CN114997514A - Evaluation and prediction method for development degree of rammed earth site crack diseases - Google Patents

Evaluation and prediction method for development degree of rammed earth site crack diseases Download PDF

Info

Publication number
CN114997514A
CN114997514A CN202210744243.0A CN202210744243A CN114997514A CN 114997514 A CN114997514 A CN 114997514A CN 202210744243 A CN202210744243 A CN 202210744243A CN 114997514 A CN114997514 A CN 114997514A
Authority
CN
China
Prior art keywords
evaluation
weight
index
evaluation index
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
Application number
CN202210744243.0A
Other languages
Chinese (zh)
Other versions
CN114997514B (en
Inventor
崔凯
俞莉
王东华
于翔鹏
吴国鹏
王冠众
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.)
Lanzhou University of Technology
Original Assignee
Lanzhou University of Technology
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 Lanzhou University of Technology filed Critical Lanzhou University of Technology
Priority to CN202210744243.0A priority Critical patent/CN114997514B/en
Publication of CN114997514A publication Critical patent/CN114997514A/en
Application granted granted Critical
Publication of CN114997514B publication Critical patent/CN114997514B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Artificial Intelligence (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Operations Research (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Educational Administration (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Primary Health Care (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a method for evaluating and predicting development degree of fracture diseases of rammed earth relics, which comprises the following steps: selecting factors directly related to crack disease development to establish 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 unstable index method, calculating second objective weight by using an improved entropy method, and obtaining comprehensive weight by equal weight weighted average processing; evaluating the crack disease development grade by using a TOPSIS approximate ideal solution and comprehensive weight; and constructing a BP neural network prediction model, and predicting the future development trend of the rammed earth relic crack diseases in the northwest arid regions by taking the data of the evaluation indexes as input data and the evaluation results as output data. The method evaluates and predicts the fissure disease development of the rammed earth relic based on natural environment characteristics, provides a method for predicting the fissure disease development trend with high precision, and improves the effectiveness and controllability of fissure disease treatment.

Description

Evaluation and prediction method for development degree of fracture disease of rammed earth site
Technical Field
The invention relates to the technical field of rammed earth site disease development characteristics, in particular to a method for evaluating and predicting the development degree of fracture diseases of rammed earth sites.
Background
The reasons for the disease development of the rammed earth ruins are complex, and generally mainly comprise two main types of internal factors and external factors, wherein the internal factors mainly comprise the factors of rammed earth building materials and the ruin construction process, and the external factors comprise the aspects of an earthen ruin occurrence environment, a meteorological environment, a geological environment and the like. The safety and stability of the rammed earth site are seriously threatened by factors such as natural erosion of temperature, rainfall, wind, salinization and the like and human destruction, and the process that the rammed earth site undergoes mass development of typical diseases such as cracks, gullies, undercuts, flaking, collapse and the like to rapid death and the quality of the rammed earth site is changed is caused. The effective evaluation, prediction, prevention and alleviation of the damage of the rammed earth site under the action of natural environment characteristics are comprehensive application science, and particularly, the effective evaluation, prediction, prevention and alleviation of the damage of the rammed earth site in northwest arid regions lack targeted research on disease characteristics, system evaluation and prediction and the like at home and abroad and also lack of targeted protective measures. The rare research is based on natural environment characteristics, the disease development severity grade is quantitatively distinguished through an effective evaluation method, and the rare research further predicts and analyzes the future development trend of the disease by utilizing an effective prediction early warning system, so that hierarchical scientific protection is further realized.
Disclosure of Invention
Aiming at the technical problem that a scientific quantitative evaluation and prediction early warning system for the development of the rammed earth site diseases is lacked at present, the invention provides an evaluation and prediction method for the development degree of the rammed earth site fracture diseases, wherein the evaluation and prediction are carried out on the development of the rammed earth site fracture diseases based on natural environmental characteristics, and evaluation indexes influencing the development of the rammed earth site fracture diseases are comprehensively considered; weighting by an objective combination weight method is fully considered, an optimal ideal solution is selected to grade the crack disease development degree of a researched area, a method for predicting crack disease development trend with high precision is provided, and effectiveness and controllability of crack disease treatment are improved.
In order to achieve the purpose, the technical scheme of the invention is realized as follows: a method for evaluating and predicting development degree of fracture diseases of rammed earth site comprises the following steps:
step S1: selecting factors directly related to crack disease development to establish an evaluation index system, wherein the evaluation indexes comprise: the gap length, the gap opening degree, the gap communication rate and the natural environment characteristics;
step S2: calculating subjective weight according to an evaluation index system by using a fuzzy analytic hierarchy process, calculating first objective weight by using a multivariate unstable index method according to data of the evaluation index system of a research region, calculating second objective weight by using an improved entropy method, and processing the subjective weight, the first objective weight and the second objective weight by equal-weight weighted average to obtain comprehensive weight of the evaluation index;
step S3: evaluating the crack disease development grade by using a TOPSIS approximate ideal solution method: calculating Euclidean distances between each evaluation scheme and the positive and negative ideal solutions according to the comprehensive weight determined in the step S2, and evaluating the development degree of the fracture diseases of the rammed earth relics of the northwest arid regions through the Euclidean distances to obtain the development grade of the fracture diseases;
step S4: and (4) constructing a BP neural network prediction model by using a machine learning BP neural network, predicting the future development trends of the rammed earth relic fracture diseases in the northwest drought regions by using all evaluation indexes of an evaluation index system as input data and the evaluation result of the step S3 as output data, and verifying the prediction results.
Preferably, the gap length in the evaluation index includes a total gap length and an average gap length; the gap opening degree comprises a maximum gap opening degree and an average gap opening degree; the fracture connectivity comprises bulk density and linear density; the natural environmental characteristics include the annual average temperature, annual average rainfall, annual average evaporation, drought index and annual average sunshine hours.
Preferably, the determination of the directivity of each evaluation index results in that the directivity of each evaluation index is negative.
Preferably, the implementation method of the fuzzy analytic hierarchy process is as follows:
(1) constructing an FAHP model: the crack disease development degree index layer comprises a target layer, a criterion layer and an index layer, wherein the target layer is the crack disease development degree A; the criterion layer comprises a gap length B1, a gap opening B2, a gap connectivity B3 and an environmental factor B4; the indicator layer comprises a total gap length C1, an average gap length C2, a maximum gap opening C3, an average gap opening C4, a bulk density C5, a linear density C6, an annual average temperature C7, an annual average rainfall C8, an annual average evaporation C9, a drought index C10 and an annual average sunshine duration C11;
(2) constructing a fuzzy judgment matrix A (a) through expert scoring ij ) n×n Wherein, the element a ii ＝0.5；a ij +a ji ＝1,a ij Not less than 0; n represents the number of selected evaluation indexes;
(3) calculating subjective weights of all evaluation indexes according to the fuzzy judgment matrix A;
Figure BDA0003716463070000021
Figure BDA0003716463070000022
Figure BDA0003716463070000023
wherein r is i The sum of the i-th row evaluation index scales, r, representing the fuzzy judgment matrix A j Is represented by the formula i The corresponding j columns of elements; r is ij Expressing constructed subjective weight W i A matrix element of (a);
(4) and (3) consistency test:
by a weight vector (W) 1 ,W 2 ,W 3 ..,W i ,...W n ) T Construct feature matrix W ═ W ij ) n×n Element W of the feature matrix W ij Comprises the following steps:
Figure BDA0003716463070000031
checking the consistency of the fuzzy judgment matrix A and the characteristic matrix W:
construction of fuzzy complementary judgment matrix
Figure BDA0003716463070000032
Taking a threshold value alpha as 0.1; the smaller the threshold value alpha is, the higher the satisfaction degree of the fuzzy judgment matrix A is, and the higher the consistency requirement is.
Preferably, the method for calculating subjective weight comprises: calculating weights of a gap length B1, a gap opening B2, a crack communication rate B3 and natural environment characteristics B4 of the criterion layer by constructing a fuzzy judgment matrix A1 about the gap length B1, the gap opening B2, the crack communication rate B3 and the natural environment characteristics B4 in the criterion layer through expert scoring; respectively constructing a fuzzy judgment matrix A2 of an index layer of a gap length B1, a fuzzy judgment matrix A3 of an index layer of a gap opening B2, a fuzzy judgment matrix A4 of an index layer of a gap connection rate B3 and a fuzzy judgment matrix A5 of an index layer of a natural environment characteristic B4 by expert scoring, calculating weights of a total gap length C1 and an average gap length C2 of evaluation indexes of the index layer according to the fuzzy judgment matrix A2, calculating weights of a maximum gap opening C3 and an average gap opening C4 of the evaluation indexes of the index layer according to the fuzzy judgment matrix A3, calculating weights of a volume density C5 and a linear density C6 of the evaluation indexes of the index layer according to the fuzzy judgment matrix A4, and calculating an annual average C7, an annual rainfall C8, an annual average evaporation capacity C9, an annual average weight C10 and an annual average sunshine C11 of the evaluation indexes of the air temperature layer according to the fuzzy judgment matrix A5; and multiplying the weight of the evaluation index of the index layer and the weight of the corresponding criterion layer to obtain the subjective weight of each evaluation index.
Preferably, the multivariate unstable index method analyzes the variation coefficient among the evaluation indexes in the research area in a statistical measurement mode, and calculates the weight of each evaluation index as a first objective weight according to the variation coefficient through data normalization processing; the improved entropy method determines a second objective weight by normalizing the evaluation index data of each research area and then performing translation processing on the evaluation index.
Preferably, the calculation method of the first objective weight is:
1) normalizing the processed data: so that the data maps between [0,1 ]; since the directionality of the evaluation index is negative, the data is normalized to:
Figure BDA0003716463070000033
wherein X represents the corresponding numerical value of the j study area of the ith evaluation index; x * Representing dimensionless matrix elements obtained after normalization of the negative correlation indexes; max represents the maximum value in the j study region range of the ith evaluation index; min represents the minimum value in the range of the j research area of the ith evaluation index;
2) sample fraction analysis: the evaluation indexes are as follows:
Figure BDA0003716463070000041
wherein, a ij Representing elements of the normalized dimensionless matrix; x ij The occupation importance degree of the j research area of the ith evaluation index is represented;
3) sample mean value
Figure BDA0003716463070000042
Comprises the following steps:
Figure BDA0003716463070000043
wherein x is 1 、x 2 、x nl Is the degree of importance X of the proportion ij Judging the elements with the importance degree ratio; n1 represents the number of study areas;
4) calculate the sample standard deviation as:
Figure BDA0003716463070000044
wherein σ i Represents the standard deviation;
5) calculating the coefficient of variation of each evaluation index as:
Figure BDA0003716463070000045
6) determining a first objective weight W of the evaluation index 1i Comprises the following steps:
Figure BDA0003716463070000046
preferably, the second objective weight is calculated by:
A1. normalization treatment:
Figure BDA0003716463070000047
wherein, X ij A corresponding value of the jth study area representing the ith evaluation index; x * ij Representing dimensionless matrix elements obtained after normalization of the negative correlation indexes; max ij The maximum value in the range of the j research area of the ith evaluation index; min ij A minimum value within the range of the j-th study region representing the ith evaluation index;
A2. evaluation index translation processing: x' ij ＝X * ij +p；
Wherein, p is the translation amplitude of the evaluation index; x' ij Representing new matrix elements obtained by index translation of the dimensionless matrix elements after normalization;
A3. calculating the proportion of the jth sample in the ith evaluation index:
Figure BDA0003716463070000048
where n1 represents the total number of regions of interest;
A4. calculating the information entropy of the ith evaluation index:
Figure BDA0003716463070000051
A5. calculating the information utility value of the ith evaluation index: d i ＝1-e i ；
A6. Calculating a second objective weight of the ith evaluation index as:
Figure BDA0003716463070000052
adopting an equal weight weighted average method to apply subjective weight W i First objective weight W 1i And a second objective weight W 2i And combining to obtain the evaluation index of the development degree of the fracture disease of the rammed earth site, wherein the comprehensive weight is as follows:
Figure BDA0003716463070000053
preferably, the implementation method for obtaining the fissure disease development grade by using the TOPSIS approximate ideal solution in the step S3 includes:
B1. establishing an evaluation matrix D1 of the original data;
B2. normalizing the data of the evaluation matrix D1;
B3. constructing a normalized decision matrix Z, wherein:
Figure BDA0003716463070000054
wherein Z is ij Representing elements in a normalized decision matrix Z;
Figure BDA0003716463070000055
shows the elements of the j th research area of the i evaluation indexes after being normalized；
B4. Constructing a weighted normalized decision matrix V, wherein the element V ij ＝λ i ×Z ij ，λ i Is the integrated weight of the ith evaluation index, Z ij Elements of a normalized decision matrix Z; n represents the number of evaluation indexes;
B5. determining the positive ideal solution and the negative ideal solution as follows:
the positive ideal solution:
Figure BDA0003716463070000056
negative ideal solution:
Figure BDA0003716463070000057
B6. determining the distance between the positive and negative ideal solutions and the fissure development degree of each research area:
j study area crack development degree to positive ideal solution V + Is a distance of
Figure BDA0003716463070000058
Comprises the following steps:
Figure BDA0003716463070000059
the j research area crack development degree reaches the negative ideal solution V - Of (2) is
Figure BDA00037164630700000510
Comprises the following steps:
Figure BDA00037164630700000511
B7. determining the closeness of the crack development degree of each research area to the positive and negative ideal solutions
Figure BDA0003716463070000061
Proximity is the score value D;
B8. when the score value D belongs to (0,0.2), the research area is a non-emergence area; when the score value D belongs to [0.2,0.35], the research area is a low-susceptibility area; when the score value D belongs to (0.35, 0.5), the research area is a medium-easy area, and when the score value D belongs to (0.5,1), the research area is a high-easy area.
Preferably, the BP neural network prediction model is constructed by Matlab programming software, data of total gap length C1, average gap length C2, maximum gap opening C3, average gap opening C4, bulk density C5, linear density C6, annual average temperature C7, annual average rainfall C8, annual average evaporation C9, drought index C10 and annual average sunshine hours C11 of evaluation indexes are used as input layer data, a halved value D is used as output data, an input layer of the BP neural network prediction model comprises 11 neurons, an output layer comprises 1 neuron and a hidden layer comprises 4 neurons, and a levenberg-marquardt algorithm is selected for training of the BP neural network prediction model; data of evaluation indexes of the research area are sample data, training samples are randomly selected to be 70% of the sample data, inspection samples are 15% of the sample data, and prediction samples are 15% of the sample data.
Compared with the prior art, the invention has the beneficial effects that:
1. the problems of artificial subjective deviation, variability of data and discreteness are fully considered, and 3 evaluation-combined weighting methods are adopted to carry out comprehensive weighting on crack disease evaluation indexes.
2. Fully considering the response relation between the development degree of the fracture diseases of the rammed earth site and the characteristics of the natural environment, finding out internal and external factor dominant evaluation factors, constructing a reasonable score value division standard, establishing a score grade system suitable for the development degree of the fracture diseases of the rammed earth site, and performing scientific system evaluation on the rammed earth fracture disease treatment.
3. In the invention, quantitative evaluation, prediction and early warning can be carried out on the fracture diseases of the rammed earth relics in other arid regions by a subjective and objective comprehensive weighting-TOPSIS evaluation method and a BP neural network prediction model combined with machine learning.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a schematic diagram of an evaluation hierarchy model of the FAHP method of the present invention.
FIG. 3 is a block diagram of a BP neural network prediction model according to the present invention.
FIG. 4 is an analysis chart of the evaluation result of the development degree of 7 fissure diseases according to the present invention.
FIG. 5 is an analysis chart of low, medium and high susceptibility regions of the evaluation result of the development degree of 7 fissure diseases.
FIG. 6 is a trend chart of fissure disease characteristic values and natural environment characteristic values of high, medium and low 3 research areas of the invention.
FIG. 7 is a development trend chart of fissure diseases in high, medium and low 3 study areas of the invention.
FIG. 8 is a graph comparing the actual score value and the predicted score value of the training sample of the present invention.
FIG. 9 is a comparison graph of the actual score value and the predicted score value of the BP neural network prediction model of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, in the embodiment, taking a fracture disease of a rammed earth site as an example, by investigating self factors such as fracture disease area, gap length, gap opening, bulk density and linear density, collecting all factors of natural climate where an area is located, analyzing response relation between the self factors of the fracture and the climate factors, quantitatively evaluating the disease development degree grade of the fracture together, and predicting the future fracture development degree, the method comprises the following specific steps:
step S1: selecting factors directly related to crack disease development to establish an evaluation index system, wherein the evaluation indexes comprise: the length of the gap, the opening degree of the gap, the communication rate of the gap and the characteristics of the natural environment.
And selecting a research area and an evaluation index, wherein the evaluation index is a factor directly related to crack disease development. Evaluating indexes, wherein the gap length comprises total gap length and average gap length; the gap opening degree includes: maximum gap opening and average gap opening; the fracture connectivity includes: bulk density, linear density; the natural environment features include: annual average temperature, annual average rainfall, annual average evaporation, drought index, annual average sunshine duration; data for typical drought-type study areas and evaluation indices are shown in table 1.
The crack length refers to the crack length which is generated on a rammed earth site body due to geological structure action (stress release), stress redistribution, fault and joint structure and construction process material, wherein the length of the crack diseases developed on the body per unit area is referred to as the crack length and comprises the total crack length (m) and the average crack length (m). The gap opening refers to the defects of unloading cracks, deformation cracks, structural cracks and construction process cracks generated on a rammed earth relic body due to geological structure action (stress release), stress redistribution, fault and joint structure and construction process materials, and the width of the crack defects on the unit-area body is referred to as the gap opening, and comprises the maximum gap opening (cm) and the average gap opening (cm).
The fracture communication rate refers to the body stability influenced by the fact that the body of the rammed earth site is broken due to the development of unloading fractures, deformation fractures, structural fractures and construction process fracture diseases, other disease development is caused, the development of the existing diseases is aggravated, and the like, and the density generated on the body per unit area is hereinafter referred to as the fracture communication rate and comprises the body density and the linear density. The density of the total gap length is m.m -2 . The linear density is the density of the number of the crack lengths of the crack communication rate generated by the rammed earth site body in unit area, and the unit is a strip.
TABLE 1 typical study area and index of drought rammed earth site
Figure BDA0003716463070000081
The typical evaluation index system for the development degree of crack diseases in drought type research areas is shown in table 2, and the directionality of each evaluation index is judged and explained through empirical summary induction.
TABLE 2 typical evaluation index system for crack disease development degree in drought type research area
Figure BDA0003716463070000082
The development of the gaps is mainly characterized in that the development of the gaps is caused by the conditions of unloading cracks, deformation cracks, structural cracks and construction process cracks generated in a rammed earth site body due to the reasons of geological structure action (stress release), stress redistribution, faults, joint structures, construction process materials and the like, so that the stability of a wall body is influenced, a soft structural surface and a broken block are generated, other secondary diseases are caused to develop in a chain, and the directionality of the evaluation index is negative.
The body density and the linear density are mainly due to the fact that unloading cracks, deformation cracks, structural cracks and construction process crack disease development generate broken blocks on a rammed earth site body, other disease development is caused, existing disease development is aggravated, and the like, so that the stability of the body is affected.
The temperature difference between the early and the late in the northwest arid region is large, the annual average temperature variation range is 1.5-7.7 ℃, and most of the temperature is concentrated at about 4 ℃. The lower the air temperature is, the more serious the fracture dry shrinkage of the rammed earth site is; the crack bursting property is increased along with the rise of the temperature, and the expansion and contraction change is rapid and obvious due to large temperature difference, so that the crack development is influenced, the crack disease development is promoted to be serious, and the directionality of the annual average temperature index is negative.
The annual average rainfall variation range is 125-544 mm, the soil rammed earth belongs to arid regions in northwest and west, and due to the fact that climates in arid regions in northwest and west are extreme, rainfall is mainly concentrated, the walls of rammed earth relics are washed violently, rainwater infiltrates, existing crack diseases are seriously developed, new crack diseases are easily generated, and the directionality of annual average rainfall indexes is negative.
The annual average evaporation capacity changes within a range of 875-2665 mm, due to the fact that the climate is dry in northwest arid areas, the evaporation capacity suddenly increases due to the extremely dry climate after centralized rainfall, the phenomenon of water salt migration in a rammed earth site wall occurs, the easy soluble salt is crystallized and separated out to cause salinization of the wall, the further phenomenon of crystal expansion induces the crack disease development of the wall, and therefore the direction of the annual average evaporation capacity index is negative.
The drought index is the ratio of the annual evaporation capacity to the annual precipitation amount, represents the index of the weather drought degree, has a variation range of 1.62-9.6, and indicates that the drying degree is more serious when the drought index is larger; because the rammed earth site wall is exposed in the field for a long time, chaps are easily formed on the surface of the wall due to the large dry and cold wind sand, and the crack diseases are seriously developed due to the infiltration of centralized rainfall and rainwater, the directionality of the drought index is negative.
The annual average sunshine duration range is 2536-3221 h, the whole sunshine radiation amount in a northwest drought area is large, the daily average radiation time is long, a rammed earth site is irradiated under strong sunshine for a long time, the surface temperature is extremely high, the internal temperature of a wall body is low, heat absorption and heat release generate temperature stress difference, the wall body is easy to cause heat damage and heat damage, and further crack disease development is aggravated, so the directionality of the annual average sunshine duration index is negative.
The elements are positive indexes, so that the rammed earth site has the capability of resisting deterioration, for example, the larger the indexes of compression-resistant, tension-resistant and shear-resistant elements are, the better the mechanical property of the rammed earth site is, the higher the strength is, the stronger the external damage resistance of the wall body is, and the firmer the rammed earth site is. Elements are negative indexes, so that the deterioration of the rammed earth site is aggravated, such as rainfall indexes, daily radiation indexes and the like, and the larger the negative indexes, the stronger the deterioration of the rammed earth site is. The selected evaluation indexes are negative indexes, and the weight of the negative evaluation indexes reflects the influence of the negative evaluation indexes on the development degree of the crack diseases, and accords with the evaluation theme of the crack development degree under the influence of natural environment characteristics. Because the data volume is large and the units are inconsistent, the data characterization features with different attributes (different units) have comparability, dimensionless processing needs to be carried out on the data before evaluation, the positive and negative index calculation formulas in the data normalization processing are different, and the positive and negative indexes need to be distinguished in the selection of the calculation formula.
Step S2: the method comprises the steps of constructing a FAHP model according to an evaluation index system by using a fuzzy analytic hierarchy process to calculate subjective weight, determining first objective weight by using a multivariate unstable index method according to data of evaluation indexes of a research region, calculating second objective weight by using an improved entropy method, and processing the subjective weight, the first objective weight and the second objective weight by equal weight weighted average to obtain comprehensive weight of the evaluation indexes.
Constructing a multivariate unsteady index and improving an entropy method logical relationship model, determining objective weight, and determining index combination weight by using a subjective and objective weighting method.
The subjective weight is determined by constructing an FAHP model comprising a target layer, a criterion layer and an index layer. Constructing an FAHP model, as shown in FIG. 2, according to a target layer: the fissure disease development degree A; a criterion layer: gap length B1, gap opening B2, gap connectivity B3 and environmental factor B4; an index layer: total gap length C1, average gap length C2, maximum gap opening C3, average gap opening C4, bulk density C5, linear density C6, annual average temperature C7, annual average rainfall C8, annual average evaporation C9, drought index C10 and annual average sunshine duration C11.
And determining subjective weight by using a Fuzzy Analytic Hierarchy Process (FAHP), scoring each evaluation index by an expert, constructing a fuzzy complementary judgment matrix, and checking the consistency of the weight values by using the compatibility of the fuzzy complementary judgment matrix. When a complex decision problem is processed, the ambiguity of a judgment matrix is not always considered when the AHP analytic hierarchy process constructs the judgment matrix, the ambiguity is well solved by the ambiguity analytic hierarchy process (FAHP), the AHP analytic hierarchy process is a method combining a fuzzy analytic hierarchy process and an analytic hierarchy process, the basic idea and the steps are basically consistent with the AHP, and fuzzy judgment is introduced into an evaluation system.
1. And establishing a hierarchical analysis structure. As shown in fig. 2.
2. Constructing a fuzzy judgment matrix: comparing and judging two evaluation indexes, quantitatively representing the importance degree of one evaluation index to the other evaluation index, and showing the scale a of fuzzy judgment matrix in Table 3 ij Meaning, get fuzzy judge matrix A ═ a ij ) n×n Wherein a is ii ＝0.5；a ij +a ji ＝1，a ij Is more than or equal to 0. n represents the number of selected evaluation indexes. For example, the criterion layer has four indexes B1, B2, B3 and B4, where n is 4, and the construction matrix is 4 × 4.
TABLE 3 Scale implications of fuzzy decision matrix
Figure BDA0003716463070000101
3. The subjective weight formula for solving the fuzzy judgment matrix A is as follows:
Figure BDA0003716463070000102
Figure BDA0003716463070000103
Figure BDA0003716463070000111
wherein r is i Represents the sum of the ith evaluation index scales, r, of the fuzzy judgment matrix A j Is represented by the formula i The corresponding j columns of elements; r is ij Expression construction to obtain subjective weight W i Of the matrix element(s).
4. And (5) checking the consistency. And constructing a characteristic matrix W of the fuzzy judgment matrix A, and checking the consistency of the fuzzy judgment matrix A and the characteristic matrix W.
(1) Determine the weight vector (W) of matrix A by blurring 1 ,W 2 ,W 3 ..,W i ,...W n ) T The feature matrix W for constructing the fuzzy determination matrix a is (W) ij ) n×n Element W of the feature matrix W ij Comprises the following steps:
Figure BDA0003716463070000112
(2) checking the consistency of the fuzzy judgment matrix A and the feature matrix W, constructing a fuzzy complementary judgment matrix X, and using a formula (5), when alpha is about 0.1, namely the alpha is smaller, indicating that the higher the satisfaction of constructing the fuzzy judgment matrix A and the higher the consistency requirement.
Figure BDA0003716463070000113
And (3) constructing a criterion layer fuzzy judgment matrix A through expert scoring, calculating to obtain a characteristic matrix W and a fuzzy complementary judgment matrix X, and performing calculation weight and consistency test, wherein the calculation weight and the consistency test are shown in Table 4.
Table 4 criteria level constructed matrix and weight consistency check
Figure BDA0003716463070000114
Figure BDA0003716463070000121
Fuzzy judgment matrixes of B1, B2 and B3 standard layers are respectively constructed by expert scoring, corresponding feature matrixes and complementary judgment matrixes are calculated, and calculation weight and consistency check are carried out, as shown in Table 5.
Table 5 matrix and weight consistency check built by index layers B1, B2, B3
Figure BDA0003716463070000122
Figure BDA0003716463070000131
And (3) constructing a fuzzy judgment matrix of a B4 standard layer by expert scoring, calculating a corresponding characteristic matrix and a complementary judgment matrix, and performing calculation weight and consistency test, wherein the calculation weight and the consistency test are shown in table 6.
Table 6 index level B4 constructed matrix and weight consistency check
Figure BDA0003716463070000132
The subjective weights of the evaluation indexes are obtained by multiplying the weights obtained by the criterion layer and the index layer, as shown in table 7.
TABLE 7 FAHP subjective weights
Figure BDA0003716463070000133
Figure BDA0003716463070000141
Calculating a first objective weight by using a multivariate unstable exponential method: the method analyzes the variation coefficient among all evaluation indexes in a research area in a statistical measurement mode, calculates the weight of each evaluation index factor as a first objective weight according to the variation coefficient through data normalization processing, is objective, and focuses on the variability analysis of data. The method comprises the following steps:
1. and normalizing the processed data. In order to remove different dimensions and dimension units among data and enable the data to have comparability with each other, the data after linear transformation can not cause 'failure', so that the data are mapped between [0,1 ]; since all the indexes are negative in directivity, the following formula is used:
Figure BDA0003716463070000142
wherein X represents the corresponding numerical value of the j study area of the i-th evaluation index. And X represents the dimensionless matrix elements obtained after normalization of the negative correlation indexes. max represents the maximum value within the range of the j-th study region of the i-th evaluation index. min represents the minimum value in the range of the j study area of the ith evaluation index.
2. And (4) analyzing the sample ratio. Analyzing the evaluation indexes at the ratio of the total sample number, wherein the higher the ratio is, the higher the severity of the influence of the evaluation indexes on the crack disease development degree of the data is. The formula is as follows:
Figure BDA0003716463070000143
wherein, a ij Representing the elements of the dimensionless matrix after normalization. X ij The occupation importance degree of the j-th study area of the i-th evaluation index is represented.
3.
Figure BDA0003716463070000144
The sample mean reflects the degree of the center surrounded by the fluctuation in the array, and the formula is as follows:
Figure BDA0003716463070000145
wherein x is 1 、x 2 、x nl Is the degree of importance X of the ratio ij Judging the elements with the importance degree ratio; n1 represents the number of regions of interest, and the value in this example is 14.
4. The sample standard deviation was calculated. Deviation of samples from sample mean
Figure BDA0003716463070000146
The standard deviation of the data is measured, and the formula is as follows:
Figure BDA0003716463070000147
wherein σ i The standard deviation is indicated.
5. And calculating the variation coefficient of each evaluation index. The variation coefficient represents the acuity of each evaluation index factor on the development degree of the fracture diseases of the rammed earth site, and the higher the variation coefficient is, the higher the probability that the evaluation index factor influences the development degree of the fracture diseases is. The formula is as follows:
Figure BDA0003716463070000151
6. a first objective weight of the evaluation index is determined. As shown in table 8, in the evaluation index system for the development degree of fissure diseases of the rammed earth ruins, the first objective weight of each evaluation factor is calculated by dividing the variation coefficient of each evaluation index factor by the sum of the variation coefficients of all factors, which is the weight of each index factor for evaluating fissure diseases, and the formula is as follows:
Figure BDA0003716463070000152
TABLE 8 determination of first objective weight by multivariate instability index method
Figure BDA0003716463070000153
And calculating a second objective weight by using an improved entropy value method, wherein entropy is a measure of uncertain information, and reflects the distinguishing degree of the evaluation index from the angle of the index discrete degree. The smaller the entropy value is, the larger the degree of dispersion is, the larger the influence of the evaluation index on the evaluation is, that is, the larger the weight is. After data normalization, carrying out translation processing on the evaluation index to determine a second objective weight, wherein the calculation steps are as follows:
1. and (6) normalization processing. By using
Figure BDA0003716463070000154
Wherein, X ij A corresponding value of the jth study area representing the ith evaluation index; x * ij After normalization to a negative correlation indicatorObtaining dimensionless matrix elements; max ij The maximum value in the range of the j study area of the ith evaluation index; min ij The minimum value in the range of the j-th study region representing the ith evaluation index.
2. And (5) evaluation index translation processing. Some evaluation indexes may have a small value or zero after normalization processing, and the normalized value is subjected to translation processing for calculation uniformity, so that the situation is eliminated.
X′ ij ＝X * ij + p formula (13)
Wherein, p is the translation amplitude of the evaluation index and is 0.1. X' ij And representing new matrix elements obtained by index translation of the dimensionless matrix elements after normalization. Some indexes are 0 or smaller after normalization processing, and the accuracy of entropy values can be influenced in the calculation process, so that unified translation processing is performed.
3. Calculating the proportion of the jth sample in the ith evaluation index:
Figure BDA0003716463070000161
where n1 represents the total number of regions of interest.
4. Calculating the information entropy of the ith evaluation index:
Figure BDA0003716463070000162
wherein, y ij The specific gravity of the evaluation index is represented by a non-dimensionalization of data by the specific gravity method.
5. And calculating the information utility value of the ith evaluation index.
d i ＝1-e i Formula (16)
6. The second objective weight of the jth evaluation index is calculated, as shown in table 9, as follows:
Figure BDA0003716463070000163
TABLE 9 determination of objective weights by entropy method
Figure BDA0003716463070000164
Fuzzy analytic hierarchy process FAHP determines subjective weight, multivariable unsteady index method and improved entropy method respectively determine first objective weight and second objective weight, but subjective weighting of fuzzy analytic hierarchy process FAHP's expert is scored to produce subjective deviation easily, multivariable unsteady index method focuses on data variability analysis, improved entropy method focuses more on data dispersion degree, 3 methods have each advantage and disadvantage, in order to avoid subjective deviation, avoid objective deviation of data quality or integrity, etc., 3 methods are combined by adopting equal weight weighted average method, thus obtaining comprehensive weight of rammed earth site crack disease development degree evaluation index, as shown in Table 10, the following formula is utilized:
Figure BDA0003716463070000165
wherein, W i Denotes the subjective weight, W 1i Representing multivariate unstable exponential weights, W 2i The entropy method weight is expressed, and n represents the number of evaluation indexes.
The advantages of combining weights: firstly, the 3 weight combinations take the advantages of subjective weight and objective weight into consideration, and avoid the defects of the weight combinations; the 3 weight combination methods are weighted average methods, so that the condition of maximum or minimum weight assignment is avoided, and the importance of each evaluation factor is considered; compared with a single weight + TOPSIS evaluation method or other 2 weight + TOPSIS evaluation methods, the 3 weight + TOPSIS evaluation methods are closer to the actual development condition of the fissure disease, the evaluated object has good discrimination, and a certain guiding effect is provided for the later-stage fissure disease protection measures.
TABLE 10 determination of subjective and objective combination weights
Figure BDA0003716463070000171
The comprehensive weight sorting shows that the fracture connectivity influences the fracture disease severity, especially the bulk density, to the highest extent; the degree of influence of the gap opening and the gap length on the development of the crack diseases is important, particularly the total gap length and the maximum gap opening, the cracks can be further developed into gullies due to the infiltration of rainfall, and finally, through surfaces are generated to damage the wall; among the factors influencing natural environment, the temperature index is more important, because the rammed earth site is always in a drought and rainless area, and the influence degree of temperature and solar radiation on the crack disease development of the site is higher. The comprehensive weight after subjective and objective weighting has reasonability, suitability and representativeness, and the development of the fracture diseases of the rammed earth site in the drought research area can be evaluated.
Step S3: evaluating the crack disease development grade by using a TOPSIS approximate ideal solution method: and calculating Euclidean distances between each evaluation scheme and the positive and negative ideal solutions according to the comprehensive weight determined in the step S2, and evaluating the development degree of the fracture diseases of the rammed earth relics of the northwest arid regions through the Euclidean distances to obtain the development grade of the fracture diseases.
Determining Euclidean distances between each evaluation scheme and a positive and negative ideal solution by using a TOPSIS approximate ideal solution, namely judging a reasonable degree according to the distance closest to the ideal degree, evaluating and sequencing the development degrees of the rammed earth relic crack diseases in a plurality of northwest arid regions, and obtaining a disease development grade.
1. An evaluation matrix of the raw data was established using table 1. And establishing an original evaluation matrix D by 14 schemes to be evaluated and 11 evaluation indexes.
2. The data of evaluation matrix D is normalized. The evaluation index is an extremely large and small index, the directionality of the evaluation index is judged to be negative according to the front, and the data is subjected to de-dimensionization processing according to a formula (12).
3. Constructing a normalized decision matrix Z, and utilizing the following formula:
Figure BDA0003716463070000181
wherein Z is ij Representing elements in a normalized decision matrix Z;
Figure BDA0003716463070000182
the element is represented by i evaluation indexes normalized for the jth study region, and nl is represented by the number of study regions.
4. Constructing a weighted normalized decision matrix V, wherein V ij ＝λ j ×Z ij ，λ i As a composite weight of the evaluation index, Z ij N represents the number of evaluation indexes as an element of the normalized decision matrix Z.
5. A positive ideal solution and a negative ideal solution are determined. Element V in weighted normalized decision matrix V ij A larger value indicates a better evaluation scheme j.
The positive ideal solution:
Figure BDA0003716463070000183
negative ideal solution:
Figure BDA0003716463070000184
7. and determining the distance between the positive and negative ideal solutions and the optimal evaluation scheme of the fissure disease development degree of each area to be researched. Each evaluation scheme reaches positive ideal solution V + S distance of + i Sum to negative ideal solution V - S distance of - i Using the following formula:
Figure BDA0003716463070000185
Figure BDA0003716463070000186
8. the closeness of the fissure disease development degree of each study area to the positive and negative ideal solution was determined as shown in table 11. Fissure disease of 14 research areasThe development degree score is close to the positive ideal solution and farthest from the negative ideal solution, so that the score is the best and the best evaluation scheme is obtained. Judging the optimal evaluation scheme, simultaneously considering the distance between the evaluation scheme and the positive and negative ideal solutions, and evaluating the scheme distance S + i The larger the value, the longer the distance S from the optimal solution is - i The larger the value, the farther away from the worst solution is indicated; most understandably, the distance S + i The smaller the value is while the distance S is - i The larger the value. Setting a proximity scale to C i And are ordered according to the magnitude of the relative proximity, C i The larger the value of (b), the higher the overall level. Proximity C i Between 0 and 1, when C i When the performance level is 1, the performance level is highest, and the optimal state is reached; when C is present i When 0, no performance is obtained, and the state is highly disordered. The calculation formula is as follows:
Figure BDA0003716463070000187
TABLE 11 optimal scheme and ideal solution for development degree of fissure diseases in research area
Figure BDA0003716463070000188
Figure BDA0003716463070000191
Specifically, evaluation of development degree of fracture diseases of rammed earth ruins is divided into four evaluation grades: the interval D of the score values and the explanation of the adopted protective measures are shown in Table 12. As can be seen from Table 12, when the score value D belongs to (0,0.2), the study region is a non-volatile region; when the score value D belongs to [0.2,0.35], the research area is a low-susceptibility area; when the evaluation value D belongs to (0.35, 0.5), the research area is a medium easy-to-develop area, when the evaluation value D belongs to (0.5,1), the research area is a high easy-to-develop area, the corresponding relation between four evaluation levels of the fracture disease development degree of the rammed earth ruins and the evaluation value D fully considers the response relation between the natural environmental characteristics and the fracture disease development degree, the internal and external factor dominant evaluation factors are excavated, the optimal evaluation scheme is selected, the division standard of reasonable evaluation values and evaluation levels is constructed, the evaluation level system suitable for the fracture disease development degree of the rammed earth ruins is established, and the scientific system evaluation is carried out on the rammed earth fracture disease treatment.
TABLE 12 Classification standard for development degree of fracture disease of rammed earth site
Figure BDA0003716463070000192
Grading the development degree grade of the rammed earth ruin fissure diseases of the research areas according to a TOPSIS approximation ideal solution, and grading the fissure evaluation grade of each research area of 14 according to a grading value D table 12 as shown in a table 13.
TABLE 13 research regional fissure disease development degree score values and rank ordering
Figure BDA0003716463070000193
Figure BDA0003716463070000201
From Table 14 evaluation values D and evaluation levels of fissure disease development degrees in the study area, it can be seen that (1) FAHP (w) was evaluated by 7 evaluation methods i ) + multivariable instability index (w) 1i ) + entropy method (w) 2i ) Composite weight + TOPSIS,. sup.FAHP (w) i ) + TOPSIS, objective weighting of multivariate instability index (w) 1i ) + TOPSIS, r entropy method (w) 2i )+TOPSIS、⑤FAHP(w i ) + multivariate instability index (w) 1i ) Weight of combination + TOPSIS, sixthly FHAP (w) i ) + entropy method (w) 2i ) The integrated weight + TOPSIS [ ] multivariate unstable index (w [ ]) 1i ) + entropy method (w) 2i ) The score value D calculated by the integrated weight + TOPSIS is compared and analyzed, and different weights or weights are calculated by different methodsThe combination is combined with TOPSIS to calculate the score value to obtain the evaluation grade. As can be seen from the score values D of 7 evaluation methods in the study area of fig. 4, most of the study areas are in the middle susceptibility area and the high susceptibility area, and a small part of the study areas are in the low susceptibility area, so that the low susceptibility area has no study point, which meets the actual situation of the development degree of the fissure diseases, and the score value division and evaluation grades are suitable for the evaluation method. The mode for analyzing 7 evaluation grades of 14 study areas is shown in table 15, and is respectively a middle easy-to-develop area, a low easy-to-develop area, a high easy-to-develop area, a middle easy-to-develop area, a high easy-to-develop area, a low easy-to-develop area, a middle easy-to-develop area and a high easy-to-develop area, and the subjective weight + the first objective weight + the second objective weight in combination with the TOPSIS conforms to the mode of 7 evaluation grades, conforms to the actual development condition of fracture diseases, and has certain utilization value. It can be seen from the 7 evaluation method score value graphs in the research area of fig. 5 that the low incidence area to the high incidence area of the research area are ranked according to the score value of the research area, the curves of the evaluation method combining the subjective weight, the first objective weight and the second objective weight with the TOPSIS are always in the middle positions of all the curves and are relatively stable, and the curves of the other evaluation methods have large volatility and discreteness, so that the evaluation method combining the subjective weight, the first objective weight and the second objective weight with the TOPSIS is suitable for evaluating the development degree of the fissure diseases in the arid area.
Table 14 research area 7 evaluation methods crack disease development degree score D and evaluation grade
Figure BDA0003716463070000202
Connect the table
Figure BDA0003716463070000211
TABLE 15 evaluation rating mode
Figure BDA0003716463070000212
3 areas of spring, fluid and Yonchang in the high-incidence area, the middle-incidence area and the low-incidence area of the evaluation result are selected for research and analysis, and the characteristic values of linear density, maximum gap opening, bulk density, average gap length, annual average temperature and drought index crack disease are compared by using a graph 6 and a graph 7 to discover: the alcoholic spring is more than fluid tension and more than Yongchang, which accords with the development degree of crack diseases under the actual condition; according to the evaluation grade results of the subjective and objective combination weight combined with TOPSIS, the high-susceptibility area (spring), the middle-susceptibility area (fluid stress), and the low-susceptibility area (Yongchang) are similar to the actual crack disease development scale, and the annual average temperature and the drought index are used as environmental factors with larger weight, and the natural environmental factors are explained from the side to play an important response to the crack disease development. The evaluation method combining the subjective weight, the first objective weight and the second objective weight with the TOPSIS can be determined from the quantitative and qualitative aspects, and is suitable for evaluating the crack disease development degree.
By carrying out grade evaluation on the development degree of the fracture diseases of the rammed earth relics of 14 research areas, most of the fracture diseases are in a medium-prone section, no fracture diseases are in a non-prone section, and accordingly the development rate and the communication rate of the fracture diseases of the wall are high, but the danger is controllable, and most of the crack diseases are protected by corresponding reasonable measures. The crack diseases at the Datong and the spring are in a high-incidence area, which indicates that enough attention should be paid, and a scientific and systematic protective measure is taken before the cracks develop into a communication failure surface; the Yongchang and Mengmen fissure diseases are in low incidence sections, which indicates that the fissure disease development rate is slightly high, and corresponding protective measures are taken to prevent the further development of the diseases.
The importance level of each evaluation factor can be seen from subjective and objective comprehensive weight ranking, the fracture connectivity weight ranking is first, and the crack body density of Datong, Jiuquan and Honggu is 0.12m.m -2 、0.11m.m -2 、0.07m.m -2 The reason that the three are in the section with high incidence of fissure diseases is reflected from the side face. Therefore, the actual condition of the development of the rammed earth relic crack diseases in the northwest arid region can be revealed by combining subjective and objective comprehensive weight with the TOPSIS evaluation method, and the main internal cause and external cause influencing the development of the diseases are found, so that the corresponding method is adoptedThe protecting measures of the method are used for scientifically and systematically protecting the site body, and the method has certain accuracy and rationality when being applied to the problem of development and evaluation of fracture diseases of the rammed earth site.
For the classification standard and the evaluation grade of the development degree of the fracture disease of the rammed earth site, the response relation between the natural environment characteristics and the development degree of the fracture disease is fully considered, internal and external factor leading evaluation factors are explored, an optimal evaluation scheme is selected, and a reasonable score value classification standard is constructed. And (3) introducing a discrimination standard to process the crack disease development degree score values of 14 research areas, and judging which area has the most serious crack disease development.
Step S4: and (4) constructing a BP neural network prediction model by using a machine learning BP neural network, predicting the future development trends of the rammed earth relic fracture diseases in the northwest drought regions by using all evaluation indexes of an evaluation index system as input data and the evaluation result of the step S3 as output data, and verifying the prediction results.
And applying a BP neural network machine learning method to the protection of the earthen site fracture diseases by combining the evaluation result of subjective and objective combination weight-TOPSIS, predicting and early warning the future development trend of the rammed earthen site fracture diseases in the northwest arid region, aiming at better predicting the existing fracture development trend and the expected fracture disease occurrence possibility of the wall body, and further providing corresponding preventive protection measures to prevent the earthen site from being attacked in the bud.
Northwest arid region rammed earth ruined site crack disease BP neural network prediction model, as shown in fig. 3, divide into input layer, hidden layer, output layer according to the structure, input layer 1 layer includes 11 neurons, output layer 1 layer includes 1 neuron, and hidden layer 1 layer includes 4 neurons, and hidden layer neuron generally uses:
Figure BDA0003716463070000221
a BP neural network prediction model is constructed by Matlab programming software, a research area in the table 1 is sample data, about 70% of training samples, about 15% of inspection samples and about 15% of prediction samples are randomly selected, and the method is shown in the table 16. Wherein, the evaluation indexes C1-C11 are used as input layer data, and the bisection value D is used asTo output the data, the training algorithm selects the levenberg-marquardt algorithm. The output results of the training, testing and predicting stages of the data samples are shown in table 16, the actual score values and the predicted score values of the training stage, the testing stage and the predicting stage are compared and analyzed, the predicted effect and accuracy are tested, and the output result of the BP neural network prediction model is shown in table 17.
TABLE 16 evaluation grade of evaluation indexes of rammed earth ancient site crack diseases in northwest arid regions
Figure BDA0003716463070000231
TABLE 17 BP neural network prediction model output results
Figure BDA0003716463070000232
The results of the BP neural network prediction model are examined, and it can be seen from fig. 8 that the fitting effect of the regression curve between the actual score D of the training sample and the score T of the BP neural network prediction model is very good, and the correlation coefficient R of the two is 0.99062. As can be seen from fig. 9, the BP neural network prediction was performed on the whole sample, and the actual score D and the predicted score T were fitted, and the correlation coefficient R of the regression curve between the two values was 0.96546.
Further carrying out precision test on the BP neural network prediction model, and introducing Mean Square Error (MSE) and absolute variance (R) 2 ) And Relative Root Mean Square Error (RRMSE) three evaluation methods, carry on the precision test to training stage, test stage and prediction stage, the concrete formula is as follows, the result is shown in Table 18:
Figure BDA0003716463070000241
Figure BDA0003716463070000242
Figure BDA0003716463070000243
table 18 output test results of BP neural network prediction model
Figure BDA0003716463070000244
Wherein D is the actual evaluation value of the subjective and objective combination weight-TOPSIS on the development degree of the crack disease, T is the prediction evaluation value of a BP neural network prediction model, N is the sampling values of the samples in the training, inspection and prediction stages are respectively 10, 2 and 2, the smaller the Mean Square Error (MSE) and the absolute Relative Root Mean Square Error (RRMSE) are, the smaller the absolute variance R is 2 The larger the model, the higher the accuracy of the BP neural network prediction model. As can be seen from Table 18, the correlation coefficients of the actual score value D and the predicted score value T in the training, testing and predicting stages are highly correlated, the MSE and RRMSE values are smaller, and R is smaller 2 The values are all relatively large, approaching 1. The general description shows that the BP neural network prediction model established on the basis of the subjective and objective combination weight-TOPSIS evaluation method is high in accuracy, can be applied to evaluation of the fracture diseases of rammed earth relics in northwest arid regions, and has certain rationality and suitability.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.

Claims (10)

1. A method for evaluating and predicting development degree of fracture diseases of rammed earth site is characterized by comprising the following steps:
step S1: selecting factors directly related to crack disease development to establish an evaluation index system, wherein the evaluation indexes comprise: the length of the gap, the opening degree of the gap, the communication rate of the gap and the characteristics of the natural environment;
step S2: calculating subjective weight according to an evaluation index system by using a fuzzy analytic hierarchy process, calculating first objective weight by using a multivariate unstable index method according to data of the evaluation index system of a research region, calculating second objective weight by using an improved entropy method, and processing the subjective weight, the first objective weight and the second objective weight by equal-weight weighted average to obtain comprehensive weight of the evaluation index;
step S3: evaluating the crack disease development grade by using a TOPSIS approximation ideal solution method: calculating Euclidean distances between each evaluation scheme and the positive and negative ideal solutions according to the comprehensive weight determined in the step S2, and evaluating the development degree of the fracture diseases of the rammed earth relics of the northwest arid regions through the Euclidean distances to obtain the development grade of the fracture diseases;
step S4: and (4) constructing a BP neural network prediction model by using a machine learning BP neural network, predicting the future development trends of the rammed earth relic fracture diseases in the northwest drought regions by using all evaluation indexes of an evaluation index system as input data and the evaluation result of the step S3 as output data, and verifying the prediction results.
2. The method for evaluating and predicting the development degree of the fracture disease of the rammed earth site according to claim 1, wherein the gap length in the evaluation index comprises a total gap length and an average gap length; the gap opening degree comprises a maximum gap opening degree and an average gap opening degree; the fracture connectivity comprises bulk density and linear density; the natural environmental characteristics include the annual average temperature, annual average rainfall, annual average evaporation, drought index and annual average sunshine hours.
3. The method for evaluating and predicting the development degree of the fracture diseases of the rammed earth site according to claim 2, wherein the directionality of each evaluation index is judged to be negative.
4. The method for evaluating and predicting the development degree of the rammed earth site fissure disease according to claim 2 or 3, wherein the implementation method of the fuzzy analytic hierarchy process is as follows:
(1) constructing an FAHP model: the crack disease development degree index layer comprises a target layer, a criterion layer and an index layer, wherein the target layer is the crack disease development degree A; the criterion layer comprises a gap length B1, a gap opening B2, a gap connectivity B3 and an environmental factor B4; the indicator layer comprises a total gap length C1, an average gap length C2, a maximum gap opening C3, an average gap opening C4, a bulk density C5, a linear density C6, an annual average temperature C7, an annual average rainfall C8, an annual average evaporation C9, a drought index C10 and an annual average sunshine duration C11;
(2) constructing fuzzy judgment matrix A (a) by expert scoring ij ) n×n Wherein, the element a ii ＝0.5；a ij +a ji ＝1,a ij Not less than 0; n represents the number of selected evaluation indexes;
(3) calculating subjective weights of all evaluation indexes according to the fuzzy judgment matrix A;
Figure FDA0003716463060000011
Figure FDA0003716463060000021
Figure FDA0003716463060000022
wherein r is i The sum of the evaluation index scales of the ith row, r, representing the fuzzy judgment matrix A j Is represented by the formula i The corresponding j columns of elements; r is ij Expressing constructed subjective weight W i A matrix element of (a);
(4) and (3) consistency test:
by a weight vector (W) 1 ,W 2 ,W 3 ..,W i ,...W n ) T Construct feature matrix W ═ W ij ) n×n Element W of the feature matrix W ij Comprises the following steps:
Figure FDA0003716463060000023
checking the consistency of the fuzzy judgment matrix A and the characteristic matrix W:
construction of fuzzy complementary judgment matrix
Figure FDA0003716463060000024
Taking a threshold value alpha as 0.1; the smaller the threshold value alpha is, the higher the satisfaction degree of the fuzzy judgment matrix A is, and the higher the consistency requirement is.
5. The method for evaluating and predicting the development degree of the rammed earth site fissure disease according to claim 4, wherein the method for calculating the subjective weight comprises the following steps: constructing a fuzzy judgment matrix A1 about the gap length B1, the gap opening B2, the crack communication rate B3 and the natural environment characteristic B4 in a criterion layer through expert scoring, and calculating the weights of the gap length B1, the gap opening B2, the crack communication rate B3 and the natural environment characteristic B4 of the criterion layer; respectively constructing a fuzzy judgment matrix A2 of an index layer of a gap length B1, a fuzzy judgment matrix A3 of an index layer of a gap opening B2, a fuzzy judgment matrix A4 of an index layer of a gap communication rate B3 and a fuzzy judgment matrix A5 of an index layer of a natural environment characteristic B4 by expert scoring, calculating weights of a total gap length C1 and an average gap length C2 of evaluation indexes of the index layer according to the fuzzy judgment matrix A2, calculating weights of a maximum gap opening C3 and an average gap opening C4 of the evaluation indexes of the index layer according to the fuzzy judgment matrix A3, calculating weights of a volume density C5 and a linear density C6 of the evaluation indexes of the index layer according to the fuzzy judgment matrix A4, and calculating weights of an average air temperature C7, an average rainfall C8, an average evaporation amount C9, an average weather number C10 and an average sunshine number C11 of the evaluation indexes of the index layer according to the fuzzy judgment matrix A5; and multiplying the weight of the evaluation index of the index layer and the weight of the corresponding criterion layer to obtain the subjective weight of each evaluation index.
6. The method for evaluating and predicting the development degree of the fracture diseases of the rammed earth site according to claim 1 or 5, wherein the multivariate unsteady index method analyzes the variation coefficient among the evaluation indexes in the research area in a statistical measurement mode, and calculates the weight of each evaluation index as a first objective weight according to the variation coefficient through data normalization processing; the improved entropy method determines a second objective weight by normalizing the evaluation index data of each research area and then performing translation processing on the evaluation index.
7. The method for evaluating and predicting the development degree of the rammed earth ruins fissure diseases according to claim 6, wherein the first objective weight is calculated by:
1) normalizing the processed data: so that the data maps between [0,1 ]; since the directionality of the evaluation index is negative, the data is normalized to:
Figure FDA0003716463060000031
wherein X represents the corresponding numerical value of the j study area of the ith evaluation index; x * Expressing dimensionless matrix elements obtained after normalization of the negative correlation indexes; max represents the maximum value within the range of the j study region of the ith evaluation index; min represents the minimum value in the jth research area range of the ith evaluation index;
2) sample fraction analysis: the evaluation indexes are as follows:
Figure FDA0003716463060000032
wherein, a ij Representing elements of the normalized dimensionless matrix; x ij The occupation importance degree of the j research area of the ith evaluation index is represented;
3) sample mean value
Figure FDA0003716463060000033
Comprises the following steps:
Figure FDA0003716463060000034
wherein x is 1 、x 2 、x nl Is the degree of importance X of the ratio ij Judging the elements with the importance degree ratio; n1 represents the number of study areas;
4) calculate the sample standard deviation as:
Figure FDA0003716463060000035
wherein σ i Represents the standard deviation;
5) calculating the coefficient of variation of each evaluation index as:
Figure FDA0003716463060000036
6) determining a first objective weight W of the evaluation index 1i Comprises the following steps:
Figure FDA0003716463060000037
8. the method for evaluating and predicting the development degree of the rammed earth ruin fissure disease according to claim 7, wherein the second objective weight is calculated by:
A1. normalization treatment:
Figure FDA0003716463060000038
wherein, X ij A corresponding value of the jth study area representing the ith evaluation index; x * ij Expressing dimensionless matrix elements obtained after normalization of the negative correlation indexes; max ij The maximum value in the range of the j research area of the ith evaluation index; min ij A minimum value within the range of the j-th study region representing the ith evaluation index;
A2. evaluation index translation processing: x i ′ j ＝X * ij +p；
Wherein, p is the translation amplitude of the evaluation index; x i ′ j Representing new matrix elements obtained by index translation of the dimensionless matrix elements after normalization;
A3. calculating the proportion of the jth sample in the ith evaluation index:
Figure FDA0003716463060000041
where n1 represents the total number of regions of interest;
A4. calculating the information entropy of the ith evaluation index:
Figure FDA0003716463060000042
A5. calculating the information utility value of the ith evaluation index: d i ＝1-e i ；
A6. Calculating a second objective weight of the ith evaluation index as:
Figure FDA0003716463060000043
adopting an equal weight weighted average method to apply subjective weight W i First objective weight W 1i And a second objective weight W 2i And combining to obtain the evaluation index of the development degree of the fracture disease of the rammed earth site, wherein the comprehensive weight is as follows:
Figure FDA0003716463060000044
9. the method for evaluating and predicting the development degree of the fracture diseases of the rammed earth ruins according to claim 2, 3, 5, 7 or 8, wherein the method for obtaining the development grade of the fracture diseases by approaching an ideal solution to TOPSIS in the step S3 comprises the following steps:
B1. establishing an evaluation matrix D1 of the original data;
B2. normalizing the data of the evaluation matrix D1;
B3. constructing a normalized decision matrix Z, wherein:
Figure FDA0003716463060000045
wherein Z is ij Representing elements in a normalized decision matrix Z;
Figure FDA0003716463060000046
representing the normalized elements of the j research area of the i evaluation indexes;
B4. constructing a weighted normalized decision matrix V, wherein the element V ij ＝λ i ×Z ij ，λ i Is the integrated weight of the ith evaluation index, Z ij Elements of a normalized decision matrix Z; n represents the number of evaluation indexes;
B5. determining the positive ideal solution and the negative ideal solution as follows:
the positive ideal solution:
Figure FDA0003716463060000051
negative ideal solution:
Figure FDA0003716463060000052
B6. determining the distance between the positive and negative ideal solutions and the fissure development degree of each research area:
j study area crack development degree to positive ideal solution V + Is a distance of
Figure FDA0003716463060000053
Comprises the following steps:
Figure FDA0003716463060000054
the j research area crack development degree reaches the negative ideal solution V - Is a distance of
Figure FDA0003716463060000055
Comprises the following steps:
Figure FDA0003716463060000056
B7. determining the closeness of the crack development degree of each research area to the positive and negative ideal solutions
Figure FDA0003716463060000057
Proximity is the score value D;
B8. when the score value D belongs to (0,0.2), the research area is a non-emergence area; when the score value D belongs to [0.2,0.35], the research area is a low-susceptibility area; when the score value D belongs to (0.35, 0.5), the research area is a medium-easy area, and when the score value D belongs to (0.5,1), the research area is a high-easy area.
10. The method for evaluating and predicting the development degree of the rammed earth relic fissure disease according to claim 9, wherein a BP neural network prediction model is constructed by Matlab programming software, data of total gap length C1, average gap length C2, maximum gap opening C3, average gap opening C4, bulk density C5, linear density C6, annual average temperature C7, annual average rainfall C8, annual average evaporation C9, drought index C10 and annual average sunshine duration C11 of evaluation indexes are used as input layer data, a bisection value D is used as output data, the input layer of the BP neural network prediction model comprises 11 neurons, the output layer comprises 1 neuron and the hidden layer comprises 4 neurons, and a levenberg-marquardt algorithm is selected for training of the BP neural network prediction model; and taking the data of the evaluation indexes of the research area as sample data, randomly selecting a training sample as 70% of the sample data, checking the sample as 15% of the sample data, and predicting the sample as 15% of the sample data.
CN202210744243.0A 2022-06-27 2022-06-27 Evaluation and prediction method for development degree of fracture disease of rammed earth site Active CN114997514B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210744243.0A CN114997514B (en) 2022-06-27 2022-06-27 Evaluation and prediction method for development degree of fracture disease of rammed earth site

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210744243.0A CN114997514B (en) 2022-06-27 2022-06-27 Evaluation and prediction method for development degree of fracture disease of rammed earth site

Publications (2)

Publication Number Publication Date
CN114997514A true CN114997514A (en) 2022-09-02
CN114997514B CN114997514B (en) 2023-02-07

Family

ID=83036099

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210744243.0A Active CN114997514B (en) 2022-06-27 2022-06-27 Evaluation and prediction method for development degree of fracture disease of rammed earth site

Country Status (1)

Country Link
CN (1) CN114997514B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116957413A (en) * 2023-08-01 2023-10-27 四川省国土科学技术研究院(四川省卫星应用技术中心) Method for decomposing newly-increased construction land indexes
CN117764454A (en) * 2023-12-27 2024-03-26 兰州理工大学 Evaluation method for development degree of flaky stripping of wall site in open great wall of Hexi corridor

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014107303A1 (en) * 2013-01-04 2014-07-10 Siemens Corporation Probabilistic modeling and sizing of embedded flaws in nondestructive inspections for fatigue damage prognostics and structural integrity assessment
CN114444319A (en) * 2022-02-08 2022-05-06 青海省水文地质工程地质环境地质调查院 Method for evaluating risk of loess underground disease body
CN114548725A (en) * 2022-02-15 2022-05-27 大连理工大学 Deep foundation pit stability evaluation method based on entropy weight-level analysis fuzzy comprehensive evaluation method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014107303A1 (en) * 2013-01-04 2014-07-10 Siemens Corporation Probabilistic modeling and sizing of embedded flaws in nondestructive inspections for fatigue damage prognostics and structural integrity assessment
CN114444319A (en) * 2022-02-08 2022-05-06 青海省水文地质工程地质环境地质调查院 Method for evaluating risk of loess underground disease body
CN114548725A (en) * 2022-02-15 2022-05-27 大连理工大学 Deep foundation pit stability evaluation method based on entropy weight-level analysis fuzzy comprehensive evaluation method

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
俞莉等: "嘉峪关典型土遗址裂缝变形气温响应特征研究", 《地震工程学报》 *
崔 凯 等: "干旱区线性夯土遗址径流型冲沟影响因素", 《兰 州 理 工 大 学 学 报》 *
李隘优: "基于KCPSO算法对闽西地区崩塌地判释", 《江南大学学报(自然科学版)》 *
毕鸿基 等: "基于三种多变量不安定指数分析模型的", 《中国地质灾害与防治学报》 *
陈文迅: "基于土遗址监测数据的模糊评估应用研究", 《科技展望》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116957413A (en) * 2023-08-01 2023-10-27 四川省国土科学技术研究院(四川省卫星应用技术中心) Method for decomposing newly-increased construction land indexes
CN117764454A (en) * 2023-12-27 2024-03-26 兰州理工大学 Evaluation method for development degree of flaky stripping of wall site in open great wall of Hexi corridor

Also Published As

Publication number Publication date
CN114997514B (en) 2023-02-07

Similar Documents

Publication Publication Date Title
CN114997514B (en) Evaluation and prediction method for development degree of fracture disease of rammed earth site
Willems A time series tool to support the multi-criteria performance evaluation of rainfall-runoff models
CN106599571B (en) Watershed hydrological model stage calibration method considering both flow and evaporation
Elshorbagy et al. Performance evaluation of artificial neural networks for runoff prediction
Thube Artificial neural network (ANN) based pavement deterioration models for low volume roads in India
CN110346844A (en) Quantitative Precipitation estimating and measuring method of the NRIET based on cloud classification and machine learning
CN113496359B (en) Multi-combination subjective and objective uniform optimization empowerment risk evaluation method
Obled et al. Recent developments of avalanche forecasting by discriminant analysis techniques: a methodological review and some applications to the Parsenn area (Davos, Switzerland)
CN113033997A (en) Urban water quality grade determination method, device and medium based on improved set pair analysis
CN113128893A (en) Regional drought prevention and disaster reduction assessment method and device
CN115270266B (en) Slope monitoring state risk judging method based on improved analytic hierarchy process
CN116167549A (en) Water resource bearing capacity evaluation method
CN113869671B (en) Safety evaluation method suitable for power transmission towers in landslide areas under multiple working conditions
CN115948964A (en) Road flatness prediction method based on GA-BP neural network
CN109657287B (en) Hydrological model precision identification method based on comprehensive scoring method
CN107194561A (en) Method based on Information Entropy and grey GM11 model prediction real estate risks
CN111582634B (en) Multi-factor safety grading method and system for underground large-space construction
CN116681205A (en) Method for evaluating and predicting development degree of rammed earth site gully disease
CN112861418A (en) Short-term icing thickness prediction method for stay cable based on GA-WOA-GRNN network
CN112488463A (en) Landslide evaluation method based on combined weighting method and good-bad solution distance method
CN109270010A (en) A kind of plant regulation of absorbing dust capability detection method based on random forests algorithm
CN114118688A (en) Power grid engineering cost risk early warning method based on sequence relation analysis
CN115544891A (en) Method and system for predicting height of original pressure-bearing height guide belt
CN110990916B (en) Integration method for evaluating and predicting long-term operation safety of dam by considering hysteresis effect
CN114021905A (en) Credit risk evaluation method for small and medium-sized enterprises

Legal Events

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