CN108304625B - Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer - Google Patents

Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer Download PDF

Info

Publication number
CN108304625B
CN108304625B CN201810036980.9A CN201810036980A CN108304625B CN 108304625 B CN108304625 B CN 108304625B CN 201810036980 A CN201810036980 A CN 201810036980A CN 108304625 B CN108304625 B CN 108304625B
Authority
CN
China
Prior art keywords
genetic programming
vector
component
target
genetic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810036980.9A
Other languages
Chinese (zh)
Other versions
CN108304625A (en
Inventor
董云峰
李培昀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Original Assignee
Beihang University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beihang University filed Critical Beihang University
Priority to CN201810036980.9A priority Critical patent/CN108304625B/en
Publication of CN108304625A publication Critical patent/CN108304625A/en
Application granted granted Critical
Publication of CN108304625B publication Critical patent/CN108304625B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Computational Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • General Factory Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a genetic programming decision method for writing a digital aircraft code by an artificial intelligence programmer, which particularly comprises the steps of determining and storing a target sample component input instruction vector, a component internal state vector and a component output physical quantity vector of each component in a digital aircraft, converting the target sample component input instruction vector, the component internal state vector and the component output physical quantity vector into a genetic programming input vector and a genetic programming target output vector, carrying out genetic programming operation, optimizing a model function of each component according to an adaptive value, reasonably finishing the genetic programming decision of a digital aircraft source code, realizing automation and intellectualization of writing of the digital aircraft source code, and reducing the simulation cost of the aircraft.

Description

Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer
Technical Field
The invention relates to the field of aircraft design, in particular to a genetic programming decision method for an artificial intelligence programmer to write a digital aircraft code.
Background
In the design and development process of the aircraft, in order to ensure high reliability of the final application of the aircraft, a large number of mainstream methods of the existing design need to be adopted in the design, and simulation verification and ground test need to be carried out. Some of these ground tests are not completely reflective of the actual in-orbit behavior of the aircraft and are costly and therefore limited.
The simulation verification method of the digital aircraft has no limitation of environmental conditions, and the working condition of the aircraft can be well simulated as long as the model is established accurately enough, so that the simulation verification method is widely applied to aircraft design, and aircraft numerical simulation is already used for verification of the aircraft design.
In the process of building the digital aircraft, a large amount of source codes need to be written, and the workload is large. Currently, people are basically relied on to complete the decision of a series of problems in source code. The manual code writing is time-consuming and labor-consuming, the manual intelligence is used for replacing the manual writing of the digital aircraft source code, the source code of the aircraft simulation model can be written automatically according to the specific design condition of the aircraft, the selection of the modules in the model is decided, and the manual writing of the heavy digital aircraft source code is released.
Genetic programming is a machine learning technology utilizing an evolutionary algorithm, is simple and universal, has strong robustness, has strong solving capability on nonlinear complex problems, and is successfully applied to many fields. The genetic programming can make a set formed by a series of initial programs continuously evolve through the genetic operations of copying, crossing, mutation and the like according to the input and output samples and the principle of selecting the superior or the inferior of the function, and finally, the program which is closest to the input and output samples is written.
Therefore, how to provide a genetic programming decision method using artificial intelligence to write digital aircraft codes autonomously is a problem that needs to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a genetic programming decision method for an artificial intelligence programmer to write a digital aircraft code, which overcomes the defects of the prior art, writes a digital aircraft source code by using an artificial intelligence substitute person, and can perform autonomous decision according to a solution of a problem obtained by genetic programming, the writing efficiency is improved, and the aircraft simulation cost is reduced.
In order to achieve the purpose, the invention adopts the following technical scheme:
a genetic programming decision method for an artificial intelligence programmer to write digital aircraft code, the method comprising the steps of:
collecting N target samples of a component in the digital aircraft, wherein one target sample comprises a component input instruction vector R, a component internal state vector S and a component output physical quantity vector Q; writing the ID of the target sample and the R vector, the S vector and the Q vector of the target sample into a line and storing the line into a table corresponding to the component name in a database, wherein N target samples are stored in the table corresponding to the component name;
Step two, converting the component input instruction vectors R, the component internal state vectors S and the component output physical quantity vectors Q of the N target samples in the step one into N genetic programming input vectors I and genetic programming target output vectors A, wherein I and A correspond to each other one by one;
step three, taking N combinations formed by the genetic programming input vector I and the genetic programming target output vector A and a required function set as the input of genetic programming operation, and performing the genetic programming operation to obtain M candidate programs;
and step four, preferably selecting the target program P from the M candidate programs according to the fitness, and taking the target program P as a model function of the corresponding part when the genetic programming termination condition is met.
Preferably, in the above method for genetic programming decision making by an artificial intelligence programmer for writing digital aircraft code, the second step specifically comprises,
genetic programming input vector I of target sample IiInputting an instruction vector R by a component of target samples iiComponent internal state vector S of target sample iiCombined with the simulation step length delta T, memory Si+ΔTIs SiComponent internal state vectors after a time of Δ T; genetically programmed target output vector A of target sample iiOutputting a physical quantity vector Q by a component of a target sample i iAnd Si+ΔTAnd (3) combining the components.
Preferably, in the above method for genetic programming decision making by an artificial intelligence programmer for writing digital aircraft code, in step three, the genetic programming operation includes the following procedures:
(1) generating an initial population, wherein one individual in the initial population is an object program, and the initial population is a set formed by the object programs for genetic programming and is a starting point of the genetic programming;
(2) carrying out genetic operation to generate new individuals, and adding the new individuals into the population;
(3) evaluating the fitness value e of each individual in the population;
(4) adding 1 to the genetic algebra;
(5) and judging whether the termination criterion is met, if so, terminating the genetic programming operation and outputting the target program P with the lowest current fitness value e.
The above processes are circularly carried out until the program exits and the target program P is output after the termination criterion is met.
Preferably, the genetic programming decision of the digital aircraft code is written by the artificial intelligence programmerIn the method, the termination criterion in step three is: the fitness e of the program reaches a specified value, or reaches the maximum genetic algebra GmaxThe genetic programming operation is terminated.
Preferably, in the above genetic programming decision method for the artificial intelligence programmer to write the digital aircraft code, the fitness of the program in the third step is evaluated by the following steps:
(1) Inputting all N genetic programming input vectors I in the second stepiSequentially inputting a program to obtain
To N genetic programming actual output vectors, denoted
A′i＝(M′xi，M′yi，M′zi，ω′xi+ΔT，ω′yi+ΔT，ω′zi+ΔT，ω′ri+ΔT)，i＝1，2，…，N
(2) N genetically programmed actual output vectors A'iRespectively with the N genetic programming in step two
Target output vector AiOne-to-one correspondence, making difference values and taking a module to obtain N module values, and combining the N module values
And summing the modulus values, recording as a fitness value e of the program:
Figure BDA0001548285090000031
(3) and sequencing the obtained fitness values e of the M programs from high to low, wherein the candidate program with the lowest fitness value e is the target program P.
Preferably, in the above-mentioned genetic programming decision method for the artificial intelligence programmer to write the digital aircraft code, the method for generating the initial population in the third step includes, but is not limited to, a complete method, a growing method, and a mixed method.
Preferably, in the above method for genetic programming decision making by an artificial intelligence programmer for writing digital aircraft code, the genetic operations in the third step include replication, hybridization and mutation.
According to the technical scheme, compared with the prior art, the invention discloses a genetic programming decision method for writing the digital aircraft code by an artificial intelligence programmer, and the autonomous decision can be made according to the solution of the problem obtained by genetic programming on the problems of writing the code, selecting the module in the aircraft model and the like in the writing process, so that the writing efficiency is improved.
The artificial intelligence is used for replacing the writing of the digital aircraft source code by people, the digital aircraft source code can be independently written according to task requirements, and the problems of code writing in the writing of the source code, module selection in an aircraft model and the like are independently decided, so that people are liberated from the heavy digital aircraft source code writing process. The method specifically comprises the steps of determining and storing target sample component input instruction vectors, component internal state vectors and component output physical quantity vectors of all components in the digital aircraft, converting the target sample component input instruction vectors, the component internal state vectors and the component output physical quantity vectors into genetic programming input vectors and genetic programming target output vectors to perform genetic programming operation, and reasonably finishing genetic programming decision of source codes of the digital aircraft according to model functions of all the components which are optimized according to fitness, so that automation and intellectualization of writing of the source codes of the digital aircraft are realized, and the simulation cost of the aircraft is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart of the present invention for constructing genetic programming decisions;
FIG. 2 is a schematic overall flow chart of the genetic programming decision method for an artificial intelligence programmer to write digital aircraft codes according to 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a genetic programming decision method for writing a digital aircraft code by an artificial intelligence programmer, which overcomes the defects of the prior art, writes the source code of the digital aircraft by using artificial intelligence instead of people, can independently make decisions according to the input and output characteristics of aircraft parts on the problems of code writing, internal operation flow of modules in an aircraft model and the like in the writing process, improves the writing efficiency and reduces the simulation cost of the aircraft.
Referring to fig. 1, fig. 1 is a schematic flow chart of the genetic programming decision system according to the present invention. On the basis, fig. 2 shows an overall flow chart of a genetic programming decision method for an artificial intelligence programmer to write digital aircraft codes. The genetic programming decision method for the artificial intelligence programmer to write the digital aircraft code specifically comprises the following steps:
step S101: collecting N target samples of a component in the digital aircraft, wherein one target sample comprises a component input instruction vector R, a component internal state vector S and a component output physical quantity vector Q; writing the ID of the target sample and the R vector, the S vector and the Q vector of the target sample into a line and storing the line into a table corresponding to the component name in a database, wherein N target samples are stored in the table corresponding to the component name.
The specific execution method comprises the following steps:
(1) methods of collecting target samples include, but are not limited to, obtaining from measured component operational real-world data, obtaining from the internet;
(2) storing the target sample into a database in a storage mode including but not limited to a database file, an Excel file and a text file; the input instruction vector R, the internal state vector S and the output physical quantity vector Q of the same component are all a plurality of vectors.
Taking the example of a three-front-mounted-one-oblique-configuration momentum wheel as an example, a total of N target samples is obtained.
For target sample i, its component input instruction vector is written as:
Ri＝(βxi，βyi，βzi，βri)，i＝1，2，…，N
wherein, betaxi～βriThe angular acceleration commands for the 4 momentum wheels.
The component internal state vector is written as:
Si＝(ωxi，ωyi，ωzi，ωri)，i＝1，2，…，N
wherein, ω isxi～ωriThe current angular velocity of the 4 momentum wheels.
The component output physical quantity vector is written as:
Qi＝(Mxi，Myi，Mzi)，i＝1，2，…，N
wherein M isxi～MziThe three-axis control moment output by the momentum wheel.
In addition to the momentum wheel, the method is also used for collecting target samples for models of other components such as control moment gyros, batteries, solar panels, liquid-filled tanks, and the like. The names of components that have the same meaning but different names are replaced with a Unicode string or ID.
Step S102: converting the component input instruction vector R, the component internal state vector S and the component output physical quantity vector Q of the N target samples in the step S101 into N genetic programming input vectors I and genetic programming target output vectors A, wherein I and A correspond to each other one by one.
Genetic programming input vector I of target sample IiThe instruction vector R is input by the component of the target sample i in step S101iComponent internal state vector SiCombined with the simulation step length Δ T, and recorded as:
Ii＝(βxi，βyi，βzi，βri，ωxi，ωyi，ωzi，ωri，ΔT)，i＝1，2，…，N
Note Si+ΔTIs SiComponent internal state vector after Δ T time:
Si+ΔT＝(ωxi+ΔT，ωyi+ΔT，ωzi+ΔT，ωri+ΔT)，i＝1，2，…，N
genetically programmed target output vector A of target sample iiOutputting the physical quantity vector Q by the component of the target sample i in step S101iAnd Si+ΔTCombined, recorded as:
Ai＝(Mxi，Myi，Mzi，ωxi+ΔT，ωyi+ΔT，ωzi+ΔT，ωri+ΔT)，i＝1，2，…，N
step S103: inputting vector I by genetic Programming in step S102iAnd genetic programming target output vector AiAnd taking the N formed combinations and the required function set as the input of the genetic programming operation, and performing the genetic programming operation to obtain M candidate programs. And preferably selecting the target program P from the M candidate programs according to the fitness. When the genetic programming termination condition is satisfied, the target program P is taken as a model function of the component.
The set of functions required in the genetic programming operation include, but are not limited to:
1. arithmetic operations, e.g. +, -, ×, ÷ etc
2. Mathematical functions, e.g. sin, cos, exp, log, etc
3. Boolean operation: AND, OR, NOT
4. Conditional operators: IF-THEN-ELSE
5. And (3) cyclic operator: FOR, WHILE, DO-WHILE
The genetic programming operation includes the following procedures:
1. generating an initial population;
2. carrying out genetic operation to generate new individuals, and adding the new individuals into the population;
3. evaluating the fitness value e of each individual in the population;
4. adding 1 to the genetic algebra;
5. judging whether the termination criterion is satisfied, if so, terminating the genetic programming operation and outputting the current
The target program P with the lowest fitness value e.
The above processes are circularly carried out until the program exits and the target program P is output after the termination criterion is met.
Methods for generating the starting population include, but are not limited to, complete methods, growing methods, mixed methods, among others. Genetic manipulation includes replication, hybridization, and mutation. The termination criteria are: the fitness value e of the program reaches a specified value, e.g. 0.01, or a maximum genetic algebra GmaxThe genetic programming operation is terminated.
Evaluation was performed using the fitness value e of the program as an index, and the lower the fitness value e of the program, the better.
The closer the output of the target program is to the genetic programming target output vector AiThe better the procedure.
The "fitness value e of the program" was evaluated by the following procedure:
1. all N genetic programming input vectors I in step S102iInputting a program in sequence to obtain N genetic programming actual output vectors, and recording the N genetic programming actual output vectors as
A′i＝(M′xi，M′yi，M′zi，ω′xi+ΔT，ω′yi+ΔT，ω′zi+ΔT，ω′ri+ΔT)，i＝1，2，…，N
2. N genetically programmed actual output vectors A'iRespectively corresponding to the N genetic programming target output vectors A in step S102iAnd (3) correspondingly, making difference values and taking a module, summing the N modules, and recording the sum as a fitness value e of the program:
Figure BDA0001548285090000071
3. and sequencing the obtained fitness values e of the M programs from high to low, and finding out the target program P with the lowest fitness value e.
In the step of determining whether the termination criterion is satisfied, e.g.If the fitness value e of the target program P meets the requirement, finishing the genetic programming operation and outputting the target program P; if the fitness value e of the target program P does not meet the requirement, but the genetic algebra G is already larger than the maximum genetic algebra GmaxThe target program P is also output. If any of the termination conditions are not met, operation continues as per the flow.
The target program P can completely reflect the input-output relationship of the component, that is, the input-output relationship is a model function of the corresponding component.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (5)

1. A genetic programming decision method for an artificial intelligence programmer to write digital aircraft code, the method comprising the steps of:
collecting N target samples of a component in the digital aircraft, wherein one target sample comprises a component input instruction vector R, a component internal state vector S and a component output physical quantity vector Q; writing the ID of the target sample and the R vector, the S vector and the Q vector of the target sample into a line and storing the line into a table corresponding to the component name in a database, wherein N target samples are stored in the table corresponding to the component name;
step two, converting the component input instruction vectors R, the component internal state vectors S and the component output physical quantity vectors Q of the N target samples in the step one into N genetic programming input vectors I and genetic programming target output vectors A, wherein I and A correspond to each other one by one;
step three, taking N combinations formed by the genetic programming input vector I and the genetic programming target output vector A and a required function set as the input of genetic programming operation, and performing the genetic programming operation to obtain M candidate programs;
in the third step, the first step is that,
the genetic programming operation includes the following procedures:
(1) Generating an initial population, wherein one individual in the initial population is an object program, and the initial population is a set formed by the object programs for genetic programming and is a starting point of the genetic programming;
(2) carrying out genetic operation to generate new individuals, and adding the new individuals into the population;
(3) evaluating the fitness value e of each individual in the population;
(4) adding 1 to the genetic algebra;
(5) judging whether a termination criterion is met, if so, terminating the genetic programming operation and outputting a target program P with the lowest current fitness value;
the above processes are circularly carried out, and the program exits and outputs the target program P after the termination criterion is met;
the fitness value e of the procedure in step three is evaluated by the following step, where the genetic programming input vector of the target sample I is Ii：
(1) Inputting all N genetic programming input vectors I in the second stepiInputting a target program in sequence to obtain N genetic programming actual output vectors A'i；
(2) N genetically programmed actual output vectors A'iRespectively corresponding to the N genetic programming target output vectors A in the step twoiMaking difference values in a one-to-one correspondence mode, taking a module to obtain N module values, summing the N module values, and recording the sum as a fitness value e of a program;
(3) sorting the obtained fitness values e of the M programs from high to low, wherein the candidate program with the lowest fitness value e is the target program P;
And step four, preferably selecting the target program P from the M candidate programs according to the fitness, and taking the target program P as a model function of the corresponding part when the genetic programming termination condition is met.
2. The artificial intelligence programmer's genetic programming decision-making method for writing digital aircraft codes as claimed in claim 1, wherein said step two specifically includes,
genetic programming input vector I of target sample IiInputting an instruction vector R by a component of target samples iiComponent internal state vector S of target sample iiCombined with the simulation step length delta T; note Si+ΔTIs SiComponent internal state vectors after a time of Δ T; genetically programmed target output vector A of target sample iiOutputting a physical quantity vector Q by a component of a target sample iiAnd Si+ΔTAnd (3) combining the components.
3. The artificial intelligence programmer's genetic programming decision-making method of writing digital aircraft code according to claim 1, wherein the termination criteria in step three are: the fitness e of the program reaches a specified value, or reaches the maximum genetic algebra GmaxThe genetic programming operation is terminated.
4. The artificial intelligence programmer's genetic programming decision-making method of writing digital aircraft code according to claim 1, wherein the method of generating an initial population in step three comprises a complete method, a growing method, a mixed method.
5. The method of claim 1, wherein the genetic manipulation in step three comprises replication, hybridization, and mutation.
CN201810036980.9A 2018-01-15 2018-01-15 Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer Active CN108304625B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810036980.9A CN108304625B (en) 2018-01-15 2018-01-15 Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810036980.9A CN108304625B (en) 2018-01-15 2018-01-15 Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer

Publications (2)

Publication Number Publication Date
CN108304625A CN108304625A (en) 2018-07-20
CN108304625B true CN108304625B (en) 2021-10-08

Family

ID=62869050

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810036980.9A Active CN108304625B (en) 2018-01-15 2018-01-15 Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer

Country Status (1)

Country Link
CN (1) CN108304625B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102323906A (en) * 2011-09-08 2012-01-18 哈尔滨工程大学 MC/DC test data automatic generation method based on genetic algorithm
CN102331966A (en) * 2011-01-10 2012-01-25 中国矿业大学 Software test data evolution generation system facing path
CN103559129A (en) * 2013-10-31 2014-02-05 中国矿业大学 Statistical regression test data generation method based on genetic algorithm
CN107391385A (en) * 2017-08-28 2017-11-24 北京航空航天大学 A kind of construction method of Generation of software test case technology

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1672569A1 (en) * 2004-12-20 2006-06-21 STMicroelectronics S.r.l. A method of performing a quantum algorithm for simulating a genetic algorithm

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102331966A (en) * 2011-01-10 2012-01-25 中国矿业大学 Software test data evolution generation system facing path
CN102323906A (en) * 2011-09-08 2012-01-18 哈尔滨工程大学 MC/DC test data automatic generation method based on genetic algorithm
CN103559129A (en) * 2013-10-31 2014-02-05 中国矿业大学 Statistical regression test data generation method based on genetic algorithm
CN107391385A (en) * 2017-08-28 2017-11-24 北京航空航天大学 A kind of construction method of Generation of software test case technology

Also Published As

Publication number Publication date
CN108304625A (en) 2018-07-20

Similar Documents

Publication Publication Date Title
CN108563555B (en) Fault change code prediction method based on four-target optimization
CN108399273B (en) Decision decomposition method for writing digital aircraft source code by artificial intelligence programmer
Durkin Expert system development tools
Hatledal et al. JIOP: A Java Intelligent Optimisation And Machine Learning Framework.
Hu et al. Automated design of agentic systems
Li et al. A Study on Training and Developing Large Language Models for Behavior Tree Generation
CN108304625B (en) Genetic programming decision-making method for writing digital aircraft code by artificial intelligence programmer
Frank Reflecting on planning models: A challenge for self-modeling systems
Cohn Theory and practice of structural optimization
Yang et al. Efficient validation of self-adaptive applications by counterexample probability maximization
Koseler et al. Realization of a Machine Learning Domain Specific Modeling Language: A Baseball Analytics Case Study.
Chen Comparing deep reinforcement learning methods for engineering applications
CN115338610A (en) Biaxial hole assembling method and device, electronic device and storage medium
Shimada et al. Knowledge-based simulation of regulatory action in lambda phage
Jones How should life support be modeled and simulated?
Avison et al. Identifying and incorporating change in information systems
CN117151247B (en) Method, apparatus, computer device and storage medium for modeling machine learning task
CN118228609B (en) Mine blasting charge structure selection method and system
Jichan Simulation Analysis of Avionics System of UAV Based on MATLAB
Komendantskaya et al. Neural Network Verification for the Masses (of AI graduates)
Buinevich et al. On the Implementation of Residual Knowledge Continuous Assessment Technology in an Educational Organization Using Artificial Intelligence Tools
Holman et al. Applications of fuzzy logic and best-worst method for tritium sensor selection
Rahbek Conceptual Design Tool for Structural Layout Optimization in the Early Design Phase
Abednego et al. A Block World Problem Based Sudoku Solver
CN114840924A (en) Vehicle body curved surface simulation prediction method and system based on machine learning

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