CN106384161B - Optimization method for division of aerospace patrol plan region - Google Patents

Optimization method for division of aerospace patrol plan region Download PDF

Info

Publication number
CN106384161B
CN106384161B CN201610780816.XA CN201610780816A CN106384161B CN 106384161 B CN106384161 B CN 106384161B CN 201610780816 A CN201610780816 A CN 201610780816A CN 106384161 B CN106384161 B CN 106384161B
Authority
CN
China
Prior art keywords
plan
patrol
temporary
temporary take
landing
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.)
Expired - Fee Related
Application number
CN201610780816.XA
Other languages
Chinese (zh)
Other versions
CN106384161A (en
Inventor
徐超
郑岩
崔晨晖
赵锐
高梦雅
周筑博
张娟
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.)
Tianjin University
Tianjin Aerospace Zhongwei Date Systems Technology Co Ltd
Original Assignee
Tianjin University
Tianjin Aerospace Zhongwei Date Systems Technology Co Ltd
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 Tianjin University, Tianjin Aerospace Zhongwei Date Systems Technology Co Ltd filed Critical Tianjin University
Priority to CN201610780816.XA priority Critical patent/CN106384161B/en
Publication of CN106384161A publication Critical patent/CN106384161A/en
Application granted granted Critical
Publication of CN106384161B publication Critical patent/CN106384161B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an optimization algorithm for division of an aerospace patrol plan region, which comprises the following steps: step (1), establishing a plan to be patrolled and patrolling by taking the patrolling plan as input dataLine of sight LiThe corresponding relation set of (2); step (2), allocating patrol projects to temporary take-off and landing points according to two constraint conditions, namely the distance between the temporary take-off and landing points and a patrol line corresponding to a plan and the online rate; step (3), clustering the temporary take-off and landing points into areas according to two constraint conditions of the capacity of the patrol areas and the maximum distance of area clustering; step (4), according to the constraint condition of the altitude plan, a plan list which is not summarized to the temporary take-off and landing point is forcibly distributed; and (5) recording the inspection items which still cannot be summarized as a part of data returned finally. Compared with the prior art, the invention can form the patrol area aiming at the patrol plan of each year. And an optimal patrol operation plan is given, so that patrol efficiency is optimized.

Description

Optimization method for division of aerospace patrol plan region
Technical Field
The invention relates to an optimization algorithm of an aerospace route, in particular to a clustering optimization algorithm for aerospace tour routes and temporary take-off and landing points.
Background
The related prior art of the invention comprises an optimization algorithm and an aerospace patrol plan region division optimization algorithm.
First, optimization algorithms have been one of the hot problems that researchers are dedicated to research, exploration and solution for many years. The mainstream solution at present mainly includes ant colony algorithm and dynamic optimization. The ant colony algorithm is a simulation of the ant colony food collection process and is proposed by Marco Dorigo in 1992 in his doctor's paper, and the inspiration thereof is derived from the behavior of ants in finding paths in the process of searching food. However, the optimization performance depends on the parameter setting to a large extent, and is greatly influenced by the initial value. Dynamic optimization is also a branch of operations research and is a mathematical method for solving the optimization of a decision making process. Bellman et al, r.e. american mathematician in the early 50 s of the 20 th century, proposed a well-known optimization principle when studying the optimization problem of a multi-stage decision-making process. The basic principle is to decompose the problem to be solved into a plurality of sub-problems (stages), solve the sub-stages in sequence, and the solution of the former sub-problem provides useful information for the solution of the latter sub-problem.
And secondly, the aerospace patrol plan area division optimization algorithm realizes reasonable classification and optimization according to the distribution characteristics of patrol routes of the power transmission line helicopters and considering various factors such as the operation performance of helicopter patrol and combines the main characteristics of patrol areas to provide an optimal patrol operation plan so as to optimize patrol efficiency.
Disclosure of Invention
Based on the defects in the prior art, the invention provides an optimization method for dividing the aerospace patrol plan region, and the aerospace patrol plan region division optimization algorithm realizes reasonable classification and optimization according to the patrol route distribution characteristics of the power transmission line helicopters and considering various factors such as the operation performance of helicopter patrol and the like and by combining the main characteristics of patrol regions.
The invention discloses an optimization method for division of a space patrol plan region, which comprises the following steps:
step 1, taking a patrol plan as input data, establishing a plan to be patrolled and a patrol route LiThe corresponding relation set of (2);
step 2, allocating patrol projects to temporary take-off and landing points according to two constraint conditions, namely the distance between the temporary take-off and landing points and the patrol line corresponding to the plan and the online rate; (ii) a
Step 3, clustering the temporary take-off and landing points into areas according to two constraint conditions of the capacity of the patrol areas and the maximum distance of area clustering;
step 4, forcibly distributing a plan list which is not summarized to the temporary take-off and landing point according to the constraint condition of the altitude plan;
and 5, recording the inspection items which still cannot be summarized as part of the finally returned data.
The step 2 further specifically includes the following processing:
calculating the distance between the temporary take-off and landing point and the patrol line corresponding to the plan, and selecting and recording the closest distance dis _ pa between the temporary take-off and landing point and the patrol line corresponding to the plan; calculating the online rate of patrolling the patrolling line corresponding to the plan from the temporary take-off and landing point, wherein the online rate formula is as follows:
per_on＝t_on/t_on+t_off
t_on＝l_len/v_on
t_off＝dis_pa+dis_st+dis_pen
wherein per _ on is an online rate, t _ on is the online flight time of the airplane during the inspection of the line, and t _ off is the offline flight time of the airplane;
for each temporary take-off and landing point, selecting a minimum value min _ dis _ pa in the nearest distance and a maximum value max _ per _ on of the online rate;
if the distance constraint landingPointdistance for summarizing the plan to the temporary rising and falling point is less than or equal to min _ dis _ pa, summarizing the plan to the corresponding temporary rising and falling point; if the maximum online rate max _ per _ on is not met, judging the limiting condition, and if the maximum online rate max _ per _ on is greater than or equal to the maximum online rate specified by the system, namely the maximum online rate of 80%, summarizing the plan to the corresponding temporary take-off and landing point;
and putting the plans which are not summarized to the temporary take-off and landing points into a plan list which is not summarized to the temporary take-off and landing points for the plans which are not summarized to the temporary take-off and landing points through the steps.
The step 4 further specifically includes the following processing:
the temporary take-off and landing points are divided into two categories, namely the first category is the set S of temporary take-off and landing points containing plans for high altitudehighThe second type is a temporary set of take-off and landing points S containing only low-altitude planslow；
Clustering all temporary take-off and landing point sets including high altitude plans, i.e. set ShighClustering is carried out;
after the clustering of the temporary take-off and landing points at high altitude is finished, the high-altitude area starts to absorb the temporary take-off and landing points at low altitude, and whether the plan can be added into the area corresponding to the nearest temporary take-off and landing point is judged according to whether the distance between the temporary take-off and landing points is nearest and whether the capacity of the area is exceeded;
clustering the rest low-altitude temporary take-off and landing points;
and after the clustering is finished, returning all the generated regions.
Compared with the prior art, the method and the device have the advantages that the model is formed and the regional division of the inspection tasks is completed according to the distribution characteristics of the aerospace inspection tasks and various actual factors, and the inspection region can be formed according to the inspection plan of each year. And giving an optimal patrol operation plan to optimize patrol efficiency.
Drawings
FIG. 1 is a flow chart of an optimization method for division of a space patrol plan region according to the present invention;
FIG. 2 is a schematic view of an aircraft online rate calculation;
fig. 3 is a result schematic diagram of an operation example of the optimization method for dividing the aerospace patrol plan region according to the present invention.
Detailed Description
The method classifies the all-year-round inspection plans, the classification of the all-year-round inspection plans mainly takes temporary take-off and landing points as the core, the all-year-round inspection plans are classified to the temporary take-off and landing points according to set constraints, the inspection plans which do not meet the set constraints are recorded in the process, after the all-year-round inspection plans are classified to the temporary take-off and landing points, the temporary take-off and landing points are clustered according to the constraint, saving and optimizing principles, and finally the region formed by clustering is generated. After the area division is completed, the previously unallocated patrol plans are arranged into the areas according to an optimal principle, and the total capacity of each area is not exceeded. After completion, the aircraft is equipped according to whether a high altitude plan exists in each area.
As shown in fig. 1, a flowchart of an optimization method for dividing a space patrol plan region according to the present invention includes the following steps:
step 1, traversing a plan (forming each task needing to be arranged of a tour project), numbering the plan as i, and setting and planning TiThe relevant parameters include the patrol route LiP of provinceiFor each plan in the plan list, preprocessing is performed, the preprocessing including:
(1-1) creation of plans and LiCorresponding relation set IiExpressed as:
Ii＝{Ts,Tj...|s,j...∈X}
wherein X represents all the patrol routes LiWhere s, j respectively denote any two patrol routes, Ts、TjPlans corresponding to two patrol lines are respectively established in the setiThe index between the data points records and stores the task establishment relation corresponding to the same tour route in all plans;
(1-2) establishing a plan with PiCorresponding relation set NiExpressed as:
Ni＝{Ts,Tj...|s,j...∈Y}
wherein Y represents all the province numbers PiWhere s, j each denote any two provinces, Ts、TjPlans corresponding to any two provinces respectively, and the set establishes the plans and the belonged provinces PiThe index between the provinces records and stores the task establishment relation corresponding to the same province in all the plans;
(1-3) traversing the historical data, establishing a historical data-based link with LiRelational set of related historical data Oi：
Oi＝{Ts,Tj...|s,j...∈Z}
Where Z is a set of 1 to 12 months, where s, j respectively denote any two months that have occurred in the history, Ts、TjThe historical task book sets corresponding to any two provinces respectively establish a tour route and all the security of the route in the historical dataIndexing between the time lines, each line possibly corresponding to a plurality of times;
step 2, distributing the items to be patrolled to temporary take-off and landing points according to the constraints such as distance, online rate and the like; the data required by the step comprises a plan list, initially input temporary take-off and landing point information, a plan list (a temporary empty list) which does not summarize the temporary take-off and landing points, a distance constraint LandingPointDistance which summarizes the plan to the temporary take-off and landing points, and finally a temporary take-off and landing point set which is formed by summarizing the temporary take-off and landing points of the plan list is returned. The method specifically comprises the following steps:
(2-1) as shown in FIG. 2, calculating the distance between the temporary take-off and landing point and the patrol line corresponding to the plan, and selecting and recording the closest distance dis _ pa between the temporary take-off and landing point and the patrol line corresponding to the plan; calculating the online rate of patrolling the patrolling line corresponding to the plan from the temporary take-off and landing point, wherein the online rate formula is as follows:
per_on＝t_on/t_on+t_off
t_on＝l_len/v_on
t_off＝dis_pa+dis_st+dis_pen
wherein per _ on is an online rate, t _ on is the online flight time of the airplane during the inspection of the line, t _ off is the offline flight time of the airplane, l _ len is the length of the inspection line, dis _ st is the distance between the tower closest to the temporary take-off and landing point and the tower at the beginning of the inspection line, dis _ pen is the distance between the temporary take-off and landing point and the tower at the end of the inspection line, v _ on is the online flight speed of the airplane, usually 20km/h, and v _ off is the offline flight speed of the airplane;
(2-2) selecting a minimum value min _ dis _ pa in the nearest distance and a maximum value max _ per _ on of the online rate for each temporary take-off and landing point;
(2-3) firstly, carrying out constraint condition limitation on the minimum nearest distance min _ dis _ pa, and if the minimum nearest distance min _ dis _ pa is less than or equal to the distance constraint landPoint distance for summarizing the plan to the temporary take-off and landing point, summarizing the plan to the corresponding temporary take-off and landing point; if the maximum online rate max _ per _ on is not met, judging the limiting condition, and if the maximum online rate max _ per _ on is greater than or equal to the maximum online rate (80%) specified by the system, summarizing the plan to the corresponding temporary take-off and landing point;
(2-4) putting the plan which is not summarized to the temporary take-off and landing point into a plan list which is not summarized to the temporary take-off and landing point for the plan which is not summarized to the temporary take-off and landing point in the three steps;
step 3, after the plan is distributed to the temporary take-off and landing points, clustering the temporary take-off and landing points according to the temporary take-off and landing point set generated in the step 2, the average area capacity per capacity, the high and low altitude boundary highLimit, the maximum distance of area clustering and the plan which does not meet the constraint but is not successfully distributed in the process to form an area, and finally generating a group of area lists, wherein the maximum distance constraint of area clustering means that the distance from the non-clustered temporary take-off and landing points to a first temporary take-off and landing point added into the area does not exceed the maximum distance;
and 4, forcibly distributing unreduced patrol items (unreduced to a plan list of temporary take-off and landing points), after the basic division of the areas is completed, forcibly distributing the unallocated items which are not restricted by the distance between the temporary take-off and landing points to the areas corresponding to the nearest temporary take-off and landing points, and simultaneously, forcibly meeting the requirement that the average annual patrol capacity of each area is not exceeded.
According to practical constraints, an aircraft with a high flight ceiling can patrol a high altitude plan and a low altitude plan, while an aircraft with a low flight ceiling can only patrol a low altitude plan, and all high altitude plans have high priority, so that the step needs to process high altitude projects first. The method comprises the following steps:
(4-1) according to whether the temporary take-off and landing points include the high-altitude plan or not, the temporary take-off and landing points are divided into two types, wherein the first type is a temporary take-off and landing point set S containing the high-altitude planhighThe second type is a temporary set of take-off and landing points S containing only low-altitude planslow。
Shigh＝{x|x.ceilingUp≥highLimit，x∈P}
Slow＝{x|x.ceilingUp＜highLimit，x∈P}
Wherein, P represents the sum of all items to be patrolled arranged to the temporary take-off and landing point, and highLimit represents a high-low altitude boundary;
(4-2), toAll temporary take-off and landing point sets including high altitude plans are clustered, i.e. set ShighAnd (6) clustering. The basic core algorithm of clustering is as follows:
1) newly building an area A, from ShighTaking out a temporary take-off and landing point and recording the temporary take-off and landing point as LINiAdding into the area A;
2) jiliniIs ShighCalculating the distance d between other temporary take-off and landing points and the temporary take-off and landing point to generate a set:
D＝{d|d＝distance(Li，L1)，i∈Z，i≤size(Shigh)，i≠1}
3) selecting a minimum distance from the set D, judging whether a temporary take-off and landing point corresponding to the distance can be added into the area A, and if the total capacity of the area is not exceeded, adding the temporary take-off and landing point into the area A; the total capacity is over, and no operation is carried out;
4) removing the minimum distance from the set D, and if the set D is empty, carrying out the next step; if not, repeating the step 2) to the step 4);
(4-3) after the clustering of the temporary take-off and landing points including the high altitude is finished, the high altitude area starts to absorb the temporary take-off and landing points with the low altitude, the core constraint is still a distance, and whether the plan can be added into the area corresponding to the nearest temporary take-off and landing point is judged according to whether the distance is nearest and whether the area capacity is exceeded; the specific steps are basically the same as those in (4-2);
(4-4) after the high-altitude plan is used for absorbing the low-altitude temporary take-off and landing points, possibly remaining part of the low-altitude temporary take-off and landing points, similarly clustering the remaining low-altitude temporary take-off and landing points according to the step (4-1), and then executing the same processing as the step (4-2);
and (4-5) returning all the generated regions after clustering is completed.
And 5, recording the item which still cannot be inserted after the step is completed as a part of the final return.
The total plan length in fig. 1 refers to the sum of the patrol route lengths in all patrol plans.
As shown in fig. 3, data provided by the space flight is used as an input parameter of the optimization method for dividing the space flight patrol plan region, and is successfully divided into 4 regions: the specific result is shown in the figure, wherein the first area comprises 1 temporary take-off and landing point, and the temporary take-off and landing point comprises 87 plans.

Claims (3)

1. An optimization method for division of a space patrol plan region is characterized by comprising the following steps:
step (1), taking the patrol plan as input data, establishing a plan to be patrolled and a patrol route LiThe corresponding relation set of (2);
step (2), allocating a patrol plan to the temporary take-off and landing points according to the two constraint conditions of the distance between the temporary take-off and landing points and the patrol line corresponding to the plan and the online rate;
step (3), clustering the temporary take-off and landing points into areas according to two constraint conditions of the capacity of the patrol areas and the maximum distance of area clustering;
step (4), according to the constraint condition of the altitude plan, a plan list which is not summarized to the temporary take-off and landing point is forcibly distributed;
and (5) recording the inspection plan which still cannot be summarized as a part of the data returned finally.
2. The optimization method for division of the aerospace patrol plan region according to claim 1, wherein the step (2) further specifically includes the following steps:
calculating the distance between the temporary take-off and landing point and the patrol line corresponding to the plan, and selecting and recording the closest distance dis _ pa between the temporary take-off and landing point and the patrol line corresponding to the plan; calculating the online rate of patrolling the patrolling line corresponding to the plan from the temporary take-off and landing point, wherein the online rate formula is as follows:
per_on＝t_on/t_on+t_off
t_on＝l_len/v_on
t_off＝dis_pa+dis_st+dis_pen
wherein per _ on is an online rate, t _ on is the online flight time of the airplane during the inspection of the line, and t _ off is the offline flight time of the airplane;
for each temporary take-off and landing point, selecting a minimum value min _ dis _ pa in the nearest distance and a maximum value max _ per _ on of the online rate;
if the distance constraint landingPointdistance for summarizing the plan to the temporary rising and falling point is less than or equal to min _ dis _ pa, summarizing the plan to the corresponding temporary rising and falling point; if the maximum online rate max _ per _ on is not met, judging the limiting condition, and if the maximum online rate max _ per _ on is greater than or equal to the maximum online rate specified by the system, namely 80% online rate, summarizing the plan to the corresponding temporary take-off and landing point;
and putting the plans which are not summarized to the temporary take-off and landing points into a plan list which is not summarized to the temporary take-off and landing points for the plans which are not summarized to the temporary take-off and landing points through the steps.
3. The optimization method for division of the aerospace patrol plan region according to claim 1, wherein the step (4) further specifically includes the following steps:
the temporary take-off and landing points are divided into two categories, namely the first category is the set S of temporary take-off and landing points containing plans for high altitudehighThe second type is a temporary set of take-off and landing points S containing only low-altitude planslow；
Clustering all temporary take-off and landing point sets including high altitude plans, i.e. set ShighClustering is carried out;
after the clustering of the temporary take-off and landing points at high altitude is finished, the high-altitude area starts to absorb the temporary take-off and landing points at low altitude, and whether the plan can be added into the area corresponding to the nearest temporary take-off and landing point is judged according to whether the distance between the temporary take-off and landing points is nearest and whether the capacity of the area is exceeded;
clustering the rest low-altitude temporary take-off and landing points;
and after the clustering is finished, returning all the generated regions.
CN201610780816.XA 2016-08-31 2016-08-31 Optimization method for division of aerospace patrol plan region Expired - Fee Related CN106384161B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610780816.XA CN106384161B (en) 2016-08-31 2016-08-31 Optimization method for division of aerospace patrol plan region

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610780816.XA CN106384161B (en) 2016-08-31 2016-08-31 Optimization method for division of aerospace patrol plan region

Publications (2)

Publication Number Publication Date
CN106384161A CN106384161A (en) 2017-02-08
CN106384161B true CN106384161B (en) 2020-12-29

Family

ID=57939332

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610780816.XA Expired - Fee Related CN106384161B (en) 2016-08-31 2016-08-31 Optimization method for division of aerospace patrol plan region

Country Status (1)

Country Link
CN (1) CN106384161B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909739B (en) * 2017-02-28 2018-04-27 中国人民解放军空军装备研究院雷达与电子对抗研究所 A kind of the departure procedure optimization method and device of operation of persistently climbing
CN107515003B (en) * 2017-07-19 2020-08-11 中国南方电网有限责任公司超高压输电公司检修试验中心 Method for planning flight route of airplane for patrolling power transmission line
CN109508868B (en) * 2018-10-22 2022-06-28 南京航空航天大学 Efficient intelligent air traffic area division system
CN109508867B (en) * 2018-10-22 2022-06-28 南京航空航天大学 Air traffic area division method based on fuzzy C-means clustering
CN111161443A (en) * 2019-01-17 2020-05-15 浙江诸暨美数信息科技有限公司 Patrol path setting method based on historical data
CN114693023A (en) * 2020-12-29 2022-07-01 江苏金恒信息科技股份有限公司 Equipment point inspection system and operation method thereof

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496884A (en) * 2011-11-17 2012-06-13 广东电网公司广州供电局 Method and device for formulating line patrol flight scheme of helicopter
US9162753B1 (en) * 2012-12-31 2015-10-20 Southern Electrical Equipment Company, Inc. Unmanned aerial vehicle for monitoring infrastructure assets
CN103824340B (en) * 2014-03-07 2015-12-02 山东鲁能智能技术有限公司 Unmanned plane power transmission line intelligent cruising inspection system and method for inspecting
CN103812052B (en) * 2014-03-07 2016-06-01 国家电网公司 A kind of for without the centralized monitoring system of man-machine polling transmission line and monitoring method
CN105549619B (en) * 2016-02-03 2020-11-03 武汉大势智慧科技有限公司 Multi-take-off and landing point route planning method for cruising ability of unmanned aerial vehicle
CN106056250A (en) * 2016-06-02 2016-10-26 国网天津市电力公司 Power distribution network patrol method based on path optimization

Also Published As

Publication number Publication date
CN106384161A (en) 2017-02-08

Similar Documents

Publication Publication Date Title
CN106384161B (en) Optimization method for division of aerospace patrol plan region
CN109508812B (en) Aircraft track prediction method based on deep memory network
CN109902954B (en) Flexible job shop dynamic scheduling method based on industrial big data
CN112464784A (en) Distributed training method based on hybrid parallel
CN102081706B (en) Process planning method based on similarity theory
CN104751681B (en) Statistical learning model based gate position allocation method
KR102042318B1 (en) Smart Factory Layout Design Method and System
CN104820733B (en) A kind of bullet train demand meta-model method for building up and device
CN109492774A (en) A kind of cloud resource dispatching method based on deep learning
CN112633562B (en) Airport stand intelligent scheduling method
CN113657671B (en) Flight delay prediction method based on ensemble learning
CN109840610A (en) Irregular flight aircraft path and passenger's stroke automatic recovery system and method
CN106127229A (en) A kind of computer data sorting technique based on time series classification
CN105808582A (en) Parallel generation method and device of decision tree on the basis of layered strategy
CN103425774A (en) Tacit knowledge acquisition method based on HWME (Hall for Workshop of Metasynthetic Engineering)
CN110378744A (en) Civil aviaton's frequent flight passenger value category method and system towards incomplete data system
CN115564204B (en) Parallel processing method for demand resource allocation in supply chain
CN103714396A (en) Rapid intelligent optimization method and system for motor train unit application and maintenance scheme
CN111191845A (en) Power communication network work monotony scheduling method based on DBSCAN algorithm and KMP mode matching method
CN113112874A (en) Collaborative optimization allocation method for air route time slot and height layer
CN101887531B (en) Flight data knowledge acquisition system and acquisition method thereof
CN116258438A (en) Workshop logistics knowledge graph construction and logistics equipment path planning method
Patil Machine Learning for Traffic Management in Large-Scale Urban Networks: A Review
CN108364030A (en) A kind of multi-categorizer model building method based on three layers of dynamic particles group's algorithm
CN112667606A (en) Knowledge base system based on multi-source knowledge acquisition technology and construction method thereof

Legal Events

Date Code Title Description
C06 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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20201229

Termination date: 20210831