CN115993077A - Optimal decision method and optimal decision system for inertial navigation system under complex road condition transportation condition - Google Patents
Optimal decision method and optimal decision system for inertial navigation system under complex road condition transportation condition Download PDFInfo
- Publication number
- CN115993077A CN115993077A CN202310280797.4A CN202310280797A CN115993077A CN 115993077 A CN115993077 A CN 115993077A CN 202310280797 A CN202310280797 A CN 202310280797A CN 115993077 A CN115993077 A CN 115993077A
- Authority
- CN
- China
- Prior art keywords
- inertial navigation
- navigation system
- rule
- quality state
- transportation
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 55
- 239000013598 vector Substances 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 10
- 230000004913 activation Effects 0.000 claims description 23
- 230000004927 fusion Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 235000015842 Hesperis Nutrition 0.000 description 2
- 235000012633 Iberis amara Nutrition 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000003930 cognitive ability Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000008093 supporting effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a method and a system for deciding optimal inertial navigation system under complex road condition transportation, and relates to the field of inertial navigation systems; the inertial navigation system is an inertial navigation system in the aircraft; inputting monitoring information of the road transportation mileage, the railway transportation mileage and a plurality of key characteristic indexes of the inertial navigation system into a preferred decision model of the inertial navigation system, and outputting a quality state characteristic vector of the inertial navigation system; the optimal decision model of the inertial navigation system is obtained by training an optimal decision initial model of the inertial navigation system according to a data set, and the optimal decision initial model of the inertial navigation system is constructed based on a confidence rule base; the quality state grade of the inertial navigation system is determined according to the quality state feature vector output by the optimal decision model of the inertial navigation system, and the accuracy of optimal decision is improved.
Description
Technical Field
The invention relates to the technical field of inertial navigation systems, in particular to an optimal decision method and system of an inertial navigation system under the condition of complex road condition transportation.
Background
An inertial navigation system (Inertial Navigation System, INS), abbreviated as inertial navigation system, is an autonomous navigation system that does not rely on external information nor radiates energy to the outside. In aerospace vehicles such as carrier rockets, an inertial navigation system is used as one of key indexes for measuring performances of the aerospace vehicles, and the flight effect of the rocket is directly determined. Therefore, the inertial navigation system with good performance is selected to have a stronger supporting effect on the task execution of the rocket. The preferred decision method (Preference decision, PD) is an important aspect of health management, and aims to list and rank all the solutions, thereby selecting the optimal solution. At present, key characteristics of an object inertial navigation system are concentrated in integrated design, high automation degree, high subsystem coupling, high real-time requirement, important task bearing and the like, and high requirements are put forward for optimal decision.
Analyzing the problems faced in the current subject inertial navigation system preference decisions can be summarized in three ways: firstly, in the actual running process of an object inertial navigation system, along with the interference of complex road conditions, the internal mechanism of the object inertial navigation system is changed, so that the structure and parameters of sensitive equipment are changed to influence the accuracy of the sensitive equipment, and the problem needs to be solved by introducing a new influence factor; secondly, with the continuous improvement of the equipment manufacturing industry level, the required cost is continuously increased, and the fault data is particularly lacking; thirdly, because of the high coupling among all subsystems of the object inertial navigation system and the adoption of integrated design, the factors influencing the working state of the object inertial navigation system are more, and an accurate mathematical model is difficult to build by simply relying on expert knowledge, so that the expert knowledge is uncertain.
Disclosure of Invention
The invention aims to provide a preferred decision method and a preferred decision system for an inertial navigation system under the condition of complex road condition transportation, and the accuracy of the preferred decision is improved.
In order to achieve the above object, the present invention provides the following solutions:
an inertial navigation system optimal decision-making method under complex road condition transportation conditions comprises the following steps:
acquiring monitoring information of a plurality of key characteristic indexes of a road transportation mileage, a railway transportation mileage and an inertial navigation system passing through an aircraft flight path; the inertial navigation system is an inertial navigation system in the aircraft;
inputting monitoring information of the road transportation mileage, the railway transportation mileage and a plurality of key characteristic indexes of the inertial navigation system into a preferred decision model of the inertial navigation system, and outputting a quality state characteristic vector of the inertial navigation system; the optimal decision model of the inertial navigation system is obtained by training an optimal decision initial model of the inertial navigation system according to a data set, and the optimal decision initial model of the inertial navigation system is constructed based on a confidence rule base;
determining the quality state grade of the inertial navigation system according to the quality state feature vector output by the optimal decision model of the inertial navigation system;
the inertial navigation system preferably makes a decision initial model for:
determining road condition influence factors of an inertial navigation system of the aircraft according to a road transportation stage and a railway transportation stage passing through in a flight path of the aircraft;
determining the matching degree of all the key characteristic indexes in each rule according to the road condition influence factors, the monitoring information of a plurality of key characteristic indexes and a confidence rule base; the confidence rule base is a rule set between monitoring information of key characteristic indexes and quality state characteristic vectors;
determining the activation weight of each rule according to the matching degree;
and determining a fusion quality state characteristic vector of each quality state according to the activation weight of each rule and the quality state characteristic vector of each rule corresponding to each quality state.
Optionally, the determining the road condition influence factor of the inertial navigation system of the aircraft according to the road transportation stage and the railway transportation stage passing in the flight path of the aircraft specifically includes:
according to the formula
Calculating road condition influence factors of an inertial navigation system of the aircraft;
wherein y represents road condition influence factor, beta 1 Coefficients, beta, representing the phase of road transport 2 Coefficient representing railway transportation stage, X 1 Representing the mileage of the highway transportation stage, X 2 Represents the mileage of a railway transportation stage, a 1 Representing the minimum value of the calculated value of the inertial navigation specified transportation mileage, a 2 Representing the maximum value of the inertial navigation-specified mileage conversion value.
Optionally, determining the matching degree of all the key feature indexes in each rule according to the road condition influence factors, the monitoring information of the plurality of key feature indexes and the confidence rule base, which specifically includes:
according to the formula
Determining the matching degree of all the key characteristic indexes in each rule;
wherein ,ak Representing the matching degree of all the key characteristic indexes in the kth rule, M represents the number of the key characteristic indexes, y represents the road condition influence factor,
matching degree of monitoring information representing ith key feature index in kth rule,/>
Representing the relative weight of the ith key feature index;
wherein ,
the weight of the i-th key feature index is represented.
Optionally, determining the activation weight of each rule according to the matching degree specifically includes:
according to the formula
Determining the activation weight of each rule;
wherein ,wk The activation weight of the kth rule is represented,
weights representing the kth rule, +.>
The weight of the first rule, L represents the number of rules, a l Representing the matching degree of all the key characteristic indexes in the first rule, a k And representing the matching degree of all the key characteristic indexes in the kth rule.
Optionally, determining a fused quality state feature vector of each quality state according to the activation weight of each rule and the quality state feature vector of each rule corresponding to each quality state specifically includes:
and fusing the quality state feature vectors of the rules corresponding to each quality state by adopting a evidence reasoning algorithm, and determining the fused quality state feature vector of each quality state.
The invention also discloses a preferred decision system of the inertial navigation system under the complex road condition transportation condition, which comprises the following components:
the data acquisition module is used for acquiring monitoring information of a plurality of key characteristic indexes of road transportation mileage, railway transportation mileage and inertial navigation system passing through in the flight path of the aircraft; the inertial navigation system is an inertial navigation system in the aircraft;
the inertial navigation system decision module is used for inputting monitoring information of the road transportation mileage, the railway transportation mileage and a plurality of key characteristic indexes of the inertial navigation system into a preferred decision model of the inertial navigation system and outputting a quality state characteristic vector of the inertial navigation system; the optimal decision model of the inertial navigation system is obtained by training an optimal decision initial model of the inertial navigation system according to a data set, and the optimal decision initial model of the inertial navigation system is constructed based on a confidence rule base;
the quality state grade determining module is used for determining the quality state grade of the inertial navigation system according to the quality state characteristic vector output by the optimal decision model of the inertial navigation system;
the inertial navigation system preferably makes a decision initial model for:
determining road condition influence factors of an inertial navigation system of the aircraft according to a road transportation stage and a railway transportation stage passing through in a flight path of the aircraft;
determining the matching degree of all the key characteristic indexes in each rule according to the road condition influence factors, the monitoring information of a plurality of key characteristic indexes and a confidence rule base; the confidence rule base is a rule set between monitoring information of key characteristic indexes and quality state characteristic vectors;
determining the activation weight of each rule according to the matching degree;
and determining a fusion quality state characteristic vector of each quality state according to the activation weight of each rule and the quality state characteristic vector of each rule corresponding to each quality state.
The invention also discloses an electronic device, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic device to execute the optimal decision method of the inertial navigation system under the complex road condition transportation condition.
The invention also discloses a computer readable storage medium storing a computer program which when executed by a processor realizes the optimal decision method of the inertial navigation system under the complex road condition transportation condition.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the invention, the optimal decision initial model of the inertial navigation system constructed based on the confidence rule base is trained, the optimal decision model of the inertial navigation system is obtained, monitoring information of a plurality of key characteristic indexes of road transportation mileage, railway transportation mileage and the inertial navigation system is input into the optimal decision model of the inertial navigation system, and a quality state characteristic vector of the inertial navigation system is output, so that the quality state grade of the inertial navigation system is determined, and the accuracy of optimal decision is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a preferred decision method of an inertial navigation system under the condition of complex road condition transportation;
FIG. 2 is a flow chart of a preferred decision mechanism of the present invention;
FIG. 3 is a schematic diagram of key index test data according to the present invention;
FIG. 4 is a schematic diagram of the evaluation result of the preferred decision model of the inertial navigation system of the present invention;
fig. 5 is a schematic structural diagram of an inertial navigation system preferred decision-making system under a complex road condition transportation condition.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a preferred decision method and a preferred decision system for an inertial navigation system under the condition of complex road condition transportation, and the accuracy of the preferred decision is improved.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
The invention aims to solve the problems of few fault samples, uncertain expert knowledge and complex road condition transportation influence faced in the optimal decision process of the inertial navigation system, and establishes an optimal decision method of the inertial navigation system under the complex road condition transportation condition based on a confidence rule base (BRB) expert system to obtain optimal performance selection and provide decision support for the use of subsequent aircrafts.
In the optimal decision method of the inertial navigation system under the complex road condition transportation condition, key characteristic indexes of the inertial navigation system are firstly determined, and the acquired multi-element monitoring information is converted into a unified frame, so that a foundation is laid for the next information fusion. Then, a rule base is constructed according to key characteristic indexes of the inertial navigation system, activation weights of the rules are calculated according to the monitoring information, fusion is carried out through a evidence reasoning (Evidential Reasoning, ER) algorithm, quality state characteristic vectors are obtained, and a performance result of the inertial navigation system is output.
Example 1
As shown in FIG. 1, the optimal decision method of the inertial navigation system under the condition of complex road condition transportation of the invention comprises the following steps:
step 101: acquiring monitoring information of a plurality of key characteristic indexes of a road transportation mileage, a railway transportation mileage and an inertial navigation system passing through an aircraft flight path; the inertial navigation system is an inertial navigation system in the aircraft.
Step 102: inputting monitoring information of the road transportation mileage, the railway transportation mileage and a plurality of key characteristic indexes of the inertial navigation system into a preferred decision model of the inertial navigation system, and outputting a quality state characteristic vector of the inertial navigation system; the optimal decision model of the inertial navigation system is obtained by training an optimal decision initial model of the inertial navigation system according to a data set, and the optimal decision initial model of the inertial navigation system is constructed based on a confidence rule base.
The sample data in the data set comprises road transportation mileage, railway transportation mileage, monitoring information of a plurality of key characteristic indexes and tag data quality state characteristic vectors.
Taking the monitoring information of road transportation mileage, railway transportation mileage and a plurality of key characteristic indexes as input, taking the quality state characteristic vector as output to train the optimal decision initial model of the inertial navigation system, and taking the trained optimal decision initial model of the inertial navigation system as the optimal decision model of the inertial navigation system.
The preferred decision mechanism of the present invention is shown in figure 2.
According to the construction mode of rules in BRB, the optimal decision method of the inertial navigation system under the complex road condition transportation condition in the invention is expressed as follows:
wherein ,Bk (t) monitoring information, delta, of M key characteristic indexes of the inertial navigation system at the moment t i Attribute weight (attribute weight) representing the ith key feature index, x i The monitoring information of the ith key characteristic index is represented, y (t) represents a set of quality state characteristic vectors of the inertial navigation system at the moment t, the value range of i is 1 to M,
representing the reference level corresponding to each key characteristic index, wherein +.>
And the reference level of the kth rule of the ith key characteristic index is represented. { D 1 ，…，D N N mass states of inertial navigation system, [ beta ] 1,k ，β 2,k ，…，β N,k ]A quality state feature vector, θ, representing N quality states corresponding to the kth rule k Representing rule weight, k=1, 2, …, L represents the number of rules.
In a specific embodiment, the monitoring information is a measurement value of an accelerometer.
The inertial navigation system preferably makes a decision initial model for:
and determining road condition influence factors of an inertial navigation system of the aircraft according to the road transportation stage and the railway transportation stage passing through in the flight path of the aircraft.
The sources of the vibration impact of the inertial navigation system are mainly railway transportation and road transportation, and the greater the impact of the vibration impact on the inertial navigation is generally along with the increase of the transportation mileage, and the different vibration impact degrees of the railway transportation and the road transportation are. While the maximum transportation mileage of inertial navigation equipment is required.
Therefore, the road condition influence factor of the inertial navigation system of the aircraft is calculated according to the formula (2).
Wherein y represents road condition influence factors, namely y represents influence degree of vibration impact on inertial navigation in railway transportation and road transportation processes. Beta 1 Coefficients, beta, representing the phase of road transport 2 Coefficient representing railway transportation stage, X 1 Representing the mileage of the highway transportation stage, X 2 Represents the mileage of a railway transportation stage, a 1 Representing the minimum value of the calculated value of the inertial navigation specified transportation mileage, a 2 Representing the maximum value of the inertial navigation-specified mileage conversion value. General beta 1 :β 2= 1:10。
Determining the matching degree of all the key characteristic indexes in each rule according to the road condition influence factors, the monitoring information of a plurality of key characteristic indexes and a confidence rule base; the confidence rule base is a rule set between monitoring information of key characteristic indexes and quality state characteristic vectors.
According to the actual working condition of the inertial navigation system, the quality state characteristic indexes of the set quantity are determined, and as the acquired multi-element monitoring information (the monitoring information of a plurality of key characteristic indexes) is different in format and cannot be directly used, the multi-element monitoring information needs to be converted into a unified frame through the following formula:
wherein ,
monitoring information representing ith key characteristic index at t moment, R ik Representing the reference level of the ith key feature index in the kth rule, R i(k+1) And representing the reference grade of the ith key feature index in the (k+1) th rule, wherein the reference grade is required to be determined by combining the information distribution and the type of the features. L' represents the number of rules after adjustment of the inertial navigation system preferred initial decision model (inertial navigation system preferred decision model), ->
The monitoring information representing the ith key feature index is matched in the jth rule after format conversion.
After the matching degree of each index in each rule is obtained, the matching degree of all key characteristic indexes in the kth rule can be obtained through the following formula:
wherein ,ak Representing the matching degree of all the key characteristic indexes in the kth rule, M represents the number of the key characteristic indexes, y represents the road condition influence factor,
matching degree of monitoring information representing ith key characteristic index in kth rule after format conversion, ++>
Representing the relative of the ith key feature indexWeighting; />
The weight of the i-th key feature index is represented.
In the constructed preferred decision model, different monitoring information can have different effects on different rules, and the activation weight of each rule is determined according to the matching degree. The method specifically comprises the following steps:
the activation weight for each rule is determined according to equation (6).
wherein ,wk The activation weight of the kth rule is represented,
the weight of the kth rule is expressed, i.e. when the rule is important in the preferred decision model relative to the other rules, +.>
The weight of the first rule, L represents the number of rules, a l Representing the matching degree of all the key characteristic indexes in the first rule, a k And representing the matching degree of all the key characteristic indexes in the kth rule.
According to the activation weight of each rule and the quality state feature vector of each rule corresponding to each quality state, determining a fusion quality state feature vector of each quality state specifically comprises the following steps:
and fusing the quality state feature vectors of the rules corresponding to each quality state by adopting a evidence reasoning algorithm, and determining the fused quality state feature vector of each quality state.
The activated rule produces a feature vector of the system quality state that represents the results produced by the rule diagnosis. The quality state feature vectors output by all rules can be fused through a evidence reasoning (Evidential Reasoning, ER) algorithm to obtain the final output quality state feature vector. The ER algorithm resolution format is as follows:
wherein ,[β1 ,β 2 ,…,β N ]Preferred decision model output quality state feature vector for inertial navigation system, beta n Represents the nth output result level D n Is a confidence level of (2). Beta is not less than 0 n Is less than or equal to 1
。
Step 103: and determining the quality state grade of the inertial navigation system according to the quality state characteristic vector output by the optimal decision model of the inertial navigation system.
Quality status classes include excellent, good, neutral, and poor.
The preferred decision is to evaluate the quality of the inertial navigation system in good and bad condition, and the inertial navigation system with different quality can be used for different tasks.
Step 103 specifically includes: and determining a quality state evaluation grade of the inertial navigation system according to the fusion quality state characteristic vector and the utility of each quality state.
If a single evaluation result D n Is effective as u (D) n ) The final output result of the inertial navigation system quality state evaluation model is expressed as:
wherein ,
and the final output result of the inertial navigation system quality state evaluation model constructed based on the BRB, namely the quality state evaluation grade of the inertial navigation system obtained by monitoring information.
The invention increases the reason for optimizing the optimal decision initial model of the inertial navigation system: because the BRB initial model (the optimal decision initial model of the inertial navigation system) is given by an expert, and is influenced by the limitation of the cognitive ability of the expert, the parameters of the BRB initial model have certain deviation, so that the actual modeling effect cannot meet the requirements, and therefore, an optimization model needs to be built to optimize the parameters of the BRB model, and meanwhile, the fusion of data and knowledge is achieved. In terms of model parameter updating, because the BRB belongs to an expert system, strict requirements are imposed on the physical meaning of the model parameters. Therefore, the following constraints need to be obeyed in the model parameter optimization process:
0≤θ k ≤1 （10）
0≤δ k ≤1，i=1,2,…,M （11）
0≤β 1 ≤1，n=1,2,…,N，k=1,2,…,L’ （12）
in order to verify the effectiveness of the invention, experimental verification is carried out by an inertial navigation system under the condition of complex road condition transportation, and the method mainly comprises the following steps:
step one: problem description and road condition influence factor calculation.
In the case of rockets, the position and velocity of the rocket are variable due to the long flight time, and these data are initial parameters of the launched rocket, directly affecting the accuracy of the rocket's flight, thus requiring the provision of high accuracy position, velocity and vertical alignment signals. The inertial navigation is carried out independently and independently by means of the carrier equipment, does not depend on external information, has the advantages of good concealment, and high accuracy, and works are not affected by meteorological conditions and artificial interference. The inertial navigation technology is gradually popularized to the fields of aerospace, aviation, navigation, petroleum development, geodetic survey, marine survey, geological drilling control, robot technology, railway and the like, and is applied to automobile industry and medical electronic equipment along with the appearance of novel inertial sensitive devices. In the experiment, the disturbance received in the real working environment is simulated by the simulation disturbance device, the selected key characteristic indexes are output results of three accelerometers, the monitoring information of each key characteristic index collected in the experiment is shown in fig. 3, (a) is the monitoring information of the accelerometer 1, (b) is the monitoring information of the accelerometer 2, and (c) is the monitoring information of the accelerometer 3. The abscissa in fig. 3 represents the number of sample groups, and the ordinate represents the monitored information value.
Step two: establishment of optimal decision model of inertial navigation system under complex road condition transportation condition
In the monitoring data of the three accelerometers, the reference levels of the monitoring information of the three accelerometers are respectively determined to be 4 by combining the data quantity, the complexity of the model, the diagnosis precision, the diagnosis real-time performance and the like, and are shown in table 1. In combination with the rule construction mode shown in the formula (1), the constructed preferred decision model has 64 rules in total. Since accelerometers are susceptible to environmental influences during actual use, three accelerometer monitoring information needs to be considered simultaneously in determining the rule output confidence, and an initial diagnostic model is shown in table 2. In the initial model, it is assumed that the rule is equally important, i.e. the rule weight is set to 1.
Wherein Y, L, Z, C represents the excellent, good, medium and poor, respectively.
Step three: training and testing of optimal decision model of inertial navigation system under complex road condition transportation condition
Under the condition of complex road condition transportation, the inertial navigation system has the following four stages: no transportation stage, highway transportation stage, railway transportation stage, highway and railway transportation stage. In the experimental process, the data 1300 sets are collected together, wherein the accelerometer 1 is subjected to shaking and collecting 300 sets, the accelerometer 2 is subjected to shaking and collecting 300 sets, and the accelerometer 3 is subjected to shaking and collecting 300 sets. The set 650 is randomly screened from the dataset as training data to train the constructed preferred decision model.
In FIG. 4, the abscissa indicates the number of groups and the ordinate indicates the model output value, and it can be seen from FIG. 4 that the points are after the initial model is optimized in use
) The line segment is a model output value, the continuous line represents an actually calculated value, and it can be seen that the optimal decision model of the inertial navigation system can evaluate the quality state of the inertial navigation system more accurately, and can make accurate evaluation at partial monitoring points which cannot be accurately judged by an expert, thereby effectively overcoming uncertainty and partial unknowness of expert knowledge, achieving effective back feeding of monitoring data to the expert knowledge, perfecting the expert system, realizing effective fusion of the monitoring data and the expert knowledge, and accurately performing optimal decision sequencing. After training, the index weights of the influence factors are respectively 0.9. The MSE of the trained model is 0.0237, which is far smaller than the mean value of safety evaluation, and the evaluation accuracy is higher.
Example 2
Fig. 5 is a schematic structural diagram of an inertial navigation system preferred decision system under a complex road condition transportation condition according to the present invention, as shown in fig. 5, and the inertial navigation system preferred decision system under a complex road condition transportation condition includes:
the data acquisition module 201 is used for acquiring monitoring information of a plurality of key characteristic indexes of road transportation mileage, railway transportation mileage and inertial navigation system passing through in the flight path of the aircraft; the inertial navigation system is an inertial navigation system in the aircraft.
The inertial navigation system decision module 202 is configured to input monitoring information of the road transportation mileage, the railway transportation mileage and a plurality of key feature indexes of the inertial navigation system into an inertial navigation system optimal decision model, and output a quality state feature vector of the inertial navigation system; the optimal decision model of the inertial navigation system is obtained by training an optimal decision initial model of the inertial navigation system according to a data set, and the optimal decision initial model of the inertial navigation system is constructed based on a confidence rule base.
The quality state grade determining module 203 is configured to determine a quality state grade of the inertial navigation system according to the quality state feature vector output by the preferred decision model of the inertial navigation system.
The inertial navigation system preferably makes a decision initial model for:
and determining road condition influence factors of an inertial navigation system of the aircraft according to the road transportation stage and the railway transportation stage passing through in the flight path of the aircraft.
Determining the matching degree of all the key characteristic indexes in each rule according to the road condition influence factors, the monitoring information of a plurality of key characteristic indexes and a confidence rule base; the confidence rule base is a rule set between monitoring information of key characteristic indexes and quality state characteristic vectors.
And determining the activation weight of each rule according to the matching degree.
And determining a fusion quality state characteristic vector of each quality state according to the activation weight of each rule and the quality state characteristic vector of each rule corresponding to each quality state.
Example 3
The embodiment discloses an electronic device, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic device to execute the optimal decision method of an inertial navigation system under the complex road condition transportation condition according to the embodiment 1.
The present embodiment also discloses a computer readable storage medium storing a computer program which when executed by a processor implements the inertial navigation system preference decision method under the complex road condition transportation situation as described in embodiment 1.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (6)
1. The optimal decision method of the inertial navigation system under the condition of complex road condition transportation is characterized by comprising the following steps:
acquiring monitoring information of a plurality of key characteristic indexes of a road transportation mileage, a railway transportation mileage and an inertial navigation system passing through an aircraft flight path; the inertial navigation system is an inertial navigation system in the aircraft;
inputting monitoring information of the road transportation mileage, the railway transportation mileage and a plurality of key characteristic indexes of the inertial navigation system into a preferred decision model of the inertial navigation system, and outputting a quality state characteristic vector of the inertial navigation system; the optimal decision model of the inertial navigation system is obtained by training an optimal decision initial model of the inertial navigation system according to a data set, and the optimal decision initial model of the inertial navigation system is constructed based on a confidence rule base;
determining the quality state grade of the inertial navigation system according to the quality state feature vector output by the optimal decision model of the inertial navigation system;
the inertial navigation system preferably makes a decision initial model for:
determining road condition influence factors of an inertial navigation system of the aircraft according to a road transportation stage and a railway transportation stage passing through in a flight path of the aircraft;
determining the matching degree of all the key characteristic indexes in each rule according to the road condition influence factors, the monitoring information of a plurality of key characteristic indexes and a confidence rule base; the confidence rule base is a rule set between monitoring information of key characteristic indexes and quality state characteristic vectors;
determining the activation weight of each rule according to the matching degree;
and determining a fusion quality state characteristic vector of each quality state according to the activation weight of each rule and the quality state characteristic vector of each rule corresponding to each quality state.
2. The method for determining the optimal decision of the inertial navigation system under the complex road condition transportation condition according to claim 1, wherein the determining the road condition influence factor of the inertial navigation system of the aircraft according to the road transportation stage and the railway transportation stage passing in the flight path of the aircraft specifically comprises:
according to the formula
Calculating road condition influence factors of an inertial navigation system of the aircraft;
wherein y represents road condition influence factor, beta 1 Coefficients, beta, representing the phase of road transport 2 Coefficient representing railway transportation stage, X 1 Representing the mileage of the highway transportation stage, X 2 Represents the mileage of a railway transportation stage, a 1 Representing the minimum value of the calculated value of the inertial navigation specified transportation mileage, a 2 Representing the maximum value of the inertial navigation-specified mileage conversion value.
3. The optimal decision method of the inertial navigation system under the complex road condition transportation condition according to claim 1, wherein the determining the matching degree of all the key feature indexes in each rule according to the road condition influence factor, the monitoring information of a plurality of key feature indexes and the confidence rule base specifically comprises:
according to the formula
Determining the matching degree of all the key characteristic indexes in each rule;
wherein ,ak Representing the matching degree of all the key characteristic indexes in the kth rule, M represents the number of the key characteristic indexes, y represents the road condition influence factor,
the degree of matching of the monitoring information representing the ith key feature index in the kth rule,
representing the relative weight of the ith key feature index;
wherein ,
the weight of the i-th key feature index is represented.
4. The optimal decision method of the inertial navigation system under the complex road condition transportation condition according to claim 1, wherein the determining the activation weight of each rule according to the matching degree specifically comprises:
according to the formula
Determining the activation weight of each rule;
wherein ,wk The activation weight of the kth rule is represented,
weights representing the kth rule, +.>
The weight of the first rule, L represents the number of rules, a l Representing the matching degree of all the key characteristic indexes in the first rule, a k And representing the matching degree of all the key characteristic indexes in the kth rule.
5. The method for determining the optimal decision of the inertial navigation system under the complex road condition transportation condition according to claim 1, wherein the determining the fused mass state feature vector of each mass state according to the activation weight of each rule and the mass state feature vector of each rule corresponding to each mass state specifically comprises:
and fusing the quality state feature vectors of the rules corresponding to each quality state by adopting a evidence reasoning algorithm, and determining the fused quality state feature vector of each quality state.
6. An inertial navigation system optimal decision system under complex road condition transportation condition is characterized by comprising:
the data acquisition module is used for acquiring monitoring information of a plurality of key characteristic indexes of road transportation mileage, railway transportation mileage and inertial navigation system passing through in the flight path of the aircraft; the inertial navigation system is an inertial navigation system in the aircraft;
the inertial navigation system decision module is used for inputting monitoring information of the road transportation mileage, the railway transportation mileage and a plurality of key characteristic indexes of the inertial navigation system into a preferred decision model of the inertial navigation system and outputting a quality state characteristic vector of the inertial navigation system; the optimal decision model of the inertial navigation system is obtained by training an optimal decision initial model of the inertial navigation system according to a data set, and the optimal decision initial model of the inertial navigation system is constructed based on a confidence rule base;
the quality state grade determining module is used for determining the quality state grade of the inertial navigation system according to the quality state characteristic vector output by the optimal decision model of the inertial navigation system;
the inertial navigation system preferably makes a decision initial model for:
determining road condition influence factors of an inertial navigation system of the aircraft according to a road transportation stage and a railway transportation stage passing through in a flight path of the aircraft;
determining the matching degree of all the key characteristic indexes in each rule according to the road condition influence factors, the monitoring information of a plurality of key characteristic indexes and a confidence rule base; the confidence rule base is a rule set between monitoring information of key characteristic indexes and quality state characteristic vectors;
determining the activation weight of each rule according to the matching degree;
and determining a fusion quality state characteristic vector of each quality state according to the activation weight of each rule and the quality state characteristic vector of each rule corresponding to each quality state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280797.4A CN115993077B (en) | 2023-03-22 | 2023-03-22 | Optimal decision method and optimal decision system for inertial navigation system under complex road condition transportation condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280797.4A CN115993077B (en) | 2023-03-22 | 2023-03-22 | Optimal decision method and optimal decision system for inertial navigation system under complex road condition transportation condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115993077A true CN115993077A (en) | 2023-04-21 |
| CN115993077B CN115993077B (en) | 2023-06-06 |
Family
ID=85993718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310280797.4A Active CN115993077B (en) | 2023-03-22 | 2023-03-22 | Optimal decision method and optimal decision system for inertial navigation system under complex road condition transportation condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115993077B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451912A (en) * | 2023-06-19 | 2023-07-18 | 西北工业大学 | Complex electromechanical system performance evaluation method and system under condition of influence of replacement |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001031450A1 (en) * | 1999-10-28 | 2001-05-03 | General Electric Company | Apparatus and method for performance and fault data analysis |
| EP1462767A1 (en) * | 2003-02-27 | 2004-09-29 | The Boeing Company | Flight guidance system and symbology and control system providing perspective flight guidance |
| US20050125117A1 (en) * | 1995-06-07 | 2005-06-09 | Breed David S. | Vehicular information and monitoring system and methods |
| US20080154495A1 (en) * | 1997-10-22 | 2008-06-26 | Intelligent Technologies International, Inc. | Inertial Measurement Unit for Aircraft |
| CN111259551A (en) * | 2020-01-17 | 2020-06-09 | 中国人民解放军火箭军工程大学 | Inertial measurement unit fault prediction method based on confidence rule base |
| CN111931307A (en) * | 2020-08-11 | 2020-11-13 | 西北工业大学 | Part quality prediction and evaluation optimization method and system |
| CN112418682A (en) * | 2020-11-26 | 2021-02-26 | 中国人民解放军火箭军工程大学 | Security assessment method fusing multi-source information |
| WO2022100687A1 (en) * | 2020-11-12 | 2022-05-19 | 医渡云（北京）技术有限公司 | Fusion decision-making method and apparatus, and computer-readable storage medium and electronic device |
| US20220406201A1 (en) * | 2021-06-22 | 2022-12-22 | Honeywell International Inc. | Automatic autoland activation methods and systems |
| CN115638808A (en) * | 2022-12-23 | 2023-01-24 | 中国人民解放军火箭军工程大学 | Inertial navigation system quality state determination method and system integrating time-space domain information |
-
2023
- 2023-03-22 CN CN202310280797.4A patent/CN115993077B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050125117A1 (en) * | 1995-06-07 | 2005-06-09 | Breed David S. | Vehicular information and monitoring system and methods |
| US20080154495A1 (en) * | 1997-10-22 | 2008-06-26 | Intelligent Technologies International, Inc. | Inertial Measurement Unit for Aircraft |
| WO2001031450A1 (en) * | 1999-10-28 | 2001-05-03 | General Electric Company | Apparatus and method for performance and fault data analysis |
| EP1462767A1 (en) * | 2003-02-27 | 2004-09-29 | The Boeing Company | Flight guidance system and symbology and control system providing perspective flight guidance |
| CN111259551A (en) * | 2020-01-17 | 2020-06-09 | 中国人民解放军火箭军工程大学 | Inertial measurement unit fault prediction method based on confidence rule base |
| CN111931307A (en) * | 2020-08-11 | 2020-11-13 | 西北工业大学 | Part quality prediction and evaluation optimization method and system |
| WO2022100687A1 (en) * | 2020-11-12 | 2022-05-19 | 医渡云（北京）技术有限公司 | Fusion decision-making method and apparatus, and computer-readable storage medium and electronic device |
| CN112418682A (en) * | 2020-11-26 | 2021-02-26 | 中国人民解放军火箭军工程大学 | Security assessment method fusing multi-source information |
| US20220406201A1 (en) * | 2021-06-22 | 2022-12-22 | Honeywell International Inc. | Automatic autoland activation methods and systems |
| CN115638808A (en) * | 2022-12-23 | 2023-01-24 | 中国人民解放军火箭军工程大学 | Inertial navigation system quality state determination method and system integrating time-space domain information |
Non-Patent Citations (2)
| Title |
|---|
| 董昕昊等: "基于分层置信规则库的惯导系统性能评估方法", 航空学报, vol. 42, no. 07, pages 1 - 11 * |
| 陈雷雨等: "融合多元信息的武器装备性能评估方法", 系统工程与电子技术, vol. 42, no. 07, pages 1527 - 1533 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451912A (en) * | 2023-06-19 | 2023-07-18 | 西北工业大学 | Complex electromechanical system performance evaluation method and system under condition of influence of replacement |
| CN116451912B (en) * | 2023-06-19 | 2023-09-19 | 西北工业大学 | Complex electromechanical system performance evaluation method and system under condition of influence of replacement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115993077B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Morelli et al. | Application of system identification to aircraft at NASA Langley Research Center | |
| CN109866752A (en) | Double mode parallel vehicles track following driving system and method based on PREDICTIVE CONTROL | |
| US8855852B2 (en) | Method and system for monitoring a structure | |
| CN104773304B (en) | Load estimation system for aerodynamic structures | |
| Sushchenko et al. | Processing of redundant information in airborne electronic systems by means of neural networks | |
| CN109188026B (en) | Automatic calibration deep learning method suitable for MEMS accelerometer | |
| CN110348752B (en) | Large industrial system structure safety assessment method considering environmental interference | |
| CN102037421A (en) | Estimating a loading criterion for the load experienced by a structural component of an aircraft, and assistance with detection of a so-called ''hard'' landing using such a criterion | |
| CN115993077B (en) | Optimal decision method and optimal decision system for inertial navigation system under complex road condition transportation condition | |
| CN111638034B (en) | Strain balance temperature gradient error compensation method and system based on deep learning | |
| CN104048676B (en) | MEMS (Micro Electro Mechanical System) gyroscope random error compensating method based on improved particle filter | |
| CN109615860A (en) | A kind of signalized intersections method for estimating state based on nonparametric Bayes frame | |
| CN111190211B (en) | GPS failure position prediction positioning method | |
| CN116519021B (en) | Inertial navigation system fault diagnosis method, system and equipment | |
| Lerro et al. | Aerodynamic angle estimation: comparison between numerical results and operative environment data | |
| CN115742855A (en) | Electric automobile remaining mileage prediction method and device, electric automobile and medium | |
| Liu et al. | Road roughness acquisition and classification using improved restricted Boltzmann machine deep learning algorithm | |
| Shi et al. | Tilt angle monitoring by using sparse residual LSTM network and grid search | |
| CN108362307B (en) | Method for determining principal component factors of star sensor on-orbit attitude measurement accuracy | |
| CN105447228A (en) | Earth disturbing gravity assignment model applicability evaluating method | |
| CN113703025B (en) | GNSS (Global navigation satellite System) multiple failure state-oriented intelligent vehicle positioning error prediction method | |
| Vrijdag et al. | Systematic modelling, verification, calibration and validation of a ship propulsion simulation model | |
| Wagner | GNSS/INS integration: still an attractive candidate for automatic landing systems? | |
| He et al. | Development of regime recognition tools for usage monitoring | |
| CN116451912B (en) | Complex electromechanical system performance evaluation method and system under condition of influence of replacement |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |