CN105045665B - Driving cabin dynamic function-allocation method based on operator's functional status - Google Patents
Driving cabin dynamic function-allocation method based on operator's functional status Download PDFInfo
- Publication number
- CN105045665B CN105045665B CN201510378767.2A CN201510378767A CN105045665B CN 105045665 B CN105045665 B CN 105045665B CN 201510378767 A CN201510378767 A CN 201510378767A CN 105045665 B CN105045665 B CN 105045665B
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- hrv
- msub
- operator
- mrow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention provides a kind of driving cabin dynamic function-allocation method based on operator's functional status, the function privilege of automation grade is determined first, carry out obscurity model building, then to the fuzzy division of dual input list output variable domain, the form and location parameter of the suitable fuzzy set of selection and fuzzy set, the concrete form of fuzzy rule is finally determined, the fuzzy rule of system is generated, carries out de-fuzzy after fuzzy reasoning clearing.The present invention carries out the shortcomings that dynamic function-allocation can overcome conventional static function distribution to the man-machine automated system of driving cabin, can accurately adjust systemic-function allocation strategy in real time.
Description
Technical field
The present invention relates to a kind of the Automation Design technology of civil aircraft driving cabin.
Background technology
The concept of function distribution (Function Allocation, FA) by P.M.Fitts in nineteen fifty-one propose, refer to by
Either task (Task) is assigned and given people or the process of machine for function (Function) in system, and it mainly emphasizes system each group
Into the Function Decomposition between composition.Aircraft cockpit man-machine function allocation is exactly that the function that aircraft cockpit to be realized is being flown
Reasonably distributed between member and driving cabin automation subsystem.Reasonably carry out the work(of pilot and automation subsystem
Energy/task distribute, both people, machine can be made full use of possessed by functional resources, pilot is able to maintain that higher scene
Perception level, while its work fatigue and operation error are reduced, and can enough gives full play to automated system advantage, so as to efficiently
Complete aerial mission.
Traditional function assigning method completes the capacity superiority of specific function by comparing people and machine, determines the function
Distribution gives people or machine.This method of salary distribution has determined that people and the respective role of machine, Er Qie in system design stage
Any reallocation is not allowed during system operation, referred to as static function distribution.But determine an optimal static function distribution
It is infeasible that scheme, which ensures that the performance of flight deck system remains at optimum state,.On the one hand, if assigned to pilot
More task, then during execution task, once running into task environment complicated and changeable, pilot work load can
It can exceed threshold value, cause work efficiency drop, aircraft accident can be triggered when serious.On the other hand, if giving automation subsystem
The higher authority of system, pilot are under monitor state for a long time, it will cause situational awareness to decline, it is impossible to urgent thing
Part makes fast reaction.Compared to static function distribution, another function distribution form --- dynamic function-allocation allows system to exist
The change of operation phase according to circumstances, systemic-function is dynamically redistributed between people, machine, so as to make one, machine place of working
More coordinate, improve the overall functional effect of system.At present, dynamic function-allocation research traffic control in the air, process control,
Obtain widely applying in the fields such as Military Command and Control system.
China's large-sized civil transporter project is formally set up the project already, is developed the large-sized civil with independent intellectual property right and is transported
Machine needs the support of a large amount of correlation techniques, and dynamic function-allocation is exactly one of key technology therein.In view of its application background
Sensitiveness, at present on the not disclosed report of its core technology, system and complete method are not formed.From adaptation dynamic change
From the point of view of environment, because physiological parameter measurement value can reflect the working condition of operator in real time, the triggering machine based on measurement
System is most suitable.By the measurement to these physiological signals of operator, extraction can reflect the index of operator's load, accurate in real time
The functional status (Operator Functional State, OFS) of true ground evaluating operator, adjusted according to operator's functional status
Whole systemic-function allocation strategy, make one to reach optimal operating characteristics state with machine, without estimating recognizing for operator
Know state.
The content of the invention
For overcome the deficiencies in the prior art, the present invention provides a kind of driving cabin dynamic work(based on operator's functional status
Energy distribution method, i.e., according to physiological parameter measurement value estimation operator's functional status, so as to carry out the dynamic of function automation grade
State adjusts.
The technical solution adopted for the present invention to solve the technical problems comprises the following steps:
1) determine that civil aircraft flight deck system respectively automates the function privilege corresponding to grade;
2) heart rate to operator and EEG signals data measure, quick to functional status from the extracting data of collection
The characteristic index of sense;Choose HRV2And TLI2As the two indices of weighing operations person's physiological parameter change, and it is used as fuzzy logic
Input;The output of fuzzy logic is the automation grade of system;Wherein, HRV2For HR standard deviation sigmas in one minuteHRVWith it is average
Value μHRVRatio;Task load index TLI2The ratio of the different frequency range power of different EEG electrodes is represented, i.e.,Fz, Pz represent collection point of the EEG signals in the electrode placement standard of the 10-20 worlds, Pθ,FzExpression is gathering
The energy intensity for the brain electricity θ sections that point Fz is measured, Pα,PzRepresent the energy intensity in the collection point Pz brain electricity α sections measured;
3) by operator's performance parameter HRV2、TLI2Five grades are divided into, automation grade LOA is divided into four
Grade, represented with fuzzy language value, and provide standard fuzzy value scope;Operator's performance parameter HRV2、TLI2With automation grade
Fuzzy subset's type is triangle corresponding to LOA;
4) by operator's performance parameter HRV of input2、TLI2The output of dual input list is established with the automation grade LOA of output
Fuzzy controller, the rule base of fuzzy controller is Rl:If X is AiAnd Y is Bj, then Z is Ck, wherein X, Y is the input of rule
Linguistic variable, Z are output language variable, AiAnd BjFor fuzzy set, C corresponding to dual input variablekFor corresponding to single output variable
Fuzzy set, RlThe l articles fuzzy rule is represented, l=1,2 ..., m, i=1,2 ..., n, k=1,2 ..., n, m represent fuzzy rule
Total number then;
5) fuzzy reasoning is carried out using max-min gravity model appoaches, draws output fuzzy quantity C=(A × B) ο R, wherein,
6) subset for exporting fuzzy quantity is converted into the exact value to OFS evaluations
The beneficial effects of the invention are as follows:Carrying out dynamic function-allocation to the man-machine automated system of driving cabin can overcome in the past
The shortcomings that static function distribution, systemic-function allocation strategy can be accurately adjusted in real time.
Brief description of the drawings
Fig. 1 is the man-machine dynamic function-allocation adjustment schematic diagram of civil aircraft driving cabin;
Fig. 2 is HRV2 membership function schematic diagram;
Fig. 3 is LI2 membership function schematic diagram;
Fig. 4 is LOA membership function schematic diagram;
Fig. 5 is dynamic function regulation rule schematic diagram;
Fig. 6 is fuzzy reasoning input, output characteristics curved surface schematic diagram.
Embodiment
The present invention is further described with reference to the accompanying drawings and examples, and the present invention includes but are not limited to following implementations
Example.
The present invention comprises the following steps:
1. determine the function privilege of automation grade
The automation partition of the level method of Sheridan and the Verplank man-machine interactive system proposed is merged excellent
Change, determine that civil aircraft flight deck system respectively automates the function privilege corresponding to grade.As shown in table 1, table 2:
Table 1 automates grade LOA (Modification)
The function privilege of the different automation grades (LOA) of table 2
2. obscurity model building
The schematic diagram of civil aircraft driving cabin dynamic function-allocation based on operator's functional status is as shown in Figure 1:
Operator's heart rate (Heart Rate, HR), electric (Electroencephalogram, the EEG) signal data of brain are entered
Row measures, the characteristic index sensitive to OFS from the extracting data of collection, selects the input/output variable of fuzzy controller, really
Determine the quantity of input/output variable.Choose HRV2、TLI2As the two indices of weighing operations person's physiological parameter change, and it is used as
The input of fuzzy logic;The output of fuzzy logic is the automation grade (LOA) of system.
HRV2It is defined as the ratio of HR standard deviations and average value in one minute period.HRV2Calculation formula it is as follows:
Wherein σHRVAnd μHRVThe standard deviation and average of HR data in respectively 1 minute period.
Task load index TLI2 represents the ratio of the different frequency range power of different EEG electrodes.TLI2 calculation formula is such as
Under:
Wherein Fz, Pz represent collection point of the EEG signals in the electrode placement standard of the 10-20 worlds, Pθ,FzExpression is gathering
The energy intensity for the brain electricity θ sections (4-8Hz) that point Fz is measured, Pα,PzRepresent in the collection point Pz brain electricity α sections (8-13Hz) measured
Energy intensity.
3. the determination of linguistic variable and fuzzy set
To the fuzzy division of dual input list output variable domain, the form of suitable fuzzy set and fuzzy set is selected
And location parameter.
By operator's performance parameter HRV2、TLI2Five grades are divided into, are expressed as with fuzzy language value:" very low ",
" low ", " in ", " height ", " very high ";The automation grade LOA hairs of output function are divided into four grades, use fuzzy language
Value is expressed as:" low ", " in ", " height ", " very high ".According to each fuzzy set being defined on basic domain, to determine essence
The really belonging fuzzy subset of amount and its corresponding membership function.HRV2、TLI2With the scope of tri- Fuzzy Linguistic Variables of LOA, such as
Shown in table 3.
The Fuzzy Linguistic Variable of table 3 and its fuzzy set
Input, output variable, use and be uniformly distributed (central point of each triangle is uniformly distributed on domain), full friendship
The repeatedly triangular membership of (end points of each triangle base is precisely the central point of two neighboring triangle).Degree of membership letter
Number difference is as shown in Figure 2, Figure 3, Figure 4.
4. fuzzy rule constructs
The concrete form of fuzzy rule is determined, generates the fuzzy rule of system.Establish the fuzzy control of dual input list output
Device " Ruo-if " rule base of form is as follows:
Rl:If (X is Ai) and (Y is Bj), then (Z is Ck) l=1,2 ..., m
Wherein X, Y are the input language variable of rule, and Z is output language variable.Ai(i=1,2 ..., n) and Bj(j=1,
2 ..., n) it is fuzzy set, C corresponding to dual input variablek(k=1,2 ..., n) is fuzzy set, R corresponding to single output variablel
The l articles fuzzy rule is represented, m represents the total number of fuzzy rule.
Due to HRV2And TLI2Respectively there are 5 fuzzy numbers, so sharing 25 fuzzy control rules.Establish the output of dual input list
Fuzzy controller " Ruo-if " the specific rules storehouse of form is as follows:
R1:If (HRV2It is VL) and (TIL2It is VL), then (LOA is L);
R2:If (HRV2It is VL) and (TIL2It is L), then (LOA is L);
R3:If (HRV2It is VL) and (TIL2It is M), then (LOA is L);
R4:If (HRV2It is VL) and (TIL2It is H), then (LOA is M);
R5:If (HRV2It is VL) and (TIL2It is VH), then (LOA is H);
R6:If (HRV2It is L) and (TIL2It is VL), then (LOA is L);
R7:If (HRV2It is L) and (TIL2It is L), then (LOA is L);
R8:If (HRV2It is L) and (TIL2It is M), then (LOA is M);
R9:If (HRV2It is L) and (TIL2It is H), then (LOA is H);
R10:If (HRV2It is L) and (TIL2It is VH), then (LOA is VH);
R11:If (HRV2It is M) and (TIL2It is VL), then (LOA is L);
R12:If (HRV2It is M) and (TIL2It is L), then (LOA is M);
R13:If (HRV2It is M) and (TIL2It is M), then (LOA is M);
R14:If (HRV2It is M) and (TIL2It is H), then (LOA is H);
R15:If (HRV2It is M) and (TIL2It is VH), then (LOA is VH);
R16:If (HRV2It is H) and (TIL2It is VL), then (LOA is M);
R17:If (HRV2It is H) and (TIL2It is L), then (LOA is H);
R18:If (HRV2It is H) and (TIL2It is M), then (LOA is H);
R19:If (HRV2It is H) and (TIL2It is H), then (LOA is H);
R20:If (HRV2It is H) and (TIL2It is VH), then (LOA is VH);
R21:If (HRV2It is VH) and (TIL2It is VL), then (LOA is H);
R22:If (HRV2It is VH) and (TIL2It is L), then (LOA is VH);
R23:If (HRV2It is VH) and (TIL2It is M), then (LOA is VH);
R24:If (HRV2It is VH) and (TIL2It is H), then (LOA is VH);
R25:If (HRV2It is VH) and (TIL2It is VH), then (LOA is VH).
Adaptation function distribution regulation rule based on operator's functional status (OFS) can be remembered with Fuzzy Correlation
(Fuzzy Associative Memory, FAM) is described, as shown in 5 × 5 matrixes in Fig. 5.
5. Fuzzy Logic Reasoning Algorithm
Oneself knows that the input of fuzzy controller is X=A and Y=B, then according to fuzzy control rule, using Mamdani max-
Min gravity model appoaches, which carry out fuzzy reasoning, can show that output fuzzy quantity Z is
C=(A × B) ο R (3)
Rl=(Ai×Bj×Ck) (5)
Its base attribute is arranged to:"AND" (and) computing between input variable uses minimum computing;Between Different Rule
"or" (or) computing use very big computing;Fuzzy implication uses minimum computing;It is gravity model appoach that de-fuzzy, which then uses,.
Wherein include three kinds of main fuzzy logic operations:
(1) AND operation is obscured
Fuzzy "AND" (and) it is annexation between regular conditional, using minimum computing;
μA∩B(u)=min { μA(u),μB(u)} (6)
(2) inclusive-OR operation is obscured
Fuzzy "or" (or) is the relation between rule, using very big computing:
μA∪B(u)=max { μA(u),μB(u)} (7)
(3) Fuzzy implication
Fuzzy implication (implication) is the relation between regular conditional and conclusion, using minimum computing.
A and B is defined in the fuzzy set on X and Y respectively, is defined in by the Fuzzy implication represented by A → B on X × Y
Special implication relation.
6. de-fuzzy
The fuzzy subset that model exports is converted into the exact value evaluated OFS using gravity model appoach.Z possibility distrabtion is bent
Seek the center of gravity of the area on the area that line and axis of abscissas are surrounded, the result of the abscissa of center of gravity as ambiguity solution.Formula is:
Fig. 6 is according to 25 fuzzy control rules, is utilized MATLAB fuzzy toolbox (Fuzzy Logic Tool Box)
Obtained fuzzy inference system inputs, output characteristics curved surface.
Claims (1)
- A kind of 1. driving cabin dynamic function-allocation method based on operator's functional status, it is characterised in that comprise the steps:1) determine that civil aircraft flight deck system respectively automates the function privilege corresponding to grade;2) heart rate to operator and EEG signals data measure, sensitive to functional status from the extracting data of collection Characteristic index;Choose HRV2And TLI2As the two indices of weighing operations person's physiological parameter change, and it is defeated as fuzzy logic Enter;The output of fuzzy logic is the automation grade of system;Wherein, HRV2For HR standard deviation sigmas in one minuteHRVAnd average value muHRV Ratio;Task load index TLI2The ratio of the different frequency range power of different EEG electrodes is represented, i.e.,Fz、 Pz represents collection point of the EEG signals in the electrode placement standard of the 10-20 worlds, Pθ,FzRepresent the brain electricity θ measured in collection point Fz The energy intensity of section, Pα,PzRepresent the energy intensity in the collection point Pz brain electricity α sections measured;3) by operator's performance parameter HRV2、TLI2Five grades are divided into, automation grade LOA is divided into four grades, Represented with fuzzy language value, and provide standard fuzzy value scope;Operator's performance parameter HRV2、TLI2With LOA pairs of grade of automation The fuzzy subset's type answered is triangle;4) by operator's performance parameter HRV of input2、TLI2The mould of dual input list output is established with the automation grade LOA of output Fuzzy controllers, the rule base of fuzzy controller is Rl:If X is AiAnd Y is Bj, then Z is Ck, wherein X, Y is the input language of rule Variable, Z are output language variable, AiAnd BjFor fuzzy set, C corresponding to dual input variablekTo be obscured corresponding to single output variable Set, RlThe l articles fuzzy rule is represented, l=1,2 ..., m, i=1,2 ..., n, k=1,2 ..., n, m represent fuzzy rule Total number;5) fuzzy reasoning is carried out using max-min gravity model appoaches, draws output fuzzy quantity C=(A × B) o R, wherein,<mrow> <mi>R</mi> <mo>=</mo> <munderover> <mrow> <mi></mi> <mo>&cup;</mo> </mrow> <mrow> <mi>l</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msub> <mi>R</mi> <mi>l</mi> </msub> <mo>,</mo> <msub> <mi>R</mi> <mi>l</mi> </msub> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>A</mi> <mi>i</mi> </msub> <mo>&times;</mo> <msub> <mi>B</mi> <mi>j</mi> </msub> <mo>&times;</mo> <msub> <mi>C</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>;</mo> </mrow>6) subset for exporting fuzzy quantity is converted into the exact value to OFS evaluations
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510378767.2A CN105045665B (en) | 2015-07-01 | 2015-07-01 | Driving cabin dynamic function-allocation method based on operator's functional status |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510378767.2A CN105045665B (en) | 2015-07-01 | 2015-07-01 | Driving cabin dynamic function-allocation method based on operator's functional status |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105045665A CN105045665A (en) | 2015-11-11 |
CN105045665B true CN105045665B (en) | 2018-04-10 |
Family
ID=54452229
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510378767.2A Active CN105045665B (en) | 2015-07-01 | 2015-07-01 | Driving cabin dynamic function-allocation method based on operator's functional status |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105045665B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090654A (en) * | 2017-11-30 | 2018-05-29 | 中国航空工业集团公司沈阳飞机设计研究所 | A kind of man-machine function allocation method based on pilot's physiological data |
CN109377012A (en) * | 2018-09-26 | 2019-02-22 | 中国航天员科研训练中心 | A kind of dynamic man-machine function allocation system and unmanned plane |
CN113435624A (en) * | 2021-05-25 | 2021-09-24 | 中国航空工业集团公司沈阳飞机设计研究所 | Man-machine function distribution method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101224113A (en) * | 2008-02-04 | 2008-07-23 | 电子科技大学 | Method for monitoring vehicle drivers status and system thereof |
CN101930490A (en) * | 2010-08-06 | 2010-12-29 | 西北工业大学 | Man-machine function allocation method of civil aircraft cockpit |
CN103198617A (en) * | 2013-03-26 | 2013-07-10 | 无锡商业职业技术学院 | Fatigue driving warning system |
CN103902766A (en) * | 2014-03-14 | 2014-07-02 | 西北工业大学 | Dynamic function distribution method based on brain load model and fuzzy logic |
DE102014204980A1 (en) * | 2013-07-05 | 2015-01-08 | Ford Global Technologies, Llc | Method and apparatus for restricting or forcibly activating motor vehicle functions |
-
2015
- 2015-07-01 CN CN201510378767.2A patent/CN105045665B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101224113A (en) * | 2008-02-04 | 2008-07-23 | 电子科技大学 | Method for monitoring vehicle drivers status and system thereof |
CN101930490A (en) * | 2010-08-06 | 2010-12-29 | 西北工业大学 | Man-machine function allocation method of civil aircraft cockpit |
CN103198617A (en) * | 2013-03-26 | 2013-07-10 | 无锡商业职业技术学院 | Fatigue driving warning system |
DE102014204980A1 (en) * | 2013-07-05 | 2015-01-08 | Ford Global Technologies, Llc | Method and apparatus for restricting or forcibly activating motor vehicle functions |
CN103902766A (en) * | 2014-03-14 | 2014-07-02 | 西北工业大学 | Dynamic function distribution method based on brain load model and fuzzy logic |
Non-Patent Citations (1)
Title |
---|
基于D-S证据理论的飞行员辅助系统自动化级别动态调整方法;武俊兆 等;《计算机与现代化》;20140211;第221卷(第1期);第67-70、76页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105045665A (en) | 2015-11-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cho et al. | Emergence of bi-cluster flocking for the Cucker–Smale model | |
CN105045665B (en) | Driving cabin dynamic function-allocation method based on operator's functional status | |
CN105138849B (en) | A kind of Power Network Partitioning method based on AP clusters | |
CN106483850A (en) | The Fuzzy Self-adaptive PID method for designing that a kind of aero-engine is feedovered based on RBF neural | |
CN107516107A (en) | A kind of driving cycle classification Forecasting Methodology of motor vehicle driven by mixed power | |
CN105305468B (en) | Thermal power generation unit primary frequency modulation parameter optimization method based on particle cluster algorithm | |
CN108171315A (en) | Multiple no-manned plane method for allocating tasks based on SMC particle cluster algorithms | |
CN103279032B (en) | A kind of robust convergent control method of heterogeneous multi-agent system | |
CN106529064A (en) | Multi-agent based route selection simulation system in vehicle online environment | |
CN102998976A (en) | Online real-time control method for intelligent seismic reduction structure | |
CN105843189A (en) | Simplified simulation model based high efficient scheduling rule choosing method for use in semiconductor production lines | |
CN103530700B (en) | Urban distribution network saturation loading Comprehensive Prediction Method | |
Fu et al. | A discrete multi-objective rider optimization algorithm for hybrid flowshop scheduling problem considering makespan, noise and dust pollution | |
CN105896547A (en) | Large power network graded voltage control method under wind power access | |
CN106647279A (en) | Locomotive intelligent control optimization calculating method based on fuzzy rules | |
CN106934461B (en) | FURIA-based locomotive intelligent operation optimization rule induction method | |
CN114756980B (en) | Info-GAN-based multi-design space coupling pneumatic shape optimization method and system | |
CN108519764A (en) | Multi-Agent coordination control method based on data-driven | |
CN113554215A (en) | Helicopter scheduling route planning method based on ant colony-genetic fusion algorithm | |
Yan et al. | Autonomous coordinated control strategy for complex process of traffic information physical fusion system based on big data | |
CN104523237B (en) | A kind of mobile cabin occupant's job method of adjustment | |
Nie et al. | The derivation of the analytical structure of a class of Interval type-2 fuzzy PD and PI controllers | |
Dai et al. | The simulation research of automobile ABS system based on fuzzy theory | |
CN107908108A (en) | Absorbing natural gas tower sweetening process control method based on UKF and GDHP | |
Liu et al. | Fuzzy synthetic assessment of air traffic controllers situational awareness based on short-term memory measurement |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |