CN117764454A - Evaluation method for development degree of flaky stripping of wall site in open great wall of Hexi corridor - Google Patents
Evaluation method for development degree of flaky stripping of wall site in open great wall of Hexi corridor Download PDFInfo
- Publication number
- CN117764454A CN117764454A CN202311820589.5A CN202311820589A CN117764454A CN 117764454 A CN117764454 A CN 117764454A CN 202311820589 A CN202311820589 A CN 202311820589A CN 117764454 A CN117764454 A CN 117764454A
- Authority
- CN
- China
- Prior art keywords
- evaluation index
- evaluation
- value
- weight
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 249
- 238000011161 development Methods 0.000 title claims abstract description 54
- 239000011159 matrix material Substances 0.000 claims abstract description 93
- 238000000034 method Methods 0.000 claims abstract description 91
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 34
- 201000010099 disease Diseases 0.000 claims abstract description 33
- 239000002689 soil Substances 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 206010040844 Skin exfoliation Diseases 0.000 claims description 18
- 230000000877 morphologic effect Effects 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 10
- 239000000843 powder Substances 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 230000008020 evaporation Effects 0.000 claims description 6
- 238000001704 evaporation Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 6
- 238000001556 precipitation Methods 0.000 claims description 6
- 150000003839 salts Chemical class 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000010831 paired-sample T-test Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 2
- 238000004299 exfoliation Methods 0.000 claims 6
- 239000010410 layer Substances 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000001364 causal effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012353 t test Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for evaluating the degree of flaky stripping development of a great wall site in a Hexi corridor, which comprises the following steps: selecting an evaluation index related to the soil site flaky stripping disease in the arid region; the subjective weight of the evaluation index is calculated through a decision laboratory analysis method, the first objective weight of the evaluation index is determined through a unique weight coefficient method, the second objective weight of the evaluation index is determined through an inverse entropy weight method, and the subjective weight and each objective weight are averaged to obtain a combined weight; the normalized matrix of each evaluation index value of each arid region is subjected to weight adjustment through the combined weight to obtain a comprehensive weighting matrix; classifying and evaluating each arid region according to the comprehensive weighting matrix by a rank sum ratio comprehensive evaluation method; predicting the soil site flaky stripping disease of the arid region by a ridge regression model, and comparing with an evaluation result. According to the invention, the comprehensive weight is calculated through various weighting methods, so that the accuracy of classifying and evaluating the development degree of the flaking stripping in each region by a rank sum ratio comprehensive evaluation method is improved.
Description
Technical Field
The invention relates to the technical field of development degree of soil-site diseases, in particular to a method for evaluating development degree of leaf stripping of a soil site in a great wall of a Hexi corridor, which is used for comprehensively evaluating and scientifically predicting the leaf stripping of a rammed soil site based on the shape characteristics of leaf stripping of the rammed soil site, intrinsic factors of soil and natural environment factors, and researching influence and protection of the development degree of the soil-site diseases on the soil site.
Background
The earthen site plays an important role in the fields of cultural inheritance, historical exploration, scientific research and the like, and ancient earthen sites in northwest arid regions of China are divided into open-air earthen sites and indoor earthen sites according to the environment, and the open-air earthen sites are more seriously influenced by natural environments, so the protection of the open-air earthen sites is particularly important. Among the diseases of the open-air rammed earth remains, flaky stripping is one of the most common diseases, the wall body is dried and contracted due to rapid change of dry and wet circulation, cracks are formed on the surface, so that a soft surface is formed between the soil body on the surface layer and the wall body, the soil body is gradually stripped under the influence of wind power and other various actions, a certain protection effect on the resistance of the earth remains to weathering is achieved in the early stage of the formation, but the damage of the earth remains is accelerated by rapid stripping in the later stage, and the method has great significance in evaluation and prediction of the development degree of the earth remains.
The flaking is a disease generated by multi-factor coupling action, the influencing factors and the forming mechanism are complex, the influencing factors and the forming mechanism for the disease development are slightly achieved at present, but the evaluation and the prediction of the flaking disease are rarely carried out, and particularly, the scientific quantitative evaluation and the prediction early warning system for the flaking morphological characteristics are carried out under the influence of the intrinsic factors and the natural environment factors of soil.
The invention patent with application number 202210744243.0 provides a method for evaluating and predicting the development degree of a rammed earth site crack disease, which comprises the following steps: selecting factors directly related to crack disease development and establishing an evaluation index system; calculating subjective weight according to an evaluation index system by using a fuzzy analytic hierarchy process, calculating first objective weight by using a multivariate unsteady index method, calculating second objective weight by using an improved entropy value method, and obtaining comprehensive weight by equal weight weighted average treatment; evaluating the development grade of the crack disease by utilizing a TOPSIS approach ideal solution and comprehensive weight; and constructing a BP neural network prediction model, and predicting future development trend of the rammed earth site crack diseases in the northwest drought areas by taking the data of the evaluation index as input data and the evaluation result as output data. Said invention utilizes natural environment characteristics to evaluate and predict development of rammed earth site crack disease, and provides high-accuracy crack disease development trend prediction method so as to raise effectiveness and controllability of crack disease treatment. However, consistency test based on the fuzzy hierarchy method in the invention lacks scientific basis, and TOPSIS approach ideal solution has strong sensitivity to data, if abnormal value or missing value exists, the decision result can be greatly influenced, and the effect of nonlinear problem such as the flaking development degree can be greatly reduced because each index is assumed to be linear; meanwhile, the structure of the BP neural network needs to be selected according to practical problems, and the accuracy of a predicted result is directly influenced by the suitability of the network structure, so that a unified and complete theoretical guidance for the selection of the structure is not available so far, and the structure can be generally selected only by experience.
Disclosure of Invention
Aiming at the technical problems that the existing evaluation and prediction method for the development degree of the flaky stripping disease cannot comprehensively consider influence factors and formation mechanisms and has low prediction accuracy, the invention provides the evaluation method for the development degree of the flaky stripping disease of the great wall of the Hexi corridor, which is used for determining the development condition of the existing part of the soil site through comprehensive evaluation, and then obtaining the development condition of the flaky stripping disease of other soil sites by using the evaluation standard and the prediction model, thereby improving the timeliness and effectiveness of the protection of the soil site to a certain extent.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows: a method for evaluating the degree of flaky stripping development of a great wall site in a Hexi corridor comprises the following steps:
step one: selecting an evaluation index related to the soil site flaky stripping disease in the arid region to establish an evaluation index system;
step two: the subjective weight of each evaluation index is calculated through a decision laboratory analysis method according to an evaluation index system, the first objective weight of each evaluation index is determined through a independent weight coefficient method according to the actual data of each evaluation index, the second objective weight of each evaluation index is determined through an anti-entropy weight method, and the subjective weight, the first objective weight and the second objective weight are subjected to arithmetic average to obtain a combined weight;
step three: carrying out weight adjustment on the normalized matrix of the numerical value of each evaluation index in each arid region by combining weights to obtain a comprehensive weighting matrix;
step four: classifying and evaluating each arid region by a rank sum ratio comprehensive evaluation method according to the comprehensive weighting matrix obtained in the step three;
step five: predicting the soil site flaky stripping disease in the arid region by a ridge regression model, and comparing the disease with the evaluation result in the step four.
Preferably, the evaluation index includes: the method comprises the following steps of flaky stripping morphological characteristics, soil intrinsic factors and natural environment factors, wherein the flaky stripping morphological characteristics comprise: shell layer stripping thickness, powder layer stripping thickness and stripping area; intrinsic factors of soil mass include: specific surface area, disintegration rate, liquid index, porosity, total amount of soluble salt; natural environmental factors include: precipitation, evaporation, daily poor annual average temperature and dryness;
the specific surface area is a positive index, and the shell layer stripping thickness, the powder layer stripping thickness, the stripping area, the disintegration speed, the liquid index, the porosity, the total salt soluble amount, the precipitation amount, the evaporation amount, the daily poor annual average temperature and the dryness are negative indexes.
Preferably, the method for calculating subjective weight by using the decision laboratory analysis method comprises the following steps:
1) Quantifying the interrelationship among the evaluation indexes in the evaluation index system to obtain a direct influence matrix O;
2) Normalizing the direct influence matrix O to obtain a normalized direct influence matrix N;
3) Calculating a composite influence matrix t=n (I-N) from the canonical direct influence matrix N -1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein I is an identity matrix, (I-N) -1 Is the inverse of matrix (I-N);
4) Obtaining the centrality M of the jth evaluation index from the comprehensive influence matrix T j ＝D j +C j Wherein, the influence degreeIs affected by->t ji1 For the j-th row and i-th row in the comprehensive influence matrix T 1 Element value of column, t i1j For the ith in the comprehensive influence matrix T 1 Element values of the row and the j-th column, wherein n is the number of evaluation indexes;
5) Center degree M j Normalized to obtain subjective weight w of the j-th evaluation index 1 。
Preferably, the method for determining the first objective weight by the independent weight coefficient method is as follows:
1) Determining the values of all evaluation indexes of the arid region and constructing an original numerical matrix;
2) Calculating complex correlation coefficients of each evaluation index and other evaluation indexes according to the original numerical matrix;
3) And carrying out normalization processing on the reciprocal of the complex correlation coefficient to obtain the first objective weight of each evaluation index.
Preferably, the value on the diagonal line of the direct influence matrix O is represented by 0, and the value of the other element value in the direct influence matrix O determines the relationship strength of the two evaluation indexes by adopting a 5-level scale;
the normalization method is a range normalization method;
the complex correlation coefficient is
Wherein y represents an evaluation index value in the original value matrix,represents the average value of all values under the evaluation index of the value y,/, for>A regression value representing the value y;
the regression valueIs obtained by linear regression with all other values under the same evaluation index as independent variables.
Preferably, the method for determining the second objective weight of each evaluation index by using the inverse entropy weight method comprises the following steps:
1) Determining the values of all evaluation indexes of the arid region and constructing an original numerical matrix;
2) Normalizing the element values of the numerical matrix to obtain a normalized matrix;
3) Calculating the proportion of the ith sample in the jth evaluation index to the evaluation index;
4) Calculating the inverse entropy value h of the j-th evaluation index according to the specific gravity j ；
5) According to the inverse entropy value h j Calculate the second objective weight w of the j-th evaluation index 3 。
Preferably, the proportion of the ith sample to all sample values in the jth evaluation index is
Wherein n is ij Sample value of ith arid region representing jth evaluation index in normalized matrix, m is trunkNumber of arid regions.
The inverse entropy value of the j-th evaluation index is
Second objective weight of jth evaluation indexn is the number of evaluation indexes;
the combining weights
The weight adjustment method in the third step comprises the following steps: the numerical value of each evaluation index for each arid region is multiplied by the combining weight.
Preferably, the implementation method of the rank sum ratio comprehensive evaluation method comprises the following steps:
1) Sequentially sequencing the arid regions in sequence;
2) According to the sequence numbers, the ranks of all arid regions under each evaluation index are compiled through a total rank sum ratio method, and rank matrixes are listed; calculating a rank sum ratio WRSR value after weighting according to the rank matrix;
3) Listing the distribution table condition of the rank sum ratio WRSR value and each group of frequency f, calculating the accumulated frequency Sigma f and the accumulated frequency of each arid region, and converting the accumulated frequency into a probability unit to obtain a inhibit value;
4) Taking the Probit value as an independent variable, taking the WRSR value as a dependent variable, performing simple linear regression, and fitting a corresponding WRSR estimated value regression equation;
5) And sequencing according to the fitted WRSR estimated value as a characteristic value, and grading each arid region.
Preferably, the method for listing the rank matrix by the whole rank sum ratio method is as follows: sequencing according to the index value of each evaluation index, wherein the positive index is ranked from small to large, the negative index is ranked from large to small, and the average ranks of the same evaluation index data are ranked to obtain a rank matrix R a ＝(R ij ) m×n ；
The calculation formula of the rank sum ratio WRSR value is as follows:
wherein WRSR is as follows i For the rank sum ratio of the ith arid region, R ij Rank of the j-th evaluation index of the i-th arid region, W j A weight indicating a j-th evaluation index;
according to the accumulated frequency query percentage and the probability unit comparison table, converting the percentage form of the evaluation rank number, namely the evaluation rank number/n 100%, into a probability unit;
the 4 steps are classified into 4 steps according to the WRSR evaluation value, and are positioned at [ - ≡ 0.2392) with low development level, [0.2392,0.4794) with medium development level, [0.4794,0.7196) with high development level, [0.7196, + fact) with extremely high development level.
Preferably, the implementation method for predicting the ridge regression model comprises the following steps:
(1) Constructing a ridge regression model through SPSS software to obtain a predicted value of the stripping characteristic under the ridge regression model; respectively constructing a ridge regression model for the thickness of the shell layer, the thickness of the powder layer and the stripping area to obtain regression model coefficients, and respectively multiplying other non-morphological characteristic factors by the regression model coefficients to obtain predicted values;
(2) Substituting the actual value of the stripping morphological feature in the original numerical matrix constructed by the numerical values of each evaluation index of the arid region with a predicted value, and obtaining a new evaluation result by a rank sum ratio evaluation method to obtain a predicted result;
(3) Analyzing and comparing the predicted result with the real result: the ridge regression model fitness test was performed by paired sample T test using SPSS software.
Compared with the prior art, the invention has the beneficial effects that: selecting factors related to the flaky stripping diseases and establishing a basic evaluation index system; the decision laboratory analysis method is utilized to give weight to subjective weight to each evaluation index, a plurality of factors are considered, and the factors and the relations among the factors are quantized, so that the relative importance and degree among different factors are reflected, meanwhile, the data and the results are visually displayed in the form of charts and graphs, and the visual analysis can more intuitively represent the interrelationship among the factors. The invention determines the first objective weight by using each actual value through a independent weight coefficient method, determines the index weight according to the collinearity intensity between each evaluation index and other indexes, avoids the influence of subjective factors, ensures the objectivity of weight determination, ensures clear interpretability of the obtained result, can clearly see the contribution degree and relative independence of each index, and is beneficial to guiding decision and evaluating the importance of the index. The invention determines the second objective weight by using the inverse entropy weight method, can avoid weight conflict generated by high correlation among indexes, and considers the correlation among evaluation indexes when calculating the weight, thereby effectively resisting noise interference; the average subjective weight and each objective weight obtain a combined weight, and the combined weight is adopted to reduce the error of subjective factors caused by subjective judgment on one hand, improve the stability of the objective weight on the other hand, avoid the direct influence of a single weight and improve the reliability of the weight; on the basis of the combination weight, classifying and evaluating each region by a rank and ratio comprehensive evaluation method (RSR), and selecting an evaluation index on the basis of an nonparametric method has no special requirement, so that the method is applicable to various evaluation objects, and because the numerical value used in calculation is rank order, the interference of abnormal values can be eliminated; the ridge regression model is constructed, the development degree of the flaky stripping disease is predicted by inputting related index parameters, and the prediction method is beneficial to timely protecting the earthen site which does not show the flaky stripping morphological characteristics or has unobvious characteristics. According to the invention, the comprehensive weight is calculated by adopting various weighting methods, so that the accuracy of classifying and evaluating the flaking development degree of each region by using a rank sum ratio comprehensive evaluation method is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a schematic diagram of the evaluation index system of the present invention.
FIG. 3 is a schematic diagram of the centrality-causal degree in the Demate method of the present invention.
FIG. 4 is a schematic diagram of the evaluation results of the present invention.
Fig. 5 is a fitted view of the predictive model of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the method for evaluating the degree of flaky peeling development of the great wall remains in the river corridor comprises the following steps:
step one: selecting an evaluation index related to the soil site flaky stripping disease in the arid region to establish an evaluation index system, wherein the evaluation indexes comprise: form characteristics of flaking, intrinsic factors of soil and natural environment factors.
The flaky stripping morphological characteristics of the earthen site in the evaluation index comprise: shell layer stripping thickness, powder layer stripping thickness and stripping area; intrinsic factors of soil mass include: specific surface area, disintegration rate, liquid index, porosity, total amount of soluble salt; natural environmental factors include: precipitation, evaporation, daily average temperature, and dryness.
The specific surface area in the evaluation index is a positive index, and the shell layer stripping thickness, the powder layer stripping thickness, the stripping area, the disintegration speed, the liquid index, the porosity, the total salt soluble amount, the precipitation amount, the evaporation amount, the daily poor annual average temperature and the dryness are negative indexes. The positive index and the negative index can be distinguished to more accurately reflect the quality degree of the evaluation object, and the accuracy and the rationality of the evaluation are improved.
Step two: the subjective weight of each evaluation index is calculated through a Dematel decision laboratory analysis method according to an evaluation index system, the first objective weight of the evaluation index is determined through a independent weight coefficient method according to actual data of each evaluation index, the second objective weight of the evaluation index is determined through an inverse entropy weight method, and the subjective weight, the first objective weight and the second objective weight are processed through an arithmetic average method to obtain a combined weight.
The implementation method for calculating the subjective weight by the Dematel decision laboratory analysis method comprises the following steps:
1) From the research purpose, the evaluation indexes are determined, and the interrelation among the evaluation indexes is quantized to obtain the direct influence matrix O.
The binary relation between the evaluation indexes is determined by pairwise comparison. Wherein the evaluation index S i1 Heel evaluation index S j To be compared twice, respectively are the evaluation indexes S i1 For evaluation index S j Direct influence of (a) and evaluation index S j For evaluation index S i1 Is a direct influence of (a). N evaluation indexes are compared n (n-1) times for the whole evaluation index system. The evaluation index itself does not need to be compared, i.e. the value on the diagonal line of the direct impact matrix O is usually represented by 0, and the measurement method for the relation strength is measured by adopting a 5-level scale, i.e. a five-division method, i.e. a method of taking 0 to 4, as shown in table 1.
The data source of the judgment matrix is expert judgment, and the relative influence degree among all evaluation indexes can be more clearly represented by drawing a network diagram, namely a figure 2. Obtaining the direct influence matrix through the stepsn is the number of evaluation indexes, and is shown in table 2.
TABLE 1 determination of the scale meaning of the matrix
TABLE 2 direct impact matrix
2) The direct influence matrix O is normalized to obtain a normalized direct influence matrix N, as shown in table 3 below, by which problems due to order of magnitude or dimension differences can be reduced while maintaining the relative relationship between the data.
All normalization methods in the invention adopt the same calculation method, namely the range normalization method, and formulas are not shown one by one in the follow-up content, and are as follows:wherein X represents any element in the direct influence matrix, X min Representing the minimum value of the column in which the element X is located, X max Represents the maximum value of the column where the element X is located, and X' represents the normalized value of the element X.
Table 3 Specification direct impact matrix
3) The comprehensive influence matrix T is obtained by calculating the standard direct influence matrix N, and the calculation formula is as follows, as shown in the following table 4:
T＝N(I-N) -1
wherein T is a comprehensive influence matrix, N is a standard direct influence matrix, I is a unit matrix, (I-N) -1 Is the inverse of matrix (I-N). Since the canonical direct influence matrix N can only represent the direct influence between the evaluation indexes, the comprehensive influence matrix needs to be obtained through calculation so as to reflect the comprehensive influence matrix in the systemThere are direct and indirect influence relationships between the metrics, so that influence relationships in the system can be more fully described.
TABLE 4 comprehensive impact matrix
4) Obtaining the influence degree D of each evaluation index from the comprehensive influence matrix T j Degree of influence C j Center degree M j Degree of cause R j As shown in table 5, the calculation formulas are as follows:
M j ＝D j +C j
R j ＝D j -C j
and drawing the figure 3 by calculating the center degree and the cause degree and taking the center degree and the cause degree as a coordinate system, and revealing the position and the action mode of each evaluation index in the system.
Table 5 influence, affected, center, and cause of each evaluation index
5) Center degree M i The subjective weights were obtained after normalization treatment, see table 6 below. The centrality is an index parameter for measuring the status and the action of the evaluation index in the evaluation index system, and considers the evaluation index to all other factorsThe degree of influence of the evaluation index and the degree of influence by all other evaluation indexes. The cause degree can reflect the action and the influence mode of the evaluation index in the evaluation index system, but the cause degree is more focused on revealing the causal relation among the evaluation indexes. The evaluation index having a high cause degree has a large influence on other evaluation indexes, but is not necessarily of equal importance in the evaluation index system. Thus, normalizing the weights using the causal degree may produce some bias and unreasonable results.
Table 6 subjective weights of the evaluation indexes
The subjective weight can be determined by a Dematel decision laboratory analysis method, all relevant evaluation indexes can be fully considered, and the relevant weights are given to the subjective weight, so that more comprehensive information is covered in the decision process, the influence degree of each evaluation index on the final decision can be clearly explained, and the decision process has transparency and understandability.
The independent weight coefficient refers to a measure of linear dependence between a random variable and a set of random variables, which shows the correlation between data, and is implemented by: the weight is determined by using the collinearity strength between the evaluation indexes, if the correlation between a certain evaluation index and other evaluation indexes is strong, the information is indicated to have larger overlapping, which means that the weight of the evaluation index is lower, otherwise, if the correlation between the certain evaluation index and other evaluation indexes is weaker, the information carried by the evaluation index is indicated to be larger, and the evaluation index is supposed to be given higher weight. The independent weight coefficient method only considers the correlation between data, and the calculation mode is that the complex correlation coefficient R value obtained by regression analysis is used for representing the collinearity strength (namely, the correlation strength), and the larger the value is, the stronger the collinearity is, and the lower the weight is.
The implementation method for determining the first objective weight through the independent weight coefficient method comprises the following steps:
1) And determining the numerical value of each evaluation index of the arid region and constructing a numerical matrix.
Determining a numerical matrix X according to the numerical value of each evaluation index of each arid region 1 ,X 2 ,....,X n N represents the number of evaluation indexes, and the content of the index items is shown in the following table 7, which is obtained by the prior experiments and researches.
TABLE 7 study area and evaluation index
2) Calculating complex correlation coefficients of each evaluation index and other evaluation indexes, wherein the correlation coefficients are shown in a formula:
wherein y represents any value under a certain evaluation index,represents the average of all values under the evaluation index of y,and (3) representing a regression value of y, wherein the regression value is obtained by performing linear regression by taking all other values under the same evaluation index as independent variables and can be obtained by adopting SPSS software.
Obtaining complex correlation coefficient R of each evaluation index 1 ,R 2 ,....,R n And the reciprocal of the complex correlation coefficient is shown in table 8 below.
TABLE 8 Complex correlation coefficient and reciprocal of evaluation indices
3) And weighting each evaluation index to obtain a first objective weight.
The inverse of the complex correlation coefficient is normalized to obtain the first objective weight for each evaluation index, see table 9 below.
Table 9 objective weight of each index
The inverse entropy weight method is a method for reflecting the data information amount based on the entropy weight method, and the inverse entropy shows the difference of indexes, and the realization method is as follows: and (3) calculating the inverse entropy value of each evaluation index to obtain the difference of the evaluation indexes, wherein the larger the inverse entropy is, the higher the corresponding weight is.
The implementation method for determining the second objective weight of the evaluation index by using the inverse entropy weight method comprises the following steps:
1) Determining each evaluation index item and constructing a data matrix
Data matrix X for determining evaluation indexes 1 ,X 2 ,....,X n The matrix is shown in Table 7.
2) The numerical matrix was normalized by the pole difference method, as shown in table 10 below.
Table 10 normalization processing results
3) The specific gravity of the ith sample value in the jth evaluation index to the evaluation index was calculated, as shown in table 11 below.
Wherein r is ij Indicating the specific gravity of the ith sample to all sample values in the jth evaluation index, n ij And the ith sample value in the jth evaluation index in the normalized matrix is represented, and m is the sample number.
Table 11 specific gravity of each sample in the evaluation index
4) The inverse entropy value of the j-th evaluation index is calculated, see table 12 below.
Table 12 inverse entropy values of evaluation indexes
5) The second objective weight of the j-th evaluation index is calculated, see table 13 below.
TABLE 13 second objective weight for evaluation indicators
The combination weights were obtained by the method of arithmetic averaging of the subjective weights and the objective weights obtained as described above, and the specific data are shown in table 14 below.
The advantages of using combining weights are: (1) the Demtal decision laboratory analysis method only considers the influence among evaluation indexes, has a certain subjective limitation, and reduces the one-sided influence of subjective factors by combining and adjusting assignment added with an objective weight method. (2) The 3 methods perform arithmetic average combination to reduce the adverse effect on the overall evaluation when error values occur in a single method. (3) The combined weight is adopted to adjust the weight of each evaluation index, so that the data can be more accurate and stable when rank and ratio evaluation is carried out.
Table 14 combining weights
Step three: and carrying out weight adjustment on the normalized matrix of the numerical value of each evaluation index in each arid region by combining weights to obtain a comprehensive weighting matrix.
And (3) carrying out weight adjustment on each evaluation index according to the combined weight obtained in the step (II) by using a normalized matrix of the values of each evaluation index in each arid region, namely a matrix normalized in the table (10), namely multiplying the value of each evaluation index in the table (7) by the corresponding weight to obtain a comprehensive weighting matrix.
Step four: and step three, the comprehensive weighting matrix obtained in the step is used for classifying and evaluating each arid region by a rank sum ratio comprehensive evaluation method.
The method for realizing the rank sum ratio comprehensive evaluation method comprises the following steps:
1) The arid region is sequentially numbered from 1 to 18 according to the order of spring, plateau, linzheng, zhangye, wu Wei, cloisonne, yongchang, noble, ledu, folk music, safe, yongjing, yongden, tianzhu, datong, ganzhong and Haidong, so that the description is convenient in sorting, and the method has no other significance.
2) Listing a rank matrix by a whole rank sum ratio method, and compiling ranks of each arid region under each evaluation index: sequencing according to the index value of each specific evaluation index, wherein the positive index is ranked from small to large, the negative index is ranked from large to small, the average rank of the same evaluation index data is ranked, and a rank matrix is obtained, and R is recorded a ＝(R ij ) m×n See tables 15 and 16.
Table 15 comprehensive weighting matrix
Table 16 rank matrix
Rank sum ratio WRSR value and WRSR value rank after weighting is obtained through calculation, the correlation value and rank are shown in a table 17, and the calculation formula is as follows:
wherein R is ij Rank of the j-th evaluation index of the i-th arid region, W j The weight of the j-th evaluation index is represented, and the sum of the weights is 1.WRSR (Wireless sensor System) i The larger the value of (2) is, the better the evaluation object is.
Table 17WRSR values and ranks
/>
The dimensionless statistic WRSR obtained by rank conversion ranks or ranks the merits of the evaluation objects (i.e., arid regions) by WRSR values. In the comprehensive evaluation, the WRSR value can contain information of all evaluation indexes, and the comprehensive level of the evaluation indexes is displayed, and the larger the WRSR value is, the better the comprehensive evaluation is.
3) The distribution table condition of the WRSR value and the frequency f of each group are listed, the cumulative frequency Σf and the cumulative frequency p of each group are calculated, and the cumulative frequency can be queried into a percentage form of the evaluation rank, namely, the evaluation rank/n×100% in table 18, is converted into a probability unit Probit by a percentage and probability unit comparison table, so as to obtain a Probit value, and the Probit value is shown in the following table 18.
Table 18 distribution table case of WRSR and Probit values
4) Simple linear regression is performed by SPSS software with the Probit value as an independent variable and the WRSR value as a dependent variable, and a regression equation of the corresponding WRSR estimated value is fitted and F test (variance ratio test), significance test and t test (difference test) are performed, and the regression result and analysis result are shown in the following table 19.
Table 19WRSR estimate regression equation and analysis
/>
Wherein B represents the coefficient of the independent variable, the standard error represents the standard deviation of the sample, beta represents the standard regression coefficient, t represents the t value at the time of t test, namely the statistic of the difference between the comparison means, P represents the P value in the significance test, namely the significance level, VIF represents the severity of multiple collinearity, R 2 Represents the fitting degree of curve regression, and the adjustment of R2 is performed at the fitting degree R 2 To prevent overfitting of the model, F represents a statistic in the F test to compare whether the variances of the samples differ significantly.
5) And sorting according to the fitted WRSR values as characteristic values, and grading. In the case of the classification, three classification cases of 3, 4 and 5 were adopted, and according to the related studies on the sheet peeling in the past, the classification case of 4 was good, and the classification case of 4 was preferentially selected, as shown in tables 20 and 21 below, wherein the classification was 4 grades according to the WRSR value, and the classification was low in the development level [ - ≡ 0.2392), medium in the development level [0.2392,0.4794), high in the development level [0.4794,0.7196), and extremely high in the development level [0.7196, ++). The WRSR threshold (fitting value) is obtained from the regression equation substituted into table 19 with the Probit value. A scatter diagram as shown in fig. 4 can be drawn by taking a sample of each arid region as an abscissa and a WRSR value as an ordinate, so as to show classification conditions of each arid region.
TABLE 20 ranking threshold table
TABLE 21 extent of development of arid regions
/>
The method for analyzing parameters is integrated by adopting a rank sum comparison comprehensive evaluation method, the result is more accurate, because the numerical value used for calculation is rank order, the interference of abnormal values can be eliminated, and in order to be more matched with the evaluation data, three, four and five grade evaluation categories are respectively carried out for comparing the evaluation result, more reasonable classification grades are selected, and the difference caused by subjective evaluation classification grade selection is eliminated.
Step five: predicting the soil site flaky stripping disease in the arid region by a ridge regression method, and comparing the disease with the evaluation result in the step four. Since the peeling morphology features are the features of a long-term dynamic development process and can not be directly observed, the peeling morphology features of the rammed earth site can be predicted by intrinsic factors and environmental factors and then substituted into an evaluation system to obtain an evaluation result, thereby obtaining an evaluation and prediction method for the development degree of the peeling disease of the earth site in the arid region.
And a certain technical support is provided for protecting and reinforcing the earthen site through comprehensive evaluation of the flaky stripping diseases. However, the invention provides a prediction model based on the limited effective information generated by the comprehensive evaluation result.
The implementation method of the ridge regression model prediction comprises the following steps: the method comprises the steps of establishing a ridge regression (RSR) model through SPSS software, classifying and evaluating the arid regions by the obtained fitting characteristic values, predicting the flaky peeling morphological characteristics through non-characteristic factors, combining predicted data with a rank and ratio evaluation method, namely replacing the actual flaky peeling morphological characteristics in a rank and ratio evaluation system with predicted values to obtain a predicted evaluation structure, comparing the predicted evaluation structure with actual evaluation results, and carrying out verification analysis to finally obtain the flaky peeling development conditions of each arid region through the non-characteristic factors obtained through some experiments. Because the weights of the indexes are adjusted through comprehensive weights before calculating the rank value, the WRSR is used for replacing the RSR, the meaning of the WRSR is similar, the WRSR is a characteristic value after weight adjustment, and the greater the characteristic value is, the smaller the development degree of the flaky stripping disease is indicated.
1) And constructing a ridge regression model through SPSS software to obtain a predicted value of the stripping characteristic under the ridge regression model. Since the ridge regression belongs to one of linear regression, it is necessary to construct a ridge regression model for the shell thickness, powder layer thickness and peeling area to obtain regression model coefficients, and R is performed on the ridge regression model 2 The value is calculated and F test is carried out, and the significance P value of the three models based on the F test is 0<0.01, shows significance on the level, refuses the original hypothesis, and shows that a regression relationship exists between the independent variable and the dependent variable. Meanwhile, the goodness of fit R2 of the three models is 0.959, 0.954 and 0.926 respectively, and the models are excellent. The correlation coefficients are shown in Table 22 below. The model coefficient can be used for obtaining a ridge regression model of three morphological characteristic indexes, and other non-morphological characteristic factors are multiplied by the coefficients respectively to directly obtain a predicted value.
Table 22 model coefficients
2) The true values of the peeling morphology features in table 7 are replaced by predicted values so as to be convenient for evaluation when the sheet development features are not obvious, namely, the sheet development features cannot be directly observed, the new predicted values and the true values are shown in the following table, the predicted values are obtained through substituting the model in the step five (1) into the calculation, and then new evaluation results are obtained through a rank sum ratio evaluation method, and the following table 23 is shown. And (3) reevaluating the predicted value and the true value of other indexes according to the steps S1-S5, and carrying out fitting degree test on the evaluation result to obtain an excellent prediction model. The predicted situation is further shown by plotting the WRSR value true value and the predicted value into a double-line graph, see fig. 5.
TABLE 23 prediction of extent of development
3) Analyzing and comparing the predicted result with the real result: model fitting degree test is carried out through paired sample T test by using SPSS software, the calculation results are shown in the following table 24, the paired sample T test results show that the paired WRSR predicted value is paired based on the actual value of the variable WRSR, the significance value P is 1.000, the significance is not presented horizontally, the original assumption cannot be refused, and therefore, no significance difference exists between the paired WRSR predicted values of the WRSR actual value. The difference amplitude value is as follows: 0.0, the difference amplitude is very small, and the model prediction condition is good.
Table 24 fitness test table
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. A method for evaluating the degree of flaky stripping development of a great wall site in a Hexi corridor is characterized by comprising the following steps:
step one: selecting an evaluation index related to the soil site flaky stripping disease in the arid region to establish an evaluation index system;
step two: the subjective weight of each evaluation index is calculated through a decision laboratory analysis method according to an evaluation index system, the first objective weight of each evaluation index is determined through a independent weight coefficient method according to the actual data of each evaluation index, the second objective weight of each evaluation index is determined through an anti-entropy weight method, and the subjective weight, the first objective weight and the second objective weight are subjected to arithmetic average to obtain a combined weight;
step three: carrying out weight adjustment on the normalized matrix of the numerical value of each evaluation index in each arid region by combining weights to obtain a comprehensive weighting matrix;
step four: classifying and evaluating each arid region by a rank sum ratio comprehensive evaluation method according to the comprehensive weighting matrix obtained in the step three;
step five: predicting the soil site flaky stripping disease in the arid region by a ridge regression model, and comparing the disease with the evaluation result in the step four.
2. The method for evaluating the degree of development of sheet exfoliation in a great wall site of a river channel according to claim 1, wherein the evaluation index comprises: the method comprises the following steps of flaky stripping morphological characteristics, soil intrinsic factors and natural environment factors, wherein the flaky stripping morphological characteristics comprise: shell layer stripping thickness, powder layer stripping thickness and stripping area; intrinsic factors of soil mass include: specific surface area, disintegration rate, liquid index, porosity, total amount of soluble salt; natural environmental factors include: precipitation, evaporation, daily poor annual average temperature and dryness;
the specific surface area is a positive index, and the shell layer stripping thickness, the powder layer stripping thickness, the stripping area, the disintegration speed, the liquid index, the porosity, the total salt soluble amount, the precipitation amount, the evaporation amount, the daily poor annual average temperature and the dryness are negative indexes.
3. The method for evaluating the degree of flaky peeling development of the great wall remains of the river channel according to claim 1 or 2, wherein the method for calculating subjective weights by using the decision laboratory analysis method is as follows:
1) Quantifying the interrelationship among the evaluation indexes in the evaluation index system to obtain a direct influence matrix O;
2) Normalizing the direct influence matrix O to obtain a normalized direct influence matrix N;
3) Calculating a composite influence matrix t=n (I-N) from the canonical direct influence matrix N -1 The method comprises the steps of carrying out a first treatment on the surface of the Wherein I is an identity matrix, (I-N) -1 Is the inverse of matrix (I-N);
4) Obtaining the centrality M of the jth evaluation index from the comprehensive influence matrix T j ＝D j +C j Wherein, the influence degreeIs affected by-> For the j-th row and i-th row in the comprehensive influence matrix T 1 Element value of column,/->For the ith in the comprehensive influence matrix T 1 Element values of the row and the j-th column, wherein n is the number of evaluation indexes;
5) Center degree M j Normalized to obtain subjective weight w of the j-th evaluation index 1 。
4. The method for evaluating the degree of development of sheet exfoliation in a great wall site in a river channel according to claim 3, wherein the method for determining the first objective weight by the independent weight coefficient method comprises the steps of:
1) Determining the values of all evaluation indexes of the arid region and constructing an original numerical matrix;
2) Calculating complex correlation coefficients of each evaluation index and other evaluation indexes according to the original numerical matrix;
3) And carrying out normalization processing on the reciprocal of the complex correlation coefficient to obtain the first objective weight of each evaluation index.
