CN108062448A - Predict modeling and analysis method, the equipment and storage medium of slope stability - Google Patents
Predict modeling and analysis method, the equipment and storage medium of slope stability Download PDFInfo
- Publication number
- CN108062448A CN108062448A CN201711423677.6A CN201711423677A CN108062448A CN 108062448 A CN108062448 A CN 108062448A CN 201711423677 A CN201711423677 A CN 201711423677A CN 108062448 A CN108062448 A CN 108062448A
- Authority
- CN
- China
- Prior art keywords
- slope
- data
- stability
- data set
- naive bayes
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of modeling and analysis method for predicting slope stability, equipment and storage mediums.Modeling method comprises the following steps：Slope stability history data set is established, the history data set is selected from history case, and multiple features including describing the data, and the history data set includes losing data；Discretization is carried out to the continuous factor in characteristic factor；The maximum likelihood estimator of the loss data is determined using EM algorithm, to form new complete slope stability data set；Using the stability state of side slope reality as criteria for classification, the data of the slope stability data set are trained using Naive Bayes Classifier, it determines conditional probability of each characteristic factor respectively under the various stability states of side slope, obtains Naive Bayes Classification Model.
Description
Technical field
The disclosure relates generally to Analysis of Slope Stability technical field more particularly to a kind of modeling for predicting slope stability
And analysis method, equipment and storage medium.
Background technology
Landslide is one of Serious geological disasters that possible cause serious life and property loss, becomes great concern.It comments
The stability for estimating and predicting side slope is the overriding concern factor for identifying potential Landslide Section and being damaged caused by mitigating landslide.It is accurate
Really the stability of prediction side slope is a challenging task, because it depends on various ground and physical factor.In addition,
Interaction between these factors is complicated, and " being generally difficult to be described with mathematics ".
In the prior art, it has been proposed that many methods are come the stability analyzing or predict side slope, wherein limit equilibrium method
It is most common method with numerical method (such as FInite Element (FEM)).Some other method includes empirical equation and is based on down
The restriction analysis method of limit and upper bound theorem.Above-mentioned all methods have certain limitation.For example, Lenchman and
Griffiths proposes that limiting equilibrium method cannot reflect the actual stress state of sliding surface, and due to simplify it is assumed that they
Precision is affected.Numerical method usually takes very much, and its accuracy is heavily dependent on to ground and physics
The accurate estimation of parameter.
In addition, artificial neural network and support vector machines etc. manually intelligent Forecasting also in terms of slope stability is calculated
Certain application is obtained.However, since these methods require gathered data must be complete, but in Practical Project,
Be difficult often to obtain complete slope data especially in the primary stage of slope design, for example, pore pressure ratio (ru) acquisition just
It is extremely difficult.And for such case of complete slope data can not be obtained, then it can not use artificial neural network and support
The Forecasting Methodology of vector machine, this also results in such computational methods and cannot obtain widely should in terms of slope stability is predicted
With.
The content of the invention
In view of drawbacks described above of the prior art or deficiency, are intended to provide a kind of modeling and analysis for predicting slope stability
Scheme.
In a first aspect, the embodiment of the present application provides a kind of modeling method for predicting slope stability, comprise the following steps：
Slope stability history data set is established, the history data set is selected from history case, and including describing the number
According to multiple features, the history data set include lose data；
Discretization is carried out to the continuous factor in characteristic factor；
The maximum likelihood estimator of the loss data is determined using EM algorithm, to form new complete side slope
Stability data collection；
Using the stability state of side slope reality as criteria for classification, using Naive Bayes Classifier to the slope stability
At least part data of data set are trained, and determine condition of each characteristic factor respectively under the various stability states of side slope
Probability obtains Naive Bayes Classification Model.
The object of the invention to solve the technical problems also can be used following technical measures and further realize.
The characteristic factor includes：Slope height, slope angle (α), cohesive force (c), rubbing angle (φ), Unit Weight (γ)
With pore pressure ratio (ru), wherein pore pressure ratio abbreviation pore pressure ratio (ru), be defined as pore pressure and burden pressure it
Than.Using above-mentioned factor as characteristic factor, it can reflect the principal element for influencing stability of slope comprehensively；In addition, pass through correlation
Analysis is found, each independent between above-mentioned each factor, is met the conditional independence assumption of Naive Bayes Classifier, is very suitable for adopting
Use the method.
The continuous factor in characteristic factor, which carries out discretization, to be included using wide merging algorithm and/or frequency is waited to merge
Algorithm.Former algorithm is used to gamut being divided into multiple sections with identical " width ", and the latter is for will be whole
A scope is divided into several sections, and each section includes the history case of approximately same number.
It is described to include, using expectation maximization EM algorithms, compared to common gradient declining using EM algorithm
(Gradient Descent) algorithm, EM algorithms not only have faster arithmetic speed, but also can effectively handle history case
Deficiency of data in example..
Trained partial data, which is had neither part nor lot in, using slope stability historical data concentration assesses the naive Bayesian
The performance of grader can further improve the accuracy of model.
According to the result of assessment performance to each characteristic factor conditional probability under the various stability states of side slope respectively
It is adjusted.
Second aspect, the embodiment of the present application provide a kind of analysis method for predicting slope stability, including：Download is treated pre-
Slope data collection is surveyed, the slope data collection to be predicted includes describing at least part feature of the data；Using as described above
Modeling method formed Naive Bayes Classification Model to the slope data to be predicted according to side slope stable state carry out
Classification.
A kind of analysis method for predicting slope stability, including：Download slope data collection to be predicted, the side slope to be predicted
Data set includes describing at least part feature of the data；Utilize the simplicity formed by naive Bayesian training modeling method
Bayesian Classification Model classifies to the slope data to be predicted according to the stable state of side slope.
The third aspect, the embodiment of the present application provide a kind of equipment, and the equipment includes：
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are performed by one or more of processors so that one or more of places
Reason device realizes modeling and/or the analysis of above-mentioned prediction slope stability method when performing.
A kind of computer readable storage medium for being stored with computer program, the program are realized above-mentioned when being executed by processor
The method for predicting modeling and/or the analysis of slope stability.
The scheme of prediction slope stability provided by the embodiments of the present application, using Naive Bayes Classifier NBC for place
It is particularly useful or even good prediction result can be also generated in the case of data volume very little to manage incomplete data so that it
Be very suitable for being analyzed with limited (or incomplete) geotechnical data, can be obtained in terms of slope stability is predicted wide
General application.In addition, can effectively be trained using Naive Bayes Classifier NBC, and can be used for obtaining non-
Often good forecasting accuracy.
Description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1：69 naive Bayesian training slope cases in the embodiment of the present application one；
Fig. 2 shows a kind of slope stability detection structure signal of Naive Bayes Classifier in the embodiment of the present application
Figure；
Fig. 3 shows the conditional probability after Naive Bayes Classifier and parameter learning using expectation maximization EM algorithms
Table (CPT).
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, illustrated only in attached drawing with inventing relevant part.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Embodiment one
As described in background technology, the prediction model for being currently based on artificial neural network or support vector machine method exploitation has
When can generate and more accurately predicted than traditional Method for Slope Stability Analysis, but when data are imperfect, especially exist
The starting stage of Slope Design, in database some pore pressure ratio (ru) values lack case, employment artificial neural networks or
Support vector machine method prediction gradient stability is infeasible.In order to overcome this problem, we have proposed naive Bayesians
Grader (NBC) predicts the stability of side slope.
The embodiment of the present application provides a kind of scheme that can effectively predict slope stability, specifically includes prediction stability of slope
Property modeling method, predict slope stability analysis method and to predict the equipment of slope stability and storage medium.
Slope stability modeling method, specifically includes procedure below：
1) database processing and correlation analysis
1.1) choosing influences six indexs of stability of slope sexual factor, including：Ramp height (H), slope angle (α), cohesive force
(c), rubbing angle (φ), Unit Weight (γ) and hydraulics (i.e. pore pressure ratio r u, abbreviation pore pressure ratio (ru), definition
For the ratio between pore pressure and burden pressure).
1.2) case study of Slope Stability is summarized, and has worked out a number for including 69 slope cases
According to storehouse.Pore pressure ratio (ru) value of 10 slope cases is missing values wherein, i.e. input data is " incomplete ".
1.3) actual conditions of the slope stability of statistics；See Fig. 1 in Figure of description, be contained in data
In storehouse.
2) incomplete slope data collection is established, using 69 groups of fragmentary data collection comprising six parameters as database.
3) parameter optimization, including procedure below：
3.1) discretization of the continuous factor, 6 continuous variable parameters being chosen in the range of real number.Handle continuous variable
Two methods include the discretization of continuous data or specified density function.If data are limited, an accurate density letter is specified
Number is extremely difficult, therefore the present invention handles this six parameters using discretization method.It is wide to merge algorithm and frequency is waited to close
And algorithm is for determining the two of state cut-point kinds of common discretization algorithms.Former algorithm is used to divide gamut
For multiple sections with identical " width ", and the latter is used to gamut being divided into several sections, and each section includes
The frequency such as the history case of approximately same number, the embodiment of the present application use merges algorithm, because experiments have shown that it can be generated more
High precision of prediction.
Table 2 lists the Interval Set of each state of parameter and corresponding definition.
The general introduction of the interval of table 2. and corresponding Status Name
3.2) data of loss are estimated using expectation maximization (EM) algorithm, in 69 cases, wherein 10 do not have pore pressure
Than ru values.Assuming that data are random loss, i.e., loss data are unrelated with observation data, then expectation-maximization algorithm (EM algorithms)
It can be used for estimating the conditional probability in Naive Bayes Classifier NBC.EM algorithms can be divided into two steps：Desired step (E
Step) and maximization steps (M steps).EM iteration is being performed between E steps and M steps alternately, wherein by being based on joining
Several currently estimates to calculate the expectation to missing values to complete Supplementing Data, wherein, based on " the completion in previous E steps
" data determine the new maximal possibility estimation of parameter.These estimates can be used in next E steps.
For Naive Bayes Classifier (Naive Bayes classifier/NBC) parameter learning, naive Bayesian point
Class device NBC is to a small amount of training data (the above-mentioned incomplete data sets for including six parameters), for estimating necessary sorting parameter.
Choose X=(x1, x2 ..., xn) (present invention in n=6) represent to influence slope stability six independent factors (i.e. γ, c,
φ, α, H and ru) and (C1, C2 ..., Ck) (k=2 in the present embodiment) input vector represent stability of slope two results
(stable or unstability).When working as x1, x2 ..., xn discrete, using Bayes' theorem, the conditional probability of k-th of possible outcome can be with
It represents as follows：
4) using Bayes classifier, incomplete slope data collection is trained：
Data set in case is trained according to NB Algorithm.In the conditional probability table of wherein each node
Parameter is that the slope case based on deficiency of data is obtained with expectation maximization EM algorithms.Fig. 3 shows simple pattra leaves
This grader NBC and obtained conditional probability table (CPTs).Based on obtained Naive Bayes Classifier and conditional probability parameter
(Fig. 3) can carry out probability inference.Specifically include following steps：
It is assumed that certain slope parameter is as follows, that is, inputting the factor is：X=(γ=25kN/m3 (in), c=46kPa (height), φ
=35 ° (big), α=50 ° (big), H=284m (height), ru=missing).It is consequently possible to calculate the probability P of slope stability is (steady
It is fixed | X).
Even if input data to be predicted is " incomplete ", Naive Bayes Classifier NBC still can estimate side slope
The probability P (stablize | X) of stability.In other words, Naive Bayes Classifier can use any one son of six input factors
Collect the stability for predicting side slope, this causes it than other soft computing techniques (such as artificial neural network or support vector machine method)
More flexibly.Naive Bayes Classifier is tested using all 69 slope data collection in database, and table 3 lists mixed
Confuse matrix.
Table 3. uses the confusion matrix of identical training sample
TP (True Positive) and TN (True Negative) represents the correct stabilization for being categorized as respective classes respectively
With the side slope quantity of unstability.FP (False Positive) expressions are categorized as the quantity on the other unstability change slope of Stabilized by mistake,
FN (False Negative) represents to be categorized as the quantity of the stabling slope of unstability classification by mistake.41 stable side slopes (are known as
Sensitivity TP/ (TP+FN)) precision be 97.6%.The precision of 28 unstability side slopes (being known as specificity, i.e. TN/ (TN+FP))
For 96.4%.Overall accuracy (i.e. (TP+TN)/(TP+TN+FP+FN)) is about 97.1%.
By being trained to grader, the modeling of prediction slope stability is completed.
Predict the analysis method of slope stability, including：Download slope data collection to be predicted, the slope data to be predicted
Collection includes describing at least part feature of the data；Utilize the simple pattra leaves formed by naive Bayesian training modeling method
This disaggregated model classifies to the slope data to be predicted according to the stable state of side slope.
With above-mentioned trained grader, stability of slope classification prediction is carried out to having neither part nor lot in trained stability of slope data,
Obtain classification results.
The verification of new case in order to verify proposed Naive Bayes Classifier, is not wrapped using what is obtained from document
13 new cases concentrated in training data are included to be tested (referring to table 5).Wherein eight group acknowledges are stable side slope, remaining five
Group is the slope of unstability.Table 5 lists the knot that the empirical equation proposed using Bayes classifier and Sah proposed et al. is predicted
Fruit.Only 2 (No. 3 and No. 11) are classified by mistake, show that performances of the NBC in new case can receive.The FoS of No. 11 cases
For 0.99,1 is approximately equal to, the P (stabilization)=50.3% of prediction, very close 1/2 threshold value.The experience that Sah et al. is proposed is public
Formula mistakenly predicts 3 (numbers 3,11 and 12).However, it may not apply to the incomplete situation of input data (No. 13 cases
Example).Therefore, it is being listed in table 4 the result shows that, the Naive Bayes Classifier proposed is than empirical equation that Sah et al. is proposed
It is performed better than in terms of forecasting accuracy, and can be applied to wider side slope situation, especially those are with incomplete
The side slope of data.
The verification result of 4. 13 new cases of table
Note：aEmpirical equation is by Sah et al. propositions, using the circular destruction in maximum Likelihood direct estimation slope
Safety coefficient, its safety coefficient are represented by：+ 1.54 (1-ru) tan (φ) of FoS=2.27c/ [γ Hsin (α)]/tan
(α)。bNA represents unavailable.
Likewise, above-mentioned trained Naive Bayes Classifier can be used, it is steady to carrying out side slope in the slope data built
Qualitatively classification prediction, it is contemplated that good prediction result is generated for processing stability of slope performance using this method.
Particularly, in accordance with an embodiment of the present disclosure, procedures described above may be implemented as computer software programs.Example
Such as, embodiment of the disclosure includes a kind of computer program product, including the meter being tangibly embodied on machine readable media
Calculation machine program, the computer program include the journey of the modeling method and/or analysis method for perform prediction slope stability
Sequence code.In such embodiments, the computer program can be downloaded and installed by communications portion from network and/
Or it is mounted from detachable media.Specific the embodiment of the present application provides a kind of predicting the equipment of slope stability, equipment
Including：One or more processors；Memory, for storing one or more programs；When one or more of programs are by institute
When stating one or more processors execution so that one or more of processors realize above-mentioned prediction slope stability when performing
Modeling method and/or analysis method.It is appreciated that equipment includes but not limited to PC, smart mobile phone, tablet computer
Deng.
As on the other hand, present invention also provides a kind of computer readable storage medium, the computer-readable storage mediums
Matter can be computer readable storage medium included in device described in above-described embodiment；Can also be individualism, not
The computer readable storage medium being fitted into equipment.There are one computer-readable recording medium storages or more than one journey
Sequence, described program are used for performing the above-mentioned prediction slope stability for being described in the application by one or more than one processor
Modeling method or analysis method.
The Naive Bayes Classifier model of the invention compared with existing empirical method, proposed is in accuracy and is applicable in
Property aspect generate better performance, take shorter, precision higher.
It is particularly useful or even can also generate in the case of data volume very little good pre- for handling incomplete data
Survey result so that they are very suitable for being analyzed with limited (or incomplete) geotechnical data.
In addition, compared with other technologies, Naive Bayes Classifier can be effectively trained, and can be obtained
Obtain extraordinary forecasting accuracy.
The preferred embodiment and the explanation to institute's application technology principle that above description is only the application.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from the inventive concept, it is carried out by above-mentioned technical characteristic or its equivalent feature
The other technical solutions for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical solution that the technical characteristic of energy is replaced mutually and formed.
Claims (10)
1. a kind of modeling method for predicting slope stability, which is characterized in that comprise the following steps：
Slope stability history data set is established, the history data set is selected from history case, and including describing the data
Multiple features, the history data set include losing data；
Discretization is carried out to the continuous factor in characteristic factor；
The maximum likelihood estimator of the loss data is determined using EM algorithm, to form new complete stability of slope
Property data set；
Using the stability state of side slope reality as criteria for classification, using Naive Bayes Classifier to the slope stability data
At least part data of collection are trained, and determine that condition of each characteristic factor respectively under the various stability states of side slope is general
Rate obtains Naive Bayes Classification Model.
A kind of 2. modeling method for predicting slope stability according to claim 1, which is characterized in that the characteristic factor
Including：Slope height H, slope angle α, cohesive force c, rubbing angle φ, Unit Weight γ and pore pressure ratio r u.
3. it is according to claim 1 it is a kind of predict slope stability modeling method, which is characterized in that it is described to feature because
The continuous factor in element, which carries out discretization, to be included using wide merging algorithm and/or frequency is waited to merge algorithm.
4. a kind of modeling method for predicting slope stability according to claim 1, which is characterized in that described using maximum
Expectation Algorithm is included using expectation maximization EM algorithms.
5. according to a kind of modeling method of any prediction slope stabilities of claim 1-4, which is characterized in that utilize institute
It states slope stability historical data concentration and has neither part nor lot in the performance that trained partial data assesses the Naive Bayes Classifier.
6. a kind of modeling method for predicting slope stability according to claim 5, which is characterized in that according to assessment performance
Result conditional probability of each characteristic factor respectively under the various stability states of side slope is adjusted.
7. a kind of analysis method for predicting slope stability, which is characterized in that including：Slope data collection to be predicted is downloaded, it is described
Slope data collection to be predicted includes describing at least part feature of the data；Utilize building as described in claim 1-6 is any
The Naive Bayes Classification Model that mould method is formed classifies to the slope data to be predicted according to the stable state of side slope.
8. a kind of analysis method for predicting slope stability, which is characterized in that including：Slope data collection to be predicted is downloaded, it is described
Slope data collection to be predicted includes describing at least part feature of the data；Modeling method is trained using by naive Bayesian
The Naive Bayes Classification Model of formation classifies to the slope data to be predicted according to the stable state of side slope.
9. a kind of equipment, which is characterized in that the equipment includes：
One or more processors；
Memory, for storing one or more programs；
When one or more of programs are performed by one or more of processors so that one or more of processors
The method as any one of claim 1-6 or claim 7 or 8 is realized during execution.
10. a kind of computer readable storage medium for being stored with computer program, which is characterized in that the program is executed by processor
Methods of the Shi Shixian as any one of claim 1-6 or claim 7 or 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711423677.6A CN108062448A (en) | 2017-12-25 | 2017-12-25 | Predict modeling and analysis method, the equipment and storage medium of slope stability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711423677.6A CN108062448A (en) | 2017-12-25 | 2017-12-25 | Predict modeling and analysis method, the equipment and storage medium of slope stability |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108062448A true CN108062448A (en) | 2018-05-22 |
Family
ID=62140130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711423677.6A Pending CN108062448A (en) | 2017-12-25 | 2017-12-25 | Predict modeling and analysis method, the equipment and storage medium of slope stability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108062448A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110406A (en) * | 2019-04-24 | 2019-08-09 | 河海大学 | A kind of Predicting Slope Stability method for realizing LS-SVM model based on Excel computing platform |
| CN112085044A (en) * | 2019-06-14 | 2020-12-15 | 中南大学 | Slope dynamic classification method based on automatic monitoring data |
| CN112668244A (en) * | 2021-01-06 | 2021-04-16 | 西南交通大学 | Slope earthquake stability prediction method, device and equipment and readable storage medium |
| CN113033108A (en) * | 2021-04-19 | 2021-06-25 | 昆明理工大学 | Side slope reliability judgment method based on AdaBoost algorithm |
| CN115063949A (en) * | 2022-06-25 | 2022-09-16 | 深圳市自然资源和不动产评估发展研究中心(深圳市地质环境监测中心) | Rainfall data-based karst collapse monitoring and early warning method and system and storage medium |
| US20230214557A1 (en) * | 2021-12-30 | 2023-07-06 | Institute Of Mechanics, Chinese Academy Of Sciences | Method for dynamically assessing slope safety |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2084535A2 (en) * | 2006-09-08 | 2009-08-05 | Richard Porwancher | Bioinformatic approach to disease diagnosis |
| CN104134010A (en) * | 2014-08-12 | 2014-11-05 | 哈尔滨工业大学 | Satellite fault diagnosis method for discrete type data based on Naive Bayes |
-
2017
- 2017-12-25 CN CN201711423677.6A patent/CN108062448A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2084535A2 (en) * | 2006-09-08 | 2009-08-05 | Richard Porwancher | Bioinformatic approach to disease diagnosis |
| CN104134010A (en) * | 2014-08-12 | 2014-11-05 | 哈尔滨工业大学 | Satellite fault diagnosis method for discrete type data based on Naive Bayes |
Non-Patent Citations (2)
| Title |
|---|
| 史秀志 等: "边坡稳定性预测的Bayes判别分析方法及应用", 《四川大学学报(工程科学版)》 * |
| 张文 等: "基于朴素贝叶斯和EM算法的软件工作量缺失数据处理方法", 《系统工程理论与实践》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110406A (en) * | 2019-04-24 | 2019-08-09 | 河海大学 | A kind of Predicting Slope Stability method for realizing LS-SVM model based on Excel computing platform |
| CN110110406B (en) * | 2019-04-24 | 2021-11-23 | 河海大学 | Slope stability prediction method for achieving LS-SVM model based on Excel computing platform |
| CN112085044A (en) * | 2019-06-14 | 2020-12-15 | 中南大学 | Slope dynamic classification method based on automatic monitoring data |
| CN112085044B (en) * | 2019-06-14 | 2023-11-24 | 中南大学 | Automatic monitoring data-based dynamic classification method for side slopes |
| CN112668244A (en) * | 2021-01-06 | 2021-04-16 | 西南交通大学 | Slope earthquake stability prediction method, device and equipment and readable storage medium |
| CN112668244B (en) * | 2021-01-06 | 2022-04-22 | 西南交通大学 | Slope earthquake stability prediction method, device and equipment and readable storage medium |
| CN113033108A (en) * | 2021-04-19 | 2021-06-25 | 昆明理工大学 | Side slope reliability judgment method based on AdaBoost algorithm |
| CN113033108B (en) * | 2021-04-19 | 2022-05-27 | 昆明理工大学 | Side slope reliability judging method based on AdaBoost algorithm |
| US20230214557A1 (en) * | 2021-12-30 | 2023-07-06 | Institute Of Mechanics, Chinese Academy Of Sciences | Method for dynamically assessing slope safety |
| CN115063949A (en) * | 2022-06-25 | 2022-09-16 | 深圳市自然资源和不动产评估发展研究中心(深圳市地质环境监测中心) | Rainfall data-based karst collapse monitoring and early warning method and system and storage medium |
| CN115063949B (en) * | 2022-06-25 | 2024-03-22 | 深圳市自然资源和不动产评估发展研究中心(深圳市地质环境监测中心) | Karst collapse monitoring and early warning method, system and storage medium based on rainfall data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062448A (en) | Predict modeling and analysis method, the equipment and storage medium of slope stability | |
| CN110659744B (en) | Training event prediction model, and method and device for evaluating operation event | |
| Emmerich | Single-and multi-objective evolutionary design optimization assisted by gaussian random field metamodels | |
| US20190251458A1 (en) | System and method for particle swarm optimization and quantile regression based rule mining for regression techniques | |
| Tashkova et al. | Parameter estimation with bio-inspired meta-heuristic optimization: modeling the dynamics of endocytosis | |
| Dobbie et al. | Sparse sampling: spatial design for monitoring stream networks | |
| Zhang et al. | Comparing the prediction of joint species distribution models with respect to characteristics of sampling data | |
| Polyzou et al. | Grade prediction with course and student specific models | |
| Evans | Uncertainty and error | |
| Lee et al. | Bayesian threshold selection for extremal models using measures of surprise | |
| Annis et al. | Bayesian statistical approaches to evaluating cognitive models | |
| Scheftelowitsch et al. | Multi-objective approaches to Markov decision processes with uncertain transition parameters | |
| CN112966770B (en) | Fault prediction method and device based on integrated hybrid model and related equipment | |
| CN112801231B (en) | Decision model training method and device for business object classification | |
| e Silva et al. | DeepData: Machine learning in the marine ecosystems | |
| Lo | Predicting software reliability with support vector machines | |
| Jin et al. | Introduction to optimization | |
| Spezia | Bayesian analysis of multivariate Gaussian hidden Markov models with an unknown number of regimes | |
| JP7014069B2 (en) | Data analyzers, methods, and programs | |
| CN115203970A (en) | Diagenetic parameter prediction model training method and prediction method based on artificial intelligence algorithm | |
| CN114780407A (en) | Test data generation method, test data generation device, server, storage medium, and program product | |
| KR20220057405A (en) | Method for quantifying algal for management of water quality | |
| Genc et al. | A Bayesian network-based data analytical approach to predict velocity distribution in small streams | |
| Beham et al. | Fitness landscape based parameter estimation for robust taboo search | |
| Merkuryeva et al. | Simulation-based fitness landscape analysis and optimisation of complex problems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |