CN111222736A - Ammunition storage reliability evaluation method based on mixed correlation vector machine model - Google Patents
Ammunition storage reliability evaluation method based on mixed correlation vector machine model Download PDFInfo
- Publication number
- CN111222736A CN111222736A CN201910929227.7A CN201910929227A CN111222736A CN 111222736 A CN111222736 A CN 111222736A CN 201910929227 A CN201910929227 A CN 201910929227A CN 111222736 A CN111222736 A CN 111222736A
- Authority
- CN
- China
- Prior art keywords
- model
- rvm
- reliability
- storage reliability
- kernel
- 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
- 239000013598 vector Substances 0.000 title claims abstract description 21
- 238000011156 evaluation Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000002790 cross-validation Methods 0.000 claims abstract description 15
- IMACFCSSMIZSPP-UHFFFAOYSA-N phenacyl chloride Chemical compound ClCC(=O)C1=CC=CC=C1 IMACFCSSMIZSPP-UHFFFAOYSA-N 0.000 claims abstract description 14
- 239000003491 tear gas Substances 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 14
- 230000008901 benefit Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000013210 evaluation model Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Strategic Management (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Tourism & Hospitality (AREA)
- Algebra (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an ammunition storage reliability evaluation method based on a mixed correlation vector machine model, which comprises the following steps of: s1, linearly forming a Mixed Function (MF) kernel by the PF kernel and the RBF kernel, and establishing a MF-RVM model; s2, based on a leave-one-out cross validation method, judging whether the model is good or bad through calculation of the average value of the comprehensive loss function, and selecting an optimal model; s3, solving the MF-RVM model based on QPSO; s4, modeling according to the sample data of the small sample tear-gas shells of certain types; and S5, predicting the reliability value according to the model. The method has stable evaluation index, and in addition, the method can effectively evaluate the ammunition storage reliability of the small sample under the condition of non-test data.
Description
Technical Field
The invention belongs to the field of system performance evaluation, and particularly relates to an ammunition storage reliability evaluation method of a mixed correlation vector machine model.
Background
In general, ammunition storage reliability assessment based on progressive theory requires the acquisition of a large amount of life data. However, the service life test of ammunition is expensive, the implementation engineering is complex, large sample data is difficult to obtain, and the result obtained by directly processing the small sample data by using a classical statistical method has inaccurate accuracy. For the situation of a small sample, Bayes theory is introduced in the literature, and the prior information is used for reliability evaluation, but the subjectivity of the obtained result is large sometimes. Later, a plurality of scholars process the service life data through a self-help capacity expansion method, large sample data meeting the classical statistical method are obtained, and the obtained result is closer to the true value. However, the above methods are based on data obtained by actual life tests, and in most basic units, there is no test condition, and therefore, it is necessary to find an effective evaluation method based on non-test data.
In order to overcome the problem that the basic unit test condition is limited, the invention provides an ammunition storage reliability evaluation method based on a mixed correlation vector machine model, and according to the research of troops, a small amount of non-test data such as storage time, temperature and humidity environment and the like can be obtained in an ammunition storage warehouse, the storage reliability evaluation is carried out by fully utilizing the data, and the method has important theoretical significance and application value for the research on the ammunition storage reliability.
Disclosure of Invention
In order to scientifically, reasonably and comprehensively determine the evaluation index value of the ammunition storage reliability, the invention provides an ammunition storage reliability evaluation method based on a mixed correlation vector machine model, and aims to solve the problem of ammunition storage reliability evaluation under the condition of small samples and non-test data.
The invention is realized in such a way that an ammunition storage reliability evaluation method based on a mixed correlation vector machine model comprises the following steps:
s1, establishing a mixed kernel function correlation vector machine (MF-RVM) model
Since ammunition storage reliability predictions have significant non-linearity, it is necessary to introduce a kernel function to convert it to linear. The selection of the kernel function and the kernel parameters directly influences the learning and generalization capability of the RVM model, so that the establishment of the RVM model with good ammunition storage reliability is critical to the selection of the proper kernel function and the proper kernel parameters. The kernel functions are divided into local kernels and global kernels, both belonging to a single kernel function. The most commonly used mononuclear functions are listed in table 1.
TABLE 1 common mononuclear functions
A Polynomial Function (PF) kernel belongs to a global kernel Function, which has the advantage that most sample values can have an influence on the kernel Function value. However, if the value of the characteristic parameter τ is larger, the dimension is higher, the calculation amount is also larger, and the complexity of the model is increased, so that an overfitting phenomenon may occur, and the generalization performance is reduced.
A Radial Basis Function (RBF) kernel belongs to a local kernel Function and has a wide convergence domain, so that the method is high in universality and suitable for various conditions of high-dimensional, low-dimensional, large-dimensional and small samples. The width parameter g controls the radial reach of the kernel function. When the value of the width parameter g is too large, the attenuation of the kernel function to the characteristic value is slowed, so that the learning performance of the model is reduced; on the contrary, when the width parameter g is too small, the generalization performance is affected accordingly.
In summary, in view of the single mapping mode of the mononuclear Function, in the RVM model for evaluating the storage reliability of the ammunition, the mononuclear Function is sometimes used to not accurately describe the characteristic change characteristics, so that when the model is established, the advantages of the respective mononuclear functions are synthesized, and at the same time, the respective deficiencies are avoided, and the PF core and the RBF core are linearly combined into a Mixed Function (MF) core, thereby establishing a Mixed Kernel Function-Relevance Vector Machine (MF-RVM) model. Wherein the MF core is of the form:
in the formula, lambda is called an adjustment coefficient, and lambda is more than or equal to 0 and less than or equal to 1.
S2, based on leave-one-out cross validation method, judging whether the model is good or bad by calculating the mean value of the comprehensive loss function, and selecting the optimal model
In order to obtain a reliable and stable model with good learning and generalization performance, a cross-validation method can be adopted to select the model. The basic idea is as follows: repeatedly using sample data, dividing the data set with given sample capacity n, combining the data set with given sample capacity n1And n2Training set and validation set of (1), hereinAnd repeatedly training and verifying on the basis.
The cross validation comprises simple cross validation, S-fold cross validation, left P cross validation and the like. As the amount of available data samples for evaluating the ammunition storage reliability is small, and in view of the high sample utilization rate of the leave-one cross validation method and the suitability for the condition of small samples, the leave-one cross validation method is adopted to select the model when the ammunition storage reliability MF-RVM model is established in the chapter. At this time, 1 element is used as the verification set, and the remaining n-1 elements are used as the training set, i.e. n is taken1＝n-1，n2Arbitrarily selecting n-1 sample data from n sample data as training sample
And (4) carrying out the following steps.
Certain loss function values are needed to measure the performance of the model during model selection. In general, the smaller the number of correlation vectors RV required for the built model, and the smaller the training root mean square error train _ RMS and the verification root mean square error verify _ RMSE, the better the overall performance of the model. Therefore, from the above parameters, equation (13) can be used as the synthetic loss function.
S3 MF-RVM model solving method based on QPSO
From the analysis, the value of the nuclear parameter in the model has a significant influence on the learning and generalization performance of the model, so that an accurate, rapid and stable nuclear parameter optimization algorithm is needed to find the most appropriate nuclear parameter combination, and thus the optimal ammunition storage reliability MF-RVM model is established.
In combination with the advantages and disadvantages of the optimization algorithms in recent years, QPSO is adopted to solve the MF-RVM model, wherein the loss function mean value is adopted
As a fitness function of the seek.
According to the steps of solving the MF-RVM model based on the QPSO, a final ammunition storage reliability evaluation model can be established. When the MF-RVM model is established, a leave-one-out cross verification method is adopted to select the model by calculating the average value of the comprehensive loss function of all possible models, so that the learning and generalization performance of the final model is ensured. Therefore, the ammunition storage reliability model established according to the above steps is based on an optimal model under MF nuclear conditions.
S4, modeling according to sample tear gas sample data of certain type of small sample
Sample data which can be used for establishing a storage reliability MF-RVM model of a tear-gas shells and is extracted according to a scientific research project group is shown in a table 1.
TABLE 2 data on the storage life, temperature and humidity environment and historical reliability of tear-gas shells
According to the data in the table, the data are divided into three groups, and a training set, a verification set and a test set are respectively formed. Wherein, the front 8 groups of data are used as a training set and a verification set, model fitting solving is carried out, and RVM model selection is carried out by adopting leave-one cross verification. The 9 th group of data was not involved in model training and was used as a generalization performance test for the final model.
S5, predicting the reliability value according to the model
Combining Matlab software, writing program code, taking M as 20, D as 3, QQ as 100, aa as 1, bb as 0.5, c1＝c2＝c3＝c4In addition, setting the initial kernel parameter value ranges to be respectively: lambda is more than 0 and less than 1, tau is more than 1 and less than 5, and g is more than 10 and less than 10, then the MF-RVM model can be trained.
The optimization path of the MF kernel parameter obtained by training is shown in fig. 2, the kernel parameter value is shown in table 3, and the weight w component value is shown in table 4.
TABLE 3 QPSO optimized MF Nuclear parameter results
TABLE 4 weight of model MF-RVM for storage reliability of tear-gas shells
The specific expression of the final storage reliability MF-RVM model of a certain type of tear-gas shells can be obtained according to the results as follows:
as can be seen from Table 4, most weight components of the final tear-gas bomb storage reliability MF-RVM model are zero, and the sparse property of the model is reflected. At this time, the sample vector corresponding to the basis function of the non-zero weight is the sample x used by the final training model1,x3,x7This is called the "correlation vector".
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 QPSO Path diagram for optimizing MF kernel parameters
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention discloses an air-ground missile hit precision evaluation method based on an error spectrum, which comprises the following steps of:
1. an ammunition storage reliability assessment method based on a mixed correlation vector machine model is characterized by comprising the following steps:
s1, linearly forming a Mixed Function (MF) kernel by the PF kernel and the RBF kernel, and establishing a MF-RVM model;
s2, based on a leave-one-out cross validation method, judging whether the model is good or bad through calculation of the average value of the comprehensive loss function, and selecting an optimal model;
s3, solving the MF-RVM model based on QPSO;
s4 sample of tear gas bomb of certain type based on small sample
In step S1, the MF core combines the advantages of the PF core and the RBF core, and according to the RVM regression principle, a normalized sample set is given:
wherein the content of the first and second substances,
representing input sample feature values; i is 1,2, …, n, n is the sample size; j is 1,2, …, d, d is the dimension of the input sample feature; riRepresenting a corresponding output reliability value.
The ammunition storage reliability MF-RVM model at this time is specifically expressed as:
the MF-RVM model involves three main nuclear parameters: a characteristic parameter tau in the PF core, a width parameter g in the RBF core, and a regulating parameter lambda for balancing the influence between the two.
After obtaining the ammunition storage reliability model based on MF-RVM, how to train to obtain a model with optimal learning and generalization performance is the key for evaluation, and the quality of the model performance needs a certain loss function as a measurement standard, namely, the model is selected through a certain strategy. To solve the problem, the optimal model is selected by judging the model quality through the calculation of the average value of the comprehensive loss function based on a leave-one-cross validation method.
In step S2, when the leave-one cross-validation is adopted, and the (ci) th time selects n-1 samples as training samples, the calculation formula of the comprehensive loss function corresponding to the model is as follows:
where ci is 1, …, n.
And
wherein R isiRepresenting a reliability value in the sample set;
representing the reliability values obtained by the model.
Further, the average value of the above n synthetic loss functions is determined
As criteria for MF-RVM model selection at cross-validation:
obviously, it is apparent from equation (13) that, when the training sample size and the verification sample size are constant, the less RV is required for the model, and the smaller train _ RMSE and verify _ RMSE are, the smaller the value of the comprehensive loss function is. Thus, when multiple models with different parameters are given, the mean of the synthetic loss function is selected
And the model corresponding to the minimum time is the optimal model.
Through the establishment and selection of the ammunition storage reliability MF-RVM model, parameters in the model are optimized finally, namely the model is solved, and the ammunition storage reliability MF-RVM model is solved based on QPSO.
In step S3, the advantages and disadvantages of each optimization algorithm in recent years are integrated, the QPSO is adopted to solve the MF-RVM model, and the average value of the loss function is calculated
As a fitness function of the seek. The QPSO-based solution of the MF-RVM model is given by combining with the RVM regression principle, as shown in the attached figure 1 of the specification. And (4) solving the MF-RVM model based on QPSO, and establishing a final ammunition storage reliability evaluation model. When an MF-RVM model is established, a leave-one-cross verification method is adopted to select all possible models by analyzing the loss function mean value, and finally the learning and generalization performance of the models is ensured. Therefore, the ammunition storage reliability model established according to the above steps is an optimal model based on the MF nuclear condition.
In step S5, test data of group 9 is inputted according to the MF-RVM model of the tear-gas bomb storage reliability to obtain a reliability output value, and a test root mean square error test _ RMSE with the historical true value is calculated as shown in table 5.
TABLE 5 reliability prediction value corresponding to normalization data of tear-gas shells in warm and humid environment
As can be seen from Table 5, according to the MF-RVM model, the storage life and the normalized data of the warm and humid environment of the newly input test set result in a prediction result of the reliability of 0.41 and a test root mean square error from the historical true value of only 0.0004. Therefore, the built tear-gas shells storage reliability MF-RVM model can accurately predict the corresponding reliability value according to the given storage age and the temperature and humidity environment data.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (6)
1. An ammunition storage reliability assessment method based on a mixed correlation vector machine model is characterized by comprising the following steps:
s1, linearly forming a Mixed Function (MF) kernel by the PF kernel and the RBF kernel, and establishing a MF-RVM model;
s2, based on a leave-one-out cross validation method, judging whether the model is good or bad through calculation of the average value of the comprehensive loss function, and selecting an optimal model;
s3, solving the MF-RVM model based on QPSO;
s4, modeling according to the sample data of the small sample tear-gas shells of certain types;
and S5, predicting the reliability value according to the model.
2. The ammunition storage reliability evaluation method based on mixed relevance vector machine model according to claim 1, characterized in that in step S1, a normalized sample set is given according to RVM regression principle
The ammunition storage reliability MF-RVM model at this time is specifically expressed as:
the MF-RVM model involves three main nuclear parameters: a characteristic parameter tau in the PF core, a width parameter g in the RBF core, and a regulating parameter lambda for balancing the influence between the two.
3. The ammunition storage reliability evaluation method based on mixed relevance vector machine model according to claim 1, characterized in that in step S2, the key indexes comprise:
wherein
And R isiRepresenting a reliability value in the sample set;
representing the reliability values obtained by the model.
Further, the average value of the above n synthetic loss functions is determined
As criteria for MF-RVM model selection at cross-validation:
when the training sample size and the verification sample size are fixed, the less RV is needed by the model, and the smaller train _ RMSE and verify _ RMSE are, the smaller the comprehensive loss function value is. Thus, when multiple models with different parameters are given, the mean of the synthetic loss function is selected
And the model corresponding to the minimum time is the optimal model.
4. The method for evaluating the reliability of storage of ammunition based on the hybrid correlation vector machine model according to claim 1, wherein in step S3, the MF-RVM model based on the QPSO is solved, wherein the updated equation in the QPSO algorithm is
And Xi,j(t+1)＝Pi,j±α|mbestj(t)-Xi,j(t)|·ln[1/ui,j(t)]
5. The method for evaluating the reliability of ammunition storage based on the mixed correlation vector machine model according to claim 1, wherein in step S4, in combination with Matlab software, program codes are written, wherein M is 20, D is 3, QQ is 100, aa is 1, bb is 0.5, c is 1001＝c2＝c3＝c4In addition, setting the initial kernel parameter value ranges to be respectively: lambda is more than 0 and less than 1, tau is more than 1 and less than 5, and g is more than 10 and less than 10, then the MF-RVM model can be trained.
6. The ammunition storage reliability evaluation method based on the mixed correlation vector machine model according to claim 1, characterized in that in step S5, the specific expression of a certain type of tear-gas bomb storage reliability MF-RVM model is as follows:
y(x)＝0.26[0.6(x·x1+1)3+0.4exp(-||x-x1||2/(2.6)2)]+0.19[0.6(x·x3+1)3+0.4exp(-||x-x3||2/(2.6)2)]+0.42[0.6(x·x7+1)3+0.4exp(-||x-x7||2/(2.6)2)]
most weight components of the final tear-gas shells storage reliability MF-RVM model are zero, and the sparse property of the model is reflected. At this time, the sample vector corresponding to the basis function of the non-zero weight is the sample x used by the final training model1,x3,x7This is called the "correlation vector".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910929227.7A CN111222736A (en) | 2019-09-29 | 2019-09-29 | Ammunition storage reliability evaluation method based on mixed correlation vector machine model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910929227.7A CN111222736A (en) | 2019-09-29 | 2019-09-29 | Ammunition storage reliability evaluation method based on mixed correlation vector machine model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111222736A true CN111222736A (en) | 2020-06-02 |
Family
ID=70830532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910929227.7A Pending CN111222736A (en) | 2019-09-29 | 2019-09-29 | Ammunition storage reliability evaluation method based on mixed correlation vector machine model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222736A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115563887A (en) * | 2022-12-02 | 2023-01-03 | 中国人民解放军海军工程大学 | Ammunition reliability evaluation method and system based on multi-source information fusion |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254252A (en) * | 2011-07-19 | 2011-11-23 | 娄文忠 | Method for monitoring and intelligent management of ammunition storage and transportation |
| CN105528657A (en) * | 2016-01-13 | 2016-04-27 | 武汉福天通科技有限公司 | Building earthquake damage prediction method based on Beidou and vector machine |
| CN106127330A (en) * | 2016-06-18 | 2016-11-16 | 上海大学 | Fluctuating wind speed Forecasting Methodology based on least square method supporting vector machine |
| CN106952183A (en) * | 2017-04-24 | 2017-07-14 | 武汉大学 | A kind of short-term load forecasting method based on particle group optimizing least square method supporting vector machine |
| EP3209966A1 (en) * | 2014-10-21 | 2017-08-30 | Moog Inc. | Ammunition storage system |
| CN107316099A (en) * | 2017-05-22 | 2017-11-03 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on particle group optimizing BP neural network |
| CN107357966A (en) * | 2017-06-21 | 2017-11-17 | 山东科技大学 | A kind of surrounding rock of actual mining roadway stability prediction and appraisal procedure |
| CN107437112A (en) * | 2017-04-19 | 2017-12-05 | 武汉理工大学 | A kind of mixing RVM model prediction methods based on the multiple dimensioned kernel function of improvement |
| CN108182500A (en) * | 2018-02-02 | 2018-06-19 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on accelerated life test |
-
2019
- 2019-09-29 CN CN201910929227.7A patent/CN111222736A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254252A (en) * | 2011-07-19 | 2011-11-23 | 娄文忠 | Method for monitoring and intelligent management of ammunition storage and transportation |
| EP3209966A1 (en) * | 2014-10-21 | 2017-08-30 | Moog Inc. | Ammunition storage system |
| CN105528657A (en) * | 2016-01-13 | 2016-04-27 | 武汉福天通科技有限公司 | Building earthquake damage prediction method based on Beidou and vector machine |
| CN106127330A (en) * | 2016-06-18 | 2016-11-16 | 上海大学 | Fluctuating wind speed Forecasting Methodology based on least square method supporting vector machine |
| CN107437112A (en) * | 2017-04-19 | 2017-12-05 | 武汉理工大学 | A kind of mixing RVM model prediction methods based on the multiple dimensioned kernel function of improvement |
| CN106952183A (en) * | 2017-04-24 | 2017-07-14 | 武汉大学 | A kind of short-term load forecasting method based on particle group optimizing least square method supporting vector machine |
| CN107316099A (en) * | 2017-05-22 | 2017-11-03 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on particle group optimizing BP neural network |
| CN107357966A (en) * | 2017-06-21 | 2017-11-17 | 山东科技大学 | A kind of surrounding rock of actual mining roadway stability prediction and appraisal procedure |
| CN108182500A (en) * | 2018-02-02 | 2018-06-19 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on accelerated life test |
Non-Patent Citations (3)
| Title |
|---|
| 宫华;舒小娟;郝永平;: "基于改进PSO优化BP神经网络的弹药储存可靠度预测", no. 04 * |
| 林静;韩玉启;朱慧明;王晔;: "基于MCMC稳态模拟方法的弹药贮存可靠性评估模型", no. 03 * |
| 陈佳欣;郭红霞;刘禄胜;: "基于威布尔分布的不同地区弹药贮存寿命评估――以***、爆震弹为例", no. 05 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115563887A (en) * | 2022-12-02 | 2023-01-03 | 中国人民解放军海军工程大学 | Ammunition reliability evaluation method and system based on multi-source information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021073541A1 (en) | Spectral similarity-based correction set and validation set selecting and modeling method | |
| CN113655385B (en) | Lithium battery SOC estimation method and device and computer readable storage medium | |
| CN110245443A (en) | A kind of polymorphic type output reliability of simulation model comprehensive estimation method based on mapping function | |
| CN112308381A (en) | Equipment contribution degree data analysis method, system, storage medium and computer equipment | |
| Wen et al. | Robust least squares support vector machine based on recursive outlier elimination | |
| CN108182500A (en) | Ammunition Storage Reliability Forecasting Methodology based on accelerated life test | |
| CN112214880B (en) | Multi-stage maintainability assessment method based on virtual-real fusion | |
| CN112180258A (en) | Method, device, medium, terminal and system for measuring average coulomb efficiency of battery | |
| CN114818828B (en) | Training method of radar interference perception model and radar interference signal identification method | |
| CN113886207A (en) | Method and device for predicting performance of storage system based on convolutional neural network | |
| CN109190901A (en) | The credible evaluation method of reliability assessment result based on multi objective measurement | |
| CN111222736A (en) | Ammunition storage reliability evaluation method based on mixed correlation vector machine model | |
| CN117472789B (en) | Software defect prediction model construction method and device based on ensemble learning | |
| CN113610266B (en) | Method and device for predicting failure of automobile part, computer equipment and storage medium | |
| CN115114843A (en) | Battery capacity prediction method, related device, equipment and storage medium | |
| CN111337833B (en) | Lithium battery capacity integrated prediction method based on dynamic time-varying weight | |
| Amini et al. | hhsmm: an R package for hidden hybrid Markov/semi-Markov models | |
| CN115935761B (en) | Reliability simulation method and device for equipment, computer equipment and storage medium | |
| CN114819107B (en) | Mixed data assimilation method based on deep learning | |
| GB2616501A (en) | Robot | |
| CN116186507A (en) | Feature subset selection method, device and storage medium | |
| CN114490412A (en) | Three-dimensional CAD software performance measurement method and device based on self-subtraction reverse cloud generator | |
| CN109858699B (en) | Water quality quantitative simulation method and device, electronic equipment and storage medium | |
| CN112365022A (en) | Engine bearing fault prediction method based on multiple stages | |
| CN107203677B (en) | Electronic system multi-degradation process research method |
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 |