CN115187040A - Bubbling self-learning comprehensive performance evaluation method for unmanned surface vehicle group - Google Patents
Bubbling self-learning comprehensive performance evaluation method for unmanned surface vehicle group Download PDFInfo
- Publication number
- CN115187040A CN115187040A CN202210778596.2A CN202210778596A CN115187040A CN 115187040 A CN115187040 A CN 115187040A CN 202210778596 A CN202210778596 A CN 202210778596A CN 115187040 A CN115187040 A CN 115187040A
- Authority
- CN
- China
- Prior art keywords
- index
- self
- value
- learning
- reference interval
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 39
- 230000005587 bubbling Effects 0.000 title claims abstract description 18
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000013507 mapping Methods 0.000 claims abstract description 20
- 238000010606 normalization Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000009434 installation Methods 0.000 claims abstract description 5
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 230000003993 interaction Effects 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a method for evaluating the comprehensive performance of bubbling self-learning unmanned surface vehicle groups, which comprises the following steps: 1) Acquiring experimental data of comprehensive performance evaluation indexes of the unmanned surface vehicle group; 2) Determining a reference interval of each single index, continuously updating the reference interval of each evaluation single index by accessing effective test data of actual installation or simulation and adopting a bubbling method, and realizing self-learning updating of the reference interval; 3) On the basis of the self-learning reference interval, sequentially carrying out dimensionless normalization processing from bottom to top, and mapping the actual index value to the normalization interval to generate a mapping value; 4) Determining the weight of each level of index; 5) And calculating the evaluation value according to the mapping value and the weight of each level of index after dimensionless normalization. The invention provides an index system for evaluating the comprehensive performance of the self-learning unmanned surface vehicle fleet, and realizes the self-learning of the evaluation model by introducing a bubbling evolution updating reference interval mode.
Description
Technical Field
The invention relates to a water surface unmanned ship group performance evaluation technology, in particular to a bubbling self-learning water surface unmanned ship group comprehensive performance evaluation method.
Background
The water surface unmanned ship group refers to an unmanned ship cluster which is formed by two or more unmanned ships to complete specific tasks in a certain sea area, has stronger robustness and flexibility, higher operation efficiency and wider operation range compared with a single ship, and can be used for executing dangerous tasks and tasks which are not suitable for being executed by the unmanned ships.
The water surface unmanned ship group executes tasks, and relates to multiple links of observation, fusion, judgment, decision, cooperation, action and the like, when the comprehensive tasks are executed, evaluation indexes are numerous and difficult to quantify, and index dimensionless processing difficulty is high.
Disclosure of Invention
The invention aims to solve the technical problem of providing a bubbling self-learning comprehensive performance evaluation method for the unmanned surface ship group aiming at the defects in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: a comprehensive performance evaluation method for bubbling self-learning unmanned surface vehicle groups comprises the following steps:
1) Acquiring experimental data of comprehensive performance evaluation indexes of the unmanned surface vehicle group;
2) Determining a reference interval of each single index, continuously updating the reference interval of each evaluation single index by accessing effective test data of actual installation or simulation and adopting a bubbling method, and realizing self-learning updating of the reference interval;
3) Sequentially carrying out dimensionless normalization processing from bottom to top on the basis of the self-learning reference interval, and mapping the actual index value to a normalization interval to generate a mapping value;
4) Determining the weight of each level of index;
5) And calculating evaluation values according to the mapping values and weights of the indexes at each level after dimensionless normalization.
According to the scheme, the comprehensive performance evaluation index of the unmanned surface vehicle group in the step 1) takes the comprehensive performance of the unmanned surface vehicle group as a primary root node, the performance of the task execution scene as a corresponding child node, and the task scene comprises the following steps: patrolling a water area, driving away a target, changing a formation through a dangerous water area, and searching an underwater target;
the water area patrol includes: the method comprises the following steps of (1) patrolling area coverage rate, task planning time, task reconstruction time, patrolling task success rate, man-machine interaction times, false alarm rate and false alarm rate;
target dislodging includes: target discovery time, effective tracking time, target dislodging task success rate, man-machine interaction times, false alarm rate and alarm missing rate;
the formation change comprises the following steps of: task planning time, water area passing time, frequency of entering a dangerous area, man-machine interaction frequency and path tracking precision;
the underwater target searching comprises the following steps: target discovery time, effective tracking time, target driving-away time, man-machine interaction times, dangerous area entering times, false alarm rate and false alarm rate.
According to the scheme, the reference interval of each evaluation single index is continuously updated in the step 2) in a bubbling method, so that the reference interval self-learning updating is realized, and the method specifically comprises the following steps:
2.1 According to the effective test data of the actual installation or simulation, determining the collection mean value of the index S, and determining a reference interval according to the maximum value and the minimum value;
assuming that the collection mean value of the index S after the nth test is S n The reference interval is
The average value of the acquisition of the index S after the n +1 test is S n+1 The reference interval is
Wherein,
is the minimum value of the index S in n tests,
the maximum value of the index S in N tests, wherein N belongs to N +;
if it is
Then
If it is
Then
If it is
Then the
By analogy, the index S reference interval self-learning updating is realized along with the continuous accumulation of the test data.
According to the scheme, the step 3) of mapping the actual index value to the normalization interval to generate a mapping value specifically comprises the following steps:
the actual value of the index is recorded as being carried out in an unmanned boat groupAfter the nth test, the average value of the index S is S n The reference interval is
If the nth test index S is evaluated, acquiring a mean value S of the index S n Performing dimensionless normalization and mapping the index to [0,1 ]]Then, the mean value S is collected n Dimensionless normalized mapped values
Comprises the following steps:
selecting formula (1) or (2) to map the index actual value to the normalization interval to generate a mapping value, ensuring that when the best result is achieved,
the invention has the following beneficial effects:
1. the invention fills the blank of lacking of performance evaluation means of the self-learning unmanned surface craft group by providing a comprehensive performance evaluation index system of the self-learning unmanned surface craft group;
2. according to the invention, self-learning of the evaluation model is realized by introducing a bubbling evolution updating reference interval, the evaluation method is scientific and effective, and the evaluation result can provide an optimized direction for performance improvement of the unmanned surface vehicle.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method of an embodiment of the present invention;
fig. 2 is a schematic diagram of an unmanned ship group comprehensive performance evaluation index tree according to an embodiment 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 is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, a method for evaluating the comprehensive performance of bubbling self-learning unmanned surface vehicle group comprises the following steps:
(1) Evaluation index tree construction
As shown in fig. 1, the comprehensive performance evaluation index tree of the unmanned ship group includes a first-level root node, a corresponding child node is an execution task scene performance, and the task scene mainly includes water patrol, target drive-off, formation change through dangerous water, underwater target search, and the like; and aiming at the performance of the task scene executed by the secondary root node, evaluating the indexes as corresponding child nodes.
(2) Bubble evolution of single-index dimensionless normalization interval
Here, a single index S is taken as an example (S is a set of next-level child nodes of a root node):
the mean value of the index S after the first test is S 1 Then the initial value reference interval is
Wherein
Assuming that the collection mean value of the index S after the nth test is S n The reference interval is
The average value of the acquisition of the index S after the n +1 test is S n+1 The reference interval is
Wherein
Is the minimum value of the index S in n tests,
is the maximum value of the index S in N times of tests, and N belongs to N +;
if it is
Then
If it is
Then
If it is
Then
By analogy, the index S reference interval can be updated in a self-learning mode along with the continuous accumulation of test data.
(3) Dimensionless normalization of single indices
After the unmanned ship group is subjected to the nth test, the acquisition mean value of the index S is S n The reference interval is
If the nth test index S is evaluated, acquiring a mean value S of the index S n Performing dimensionless normalization and mapping the index to [ a,1 ]]Wherein a is more than or equal to 0 and less than 1, and the value of a can be directly 0, then collecting the average value S n Dimensionless normalized mapped values
Comprises the following steps:
or
the formula (1) or (2) is selected to be determined according to the actual index, so that when the optimal achievement is achieved,
and obtaining the dimensionless normalized mapping values of the collection mean values of different single indexes in sequence.
(4) Analytic hierarchy process weight determination
And determining the weight of the index S at the next stage of the root node by adopting an analytic hierarchy process and a 9-point scaling method by an expert from bottom to top in a form of two-to-two comparison and scoring through solving a normalized eigenvector of a judgment matrix. The weight corresponding to the index S after the nth test is as
(5) Evaluation of comprehensive Properties
After obtaining the mapping value and the weight of the next-level evaluation index S of the root node after dimensionless normalization, the evaluation value V of the root node at each level of the evaluation index tree is the sum of the mapping value of each next-level evaluation index after dimensionless normalization multiplied by the corresponding weight:
if mapped to a corresponding percentage, the percentage evaluation value V 100 Comprises the following steps:
V 100 ＝V×100
from bottom to top, the second-level root nodes can be obtained in sequence to execute the taskThe evaluation value of business scene performance and the evaluation value of the comprehensive performance of the unmanned ship group of the primary root node are obtained, and the closer the evaluation value V is to 1 or the evaluation value V is measured in percentage 100 A closer to 100 points indicates better overall performance for the unmanned boat fleet.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (4)
1. A comprehensive performance evaluation method for bubbling self-learning unmanned surface vehicle groups is characterized by comprising the following steps:
1) Acquiring experimental data of comprehensive performance evaluation indexes of the unmanned surface vehicle group;
2) Determining a reference interval of each single index, continuously updating the reference interval of each evaluation single index by accessing effective test data of actual installation or simulation and adopting a bubbling method, and realizing self-learning updating of the reference interval;
3) On the basis of the self-learning reference interval, sequentially carrying out dimensionless normalization processing from bottom to top, and mapping the actual index value to the normalization interval to generate a mapping value;
4) Determining the weight of each level of index;
5) And calculating evaluation values according to the mapping values and weights of the indexes at each level after dimensionless normalization.
2. The bubbling self-learning method for evaluating the comprehensive performance of the unmanned surface vehicle cluster as claimed in claim 1, wherein the comprehensive performance evaluation index of the unmanned surface vehicle cluster in step 1) takes the comprehensive performance of the unmanned surface vehicle cluster as a primary root node and the performance of a task scene as a corresponding child node, and the task scene comprises: patrolling a water area, driving away a target, changing a formation through a dangerous water area, and searching an underwater target;
the water area patrol includes: the method comprises the following steps of (1) patrolling area coverage rate, task planning time, task reconstruction time, patrolling task success rate, man-machine interaction times, false alarm rate and false alarm rate;
target dislodging includes: target discovery time, effective tracking time, target dislodging task success rate, man-machine interaction times, false alarm rate and alarm missing rate;
the formation change comprises the following steps of: task planning time, water area passing time, frequency of entering a dangerous area, man-machine interaction frequency and path tracking precision;
the underwater target searching comprises the following steps: target discovery time, effective tracking time, target driving-away time, man-machine interaction times, dangerous area entering times, false alarm rate and false alarm rate.
3. The bubbling self-learning method for evaluating the comprehensive performance of the unmanned surface vehicle fleet according to claim 1, wherein the reference intervals of each evaluation individual index are continuously updated in the step 2) by adopting a bubbling method, so as to realize the self-learning updating of the reference intervals, and specifically the following steps are performed:
2.1 According to the effective test data of the actual installation or simulation, determining the collection mean value of the index S, and determining a reference interval according to the maximum value and the minimum value;
assuming that the collection mean value of the index S after the nth test is S n The reference interval is
The average value of the acquisition of the index S after the n +1 test is S n+1 The reference interval is
Wherein,
is the minimum value of the index S in n tests,
the maximum value of the index S in N tests, wherein N belongs to N +;
if it is
Then
If it is
Then
If it is
Then the
By analogy, the index S reference interval self-learning updating is realized along with the continuous accumulation of the test data.
4. The bubbling self-learning comprehensive performance evaluation method for the unmanned surface vehicle fleet according to claim 1, wherein the actual index value is mapped to the normalized interval in the step 3) to generate a mapping value, which is specifically as follows:
the actual value of the index is recorded as the average value of the acquisition of the index S after the nth test is carried out on the unmanned ship group n The reference interval is
If the nth test index S is evaluated, acquiring a mean value S of the index S n Performing dimensionless normalization and mapping the index to [0,1 ]]Then collect the mean value S n Dimensionless normalized mapped values
Comprises the following steps:
selecting formula (1) or (2) to map the index actual value to the normalization interval to generate a mapping value, ensuring that when the best result is achieved,
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210778596.2A CN115187040A (en) | 2022-06-30 | 2022-06-30 | Bubbling self-learning comprehensive performance evaluation method for unmanned surface vehicle group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210778596.2A CN115187040A (en) | 2022-06-30 | 2022-06-30 | Bubbling self-learning comprehensive performance evaluation method for unmanned surface vehicle group |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115187040A true CN115187040A (en) | 2022-10-14 |
Family
ID=83515491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210778596.2A Pending CN115187040A (en) | 2022-06-30 | 2022-06-30 | Bubbling self-learning comprehensive performance evaluation method for unmanned surface vehicle group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115187040A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702453A (en) * | 2023-05-23 | 2023-09-05 | 中国舰船研究设计中心 | Unmanned equipment virtual-real test design system and method |
| CN116720330A (en) * | 2023-05-23 | 2023-09-08 | 中国舰船研究设计中心 | Unmanned equipment simulation test system |
-
2022
- 2022-06-30 CN CN202210778596.2A patent/CN115187040A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702453A (en) * | 2023-05-23 | 2023-09-05 | 中国舰船研究设计中心 | Unmanned equipment virtual-real test design system and method |
| CN116720330A (en) * | 2023-05-23 | 2023-09-08 | 中国舰船研究设计中心 | Unmanned equipment simulation test system |
| CN116720330B (en) * | 2023-05-23 | 2024-05-28 | 中国舰船研究设计中心 | Unmanned equipment simulation test system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115187040A (en) | Bubbling self-learning comprehensive performance evaluation method for unmanned surface vehicle group | |
| CN114280696B (en) | Sea fog grade intelligent forecasting method and system | |
| CN110110943B (en) | Fleet energy efficiency comprehensive intelligent optimization management system and optimization method based on big data | |
| CN111582380B (en) | Ship track density clustering method and device based on space-time characteristics | |
| CN111311081B (en) | Ocean ecological abnormity danger identification method and device based on multi-source heterogeneous data | |
| CN113157732B (en) | Underground scraper fault diagnosis method based on PSO-BP neural network | |
| CN103743402B (en) | A kind of underwater intelligent self adaptation Approach of Terrain Matching of topographic information based amount | |
| CN112686453A (en) | Intelligent prediction method and system for locomotive energy consumption | |
| CN106374465A (en) | GSA-LSSVM model-based short period wind electricity generation power prediction method | |
| CN108734359B (en) | Wind power prediction data preprocessing method | |
| CN110826891B (en) | Relative collision risk degree obtaining method based on ship cluster situation | |
| CN115342814A (en) | Unmanned ship positioning method based on multi-sensor data fusion | |
| Belghith et al. | Acoustic diversity classifier for automated marine big data analysis | |
| CN115728463A (en) | Interpretable water quality prediction method based on semi-embedded feature selection | |
| CN116244647A (en) | Unmanned aerial vehicle cluster running state estimation method | |
| CN115984263A (en) | Bolt looseness detection algorithm and detection system based on improved twin neural network | |
| CN114910980A (en) | Tropical cyclone gale wind circle forecasting method based on subjective path strength forecasting and parameterized wind field model | |
| CN108832623B (en) | Physical-statistical hybrid two-stage wind power prediction method | |
| CN109711593B (en) | Instantaneous calculation decision-oriented high-speed railway line wind speed prediction method | |
| CN116105739A (en) | Unmanned aerial vehicle wind power detection dynamic path optimal planning method and system | |
| CN114155428A (en) | Underwater sonar side-scan image small target detection method based on Yolo-v3 algorithm | |
| KR20120136565A (en) | Red tide blooms prediction method using fuzzy reasoning | |
| Xue et al. | Busy fishing area recognition based on improved K-means with random walking centroid | |
| Liu et al. | A collision avoidance manoeuvre and ship domain based model for identifying collision risk index between ships | |
| CN116484954B (en) | Artificial intelligent offshore voltaic model generation method and storage medium |
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 |