5. The method for evaluating the degree of development of the sheet exfoliation of the great wall site in the Hexicorridor according to claim 4, wherein the value on the diagonal line of the direct influence matrix O is represented by 0, and the value of the other element value in the direct influence matrix O is used for determining the relation strength of two evaluation indexes by adopting a 5-level scale;
the normalization method is a range normalization method;
the complex correlation coefficient is
Wherein y represents an evaluation index value in the original value matrix,represents the average value of all values under the evaluation index of the value y,/, for>A regression value representing the value y;
the regression valueIs obtained by linear regression with all other values under the same evaluation index as independent variables.
6. The method for evaluating the degree of development of the flaky peeling of the great wall remains of the Hexicorridor according to claim 4, wherein the method for determining the second objective weight of each evaluation index by using the inverse entropy weight method is as follows:
1) Determining the values of all evaluation indexes of the arid region and constructing an original numerical matrix;
2) Normalizing the element values of the numerical matrix to obtain a normalized matrix;
3) Calculating the proportion of the ith sample in the jth evaluation index to the evaluation index;
4) Calculating the inverse entropy value h of the j-th evaluation index according to the specific gravity j ；
5) According to the inverse entropy value h j Calculate the second objective weight w of the j-th evaluation index 3 。
7. The method for evaluating and predicting the development degree of a rammed earth site flaky stripping disease according to claim 6, wherein the specific gravity of the ith sample to all sample values in the jth evaluation index is
Wherein n is ij And (3) representing a sample value of an ith arid region of the jth evaluation index in the normalized matrix, wherein m is the number of the arid regions.
The inverse entropy value of the j-th evaluation index is
Second objective weight of jth evaluation indexn is the number of evaluation indexes;
the combining weights
The weight adjustment method in the third step comprises the following steps: the numerical value of each evaluation index for each arid region is multiplied by the combining weight.
8. The evaluation method for the degree of development of sheet exfoliation in the great wall site of the Hexi corridor according to any one of claims 1, 2 and 4 to 7, wherein the method for realizing the rank sum ratio comprehensive evaluation method is as follows:
1) Sequentially sequencing the arid regions in sequence;
2) According to the sequence numbers, the ranks of all arid regions under each evaluation index are compiled through a total rank sum ratio method, and rank matrixes are listed; calculating a rank sum ratio WRSR value after weighting according to the rank matrix;
3) Listing the distribution table condition of the rank sum ratio WRSR value and each group of frequency f, calculating the accumulated frequency Sigma f and the accumulated frequency of each arid region, and converting the accumulated frequency into a probability unit to obtain a inhibit value;
4) Taking the Probit value as an independent variable, taking the WRSR value as a dependent variable, performing simple linear regression, and fitting a corresponding WRSR estimated value regression equation;
5) And sequencing according to the fitted WRSR estimated value as a characteristic value, and grading each arid region.
9. The method for evaluating the degree of development of sheet exfoliation in a great wall of a river channel in accordance with claim 8, wherein the method for listing the rank matrix by the overall rank sum ratio method comprises: sequencing according to the index value of each evaluation index, wherein the positive index is ranked from small to large, the negative index is ranked from large to small, and the average ranks of the same evaluation index data are ranked to obtain a rank matrix R a ＝(R ij ) m×n ；
The calculation formula of the rank sum ratio WRSR value is as follows:
wherein WRSR is as follows i For the rank sum ratio of the ith arid region, R ij Rank of the j-th evaluation index of the i-th arid region, W j A weight indicating a j-th evaluation index;
according to the accumulated frequency query percentage and the probability unit comparison table, converting the percentage form of the evaluation rank number, namely the evaluation rank number/n 100%, into a probability unit;
the 4 steps are classified into 4 steps according to the WRSR evaluation value, and are positioned at [ - ≡ 0.2392) with low development level, [0.2392,0.4794) with medium development level, [0.4794,0.7196) with high development level, [0.7196, + fact) with extremely high development level.
10. The method for evaluating the degree of development of sheet exfoliation in a great wall of a river channel according to claim 9, wherein the ridge regression model is implemented by:
(1) Constructing a ridge regression model through SPSS software to obtain a predicted value of the stripping characteristic under the ridge regression model; respectively constructing a ridge regression model for the thickness of the shell layer, the thickness of the powder layer and the stripping area to obtain regression model coefficients, and respectively multiplying other non-morphological characteristic factors by the regression model coefficients to obtain predicted values;
(2) Substituting the actual value of the stripping morphological feature in the original numerical matrix constructed by the numerical values of each evaluation index of the arid region with a predicted value, and obtaining a new evaluation result by a rank sum ratio evaluation method to obtain a predicted result;
(3) Analyzing and comparing the predicted result with the real result: the ridge regression model fitness test was performed by paired sample T test using SPSS software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311820589.5A CN117764454B (en) | 2023-12-27 | Method for evaluating development degree of site flaky stripping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311820589.5A CN117764454B (en) | 2023-12-27 | Method for evaluating development degree of site flaky stripping |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117764454A true CN117764454A (en) | 2024-03-26 |
| CN117764454B CN117764454B (en) | 2024-07-02 |
Family
ID=
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10032600A1 (en) * | 2000-07-07 | 2002-01-17 | Schenck Vibro Gmbh | Rotor balancing method by calculating new balancing masses from coefficients of influence calculated when remaining imbalance exceeds threshold |
| JP2007034761A (en) * | 2005-07-28 | 2007-02-08 | Hitachi Ltd | Business value evaluation support apparatus and business value evaluation support program |
| KR100776193B1 (en) * | 2006-06-20 | 2007-11-16 | 연세대학교 산학협력단 | Method of technology evaluation using reject inference |
| JP2017010318A (en) * | 2015-06-23 | 2017-01-12 | キヤノン株式会社 | Information processing apparatus and information processing method |
| CN108182511A (en) * | 2017-12-11 | 2018-06-19 | 上海电力学院 | It is a kind of based on Demand Side Response reserve value assessment method of the sum of ranks than method |
| CN109102201A (en) * | 2018-08-27 | 2018-12-28 | 国网河北省电力有限公司经济技术研究院 | A kind of power distribution network input-output efficiency evaluation method of component voltage grade |
| KR20190032252A (en) * | 2017-09-19 | 2019-03-27 | 한국생명공학연구원 | Method for evaluating tumorigenicity of cell therapeutic products |
| CN110565623A (en) * | 2019-09-17 | 2019-12-13 | 兰州理工大学 | Method for stripping and reinforcing earthen site sheets |
| WO2020041955A1 (en) * | 2018-08-28 | 2020-03-05 | 大连理工大学 | Method for evaluating comprehensive performance of numerical control machine tool based on improved pull-apart grade method |
| CN114997514A (en) * | 2022-06-27 | 2022-09-02 | 兰州理工大学 | Evaluation and prediction method for development degree of rammed earth site crack diseases |
| CN115099699A (en) * | 2022-07-22 | 2022-09-23 | 自然资源部第三海洋研究所 | MABAC comprehensive algorithm-based coast erosion intensity evaluation method |
| CN115689117A (en) * | 2022-11-08 | 2023-02-03 | 山东大学 | College laboratory safety comprehensive evaluation interaction system and method |
| CN116681205A (en) * | 2023-05-18 | 2023-09-01 | 兰州理工大学 | Method for evaluating and predicting development degree of rammed earth site gully disease |
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10032600A1 (en) * | 2000-07-07 | 2002-01-17 | Schenck Vibro Gmbh | Rotor balancing method by calculating new balancing masses from coefficients of influence calculated when remaining imbalance exceeds threshold |
| JP2007034761A (en) * | 2005-07-28 | 2007-02-08 | Hitachi Ltd | Business value evaluation support apparatus and business value evaluation support program |
| KR100776193B1 (en) * | 2006-06-20 | 2007-11-16 | 연세대학교 산학협력단 | Method of technology evaluation using reject inference |
| JP2017010318A (en) * | 2015-06-23 | 2017-01-12 | キヤノン株式会社 | Information processing apparatus and information processing method |
| KR20190032252A (en) * | 2017-09-19 | 2019-03-27 | 한국생명공학연구원 | Method for evaluating tumorigenicity of cell therapeutic products |
| CN108182511A (en) * | 2017-12-11 | 2018-06-19 | 上海电力学院 | It is a kind of based on Demand Side Response reserve value assessment method of the sum of ranks than method |
| CN109102201A (en) * | 2018-08-27 | 2018-12-28 | 国网河北省电力有限公司经济技术研究院 | A kind of power distribution network input-output efficiency evaluation method of component voltage grade |
| WO2020041955A1 (en) * | 2018-08-28 | 2020-03-05 | 大连理工大学 | Method for evaluating comprehensive performance of numerical control machine tool based on improved pull-apart grade method |
| CN110565623A (en) * | 2019-09-17 | 2019-12-13 | 兰州理工大学 | Method for stripping and reinforcing earthen site sheets |
| CN114997514A (en) * | 2022-06-27 | 2022-09-02 | 兰州理工大学 | Evaluation and prediction method for development degree of rammed earth site crack diseases |
| CN115099699A (en) * | 2022-07-22 | 2022-09-23 | 自然资源部第三海洋研究所 | MABAC comprehensive algorithm-based coast erosion intensity evaluation method |
| CN115689117A (en) * | 2022-11-08 | 2023-02-03 | 山东大学 | College laboratory safety comprehensive evaluation interaction system and method |
| CN116681205A (en) * | 2023-05-18 | 2023-09-01 | 兰州理工大学 | Method for evaluating and predicting development degree of rammed earth site gully disease |
Non-Patent Citations (2)
| Title |
|---|
| QIUPING BI: "Optimization of Complex Mine Ventilation System Based on AHP-WRSR", 2021 IEEE 16TH CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA), 31 December 2021 (2021-12-31), pages 603 - 608 * |
| 杜昱民 等: "青海明长城烽火台病害发育与海拔相关性研究", 工程地质学报, vol. 2016, 13 October 2016 (2016-10-13), pages 121 - 127 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109472003A (en) | A kind of arithmetic of linearity regression applied to cost analysis | |
| CN109472403B (en) | Medium-and-long-term runoff forecasting method integrating empirical mode decomposition and remote correlation | |
| CN113570000A (en) | Ocean single-factor observation quality control method based on multi-model fusion | |
| CN114971301B (en) | Ecological interference risk identification and evaluation method based on automatic parameter adjustment optimization model | |
| CN111797364B (en) | Landslide multilayer safety evaluation method based on composite cloud model | |
| CN110852511B (en) | Resident short-term electricity consumption prediction method based on weather temperature and k-nearest neighbor theory | |
| CN108416466A (en) | Methods of electric load forecasting, the computer information processing system of complex characteristics influence | |
| Hao et al. | The application of information diffusion technique in probabilistic analysis to grassland biological disasters risk | |
| CN111931983A (en) | Precipitation prediction method and system | |
| CN112950067A (en) | Power consumer electricity utilization efficiency assessment method based on fuzzy comprehensive evaluation | |
| Zhang et al. | Component-based reconstruction prediction of runoff at multi-time scales in the source area of the Yellow River based on the ARMA model | |
| CN113240527A (en) | Bond market default risk early warning method based on interpretable machine learning | |
| CN110414088B (en) | Space fuzzy evaluation method for suitability of birds-involved habitat by combining hydrodynamic model | |
| Wang et al. | A Decomposition-based Multi-model and Multi-parameter ensemble forecast framework for monthly streamflow forecasting | |
| CN115096357A (en) | Indoor environment quality prediction method based on CEEMDAN-PCA-LSTM | |
| CN107194561A (en) | Method based on Information Entropy and grey GM11 model prediction real estate risks | |
| CN117078114B (en) | Water quality evaluation method and system for water-bearing lakes under influence of diversion engineering | |
| CN117764454B (en) | Method for evaluating development degree of site flaky stripping | |
| CN117764454A (en) | Evaluation method for development degree of flaky stripping of wall site in open great wall of Hexi corridor | |
| CN116561569A (en) | Industrial power load identification method based on EO feature selection and AdaBoost algorithm | |
| CN110533213A (en) | Transmission line of electricity defect Risk Modeling and its prediction technique based on support vector machines | |
| CN114997514A (en) | Evaluation and prediction method for development degree of rammed earth site crack diseases | |
| CN115358587A (en) | Regional multi-department collaborative infrastructure planning method and system | |
| CN110322063B (en) | Power consumption simulation prediction method and storage medium | |
| CN114118688A (en) | Power grid engineering cost risk early warning method based on sequence relation analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |