CN112101780A - Airport scene operation comprehensive evaluation method based on structure entropy weight method - Google Patents
Airport scene operation comprehensive evaluation method based on structure entropy weight method Download PDFInfo
- Publication number
- CN112101780A CN112101780A CN202010965058.5A CN202010965058A CN112101780A CN 112101780 A CN112101780 A CN 112101780A CN 202010965058 A CN202010965058 A CN 202010965058A CN 112101780 A CN112101780 A CN 112101780A
- Authority
- CN
- China
- Prior art keywords
- airport
- time
- index
- actual
- planned
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000011156 evaluation Methods 0.000 title claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 18
- 238000013459 approach Methods 0.000 claims description 13
- 230000000903 blocking effect Effects 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 230000035484 reaction time Effects 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000006872 improvement Effects 0.000 abstract description 8
- 230000008447 perception Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000010006 flight Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013278 delphi method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000019580 granularity Nutrition 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012163 sequencing technique Methods 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention belongs to the technical field of airport operation information perception and identification, and particularly relates to an airport scene operation comprehensive evaluation method based on a structure entropy weight method, wherein the airport scene operation comprehensive evaluation method based on the structure entropy weight method comprises the following steps: extracting relevant data of airport scene operation and preprocessing the data; defining and calculating relevant indexes of airport scene operation; carrying out grade division on the related index values; calculating the weight of each index; and evaluating the operation of the airport according to the grade and the corresponding weight of each index, thereby realizing reasonable evaluation of the operation efficiency of the airport surface, finding the short operation plate of the airport surface, and supporting the operation quality improvement and efficiency improvement of the airport surface.
Description
Technical Field
The invention belongs to the technical field of airport operation information perception and recognition, and particularly relates to an airport scene operation comprehensive evaluation method based on a structure entropy weight method.
Background
With the continuous expansion of air traffic networks, the operation of air traffic activities is more complicated. The airport is one of three important participants in the air traffic field, and the operation efficiency of the airport scene directly influences the operation condition of the whole air traffic system. Therefore, how to objectively evaluate the operation efficiency of the airport scene to find the short operation link and improve the operation efficiency of the airport scene becomes a technical problem which is urgently solved by the requirements of the airport and the relevant parties of the whole air traffic system.
The current research on the operation efficiency of airport scenes mainly focuses on the relevant field of flight taxi optimization. The technology focuses on monitoring the taxiing process of the aircraft from a single link, and only focuses on the time-space behavior of the aircraft at each key node of a key taxiway, so that the taxiing path of the aircraft is planned. However, there are few relevant studies on the evaluation of the airport surface operation efficiency from the aspect of the airport surface operation full flow, and a method for scientifically and reasonably evaluating the airport surface operation efficiency from a macro level is lacked.
Therefore, a new comprehensive evaluation method for airport scene operation based on the structure entropy weight method needs to be designed based on the technical problems.
Disclosure of Invention
The invention aims to provide a comprehensive evaluation method for airport scene operation by a structure entropy weight method.
In order to solve the technical problem, the invention provides an airport scene operation comprehensive evaluation method based on a structure entropy weight method combined subjectively and objectively, which comprises the following steps:
extracting relevant data of airport scene operation and preprocessing the data;
defining and calculating relevant indexes of airport scene operation;
carrying out grade division on the related index values;
calculating the weight of each index; and
and evaluating the operation of the airport according to the grade and the corresponding weight of each index.
Further, the method for extracting and preprocessing the relevant data of airport scene operation comprises the following steps:
extraction of data relevant to airport scene operations, i.e.
Extracting a planned take-off airport, an actual take-off airport, a planned landing airport, an actual landing airport, a planned arrival time, an actual arrival time, a planned departure time, an actual departure time, a planned closing time of a cabin door, an actual closing time of the cabin door, a planned removing time of a wheel gear, an actual removing time of the wheel gear, a planned blocking time of the wheel gear, an actual blocking time of the wheel gear, a planned pushing time and an actual pushing time from a flight plan database and a production system database according to the flight number;
preprocessing the extracted airport scene operation-related data, i.e.
And screening the extracted operation related data of all airport scenes to delete the records of missing planned take-off airports, actual take-off airports, planned landing airports, actual landing airports, planned arrival time, actual arrival time, planned departure time, actual departure time, planned cabin door closing time, actual cabin door closing time, planned wheel gear withdrawing time, actual wheel gear withdrawing time, planned wheel gear blocking time, actual wheel gear blocking time, planned wheel gear pushing time and actual pushing time.
Further, the method for defining and calculating the airport scene operation related index comprises the following steps:
defining the relevant indexes of airport surface operation and calculating the relevant indexes of airport surface operation, namely
Extracting all indexes influencing the operation efficiency of the airport scene from the operation flow according to the operation flow of the airport scene, and calculating the relevant indexes of the airport scene operation according to the preprocessed data related to the airport scene operation;
the indicators include: airport approach throughput, airport departure throughput, slide-in time bias, additional slide-in time, slide-out time bias, additional slide-out time, transit time bias, additional transit time, push-out reaction time bias, approach delay time, departure delay time, onboard delay time, arrival punctuation rate, departure punctuation rate, wheel gear shift punctuation rate, wheel gear withdrawal punctuation rate.
Further, the method for ranking the correlation index values includes:
step S1, inputting an efficacy index data set D of n different data values of the same index and the estimated grade number k;
step S2, randomly generating k grade centers C according to the current index data set Di(i ═ 1, 2.. times, k), the k rank centers CiFor randomly selected k data points p (p ∈ D);
step S3, calculating each data point p and each cluster level center CiOf Euclidean distance dji：dji＝|pj-Ci|2；
Wherein p isj∈D(j＝1,2,...,n)；
Step S4, dividing all data points p into grades k represented by grade centers with Euclidean distances being the nearest;
step S5, calculate the mean of all data points in k levels and as the center of the corresponding level:
wherein n isiRepresents all data points belonging to the ith level;
step S6, when the grade center C 'is updated'iGrade center C from last iterationiWhen the difference value of (a) is less than the threshold value or the iteration frequency reaches the maximum value, stopping the iteration; otherwise, go to step S2 to continue execution;
in step S7, the maximum value and the minimum value in each level are output as the threshold range of the level to complete the level division of the correlation index value.
Further, the method for calculating the weight of each index comprises the following steps:
t experts rank the indexes respectively, and the corresponding expert ranking vector A (i) is: a (i) ═ ai1,...,aij,...,ain}；
The ranking matrix a for all experts is:
wherein, aijThe sequence number of the ith expert for the jth index is represented;
according to the sorting matrix A, a membership function of sorting transformation is defined for the sorting result by adopting an entropy theory:
χ(L)＝-λpn(L)lnpn(L)；
when in use
When the temperature of the water is higher than the set temperature,
when in use
When the temperature of the water is higher than the set temperature,
z is defined as [0,1 ]]Taking z (L) as a membership function of L, wherein L is a sorting sequence number in the sorting matrix, and L is 1, 2. m is a transformation parameter, and j + 2; p is a radical ofn(L) is a membership deviation function; λ is a membership parameter;
ordering a in the matrixijSubstituting z (L), z (u)ij)＝vij；
vijFor the membership degree of the sequence number L, a membership degree matrix V ═ is constructedij)t×n；
Calculating the average identification degree v of the expert for any index in the index set based on the membership matrixj：
Uncertainty definition variable s in expert rank vectorsjThen sjComprises the following steps:
the overall identification value of the index is recorded as yj：
yj＝vj(1-sj)；
The overall identification vector of each index in the index set is Y ═ Y1,y2,...,yn}；
Converting the integral identification vector into a weight vector alpha according to normalizationj：
The weight vector of the output normalized index set is W ═ a1,a2,...,anAnd obtaining the weight of each index.
Further, the method for evaluating the operation of the airport according to the grade and the corresponding weight of each index comprises the following steps:
dividing a threshold range according to the obtained grades of the indexes, grading the grades, and obtaining grade grades of the index values;
and evaluating the operation condition of the airport scene according to the weight of each index and the obtained score of each index value.
The invention has the beneficial effects that the invention extracts the relevant data of airport scene operation and carries out pretreatment; defining and calculating relevant indexes of airport scene operation; carrying out grade division on the related index values; calculating the weight of each index; and evaluating the operation of the airport according to the grade and the corresponding weight of each index, thereby realizing reasonable evaluation of the operation efficiency of the airport surface, finding the short operation plate of the airport surface, and supporting the operation quality improvement and efficiency improvement of the airport surface.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a comprehensive evaluation method for airport scene operation based on a structure entropy weight method of subjective and objective combination according to the present invention;
fig. 2 is a schematic diagram of a framework of an airport surface operation comprehensive evaluation index according to the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. 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.
Example 1
FIG. 1 is a flow chart of a comprehensive evaluation method for airport scene operation based on a structure entropy weight method of subjective and objective combination according to the invention.
As shown in fig. 1, this embodiment 1 provides a comprehensive evaluation method for airport scene operation based on a structure entropy weight method based on subjective and objective combination, which includes: extracting relevant data of airport scene operation and preprocessing the data; defining and calculating relevant indexes of airport scene operation; carrying out grade division on the related index values according to a clustering algorithm; calculating each index weight according to a structure entropy weight method combined subjectively and objectively; and evaluating the operation of the airport according to the grade and the corresponding weight of each index, thereby realizing reasonable evaluation of the operation efficiency of the airport surface, finding the short operation plate of the airport surface, and supporting the operation quality improvement and efficiency improvement of the airport surface.
In this embodiment, the method for extracting and preprocessing the data related to airport scene operation includes: extracting airport scene operation related data, namely extracting a planned take-off airport, an actual take-off airport, a planned landing airport, an actual landing airport, planned arrival time, actual arrival time, planned departure time, actual departure time, planned closing time, actual closing time, planned removing time, actual removing time, planned blocking time, actual blocking time, planned pushing time, actual pushing time and the like from a flight planning database and a production system database according to flight numbers (taking the flight numbers as key words), wherein the data can be used for subsequent index calculation;
preprocessing the extracted airport scene operation related data, namely, performing validity screening on all the extracted airport scene operation related data to delete the missing records of a planned take-off airport, an actual take-off airport, a planned landing airport, an actual landing airport, planned arrival time, actual arrival time, planned departure time, actual departure time, planned closing time, actual closing time, planned gear-removing time, actual gear-removing time, planned gear-blocking time, actual gear-blocking time, planned push-out time and actual push-out time; the required data are accurately acquired, and the subsequent index calculation is more accurate.
Fig. 2 is a schematic diagram of a framework of an airport surface operation comprehensive evaluation index according to the present invention.
As shown in fig. 2, in this embodiment, the method for defining and calculating the airport surface operation related index includes: defining relevant indexes of airport scene operation, and calculating the relevant indexes of the airport scene operation, namely extracting all indexes which possibly influence the operation efficiency of the airport scene under the current data condition from the operation flow according to the operation flow of the airport scene, relatively completely combing various key indexes relevant to the airport scene operation, and calculating the relevant indexes of the airport scene operation according to the preprocessed relevant data of the airport scene operation;
the indicators include: airport approach throughput, airport departure throughput, slide-in time deviation, additional slide-in time, slide-out time deviation, additional slide-out time, station passing time deviation, additional station passing time, push-out reaction time deviation, approach delay time, departure delay time, onboard delay time, arrival punctuation rate, departure punctuation rate, wheel gear blocking punctuation rate and wheel gear withdrawal punctuation rate are 19 indexes in total, and calculation of different statistical granularities such as 15 minutes, 30 minutes, 60 minutes, days and months is supported; the calculation method of the index comprises the following steps:
airport approach throughput: obtaining the actual number of arriving flights in a given time period based on the actual landing time;
airport departure throughput: obtaining the actual takeoff flight number in a given time period based on the actual takeoff time;
the slide-in time is as follows: subtracting the actual gear shift time from the actual landing time;
slip-in time offset: subtracting the smooth slide-in time from the congestion slide-in time;
additional slide-in time: subtracting the smooth-in time from the slide-in time;
slide-out time: subtracting the actual gear removing time from the actual takeoff time;
slip-out time offset: subtracting the smooth slide-out time from the jammed slide-out time;
additional roll-off time: subtracting the smooth slide out time from the slide out time;
the station-passing time is as follows: subtracting the actual gear shifting time from the actual gear shifting time;
deviation of the station-passing time: subtracting the unblocked station-passing time from the blocked station-passing time;
additional station-crossing time: subtracting the clear station-passing time from the station-passing time;
deducing the reaction time deviation: subtracting the actual ready-to-push time from the actual gear withdrawing time and subtracting the unblocked push-out reaction time from the actual gear withdrawing time;
approach delay time: subtracting the planned landing time from the actual landing time plus the standard harboring sliding time;
off-field delay time: subtracting the planned takeoff time from the actual takeoff time and subtracting the standard departure taxi time;
delay time on board: subtracting the actual door closing time from the actual take-off time and subtracting the empirical slide-out time from the actual door closing time;
the arrival punctuality rate: dividing the difference of the approach throughput minus the amount of approach delay flights by the approach throughput;
departure punctuality rate: dividing the difference of the departure throughput minus the departure delay flight quantity by the departure throughput;
the gear shift time punctuality rate of the gear wheel: dividing the difference of the approach throughput minus the delayed flight amount of the gear shift by the approach throughput;
and (3) gear removing moment punctual rate: dividing the difference of the departure throughput minus the delayed flight amount of the wheel-withdrawing gear by the departure throughput; according to the indexes, the airport scene operation efficiency is evaluated from the aspect of the airport scene operation full flow; the data involved in the index calculation may be extracted from the flight plan database and the production system database.
In this embodiment, the method for ranking correlation index values includes:
step S1, inputting an efficacy index data set D of n different data values of the same index and the expected grade number K of the division (inputting the grade division number K and each index value into a K-means clustering algorithm to obtain a clustering result after each index value is divided into K classes);
step S2, randomly generating k grade centers C according to the current index data set Di(i ═ 1, 2.. times, k), the k rank centers CiFor randomly selected k data points p (p ∈ D);
step S3, calculating each data point p and each clusterGrade center CiOf Euclidean distance dji：
dji＝|pj-Ci|2；
Wherein p isj∈D(j＝1,2,...,n)；
Step S4, dividing all data points p into grades k represented by grade centers with Euclidean distances being the nearest;
step S5, calculate the mean of all data points in k levels and as the center of the corresponding level:
wherein n isiRepresents all data points belonging to the ith level;
step S6, when the grade center C 'is updated'iGrade center C from last iterationiWhen the difference value of (a) is less than the threshold value or the iteration frequency reaches the maximum value, stopping the iteration; otherwise, go to step S2 to continue execution;
in step S7, the maximum value and the minimum value in each class (the values in the result of each class of each index are sorted in ascending order, and the maximum value and the minimum value in each class are output) are output as the threshold range of the class, so that the classification of the correlation index value is completed.
In this embodiment, the method for calculating the weights of the indexes includes: in order to reduce the judgment error of expert opinions on a multi-index multi-level target system, final weight is set by combining the expert opinions and a scientific method; in the structural entropy weight assignment method, a multi-level evaluation index system is disassembled into a single-level independent structure, and potential deviation in the subjective assignment process is eliminated through objective quantitative analysis of entropy and expert subjective identification uncertainty so as to obtain importance measurement of each basic index in a single-level structure; sorting the importance of each index by using an importance sorting matrix of a Delphi method based on the industrial experience of a plurality of experts, and outputting an importance sorting matrix of relevant indexes of airport scene operation;
supposing that t experts participate in consultation, the t experts rank the importance of each index according to experience and knowledge, and the corresponding expert ranking vector A (i) is as follows: a (i) ═ ai1,...,aij,...,ain}；
After all experts perform multiple rounds of evaluation, a ranking matrix a that can be formed is:
wherein, aijThe sequence number of the ith expert to the jth index and the first rule a of the importance ranking of the indexesijIs 1, the second rule aij2, and so on;
according to the ranking matrix A, an entropy theory (entropy information) is adopted to reduce uncertainty caused by different cognition of experts, reduce deviation caused by subjective factors, further calculate the weight of relatively stable indexes, and define a membership function of ranking conversion for a ranking result:
χ(L)＝-λpn(L)lnpn(L)；
when in use
When the temperature of the water is higher than the set temperature,
when in use
When the temperature of the water is higher than the set temperature,
z is defined as [0,1 ]]The variable above is represented by z (L) as a membership function of L, where L is a ranking number in the ranking matrix, L is 1, 2., j, j +1,j is the maximum value of the sequencing sequence number; m is a transformation parameter, and j + 2; p is a radical ofn(L) is a membership deviation function; λ is a membership parameter;
ordering a in the matrixijSubstituting z (L), z (u)ij)＝vij；
vijFor the degree of membership of the rank L, a matrix V ═ V (V) can be constructed therefromij)t×n；
Calculating the average identification degree v of the expert for any index in the index set based on the membership matrixj：
Defining a variable s for uncertainty in an expert ranking number vectorjThen sjComprises the following steps:
the overall identification value of the index is recorded as yj：
yj＝vj(1-sj)；
The overall identification vector of each index in the index set is Y ═ Y1,y2,...,yn}；
Processing according to normalization to convert the whole identification vector into weight vector alphaj：
The weight vector of the output normalized index set is W ═ a1,a2,...,anAnd obtaining the weight of each index.
In this embodiment, the method for evaluating the operation of the airport according to the grade and the corresponding weight of each index includes: acquiring grade scores, and comprehensively evaluating the airport scene operation conditions according to the grade scores and the weights of all indexes; grading each grade according to the obtained grade division threshold range of each index and combining with expert prior knowledge to obtain the grade of each index value; and evaluating the operation condition of the airport scene according to the weight of each index and the obtained score of each index value, so as to realize objective evaluation of the operation efficiency of the airport scene, find short operation link boards and improve the operation efficiency of the airport scene.
In conclusion, the method extracts the relevant data of airport scene operation and carries out preprocessing; defining and calculating relevant indexes of airport scene operation; carrying out grade division on the related index values; calculating the weight of each index; and evaluating the operation of the airport according to the grade and the corresponding weight of each index, thereby realizing reasonable evaluation of the operation efficiency of the airport surface, finding the short operation plate of the airport surface, and supporting the operation quality improvement and efficiency improvement of the airport surface.
In the several embodiments provided herein, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (6)
1. A comprehensive evaluation method for airport scene operation based on an objective and subjective combined structure entropy weight method is characterized by comprising the following steps:
extracting relevant data of airport scene operation and preprocessing the data;
defining and calculating relevant indexes of airport scene operation;
carrying out grade division on the related index values;
calculating the weight of each index; and
and evaluating the operation of the airport according to the grade and the corresponding weight of each index.
2. The method of comprehensive evaluation of airport surface operations of claim 1,
the method for extracting and preprocessing the airport scene operation related data comprises the following steps:
extraction of data relevant to airport scene operations, i.e.
Extracting a planned take-off airport, an actual take-off airport, a planned landing airport, an actual landing airport, a planned arrival time, an actual arrival time, a planned departure time, an actual departure time, a planned closing time of a cabin door, an actual closing time of the cabin door, a planned removing time of a wheel gear, an actual removing time of the wheel gear, a planned blocking time of the wheel gear, an actual blocking time of the wheel gear, a planned pushing time and an actual pushing time from a flight plan database and a production system database according to the flight number;
preprocessing the extracted airport scene operation-related data, i.e.
And screening the extracted operation related data of all airport scenes to delete the records of missing planned take-off airports, actual take-off airports, planned landing airports, actual landing airports, planned arrival time, actual arrival time, planned departure time, actual departure time, planned cabin door closing time, actual cabin door closing time, planned wheel gear withdrawing time, actual wheel gear withdrawing time, planned wheel gear blocking time, actual wheel gear blocking time, planned wheel gear pushing time and actual pushing time.
3. The method of comprehensive evaluation of airport surface operations of claim 2,
the method for defining and calculating the relevant indexes of the airport scene operation comprises the following steps:
defining the relevant indexes of airport surface operation and calculating the relevant indexes of airport surface operation, namely
Extracting all indexes influencing the operation efficiency of the airport scene from the operation flow according to the operation flow of the airport scene, and calculating the relevant indexes of the airport scene operation according to the preprocessed data related to the airport scene operation;
the indicators include: airport approach throughput, airport departure throughput, slide-in time bias, additional slide-in time, slide-out time bias, additional slide-out time, transit time bias, additional transit time, push-out reaction time bias, approach delay time, departure delay time, onboard delay time, arrival punctuation rate, departure punctuation rate, wheel gear shift punctuation rate, wheel gear withdrawal punctuation rate.
4. The method of comprehensive evaluation of airport surface operations of claim 3,
the method for grading the correlation index value comprises the following steps:
step S1, inputting an efficacy index data set D of n different data values of the same index and the estimated grade number k;
step S2, randomly generating k grade centers C according to the current index data set Di(i ═ 1, 2.. times, k), the k rank centers CiFor randomly selected k data points p (p ∈ D);
step S3, calculating each data point p and each cluster level center CiOf Euclidean distance dji：dji＝|pj-Ci|2；
Wherein p isj∈D(j＝1,2,...,n)；
Step S4, dividing all data points p into grades k represented by grade centers with Euclidean distances being the nearest;
step S5, calculate the mean of all data points in k levels and as the center of the corresponding level:
wherein n isiRepresents all data points belonging to the ith level;
step S6, when the grade center C 'is updated'iGrade center C from last iterationiWhen the difference value of (a) is less than the threshold value or the iteration frequency reaches the maximum value, stopping the iteration; otherwise, go to step S2 to continue execution;
in step S7, the maximum value and the minimum value in each level are output as the threshold range of the level to complete the level division of the correlation index value.
5. The method of comprehensive evaluation of airport surface operations of claim 4,
the method for calculating the weight of each index comprises the following steps:
t experts rank the indexes respectively, and the corresponding expert ranking vector A (i) is:
A(i)＝{ai1,...,aij,...,ain}；
the ranking matrix a for all experts is:
wherein, aijThe sequence number of the ith expert for the jth index is represented;
according to the sorting matrix A, a membership function of sorting transformation is defined for the sorting result by adopting an entropy theory:
χ(L)＝-λpn(L)lnpn(L)；
when in use
When the temperature of the water is higher than the set temperature,
when in use
When the temperature of the water is higher than the set temperature,
z is defined as [0,1 ]]Taking z (L) as a membership function of L, wherein L is a sorting sequence number in the sorting matrix, and L is 1, 2. m is a transformation parameter, and j + 2; p is a radical ofn(L) is a membership deviation function; λ is a membership parameter;
ordering a in the matrixijSubstituting z (L), z (u)ij)＝vij；
vijFor the membership degree of the sequence number L, a membership degree matrix V ═ is constructedij)t×n；
Calculating the average identification degree v of the expert for any index in the index set based on the membership matrixj：
Uncertainty definition variable s in expert rank vectorsjThen sjComprises the following steps:
the overall identification value of the index is recorded as yj：
yj＝vj(1-sj)；
The overall identification vector of each index in the index set is Y ═ Y1,y2,...,yn}；
Converting the integral identification vector into a weight vector alpha according to normalizationj：
The weight vector of the output normalized index set is W ═ a1,a2,...,anAnd obtaining the weight of each index.
6. The method of comprehensive evaluation of airport surface operations of claim 5,
the method for evaluating the operation of the airport according to the grade and the corresponding weight of each index comprises the following steps:
dividing a threshold range according to the obtained grades of the indexes, grading the grades, and obtaining grade grades of the index values;
and evaluating the operation condition of the airport scene according to the weight of each index and the obtained score of each index value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010965058.5A CN112101780A (en) | 2020-09-15 | 2020-09-15 | Airport scene operation comprehensive evaluation method based on structure entropy weight method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010965058.5A CN112101780A (en) | 2020-09-15 | 2020-09-15 | Airport scene operation comprehensive evaluation method based on structure entropy weight method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112101780A true CN112101780A (en) | 2020-12-18 |
Family
ID=73751044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010965058.5A Pending CN112101780A (en) | 2020-09-15 | 2020-09-15 | Airport scene operation comprehensive evaluation method based on structure entropy weight method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101780A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570186A (en) * | 2021-06-11 | 2021-10-29 | 飞友科技有限公司 | Airport operation efficiency evaluation method and device based on multidimensional indexes |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473469A (en) * | 2013-09-25 | 2013-12-25 | 南京航空航天大学 | Sector traffic state multilevel fuzzy evaluation method based on objective indicator |
| CN108710623A (en) * | 2018-03-13 | 2018-10-26 | 南京航空航天大学 | Airport departure from port delay time at stop prediction technique based on Time Series Similarity measurement |
-
2020
- 2020-09-15 CN CN202010965058.5A patent/CN112101780A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473469A (en) * | 2013-09-25 | 2013-12-25 | 南京航空航天大学 | Sector traffic state multilevel fuzzy evaluation method based on objective indicator |
| CN108710623A (en) * | 2018-03-13 | 2018-10-26 | 南京航空航天大学 | Airport departure from port delay time at stop prediction technique based on Time Series Similarity measurement |
Non-Patent Citations (2)
| Title |
|---|
| 赵立: "基于聚类熵权的空港竞争力评价", 中国优秀硕士学位论文全文数据库, no. 2016, 15 February 2016 (2016-02-15), pages 151 - 150 * |
| 郝志峰 等: "《数据科学与数学建模》", vol. 2019, 31 January 2019, 华中科技大学出版社, pages: 36 - 41 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570186A (en) * | 2021-06-11 | 2021-10-29 | 飞友科技有限公司 | Airport operation efficiency evaluation method and device based on multidimensional indexes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112101779A (en) | Comprehensive evaluation system for airport scene operation based on subjective and objective combination structure entropy weight method | |
| CN109191922B (en) | Large-scale four-dimensional track dynamic prediction method and device | |
| CN110503245B (en) | Prediction method for large-area delay risk of airport flight | |
| CN108710623B (en) | Airport departure delay time prediction method based on time series similarity measurement | |
| CN113159364A (en) | Passenger flow prediction method and system for large-scale traffic station | |
| Utari et al. | Implementation of data mining for drop-out prediction using random forest method | |
| CN107633035B (en) | Shared traffic service reorder estimation method based on K-Means and LightGBM model | |
| CN110942171A (en) | Enterprise labor and resource dispute risk prediction method based on machine learning | |
| CN111599219B (en) | Multi-data-source flight takeoff time prediction method based on sequencing learning | |
| CN112183605A (en) | Civil aviation control sector classification method based on operation characteristics | |
| CN115438849A (en) | Demand prediction method for subsequent spare parts of equipment based on ensemble learning | |
| Wu et al. | An improved svm model for flight delay prediction | |
| CN113657671A (en) | Flight delay prediction method based on ensemble learning | |
| Singh et al. | Feature selection based classifier combination approach for handwritten Devanagari numeral recognition | |
| CN112101780A (en) | Airport scene operation comprehensive evaluation method based on structure entropy weight method | |
| Lu et al. | Flight delay prediction using gradient boosting machine learning classifiers | |
| Schösser et al. | On the Performance of Machine Learning Based Flight Delay Prediction–Investigating the Impact of Short-Term Features | |
| CN109165854B (en) | Empty pipe operation efficiency grade evaluation method and device | |
| CN116956757A (en) | Departure flight taxi time prediction method, electronic device, and storage medium | |
| Gürbüz et al. | Classification rule discovery for the aviation incidents resulted in fatality | |
| Rao et al. | Flight Ticket Prediction using Random Forest Regressor Compared with Decision Tree Regressor | |
| Almaameri et al. | Predicting Airplane Flight Delays Using Neural Networks | |
| CN111090793B (en) | Airport day delay characteristic classification method based on average delay time sequence | |
| Widiyaningtyas et al. | Use of ARIMA method to predict the number of train passenger in Malang City | |
| Zhang et al. | Research on improvement and optimisation of modelling method of China’s civil aircraft market demand forecast model |
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 |