CN106202002A - A kind of for detecting the method whether series of hydrological parameter makes a variation - Google Patents

A kind of for detecting the method whether series of hydrological parameter makes a variation Download PDF

Info

Publication number
CN106202002A
CN106202002A CN201610488582.1A CN201610488582A CN106202002A CN 106202002 A CN106202002 A CN 106202002A CN 201610488582 A CN201610488582 A CN 201610488582A CN 106202002 A CN106202002 A CN 106202002A
Authority
CN
China
Prior art keywords
series
parameter
variation
hydrological
detecting
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
Application number
CN201610488582.1A
Other languages
Chinese (zh)
Other versions
CN106202002B (en
Inventor
胡义明
梁忠民
李彬权
王军
杨靖
唐甜甜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hohai University HHU
Original Assignee
Hohai University HHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hohai University HHU filed Critical Hohai University HHU
Priority to CN201610488582.1A priority Critical patent/CN106202002B/en
Publication of CN106202002A publication Critical patent/CN106202002A/en
Application granted granted Critical
Publication of CN106202002B publication Critical patent/CN106202002B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Evolutionary Biology (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)

Abstract

The invention discloses a kind of for detecting the method whether series of hydrological parameter makes a variation, detecting series of hydrological parameter variation degree by the diversity of different times estimates of parameters distribution function being carried out the overlapping degree of significance test and tolerance different times estimates of parameters probability-distribution function.What the present invention provided is used for detecting the method whether series of hydrological parameter makes a variation, overcome the current jumping characteristic method of inspection and can only identify change point position, and in None-identified series of hydrological, which kind of parameter morphs, and this is not enough, can be used for detecting the problems the such as whether parameter such as the average of series of hydrological, coefficient of dispersion and the coefficient of skew morphs and parameter variation is the most notable, there is stronger engineering significance.

Description

A kind of for detecting the method whether series of hydrological parameter makes a variation
Technical field
The present invention relates to a kind of for detecting the method whether series of hydrological parameter makes a variation, be specifically related to a kind of by not The diversity of same time estimates of parameters distribution function carries out significance test and tolerance different times estimates of parameters probability The overlapping degree of distribution function detects the method for series of hydrological parameter variation degree.
Background technology
Hydrologic(al) frequency analysis is the standard method inquiring into the design flood meeting engineering design requirements.Application hydrological frequency is divided The precondition of analysis method is hydrology extreme value series coherence request to be met.But, due to climate change and mankind's activity Impact so that more and more prominent for the nonuniformity problem of the hydrology extreme value series of hydrologic(al) frequency analysis.To this end, carrying out water Before literary composition frequency analysis, it is necessary first to the variability of hydrology extreme value series is tested, consistent to judge whether series meets Property requirement.
At present numerous to the jumping characteristic method of inspection of hydrology extreme value series, as sequence cluster analysis, slip rank test method and Pettitt method etc..It would be appreciated that these methods are only capable of providing the position of change point, and in None-identified series of hydrological Which kind of parameter morphs, and i.e. cannot detect whether the parameters such as the average of series of hydrological, coefficient of dispersion and the coefficient of skew become The problems such as different and parameter variation is the most notable.
Summary of the invention
For solving the deficiencies in the prior art, it is an object of the invention to provide a kind of for whether detecting series of hydrological parameter The method of variation, by carrying out significance test and tolerance to the diversity of different times estimates of parameters probability density function The overlapping degree of different times estimates of parameters probability density function detects parameters in series degree of variation, overcomes at present conventional Jumping characteristic variability diagnostic method, can only identify change point position, and cannot judge whether the statistical parameter of series changes Deficiency.
In order to realize above-mentioned target, the present invention adopts the following technical scheme that:
A kind of it is characterized in that for detecting the method whether series of hydrological parameter makes a variation, comprise the steps:
(1) according to the jumping characteristic method of inspection of hydrology extreme value series, the change point position τ of series is identified；
(2) at change point position τ, whole series of hydrological is divided into former and later two subfamilies X1And X2；
(3) respectively from X1And X2Series is repeatedly put back to each 5000 groups of the sample drawn in ground；
(4) for parameter θ to be detected, according to X15000 groups of samples that series is corresponding, are calculated 5000 of parameter θ Estimated value；
(5) for parameter θ to be detected, according to X25000 groups of samples that series is corresponding, are calculated 5000 of parameter θ Estimated value；
(6) under level of significance α, series of X is checked15000 corresponding estimates of parameters and X2The 5000 of series correspondence Individual estimates of parameters, if obey identical distribution；
If obedience same distribution, then show that parameter θ does not morph before and after change point；
If the same distribution of disobeying, then showing under level of significance α, there is significant variation in parameter θ before and after change point；
(7) 5000 estimated values of parameter θ in step (4) and (5) being carried out probability density function matching respectively, it is right to obtain The probability density function f answered1(θ) and f2(θ)；
(8) calculating probability density function f1(θ) and f2(θ) lap area A (0≤A≤1), then two probability density letters The diversity of number is As parameter variation degree metric.
Further, described step (4) and (5) use Bootstrap resampling technique to obtain 5000 groups of samples, and then obtain Obtain 5000 estimated values of parameter θ,
Further, in described step (6), level of significance α is 0.05, uses the inspection of Kolmogorov-Smirnov method Test X1And X2Whether 5000 estimates of parameters of series correspondence are from same distribution function.
Further, in described step (7), use norm of nonparametric kernel density method that the probability density function of estimates of parameters is entered Row matching.
The beneficial effect that the present invention is reached: what the present invention provided is used for detecting the method whether series of hydrological parameter makes a variation Overcome the current jumping characteristic method of inspection and can only identify change point position, and in None-identified series of hydrological, which kind of parameter becomes This deficiency different, can be used for detecting whether the parameters such as the average of series of hydrological, coefficient of dispersion and the coefficient of skew morph and join The problems such as number variation is the most notable, have stronger engineering significance.
Detailed description of the invention
The invention will be further described below.Following example are only used for clearly illustrating the technical side of the present invention Case, and can not limit the scope of the invention with this.
Below in conjunction with example, the present invention is further described.
The existing a certain hydrological observation website flood peak extreme value series sample of 50 years, series presents jumping characteristic variation characteristic；Depend on According to the inventive method, whether this series of hydrological parameter makes a variation determines that process is:
(1) use sequence cluster analysis, slip rank test method, Pettitt method of inspection to hydrology extreme value series x1,x2,…, x50Change point position carry out comprehensive diagnos, final judge that this series occurs jumping characteristic to make a variation at the 28th sample point；
(2) by whole series of hydrological xi, i=1,2 ..., 50 are divided into former and later two subfamilies at the 28th sample, point It is not designated as X1={ x1,x2,…,x28And X2={ x29,x30,…,x50}；
(3) Bootstrap resampling technique is used, from X1Wait capacity sample drawn 5000 while series is repeatedly put back to Group, the capacity often organizing series of samples is 28；
(4) Bootstrap resampling technique is used, from X2Wait capacity sample drawn 5000 while series is repeatedly put back to Group, the capacity often organizing series of samples is 22；
(5) for average Ex to be detected, variance Sd and tri-parameters of coefficient of skew Cs, according to X1The 5000 of series correspondence Group sample, is respectively adopted linear Moment method estimators and obtains 5000 estimated values of Ex, Sd and Cs, be designated as Ex1 (i), Sd1 (i) and Cs1 (i), i=1,2 ..., 5000；
(6) for average Ex to be detected, variance Sd and tri-parameters of coefficient of skew Cs, according to X2The 5000 of series correspondence Group sample, is respectively adopted linear Moment method estimators and obtains 5000 estimated values of Ex, Sd and Cs, be designated as Ex2 (i), Sd2 (i) and Cs2 (i), i=1,2 ..., 5000；
(7) significance level 0.05 time, Kolmogorov-Smirnov method, inspection parameter Ex or Sd or Cs pair are used 5000 estimated values Ex1 (i) answered and Ex2 (i) or Sd1 (i) and Sd2 (i) or Cs1 (i) and Cs2 (i), i=1,2 ..., 5000, if obey identical distribution.
If obedience same distribution, then show that parameter Ex or Sd or Cs do not morph before and after change point；
If the same distribution of disobeying, then show that parameter Ex or Sd or Cs are before and after change point significance level 0.05 time There is significant variation.
(8) norm of nonparametric kernel density method is used, respectively to parameter Ex or the 5000 of Sd or Cs obtained in step (5) and (6) Individual estimated value carries out probability density function matching, obtains the probability density function f of correspondence1And f (Ex)2Or f (Ex)1And f (Sd)2 Or f (Sd)1And f (Cs)2(Cs)；
(9) for given parameter Ex, Sd and Cs, the probability density function f of its correspondence is calculated1() and f2() is overlapping Area A (0≤A≤1), then the diversity of two probability density functions is Can be as parameter variation degree Metric.
IfBefore and after change point is described, the degree of variation of average Ex is more than variance Sd with inclined The degree of variation of state coefficient Cs, and the degree of variation of variance Sd is more than the degree of variation of coefficient of skew Cs；Other is similar to.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For Yuan, on the premise of without departing from the technology of the present invention principle, it is also possible to make some improvement and deformation, these improve and deformation Also should be regarded as protection scope of the present invention.

Claims (4)

1., for detecting the method whether series of hydrological parameter makes a variation, it is characterized in that, comprise the steps:
(1) according to the jumping characteristic method of inspection of hydrology extreme value series, the change point position τ of series is identified；
(2) at change point position τ, whole series of hydrological is divided into former and later two subfamilies X1And X2；
(3) respectively from X1And X2Series is repeatedly put back to each 5000 groups of the sample drawn in ground；
(4) for parameter θ to be detected, according to X15000 groups of samples that series is corresponding, are calculated 5000 estimations of parameter θ Value；
(5) for parameter θ to be detected, according to X25000 groups of samples that series is corresponding, are calculated 5000 estimations of parameter θ Value；
(6) under level of significance α, series of X is checked15000 corresponding estimates of parameters and X25000 ginsengs that series is corresponding Number estimated value, if obey identical distribution；
If obedience same distribution, then show that parameter θ does not morph before and after change point；
If the same distribution of disobeying, then showing under level of significance α, there is significant variation in parameter θ before and after change point；
(7) 5000 estimated values of parameter θ in step (4) and (5) are carried out probability density function matching respectively, obtain correspondence Probability density function f1(θ) and f2(θ)；
(8) calculating probability density function f1(θ) and f2(θ) lap area A (0≤A≤1), then two probability density functions Diversity is As parameter variation degree metric.
The most according to claim 1 a kind of it is characterized in that for detecting the method whether series of hydrological parameter makes a variation, described Step (4) and (5) use Bootstrap resampling technique to obtain 5000 groups of samples, and then obtain 5000 estimations of parameter θ Value.
The most according to claim 1 a kind of it is characterized in that for detecting the method whether series of hydrological parameter makes a variation, institute Stating level of significance α in step (6) is 0.05, uses Kolmogorov-Smirnov method inspection X1And X2Series correspondence Whether 5000 estimates of parameters are from same distribution function.
The most according to claim 1 a kind of it is characterized in that for detecting the method whether series of hydrological parameter makes a variation, described In step (7), use norm of nonparametric kernel density method that the probability density function of estimates of parameters is fitted.
CN201610488582.1A 2016-06-28 2016-06-28 A method of for detecting whether series of hydrological parameter makes a variation Active CN106202002B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610488582.1A CN106202002B (en) 2016-06-28 2016-06-28 A method of for detecting whether series of hydrological parameter makes a variation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610488582.1A CN106202002B (en) 2016-06-28 2016-06-28 A method of for detecting whether series of hydrological parameter makes a variation

Publications (2)

Publication Number Publication Date
CN106202002A true CN106202002A (en) 2016-12-07
CN106202002B CN106202002B (en) 2018-08-28

Family

ID=57461035

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610488582.1A Active CN106202002B (en) 2016-06-28 2016-06-28 A method of for detecting whether series of hydrological parameter makes a variation

Country Status (1)

Country Link
CN (1) CN106202002B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106600508A (en) * 2016-12-19 2017-04-26 中国水利水电科学研究院 Watershed-scale hydrological nonconformity diagnosis method
CN106777985A (en) * 2016-12-19 2017-05-31 中国水利水电科学研究院 A kind of Hydrologic Series nonuniformity diagnostic method based on classification
CN108304353A (en) * 2018-01-10 2018-07-20 武汉大学 Hydrologic Series dependence degree of variation analysis method
CN110260774A (en) * 2019-07-22 2019-09-20 安徽理工大学 A kind of inspection of GNSS deformation information and method for early warning based on Pettitt algorithm
CN111784193A (en) * 2020-07-17 2020-10-16 中国人民解放军国防科技大学 Product performance consistency inspection method based on normal distribution

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4720799A (en) * 1985-06-19 1988-01-19 Woithe Stanley D Hydrologic data acquisition system
CN102880755A (en) * 2012-09-25 2013-01-16 河海大学 Method and system for quantitatively forecasting extreme rainfall
CN103745094A (en) * 2013-12-25 2014-04-23 河海大学 Interactive simulation-prediction method and interactive simulation-prediction system for hydrologic series of tidal reaches
CN104281776A (en) * 2014-09-23 2015-01-14 水利部交通运输部国家能源局南京水利科学研究院 Method for judging remarkable influence period of human activities on river flow

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4720799A (en) * 1985-06-19 1988-01-19 Woithe Stanley D Hydrologic data acquisition system
CN102880755A (en) * 2012-09-25 2013-01-16 河海大学 Method and system for quantitatively forecasting extreme rainfall
CN103745094A (en) * 2013-12-25 2014-04-23 河海大学 Interactive simulation-prediction method and interactive simulation-prediction system for hydrologic series of tidal reaches
CN104281776A (en) * 2014-09-23 2015-01-14 水利部交通运输部国家能源局南京水利科学研究院 Method for judging remarkable influence period of human activities on river flow

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
李新 等；: "《洪水序列变异条件下的频率分析与计算》", 《水力发电学报》 *
梁忠民 等；: "《非一致性条件下水文设计值估计方法探讨》", 《南水北调与水利科技》 *
胡义明 等: "《基于跳跃性诊断的非一致性水文频率分析》", 《人民黄河》 *
胡义明 等；: "《考虑抽样不确定性的水文设计值估计》", 《水科学进展》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106600508A (en) * 2016-12-19 2017-04-26 中国水利水电科学研究院 Watershed-scale hydrological nonconformity diagnosis method
CN106777985A (en) * 2016-12-19 2017-05-31 中国水利水电科学研究院 A kind of Hydrologic Series nonuniformity diagnostic method based on classification
CN106777985B (en) * 2016-12-19 2018-07-06 中国水利水电科学研究院 A kind of Hydrologic Series nonuniformity diagnostic method based on classification
CN108304353A (en) * 2018-01-10 2018-07-20 武汉大学 Hydrologic Series dependence degree of variation analysis method
CN110260774A (en) * 2019-07-22 2019-09-20 安徽理工大学 A kind of inspection of GNSS deformation information and method for early warning based on Pettitt algorithm
CN110260774B (en) * 2019-07-22 2022-03-08 安徽理工大学 GNSS deformation information inspection and early warning method based on Pettitt algorithm
CN111784193A (en) * 2020-07-17 2020-10-16 中国人民解放军国防科技大学 Product performance consistency inspection method based on normal distribution
CN111784193B (en) * 2020-07-17 2024-03-26 中国人民解放军国防科技大学 Product performance consistency inspection method based on normal distribution

Also Published As

Publication number Publication date
CN106202002B (en) 2018-08-28

Similar Documents

Publication Publication Date Title
CN106202002A (en) A kind of for detecting the method whether series of hydrological parameter makes a variation
CN110807781B (en) Point cloud simplifying method for retaining details and boundary characteristics
CN104766175A (en) Power system abnormal data identifying and correcting method based on time series analysis
CN101526994B (en) Fingerprint image segmentation method irrelevant to collecting device
CN106373124B (en) Industrial products surface defect visible detection method based on gray level co-occurrence matrixes and RANSAC
CN105509653A (en) Method and system for visual measurement of profile of machine part
CN106340010B (en) A kind of angular-point detection method based on second order profile difference
CN106643965B (en) Method for accurately identifying liquid level by utilizing template matching
CN105184786B (en) A kind of floating type triangle character describes method
CN103903238A (en) Method for fusing significant structure and relevant structure of characteristics of image
CN106991705A (en) A kind of location parameter method of estimation based on P3P algorithms
CN105574265B (en) Entire assembly model quantitative description towards model index
CN110110687A (en) Fruit automatic identifying method on tree based on colouring information and three-D profile information
CN109359537A (en) Human face posture angle detecting method neural network based and system
CN102800113A (en) Digital image analysis method based on fractal dimension
CN106909881A (en) The method and system of corn breeding base ridge number are extracted based on unmanned aerial vehicle remote sensing images
CN105488798B (en) SAR image method for measuring similarity based on point set contrast
CN107016700A (en) A kind of Circle Detection method based on digital picture
CN103413306B (en) A kind of Harris angular-point detection method of adaptive threshold
CN103530885B (en) A kind of one dimensional image adaptive layered rim detection extracting method
CN103471514A (en) Garlic classifying method based on machine vision and unitary linear recursive analysis
CN104408735B (en) A kind of rectangular area recognition methods calculated based on improvement shape angle
CN105488477A (en) Apparent density peak detection algorithm based on double-check
CN103425979B (en) Hand authentication method
CN104809336A (en) Method for sampling region factor by considering spatial correlation

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant