CN112926836A - Team combat task matching method based on health state - Google Patents
Team combat task matching method based on health state Download PDFInfo
- Publication number
- CN112926836A CN112926836A CN202110133492.1A CN202110133492A CN112926836A CN 112926836 A CN112926836 A CN 112926836A CN 202110133492 A CN202110133492 A CN 202110133492A CN 112926836 A CN112926836 A CN 112926836A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- layer
- weight
- value
- subsystem
- 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
- 230000036541 health Effects 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000005259 measurement Methods 0.000 claims abstract description 58
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 30
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 210000002569 neuron Anatomy 0.000 claims description 37
- 238000010606 normalization Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 230000003862 health status Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 description 45
- 238000003745 diagnosis Methods 0.000 description 17
- 239000000446 fuel Substances 0.000 description 16
- 238000001514 detection method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 230000001629 suppression Effects 0.000 description 5
- 230000002860 competitive effect Effects 0.000 description 4
- 239000000295 fuel oil Substances 0.000 description 4
- 239000010763 heavy fuel oil Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004880 explosion Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 239000003921 oil Substances 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 239000002828 fuel tank Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000004313 glare Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 206010027175 memory impairment Diseases 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- 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
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (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
A health state-based team combat task matching method belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring M influence factors related to executing a certain task, acquiring N vehicle health state measurement values aiming at each influence factor, and establishing an initial matrix; determining the weight of the influence factor according to the initial matrix; and the artificial intelligence module corrects the weight of the influence factor. The matching method provided by the invention can match the fighting tasks of the teams according to the measured value of the health state of the influence factors, and can carry out scientific configuration.
Description
Technical Field
The invention relates to a health state-based team fighting task matching method, and belongs to the technical field of artificial intelligence.
Background
The vehicle system generally manages or executes tasks in a form of a squad, and specifically the vehicle system is composed of a vehicle body, personnel, oil, ammunition and other various influence factors, and the vehicle body can be divided into different levels of functional devices. In daily management or task execution of vehicle teams, a dispatcher generally conducts dispatching and task allocation according to task amount and vehicle health conditions, the health state of a vehicle system cannot be accurately grasped, the specific dispatching management generally depends on manual experience or simple calculation of the dispatcher to determine a scheme, a rough management mode and an experience-based management mode cause low system readiness maintenance level and bring rapid rise of maintenance and guarantee cost, and the team combat task matching based on the health state of an influence factor needs to be conducted on the vehicle system urgently to quantify scientific operation and maintenance management and use decisions.
Disclosure of Invention
The invention aims to provide a health state-based squad combat mission matching method, which can match the combat missions of squads according to health state measured values of influence factors, can carry out scientific configuration and has high vehicle combat readiness maintenance level.
In order to achieve the above object, the present invention provides a health status-based team combat mission matching method, which is characterized by comprising: s01, establishing an initial matrix: acquiring M influence factors related to executing a certain task; obtaining N vehicle state of health measurements for each impact factor, establishing an initial matrix:
element x in the matrixinIndicating the ith influence of the nth vehicleA measure of the state of health of the factor,
s02; calculating the weight of the influence factors, namely a) carrying out evolutionary normalization processing on the health state measured value to construct a normalization matrix:
wherein,
b) calculating an initial weight of the impact factor:
s03: and modifying the weight of the influence factor:
a) the artificial intelligence module compares the contribution degree of M influence factors to the technical quality index for measuring the battle tasks, and constructs a contribution vector: beta is ═ beta1,…,βi,…,βM]；
b) Determining the final weight of each influence factor according to the contribution degree:
ui＝βi×λi；
s04: determining a matching value:
a) constructing a weighted normalized matrix:
in matrix, vin＝uipin
b) Calculating the matching degree of the vehicle to the combat mission according to the following formula:
c) degree of matching enFrom large to smallSorting, degree of matching enThe largest vehicle is the best matched vehicle to perform the task.
Preferably, the health state measurements of the impact factors include: a vehicle body remaining service life measurement, a personnel condition map value, an oil balance measurement, and an ammunition balance measurement.
Preferably, the remaining service life of the vehicle body is determined by an artificial intelligence module, the artificial intelligence module comprises an input layer, a coding layer, an output layer and a model optimization layer, the working process of the artificial intelligence module comprises a training stage and a prediction stage, and in the training stage, the input layer inputs a binary sequence X' of measurement values of the repaired vehicle with the same structure; z th in coding layertThe binary sequence of neurons and input layer inputs is represented by the following functional relationship:
zt＝fen(X′,W)
in the formula, W is a network parameter of a coding layer;
the target amount of output from the output layer is represented by:
y＝[y1,…yv,…yK′]
in the formula,
r is the remaining service life;
ruc time interval for vehicle operating life;
the target quantity estimated value output by the output layer is as follows:
wherein Z is [ Z ]1,…zt,…zT]，WcAnd bcParameters matched from the coding layer to the target estimation value of the output layer; t is the number of neurons in each layer of the coding layer;
model optimization layer pass
Minimum to learn repeatedly, thereby optimizing the function fenAnd sigma.
In the prediction phase, the input layer inputs a binary sequence X of measured values of the vehicle;
z th in coding layertThe binary sequence of neurons and input layer inputs is represented by the following functional relationship:
zt＝fen(X,W)
wherein W is a network parameter of the coding layer;
the relation Z between the target quantity estimated value output by the output layer and the neuron vector of the coding layer is expressed as follows:
the artificial intelligence module determines the remaining useful life of the vehicle according to the following equation
Compared with the prior art, the health state-based squad combat mission influence factor matching method provided by the invention can match the combat missions of squads according to the health state measured values of vehicles, can carry out scientific configuration, and has high vehicle combat readiness maintenance level.
Drawings
FIG. 1 is a block diagram of the architecture of a hierarchical fusion vehicle overall health management system provided by the present invention;
FIG. 2 is a block diagram of the hardware components of the vehicle system provided by the present invention;
FIG. 3 is a block diagram of the hardware components of the dequeue system provided by the present invention;
FIG. 4 is a flow chart of a vehicle health status based system capability assessment method provided by the present invention;
FIG. 5 is a schematic diagram of an evaluation model provided by the present invention
FIG. 6 is a flowchart illustrating a health status-based team engagement mission matching method according to the present invention;
FIG. 7 is a flow diagram of the artificial intelligence diagnostic reasoning module provided by the present invention;
fig. 8 is a schematic structural diagram of the fuzzy neural network provided by the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood 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.
In describing the present invention, it is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and/or "comprising," when used in this specification, are intended to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The term "and/or" includes any and all combinations of one or more of the associated listed items. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
FIG. 1 is a block diagram of the architecture of a hierarchical fusion vehicle overall health management system provided by the present invention; as shown in fig. 1, the vehicle squad at least includes a squad management system and 1 st to nth vehicles, the squad management system is shown in fig. 2, and is a squad health management layer, and each vehicle is configured through an optimization module according to an index value and total cost of a completed task; the vehicle is provided with a vehicle system shown in figure 3, which is used for detecting state data of a vehicle subsystem, calling a learned subsystem and/or vehicle model in a database to perform anomaly detection, fault diagnosis and residual life prediction on the subsystem and/or the vehicle through a diagnosis and inference module, a prediction and inference module and an anomaly detection module, storing the location of the data in a tree-shaped node form through an integration module into a memory of the vehicle and sending the data to a squad management system, wherein each node comprises a serial number, a tag and a time stamp of the vehicle or the subsystem, the squad management system processes and stores the received data into a database of the squad and trains an anomaly detection model, a fault diagnosis model, a residual life prediction model and the like, and carrying out war ability evaluation and the like, and then carrying out intelligent decision, wherein in the invention, the intelligent decision module carries out battle task matching on the vehicle according to data sent by the vehicle.
Fig. 2 is a block diagram of hardware components of the fleet health management system provided by the present invention, and as shown in fig. 2, the system includes a processor 20 and a memory 21 connected by a bus, the memory 21 includes a database for storing data sent by vehicles, the data is stored in the form of tree nodes for N vehicles and their subsystems, and the database stores a subsystem-level diagnosis inference model, a subsystem-level prediction inference model, a subsystem-level abnormality detection model, a vehicle-level prediction inference model, a vehicle-level abnormality detection model, and the like. The processor 20 calls a program stored in the memory to implement the functions of the squad health management layer, which includes a data processing module, a model training module, a combat power assessment module, and a decision module. The data processing module processes data sent by the vehicle and stores the data in a database; the model training module calls a plurality of vehicle data for processing, and trains various models by using the processed data. The combat capability assessment module calls data and assesses the combat capability of the vehicle. The decision module is used for decision of node command and comprises a vehicle monitoring module, a task matching module and a vehicle configuration optimization module. The squad forgetting and rehabilitation management system further comprises an input/output interface 24 for data output and for inputting commands and the like. The squad health management system further comprises a communication unit 23 for communicating with the vehicle, the upper level system, etc., the communication being a confidential communication. The squad forgetfulness management system further comprises a display 22, and the execution processes and final results of the model training module, the fighting capacity evaluation module, the optimization module and the like can be displayed on the display 22 so as to be convenient for an operator to observe.
Fig. 3 is a hardware block diagram of a vehicle system provided by the present invention, and as shown in fig. 3, the vehicle system includes a plurality of sensors, such as a fire control sensor 15, a power sensor 16, etc., which are connected by a bus and arranged as a state sensing layer of a vehicle fleet health management architecture, and is used for acquiring state data of each subsystem of the vehicle and transmitting the state data to a memory 11 by the bus. The vehicle system further comprises a processor 10 and a memory 11, wherein the memory 11 comprises a database for storing data sent by the state perception layer and the trained subsystem-level diagnosis and inference model, subsystem-level prediction and inference model and subsystem-level anomaly detection model, and the processor 10 calls the models and realizes the functions of the subsystem-level diagnosis and inference module, the system-level prediction and inference module and the subsystem-level anomaly detection module according to the state data of each subsystem sent by the state perception layer stored in the memory. The subsystem level diagnosis and inference module, the subsystem level prediction and inference module, the subsystem level anomaly detection module and the database form a subsystem region management layer, and the layer also comprises an integration module which arranges the data sent by the state perception layer and the processing results of the data by the subsystem level diagnosis and inference module, the system level prediction and inference module and the subsystem level anomaly detection module and stores the data in a memory 11 of the vehicle in a tree node form. In the invention, the memory 11 also stores a trained vehicle-level diagnosis and inference model, a vehicle-level prediction and inference model and a vehicle-level abnormality detection model, and the processor 10 calls the models and implements the functions of the vehicle-level diagnosis and inference module, the vehicle-level prediction and inference module and the vehicle-level abnormality detection module on the subsystem region management layer data stored in the memory 11 and the stored related models. The vehicle health management layer further comprises an integration module, which packages the data stored in the memory 11 of the subsystem region management layer and the processing results of the vehicle-level diagnosis and inference module, the vehicle-level prediction and inference module and the vehicle-level abnormality detection module into frames and outputs the frames through the input and output interface 14, and is also used for sending the energy sub-team health management system through the communication unit 13. In the invention, the processing results of the input data by the subsystem level diagnosis and inference module, the subsystem level prediction and inference module, the subsystem level anomaly detection module, the vehicle level diagnosis and inference module, the vehicle level prediction and inference module and the vehicle level anomaly detection module can be displayed through the display 22 of the vehicle for the vehicle personnel to observe.
In the present invention, the one or more processors may be implemented as hardware as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and/or any devices that manipulate signals based on operational instructions. The processor is configured to retrieve and execute computer readable instructions stored in the memory. The software system may be implemented in various computing systems, such as a laptop, a notebook, a handheld device, a workstation, a mainframe, a server, a network cloud, and so forth. Input output (I/O) interfaces may include various software and hardware interfaces, for example, to which a printer, keyboard, usb disk, network, cable, mouse, etc. may be connected. The communication unit is configured to communicate with other devices over a wireless network, such as a WLAN, cellular, or satellite. The display is used for visual interaction with a user.
Fig. 4 is a flowchart of a system capability assessment method based on vehicle health status provided by the present invention, and as shown in fig. 4, the system capability assessment method based on vehicle health status provided by the present invention comprises the following steps:
s01, establishing a hierarchical model with a first hierarchy, a second hierarchy and a third hierarchy according to the health state of the vehicle, wherein the first hierarchy comprises maneuvering ability, firepower ability and shooting ability; the second level comprises a vehicle-mounted equipment capacity normalization estimated value, a fuel oil normalization estimated value, a personnel state normalization estimated value and an ammunition residue normalization estimated value, and the third level comprises a subsystem normalization estimated value of the vehicle-mounted equipment;
s02, determining the weight of each normalized estimation value in the first level, the second level and the third level by using an artificial intelligence module;
s03, establishing a first mapping table, a second mapping table, a third mapping table and a fourth mapping table, wherein the subsystem performance in the first mapping table corresponds to the subsystem mapping value one by one; in the second mapping table, the residual fuel quantity corresponds to the mapping values of the fuel one by one; in the third mapping table, the personnel states correspond to the personnel mapping values one by one; in the fourth mapping table, ammunition allowance corresponds to ammunition mapping values one by one;
s04: measuring the performance of the subsystem of the vehicle-mounted equipment, and determining a subsystem mapping value according to the measured value of the performance of the subsystem of the vehicle-mounted equipment; measuring the residual fuel quantity, and determining a fuel residual quantity phase mapping value according to the measured residual fuel quantity; determining a personnel mapping value according to the input vehicle-mounted personnel health condition according to the detected vehicle-mounted personnel health condition; the corresponding mapping value of the measured ammunition allowance is determined according to the input ammunition allowance;
s05, calculating the vehicle-mounted equipment normalization estimation value according to the subsystem mapping value and the subsystem weight; and calculating the technical quality index values of the maneuvering capacity, the fire capacity and the shooting capacity in the first level by using a system according to the technical quality index values of the vehicle-mounted equipment and the normalized estimated value weight thereof, the fuel mapping value and the normalized estimated value weight thereof, the personnel mapping value and the normalized estimated value weight thereof, and the ammunition mapping value and the normalized estimated value weight thereof.
