CN114627687A - Helicopter ground proximity warning method for predicting escape trajectory based on neural network - Google Patents
Helicopter ground proximity warning method for predicting escape trajectory based on neural network Download PDFInfo
- Publication number
- CN114627687A CN114627687A CN202210083861.5A CN202210083861A CN114627687A CN 114627687 A CN114627687 A CN 114627687A CN 202210083861 A CN202210083861 A CN 202210083861A CN 114627687 A CN114627687 A CN 114627687A
- Authority
- CN
- China
- Prior art keywords
- escape
- helicopter
- terrain
- neural network
- trajectory
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/04—Anti-collision systems
- G08G5/045—Navigation or guidance aids, e.g. determination of anti-collision manoeuvers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a helicopter ground proximity warning method based on escape trajectory prediction of a neural network, which comprises the following steps of 1, substituting the current manipulated variable, flight state parameters and escape transformation modes of a helicopter into a neural network model, and predicting a plurality of escape trajectories of the helicopter in different transformation directions in real time; step 2, predicting potential collision threats of forward-looking terrains by combining a terrain elevation database based on the escape tracks predicted in real time to generate a terrain envelope; step 3, making a decision for modifying and judging the potential ground collision threat by comparing whether the escape tracks intersect with the corresponding terrain envelope lines or not; and 4, carrying out alarm prompt based on the decision-making result. The method solves the problems that HTAWS is installed on helicopters flying at low altitude and ultra-low altitude, and the success rate of alarm is low, the false alarm rate is high and the like easily caused in the flying process; the problems that the escape track is difficult to realize online accurate prediction, the flight dynamics model is complex to build and the like are solved.
Description
Technical Field
The invention belongs to the technical field of helicopter flight safety, and particularly relates to a helicopter ground proximity warning method for predicting an escape trajectory based on a neural network.
Background
During the Flight of an aircraft, a crash accident caused by the failure of a driver to timely sense the dangerous proximity to surrounding Terrain or obstacles is called a Controlled Flight Impact (CFIT), which has been one of the main causes of a Flight accident in modern aircraft.
In the 70 s of the 20 th century, in order to prevent CFIT accidents, the industry introduced a Ground Proximity Warning System (GPWS) suitable for passenger airliners. In the 80 s of the 20 th century, after civil aviation airliners were forced to equip GPWS, the number of CFIT accidents occurred was obviously reduced, but the CFIT accidents were still the main cause of the aviation accidents. However, GPWS has revealed some problems during use, and there are places where further improvements are needed. To overcome the shortcomings of GPWS, the industry introduced a Terrain Awareness and Warning System (TAWS), also called Enhanced Ground Proximity Warning System (EGPWS), in 1998. The TAWS maintains the original advantages of the GPWS, and simultaneously adds new functions of forward-looking terrain warning, terrain display and the like. Since the number of CFIT accidents occurred worldwide every year was further reduced since the introduction of TAWS, which data statistics showed to be effective in preventing the occurrence of CFIT accidents.
Helicopters often fly in low-altitude and ultra-low-altitude areas with complex geographical environments, and CFIT is also an important cause of flight accidents. With the successful application of TAWS to civil aircraft, the transplantation of this system to helicopters has begun to be considered. However, compared with a civil aircraft, the helicopter has great differences in mechanical structure, maneuvering mode, flight performance and other aspects, and if the TAWS suitable for the civil aircraft is directly installed on the helicopter, a terrain collision avoidance alarm cannot be effectively provided, and a series of problems such as an excessive false alarm rate and the like are caused. Therefore, a reasonable and effective warning method needs to be researched according to the flight performance and the flight characteristics of the helicopter.
In this context, european and american avionics manufacturers, typified by Honeywell in the united states, have introduced a Helicopter Terrain Awareness and Warning System (HTAWS). The HTAWS forward-looking warning principle is similar to that of the TAWS, a virtual warning boundary is generated in the space of the forward direction of the helicopter according to the flight performance of the helicopter, and the warning boundary is composed of a forward-looking boundary, a downward-looking boundary, an upward-looking boundary and a side boundary. Obtaining terrain data information in front of the helicopter according to the terrain elevation database, comparing the spatial position relation between the warning boundary and the terrain in front in real time, triggering warning when the warning boundary is intersected with the terrain in front, and simultaneously giving warning prompts by the system.
The frequency of CFIT accidents of the helicopter is greatly reduced by launching HTAWS, but in order to consider the universality, the design of an alarm boundary of the conventional forward-looking alarm algorithm of the helicopter is conservative, and a higher safety threshold is usually set, so that the problems of overlong early alarm time, lower alarm success rate, higher false alarm rate and the like are often caused. When a helicopter, particularly a military armed helicopter, executes low-altitude and ultra-low-altitude flight tasks, the flight safety of the helicopter is guaranteed, and meanwhile, the smooth execution of the flight tasks is required to be guaranteed. Therefore, the HTAWS is not suitable for helicopters with strong maneuvering characteristics, especially military gunships, and greatly limits the performance of the helicopters. Therefore, the warning method needs to be optimally designed according to the flight performance and flight requirements of the helicopter.
At present, a helicopter ground proximity warning method is usually designed based on an escape trajectory, and accurate prediction of the escape trajectory of a helicopter is a key factor influencing the success of the warning method. The helicopter escape trajectory calculation method comprises two methods, one method is a curve fitting method based on flight test data, common curve fitting methods comprise an elliptic trajectory method and a parabolic trajectory method, the methods cannot predict the high-precision helicopter escape trajectory, and the method cannot predict the helicopter escape trajectory with a certain roll angle. The other method is a motion equation integration method based on a flight dynamics model, the helicopter escape trajectory in any flight state can be calculated by the method, but the method has high requirements on the precision and the trim calculation speed of the flight dynamics model, the dynamics model of the fixed wing aircraft is simple, and the trajectory prediction effect with good real-time performance can be obtained by applying operation in advance. However, the helicopter has a complex control system and external environmental factors, which results in a very complex flight dynamics model to be built, and a high-precision helicopter escape trajectory cannot be predicted in real time. Secondly, for helicopters of different models, the flight dynamics models of the helicopters are different greatly, so that the model is poor in portability and universality.
Disclosure of Invention
Aiming at the defects, the invention provides a helicopter ground proximity warning method for predicting an escape track based on a neural network, and aims to solve the problems that a helicopter with HTAWS installed in low altitude and ultra-low altitude flight is easy to cause low warning success rate, high false alarm rate and the like in the flight process.
In addition, the invention provides a method for predicting the escape trajectory of a helicopter based on a neural network,
a helicopter ground proximity warning method based on a neural network prediction escape track comprises the following steps,
step 1, training a neural network model, substituting the current operation amount, flight state parameters and escape transformation mode of the helicopter into the trained neural network model, and predicting a plurality of escape tracks of the helicopter in different transformation directions in real time at a certain frequency;
step 3, making a decision for modifying and judging the potential ground collision threat by comparing whether the escape tracks intersect with the corresponding terrain envelope lines or not;
and 4, carrying out alarm prompt in three modes of sound, light and display based on the decision-making result changed in the step 3.
Preferably, the neural network model is trained on the basis of helicopter real flight test data or flight simulation data, and errors and accuracy are selected as evaluation indexes.
Preferably, the error and accuracy indicators are:
Traj_E=ABS(Traj_Model-Traj_True),
Traj_Acc=(1-Traj_E/Traj_True)*100%,
wherein, Traj _ E represents the absolute value error between the escape trajectory Traj _ Model predicted based on the neural network Model and the escape trajectory Traj _ True obtained based on the real flight test data of the helicopter, and Traj _ Acc represents the relative precision between the Traj _ Model and the Traj _ True.
Preferably, the escape trajectory of the helicopter is associated with a roll-out maneuver, said roll-out maneuver comprising a direct pull-out and a roll-pull-out, corresponding to the direct pull-out trajectory and the roll-pull-out trajectory, respectively, wherein the roll-pull-out trajectory comprises a left roll-pull-out trajectory and a right roll-pull-out trajectory.
Preferably, step 2 specifically comprises:
step 2.1, determining a terrain scanning range;
step 2.2, in a scanning range, combining terrain elevation database data, performing elevation extraction on the terrain below an escape track of the helicopter at a certain frequency in real time to obtain the maximum value of the terrain elevation under a fixed step length, and taking the maximum value as the terrain elevation value under the step length to generate a terrain elevation profile;
and 2.3, superposing a vertical safety threshold on the basis of the terrain elevation profile to finally generate a terrain envelope.
Preferably, the vertical safety threshold should not be a fixed value, and it needs to consider the uncertainty of the trajectory prediction, the uncertainty of the navigation positioning, and the vertical uncertainty of the terrain database, and its calculation formula is:
SCAN_Vert=NAV+(DEM+TPA)/2
the NAV is the navigation and positioning uncertainty, the DEM is the vertical uncertainty of a terrain database, and the TPA is the track prediction uncertainty.
Preferably, step 3 specifically comprises: and sequentially comparing the escape tracks with the terrain envelope lines below the escape tracks, if the comparison results of the escape tracks and the terrain envelope lines in different departure directions do not meet the requirements, making a departure decision to judge that the potential ground collision risk exists in the helicopter, otherwise, continuing to execute the current flight task by the helicopter.
Preferably, when the escape trajectory intersects with the terrain envelope, the direction corresponding to the escape trajectory is no longer considered as an effective terrain avoidance selection, and the comparison result is determined to be unsatisfactory.
Preferably, step 4 specifically comprises: and (4) carrying out alarm prompt based on the decision-making judgment obtained in the step (3), wherein the alarm prompt comprises light alarm, voice alarm and display alarm.
The invention discloses a helicopter ground proximity warning system based on a neural network prediction escape track, which comprises an escape track prediction module, a collision threat prediction module, a transformation decision module and a warning prompt module, wherein the escape track prediction module is substituted into a neural network model according to the current parameters and the escape transformation mode of a helicopter to obtain the helicopter escape track and input the helicopter escape track into the transformation decision module; the extraction decision module compares whether the escape track intersects with the corresponding terrain envelope in real time to carry out extraction decision judgment on potential ground collision threats, and prompts the extraction decision judgment result through the alarm prompt module.
The invention has the beneficial effects that:
(1) the helicopter ground proximity warning method based on neural network prediction escape trajectory can be applied to helicopters executing low-altitude and ultra-low-altitude flight tasks, and the helicopters are allowed to execute the current flight task to the greatest extent while the flight safety of the helicopters is guaranteed;
(2) compared with an HTAWS forward-looking warning method, the helicopter warning method provided by the invention has the warning success rate of 99.95 percent and the false alarm rate of 0.97 percent, and is more suitable for helicopters executing low-altitude and ultra-low-altitude flight tasks;
(3) compared with the traditional track prediction method, the method for predicting the escape track based on the neural network has the advantages of higher calculation precision, fewer calculation times, lower complexity, better real-time property, and good track prediction accuracy and algorithm universality. The escape trajectory predicted by using the neural network is matched with real flight test data, the prediction precision of the escape trajectory is good, and the prediction precision of the trajectory in the cruise speed range of the helicopter can basically reach 95%;
(4) compared with the traditional helicopter escape trajectory prediction method, the method solves the problems that the escape trajectory is difficult to realize online accurate prediction, the flight dynamics model is complex to build and the like.
Drawings
In order to more clearly illustrate the technical solution in the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below.
FIG. 1 is a schematic diagram of a helicopter ground proximity warning method based on neural network prediction escape trajectory according to an embodiment of the present invention;
FIG. 2 is a diagram of a neural network framework suitable for escape trajectory prediction in accordance with an embodiment of the present invention;
FIG. 3 is a graph of error and accuracy test results for a neural network-based prediction of escape trajectory at different airspeeds in accordance with an embodiment of the present invention;
FIG. 4 is a schematic illustration of collision threat prediction according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a modified decision making decision according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The embodiment of the invention provides a helicopter ground proximity warning method based on neural network prediction escape trajectory, as shown in fig. 1, the helicopter ground proximity warning method is a warning method schematic diagram of the invention, and comprises an escape trajectory prediction module (101), a collision threat prediction module (102), a decision-making module (103) and a warning prompt module (104). The escape track prediction module (101) substitutes a neural network model to calculate the escape track of the helicopter in real time at a certain frequency according to the current operation amount, flight state parameters and the determined escape improvement mode of the helicopter; a collision threat prediction module (102) scans the terrain below the escape track of the helicopter through a terrain elevation database to obtain a terrain elevation profile, and a vertical safety threshold is superposed on the terrain elevation profile to generate a terrain envelope; a transformation decision module (103) detects whether an escape track intersects with a terrain envelope below the escape track in real time at a certain frequency to carry out transformation decision judgment on potential ground collision threats; the warning prompt module (104) carries out warning prompt on the collision prediction result and the changed decision suggestion in a light warning (105), a voice warning (106) and a display warning (107) prompting mode.
The invention provides a helicopter ground proximity warning method based on a neural network prediction escape trajectory, which specifically comprises the following steps:
step 1, substituting the current operation amount, flight state parameters and the determined escape change mode of the helicopter into a neural network model to solve the escape trajectory of the helicopter in an escape trajectory prediction module (101). The escape trajectory of the helicopter is calculated in real time at a certain frequency in the flying process of the helicopter, the escape trajectory refers to a motion trajectory of the helicopter after certain maneuvering measures are taken on the basis of the current flying state, and two maneuvering modes of the helicopter are common, namely direct pull-up and roll-up and pull-out. The invention determines three escape transformation modes, and simultaneously calculates three escape transformation tracks according to the current flight state parameters of the helicopter, namely directly pulling the transformation track, rolling the transformation track leftwards and pulling the transformation track rightwards.
Fig. 2 is a diagram of a neural network framework suitable for escape trajectory prediction according to the present invention. Firstly, obtaining sample data required by a neural network model through helicopter real flight test data, secondly, screening the data, determining the input quantity and the output quantity of the neural network model, and finally, segmenting and normalizing the sample data to obtain training sample data and test sample data. The input quantity of the neural network model mainly comprises helicopter control input quantity and flight state parameters, and the output quantity of the neural network model mainly comprises relative positioning information of escape track prediction points. Particularly, if the real flight test data of the helicopter cannot be acquired in the calculation process, the flight simulation data calculated by the helicopter flight dynamics model can be used for replacing the flight test data.
Training the neural network model by using the pre-processed training sample data, selecting a proper learning rate, hidden node number and learning step length of the neural network model, and converging the neural network model through iterative operation to obtain the neural network model capable of accurately and quickly predicting the escape trajectory of the helicopter.
The error and the accuracy are selected as evaluation indexes of the neural network model, the trained neural network model is checked through test sample data, the accuracy of predicting the escape trajectory of the helicopter based on the neural network model is tested, the error and accuracy test result of predicting the escape trajectory based on the neural network at different airspeeds is shown in figure 3, and the prediction effect in the cruise speed range is good, and the prediction accuracy can basically reach 95%. The method for predicting the escape trajectory error and the accuracy based on the neural network comprises the following steps of (1) and (2):
Traj_E=ABS(Traj_Model-Traj_True) (1)
Traj_Acc=(1-Traj_E/Traj_True)*100% (2)
wherein, Traj _ E represents the absolute value error between the escape trajectory Traj _ Model predicted based on the neural network Model and the escape trajectory Traj _ True obtained based on the real flight test data of the helicopter, and Traj _ Acc represents the relative precision between the Traj _ Model and the Traj _ True.
According to the determined terrain scanning range, elevation extraction is carried out on the terrain below the three helicopter escape tracks calculated by the escape track prediction module (101) in real time at a certain frequency by combining a terrain elevation database, the maximum value of the terrain elevation within a certain range of the escape track prediction points under a fixed step length is calculated, the maximum value is determined as the terrain elevation value under the step length, and a terrain elevation profile is generated.
The terrain elevation database has certain vertical uncertainty, and a vertical safety threshold value is superposed on a terrain scanning result, so that the flight safety of the helicopter is guaranteed to the maximum extent. Considering the real flight condition of the helicopter and the requirement of the combat mission, the vertical safety threshold value is not a fixed value, and the uncertainty of the track prediction, the uncertainty of the navigation and positioning and the vertical uncertainty of a terrain database are considered. The terrain vertical safety threshold calculation formula (3) is as follows:
SCAN_Vert=NAV+(DEM+TPA)/2 (3)
the NAV is the navigation and positioning uncertainty, the DEM is the vertical uncertainty of a terrain database, and the TPA is the track prediction uncertainty.
And generating a terrain envelope in the front visual area of the helicopter according to the terrain elevation superposed with the vertical safety threshold.
Step 3, in the change decision module (103), a change decision judgment is performed on the potential ground collision threat by detecting whether the three helicopter escape trajectories calculated by the escape trajectory prediction module (101) intersect with the terrain envelope generated by the collision threat prediction module (102), and a change decision judgment schematic diagram of the embodiment of the invention is shown in fig. 5. The method comprises the steps of determining that a system gives an alarm when three escape tracks predicted by the helicopter intersect with a terrain envelope below the tracks, so that the current flight task executed by the helicopter is not influenced as much as possible while flight safety is guaranteed. In the decision-making judging process, the three escape tracks and the terrain envelope below the escape tracks are updated in real time at a certain frequency, and the decision-making judging process is also carried out in real time at a corresponding frequency.
Considering that the improved decision is established on the basis of the prediction of three possible escape tracks, the possibility of collision of the predicted escape tracks of the three helicopters is judged at the same time, and a relatively safe path is selected as an improved decision suggestion. When any one of the three escape tracks intersects with the corresponding terrain envelope, the direction is no longer considered as an effective terrain avoidance choice, and the helicopter continues to execute the current flight task. When two escape trajectories are no longer valid choices, the helicopter will still be allowed to perform the current flight mission, since the third escape trajectory still provides the helicopter with an effective terrain avoidance. And only when the last escape track is intersected with the terrain envelope, the decision is changed to judge that the potential ground collision risk exists in the helicopter.
And 4, in the alarm prompt module (104), based on the change decision suggestion given by the change decision module (103), giving an alarm prompt to the collision prediction result and the change direction in a light alarm (105), a voice alarm (106) and a display alarm (107) mode. The system comprises a decision extraction module, an alarm prompt module, a decision extraction module and a decision extraction module, wherein the decision extraction module gives out decision extraction suggestions, and the alarm prompt module gives an alarm in a mode of combining sound, light and display alarms.
When the warning prompt module (104) receives the potential ground collision risk, the light warning prompts the prediction result of the potential collision, if the predicted three escape tracks are intersected with the terrain envelope below the predicted three escape tracks, the warning light displays red, and if not, the warning light displays green. The voice alarm prompts the helicopter to avoid the direction of the change of the terrain, such as direct pull-up, left rolling pull-up and right rolling pull-up. Displaying alarms by displaying an avoidance indication arrow on a multifunction display (MFD) or a head-up display (HUD), and if it is judged that there is a potential ground collision risk, displaying an arrow represented by an escape trajectory of the last alarm in a screen.
And randomly generating a navigation path based on different testing geographic environments and latitude and longitude intervals, carrying out simulation test on the ground proximity warning method in the helicopter cruising speed range, counting analysis results and taking an average value as a final test result. Table 1 shows simulation test results of the helicopter ground proximity warning method for predicting an escape trajectory based on a neural network, which is provided by the present invention, and it can be seen that, compared with the conventional HTAWS forward-looking warning method, the helicopter ground proximity warning method provided by the present invention has a higher warning success rate and a lower false alarm rate.
TABLE 1
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A helicopter ground proximity warning method based on a neural network prediction escape trajectory is characterized by comprising the following steps:
step 1, training a neural network model, substituting the current operation amount, flight state parameters and escape transformation mode of the helicopter into the trained neural network model, and predicting a plurality of escape tracks of the helicopter in different transformation directions in real time at a certain frequency;
step 2, predicting potential collision threats of forward-looking terrains in a certain range by combining a terrain elevation database based on the escape tracks predicted in real time in the step 1, and generating a terrain envelope;
step 3, making a decision for modifying and judging the potential ground collision threat by comparing whether the escape tracks intersect with the corresponding terrain envelope lines or not;
and 4, carrying out alarm prompt based on the decision-making result changed in the step 3.
2. The helicopter ground proximity warning method based on neural network prediction escape trajectory of claim 1, characterized by that, the neural network model is trained based on helicopter real flight test data or flight simulation data, and selects error and accuracy as evaluation indexes.
3. The helicopter ground proximity warning method based on neural network prediction escape trajectory of claim 2, characterized in that the error and accuracy index are respectively:
Traj_E=ABS(Traj_Model-Traj_True),
Traj_Acc=(1-Traj_E/Traj_True)*100%,
wherein, Traj _ E represents the absolute value error between the escape trajectory Traj _ Model predicted based on the neural network Model and the escape trajectory Traj _ True obtained based on the real flight test data of the helicopter, and Traj _ Acc represents the relative precision between the Traj _ Model and the Traj _ True.
4. A helicopter ground proximity warning method based on neural network prediction escape trajectory according to claim 1 or 3, characterized in that the escape trajectory of the helicopter is related to the adopted maneuver mode, said maneuver mode comprises a direct pull-up maneuver and a roll pull-up maneuver corresponding to the direct pull-up maneuver and the roll pull-up maneuver, respectively, wherein the roll pull-up maneuver comprises a left roll pull-up maneuver and a right roll pull-up maneuver.
5. The helicopter ground proximity warning method based on escape trajectory prediction of neural network of claim 4, characterized in that said step 2 specifically is:
step 2.1, determining a terrain scanning range;
step 2.2, in a scanning range, combining terrain elevation database data, performing elevation extraction on the terrain below an escape track of the helicopter at a certain frequency in real time to obtain the maximum value of the terrain elevation under a fixed step length, and taking the maximum value as the terrain elevation value under the step length to generate a terrain elevation profile;
and 2.3, superposing a vertical safety threshold on the basis of the terrain elevation profile to finally generate a terrain envelope.
6. A helicopter ground proximity warning method based on neural network prediction escape trajectory according to claim 5, characterized by that, the vertical safety threshold should not be a fixed value, and it needs to consider both the trajectory prediction uncertainty, navigation positioning uncertainty and terrain database vertical uncertainty, and its calculation formula is:
SCAN_Vert=NAV+(DEM+TPA)/2
the NAV is the navigation and positioning uncertainty, the DEM is the vertical uncertainty of a terrain database, and the TPA is the track prediction uncertainty.
7. The helicopter ground proximity warning method based on escape trajectory prediction of neural network of claim 6, characterized in that said step 3 specifically is: and sequentially comparing the escape tracks with the terrain envelope lines below the escape tracks, if the comparison results of the escape tracks and the terrain envelope lines in different departure directions do not meet the requirements, making a decision to judge that the potential ground collision risk exists in the helicopter, otherwise, continuing to execute the current flight task.
8. The helicopter ground proximity warning method based on neural network prediction escape trajectory of claim 7, characterized by that, when the escape trajectory intersects with the terrain envelope, the direction corresponding to the escape trajectory is no longer considered as an effective terrain evasion selection, and the comparison result is determined to be not satisfactory.
9. The helicopter ground proximity warning method based on neural network prediction escape trajectory according to claim 8, wherein the step 4 specifically is: and (4) carrying out alarm prompt based on the decision-making judgment obtained in the step (3), wherein the alarm prompt comprises light alarm, voice alarm and display alarm.
10. The helicopter ground proximity warning system based on neural network prediction escape trajectory according to any one of claims 1, 5, 7, 8, and 9, comprising an escape trajectory prediction module, a collision threat prediction module, a decision-making modification module and a warning prompt module, wherein the escape trajectory prediction module substitutes a neural network model according to the current parameters and escape modification mode of a helicopter to obtain a helicopter escape trajectory and inputs the helicopter escape trajectory into the decision-making modification module, and the collision threat prediction module scans the terrain below the helicopter escape trajectory to obtain a terrain elevation profile, and generates a terrain envelope on the basis of the terrain elevation profile and inputs the terrain envelope into the decision-making modification module; the extraction decision module compares whether the escape track intersects with the corresponding terrain envelope in real time to carry out extraction decision judgment on potential ground collision threats, and prompts the extraction decision judgment result through the alarm prompt module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210083861.5A CN114627687B (en) | 2022-01-19 | 2022-01-19 | Helicopter ground proximity warning method for predicting escape trajectory based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210083861.5A CN114627687B (en) | 2022-01-19 | 2022-01-19 | Helicopter ground proximity warning method for predicting escape trajectory based on neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114627687A true CN114627687A (en) | 2022-06-14 |
CN114627687B CN114627687B (en) | 2023-04-07 |
Family
ID=81899035
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210083861.5A Active CN114627687B (en) | 2022-01-19 | 2022-01-19 | Helicopter ground proximity warning method for predicting escape trajectory based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114627687B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2248426A1 (en) * | 1997-12-16 | 1999-06-16 | University Of Guelph | Computational method for designing chemical structures having common functional characteristics |
CA2805925A1 (en) * | 2013-02-06 | 2014-08-06 | Jonathan K. Biley | Method and apparatus for removing seaweed from the ocean and beach |
CN105844972A (en) * | 2016-05-24 | 2016-08-10 | 南京航空航天大学 | Warning method for forward-looking terrain of helicopter |
CN106056979A (en) * | 2016-03-24 | 2016-10-26 | 南京航空航天大学 | Anti-collision alarm method suitable for helicopter |
CA3006131A1 (en) * | 2017-06-07 | 2018-12-07 | Ge Aviation Systems Llc | Optimizing aircraft control based on noise abatement volumes |
CN109901387A (en) * | 2017-12-11 | 2019-06-18 | 上海航空电器有限公司 | A kind of automatic near-earth anti-collision system Self-adaptive flight trajectory predictions method of aircraft |
US20190378423A1 (en) * | 2018-06-12 | 2019-12-12 | Skydio, Inc. | User interaction with an autonomous unmanned aerial vehicle |
CN111290426A (en) * | 2018-12-07 | 2020-06-16 | 上海航空电器有限公司 | Prediction control method for automatically avoiding escape path of aircraft |
CN112365743A (en) * | 2020-10-12 | 2021-02-12 | 中国民用航空总局第二研究所 | Method and device for correcting flight path positioning data offset of aircraft |
-
2022
- 2022-01-19 CN CN202210083861.5A patent/CN114627687B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2248426A1 (en) * | 1997-12-16 | 1999-06-16 | University Of Guelph | Computational method for designing chemical structures having common functional characteristics |
CA2805925A1 (en) * | 2013-02-06 | 2014-08-06 | Jonathan K. Biley | Method and apparatus for removing seaweed from the ocean and beach |
CN106056979A (en) * | 2016-03-24 | 2016-10-26 | 南京航空航天大学 | Anti-collision alarm method suitable for helicopter |
CN105844972A (en) * | 2016-05-24 | 2016-08-10 | 南京航空航天大学 | Warning method for forward-looking terrain of helicopter |
CA3006131A1 (en) * | 2017-06-07 | 2018-12-07 | Ge Aviation Systems Llc | Optimizing aircraft control based on noise abatement volumes |
CN109901387A (en) * | 2017-12-11 | 2019-06-18 | 上海航空电器有限公司 | A kind of automatic near-earth anti-collision system Self-adaptive flight trajectory predictions method of aircraft |
US20190378423A1 (en) * | 2018-06-12 | 2019-12-12 | Skydio, Inc. | User interaction with an autonomous unmanned aerial vehicle |
CN111290426A (en) * | 2018-12-07 | 2020-06-16 | 上海航空电器有限公司 | Prediction control method for automatically avoiding escape path of aircraft |
CN112365743A (en) * | 2020-10-12 | 2021-02-12 | 中国民用航空总局第二研究所 | Method and device for correcting flight path positioning data offset of aircraft |
Non-Patent Citations (2)
Title |
---|
吴其昌等: "基于深度神经网络的无限时域型航天器追逃策略求解", 《航天控制》 * |
罗艳春等: "基于神经网络的光电系统空中目标威胁估计", 《计算机测量与控制》 * |
Also Published As
Publication number | Publication date |
---|---|
CN114627687B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6905091B2 (en) | System and method for controlling the acoustic signature of a device | |
US5892462A (en) | Adaptive ground collision avoidance system | |
US8145366B1 (en) | Real-time, interactive sonic boom display | |
US8629787B1 (en) | System, module, and method for presenting clearance-dependent advisory information in an aircraft | |
EP3637058A1 (en) | Vision guidance systems and methods for aircraft | |
CN105844972A (en) | Warning method for forward-looking terrain of helicopter | |
CN106927056A (en) | The display of the meteorological data in aircraft | |
US20190043374A1 (en) | System and method for collision avoidance | |
CA2776609A1 (en) | System and method for improving viewability of primary flight display | |
CN112017481B (en) | Helicopter self-adaptive forward-looking warning method and device and helicopter | |
EP2037216B1 (en) | System and method for displaying a digital terrain | |
US10691139B1 (en) | Systems and methods for altitude capture performance monitor | |
Reynal et al. | Investigating pilot’s decision making when facing an unstabilized approach: an eye-tracking study | |
IL292000A (en) | Methods and systems for depicting avionics data anomalies | |
US7382287B1 (en) | Avionics system, method and apparatus for selecting a runway | |
CN114265068A (en) | Reactive wind shear false alarm suppression method fusing meteorological radar information | |
Kuchar | Safety analysis methodology for unmanned aerial vehicle (UAV) collision avoidance systems | |
CN105679104A (en) | Airborne forward-looking terrain predicting and warning method | |
CN114627687B (en) | Helicopter ground proximity warning method for predicting escape trajectory based on neural network | |
JPH08509061A (en) | In-Flight Doppler Weather Radar Windshire Detection System | |
Neuman et al. | Investigation of a digital automatic aircraft landing system in turbulence | |
CN114610078B (en) | Unmanned aerial vehicle air route conflict early warning method and system | |
Barfield et al. | All terrain ground collision avoidance and maneuvering terrain following for automated low level night attack | |
Keller et al. | Cognitive task analysis of commercial jet aircraft pilots during instrument approaches for baseline and synthetic vision displays | |
Zollitsch et al. | System health management for safe automatic take-off |
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 |