CN115494881B - Unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning - Google Patents
Unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning Download PDFInfo
- Publication number
- CN115494881B CN115494881B CN202211442903.6A CN202211442903A CN115494881B CN 115494881 B CN115494881 B CN 115494881B CN 202211442903 A CN202211442903 A CN 202211442903A CN 115494881 B CN115494881 B CN 115494881B
- Authority
- CN
- China
- Prior art keywords
- index
- calculating
- weight
- matrix
- scaling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000015572 biosynthetic process Effects 0.000 title claims abstract description 18
- 238000005457 optimization Methods 0.000 title claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 40
- 239000013598 vector Substances 0.000 claims description 29
- 238000012937 correction Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 4
- 229940050561 matrix product Drugs 0.000 claims description 4
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims description 2
- 230000001419 dependent effect Effects 0.000 abstract 1
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative flight path planning, which is characterized in that combination weighting is carried out in a subjective and objective combination mode, and meanwhile, a subjective weighting method is reasonably improved. The flight path generated by the unmanned aerial vehicle formation in the flying process is more scientific and reasonable by the combined empowerment mode, and the requirements of task scenes are met. Different empowerment results can be calculated according to different requirements of the task scene. However, the weighting result obtained by artificial experience is not objective enough because of being too dependent on subjective experience, and the weight coefficient is obtained by multiple experimental adjustments.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicles, and particularly relates to an unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning.
Background
Along with the development of scientific technology, research and application of the concept of unmanned aerial vehicle formation cooperation in various fields are more and more, and due to the fact that the function of a single unmanned aerial vehicle with low cost is limited, a plurality of unmanned aerial vehicles need to be used for forming a formation cooperation execution task. Wherein formation track generation is an unconstrained optimization problem, based on an objective functionTherein is describedIs the weight vector of seven cost indexes of the objective function, we need to find the objective function in the next step of path pointsAnd taking the point with the minimum value as a track point of the next track. The weight vector of each cost index is specified by human experience and is obtained by lacking of scientific method calculation.
At present, research results aiming at the problems are few, the existing methods are that weight coefficients of all indexes in a cost function are manually specified, experience components are more, and scientific method calculation is lacked.
Disclosure of Invention
Technical problem to be solved
In order to avoid the defects of the prior art, the invention provides the unconstrained optimization index empowering method for unmanned aerial vehicle formation collaborative track planning, which can scientifically and reasonably empowering indexes and solve the irrationality caused by artificial experience empowering.
Technical scheme
An unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning is characterized in that: the evaluation system is constructed into seven evaluation indexes which need to be considered for generating track points during formation flight of unmanned aerial vehicles, the evaluation system needs to be subjected to combined weighting to determine the weight of each index, and the seven evaluation indexes are respectively the minimum control force costTotal time costAnd avoid barrier costTeam similarity costCollision avoidance between machinesCollision avoidance between machinesAnd the cost of uniform distribution of the restriction points(ii) a The method comprises the following steps:
step 1: according toThe scaling method obtains the weight vector of each index according to the calculation steps of the AHP method;
step 2: according toThe scaling method obtains the weight vector of each index according to the calculation steps of the AHP method;
and step 3: performing discrimination mixing on the results of the two scaling methods to obtain a subjective weighting result;
and 4, step 4: calculating five subjective weighting results to form an initial correction matrix;
and 5: and correcting the initial correction matrix according to the entropy weight method calculation step and finally correcting the weighted result of the subjective and objective combination.
The further technical scheme of the invention is as follows: the step 1 is as follows:
step 11: by usingScaling, judging matrices based on different constructions of the index importance;
Step 14: for vectorCarrying out normalization treatment, wherein the normalization formula of each component isTo obtain a vectorImmediate decision matrixThe feature vector of (2);
And step 17: calculating a decision matrixUniformity ratio of (a):whereinRIIs an average random consistency index; when in useWhen the judgment matrix is in the allowable range, the judgment matrix is consistent; thenIs correspondingly composed ofThe weighting factor of each index is scaled.
The further technical scheme of the invention is as follows: the step 2 is as follows:
step 21: by usingScaling, judging matrices based on different constructions of importance of the indicators;
Step 24: for vectorCarrying out normalization treatment, wherein the normalization formula of each component isTo obtain a vectorImmediate decision matrixThe feature vector of (2);
Step 27: calculating a decision matrixUniformity ratio of (a):whereinRIIs an average random consistency index; when in useWhen the judgment matrix is in the allowable range, the judgment matrix is consistent; thenIs correspondingly composed ofThe weighting factor of each index is scaled.
The further technical scheme of the invention is as follows: the step 3 is specifically as follows:
will be provided withScaling method andthe weighted results of the scaling method are mixed with the degree of distinction to establish a function of the degree of distinctionThrough reaction withAndperforming simultaneous calculation to obtain the three formulasAndthe final subjective weighted result is。
The further technical scheme of the invention is as follows: the step 4 is specifically as follows:
respectively carrying out discrimination mixing on five groups of indexes with different importance sequences according to two scaling methods to obtain corresponding weight vectorsAnd the five results constitute the repairPositive matrix:
The further technical scheme of the invention is as follows: the step 5 is as follows:
step 51: calculating an indexjEntropy of (d):whereinmIs composed ofThe number of the rows,jthe number of indexes to be entitled isThe number of columns;
A computer system, comprising: one or more processors, a computer readable storage medium, for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the above-described method.
A computer-readable storage medium having stored thereon computer-executable instructions for performing the above-described method when executed.
Advantageous effects
Compared with the artificial designated weight vector, the calculation process of the unconstrained optimization index weighting method for collaborative flight path planning of unmanned aerial vehicle formation provided by the invention adopts a combined weighting method of subjective and objective combination, improves the subjective weighting method, scientifically calculates the weight coefficient of each index by combining the subjective and objective combination, replaces the coefficient which is considered to be designated by people, has more scientific and reasonable calculation result, and is beneficial to generating more reasonable flight path when the unmanned aerial vehicle formation flies.
Drawings
The drawings, in which like reference numerals refer to like parts throughout, are for the purpose of illustrating particular embodiments only and are not to be considered limiting of the invention.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention provides a non-constrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning. And then, the subjective weighting result is corrected by adopting an objective weighting method of an entropy weighting method, and finally, a combined weighting result of the subjective and objective combination is obtained. The method can scientifically calculate the weight vector required by the formation of the unmanned aerial vehicle to generate the flight path, and is used for replacing the artificially-specified weight vector obtained through experience.
The solving method comprises the following five steps:
1. according toThe scaling method obtains a weight vector according to the calculation steps of the AHP method;
2. according toThe scaling method obtains a weight vector according to the calculation steps of the AHP method;
3. performing discriminative degree mixing on the results of the two scaling methods to obtain a subjective weighting result;
4. calculating five subjective weighting results to form an initial correction matrix;
5. and correcting the final weighting result of the subjective and objective combination according to the entropy weight method calculation step.
The specific steps comprise the following steps 1-16, wherein the steps 1 to 11 are an improved mixed AHP calculation flow of a subjective weighting part, and the steps 12 to 16 are an entropy weight method correction calculation flow of an objective weighting part:
step 1: the evaluation system is constructed into seven evaluation indexes which need to be considered when the track point is generated during the formation flight of the unmanned aerial vehicle, the evaluation system needs to be subjected to combined weighting to determine the weight of each index, and each index is the minimum control force costTotal time costAnd obstacle avoidance costTeam similarity costCollision avoidance between machinesCollision avoidance between machinesAnd the cost of uniform distribution of the restriction points。
Step 2: subjective weighting segment selectionScaling method andthe idea of mixing the results of the scaling calculations, the description of both scaling methods is shown in table 1;
TABLE 1 description of the two scales
Degree of importance | Method of scaling | Method of scaling |
A i AndA j of equal importance | 1 | 1 |
A i Ratio ofA j Of slight importance | 3 | 1.492 |
A i Ratio ofA j Of obvious importance | 5 | 2.226 |
A i Ratio ofA j Of strong importance | 7 | 3.320 |
A i Ratio ofA j Of utmost importance | 9 | 4.953 |
Intermediate between the above two determinations | 2、4、6、8 | 1.221、1.822、2.718、4.055 |
And step 3: respectively according to two scaling methods (table 1) according to different structures of index importance degreeAnd;
and 4, step 4: respectively calculating two judgment matrixesAndproduct of each column element ofAnd;
step 6: respectively to vectorAndperforming normalization processing toFor example, the normalization formula of each component isThe resulting vectorIs the decision matrixThe feature vector of (2);
and 7: respectively solving the maximum eigenvalues of two judgment matrixesAndwhereinIs thatTo (1) aiThe number of the components is such that,;
And step 9: the consistency ratio of the two decision matrices is calculated:whereinRIThe average random consistency index is obtained by taking the following table as followsCRThe smaller the matrix is, the better the consistency of the judgment matrix is, whenWhen the difference of the judgment matrix is within the allowable range, the judgment matrix is consistent becausen=7 soRIIs 1.32 corresponding to dimension 7;
TABLE 2 table for taking values of average random consistency index
Dimension number | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
RI | 0 | 0.58 | 0.90 | 1.12 | 1.24 | 1.32 | 1.41 | 1.45 |
Step 10: if two decision matrices are presentAndall pass the consistency check, thenAndare respectively correspondingScaling method andthe weighting coefficient of each index obtained by the scaling method is calculated.
Step 11: will be provided withScaling method andthe weighted results of the scaling method are mixed with the degree of distinction to establish a function of the degree of distinctionThrough reaction withAndperforming simultaneous calculation to obtain the three formulasAndthe final subjective weighted result is;
Step 12: respectively carrying out discriminative degree mixing on five groups of indexes with different importance ranks according to two scaling methods, namely respectively obtaining weight vectors corresponding to the five groups of indexes with different importance ranks according to the calculation processes from step 1 to step 11And forming a correction matrix from the five results:
Step 13: calculating an indexjEntropy of (d):whereinmIs composed ofThe number of the rows,jthe number of indexes to be entitled isThe number of columns;
and step 17: the final combining weight obtained from the above calculations of step 12 to step 16 is。
In order that those skilled in the art will better understand the present invention, the following detailed description is given with reference to specific examples.
Example 1:
the evaluation system is calculated and a judgment matrix is constructed according to two scaling methods in table 1, and the importance degree judgment of the first group of indexes with different importance ranks is as follows:
byScaling method andthe judgment matrixes constructed by the scale method are respectively as follows:
according to the calculation flow from step 4 to step 11, the weight calculation results of the two scaling methods are respectively:
it corresponds to,All pass consistency check, so simultaneous solution can be obtained according to the mixed calculation formula of the degrees of distinction in the step 11,And finally, mixing the results of the two scaling methods, wherein the subjective mixing weight result is as follows:
similarly, the importance degree of the second group of indexes with different importance ranks is judged as follows:
byScaling method andthe judgment matrixes constructed by the scale method are respectively as follows:
according to the calculation flow from step 4 to step 11, the weight calculation results of the two scaling methods are respectively:
corresponding thereto,All pass consistency check, so simultaneous solution can be obtained according to the mixed calculation formula of the degrees of distinction in the step 11,And finally, mixing the weights of the two scaling methods, wherein the subjective mixed weight result is as follows:
at this time, the two groups of subjective mixed weights are adjusted to the same index weight sequence and combined into a correction matrix:
The final combining weight obtained by performing the above calculation from step 13 to step 16 on the matrix is:
this weight is used as the final weight of the index system described above in place of the individual weights specified empirically, i.e. manually。
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present disclosure.
Claims (3)
1. An unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning is characterized in that: the evaluation system is constructed into seven evaluation indexes which need to be considered for generating track points during formation flight of unmanned aerial vehicles, the evaluation system needs to be subjected to combined weighting to determine the weight of each index, and the seven evaluation indexes are respectively the minimum control force costTotal time costAnd avoid barrier costTeam similarity costCollision avoidance between machinesCollision avoidance between machinesAnd the cost of uniform distribution of the restriction points(ii) a The method comprises the following steps:
step 1: according toThe scaling method obtains the weight vector of each index according to the calculation steps of the AHP method;
step 11: by usingScaling, judging matrices based on different constructions of importance of the indicators;
Step 14: for vectorCarrying out normalization treatment, wherein the normalization formula of each component isTo obtain(Vector)Immediate decision matrixThe feature vector of (2);
And step 17: calculating a decision matrixUniformity ratio of (a):whereinRIIs an average random consistency index; when in useWhen the judgment matrix is in the allowable range, the judgment matrix is consistent; thenIs correspondingly composed ofWeight coefficient of each index of scale method;
Step 2: according toThe scaling method obtains the weight vector of each index according to the calculation steps of the AHP method;
step 21: by usingScaling, judging matrices based on different constructions of the index importance;
Step 24: for vectorCarrying out normalization treatment, wherein the normalization formula of each component isTo obtain a vectorImmediate decision matrixThe feature vector of (2);
Step 27: calculating a decision matrixUniformity ratio of (a):in whichRIIs an average random consistency index; when in useWhen the judgment matrix is in the allowable range, the judgment matrix is consistent; thenIs correspondingly composed ofWeighting coefficients of each index by a scaling method;
and step 3: performing discrimination mixing on the results of the two scaling methods to obtain a subjective weighting result;
will be provided withScaling method andthe weighted results of the scaling method are mixed with the degree of distinction to establish a function of the degree of distinctionBy reacting withAndperforming simultaneous calculation to obtain the three formulasAnd withThe final subjective weighted result is;
And 4, step 4: calculating five subjective weighting results to form an initial correction matrix;
respectively carrying out discrimination mixing on five groups of indexes with different importance sequences according to two scaling methods to obtain corresponding weight vectorsAnd forming a correction matrix from the five results:
And 5: correcting the initial correction matrix according to the entropy weight method calculation step and finally correcting the weighted result of the subjective and objective combination;
step 51: calculating an indexjEntropy of (d):whereinmIs composed ofThe number of the rows,jthe number of indexes to be entitled isThe number of columns;
2. A computer system, comprising: one or more processors, a computer readable storage medium, for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of claim 1.
3. A computer-readable storage medium having stored thereon computer-executable instructions for, when executed, implementing the method of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211442903.6A CN115494881B (en) | 2022-11-18 | 2022-11-18 | Unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211442903.6A CN115494881B (en) | 2022-11-18 | 2022-11-18 | Unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115494881A CN115494881A (en) | 2022-12-20 |
CN115494881B true CN115494881B (en) | 2023-03-10 |
Family
ID=85116151
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211442903.6A Active CN115494881B (en) | 2022-11-18 | 2022-11-18 | Unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115494881B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469196A (en) * | 2015-11-18 | 2016-04-06 | 山东科技大学 | Comprehensive evaluation method and comprehensive evaluation system for evaluating mine construction project process |
CN106202267A (en) * | 2016-06-30 | 2016-12-07 | 四川农业大学 | The Citrus chachiensis Hort. integrated quality evaluation methodology of a kind of yellow fruit |
CN110599011A (en) * | 2019-08-29 | 2019-12-20 | 广东省水利水电科学研究院 | Aqueduct safety evaluation method, system and storage medium based on improved AHP-FCE method |
CN112950008A (en) * | 2021-02-08 | 2021-06-11 | 北京理工大学 | Flight path planning evaluation method of aircraft |
CN114548725A (en) * | 2022-02-15 | 2022-05-27 | 大连理工大学 | Deep foundation pit stability evaluation method based on entropy weight-level analysis fuzzy comprehensive evaluation method |
CN115168870A (en) * | 2022-07-29 | 2022-10-11 | 江苏大学 | Block chain safety assessment method based on comprehensive evaluation |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11727812B2 (en) * | 2017-07-27 | 2023-08-15 | Beihang University | Airplane flight path planning method and device based on the pigeon-inspired optimization |
CN113537663A (en) * | 2020-04-15 | 2021-10-22 | 海鹰航空通用装备有限责任公司 | Unmanned aerial vehicle track evaluation method based on TOPSIS algorithm |
-
2022
- 2022-11-18 CN CN202211442903.6A patent/CN115494881B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469196A (en) * | 2015-11-18 | 2016-04-06 | 山东科技大学 | Comprehensive evaluation method and comprehensive evaluation system for evaluating mine construction project process |
CN106202267A (en) * | 2016-06-30 | 2016-12-07 | 四川农业大学 | The Citrus chachiensis Hort. integrated quality evaluation methodology of a kind of yellow fruit |
CN110599011A (en) * | 2019-08-29 | 2019-12-20 | 广东省水利水电科学研究院 | Aqueduct safety evaluation method, system and storage medium based on improved AHP-FCE method |
CN112950008A (en) * | 2021-02-08 | 2021-06-11 | 北京理工大学 | Flight path planning evaluation method of aircraft |
CN114548725A (en) * | 2022-02-15 | 2022-05-27 | 大连理工大学 | Deep foundation pit stability evaluation method based on entropy weight-level analysis fuzzy comprehensive evaluation method |
CN115168870A (en) * | 2022-07-29 | 2022-10-11 | 江苏大学 | Block chain safety assessment method based on comprehensive evaluation |
Non-Patent Citations (1)
Title |
---|
基于改进AHP-熵权法的雷达装备可靠性评估指标赋权方法;翟芸 等;《现代防御技术》;20220831;第50卷(第4期);第2.1节,第3.1节,及表3-表8 * |
Also Published As
Publication number | Publication date |
---|---|
CN115494881A (en) | 2022-12-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112101530B (en) | Neural network training method, device, equipment and storage medium | |
Mallya et al. | Packnet: Adding multiple tasks to a single network by iterative pruning | |
Stephan | An iterative method of adjusting sample frequency tables when expected marginal totals are known | |
Shen et al. | Multi-level image thresholding using modified flower pollination algorithm | |
CN108304656B (en) | Task acceptance condition simulation method for labor crowdsourcing platform | |
Permana et al. | Fuzzy membership function generation using particle swarm optimization | |
CN111695624B (en) | Updating method, device, equipment and storage medium of data enhancement strategy | |
CN114841055B (en) | Unmanned aerial vehicle cluster task pre-allocation method based on generation countermeasure network | |
CN113691594B (en) | Method for solving data imbalance problem in federal learning based on second derivative | |
CN109799703A (en) | A kind of population Auto-disturbance-rejection Control, device and storage medium | |
CN111160511A (en) | Group intelligent method for consensus active learning | |
CN108229536A (en) | Optimization method, device and the terminal device of classification prediction model | |
CN115494881B (en) | Unconstrained optimization index weighting method for unmanned aerial vehicle formation collaborative track planning | |
CN115222271A (en) | Weapon target distribution method based on neural network | |
CN116205311A (en) | Federal learning method based on Shapley value | |
CN114936518A (en) | Method for solving design parameters of tension/compression spring | |
CN109074348A (en) | For being iterated the equipment and alternative manner of cluster to input data set | |
CN106679670A (en) | Unmanned aerial vehicle flight path planning decision-making method based on fusion weighing | |
US8700541B2 (en) | Modeling method of neuro-fuzzy system | |
CN109858533A (en) | A kind of RBF-MLP mixed structure neural network classifier of prepositus nucleus | |
CN113132482B (en) | Distributed message system parameter adaptive optimization method based on reinforcement learning | |
CN113705724B (en) | Batch learning method of deep neural network based on self-adaptive L-BFGS algorithm | |
CN115170902A (en) | Training method of image processing model | |
CN112906871A (en) | Temperature prediction method and system based on hybrid multilayer neural network model | |
Dingxue et al. | An adaptive particle swarm optimization algorithm and simulation |
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 |