CN114660977A - Automatic control system and method for airplane, electronic equipment and readable storage medium - Google Patents
Automatic control system and method for airplane, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN114660977A CN114660977A CN202210567090.7A CN202210567090A CN114660977A CN 114660977 A CN114660977 A CN 114660977A CN 202210567090 A CN202210567090 A CN 202210567090A CN 114660977 A CN114660977 A CN 114660977A
- Authority
- CN
- China
- Prior art keywords
- airplane
- mode
- excitation
- network module
- control mode
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000005284 excitation Effects 0.000 claims abstract description 95
- 230000001629 suppression Effects 0.000 claims abstract description 71
- 230000009471 action Effects 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 35
- 230000005764 inhibitory process Effects 0.000 claims description 32
- 238000005070 sampling Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013461 design Methods 0.000 abstract description 4
- 230000033228 biological regulation Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 7
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000010355 oscillation Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0423—Input/output
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/25—Pc structure of the system
- G05B2219/25257—Microcontroller
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application belongs to the technical field of design of control or regulation systems of non-electrical variables, and relates to an automatic control system of an airplane, which comprises: excitation suppression balance network module, use the aircraft flight state of present moment as input, output aircraft control mode, wherein, aircraft control mode includes: an excited mode; a suppression mode in which a maneuvering operation for controlling the aircraft is maintained unchanged; and the maneuver decision network module outputs maneuver actions for controlling the airplane by taking the airplane flight state at the current moment as input when the airplane control mode is the excitation mode. And relates to an automatic control method of the airplane, which can be implemented by the automatic control system of the airplane. Furthermore, the invention relates to an electronic device and a computer-readable storage medium thereof, which when operated can implement the above-mentioned aircraft automatic control method.
Description
Technical Field
The application belongs to the technical field of design of control or regulation systems of non-electric variables, and particularly relates to an automatic control system and method for an airplane, electronic equipment and a readable storage medium.
Background
The automatic control system of the airplane can realize automatic piloting of the airplane, but the current automatic control system of the airplane has the following defects:
1) performing maneuver decision making at fixed time intervals, outputting maneuver for controlling the airplane, namely performing the maneuver decision making only in set time, and outputting maneuver for controlling the airplane, wherein the maneuver decision making cannot be immediately made when an emergency occurs between the set time, and the corresponding maneuver is output to control the airplane, so that the airplane is in danger of automatic driving;
2) when the decision time interval of the airplane maneuvering action is set to be short, high-frequency output controls the maneuvering action of the airplane, decision oscillation is easily induced, and danger is caused.
The present application has been made in view of the above-mentioned technical drawbacks.
It should be noted that the above background disclosure is only for the purpose of assisting understanding of the inventive concept and technical solutions of the present invention, and does not necessarily belong to the prior art of the present patent application, and the above background disclosure should not be used for evaluating the novelty and inventive step of the present application without explicit evidence to suggest that the above content is already disclosed at the filing date of the present application.
Disclosure of Invention
It is an object of the present application to provide an aircraft automatic control system, method, electronic device and readable storage medium to overcome or alleviate at least one of the known technical deficiencies.
The technical scheme of the application is as follows:
one aspect provides an aircraft automatic control system comprising:
excitation suppression balance network module, use the aircraft flight state of present moment as input, output aircraft control mode, wherein, aircraft control mode includes:
an excited mode;
a suppression mode in which a maneuvering operation for controlling the aircraft is maintained unchanged;
and the maneuver decision network module outputs maneuver actions for controlling the airplane by taking the airplane flight state at the current moment as input when the airplane control mode is the excitation mode.
Optionally, in the automatic aircraft control system, the excitation suppression balance network module outputs an aircraft control mode by taking a current aircraft flight state as an input, specifically:
taking the flight state of the airplane at the current moment as input, obtaining the probability that the airplane control mode is the excitation mode, sampling Bernoulli distribution with the parameter of the probability, if the sampling result is 1, outputting the airplane control mode as the excitation mode, and if the sampling result is 0, outputting the airplane control mode as the inhibition mode; or,
the method comprises the steps of taking the flight state of an airplane at the current moment as input, obtaining the probability that the airplane control mode is the suppression mode, sampling Bernoulli distribution with the parameter of the probability, outputting the airplane control mode as the suppression mode if the sampling result is 1, and outputting the airplane control mode as the excitation mode if the sampling result is 0.
Optionally, the above automatic aircraft control system further includes:
the inhibition control mode timing module is used for configuring the sustainable time when the airplane control mode is the inhibition mode, recording the sustainable time when the airplane control mode is the inhibition mode, and when the sustainable time when the airplane control mode is the inhibition mode reaches the sustainable time, the excitation inhibition balance network module outputs the airplane control mode as the excitation mode.
Optionally, the above automatic aircraft control system further includes:
the value network training module is used for training the excitation suppression balance network module and the maneuver decision network module and comprises:
the excitation suppression balance network module takes the flight state of the airplane at the current moment as input and outputs the airplane control mode;
when the airplane control mode is the inhibition mode, the maneuvering action for controlling the airplane is maintained unchanged, and the airplane flying state at the next moment is obtained;
when the airplane control mode is an excitation mode, the maneuver decision network module takes the airplane flight state as input and outputs maneuver actions for controlling the airplane to obtain the airplane flight state at the next moment;
calculating the value of the flight state of the airplane at the current moment and the value of the flight state of the airplane at the next moment;
and updating parameters of the excitation suppression balance network module, the maneuver decision network module and the value network training module based on the value of the airplane flight state at the current moment and the value of the airplane flight state at the next moment until the maximum iteration number is reached.
Optionally, in the above automatic aircraft control system, the value network training module trains an excitation suppression balance network module and a maneuver decision network module, and the excitation suppression balance network module takes the flight state of the aircraft at the current time as an input and outputs an aircraft control mode, specifically:
the excitation suppression balance network module takes the flight state of the airplane at the current moment as input, obtains probability that the airplane control mode is the excitation mode, samples Bernoulli distribution with the parameter of the probability, outputs the airplane control mode as the excitation mode if the sampling result is 1, and outputs the airplane control mode as the suppression mode if the sampling result is 0.
Optionally, in the above automatic aircraft control system, the value network training module trains the excitation suppression balance network module and the maneuver decision network module, and updates parameters of the excitation suppression balance network module, the maneuver decision network module and the value network training module based on a value of a current flight state of the aircraft and a value of a next flight state of the aircraft, specifically:
A=A0-lrA( R+V2-V1)*P；
B=B0+lrB(R+V2-V1)*log(Pi)；
C=C0-lrC (R+V2-V1) (R+V2-V1)；
wherein,
a is the parameter updated by the excitation suppression balance network module;
a0 is a parameter of the excitation suppression balance network module at the current moment;
lrA is the learning rate of the excitement-suppression balance network module;
r is the real-time reward for controlling the maneuvering action of the airplane corresponding to the flying state of the airplane at the next moment;
v2 is the value of the flight state of the airplane at the next moment;
v1 is the value of the flight state of the airplane at the current moment;
p is the probability that the excitation suppression balance network module takes the flight state of the airplane at the current moment as input to obtain the airplane control mode as the excitation mode;
b is the updated parameter of the maneuver decision network module;
b0 is the parameter of the maneuver decision network module at the current moment;
lrB is the learning rate of the maneuver decision network module;
pi is when the airplane control mode is the excitation mode, the maneuver decision network module takes the airplane flight state as input, and outputs the probability of controlling the maneuver action of the airplane;
c is a parameter updated by the value network training module;
c0 is the parameter of the value network training module at the current moment;
lrC is the learning rate of the value network module.
Optionally, in the above automatic aircraft control system, the value network training module trains the excitation suppression balance network module and the maneuver decision network module, and further includes:
when the duration of the suppression control mode timing module recording that the airplane control mode is the suppression mode reaches the sustainable time, the excitation suppression balance network module outputs that the airplane control mode is the excitation mode.
Optionally, in the automatic control system for an aircraft, a fully-connected neural network is adopted in the excitation suppression balance network module, the maneuver decision network module and the value network training module.
In another aspect, an aircraft automatic control method is provided, including:
the flight state of the airplane at the current moment is used as input, and the airplane control mode is output, wherein the airplane control mode comprises the following steps:
an excited mode;
a suppression mode in which a maneuvering operation for controlling the aircraft is maintained unchanged;
and when the airplane control mode is the excitation mode, outputting the maneuvering action for controlling the airplane by taking the airplane flight state at the current moment as input.
Yet another aspect provides an electronic device comprising:
a processor;
a memory storing a computer program configured to enable the aircraft automatic control method described above when executed by the processor.
Yet another aspect provides a computer-readable storage medium storing a computer program which, when executed by a processor, is capable of implementing the aircraft automatic control method described above.
The application has at least the following beneficial technical effects:
on one hand, the automatic control system of the airplane is provided, which can be accessed to a flight control system, obtains data from the flight control system, obtains the flight state of the airplane at the current moment, outputs the airplane control mode as an excitation mode when judging that an emergency situation is met or a more valuable maneuver decision can be obtained by an excitation suppression balance network module, outputs the maneuver for controlling the airplane by a maneuver decision network module, transmits the maneuver for controlling the airplane to the flight control system, realizes automatic driving of the airplane, avoids danger caused by the maneuver decision at a fixed time interval, outputs the airplane control mode as a suppression mode when judging that a non-emergency situation is met and the more valuable maneuver decision cannot be obtained by the excitation suppression balance network module, and maintains the maneuver for controlling the airplane unchanged, thereby avoiding causing decision oscillations, which cause danger.
On the other hand, an automatic control method for an airplane is provided, which is implemented by the automatic control system for an airplane, and the technical effects of the automatic control method for an airplane can refer to the technical effects of relevant parts of the automatic control system for an airplane, and are not described herein again.
In addition, an electronic device and a computer-readable storage medium are provided, which can implement the above-mentioned method for automatically controlling an aircraft during operation, and the technical effects of the relevant portions of the automatic aircraft control system can also be referred to, which are not described herein again.
Drawings
Fig. 1 is a schematic diagram of an aircraft automatic control system provided in an embodiment of the present application.
Detailed Description
In order to make the technical solutions and advantages of the present application clearer, the technical solutions of the present application will be further clearly and completely described in the following detailed description with reference to the accompanying drawings, and it should be understood that the specific embodiments described herein are only some of the embodiments of the present application, and are only used for explaining the present application, but not limiting the present application. It should be noted that, for convenience of description, only the parts related to the present application are shown in the drawings, other related parts may refer to general designs, and the embodiments and technical features in the embodiments in the present application may be combined with each other to obtain a new embodiment without conflict.
In addition, unless otherwise defined, technical or scientific terms used in the description of the present application shall have the ordinary meaning as understood by one of ordinary skill in the art to which the present application belongs. The terms "upper", "lower", "left", "right", "center", "vertical", "horizontal", "inner", "outer", and the like used in the description of the present application, which indicate orientations, are used only to indicate relative directions or positional relationships, and do not imply that the devices or elements must have a specific orientation, be constructed and operated in a specific orientation, and when the absolute position of the object to be described is changed, the relative positional relationships may be changed accordingly, and thus, should not be construed as limiting the present application. The use of "first," "second," "third," and the like in the description of the present application is for descriptive purposes only to distinguish between different components and is not to be construed as indicating or implying relative importance. The use of the terms "a," "an," or "the" and similar referents in the context of describing the application is not to be construed as an absolute limitation on the number, but rather as the presence of at least one. The word "comprising" or "comprises", and the like, when used in this description, is intended to specify the presence of stated elements or items, but not the exclusion of other elements or items.
Further, it is noted that, unless expressly stated or limited otherwise, the terms "mounted," "connected," and the like are used in the description of the invention in a generic sense, e.g., connected as either a fixed connection or a removable connection or integrally connected; can be mechanically or electrically connected; they may be directly connected or indirectly connected through an intermediate medium, or they may be connected through the inside of two elements, and those skilled in the art can understand their specific meaning in this application according to the specific situation.
The present application is described in further detail below with reference to fig. 1.
An aircraft automation control system comprising:
excitation suppression balance network module, use the aircraft flight state of present moment as input, output aircraft control mode, wherein, aircraft control mode includes:
an excited mode;
a suppression mode in which a maneuvering operation for controlling the aircraft is maintained unchanged;
and the maneuvering decision network module takes the flight state of the airplane at the current moment as input and outputs maneuvering actions for controlling the airplane when the airplane control mode is the excitation mode.
The automatic control system of the airplane disclosed in the above embodiment can be accessed to a flight control system, data is acquired from the flight control system, the flight state of the airplane at the current moment is obtained, when the excitement and suppression balance network module judges that an emergency situation is met or a more valuable maneuver decision can be obtained, the control mode of the airplane is output as an excitement mode, the maneuver for controlling the airplane is output by the maneuver decision network module, the maneuver for controlling the airplane is transmitted to the flight control system, the automatic driving of the airplane is realized, the danger caused by the maneuver decision at a fixed time interval is avoided, when the excitement and suppression balance network module judges that a non-emergency situation is met and the more valuable maneuver decision cannot be obtained, the control mode of the airplane is output as a suppression mode, the maneuver for controlling the airplane is maintained unchanged, so as to avoid causing decision oscillation, causing a hazard.
In some optional embodiments, in the above automatic aircraft control system, the excitation suppression balance network module takes a current flight state of the aircraft as an input, and outputs an aircraft control mode, specifically:
taking the flight state of the airplane at the current moment as input, obtaining the probability that the airplane control mode is the excitation mode, sampling Bernoulli distribution with the parameter of the probability, if the sampling result is 1, outputting the airplane control mode as the excitation mode, and if the sampling result is 0, outputting the airplane control mode as the inhibition mode; or,
the method comprises the steps of taking the flight state of an airplane at the current moment as input, obtaining the probability that the airplane control mode is the suppression mode, sampling Bernoulli distribution with the parameter of the probability, outputting the airplane control mode as the suppression mode if the sampling result is 1, and outputting the airplane control mode as the excitation mode if the sampling result is 0.
In some optional embodiments, the above automatic aircraft control system further includes:
the inhibition control mode timing module is used for configuring the sustainable time of the airplane control mode as the inhibition mode, recording the sustainable time of the airplane control mode as the inhibition mode, outputting the airplane control mode as the excitation mode by the excitation inhibition balance network module when the sustainable time of the airplane control mode as the inhibition mode reaches the sustainable time, namely, forcibly switching the airplane control mode output by the excitation inhibition balance network module to the excitation mode when the sustainable time of the airplane control mode as the inhibition mode reaches the sustainable time, so as to avoid the unpredictable danger caused by the long-term inhibition mode of the airplane control mode.
In some optional embodiments, the above automatic aircraft control system further includes:
the value network training module is used for training the excitation suppression balance network module and the maneuver decision network module and comprises:
the excitation suppression balance network module takes the flight state of the airplane at the current moment as input and outputs the airplane control mode;
when the airplane control mode is the inhibition mode, the maneuvering action for controlling the airplane is maintained unchanged, and the airplane flying state at the next moment is obtained;
when the airplane control mode is an excitation mode, the maneuver decision network module takes the airplane flight state as input and outputs maneuver actions for controlling the airplane to obtain the airplane flight state at the next moment;
calculating the value of the flight state of the airplane at the current moment and the value of the flight state of the airplane at the next moment;
and updating parameters of the excitation suppression balance network module, the maneuver decision network module and the value network training module based on the value of the airplane flight state at the current moment and the value of the airplane flight state at the next moment until the maximum iteration number is reached.
As for the automatic aircraft control system disclosed in the above embodiments, those skilled in the art can understand that the value network training module is provided to train the excitation-suppression balance network module and the maneuver decision network module just before the automatic aircraft control system is applied, and update the relevant parameters, so that when the automatic aircraft control system is applied, it can be effectively ensured that the excitation-suppression balance network module outputs the aircraft control mode as the excitation mode and the maneuver decision network module outputs the maneuver for controlling the aircraft when an emergency situation occurs or a more valuable maneuver decision can be obtained, and when a non-emergency situation occurs and a more valuable maneuver decision cannot be obtained, the excitation-suppression balance network module outputs the aircraft control mode as the suppression mode to maintain the maneuver for controlling the aircraft unchanged, in the training process, data interaction can be carried out with the airplane simulation system, the airplane flight state can be obtained by acquiring related data from the airplane simulation system, and maneuvering actions for controlling the airplane are transmitted to the airplane simulation system.
In some optional embodiments, in the above automatic aircraft control system, in the value network training module, the excitation suppression balance network module and the maneuver decision network module are trained, and the excitation suppression balance network module takes the flight state of the aircraft at the current time as an input and outputs an aircraft control mode, specifically:
the excitation suppression balance network module takes the flight state of the airplane at the current moment as input, obtains probability that the airplane control mode is the excitation mode, samples Bernoulli distribution with the parameter of the probability, outputs the airplane control mode as the excitation mode if the sampling result is 1, and outputs the airplane control mode as the suppression mode if the sampling result is 0.
In some optional embodiments, in the above automatic aircraft control system, in the value network training module, the excitation suppression balance network module and the maneuver decision network module are trained, and based on the value of the aircraft flight state at the current time and the value of the aircraft flight state at the next time, parameters of the excitation suppression balance network module, the maneuver decision network module and the value network training module are updated, specifically:
A=A0-lrA( R+V2-V1)*P；
B=B0+lrB(R+V2-V1)*log(Pi)；
C=C0-lrC (R+V2-V1) (R+V2-V1)；
wherein,
a is the parameter updated by the excitation suppression balance network module;
a0 is a parameter of the excitation suppression balance network module at the current moment;
lrA is the learning rate of the excitement-suppression balance network module;
r is the real-time reward for controlling the maneuvering action of the airplane corresponding to the flying state of the airplane at the next moment;
v2 is the value of the flight state of the airplane at the next moment;
v1 is the value of the flight state of the airplane at the current moment;
p is the probability that the excitation suppression balance network module takes the flight state of the airplane at the current moment as input to obtain the airplane control mode as the excitation mode;
b is the updated parameter of the maneuver decision network module;
b0 is the parameter of the maneuver decision network module at the current moment;
lrB is the learning rate of the maneuver decision network module;
pi is when the airplane control mode is the excitation mode, the maneuver decision network module takes the airplane flight state as input, and outputs the probability of controlling the maneuver action of the airplane;
c is a parameter updated by the value network training module;
c0 is the parameter of the value network training module at the current moment;
lrC is the learning rate of the value network module.
In some optional embodiments, in the above automatic aircraft control system, the value network training module trains the excitation suppression balance network module and the maneuver decision network module, and further includes:
when the duration of the airplane control mode which is recorded as the inhibition mode by the inhibition control mode timing module reaches the sustainable time, the excitation inhibition balance network module outputs the airplane control mode as the excitation mode, so that the excitation inhibition balance network module outputs the airplane control mode as the inhibition mode for a long time during training.
In some optional embodiments, in the automatic aircraft control system, a fully-connected neural network is used in the excitation suppression balance network module, the maneuver decision network module and the value network training module, and a deep reinforcement learning method with a gradient descent is used in the training process.
Furthermore, those skilled in the art will appreciate that the various modules of the aircraft automatic control system disclosed in the embodiments of the present application can be implemented in electronic hardware, computer software, or a combination of both, and for the purpose of clearly illustrating the interchangeability of hardware and software, the functions described herein are generally described in terms of whether they are implemented in hardware or software, and that depending on the particular application and design constraints imposed on the technical solution, those skilled in the art will be able to select different methods for implementing the described functions for each particular application and its actual constraints, but such implementation should not be considered to be outside the scope of the present application.
In another aspect, an automatic control method for an aircraft is provided, including:
the flight state of the airplane at the current moment is used as input, and the airplane control mode is output, wherein the airplane control mode comprises the following steps:
an excited mode;
a suppression mode in which a maneuvering operation for controlling the aircraft is maintained;
and when the airplane control mode is the excitation mode, the airplane flight state at the current moment is taken as input, and the maneuvering action for controlling the airplane is output.
For the aircraft automatic control method disclosed in the above embodiment, the description is simpler when implemented by the aircraft automatic control system disclosed in the above embodiment, specific relevant points can be referred to the relevant description of the aircraft automatic control system part, and the technical effects can also be referred to the technical effects of the relevant parts of the aircraft automatic control system, which are not described herein again.
Yet another aspect provides an electronic device comprising:
a processor;
a memory storing a computer program configured to enable the aircraft automatic control method described above when executed by the processor.
In some alternative embodiments, the processor may be a central processing unit CPU or other form of processing unit having data processing capabilities and/or instruction execution capabilities, may be a general purpose processor or a special purpose processor, and may control other components in the compensation electronics to perform desired functions.
In some alternative embodiments, the memory may include various forms of computer-readable storage media, such as volatile memory, which may be random access memory, RAM, and/or cache memory, and/or non-volatile memory, which may be read-only memory, ROM, a hard disk, flash memory, and so forth. The memory may store thereon a computer program that is executed by the processor to implement the functions of the embodiments of the present application and/or other desired functions, and may store various application programs and various data.
In alternative embodiments, the processor and memory may be connected by a bus system, which may be a serial, parallel communication bus, or the like.
It should be noted that, for clarity and conciseness of representation, not all the components of the electronic device are shown in the foregoing embodiments, and in order to implement the necessary functions of the electronic device, a person skilled in the art may provide and set other components not shown according to specific needs.
For the electronic device disclosed in the above embodiment, since the processor thereof can implement the above automatic control method for the airplane when executing the computer program stored in the memory thereof, the technical effects of the above automatic control system for the airplane can be referred to accordingly, and are not described herein again.
Yet another aspect provides a computer-readable storage medium storing a computer program which, when executed by a processor, is capable of implementing the aircraft automatic control method described above.
In some alternative embodiments, the computer-readable storage medium may include a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a random access memory RAM, a read only memory ROM, an erasable programmable read only memory EPROM, a portable compact disc read only memory CD-ROM, a flash memory, or any combination of the above, as well as other suitable storage media.
The embodiments are described in a progressive mode in the specification, the emphasis of each embodiment is on the difference from the other embodiments, and the same and similar parts among the embodiments can be referred to each other.
Having thus described the present application in connection with the preferred embodiments illustrated in the accompanying drawings, it will be understood by those skilled in the art that the scope of the present application is not limited to those specific embodiments, and that equivalent modifications or substitutions of related technical features may be made by those skilled in the art without departing from the principle of the present application, and those modifications or substitutions will fall within the scope of the present application.
Claims (10)
1. An aircraft automatic control system, comprising:
excitation suppression balance network module, use the aircraft flight state of present moment as input, output aircraft control mode, wherein, aircraft control mode includes:
an excited mode;
a suppression mode in which a maneuvering operation for controlling the aircraft is maintained;
and the maneuvering decision network module takes the flight state of the airplane at the current moment as input and outputs maneuvering actions for controlling the airplane when the airplane control mode is the excitation mode.
2. An automatic aircraft control system according to claim 1,
in the excitation suppression balance network module, the flight state of the airplane at the current moment is used as input, and the control mode of the airplane is output, specifically:
taking the flight state of the airplane at the current moment as input, obtaining the probability that the airplane control mode is the excitation mode, sampling Bernoulli distribution with the parameter of the probability, if the sampling result is 1, outputting the airplane control mode as the excitation mode, and if the sampling result is 0, outputting the airplane control mode as the inhibition mode; or,
the method comprises the steps of taking the flight state of an airplane at the current moment as input, obtaining the probability that the airplane control mode is the suppression mode, sampling Bernoulli distribution with the parameter of the probability, outputting the airplane control mode as the suppression mode if the sampling result is 1, and outputting the airplane control mode as the excitation mode if the sampling result is 0.
3. An automatic aircraft control system according to claim 1,
further comprising:
the inhibition control mode timing module is used for configuring the sustainable time when the airplane control mode is the inhibition mode, recording the sustainable time when the airplane control mode is the inhibition mode, and when the sustainable time when the airplane control mode is the inhibition mode reaches the sustainable time, the excitation inhibition balance network module outputs the airplane control mode as the excitation mode.
4. An automatic aircraft control system according to claim 1,
further comprising:
the value network training module is used for training the excitation suppression balance network module and the maneuver decision network module and comprises:
the excitation suppression balance network module takes the flight state of the airplane at the current moment as input and outputs the airplane control mode;
when the airplane control mode is the inhibition mode, the maneuvering action for controlling the airplane is maintained unchanged, and the airplane flying state at the next moment is obtained;
when the airplane control mode is an excitation mode, the maneuver decision network module takes the airplane flight state as input and outputs maneuver actions for controlling the airplane to obtain the airplane flight state at the next moment;
calculating the value of the flight state of the airplane at the current moment and the value of the flight state of the airplane at the next moment;
and updating parameters of the excitation suppression balance network module, the maneuver decision network module and the value network training module based on the value of the airplane flight state at the current moment and the value of the airplane flight state at the next moment until the maximum iteration number is reached.
5. An automatic aircraft control system according to claim 4,
in the value network training module, an excitation suppression balance network module and a maneuver decision network module are trained, and the excitation suppression balance network module takes the flight state of the airplane at the current moment as input and outputs an airplane control mode, which specifically comprises the following steps:
the excitation suppression balance network module takes the flight state of the airplane at the current moment as input, obtains probability that the airplane control mode is the excitation mode, samples Bernoulli distribution with the parameter of the probability, outputs the airplane control mode as the excitation mode if the sampling result is 1, and outputs the airplane control mode as the suppression mode if the sampling result is 0.
6. An automatic aircraft control system according to claim 5,
in the value network training module, the excitation suppression balance network module and the maneuver decision network module are trained, and parameters of the excitation suppression balance network module, the maneuver decision network module and the value network training module are updated based on the value of the flight state of the airplane at the current moment and the value of the flight state of the airplane at the next moment, specifically:
A=A0-lrA( R+V2-V1)*P；
B=B0+lrB(R+V2-V1)*log(Pi)；
C=C0-lrC (R+V2-V1) (R+V2-V1)；
wherein,
a is the parameter updated by the excitation suppression balance network module;
a0 is a parameter of the excitation suppression balance network module at the current moment;
lrA is the learning rate of the excitement-suppression balance network module;
r is the real-time reward for controlling the maneuvering action of the airplane corresponding to the flying state of the airplane at the next moment;
v2 is the value of the flight state of the airplane at the next moment;
v1 is the value of the flight state of the airplane at the current moment;
p is the probability that the excitation suppression balance network module takes the flight state of the airplane at the current moment as input to obtain the airplane control mode as the excitation mode;
b is the updated parameter of the maneuver decision network module;
b0 is the parameter of the maneuver decision network module at the current moment;
lrB is the mobility decision network module learning rate;
pi is when the airplane control mode is the excitation mode, the maneuver decision network module takes the airplane flight state as input, and outputs the probability of controlling the maneuver action of the airplane;
c is a parameter updated by the value network training module;
c0 is the parameter of the value network training module at the current moment;
lrC is the learning rate of the value network training module.
7. An automatic aircraft control system according to claim 4,
in the value network training module, training the excitation suppression balance network module and the maneuver decision network module further comprises:
and when the duration of the airplane control mode which is recorded as the inhibition mode by the inhibition control mode timing module reaches the sustainable time, the excitation inhibition balance network module outputs the airplane control mode as the excitation mode.
8. An aircraft automatic control method, characterized by comprising:
the flight state of the airplane at the current moment is used as input, and the airplane control mode is output, wherein the airplane control mode comprises the following steps:
an excited mode;
a suppression mode in which a maneuvering operation for controlling the aircraft is maintained unchanged;
and when the airplane control mode is the excitation mode, outputting the maneuvering action for controlling the airplane by taking the airplane flight state at the current moment as input.
9. An electronic device, comprising:
a processor;
a memory storing a computer program configured to enable the aircraft automatic control method of claim 8 when executed by the processor.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, is capable of implementing the aircraft automatic control method according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210567090.7A CN114660977B (en) | 2022-05-24 | 2022-05-24 | Automatic control system and method for airplane, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210567090.7A CN114660977B (en) | 2022-05-24 | 2022-05-24 | Automatic control system and method for airplane, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114660977A true CN114660977A (en) | 2022-06-24 |
| CN114660977B CN114660977B (en) | 2022-08-23 |
Family
ID=82036527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210567090.7A Active CN114660977B (en) | 2022-05-24 | 2022-05-24 | Automatic control system and method for airplane, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114660977B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6882992B1 (en) * | 1999-09-02 | 2005-04-19 | Paul J. Werbos | Neural networks for intelligent control |
| CN112198890A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Aircraft attitude control method, system and device based on reinforcement learning |
| US20210103860A1 (en) * | 2019-10-03 | 2021-04-08 | The Boeing Company | Systems And Methods For Optimizing Energy Loading In Airline Operations |
| CN112633361A (en) * | 2020-12-20 | 2021-04-09 | 中国人民解放军空军预警学院 | Flight emergency prediction method and device based on LSTM neural network |
| WO2021069309A1 (en) * | 2019-10-10 | 2021-04-15 | Telefonaktiebolaget Lm Ericsson (Publ) | Reinforcement learning systems for controlling wireless communication networks |
| CN112819253A (en) * | 2021-03-02 | 2021-05-18 | 华东师范大学 | Unmanned aerial vehicle obstacle avoidance and path planning device and method |
| CN113110546A (en) * | 2021-04-20 | 2021-07-13 | 南京大学 | Unmanned aerial vehicle autonomous flight control method based on offline reinforcement learning |
-
2022
- 2022-05-24 CN CN202210567090.7A patent/CN114660977B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6882992B1 (en) * | 1999-09-02 | 2005-04-19 | Paul J. Werbos | Neural networks for intelligent control |
| US20210103860A1 (en) * | 2019-10-03 | 2021-04-08 | The Boeing Company | Systems And Methods For Optimizing Energy Loading In Airline Operations |
| WO2021069309A1 (en) * | 2019-10-10 | 2021-04-15 | Telefonaktiebolaget Lm Ericsson (Publ) | Reinforcement learning systems for controlling wireless communication networks |
| CN112198890A (en) * | 2020-12-03 | 2021-01-08 | 中国科学院自动化研究所 | Aircraft attitude control method, system and device based on reinforcement learning |
| CN112633361A (en) * | 2020-12-20 | 2021-04-09 | 中国人民解放军空军预警学院 | Flight emergency prediction method and device based on LSTM neural network |
| CN112819253A (en) * | 2021-03-02 | 2021-05-18 | 华东师范大学 | Unmanned aerial vehicle obstacle avoidance and path planning device and method |
| CN113110546A (en) * | 2021-04-20 | 2021-07-13 | 南京大学 | Unmanned aerial vehicle autonomous flight control method based on offline reinforcement learning |
Non-Patent Citations (1)
| Title |
|---|
| 王盼盼: "基于经验直觉的无人机威胁规避机动决策方法", 《南京汗孔航天大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114660977B (en) | 2022-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11521056B2 (en) | System and methods for intrinsic reward reinforcement learning | |
| US11631400B2 (en) | Electronic apparatus and controlling method thereof | |
| US20190156197A1 (en) | Method for adaptive exploration to accelerate deep reinforcement learning | |
| WO2019131527A1 (en) | Method for generating universal learned model | |
| EP3647936B1 (en) | Electronic apparatus and control method thereof | |
| CN108735208B (en) | Electronic device for providing voice recognition service and method thereof | |
| CN110232910A (en) | Dialect and language identification for the speech detection in vehicle | |
| CN107194151B (en) | Method for determining emotion threshold value and artificial intelligence equipment | |
| CN110634539A (en) | Artificial intelligence-based drug molecule processing method and device and storage medium | |
| CN112904852B (en) | Automatic driving control method and device and electronic equipment | |
| KR20190018886A (en) | Method for performing voice recognition and electronic device using the same | |
| WO2016035070A2 (en) | Social networking and matching communication platform and methods thereof | |
| CN115755564A (en) | Alarm clock control method based on sleep stage prediction, radar and storage medium | |
| CN114660977B (en) | Automatic control system and method for airplane, electronic equipment and readable storage medium | |
| KR20200054360A (en) | Electronic apparatus and control method thereof | |
| WO2020050067A1 (en) | Physiological information processing apparatus, physiological information processing method, program and storage medium | |
| CN116821684B (en) | Training method, device, equipment and medium for large language model | |
| Standage et al. | Toward a unified view of the speed-accuracy trade-off | |
| KR20230111126A (en) | A technique for identifying a dementia based on mixed tests | |
| US20220319662A1 (en) | Rehabilitation work support apparatus, rehabilitation work support system, rehabilitation work support method, and computer readable medium | |
| CN113742457A (en) | Response processing method and device, electronic equipment and storage medium | |
| CN115862031B (en) | Text processing method, neural network training method, device and equipment | |
| WO2014193944A4 (en) | Semantic database platform | |
| CN106415651B (en) | Framework and method configured to facilitate configuration of devices supported by building management systems | |
| KR20210001864A (en) | Electronic apparatus and control method thereof |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yang Chengqi Inventor after: Pu Haiyin Inventor after: Sun Yang Inventor after: Yu Jin Inventor after: Zhan Guang Inventor after: Yu Xiaoqiang Inventor after: Feng Yongming Inventor before: Yang Chengqi Inventor before: Yu Jin Inventor before: Zhan Guang |