According to one embodiment of the invention, the method further comprises:
s06: executing a technical quality index value of a certain task by a technical quality index value evaluation system according to the maneuvering capacity, the firepower capacity and the shooting capacity;
s07, sequencing the technical quality index values of a certain task and enabling the vehicle with the largest technical quality index value to execute the task;
s08: and recording the execution effect, taking a training value from the recorded result by the artificial intelligence module for training, so as to change the previously determined weight until the optimal weight and coefficient are determined, and using the optimal weight and coefficient in the evaluation model.
Fig. 5 is a schematic structural diagram of a combat capability assessment model provided by the present invention, and as shown in fig. 5, the combat capability assessment model includes a zeroth level (not shown), a first level, a second level and a third level, where the zeroth level is a task class level; the first level includes maneuvering capabilities, firepower capabilities, and shooting capabilities; the second level comprises a vehicle-mounted equipment capacity normalization estimated value, a fuel oil normalization estimated value, a personnel state normalization estimated value and an ammunition allowance normalization estimated value; and the third layer comprises a subsystem normalized estimated value of the vehicle-mounted equipment.
In the invention, the task determined by the squad or the master unit is arranged at the zeroth level. Setting a maneuvering technical quality index, a firepower technical quality index and a shooting technical quality index at a first level; and setting the vehicle-mounted equipment capacity normalized estimated value and the weight thereof, the fuel oil normalized estimated value and the weight thereof, the personnel state normalized estimated value and the weight thereof, and the ammunition residue normalized estimated value and the weight thereof at a second level. The weight coefficients are not set by human, but are learned repeatedly by the artificial intelligence module by performing the effect of the tasks in the first hierarchy.
In the present invention, if vlIf the weight of the maneuver technical quality index value, the weight of the fire technical quality index value and the weight of the fire technical quality index value in the first level are determined by the artificial intelligence module, and l is 1,2 or 3, then the maneuver technical quality index value normalization weight, the fire technical quality index value normalization weight and the fire technical quality index value normalization weight in the first level are obtained through the following formulas:
the invention obtains the task technical quality index value corresponding to the zero level through the following formula
In the formula,
the weights are normalized for the maneuver technology quality index values,
the normalizing weight is the fire technical quality index value,
normalizing the weight for the shooting technical quality index value; sigma1A mobile technology quality index value; sigma2The fire technical quality index value; sigma3For shooting technical quality index values
In the present invention, if uijThe vehicle-mounted equipment capacity normalized estimation value normalization weight, the fuel normalized estimation value weight, the personnel normalized estimation value weight and the ammunition normalized estimation value weight in the second level are determined by an artificial intelligence module, wherein i is 1,2,3, j is 1,2,3,4, and then the vehicle-mounted equipment capacity normalized estimation value normalization weight, the fuel normalized estimation value normalization weight, the personnel normalized estimation value normalization weight and the ammunition normalized estimation value normalization weight in the second level are obtained through the following formulas:
the invention obtains the maneuvering technical quality index value sigma corresponding to the first level by the following formula1Fire technical quality index value sigma2And shooting technical quality index value sigma3：
In the formula,
for normalized weight, i belongs to 1,2,3, j belongs to 1,2,3, 4;
respectively representing a normalized estimation value with vehicle-mounted equipment, a normalized estimation value of fuel oil, a normalized estimation value of personnel and a normalized estimation value of ammunition residue, which are determined by the following formula:
in the formula (f)1、f2、f3、f4Respectively representing mapping values matched with the vehicle-mounted equipment normalization estimated value, the fuel normalization estimated value, the personnel normalization estimated value and the ammunition allowance; omega12、ω13、ω14Respectively representing the influence coefficients of the fuel quantity, the personnel condition and the ammunition allowance condition on the capability of the vehicle-mounted equipment; omega21、ω23、ω24And the influence coefficients of the vehicle-mounted equipment, the personnel condition and the ammunition allowance condition on the fuel quantity are respectively represented, and the weight and the influence system are determined by repeated learning of an artificial intelligence module. These influence coefficients are also obtained by the artificial intelligence module through repeated learning. The influence coefficient may be a positive value, a negative value, or zero, and its absolute value is less than or equal to 1.
In the invention, the subsystems of the vehicle-mounted equipment are set to be a third level, the subsystems of the vehicle-mounted equipment can be divided into 12 subclasses according to functions, namely an operating system 1, an operating system 2, an action system, a positioning device, an engine system, a transmission system, a strong light defense system, a fire extinguishing and explosion suppression system, a three-prevention system, an observation system, a power supply electrical system 1 and a power supply electrical system 2, if x is x, the power supply electrical system is a power supply electrical system1nTo representAnd calculating the normalization weight of the normalized estimation value of the subsystem of the vehicle-mounted equipment according to the following formula:
in the present invention, the normalized estimation value of the vehicle-mounted device may be determined by the following formula:
in the formula (f)nThe mapping value of the nth subsystem of the vehicle-mounted equipment is obtained.
In the invention, the method also comprises the steps of establishing a first mapping table, wherein the subsystem performance measurement values in the first mapping table correspond to the subsystem normalized mapping values one by one, and the normalized mapping values of the subsystem measurement values are determined according to the measurement values of various measurement sensors of the subsystem of the vehicle-mounted equipment, as shown in the table 1:
TABLE 1 first mapping Table
In the invention, the remaining service life of the subsystem is determined according to the I measured values of the subsystem, and the normalized mapping value of the subsystem capacity is determined according to the remaining service life through the artificial intelligence module. The artificial intelligence module comprises an input layer, an encoding layer, an output layer and a model optimization layer, and the working process of the artificial intelligence module comprises a training phase and a prediction phase.
In the training stage, inputting a binary sequence X' of measurement values with the same structure and the same maintained subsystem by an input layer; z th in coding layertThe binary sequence of neurons and input layer inputs is represented by the following functional relationship:
zt＝fen(X′,W) (8)
wherein W is a network parameter of the coding layer;
the target amount of output from the output layer is represented by:
y＝[y1,…yv,…yK′]∈{0,1}K′ (9)
in the formula,
r is the remaining working life;
ruthe service life of the subsystem, c time interval;
the target quantity estimated value output by the output layer is as follows:
wherein Z is [ Z ]1,…zt,…zT]，WcAnd bcParameters matched from the coding layer to the target estimation value of the output layer; t is the number of neurons in each layer of the coding layer;
model optimization layer pass
Minimum to learn repeatedly, thereby optimizing the function fenAnd sigma.
In the prediction stage, inputting a binary sequence X of the measured values of the vehicle subsystem by an input layer;
z th in coding layertThe binary sequence of neurons and input layer inputs is represented by the following functional relationship:
zt＝fen(X,W) (11)
wherein W is a network parameter of the coding layer;
the relation Z between the target quantity estimated value output by the output layer and the neuron vector of the coding layer is expressed as follows:
the artificial intelligence module determines the remaining useful life of the subsystem according to the following formula
Therefore, the first and second electrodes are formed on the substrate,
the method further comprises the steps of establishing a second mapping table, wherein the fuel surplus in the second mapping table corresponds to the fuel mapping values one by one, and determining the fuel mapping values according to the measured fuel surplus, as shown in the table 2:
TABLE 2 second mapping Table
In the table, FuelmaxFuel, maximum Fuel tank loadcyrThe residual fuel quantity is measured by a liquid level sensor arranged in the fuel tank.
In the invention, the method also comprises the steps of establishing a third mapping table, wherein the personnel states in the third mapping table correspond to the personnel normalized value mapping values one by one, and the artificial intelligence module determines the personnel states to further determine the normalized value mapping values according to the image information of the vehicle-mounted personnel obtained by the image sensor, as shown in the table 3:
TABLE 3 third mapping Table
In the invention, the method also comprises the steps of establishing a fourth mapping table, wherein in the fourth mapping table, the ammunition allowance condition corresponds to the ammunition normalization mapping values one by one; and determining a corresponding mapping value according to the input ammunition allowance condition, as shown in the table 4:
TABLE 4 fourth mapping Table
In the table, MaterialmaxMaterials for maximum ammunition charge allocation for a certain taskcurThe residual ammunition amount is obtained by metering by a metering sensor.
According to another embodiment of the present invention, there is also provided a storage medium storing a computer program written in a computer language that can be called and processed by a processor, and performing the processes described in the above method.
Because the fighting capacity evaluation provided by the invention maps the qualitative and quantitative data of the vehicle into the mapping value through the mapping table, the capacity evaluation value can be obtained through calculation, and the vehicle can be scientifically managed.
Fig. 6 shows an affiliate combat mission matching method based on health status of influence factors, according to the present invention, as shown in fig. 6, the affiliate combat mission matching method includes: the team combat task matching method based on the health state is characterized by comprising the following steps:
s01, establishing an initial matrix: acquiring M influence factors related to executing a certain task; obtaining N vehicle state of health measurements for each impact factor, establishing an initial matrix:
element x in the matrixinA state of health measurement indicative of an ith influence factor of an nth vehicle,
s02; calculating the weight of the influence factors, namely a) carrying out evolutionary normalization processing on the health state measured value to construct a normalization matrix:
wherein,
b) calculating an initial weight of the impact factor:
s03: and modifying the weight of the influence factor:
a) the artificial intelligence module compares the contribution degree of M influence factors to the technical quality index for measuring the battle tasks, and constructs a contribution vector: beta is ═ beta1,…,βi,…,βM]；
b) Determining the final weight of each influence factor according to the contribution degree:
ui＝βi×λi；
s04: determining a matching value:
a) constructing a weighted normalized matrix:
in matrix, vin＝uipin
b) Calculating the matching degree of the vehicle to the combat mission according to the following formula:
c) degree of matching enSorting from big to small, matching degree enThe largest vehicle is the most optimal vehicle to perform the task.
Preferably, the health state measurements of the impact factors include: a vehicle body remaining service life measurement, a personnel condition map value, an oil balance measurement, and an ammunition balance measurement.
Preferably, the measurement of the remaining useful life of the vehicle is performed by the same method as the measurement of the remaining useful life of the vehicle subsystem, and the description thereof is not repeated here.
The invention provides a health state-based squad combat mission matching method which matches squad combat missions according to health state measurement values of influencing causal women, can carry out scientific configuration, and improves vehicle combat readiness maintenance level. After the vehicles are matched according to the combat mission, the sensors in the vehicle sensing layer respectively monitor and measure the subsystems, the sensors respectively transmit measured values to the subsystem area management layer, and the subsystem area management layer adopts the flow of fig. 7 to diagnose and reason the subsystems according to data transmitted by the sensors.
Fig. 7 is a flow chart of the artificial intelligence diagnostic reasoning module provided by the present invention, wherein the diagnostic reasoning module in the present invention adopts the neural network shown in fig. 8. The diagnosis inference method comprises the following steps:
a learning step: learning various measurement values when a vehicle subsystem fails as a neuron to form a two-dimensional map, wherein the failure values comprise: the system comprises a power supply electric system, a transmission system, a power supply electric; for determining the grey scale, brightness, etc. of the viewing system. In the invention, the learning (training) step is usually implemented in the vehicle health management layer, and in the vehicle health management layer, a diagnosis and inference model is established through the measurement data and the fault value of the subsystem with faults, and the learned (or trained) diagnosis and inference model is sent to the vehicle.
A calculation step: calculating similarities between subsystem measurements of the vehicle, engine measurements, drive train measurements, action system measurements, power supply electrical system measurements, observation system measurements, fire suppression and explosion suppression system measurements, three prevention system measurements, glare protection system measurements, positioning system health and operating system measurements, fuel remaining measurements, ammunition remaining measurements, and costs required to maintain them, and neurons in the two-dimensional map; the measured value is determined by sensor measurement of the sensing layer;
an estimation step: and determining the neuron with the maximum similarity in the two-dimensional graph, and estimating the fault corresponding to the neuron with the maximum similarity as the fault of the vehicle subsystem.
More specifically, the measured value of the vehicle subsystem is used as an input vector in an input layer, the learned measured value when the vehicle subsystem breaks down is used as a neuron of an output layer, and the neuron form a two-dimensional array, wherein the input node of the input layer and the output node of the output layer are combined by variable weight omegajkFully connecting; j, J is the number of input nodes; k is 1,2, …, K is the number of output nodes, and then the following steps are executed:
s01: an initialization step: initializing the fuzzy clustering neural network to initialize the weight, and determining an initial learning value eta0And the total number of learning times T;
s02: distance calculation step: calculating an input vector F ═ F1,…,fj,…,fJ]And weight d between output layer neuron weightsk：
S03: and (3) selecting neurons: neuron y of output layer to be least distant from input vector FminAs an optimal matching neuron;
s04: and a weight adjusting step: modulating neuron y byminIn its neighborhood AcNode weight coefficients contained therein:
ωjk(t)＝fjk(t-1)+ηn(fj-ωjk(t-1)) (25)
in the formula, ωjk(t) is the weight of the current t output, ωjk(t-1) is the weight of the previous output;
s05: judging whether the learning times T are reached, if not, repeating the steps S02-S04; and if so, outputting the final optimal competitive neuron, wherein the optimal competitive neuron is the corresponding fault of the subsystem.
According to another embodiment of the present invention, there is also provided a fault diagnosis module including a learning module: configured to learn measurement values at which a vehicle subsystem fails as neurons to form a two-dimensional map, the failure values comprising: the system comprises a power supply electric system, a transmission system, a power supply electric; for determining the grey scale, brightness, etc. of the viewing system;
a calculation module: configured to calculate similarities between subsystem measurements of the vehicle, engine measurements, drive train measurements, action system measurements, power supply electrical system measurements, observation system measurements, fire suppression and explosion suppression system measurements, three prevention system measurements, glare protection system measurements, positioning system health and operating system measurements, fuel residuals measurements, ammunition residuals measurements, and costs required to maintain them, and neurons in a two-dimensional map; the measured value is determined by sensor measurement of the sensing layer;
an estimation module: and the failure corresponding to the neuron with the maximum similarity is estimated as the failure of the vehicle subsystem.
More specifically, the artificial intelligence diagnostic module takes subsystem measurements as an input layerTaking the learned measured value of the vehicle subsystem in the failure as the neuron of an output layer and forming a two-dimensional array, wherein the input node of the input layer and the output node of the output layer use variable weight omegajkFully connecting; j, J is the number of input nodes; k is 1,2, …, K is the number of output nodes, and specifically includes:
an initialization module: configured to initialize fuzzy clusters to initialize weights, determine an initial learning value η0And the total number of learning times T;
a distance calculation module: calculating an input vector F ═ F according to equation (24)1,…,fj,…,fJ]And weight d between output layer neuron weightsk；
A neuron selection module: neuron y of output layer configured to minimize distance from input vector FminAs an optimal matching neuron;
the weight adjusting module: configured to adjust neuron y by equations (25) and (26)minIn its neighborhood AcNode weight coefficients contained therein:
the judging module is configured to judge whether the learning times T are reached or not, and if the learning times T are not reached, the distance calculating module, the neuron selecting module and the weight adjusting module are not repeatedly executed; and if so, outputting the final optimal competitive neuron, wherein the optimal competitive neuron is the corresponding fault of the subsystem.
Although the present invention has been described with reference to an implementation of a subsystem-level diagnostic reasoning module, a similar approach can be used to implement a vehicle-level diagnostic reasoning module.
In addition, the artificial intelligence module obtains various weights, so that the vehicle capability can be evaluated more objectively.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (3)
1. A health state-based team combat task matching method is characterized by comprising the following steps:
s01, establishing an initial matrix: acquiring M influence factors related to executing a certain task; obtaining N vehicle state of health measurements for each impact factor, establishing an initial matrix:
element x in the matrixinA state of health measurement indicative of an ith influence factor of an nth vehicle,
s02; calculating the weight of the influence factors, namely a) carrying out evolutionary normalization processing on the health state measured value to construct a normalization matrix:
wherein,
b) calculating an initial weight of the impact factor:
s03: and modifying the weight of the influence factor:
a) the artificial intelligence module compares the contribution degree of M influence factors to the technical quality index for measuring the battle tasks, and constructs a contribution vector: beta is ═ beta1,…,βi,…,βM]；
b) Determining the final weight of each influence factor according to the contribution degree:
ui＝βi×λi；
s04: determining a matching value:
a) constructing a weighted normalized matrix:
in matrix, vin＝uipin
b) Calculating the matching degree of the vehicle to the combat mission according to the following formula:
c) degree of matching enSorting from big to small, matching degree enThe largest vehicle is the most optimal vehicle to perform the task.
2. The health status-based squad combat mission matching method according to claim 1, wherein the health status measurements of the impact factors include: a vehicle body remaining service life measurement, a personnel condition map value, an oil balance measurement, and an ammunition balance measurement.
3. The health status-based squad combat mission matching method according to claim 2, wherein the remaining service life of a vehicle body is determined by an artificial intelligence module, the artificial intelligence module comprises an input layer, a coding layer, an output layer and a model optimization layer, the working process of the artificial intelligence module comprises a training phase and a prediction phase, and in the training phase, the input layer inputs a binary sequence X' of measurement values of vehicles which have the same structure and are already maintained; z th in coding layertThe binary sequence of neurons and input layer inputs is represented by the following functional relationship:
zt＝fen(X′,W)
in the formula, W is a network parameter of a coding layer;
the target amount of output from the output layer is represented by:
y＝[y1,…yv,…yK′]
in the formula,
r is the remaining service life;
ruc time interval for vehicle operating life;
the target quantity estimated value output by the output layer is as follows:
wherein Z is [ Z ]1,…zt,…zT]，WcAnd bcParameters matched from the coding layer to the target estimation value of the output layer; t is the number of neurons in each layer of the coding layer;
model optimization layer pass
Minimum to learn repeatedly, thereby optimizing the function fenAnd sigma.
In the prediction phase, the input layer inputs a binary sequence X of measured values of the vehicle;
z th in coding layertThe binary sequence of neurons and input layer inputs is represented by the following functional relationship:
zt＝fen(X,W)
wherein W is a network parameter of the coding layer;
the relation Z between the target quantity estimated value output by the output layer and the neuron vector of the coding layer is expressed as follows:
the artificial intelligence module is according toDetermining remaining useful life of a vehicle
Wherein K 'is less than K, and the ratio of K',
t is the working time of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110133492.1A CN112926836A (en) | 2021-01-31 | 2021-01-31 | Team combat task matching method based on health state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110133492.1A CN112926836A (en) | 2021-01-31 | 2021-01-31 | Team combat task matching method based on health state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112926836A true CN112926836A (en) | 2021-06-08 |
Family
ID=76169085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110133492.1A Pending CN112926836A (en) | 2021-01-31 | 2021-01-31 | Team combat task matching method based on health state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112926836A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379390A (en) * | 2021-06-23 | 2021-09-10 | 沈阳顺义科技有限公司 | War chariot team health management device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108055701A (en) * | 2017-12-13 | 2018-05-18 | 北京北方烽火科技有限公司 | A kind of resource regulating method and base station |
| CN112036651A (en) * | 2020-09-04 | 2020-12-04 | 山东科技大学 | Electricity price prediction method based on quantum immune optimization BP neural network algorithm |
-
2021
- 2021-01-31 CN CN202110133492.1A patent/CN112926836A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108055701A (en) * | 2017-12-13 | 2018-05-18 | 北京北方烽火科技有限公司 | A kind of resource regulating method and base station |
| CN112036651A (en) * | 2020-09-04 | 2020-12-04 | 山东科技大学 | Electricity price prediction method based on quantum immune optimization BP neural network algorithm |
Non-Patent Citations (2)
| Title |
|---|
| ROCKY: "吴恩达深度学习课程第一课-神经网络与深度学习", 《博客园URL：HTTPS://WWW.CNBLOGS.COM/NROCKY/P/12083370.HTML》 * |
| 伊惠芳等: "改进的柔性专利价值评价方法——基于时域-领域双重视角", 《情报杂志》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113379390A (en) * | 2021-06-23 | 2021-09-10 | 沈阳顺义科技有限公司 | War chariot team health management device |
| CN113379390B (en) * | 2021-06-23 | 2023-10-27 | 沈阳顺义科技有限公司 | Health management device for combat vehicle team |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ranasinghe et al. | Advances in Integrated System Health Management for mission-essential and safety-critical aerospace applications | |
| CN112785183B (en) | Health management system framework for layered fusion type vehicle teams | |
| CN112907781B (en) | System fault diagnosis method and device, computer equipment and storage medium | |
| CN111539515B (en) | Complex equipment maintenance decision method based on fault prediction | |
| US8855954B1 (en) | System and method for prognosticating capacity life and cycle life of a battery asset | |
| Liu et al. | Self-tuning of fuzzy belief rule bases for engineering system safety analysis | |
| CN105096053A (en) | Health management decision-making method suitable for complex process system | |
| JP2008537262A (en) | Decision support method and system | |
| US11396825B2 (en) | Turbine diagnostic feature selection system | |
| CN110348752A (en) | A kind of large scale industry system structure security assessment method considering environmental disturbances | |
| Shmelov et al. | Expert system for identification of the technical state of the aircraft engine TV3-117 in flight modes | |
| Veshneva et al. | Increasing the safety of flights with the use of mathematical model based on status functions | |
| US20040117042A1 (en) | System and method for implementing real-time applications based on stochastic compute time algorithms | |
| RU2431175C1 (en) | System for integral monitoring of operation of aircraft onboard equipment | |
| CN112926836A (en) | Team combat task matching method based on health state | |
| CN112785074B (en) | Equipment maintenance and repair opportunity determination system and method based on deep learning | |
| Petukhov et al. | Assessment of vocational aptitude of man-machine systems operators | |
| CN112884210B (en) | Vehicle health management system based on fuzzy clustering | |
| Jigajinni et al. | Health management of a typical small aircraft fuel system using an adaptive technique | |
| Virk et al. | Fault prediction using artificial neural network and fuzzy logic | |
| Mahdi et al. | Development of a Method of Structural-Parametric Assessment of the Object State | |
| Pan et al. | Human error probability evaluation based on reference task using intuitionistic fuzzy theory | |
| CN112818598A (en) | Simulation demonstration system and method for vehicle-mounted health management system | |
| CN112819328A (en) | Vehicle grouping comprehensive capability evaluation system and method based on health state | |
| Mackall et al. | Verification and validation of neural networks for aerospace systems |
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 |