carlo method to predict the reliability probability P of the structure under the combination of the l turning speeds and the radii under the condition of considering the load uncertainty i ，i＝1，2···36。
And 8: reliability threshold P for a given aircraft th With a reliability threshold P th For constraint, the time for completing the task is the minimum as an objective function, and an optimal task path is determined in the subsequent optional paths of the task by adopting an optimization method; in this embodiment, a reliability threshold P for the strake is given th With a reliability threshold P th And for constraint, aiming at the shortest time of the task, and determining the optimal completion path of the task by adopting an optimization method in combination with the subsequent optional turning path of the task.
Example 2:
based on the invention process of fig. 1, the present embodiment is described by using online sensing, state inference and path planning based on resistance information under damage caused by low-speed impact on an aircraft fuselage panel, and a specific process is shown in fig. 3 and can be divided into the following stages: step one, constructing an offline impact damage state library; stage two, structure impact damage state online reasoning; and step three, a path selection method based on reliability constraint.
Wherein, the first stage comprises the following steps:
step 1: establishing a simulation model of the structural response state of the aircraft under the action of flight load according to the structural characteristics of the aircraft; in the present embodiment, an aircraft fuselage panel is taken as an example for explanation, and in an aircraft fuselage typical panel array 6 × 12 electrode measuring points, panel structural features and sensor layout features are shown in fig. 3, and a resistance change response model of the fuselage panel impacted by low speed is established.
Step 2: according to the simulation model of the aircraft obtained in the step 1, dividing the aircraft structure into m regions R 1 ，R 2 ···R m Based on the typical failure characteristics of the conventional aircraft structure, a simulation model containing n different damage states S is respectively established in each region, wherein R is i The simulation model contained in the region is represented as M i,1 ，M i,2 ···M i,n (ii) a In the present exemplary embodiment, the aircraft fuselage representative panel is considered as a whole as 1 region, i.e. m is 1. Considering only the impact damage state as a typical failure characteristic, a total of 50 different damage states were modeled, i.e., n 50. Different impact damage states are generated by changing the damage center position (x, y), the impact depth h, the damage length a and width b and the damage area A, and the finally obtained simulation model is M 1,1 ，M 1,2 ···M 1,50 。
And step 3: applying typical flight conditions F ═ F of q aircrafts to each simulation model 1 ，f 2 ···f q Extracting sensing data information corresponding to the actual aircraft including the measuring points of each simulation model, classifying and reducing the sensing data information according to the acquired information type and magnitude difference, for example, classifying ultrasonic signals, electric signals and strain signals, and reducing the data dimension based on the strain information in a specific direction; the processed sensing information is represented as D, wherein R i The sensing information of the j damage state of the area under the k typical flight condition is represented as D i,j,k (ii) a In the present exemplary embodiment, the loading conditions of the aircraft on the fuselage panels at 20 respective pull-up speeds v are considered, i.e. q is 20. Obtaining resistance and impedance information D of materials between adjacent electrode sensors, classifying according to the two types of information of the resistance and the impedance, namely the classification number is 2, then carrying out principal component analysis on the obtained resistance and impedance information to extract main characteristics, obtaining a characteristic value lambda and a characteristic vector g to be used for judging corresponding characteristics of a subsequent database, and integrally representing D ═ lambda, g }.
And 4, step 4: combining the damage state and the flight condition of each simulation model with corresponding sensing data information to form a database O ═ damage state S, flight condition F,Sensing information D }; in this embodiment, the damage state S is { x, y, a, b, h }, and the flight condition F is { F { (F) } 1 ，f 2 ···f 20 And the sensing information D is { λ, g }, and the damage state library O is { S, F, D }.
The second stage comprises the following steps:
and 5: when the aircraft executes a task, acquiring sensing information of the aircraft in real time, classifying and reducing the acquired sensing information according to the storage characteristics of the sensing information in the off-line damage state library, and expressing the classification as D online (ii) a In the embodiment, resistance and impedance information between electrodes in the online flight process of the aircraft fuselage panel is obtained, and the characteristic value lambda is obtained through principal component analysis online And the feature vector g online Overall characterized by D online ＝{λ online ，g online }。
Step 6: based on off-line damage state database O and on-line sensing information D online Constructing a likelihood function L (S) i |D online ) In which S is i Representing the i-th damage state. Then given a priori probabilities P (S) according to the respective injury states i ) Therefore, the possible probabilities of various damage states are obtained based on Bayesian reasoning, as shown in formula (1), and the most possible damage state is selected to be inferred as the damage state of the current structure; in the present embodiment, the online sensory information D of the aircraft fuselage panel is used online And resistance and impedance characteristics in the off-line database D to construct a likelihood function L (S) i |D online ) And assuming that the prior probability of different impact damage states S of the fuselage panel is P (S) i ) 1/50, i is 1,2 · 50, the probability of the structure being in different damage states can be inferred by bayesian formula (1):
and 7: predicting flight based on Monte Carlo method under the condition of considering load uncertainty in various actions based on l actions possibly executed by the aircraft and the structural damage state obtained by reasoning in the step 6Reliability probability P of each action executed by machine i I 1,2 · l; in the present embodiment, after obtaining the impact damage state of the aircraft fuselage panel, it is determined whether the load failure of the fuselage panel is caused by 30 pull-up speeds. The calculation method adopts a Monte Carlo method to predict the reliability probability P of the structure under the combination of the turning speed and the radius of the structure under the condition of considering the load uncertainty i ，i＝1，2···30。
And 8: reliability threshold P for a given aircraft th At a reliability threshold P th For constraint, the minimum time for completing the task is taken as an objective function, and an optimal task path is determined in the subsequent optional paths of the task by adopting an optimization method; in this embodiment, a reliability threshold P for the strake is given th With a reliability threshold P th And for constraint, aiming at the shortest time of the task, combining the execution path required by the task and determining the optimal completion path of the task by adopting an optimization method.
Claims (1)
1. An intelligent aircraft task path planning method based on-line sensing is characterized in that: the method specifically comprises the following steps:
(1) constructing an offline damage state library; the (1) is specifically as follows:
step 1: establishing a simulation model of the structural response state of the aircraft under the action of flight load according to the structural characteristics of the aircraft;
step 2: according to the simulation model of the aircraft obtained in the step 1, dividing the aircraft structure into m regions R 1 ，R 2 ···R m Based on the typical failure characteristics of the conventional aircraft structure, a simulation model containing n different damage states S is respectively established in each region, wherein R is i The simulation model contained in the region is represented as M i,1 ，M i,2 ···M i,n ，i＝1～m；
And step 3: applying typical flight conditions F ═ F of q aircrafts to each simulation model 1 ，f 2 ···f q And extracting sensing data information corresponding to the actual aircraft including the measuring points of each simulation model, and aiming at the obtained information type and magnitude differenceClassifying and reducing the order of the sensing data information according to the requirement to reduce the data dimension; the processed sensing information is represented as D, wherein R i The sensing information of the j damage state of the area under the k typical flight condition is represented as D i,j,k ；
And 4, step 4: combining the damage state and the flight condition of each simulation model with corresponding sensing data information to form a database O ═ damage state S, flight condition F and sensing information D };
(2) structure damage state online reasoning; the step (2) is specifically as follows:
step 1: when the aircraft executes a task, acquiring sensing information of the aircraft in real time, classifying and reducing the acquired sensing information according to the storage characteristics of the sensing information in the off-line damage state library, and expressing the classification as D online ；
Step 2: based on off-line damage state database O and on-line sensing information D online Constructing a likelihood function L (S) i |D online ) In which S is i Representing the i-th damage state, and then given a priori probability P (S) according to each damage state i ) Therefore, the possible probabilities of various damage states are obtained based on Bayesian reasoning, as shown in formula (1), and the most possible damage state is selected to be inferred as the damage state of the current structure;
(3) a path selection method based on reliability constraints; the step (3) is specifically as follows:
step 1: based on the structural damage state obtained by inference in the step (2) and the total actions possibly executed by the aircraft, under the condition of considering load uncertainty in various actions, predicting the reliability probability P of each action executed by the aircraft based on the Monte Carlo method i ，i＝1，2···l；
Step 2: reliability threshold P for a given aircraft th With a reliability threshold P th For constraint, the minimum time for completing the task is taken as an objective function, and in the subsequent optional path of the taskAnd determining an optimal task path by adopting an optimization method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110767874.XA CN113483764B (en) | 2021-07-07 | 2021-07-07 | Intelligent aircraft task path planning method based on online sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110767874.XA CN113483764B (en) | 2021-07-07 | 2021-07-07 | Intelligent aircraft task path planning method based on online sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113483764A CN113483764A (en) | 2021-10-08 |
| CN113483764B true CN113483764B (en) | 2022-09-02 |
Family
ID=77941837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110767874.XA Active CN113483764B (en) | 2021-07-07 | 2021-07-07 | Intelligent aircraft task path planning method based on online sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113483764B (en) |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060004499A1 (en) * | 2004-06-30 | 2006-01-05 | Angela Trego | Structural health management architecture using sensor technology |
| US7366627B2 (en) * | 2005-05-31 | 2008-04-29 | Honeywell International, Inc. | Method for satisfying certification requirements and verifying the integrity of structural health management systems |
| US9506836B2 (en) * | 2012-10-09 | 2016-11-29 | The Boeing Company | Methods and systems for structural health monitoring |
| CN105841702A (en) * | 2016-03-10 | 2016-08-10 | 赛度科技（北京）有限责任公司 | Method for planning routes of multi-unmanned aerial vehicles based on particle swarm optimization algorithm |
| US10311202B2 (en) * | 2016-04-11 | 2019-06-04 | Airbus Helicopters Deutschland GmbH | Probabilistic load and damage modeling for fatigue life management |
| US9950815B2 (en) * | 2016-07-01 | 2018-04-24 | United Technologies Corporation | Systems and methods for detecting damage |
| CN107830996B (en) * | 2017-10-10 | 2020-11-03 | 南京航空航天大学 | Fault diagnosis method for aircraft control surface system |
| CN107844663B (en) * | 2017-11-22 | 2020-10-27 | 哈尔滨工业大学 | Reliability modeling method based on fatigue accumulated damage |
| CN108414626A (en) * | 2018-03-02 | 2018-08-17 | 北京航空航天大学 | A kind of multisensor damage networking monitoring method based on bayes risk function |
| CN109142085B (en) * | 2018-10-10 | 2019-07-26 | 哈尔滨工业大学 | A kind of thermal protection on-line analysis system and method based on dynamic data driving |
| US11367053B2 (en) * | 2018-11-16 | 2022-06-21 | University Of Connecticut | System and method for damage assessment and restoration |
| CN110530638B (en) * | 2019-07-31 | 2020-10-27 | 西安交通大学 | Digital twin-based method for detecting and diagnosing damage of main bearing of aero-engine |
| CN110989644B (en) * | 2019-11-29 | 2021-04-23 | 上海宇航系统工程研究所 | Aircraft trajectory planning method considering target point multi-terminal constraint |
| CN111351488B (en) * | 2020-03-03 | 2022-04-19 | 南京航空航天大学 | Intelligent trajectory reconstruction reentry guidance method for aircraft |
| CN111737811B (en) * | 2020-05-09 | 2023-01-10 | 北京航空航天大学 | Helicopter movable part service life management method, device and medium based on digital twin |
| CN111598170B (en) * | 2020-05-18 | 2022-04-22 | 北京航空航天大学 | Crack detection probability evaluation method considering model selection uncertainty |
| CN111703587B (en) * | 2020-06-08 | 2022-11-01 | 国营四达机械制造公司 | Method for repairing crack corrosion fault of electric heating leading edge skin of airplane |
| CN111812215B (en) * | 2020-07-22 | 2021-06-29 | 南京航空航天大学 | Aircraft structure damage monitoring method |
| CN112520064B (en) * | 2020-12-04 | 2022-09-20 | 中国航空工业集团公司成都飞机设计研究所 | Automatic damage identification method based on strain monitoring |
-
2021
- 2021-07-07 CN CN202110767874.XA patent/CN113483764B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113483764A (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108594788B (en) | Airplane actuator fault detection and diagnosis method based on deep random forest algorithm | |
| CN109766583B (en) | Aircraft engine life prediction method based on unlabeled, unbalanced and initial value uncertain data | |
| CN111737811B (en) | Helicopter movable part service life management method, device and medium based on digital twin | |
| CN107909179B (en) | Method for constructing prediction model of running condition of plug-in hybrid vehicle and vehicle energy management method | |
| Thirumalainambi et al. | Training data requirement for a neural network to predict aerodynamic coefficients | |
| US8676544B2 (en) | Method of predicting the aerodynamic behavior of an aircraft element | |
| CN111460676B (en) | Method for evaluating health performance of multi-rotor aircraft under atmospheric turbulence disturbance | |
| CN111680875A (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| Jeong et al. | Estimation of maximum strains and loads in aircraft landing using artificial neural network | |
| CN111598435A (en) | Quality trend prediction method based on adaptive feature selection and improved thought evolution algorithm | |
| CN107526866B (en) | Wing surface structure topology optimization method based on feature driving | |
| Rodriguez et al. | Optimized off-design performance of flexible wings with continuous trailing-edge flaps | |
| CN115576184A (en) | Fault online diagnosis and fault-tolerant control method for underwater robot propeller | |
| Secco et al. | Artificial neural networks applied to airplane design | |
| US7617166B2 (en) | Neural network for aeroelastic analysis | |
| CN113483764B (en) | Intelligent aircraft task path planning method based on online sensing | |
| Bouhelal et al. | Blade Element Momentum Theory Coupled with Machine Learning to Predict Wind Turbine Aerodynamic Performances | |
| CN112597706A (en) | Carrier rocket executing mechanism fault online diagnosis method | |
| Cui et al. | Intelligent health management of fixed-wing UAVs: A deep-learning-based approach | |
| Weckman et al. | Using neural networks with limited data to estimate manufacturing cost | |
| CN113486926B (en) | Automatic change pier equipment anomaly detection system | |
| Woodson et al. | Understanding abrupt wing stall with CFD | |
| Haas | Prediction of Structural Reliability Through an Alternative Variability-Based Methodology | |
| Chapin et al. | Analysis, design and optimization of Navier-Stokes flows around interacting sails | |
| Said et al. | Effects of leading edge enlargement on the primary vortex of blunt-edged delta wing VFE-2 Profile |
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 |