WO2019149147A1 - 一种基于煤炭资源开发的生态地质环境类型划分方法 - Google Patents

一种基于煤炭资源开发的生态地质环境类型划分方法 Download PDF

Info

Publication number
WO2019149147A1
WO2019149147A1 PCT/CN2019/073160 CN2019073160W WO2019149147A1 WO 2019149147 A1 WO2019149147 A1 WO 2019149147A1 CN 2019073160 W CN2019073160 W CN 2019073160W WO 2019149147 A1 WO2019149147 A1 WO 2019149147A1
Authority
WO
WIPO (PCT)
Prior art keywords
ecological
data
geological environment
index
fuzzy
Prior art date
Application number
PCT/CN2019/073160
Other languages
English (en)
French (fr)
Inventor
李文平
杨志
王启庆
乔伟
李小琴
Original Assignee
中国矿业大学
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 中国矿业大学 filed Critical 中国矿业大学
Priority to US16/639,138 priority Critical patent/US20200234170A1/en
Priority to AU2019214077A priority patent/AU2019214077B2/en
Publication of WO2019149147A1 publication Critical patent/WO2019149147A1/zh
Priority to ZA2020/00342A priority patent/ZA202000342B/en

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
    • G06Q10/06—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
    • 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
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
    • G06N7/023—Learning or tuning the parameters of a fuzzy system
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Definitions

  • the invention relates to the field of ecological geological environment protection, in particular to a method for classifying ecological geological environment types based on coal resource development.
  • Coal resources are an important natural resource. They are also the basic source of energy and materials for many industries such as steel, cement and chemicals. They account for more than 70% of China's one-time energy consumption structure. With the gradual depletion of coal resources in eastern China, the focus of the development of the coal industry has rapidly shifted to the western region of China. In the next 10 years, coal production in five western provinces including Shanxi, Shaanxi, Inner Mongolia, Ningxia and Xinjiang will exceed 70% of China's total coal production. However, the average annual rainfall in western China is sparse and the evaporation is huge. It belongs to arid-semi-arid regions, with poor water resources and fragile ecological environment.
  • the ecological geological environment is to study the relationship between geological environment and ecology, including the impact of various geological bodies, geological processes, environmental changes, biological effects and biological activities (mainly human activities) on the geological environment.
  • large-scale coal mining activities will have a major impact on the occurrence of water resources in aquifers. Due to surface cracking and subsidence caused by coal mining, serious water leakage may occur, resulting in a significant drop in diving water levels. The decline in the dive level will further affect the surface vegetation, as plants will not be able to absorb the moisture of the aquifer. As a result, if the diving water level continues to decline, the ecological geological environment may deteriorate.
  • the factors affecting the ecological geological environment are complicated, and the various factors are related to each other and affect each other.
  • the overall influence of each factor on the ecological geological environment is different.
  • most factors affecting the ecological geological environment have data ambiguity and fuzzy evaluation criteria. Sex and other characteristics. Therefore, using the theory and method of fuzzy mathematics, using ArcGIS and MATLAB as the computing platform, the hierarchical structure model of the type of ecological geological environment is constructed to classify the ecological geological environment of the arid and semi-arid ecologically fragile areas in the west.
  • the calculation of the weighting coefficients generated by the division results is: objective method and subjective method.
  • the objective methods mainly include the following: entropy weight method, principal component analysis method, mean square error method, etc.; subjective methods mainly include the following: direct scoring method, expert scoring method, analytic hierarchy process, ring ratio scoring method, contrast sorting method, etc. .
  • AHP analytic hierarchy process
  • Fuzzy Delphi AHP is a comprehensive analytic hierarchy process, fuzzy evaluation principle and Delphi group decision-making method. It is a decision-making method that enables decision makers to fully participate in weight determination and analysis, and forms an interactive weight vector decision analysis process. Finally, the decision-making weight vector of the decision maker is satisfied. This decision-making interaction process can be carried out under any single criterion of the hierarchy, and this method allows the decision-maker to make unreasonable judgments, and the judgment matrix does not need consistency check. . Therefore, it is necessary to carry out more accurate quantitative evaluation for the classification of indicators, in order to provide a more accurate scientific basis for the rational division of the ecological geological environment.
  • clustering is to divide the data into a specified number of clusters in a certain way, and finally make the elements in the same cluster class as small as possible, different clusters. The dissimilarity between the elements is as large as possible.
  • clustering methods such as statistics, image processing, etc.
  • These clustering algorithms mainly include model-based clustering algorithms, partitioned clustering algorithms, hierarchical clustering algorithms, etc. Algorithms have their own characteristics. The diversification and complexity of engineering problems determine that no algorithm can solve all problems.
  • the clustering method of functions has been further developed and popularized.
  • Fuzzy clustering belongs to this kind of algorithm. It is based on K-means clustering and introduces fuzzy theory. In the fuzzy C-means clustering algorithm, each attribute is added. The weight of the weighted fuzzy C-means clustering algorithm is formed, which is more scientific and accurate.
  • the present invention aims to provide a method for classifying ecological geological environment types based on coal resource development, to protect valuable aquifer water resources, maintain a fragile ecological geological environment, and select for mining area planning and mining methods.
  • the basis for the extraction of work is of great significance for the realization of ecological and environmental protection in arid-semi-arid areas.
  • a method for classifying ecological geological environment types based on coal resource development comprising the following steps:
  • Step 1 Obtain regional ecological, hydrological and geological data
  • Step 2 Establish a hierarchical structure model for the classification of ecological geological environment types
  • Step 3 According to the data obtained in step one and the hierarchical structure model established in step two, select relevant factors affecting the ecological geological environment as the index, and obtain all the types of participation in the hierarchical structure model of the ecological geological environment classification in the area to be divided. Ecological, hydrological and geological data corresponding to the indicators;
  • Step 4 Convert the relevant data of the obtained index obtained in step 3 into floating point data
  • Step 5 using a normalization function to perform dimensionless processing on the floating point data in step 4;
  • Step 6 Analyze and calculate the weight coefficients of each index by using the fuzzy Delphi analytic hierarchy process
  • Step 7 Combining the dimensionless data in step 5 with the weight coefficients described in step 6, and using the weighted fuzzy C-means clustering method to perform superimposed clustering calculation on the influencing factors;
  • Step 8 According to the clustering calculation result in step 7 and the ecological, hydrological and geological characteristics of each index, analyze and discriminate, determine different types of ecological geological environment, and obtain a map of the type of ecological geological environment.
  • the hierarchical structure model in the second step includes a target layer and an indicator layer, wherein the target layer is a total target of the ecological geological environment type division, and the indicator layer is an indicator for all participation types.
  • f i is the i-th dimensionless processed data in each partitioning index
  • a and b are the lower and upper limits of the normalized range, respectively, and there are n data in each partitioning index
  • x i is The raw data before the i-th dimensionless in each partitioning index
  • max(x i ) and min(x i ) are the maximum and minimum values of the raw data of each partitioning index.
  • step 6 is specifically: using fuzzy Delphi analytic hierarchy process, through consulting with experts on ecological, hydrological, and geological aspects, combined with the TLSaaty1-9 scale method, the overall importance of the relative ecological geological environment for each index. Scoring, establishing a fuzzy judgment matrix of the group, determining the group fuzzy weight vector, and finally calculating the weight coefficient of each division index by the single criterion weight analysis.
  • step 6 specifically includes the following steps:
  • Step 6.1 There are m division indicators to be judged and n related experts in the relevant fields.
  • the relevant experts in the relevant fields are relatively important to the target level in the indicator layer under a certain criterion.
  • Step 6.2 Construct a group of two-two fuzzy judgment matrix C that uses the triangular fuzzy number to represent the consulting experts in all relevant fields:
  • min(B ij ⁇ k ) is the minimum value of the scores of the consulting experts in all relevant fields
  • geomean(B ij ⁇ k ) is all related fields.
  • the geometric mean of the scores of the consulting experts, max(B ij ⁇ k ) is the maximum value of the scores of the consulting experts in all relevant fields;
  • Step 6.3 For each of all the partitioning indicators, the index F i is calculated, and the process calculation vector r i involved in the process of calculating the group fuzzy weight vector is:
  • a 1 , a 2 , a 3 and b 1 , b 2 , b 3 are respectively any two real numbers.
  • Step 6.4 The group fuzzy weight vector for any one of the partitioning indicators F i is:
  • step seven includes the following steps:
  • Step 7.2 calculating a weighted Euclidean distance d w-ij of the data point and the cluster center in each sample;
  • Step 7.3 calculating a membership degree of each sample within the data relative to each cluster class
  • Step 7.4 calculating a new cluster center matrix P
  • Step 7.5 repeat steps 7.2, 7.3, and 7.4.
  • the t-th iteration calculates a new cluster center matrix P (t) and the t+1th iteration calculates a new one.
  • the difference between the cluster center matrix P (t+1 ) is less than the given iteration termination threshold ⁇ , ie
  • step 7.2 includes the following steps:
  • the weight coefficient W i needs to satisfy the following formula:
  • step 7.3 includes the following steps:
  • Step 7.3.1 The new evaluation of the clustering performance error squared criterion function, that is, the new weighted objective function is:
  • Step 7.2.2 Using the Lagrangian multiplier method, the new Lagrangian function constructed is:
  • U is the fuzzy weighted partition matrix
  • P is the new cluster center matrix
  • u ij is the cluster membership degree of the jth data point to the cluster class G i
  • c i is the clustering center of the corresponding fuzzy vector set
  • ⁇ j is n constrained Lagrangian multipliers
  • Step 7.3.3 The attribution of a data point to a cluster class is determined according to the principle of maximum membership degree, and the data point belongs to the cluster class with the largest degree of membership, and the expression is:
  • the invention is based on the method of dividing the ecological geological environment type of coal resource development, which is to divide different types of ecological geological environment into arid and semi-arid areas with abundant coal resources and fragile ecological geological environment in northwest China, and draw out types of ecological geological environment. Partition map. In order to protect valuable aquifer water resources, maintain the original fragile ecological geological environment, and extract the basis for mining area planning and mining methods, it is of great significance to achieve ecological and environmental protection in arid-semi-arid areas.
  • the invention can quickly and effectively classify different types of ecological geological environment according to the existing ecological hydrogeological data, determine the ecological geological characteristics of different types of ecological geological environment and their sensitivity to coal resource exploitation activities, thereby protecting
  • the pleasing diving resources in arid and semi-arid areas provide a scientific basis for maintaining a fragile ecological environment while selecting appropriate coal mining methods to realize the development and utilization of coal resources. It is of great significance for water conservation and coal mining in the fragile areas of the northwest ecological environment.
  • the invention combines the different geological environment and the ecological environment in the mining area, and distinguishes different types of ecological geological environment, so as to provide specific coal resource mining activities according to different ecological geological environment conditions, so as to achieve To realize the development of coal resources, we can reduce the damage to the surface ecological geological environment as much as possible, and lay the necessary foundation for the restoration and control of the surface ecological geological environment of the mining area, and realize the coordinated development of coal resource development and ecological geological environment protection. .
  • Figure 2 is a hierarchical structure model of the classification of the ecological geological environment to be divided into regions;
  • Figure 3 Thematic map of vegetation index in the type of ecological geological environment
  • Figure 4 is a thematic map of the surface elevation in the type of ecological geological environment
  • Figure 5 is a thematic map of the terrain slope in the type of ecological geological environment
  • Figure 6 is a thematic map of surface lithology in the type of ecological geological environment
  • Figure 7 is a thematic map of landform types in the type of ecological geological environment
  • Figure 8 is a thematic map of the degree of influence of river network in the ecological geological environment
  • Figure 9 is a thematic map of vegetation index normalization in the type of ecological geological environment.
  • Figure 10 is a thematic map of surface elevation normalization in the type of ecological geological environment
  • Figure 11 is a thematic map of terrain slope normalization in the type of ecological geological environment
  • Figure 12 is a thematic map of surface lithology normalization in the type of ecological geological environment
  • Figure 13 is a thematic map of geomorphology normalization in the type of ecological geological environment
  • Figure 14 is a thematic map of the degree of influence of the river network in the ecological geological environment
  • Figure 15 is a zoning map of the type of ecological geological environment.
  • FIG. 1 A first figure.
  • a method for dividing the type of ecological geological environment based on coal resource development includes the following steps:
  • the target layer is the overall target of the classification of the ecological geological environment, and all the indicators of the participation type are used as the indicator layer;
  • step 3 According to the data obtained in step 1 and the hierarchical structure model established in step 2, select the relevant factors affecting the ecological geological environment as the index, and obtain the indicators of all the participating types in the hierarchical structure model of the ecological geological environment classification in the area to be divided. Corresponding ecological, hydrological and geological data;
  • step 3 The relevant data of the index obtained in step 3 is processed in ArcGIS into floating point type .flt data that can be read by MATLAB software;
  • fuzzy Delphi analytic hierarchy process through the consultation of experts in ecological, hydrological and geological aspects, combined with the TLSaaty1-9 scale method, the overall importance of the relative ecological geological environment is scored for each index, and the fuzzy of the group is established. Judging the matrix, determining the group fuzzy weight vector, and finally calculating the weight coefficient of each dividing indicator by the single criterion weight analysis;
  • the clustering result stored in the text file (.txt) calculated in step 7 is opened in the ArcGIS software, combined with the clustering center value of each factor calculated in step 7, and according to each index
  • the ecological, hydrological and geological characteristics are analyzed and discriminated, the types of different ecological geological environments are determined, and the ecological geological environment type map is obtained.
  • Step 1 of the embodiment is specifically: extracting the vegetation index (NDVI) by remote sensing image, and selecting the image for Landsat8 satellite remote sensing data, according to the scope of the research area, selecting two data images through mosaic, when the satellite transits data collection, the research area The weather is fine, the sky does not cover a large area of the cloud, so the two pictures have a low cloud volume, high image quality, clear images, and a resolution of 30 meters.
  • the ArcGIS10.5 spatial analysis function is used to extract the elevation and slope of the study area.
  • the eco-geological environment type is divided into a target layer, a vegetation normalization index (F1), a surface elevation (F2), a terrain slope (F3), a surface lithology (F4), a landform type (F5),
  • the river system (F6) is used as a dividing indicator to form a hierarchical structure model of the ecological geological environment to be divided, as shown in Figure 2.
  • step 2 the ecological, hydrological, and geological data corresponding to the six divided indicators are extracted, and step 3 is continued.
  • step 3 the ecological, hydrological and geological data of the area to be divided are imported into ArcGIS, and the single factor layer of each index is established, as shown in Fig. 3-8.
  • step 4 the data in the shp format of the evaluation factor is converted into the grid data in the grid format in ArcGIS 10.5, and then converted into ftf.flt floating point type data of MATLAB, the conversion result contains two files, one is hdr
  • the header file of the extension contains information such as the x, y coordinates, the grid size, the number of rows and columns of the raster in the lower left corner of the raster, and the other is the floating point data of the flt extension.
  • step 5 in MATLAB, the read_AGaschdr function is used to read the indicators of the area to be divided, and the normalization function is used to normalize the factors to the dimension, and the normalized components are normalized as shown in Fig. 9-14.
  • f i is the i-th dimensionless processed data in each partitioning index
  • a and b are the lower and upper limits of the normalized range, respectively
  • x i is the i-th dimensionless in each partitioning index
  • max(x i ) and min(x i ) are the maximum and minimum values of the raw data of each partition indicator.
  • Step 6 includes the following steps:
  • step 7 the clustering function custom_fcm is improved, the attribute weight W i is added in the process of calculating the Euclidean distance, the clustering parameter is set, and the above normalization factor is clustered.
  • the result is post-processed with the fprintf function.
  • the information parameters such as the x, y coordinates and the number of rows and columns of the lower left corner of the raster obtained by reading the file are first rewritten into the header file, and then the calculated grid is output.
  • the invention relates to a method for dividing an ecological geological environment type based on coal resource development, which is to divide different types of ecological geological environment into arid and semi-arid regions with abundant coal resources and fragile ecological geological environment in northwest China, and draw out Zoning map of ecological geological environment types.
  • the method of the invention firstly collects and organizes many factors affecting the ecological geological environment on the basis of the investigation of regional ecological, hydrological, geological and other related materials, and uses the normalization function to dimensionless various factors; secondly, the use of fuzzy Delphi analytic hierarchy process is used to determine the weighting coefficient of each factor on the ecological geological environment.
  • the weighted fuzzy C-means clustering method is used to superimpose and cluster the influencing factors to obtain three different types. Clustering results; Finally, the clustering results were processed by ArcGIS, and the different types of ecological geological environment were determined by clustering central value analysis of each factor.
  • the invention can quickly and effectively classify different types of ecological geological environment according to the existing ecological hydrogeological data, determine the ecological geological characteristics of different types of ecological geological environment and their sensitivity to coal resource exploitation activities, thereby protecting The pleasing diving resources in arid and semi-arid areas provide a scientific basis for maintaining a fragile ecological environment while selecting appropriate coal mining methods to realize the development and utilization of coal resources. It is of great significance for water conservation and coal mining in the fragile areas of the northwest ecological environment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • Algebra (AREA)
  • Operations Research (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Fuzzy Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Databases & Information Systems (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)

Abstract

一种基于煤炭资源开发的生态地质环境类型划分方法，属于生态地质环境保护领域，解决现有技术中缺少在实施采煤活动前，对将开采区域内地表不同的地质环境与生态环境相结合考虑。本发明在对区域生态、水文、地质等相关资料调查的基础之上，将模糊德尔菲层次分析法和加权模糊C均值聚类法结合，判断确定不同的生态地质环境类型。本发明根据现有的生态水文地质资料，能够快速有效地划分出不同的生态地质环境类型，确定生态地质特征及其对煤炭资源开采活动的敏感性，为保护类似干旱半干旱地区珍惜的潜水资源，维护好脆弱的生态环境同时选择恰当的采煤方法实现煤炭资源的开发利用提供科学依据，对西北生态环境脆弱区保水采煤具有重要意义。

Description

一种基于煤炭资源开发的生态地质环境类型划分方法 技术领域
本发明涉及生态地质环境保护领域，尤其是涉及一种基于煤炭资源开发的生态地质环境类型划分方法。
背景技术
煤炭资源是一种重要的自然资源，同时也是许多工业诸如钢铁、水泥、化工等能源及材料的基础来源，占据中国一次性能源消费结构的比重超过70％。随着中国东部地区煤炭资源逐渐枯竭，煤炭工业发展的重点迅速向中国西部地区转移。在未来10年，中国西部五省包括山西、陕西、内蒙、宁夏、新疆的煤炭产量将超过中国煤炭总产量的70％。然而，中国西部地区多年平均降雨量稀少，蒸发量巨大，属于干旱-半干旱地区，水资源贫乏，生态环境脆弱。且近几年来，随着该区煤炭资源大规模开采，尤其埋深较浅的首采煤层的开采，带来了一系列的矿山环境地质问题，地下水位下降格外凸显，产生了井泉干涸，地表径流量减少，河流两岸的流域生态严重破坏等直接后果，致使生态地质环境质量一直下降。尤其近些来，生态地质环境问题引起了人民和国家高度重视，为此，在2014年国家“973”计划项目指南中将“我国西部生态脆弱区煤炭科学规模开发与水资源保护”列入了“能源科学领域”资助研究方向之一。
生态地质环境是研究地质环境与生态的关系，包括各种地质体、地质过程、环境变化、生物效应和生物活动(主要是人类活动)对地质环境的影响。在中国西部干旱半干旱生态脆弱区，大规模煤炭开采活动将对潜水含水层水资源的赋存产生重大影响，由于采煤引起地表开裂和沉陷，可能发生严重的漏水，导致潜水水位大幅下降。潜水水位的下降将进一步影响地表植被，因为植物将无法吸收潜水含水层的水分。结果，如果潜水水位持续下降，生态地质环境可能恶化。因此，地表径流和松散砂层潜水是连接地质环境与生态环境的桥梁，具有重要的生态功能。然而，不同类型的生态地质环境对采煤活动的敏感性也是不同的。生态地质环境较差的地区对煤矿开采活动的敏感性较差，而生态地质环境较好的地区对即使小规模的采矿活动都具有很强的敏感性。因此，根据不同的生态地质环境特征分类的生态地质环境类型是必要的。这样的分类可以为保护宝贵的潜水含水层水资源，维护原本脆弱的生态地质环境，以及为矿区规划及开采方式选择等工作提取基础依据，对实现干旱-半干旱区生态环境保护开采具有重要意义。
现阶段国内外的技术多集中于采煤活动完成后造成的对原有的地表地质环境或生态环境破坏后的监测、评价及修复措施，缺少在实施采煤活动前，对将开采区域内地表不同的地质环境与生态环境相结合考虑，进行不同生态地质环境类型的区分，以根据不同的生态地质环境条件，为具体的煤炭资源开采活动提供，以达到既实现对煤炭资源的开发，又可以尽可能的减少对地表生态地质环境的破坏，并为之后的矿区地表生态地质环境的修复治理奠定必要的基础，实现煤炭资源开发与生态地质环境保护的协调发展。
影响生态地质环境的因素翻多复杂，并且各个因素之间相互关联、相互影响，各个因素对生态地质环境的整体影响作用不同，加之影响生态地质环境的各个因素大都具 有数据模糊性和评价标准模糊性等特点。因此，利用模糊数学的理论与方法，以ArcGIS和MATLAB为计算平台，采用构建划分生态地质环境类型的层次结构模型，对西部干旱半干旱生态脆弱地区的生态地质环境划分不同的类型。
对划分结果产生的权重系数的计算有：客观法和主观法。客观法主要有以下几种：熵权法、主成分分析法、均方差法等；主观法主要有以下几种：直接打分法、专家打分法、层次分析法、环比评分法、对比排序法等。然而，生态地质环境类型划分中涉及的相关因素指标多为没有确切数值只有模糊性，一般无法满足客观法的计算要求。对于这一类问题，由于层次分析法作为一种把定性分析和定量分析相结合的系统分析方法可以把复杂的问题层次化，将定性条件定量化，多广泛采用主观法中的层次分析法，然而传统的层次分析法中要求进行一致性检验，但一致性检验困难，不允许决策者出现较大的不一致的情况，其实从行为决策分析的角度来分析，应该允许决策者出现较大的不一致的情况。模糊德尔菲层次分析法是综合层次分析法、模糊评价原理以及德尔菲群体决策法，是一种能够让决策者充分参与权重确定和分析的决策方法，形成一个交互式的权重向量决策分析过程，最终确定出决策者满意的群体决策权重向量.这种决策交互的过程可以在层次结构的任意单准则下进行，并且这种方法允许决策者做出不合理的判断，判断矩阵不需要一致性检查。因此，对于划分指标需要进行更加精确的定量化评价，才能为生态地质环境的合理划分提供更加精确的科学依据。
聚类的定义是由Everitt在1974年提出的，他指出聚类就是以某种方式把数据分成指定数目的簇类，最终使得同一簇类中的元素非相似性尽可能的小，不同簇类之间的元素的非相似性尽可能的大。工程中许多问题的解决都用到了聚类方法，像统计学、图像处理等等，这些聚类算法主要有基于模型的聚类算法、划分式聚类算法、层次聚类算法等等，每种算法都有各自的特点，工程实际问题的多样化和复杂化决定了没有一种算法可以解决所有问题，但随着计算机技术的发展，数字计算和程序实现已经越来越容易操作，所以基于目标函数的聚类方法得到了更加深远的发展和推广，模糊聚类就属于该类算法，它是以K均值聚类为基础，引入了模糊理论，而在模糊C均值聚类算法中加入各属性的权重，就形成了属性加权模糊C均值聚类算法，该方法更为科学准确。
发明内容
鉴于上述的分析，本发明旨在提供一种基于煤炭资源开发的生态地质环境类型划分方法，为保护宝贵的潜水含水层水资源，维护原本脆弱的生态地质环境，以及为矿区规划及开采方式选择等工作提取基础依据，对实现干旱-半干旱区生态环境保护开采具有重要意义。
本发明的目的主要是通过以下技术方案实现的：
一种基于煤炭资源开发的生态地质环境类型划分方法，包括以下步骤：
步骤一、获取区域生态、水文、地质资料；
步骤二、建立生态地质环境类型划分的层次结构模型；
步骤三、根据步骤一获取的资料和步骤二中建立的层次结构模型，选取影响生态地质环境的相关因素作为划分指标，并获取待划分区域内生态地质环境类型划分层次结构模型中所有参与类型划分的划分指标所对应的生态、水文及地质数据；
步骤四、将步骤三中所获取划分指标的相关数据转换成浮点型数据；
步骤五、利用归一化函数对步骤四中所述浮点型数据进行无量纲化处理；
步骤六、采用模糊德尔菲层次分析法分析计算出各个划分指标的权重系数；
步骤七、将步骤五中无量纲化数据和步骤六中所述权重系数结合，利用加权模糊C均值聚类方法对影响因素进行叠加聚类计算；
步骤八、根据步骤七中的聚类计算结果和各划分指标的生态、水文及地质特征进行分析判别，确定不同生态地质环境类型，得到生态地质环境类型分区图。
进一步地，步骤二所述层次结构模型包括目标层和指标层，所述的目标层为生态地质环境类型划分的总目标，所述指标层为所有参与类型划分的指标。
进一步地，步骤五用于无量纲化处理的归一化函数为：
Figure PCTCN2019073160-appb-000001
式中，f i为每个划分指标中第i个无量纲化处理后的数据，a和b分别为归一化范围的下限和上限，每个划分指标中都有n个数据，x i是每个划分指标中第i个无量纲化前的原始数据，max(x i)和min(x i)为各划分指标原始数据的最大值和最小值。
进行无量纲化处理能够去除量纲对后面步骤中聚类计算的影响。
进一步地，所述归一化范围的下限a＝0，所述归一化范围的上限b＝1。
进一步地，步骤六具体为：利用模糊德尔菲层次分析法，通过向有关生态、水文、地质方面的专家咨询，并结合T.L.Saaty1-9标度法对各划分指标进行相对生态地质环境整体重要性评分，建立群体的模糊判断矩阵，确定群体模糊权重向量，最后单准则权重分析计算出各个划分指标的权重系数。
进一步地，步骤六具体包括以下步骤：
步骤6.1、设有m个要判断的划分指标以及n个相关领域的咨询专家，通过德尔菲专家调查法，相关领域咨询专家在某个准则下对指标层中的划分指标相对目标层的相对重要性程度的打分，第k个专家对第i个划分指标F i以及第j个划分指标F j两个划分指标之间的相对重要程度判断B ij·k，其中i＝1，2，……m，j＝1，2，……m，k＝1，2……n，确定第k个专家的两两比较判断矩阵B(k)＝[B ij·k]；
Figure PCTCN2019073160-appb-000002
其中，B ij·k＝P i·k/P j·k，P i·k为第k个专家对第i个划分指标相对于目标层重要性的打分值；P j·k为第k个专家对第j个划分指标相对于目标层重要性的打分值；
步骤6.2、构建用三角模糊数表示全部相关领域咨询专家的群体两两模糊判断矩阵C：
C＝[α ij，β ij，γ ij]＝[B 1 B 2 … B m]
式中，所述判断矩阵由α ij，β ij，γ ij三个计算元素组成，其中i＝1……m，j＝1……m，α ij≤β ij≤γ ij，α ij，β ij，γ ij∈[1/9，1]∪[1，9]，所述计算元素α ij，β ij和γ ij由下式确定：
α ij＝min(B ij·k)，k＝1，2，...，n，
Figure PCTCN2019073160-appb-000003
γ ij＝max(B ij·k)，k＝1，2，...，n，
其中，k＝1，2……n，n为相关领域咨询专家的总数，min(B ij·k)为全部相关领域咨询专家打分结果的最小值，geomean(B ij·k)为全部相关领域咨询专家打分结果的几何平均数，max(B ij·k)为全部相关领域咨询专家打分结果的最大值；
由此构造的全部相关领域咨询专家的群体两两模糊判断矩阵：
Figure PCTCN2019073160-appb-000004
步骤6.3、对于所有划分指标中的任意一个划分指标F i，计算群体模糊权重向量过程中涉及的过程计算向量r i：
Figure PCTCN2019073160-appb-000005
则确定任意一个划分指标F i群体模糊权重向量为：
Figure PCTCN2019073160-appb-000006
式中，符号
Figure PCTCN2019073160-appb-000007
和
Figure PCTCN2019073160-appb-000008
分别为三角模糊数的乘法和加法运算法则；
关于三角模糊数运算关系说明：
设a＝[a 1，a 2，a 3]和b＝[b 1，b 2，b 3]为两个正三角模糊数，根据三角模糊数理论：
Figure PCTCN2019073160-appb-000009
Figure PCTCN2019073160-appb-000010
Figure PCTCN2019073160-appb-000011
其中a 1，a 2，a 3和b 1，b 2，b 3分别为两组任意实数。
步骤6.4、对于任意一个划分指标F i的群体模糊权重向量为：
Figure PCTCN2019073160-appb-000012
其中，
Figure PCTCN2019073160-appb-000013
分别为步骤6.3中计算出来的第i个划分指标F i的群体模糊 权重向量结果中的最小值、中间值、最大值；
则任意一个划分指标F i指标的权重系数W i经归一化处理后为：
Figure PCTCN2019073160-appb-000014
进一步地，步骤七包括以下步骤：
步骤7.1、给定包含n个d维向量数据的待聚类样本集合X，X＝{x 1，x 2，x 3，……x n}，将样本集合分成c个簇类G i(i＝1，…，c)，i为第i个簇类，从样本数据中随机选取c个数据点作为初始的聚类中心，x k＝{x k1，x k2，x k3，…，x kd} T∈R d(k＝1，…c)，x kj为数据点x k的第j维属性的赋值，给定加权指数m、目标函数迭代终止阈值ε和迭代终止最大次数1的值；
步骤7.2、计算各个样本内的数据点与聚类中心的加权欧式距离d w-ij；
步骤7.3、计算每个样本内的数据相对于每个簇类的隶属度；
步骤7.4、计算新的聚类中心矩阵P；
步骤7.5、重复步骤7.2、7.3和7.4，对于各个样本指标内每个数据点，当第t次的迭代计算出新的聚类中心矩阵P (t)与第t+1次迭代计算出新的聚类中心矩阵P (t+1)的差值小于给定的迭代终止阈值ε，即||P (t+1)-P (t)||≤ε，或迭代次数达到给定的最大次数l时，停止计算。
进一步地，步骤7.1中，加权指数m＝2；迭代终止阈值ε取值0.001到0.01。
进一步地，步骤7.2包括以下步骤：
步骤7.2.1、包含n个样本数据点x k(k＝1，…，n)的样本集合X＝{x 1，x 2，x 3，…，x n}，分成c个簇类G i(i＝1，…，c)，从各样本数据点x k(k＝1，…，n)中任意选出c个数据点作为每个簇类的初始簇中心，x k＝{x k1，x k2，x k3，…，x kd} T∈R d(k＝1，…c)，其中x kj为数据点x k的第j维属性的赋值，分别计算每个样本内各数据点到初始簇类中心c i(i＝1，…c)的距离，计算各样本内数据点到初始簇类中心的误差平方和；
步骤7.2.2、对每个样本内数据点和初始簇类中心的欧式距离d ki＝||x k-c i||乘以在步骤6.4中计算得出的权重系数W i加以修正，则：
欧式距离
Figure PCTCN2019073160-appb-000015
加权欧式距离d w-ij＝d||x j-c i|| w＝[(x j-c i) TW 2(x j-c i)] 1/2，
其中，权重向量W由步骤6.4所述权重系数W i组成，所述权重向量W＝[W 1，W 2，…，W i] T，(i＝1……d)，所述权重向量中权重系数W i需满足下式：
W i≥0，i＝{1，2，…，d}且
Figure PCTCN2019073160-appb-000016
进一步地，步骤7.3包括以下步骤：
步骤7.3.1、新的评价聚类性能的误差平方和准则函数，即新的加权目标函数为：
Figure PCTCN2019073160-appb-000017
其中，
Figure PCTCN2019073160-appb-000018
步骤7.3.2、利用拉格朗日乘子法求解，构造出的新的拉格朗日函数为：
Figure PCTCN2019073160-appb-000019
式中，U为模糊加权划分矩阵，P为新的聚类中心矩阵，u ij是第j个数据点对簇类G i的聚类隶属度，c i是相应的模糊向量集的聚类中心，λ j为n个约束式的拉格朗日乘子；
结合约束条件
Figure PCTCN2019073160-appb-000020
对输入的参量m＝2，0.001≤ε≤0.01，求偏导求解，求得使新的加权目标函数式J WFCM取得最小值的必要条件为：，
Figure PCTCN2019073160-appb-000021
利
Figure PCTCN2019073160-appb-000022
步骤7.3.3、一个数据点对某一簇类的归属是按照隶属度最大原则来确定的，所述数据点归属于隶属度最大的簇类，表达式为：
Figure PCTCN2019073160-appb-000023
本发明有益效果如下：
本发明基于煤炭资源开发的生态地质环境类型划分方法，该方法是将我国西北煤炭资源丰富、生态地质环境却十分脆弱的干旱半干旱地区划分不同的生态地质环境类型，并绘制出生态地质环境类型分区图。为保护宝贵的潜水含水层水资源，维护原本脆弱的生态地质环境，以及为矿区规划及开采方式选择等工作提取基础依据，对实现干旱-半干旱区生态环境保护开采具有重要意义。
本发明能够根据现有的生态水文地质资料，快速有效地划分出不同的生态地质环境类型，确定不同类型的生态地质环境的生态地质特征及其对煤炭资源开采活动的敏感性，从而为保护类似干旱半干旱地区珍惜的潜水资源，维护好脆弱的生态环境同时选择恰当的采煤方法实现煤炭资源的开发利用提供科学依据，对西北生态环境脆弱区保水采 煤具有重要意义。
本发明对将开采区域内地表不同的地质环境与生态环境相结合考虑，进行不同生态地质环境类型的区分，以根据不同的生态地质环境条件，为具体的煤炭资源开采活动提供，以达到既能够实现对煤炭资源的开发，又可以尽可能的减少对地表生态地质环境的破坏，并为之后的矿区地表生态地质环境的修复治理奠定必要的基础，实现煤炭资源开发与生态地质环境保护的协调发展。
本发明中，上述各技术方案之间还可以相互组合，以实现更多的优选组合方案。本发明的其他特征和优点将在随后的说明书中阐述，并且，部分优点可从说明书中变得显而易见，或者通过实施本发明而了解。本发明的目的和其他优点可通过说明书、权利要求书以及附图中所特别指出的内容中来实现和获得。
附图说明
附图仅用于示出具体实施例的目的，而并不认为是对本发明的限制，在整个附图中，相同的参考符号表示相同的部件。
图1为本发明方法实施流程图；
图2为待划分区域生态地质环境类型划分的层次结构模型；
图3-为生态地质环境类型中植被指数专题图；
图4为生态地质环境类型中地表高程专题图；
图5为生态地质环境类型中地形坡度专题图；
图6为生态地质环境类型中地表岩性专题图；
图7为生态地质环境类型中地貌类型专题图；
图8为生态地质环境类型中水系河网影响程度专题图；
图9为生态地质环境类型中植被指数归一化专题图；
图10为生态地质环境类型中地表高程归一化专题图；
图11为生态地质环境类型中地形坡度归一化专题图；
图12为生态地质环境类型中地表岩性归一化专题图；
图13为生态地质环境类型中地貌归一化专题图；
图14为生态地质环境类型中水系河网影响程度归一化专题图；
图15为生态地质环境类型区划图。
具体实施方式
下面结合附图来具体描述本发明的优选实施例，其中，附图构成本申请一部分，并与本发明的实施例一起用于阐释本发明的原理，并非用于限定本发明的范围。
以下参照附图1，并举具体实施例对本发明作进一步的说明。
如图1所示，为一种基于煤炭资源开发的生态地质环境类型划分方法，包括如下步骤：
1、收集区域水文、地质、水文地质资料；
2、建立生态地质环境类型划分的层次结构模型，包括目标层和指标层，所述的目标层为生态地质环境类型划分的总目标，所有的参与类型划分的指标作为指标层；
3、根据步骤1获取的资料及步骤2建立的层次结构模型，选取影响生态地质环境的相关因素作为划分指标，并获取待划分区域内生态地质环境类型划分层次结构模型中所有参与类型划分的指标所对应的生态、水文及地质数据；
4、将步骤3所获取划分指标的相关数据在ArcGIS中处理成MATLAB软件能够读取的浮点型.flt数据；
5、在MATLAB中利用归一化函数将步骤4获得的划分指标的浮点型数据进行无量纲化处理，去除量纲对后面步骤中聚类计算的影响；
6、利用模糊德尔菲层次分析法，通过向有关生态、水文、地质方面的专家咨询，并结合T.L.Saaty1-9标度法对各划分指标进行相对生态地质环境整体重要性评分，建立群体的模糊判断矩阵，确定群体模糊权重向量，最后单准则权重分析计算出各个划分指标的权重系数；
7、利用加权模糊C均值聚类方法，将步骤5获得的各个划分指标无量纲化数据与步骤6确定的各个划分指标相对生态地质环境整体重要性的权重系数相结合在MATLAB中进行聚类计算，输出不同的聚类计算结果，并以文本文件(.txt)的形式存储；
8、将步骤7中计算得出的以文本文件(.txt)存储的聚类结果在ArcGIS中软件中打开，结合在步骤7中计算得出的各因素聚类中心值，并根据各划分指标的生态、水文及地质特征进行分析判别，确定不同生态地质环境类型，得到生态地质环境类型分区图。
本实施例步骤1具体为：通过遥感图像提取植被指数(NDVI)，所选用影像为Landsat8卫星遥感数据，根据研究区范围，选用两幅数据经图像镶嵌而成，卫星过境采集数据时，研究区天气晴朗，天空没有覆盖大面积的云层，因而两幅图全图云量较低，成像质量高，图像清晰，分辨率均为30米。基于30m的数字高程模型数据，利用ArcGIS10.5空间分析功能，提取研究区的高程和坡度，通过实地踏勘，及多年地质资料的积累，整理所需的生态、水文、地质资料。
本实施例步骤2中，生态地质环境类型划分作为目标层，植被归一化指数(F1)、地表高程(F2)、地形坡度(F3)、地表岩性(F4)、地貌类型(F5)、水系河网(F6)作为划分指标，形成待划分区域的生态地质环境的层次结构模型，如图2所示。
接着步骤2提取所述的6个划分指标对应的生态、水文、地质数据，继续执行步骤3。
步骤3中，将待划分区域的生态、水文、地质数据导入到ArcGIS中，建立各指标单因素图层，如图3-图8。
步骤4中，在ArcGIS10.5中将评价因子中shp格式的数据转换成grid格式的栅格数据，进而转换成MATLAB可识别的.flt浮点型数据，转化结果包含两个文件，一个为hdr扩展名的头文件，包含了栅格左下角的x，y坐标、栅格大小、栅格的行数和列数等信息，另一个为flt扩展名的浮点数据。
对待划分生态地质环境类型区域的各单项指标数据图层进行栅格化处理，将待评价区域划分为n个基础评价单元，n＝682*903＝615846个基础单元。
步骤5中，在MATLAB中，使用read_AGaschdr函数读取待划分区域各指标，用normalization函数对因子做归一化去量纲处理，各划分指标归一化处理后如图9-图14。
normalization函数：
Figure PCTCN2019073160-appb-000024
式中，f i为每个划分指标中第i个无量纲化处理后的数据，a和b分别为归一化范围的下限和上限，x i是每个划分指标中第i个无量纲化前的原始数据，max(x i)和min(x i)为各划分指标原始数据的最大值和最小值。
步骤6包括以下步骤：
(601)T.L.Saaty1-9标度法对各划分指标进行相对生态地质环境整体重要性评分：
Figure PCTCN2019073160-appb-000025
(602)建立两两比较判断矩阵
Figure PCTCN2019073160-appb-000026
Figure PCTCN2019073160-appb-000027
Figure PCTCN2019073160-appb-000028
Figure PCTCN2019073160-appb-000029
Figure PCTCN2019073160-appb-000030
Figure PCTCN2019073160-appb-000031
(603)构建群体的模糊判断矩阵
Figure PCTCN2019073160-appb-000032
Figure PCTCN2019073160-appb-000033
Figure PCTCN2019073160-appb-000034
(604)确定群体模糊权重向量
w 1＝[0.0630.0980.158]w 2＝[0.0570.0920.177]
w 3＝[0.0900.1430.228]w 4＝[0.177 0.2850.437]
w 5＝[0.1800.2780.419]w 6＝[0.0620.1040.173]
(605)各划分指标权重系数
Figure PCTCN2019073160-appb-000035
步骤7中，对聚类函数custom_fcm进行改进，在计算欧氏距离过程中加入属性权重W i，设置聚类参数，对上述归一化因子进行聚类分析。在MATLAB处理之后，用fprintf函数对结果进行后处理，先将文件读入时获取的栅格左下角的x，y坐标和栅格行列数等信息参数重新写入头文件，再输出计算的栅格数值，进而将计算结果转为ASCII数据，利用ArcGIS软件读取ASCII文件，将其转换成栅格文件，输出生态地质环境类型区划图，如图15。
本发明涉及了一种基于煤炭资源开发的生态地质环境类型划分方法，该方法是将我国西北煤炭资源丰富、生态地质环境却十分脆弱的干旱半干旱地区划分不同的生态地质环境类型，并绘制出生态地质环境类型分区图。本发明方法首先是在对区域生态、水文、地质等相关资料调查的基础之上，将影响生态地质环境的诸多因素收集整理，并利用归一化函数将各个因素无量纲化；其次，利用模糊德尔菲层次分析法确定每个因素对生态地质环境影响的权重系数；再次，以MATLAB为计算平台，利用加权模糊C均值聚类法对各个影响因素进行叠加聚类计算，得出三种不同的聚类结果；最后，利用ArcGIS将聚类结果进行图像处理，通过每个因素的聚类中心值分析判断确定不同的生态地质环境类型。本发 明能够根据现有的生态水文地质资料，快速有效地划分出不同的生态地质环境类型，确定不同类型的生态地质环境的生态地质特征及其对煤炭资源开采活动的敏感性，从而为保护类似干旱半干旱地区珍惜的潜水资源，维护好脆弱的生态环境同时选择恰当的采煤方法实现煤炭资源的开发利用提供科学依据，对西北生态环境脆弱区保水采煤具有重要意义。
以上所述，仅为本发明较佳的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本发明的保护范围之内。

Claims (10)

  1. 一种基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，包括以下步骤：
    步骤一、获取区域生态、水文、地质资料；
    步骤二、建立生态地质环境类型划分的层次结构模型；
    步骤三、根据步骤一获取的资料和步骤二中建立的层次结构模型，选取影响生态地质环境的相关因素作为划分指标，并获取待划分区域内生态地质环境类型划分层次结构模型中所有参与类型划分的划分指标所对应的生态、水文及地质数据；
    步骤四、将步骤三中所获取划分指标的相关数据转换成浮点型数据；
    步骤五、利用归一化函数对步骤四中所述浮点型数据进行无量纲化处理；
    步骤六、采用模糊德尔菲层次分析法分析计算出各个划分指标的权重系数；
    步骤七、将步骤五中无量纲化数据和步骤六中所述权重系数结合，利用加权模糊C均值聚类方法对影响因素进行叠加聚类计算；
    步骤八、根据步骤七中的聚类计算结果和各划分指标的生态、水文及地质特征进行分析判别，确定不同生态地质环境类型，得到生态地质环境类型分区图。
  2. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤二所述层次结构模型包括目标层和指标层，所述的目标层为生态地质环境类型划分的总目标，所述指标层为所有参与类型划分的指标。
  3. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤五用于无量纲化处理的归一化函数为：
    Figure PCTCN2019073160-appb-100001
    式中，f i为每个划分指标中第i个无量纲化处理后的数据，a和b分别为归一化范围的下限和上限，每个划分指标中都有n个数据，x i是每个划分指标中第i个无量纲化前的原始数据，max(x i)和min(x i)为各划分指标原始数据的最大值和最小值。
  4. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，所述归一化范围的下限a＝0，所述归一化范围的上限b＝1。
  5. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤六具体为：利用模糊德尔菲层次分析法，通过向有关生态、水文、地质方面的专家咨询，并结合T.L.Saaty 1-9标度法对各划分指标进行相对生态地质环境整体重要性评分，建立群体的模糊判断矩阵，确定群体模糊权重向量，最后单准则权重分析计算出各个划分指标的权重系数。
  6. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤六具体包括以下步骤：
    步骤6.1、设有m个要判断的划分指标以及n个相关领域的咨询专家，通过德尔菲专家调查法，相关领域咨询专家在某个准则下对指标层中的划分指标相对目标层的相对重要性程度的打分，第k个专家对第i个划分指标Fi以及第j个划分指标F j两个划分指标之间的相对重要程度判断B ij·k，其中i＝1，2，……m，j＝1，2，……m，k＝1，2……n，确定第k个专家的两两比较判断矩阵B(k)＝[B ij·k]；
    Figure PCTCN2019073160-appb-100002
    其中，B ij·k＝P i·k/P j·k，P i·k为第k个专家对第i个划分指标相对于目标层重要性的打分值；P j·k为第k个专家对第j个划分指标相对于目标层重要性的打分值；
    步骤6.2、构建用三角模糊数表示全部相关领域咨询专家的群体两两模糊判断矩阵C：
    C＝[α ij，β ij，γ ij]＝[B 1 B 2 … B m]
    式中，所述判断矩阵由α ij，β ij，γ ij三个计算元素组成，其中i＝1……m，j＝1……m，α ij≤β ij≤γ ij，α ij，β ij，γ ij∈[1/9，1]∪[1，9]，所述计算元素α ij，β ij和γ ij由下式确定：
    α ij＝min(B ij· k)，k＝1，2，...，n，
    Figure PCTCN2019073160-appb-100003
    γ ij＝max(B ij·k)，k＝1，2，...，n，
    其中，k＝1，2……n，n为相关领域咨询专家的总数，min(B ij·k)为全部相关领域咨询专家打分结果的最小值，geomean(B ij·k)为全部相关领域咨询专家打分结果的几何平均数，max(B ij·k)为全部相关领域咨询专家打分结果的最大值；
    步骤6.3、对于所有划分指标中的任意一个划分指标F i，计算群体模糊权重向量过程中涉及的过程计算向量r i：
    Figure PCTCN2019073160-appb-100004
    则确定任意一个划分指标F i群体模糊权重向量为：
    Figure PCTCN2019073160-appb-100005
    式中，符号
    Figure PCTCN2019073160-appb-100006
    和
    Figure PCTCN2019073160-appb-100007
    分别为三角模糊数的乘法和加法运算法则；
    步骤6.4、对于任意一个划分指标F i的群体模糊权重向量为：
    Figure PCTCN2019073160-appb-100008
    其中，
    Figure PCTCN2019073160-appb-100009
    w i U分别为步骤6.3中计算出来的第i个划分指标F i的群体模糊权重向量结果中的最小值、中间值、最大值；
    则任意一个划分指标F i指标的权重系数W i经归一化处理后为：
    Figure PCTCN2019073160-appb-100010
  7. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤七包括以下步骤：
    步骤7.1、给定包含n个d维向量数据的待聚类样本集合X，X＝{x 1，x 2，x 3，……x n}，将样本集合分成c个簇类G i(i＝1，…，c)，i为第i个簇类，从样本数据中随机选取c个数据点作为初始的聚类中心，x k＝{x k1，x k2，x k3，…，x kd} T∈R d(k＝1，…c)，x kj为数据点x k的第j维属性的赋值，给定加权指数m、目标函数迭代终止阈值ε和迭代终止最大次数l的值；
    步骤7.2、计算各个样本内的数据点与聚类中心的加权欧式距离d w-ij；
    步骤7.3、计算每个样本内的数据相对于每个簇类的隶属度；
    步骤7.4、计算新的聚类中心矩阵P；
    步骤7.5、重复步骤7.2、7.3和7.4，对于各个样本指标内每个数据点，当第t次的迭代计算出新的聚类中心矩阵P (t)与第t+1次迭代计算出新的聚类中心矩阵P (t+1)的差值小于给定的迭代终止阈值ε，即||P (t+1)-P (t)||≤ε，或迭代次数达到给定的最大次数l时，停止计算。
  8. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤7.1中，加权指数m＝2；迭代终止阈值ε取值0.001到0.01。
  9. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤7.2包括以下步骤：
    步骤7.2.1、包含n个样本数据点x k(k＝1，…，n)的样本集合X＝{x 1，x 2，x 3，…，x n}，分成c个簇类G i(i＝1，…，c)，从各样本数据点x k(k＝1，…，n)中任意选出c个数据点作为每个簇类的初始簇中心，x k＝{x k1，x k2，x k3，…，x kd} T∈R d(k＝1，…c)，其中x kj为数据点x k的第j维属性的赋值，分别计算每个样本内各数据点到初始簇类中心c i(i＝1，…c)的距离，计算各样本内数据点到初始簇类中心的误差平方和；
    步骤7.2.2、对每个样本内数据点和初始簇类中心的欧式距离d ki＝||x k-c i||乘以在步骤6.4中计算得出的权重系数W i加以修正，则：
    欧式距离
    Figure PCTCN2019073160-appb-100011
    加权欧式距离d w-ij＝d||x j-c i|| w＝[(x j-c i) TW 2(x j-c i)] 1/2，
    其中，权重向量W由步骤6.4所述权重系数W i组成，所述权重向量W＝[W 1，W 2，…，W i] T，(i＝1……d)，所述权重向量中权重系数W i需满足下式：
    W i≥0，i＝{1，2，…，d}且
    Figure PCTCN2019073160-appb-100012
  10. 根据权利要求1所述基于煤炭资源开发的生态地质环境类型划分方法，其特征在于，步骤7.3包括以下步骤：
    步骤7.3.1、新的评价聚类性能的误差平方和准则函数，即新的加权目标函数为：
    Figure PCTCN2019073160-appb-100013
    其中，
    Figure PCTCN2019073160-appb-100014
    步骤7.3.2、利用拉格朗日乘子法求解，构造出的新的拉格朗日函数为：
    Figure PCTCN2019073160-appb-100015
    Figure PCTCN2019073160-appb-100016
    式中，U为模糊加权划分矩阵，P为新的聚类中心矩阵，u ij是第j个数据点对簇类G i的聚类隶属度，c i是相应的模糊向量集的聚类中心，λ j为n个约束式的拉格朗日乘子；
    结合约束条件
    Figure PCTCN2019073160-appb-100017
    对输入的参量m＝2，0.001≤ε≤0.01，求偏导求解，求得使新的加权目标函数式J WFCM取得最小值的必要条件为：
    Figure PCTCN2019073160-appb-100018
    和
    Figure PCTCN2019073160-appb-100019
    步骤7.3.3、一个数据点对某一簇类的归属是按照隶属度最大原则来确定的，所述数据点归属于隶属度最大的簇类，表达式为：
    Figure PCTCN2019073160-appb-100020
PCT/CN2019/073160 2018-01-30 2019-01-25 一种基于煤炭资源开发的生态地质环境类型划分方法 WO2019149147A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US16/639,138 US20200234170A1 (en) 2018-01-30 2019-01-25 Method for classifying eco-geological environment types based on coal resource exploitation
AU2019214077A AU2019214077B2 (en) 2018-01-30 2019-01-25 Method for dividing ecological and geological environment types based on coal resource development
ZA2020/00342A ZA202000342B (en) 2018-01-30 2020-01-17 Method for classifying eco-geological environment types based on coal resource exploitation

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810089353.1A CN108416686B (zh) 2018-01-30 2018-01-30 一种基于煤炭资源开发的生态地质环境类型划分方法
CN201810089353.1 2018-01-30

Publications (1)

Publication Number Publication Date
WO2019149147A1 true WO2019149147A1 (zh) 2019-08-08

Family

ID=63126699

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/073160 WO2019149147A1 (zh) 2018-01-30 2019-01-25 一种基于煤炭资源开发的生态地质环境类型划分方法

Country Status (5)

Country Link
US (1) US20200234170A1 (zh)
CN (1) CN108416686B (zh)
AU (1) AU2019214077B2 (zh)
WO (1) WO2019149147A1 (zh)
ZA (1) ZA202000342B (zh)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110490478A (zh) * 2019-08-26 2019-11-22 贵州大学 一种道路行道树树池生态环境调查方法
CN111539580A (zh) * 2020-04-30 2020-08-14 上海市园林科学规划研究院 城市绿化生态技术集成应用的多方案优选方法
CN111953543A (zh) * 2020-08-14 2020-11-17 国科量子通信网络有限公司 一种基于pca-ahp的量子通信网络可靠性状况的评估方法
CN112001568A (zh) * 2020-09-11 2020-11-27 新疆大学 高海拔高寒金属矿开采风钻作业效率影响因素的评估方法
CN112001641A (zh) * 2020-08-27 2020-11-27 中国海洋大学 一种扇贝养殖区适宜性遥感评估系统
CN112067560A (zh) * 2020-08-06 2020-12-11 红云红河烟草(集团)有限责任公司 一种基于色度值结合熵权法的烟用料液稳定性测定方法
CN112785448A (zh) * 2020-11-24 2021-05-11 中国石油天然气股份有限公司 一种油气资源区带评价方法
CN116227982A (zh) * 2022-12-30 2023-06-06 中国矿业大学(北京) 一种煤炭粉尘污染程度的量化方法及装置
CN116523397A (zh) * 2023-04-25 2023-08-01 长安大学 基于熵权法和gmm聚类算法的城市交通网络弹性评估方法

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416686B (zh) * 2018-01-30 2021-10-19 中国矿业大学 一种基于煤炭资源开发的生态地质环境类型划分方法
CN111275065B (zh) * 2018-12-05 2023-08-15 中国科学院烟台海岸带研究所 一种基于海洋环境多属性的水产养殖空间分区方法
CN111127234B (zh) * 2019-10-11 2024-01-19 重庆大学 一种突出煤层群开采首采层确定方法及装置
CN111322732A (zh) * 2020-02-24 2020-06-23 杨子靖 一种空调健康状态分析方法和系统
CN112215135B (zh) * 2020-10-10 2022-07-08 东华理工大学 矿区开采与治理成效监测方法及装置
CN112561235B (zh) * 2020-11-23 2023-01-10 中铁二十四局集团福建铁路建设有限公司 一种适于高速公路路域的生态脆弱性评价方法
CN112465332A (zh) * 2020-11-24 2021-03-09 山东大学 一种城市人工湿地公园生态地质环境稳定性的评价方法
CN112785450B (zh) * 2020-12-30 2021-12-07 北京农业信息技术研究中心 一种土壤环境质量分区方法及系统
CN112861322B (zh) * 2021-01-15 2022-02-18 哈尔滨工程大学 一种海底阶梯式地貌演化定量分析方法及系统
CN112765521B (zh) * 2021-01-21 2023-06-23 南京信息工程大学 一种基于改进k近邻的网站用户分类方法
CN112883292B (zh) * 2021-02-06 2023-04-18 西北大学 用户行为推荐模型建立及基于时空信息的位置推荐方法
CN113139159B (zh) * 2021-04-22 2022-04-29 中国水利水电科学研究院 一种流域生态敏感性的评价方法
CN113327062A (zh) * 2021-06-25 2021-08-31 贵州电网有限责任公司电力科学研究院 信息的等级确定方法、装置、计算机设备和存储介质
CN113516083B (zh) * 2021-07-19 2023-04-07 中国农业科学院草原研究所 一种草原区弃耕地植被的生态修复建模方法
CN113610369B (zh) * 2021-07-26 2022-04-01 广州园林建筑规划设计研究总院有限公司 水生态服务功效的评价方法及城市滨水景观构建方法
CN114220004B (zh) * 2021-11-26 2023-04-18 北京亿耘科技有限公司 一种基于遥感影像的人工牧场地块识别方法和系统
CN115565623B (zh) * 2022-10-19 2023-06-09 中国矿业大学(北京) 一种煤地质成分的分析方法、系统、电子设备及存储介质
CN116595399B (zh) * 2023-06-14 2024-01-05 中国矿业大学(北京) 一种煤中元素相关性不一致问题的分析方法
CN117195469B (zh) * 2023-07-24 2024-03-29 国能经济技术研究院有限责任公司 选煤工艺流程全过程确定方法、设备和介质
CN117314248A (zh) * 2023-10-08 2023-12-29 中国矿业大学 基于改进遥感生态指数的矿区生态环境评价方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103049655A (zh) * 2012-12-18 2013-04-17 中国矿业大学(北京) 基于多数据源的矿区土地生态损伤信息获取方法
CN107506609A (zh) * 2017-10-09 2017-12-22 中国矿业大学 一种干旱‑半干旱区煤炭开采生态环境破坏等级划分方法
CN108416686A (zh) * 2018-01-30 2018-08-17 中国矿业大学 一种基于煤炭资源开发的生态地质环境类型划分方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104299162B (zh) * 2013-07-19 2017-07-11 中国石油化工股份有限公司 一种基于弗晰逻辑的地质风险不确定性评价方法
CN103824133B (zh) * 2014-03-06 2017-11-28 核工业北京地质研究院 一种花岗岩型铀矿田远景区综合预测方法
CN105069689B (zh) * 2015-08-21 2017-03-29 山东科技大学 基于灰色关联与fdahp相结合的煤层底板突水危险性评价方法
CN105787642A (zh) * 2016-02-03 2016-07-20 中国海洋石油总公司 一种油气勘探中潜在商业区优选方法
CN105787652A (zh) * 2016-02-23 2016-07-20 北京师范大学 一种区域综合环境风险评估和分区方法
CN106251075B (zh) * 2016-08-04 2020-05-19 中国石油天然气股份有限公司 一种油田区块套损风险预警分析方法
CN107067333B (zh) * 2017-01-16 2022-12-20 长沙矿山研究院有限责任公司 一种高寒高海拔高陡边坡稳定性监控方法
CN106846178A (zh) * 2017-02-13 2017-06-13 水利部交通运输部国家能源局南京水利科学研究院 一种河流型水源地综合安全评价方法
CN107180306A (zh) * 2017-05-24 2017-09-19 西安科技大学 一种煤炭资源有利开采区块加权叠加辨识的技术方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103049655A (zh) * 2012-12-18 2013-04-17 中国矿业大学(北京) 基于多数据源的矿区土地生态损伤信息获取方法
CN107506609A (zh) * 2017-10-09 2017-12-22 中国矿业大学 一种干旱‑半干旱区煤炭开采生态环境破坏等级划分方法
CN108416686A (zh) * 2018-01-30 2018-08-17 中国矿业大学 一种基于煤炭资源开发的生态地质环境类型划分方法

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110490478A (zh) * 2019-08-26 2019-11-22 贵州大学 一种道路行道树树池生态环境调查方法
CN111539580A (zh) * 2020-04-30 2020-08-14 上海市园林科学规划研究院 城市绿化生态技术集成应用的多方案优选方法
CN112067560A (zh) * 2020-08-06 2020-12-11 红云红河烟草(集团)有限责任公司 一种基于色度值结合熵权法的烟用料液稳定性测定方法
CN112067560B (zh) * 2020-08-06 2023-11-03 红云红河烟草(集团)有限责任公司 一种基于色度值结合熵权法的烟用料液稳定性测定方法
CN111953543A (zh) * 2020-08-14 2020-11-17 国科量子通信网络有限公司 一种基于pca-ahp的量子通信网络可靠性状况的评估方法
CN112001641B (zh) * 2020-08-27 2023-08-08 中国海洋大学 一种扇贝养殖区适宜性遥感评估系统
CN112001641A (zh) * 2020-08-27 2020-11-27 中国海洋大学 一种扇贝养殖区适宜性遥感评估系统
CN112001568A (zh) * 2020-09-11 2020-11-27 新疆大学 高海拔高寒金属矿开采风钻作业效率影响因素的评估方法
CN112785448A (zh) * 2020-11-24 2021-05-11 中国石油天然气股份有限公司 一种油气资源区带评价方法
CN112785448B (zh) * 2020-11-24 2024-03-05 中国石油天然气股份有限公司 一种油气资源区带评价方法
CN116227982A (zh) * 2022-12-30 2023-06-06 中国矿业大学(北京) 一种煤炭粉尘污染程度的量化方法及装置
CN116227982B (zh) * 2022-12-30 2023-10-31 中国矿业大学(北京) 一种煤炭粉尘污染程度的量化方法及装置
CN116523397A (zh) * 2023-04-25 2023-08-01 长安大学 基于熵权法和gmm聚类算法的城市交通网络弹性评估方法
CN116523397B (zh) * 2023-04-25 2024-03-08 长安大学 基于熵权法和gmm聚类算法的城市交通网络弹性评估方法

Also Published As

Publication number Publication date
AU2019214077A1 (en) 2020-02-13
AU2019214077B2 (en) 2021-10-14
CN108416686A (zh) 2018-08-17
CN108416686B (zh) 2021-10-19
US20200234170A1 (en) 2020-07-23
ZA202000342B (en) 2021-08-25

Similar Documents

Publication Publication Date Title
WO2019149147A1 (zh) 一种基于煤炭资源开发的生态地质环境类型划分方法
Song et al. Potential of ensemble learning to improve tree-based classifiers for landslide susceptibility mapping
CN108898096B (zh) 一种面向高分影像的信息快速精确提取方法
Bai et al. Groundwater potential mapping in hubei region of china using machine learning, ensemble learning, deep learning and automl methods
Pradhan et al. Use of different bivariate statistical landslide susceptibility methods: A case study of Kulekhani watershed, Nepal
CN106991049A (zh) 一种软件缺陷预测方法及预测系统
CN104239890A (zh) 高分1号卫星的沿岸陆地土地覆被信息自动提取的方法
CN102184423A (zh) 一种全自动的区域不透水面遥感信息精确提取方法
CN107491846A (zh) 采用类比法对煤炭资源进行概略技术经济评价的方法
CN114037891A (zh) 基于u型注意力控制网络的高分辨率遥感影像建筑物提取方法及装置
Zhao et al. Hydrogeochemical characterization and suitability assessment of groundwater in a typical coal mining subsidence area in China using self-organizing feature map
Ji et al. Multicascaded feature fusion-based deep learning network for local climate zone classification based on the So2Sat LCZ42 benchmark dataset
Chen et al. The application of the genetic adaptive neural network in landslide disaster assessment
Ji et al. Implementation of ensemble deep learning coupled with remote sensing for the quantitative analysis of changes in arable land use in a mining area
Li et al. Change detection of open-pit mine based on siamese multiscale network
CN109740504A (zh) 一种基于遥感影像提取海域资源的方法
Zhang et al. Landslide Susceptibility Mapping Using Novel Hybrid Model Based on Different Mapping Units
Wu et al. Post-flood disaster damaged houses classification based on dual-view image fusion and Concentration-Based Attention Module
Han et al. Automatic Classification Method of Quaternary Lithology in Vegetation Cover Area Combining Spectral, Textural, Topographic, Geothermal, and Vegetation
CN112801028A (zh) 基于归纳表示学习网络的光谱和空间图高光谱图像分类方法
Wu et al. Accuracy Improvement of Different Landslide Susceptibility Evaluation Models through K‐Means Clustering: A Case Study on China’s Funing County
Zhong et al. Local Climate Zone Mapping by Coupling Multi-Level Features with Prior Knowledge Based on Remote Sensing Images
CN115019184B (zh) 基于遥感影像的石漠化程度自动分级方法及装置
Chen et al. Object-Oriented Extraction of Land Occupation Types in Mining Areas by Using Densenet
Zhang et al. Recognition Method for Earthquake-induced Building Damage from Unmanned-aerial-vehicle-based Images Using Bag of Words and Histogram Intersection Kernel Support Vector Machine.

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19748072

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019214077

Country of ref document: AU

Date of ref document: 20190125

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19748072

Country of ref document: EP

Kind code of ref document: A1