CN116222670A - A monitoring method for ecological landscape slopes used in urban green space planning - Google Patents
A monitoring method for ecological landscape slopes used in urban green space planning Download PDFInfo
- Publication number
- CN116222670A CN116222670A CN202310504922.5A CN202310504922A CN116222670A CN 116222670 A CN116222670 A CN 116222670A CN 202310504922 A CN202310504922 A CN 202310504922A CN 116222670 A CN116222670 A CN 116222670A
- Authority
- CN
- China
- Prior art keywords
- dimension
- data
- interpolated
- target
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000005070 sampling Methods 0.000 claims abstract description 78
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 238000006073 displacement reaction Methods 0.000 claims description 45
- 238000010586 diagram Methods 0.000 claims description 28
- 230000008859 change Effects 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 21
- 201000010099 disease Diseases 0.000 abstract description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract 1
- 230000000052 comparative effect Effects 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
Description
技术领域technical field
本发明涉及数据处理技术领域，具体涉及一种城市绿地规划用生态景观边坡监测方法。The invention relates to the technical field of data processing, in particular to a method for monitoring ecological landscape slopes for urban green space planning.
背景技术Background technique
城市绿地规划是统计对城市绿化空间的规划、设计和建设，实现城市环境绿化、生态景观保护的过程。而生态景观边坡是城市绿化中的一项基础设施，维护城市生态平衡，并且可以降低热岛效应，提高城市的环境质量，而生态景观边坡监测是边坡建设和维护的重要环节，通过监测边坡状态来搜集形变、滑坡等信息，预防边坡发生形变地质灾害等危险情况的发生，确保城市基础设施的完整和居民生命财产的安全。Urban green space planning is the process of statistically planning, designing and constructing urban green space to realize urban environmental greening and ecological landscape protection. The ecological landscape slope is an infrastructure in urban greening, which maintains the urban ecological balance, and can reduce the heat island effect and improve the environmental quality of the city. The monitoring of the ecological landscape slope is an important link in the construction and maintenance of the slope. Through monitoring Slope status is used to collect information such as deformation and landslides, to prevent the occurrence of dangerous situations such as slope deformation and geological disasters, and to ensure the integrity of urban infrastructure and the safety of residents' lives and property.
目前对于生态景观边坡的监测主要采用布置多种传感器来实时自动化监测边坡的时序数据，根据采集的一系列监测数据进行数据预处理，进而进行数据监测分析，实现对监测数据进行异常检测及预警。而在数据监测处理过程中，数据的好坏决定着多种传感器数据综合异常分析结果的好坏即数据存在较多缺失值进而进行数据融合时出现较大误差时数据较坏，数据没有缺失值时数据较好，但由于各种传感器的采样时间点和采样频率不同，因此在进行数据融合过程中，需要对多种传感器数据进行插值来提高数据监测效果。传统的数据插值过程中往往采用相邻时序数据的数据分布特征来进行加权平均拟合得到待插值点，然而对于边坡的多种传感器数据彼此间会存在相互影响，边坡发生形变是由于多种原因共同造成的，因此在进行数据插值过程中，需要考虑多种传感器之间的互相影响来进行准确的插值，进而在后续的数据异常检测预警过程中，得到准确的监测结果。At present, the monitoring of ecological landscape slopes mainly adopts a variety of sensors to automatically monitor the time series data of slopes in real time. According to a series of monitoring data collected, data preprocessing is performed, and then data monitoring and analysis are carried out to realize abnormal detection and monitoring of monitoring data. early warning. In the process of data monitoring and processing, the quality of the data determines the quality of the comprehensive abnormal analysis results of various sensor data, that is, there are many missing values in the data, and when there is a large error in data fusion, the data is bad, and the data has no missing values. However, due to the different sampling time points and sampling frequencies of various sensors, it is necessary to interpolate the data of various sensors in the process of data fusion to improve the data monitoring effect. In the traditional data interpolation process, the data distribution characteristics of adjacent time series data are often used to carry out weighted average fitting to obtain the points to be interpolated. Therefore, in the process of data interpolation, it is necessary to consider the interaction between various sensors to perform accurate interpolation, and then obtain accurate monitoring results in the subsequent data anomaly detection and early warning process.
发明内容Contents of the invention
本发明提供一种城市绿地规划用生态景观边坡监测方法，以解决现有的问题。The invention provides an ecological landscape slope monitoring method for urban green space planning to solve the existing problems.
本发明的一种城市绿地规划用生态景观边坡监测方法采用如下技术方案：A kind of ecological landscape slope monitoring method for urban green space planning of the present invention adopts the following technical scheme:
本发明一个实施例提供了一种城市绿地规划用生态景观边坡监测方法，该方法包括以下步骤：One embodiment of the present invention provides a kind of ecological landscape slope monitoring method for urban green land planning, the method comprises the following steps:
在生态景观边坡处安装传感器，将单个传感器记为单维度，单维度中每一采样时间点对应的传感器采集的数据记为单维度数据，设定待插值维度；Install sensors on the slope of the ecological landscape, record a single sensor as a single dimension, record the data collected by the sensor corresponding to each sampling time point in the single dimension as single dimension data, and set the dimension to be interpolated;
获取待插值维度的若干个目标维度；Obtain several target dimensions of the dimension to be interpolated;
根据待插值维度上每一单维度数据的若干个数据对与每一数据对的数据变化差异及间隔时间，获取待插值维度上每一单维度数据的第一影响权重；Obtain the first influence weight of each single-dimensional data on the dimension to be interpolated according to the data change difference and interval time between several data pairs of each single-dimensional data on the dimension to be interpolated and each data pair;
获取待插值维度上每一采样时间点的若干个待分析目标维度，并获取待插值维度上每一采样时间点在每一待分析目标维度上的第二影响权重，根据待插值维度的每一单维度数据的第一影响权重、待插值维度上每一采样时间点在每一待分析目标维度上的第二影响权重，获取待插值维度的每一单维度数据的影响权重值；Obtain several target dimensions to be analyzed at each sampling time point in the dimension to be interpolated, and obtain the second influence weight of each sampling time point in the dimension to be interpolated on each target dimension to be analyzed, according to each dimension to be interpolated The first influence weight of the single-dimensional data, the second influence weight of each sampling time point on each target dimension to be analyzed in the dimension to be interpolated, and the influence weight value of each single-dimensional data of the dimension to be interpolated;
根据影响权重值对待插值维度进行插值处理，获取不同监测点的待插值维度的数据趋势项序列，根据数据趋势项序列获取两个监测点的待插值维度的相似性，根据相似性构建相似性散点图，根据相似性散点图异常检测的结果进行边坡异常监测。Perform interpolation processing on the dimensions to be interpolated according to the impact weight value, obtain the data trend item sequence of the dimension to be interpolated at different monitoring points, obtain the similarity of the dimensions to be interpolated at two monitoring points according to the sequence of data trend items, and construct a similarity distribution based on the similarity. Slope anomaly monitoring based on the results of anomaly detection in similarity scatter plots.
可选地，所述待插值维度上每一单维度数据的若干个数据对与每一数据对的数据变化差异及间隔时间，的获取方法如下：Optionally, the data change difference and interval time between several data pairs of each single-dimensional data on the dimension to be interpolated and each data pair are obtained as follows:
记关注数据的前局部范围内的任意一数据为目标数据，记目标数据与关注数据的采样时间点间隔为目标间隔，将关注数据的后局部范围内与关注数据的采样时间点间隔为目标间隔的数据记为目标数据的对比数据，将目标数据与对比数据记为关注数据的数据对；Record any data in the front partial range of the concerned data as the target data, mark the interval between the target data and the sampling time point of the concerned data as the target interval, and record the interval between the sampling time points between the rear partial range of the concerned data and the concerned data as the target interval Record the data of the target data as the comparative data of the target data, and record the target data and the comparative data as the data pair of the concerned data;
记关注数据的任意一数据对为关注数据对，将关注数据对中属于关注数据的前局部范围的数据记为关注数据对的前范围，将关注数据对中属于关注数据的后局部范围内的数据记为关注数据对的后范围，将前范围内每一数据与后范围内每一数据的差值的绝对值的均值记为关注数据对的数据变化差异；获取关注数据对中每一单维度数据与关注数据的采样时间点的差值的绝对值，记为关注数据对的间隔时间。Record any data pair of the concerned data as the concerned data pair, record the data in the concerned data pair that belongs to the front local range of the concerned data as the concerned data pair’s front range, and record the concerned data pair that belongs to the concerned data’s rear local range The data is recorded as the back range of the concerned data pair, and the mean value of the absolute value of the difference between each data in the front range and each data in the back range is recorded as the data change difference of the concerned data pair; The absolute value of the difference between the sampling time points of the dimension data and the concerned data is recorded as the interval time of the concerned data pair.
可选地，所述根据待插值维度上每一单维度数据的若干个数据对与每一数据对的数据变化差异及间隔时间，获取待插值维度上每一单维度数据的第一影响权重，计算公式如下：Optionally, the first influence weight of each single-dimensional data on the dimension to be interpolated is obtained according to the data change difference and interval time between several data pairs of each single-dimensional data on the dimension to be interpolated and each data pair, Calculated as follows:
其中，
可选地，所述获取待插值维度上每一采样时间点的若干个待分析目标维度，并获取待插值维度上每一采样时间点在每一待分析目标维度上的第二影响权重，包括的具体步骤如下：Optionally, the acquiring several target dimensions to be analyzed at each sampling time point on the dimension to be interpolated, and acquiring the second influence weight on each target dimension to be analyzed at each sampling time point on the dimension to be interpolated includes The specific steps are as follows:
获取待插值维度的每一目标维度的目标维度频次散点图，根据目标维度频次散点图获取待插值维度的任意两个目标维度的若干个匹配点对，并获取每一匹配点对的重复匹配次数与匹配距离，根据待插值维度的任意两个目标维度的每一匹配点对的重复匹配次数与匹配距离，获取待插值维度的任意两个目标维度的每一匹配点对的待调整程度，根据待调整程度得到待插值维度的每一调整后的目标维度；Obtain the target dimension frequency scattergram of each target dimension of the dimension to be interpolated, obtain several matching point pairs of any two target dimensions of the dimension to be interpolated according to the target dimension frequency scattergram, and obtain the repetition of each matching point pair Matching times and matching distance, according to the repeated matching times and matching distance of each matching point pair of any two target dimensions of the dimension to be interpolated, obtain the degree to be adjusted for each matching point pair of any two target dimensions of the dimension to be interpolated , obtain each adjusted target dimension of the dimension to be interpolated according to the degree to be adjusted;
记待插值维度的任意一采样时间点为目标时间点，获取所有含有目标时间点的待插值维度的调整后的目标维度，记为待插值维度的待分析目标维度，记待分析目标维度中任意一调整后的目标维度为目标对比维度，获取目标对比维度中在目标时间点前的所有数据与待插值维度在目标时间点前的所有数据的DTW距离，记为待插值维度的每一采样时间点在目标对比维度上的第二影响权重。Record any sampling time point of the dimension to be interpolated as the target time point, obtain all the adjusted target dimensions of the dimension to be interpolated containing the target time point, record it as the target dimension to be analyzed of the dimension to be interpolated, record any of the target dimensions to be analyzed The adjusted target dimension is the target comparison dimension, and the DTW distance between all the data in the target comparison dimension before the target time point and all the data in the dimension to be interpolated before the target time point is obtained, and recorded as each sampling time of the dimension to be interpolated The second influence weight of the point on the target contrast dimension.
可选地，所述根据待插值维度的任意两个目标维度的每一匹配点对的重复匹配次数与匹配距离，获取待插值维度的任意两个目标维度的每一匹配点对的待调整程度，计算公式如下：Optionally, according to the repeated matching times and matching distance of each matching point pair of any two target dimensions of the dimension to be interpolated, the degree to be adjusted of each matching point pair of any two target dimensions of the dimension to be interpolated is acquired ,Calculated as follows:
其中，
可选地，所述根据待插值维度的每一单维度数据的第一影响权重、待插值维度上每一采样时间点在每一待分析目标维度上的第二影响权重，获取待插值维度的每一单维度数据的影响权重值，包括的具体步骤如下：Optionally, according to the first influence weight of each single-dimensional data of the dimension to be interpolated and the second influence weight of each sampling time point on the dimension to be interpolated on each target dimension to be analyzed, the The influence weight value of each single-dimensional data includes the following specific steps:
获取待插值维度散点图，记待插值维度的任意一采样时间点为关注时间点，将待
插值维度中关注时间点对应的单维度数据为关注数据，预设范围长度
在待插值维度散点图中将关注数据的前局部范围、关注数据的后局部范围及关注数据中相邻采样时间点对应的散点进行连线，获取每一连线的斜率值，获取所有斜率值的方差，记为关注时间点的数据波动程度；In the scatter diagram of the dimension to be interpolated, connect the front local range of the concerned data, the rear local range of the concerned data, and the scattered points corresponding to the adjacent sampling time points in the concerned data, and obtain the slope value of each connection, and obtain all The variance of the slope value is recorded as the degree of data fluctuation at the time point of interest;
其中，
可选地，所述根据目标维度频次散点图获取待插值维度的任意两个目标维度的若干个匹配点对，并获取每一匹配点对的重复匹配次数与匹配距离，包括的具体步骤如下：Optionally, the acquisition of several matching point pairs of any two target dimensions of the dimension to be interpolated according to the frequency scatter diagram of the target dimension, and obtaining the repeated matching times and matching distance of each matching point pair include the following specific steps :
记待插值维度的任意一目标维度为第一待对比维度，对第一待对比维度数据频次散点图进行曲线拟合，得到第一待对比维度频次曲线，记待插值维度的目标维度中除第一待对比维度外的任意一单维度为第二待对比维度，对第二待对比维度数据频次散点图进行曲线拟合，得到第二待对比维度频次曲线，利用DTW算法对第一待对比维度频次曲线与第二待对比维度频次曲线进行匹配，获取所有匹配点对，记为第一待对比维度与第二待对比维度的匹配点对；Record any target dimension of the dimension to be interpolated as the first dimension to be compared, perform curve fitting on the data frequency scatter diagram of the first dimension to be compared, and obtain the frequency curve of the first dimension to be compared, record the target dimension of the dimension to be interpolated except Any single dimension other than the first dimension to be compared is the second dimension to be compared. Curve fitting is performed on the data frequency scatter diagram of the second dimension to be compared to obtain the frequency curve of the second dimension to be compared. The frequency curve of the comparison dimension is matched with the frequency curve of the second dimension to be compared, and all matching point pairs are obtained, which are recorded as the pair of matching points between the first dimension to be compared and the second dimension to be compared;
记任意一匹配点对为关注点对，记关注点对中属于第一待对比维度频次曲线的点为第一关注点，记关注点对中属于第二待对比维度频次曲线的点为第二关注点，获取第一关注点与第二待对比维度频次曲线匹配的点的个数记为第一关注点的匹配个数，获取第二关注点与第一待对比维度频次曲线匹配的点的个数记为第二关注点的匹配个数，将第一关注点的匹配个数与第二关注点的匹配个数的最大值记为关注点对的重复匹配次数，若第一关注点的匹配个数大于等于第二关注点的匹配个数，记第一关注点与第二待对比维度频次曲线匹配的点的欧式距离均值为关注点对的匹配距离，若第一关注点的匹配个数小于第二关注点的匹配个数，记第二关注点与第一待对比维度频次曲线匹配的点的欧式距离均值为关注点对的匹配距离。Record any pair of matching points as a pair of attention points, remember that the point in the attention point pair that belongs to the frequency curve of the first dimension to be compared is the first attention point, and remember the point in the attention point pair that belongs to the frequency curve of the second dimension to be compared is the second Concern points, get the number of points matching the first point of interest and the frequency curve of the second dimension to be compared, and record it as the number of matches of the first point of interest, and obtain the number of points matching the second point of interest and the frequency curve of the first dimension to be compared The number is recorded as the matching number of the second attention point, and the maximum value of the matching number of the first attention point and the matching number of the second attention point is recorded as the repeated matching times of the attention point pair. The number of matches is greater than or equal to the number of matches of the second point of interest. The average Euclidean distance between the first point of interest and the point matching the frequency curve of the second dimension to be compared is the matching distance of the pair of points of interest. If the number of matches of the first point of interest If the number is less than the matching number of the second attention point, record the average Euclidean distance between the second attention point and the matching point of the frequency curve of the first dimension to be compared as the matching distance of the attention point pair.
可选地，所述根据数据趋势项序列获取两个监测点的待插值维度的相似性，包括的具体步骤如下：Optionally, said obtaining the similarity of the dimensions to be interpolated of two monitoring points according to the sequence of data trend items includes the following specific steps:
记任意两个监测点的待插值维度为第一位移量维度与第二位移量维度；Note that the dimensions to be interpolated for any two monitoring points are the first displacement dimension and the second displacement dimension;
其中，
可选地，所述根据相似性构建相似性散点图，根据相似性散点图异常检测的结果进行边坡异常监测，包括的具体步骤如下：Optionally, constructing a similarity scatter diagram according to the similarity, and performing slope anomaly monitoring according to the result of abnormal detection of the similarity scatter diagram, the specific steps included are as follows:
记任意一监测点的待插值维度为目标位移量维度，以监测点序号为横坐标，以每一监测点的待插值维度与目标位移量维度的相似性为纵坐标，构建直角坐标系，构建相似性散点图；Record the dimension to be interpolated at any monitoring point as the target displacement dimension, take the serial number of the monitoring point as the abscissa, and take the similarity between the dimension to be interpolated and the target displacement dimension of each monitoring point as the ordinate, construct a rectangular coordinate system, and construct similarity scatter plot;
使用LOF算法在直角坐标系中进行异常检测，将LOF值大于
本发明的技术方案的有益效果是：本发明对待插值的维度的数据进行分析，首先获取与待插值的维度相关的维度数据，在这些维度数据中获取单个维度对待插值的维度的数据获取其影响程度；在对当前数据处理过程中获取目标维度对待插值维度的数据，通过不改变维度对待插值维度的影响程度下，调整维度数据的分布特征，并与当前数据的分布特征计算相似度，来计算维度数据的影响程度来自适应获取数据拟合权重。其中在获取影响程度的过程中，本案综合分析了数据待插值时间点的数据波动程度，综合考虑自身数据的分布以及其他维度对待插值维度的数据的影响来获取自身相邻时间点的第一影响权重值以及其他目标维度对待插值维度的影响，来综合获取待插值时间点的受到影响程度来进行数据拟合，避免了传统的数据拟合过程中，没有考虑边坡发生形变等病害由于多种原因共同造成的缺点，综合考虑多种传感器之间的互相影响来进行准确的插值，进而在后续的数据异常检测预警过程中，得到准确的监测结果。The beneficial effects of the technical solution of the present invention are: the present invention analyzes the data of the dimension to be interpolated, first obtains the dimension data related to the dimension to be interpolated, and obtains the data of the dimension to be interpolated in a single dimension in these dimension data to obtain its influence degree; in the current data processing process, obtain the data of the target dimension to treat the interpolation dimension, adjust the distribution characteristics of the dimension data without changing the influence degree of the dimension to the interpolation dimension, and calculate the similarity with the distribution characteristics of the current data to calculate The degree of influence of dimension data comes from adaptive acquisition of data fitting weights. Among them, in the process of obtaining the degree of influence, this case comprehensively analyzes the degree of data fluctuation at the time point of the data to be interpolated, and comprehensively considers the distribution of its own data and the influence of other dimensions on the data of the interpolation dimension to obtain the first influence of its own adjacent time point The influence of the weight value and other target dimensions on the interpolation dimension is used to comprehensively obtain the degree of influence of the time point to be interpolated for data fitting, avoiding the traditional data fitting process that does not consider slope deformation and other diseases due to various For the shortcomings caused by common reasons, the interaction between multiple sensors is comprehensively considered to perform accurate interpolation, and then in the subsequent data anomaly detection and early warning process, accurate monitoring results can be obtained.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.
图1为本发明一种城市绿地规划用生态景观边坡监测方法的步骤流程图。Fig. 1 is a flow chart of the steps of an ecological landscape slope monitoring method for urban green space planning according to the present invention.
具体实施方式Detailed ways
为了更进一步阐述本发明为达成预定发明目的所采取的技术手段及功效，以下结合附图及较佳实施例，对依据本发明提出的一种城市绿地规划用生态景观边坡监测方法，其具体实施方式、结构、特征及其功效，详细说明如下。在下述说明中，不同的“一个实施例”或“另一个实施例”指的不一定是同一实施例。此外，一或多个实施例中的特定特征、结构或特点可由任何合适形式组合。In order to further explain the technical means and effects that the present invention takes to achieve the intended purpose of the invention, below in conjunction with the accompanying drawings and preferred embodiments, a method for monitoring ecological landscape slopes for urban green space planning proposed according to the present invention, its specific Embodiments, structures, features and effects thereof are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures or characteristics of one or more embodiments may be combined in any suitable manner.
除非另有定义，本文所使用的所有的技术和科学术语与属于本发明的技术领域的技术人员通常理解的含义相同。Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field of the invention.
下面结合附图具体的说明本发明所提供的一种城市绿地规划用生态景观边坡监测方法的具体方案。A specific scheme of a method for monitoring ecological landscape slopes for urban green space planning provided by the present invention will be described in detail below in conjunction with the accompanying drawings.
请参阅图1，其示出了本发明一个实施例提供的一种城市绿地规划用生态景观边坡监测方法的步骤流程图，该方法包括以下步骤：Please refer to Fig. 1, it shows a kind of flow chart of the steps of ecological landscape slope monitoring method for urban green space planning that one embodiment of the present invention provides, and the method comprises the following steps:
步骤S001、采集生态景观边坡处多个传感器数据记为若干个单维度数据，设定待插值维度。Step S001, collecting multiple sensor data on the slope of the ecological landscape and recording it as several single-dimensional data, and setting the dimension to be interpolated.
通过在生态景观边坡处若干个监测点安装传感器来采集多种传感器数据：其中包括GNSS地表位仪监测仪（在边坡表面监测点安装设备，该设备主要由GNSS天线、太阳能电池板、主控机箱、支架等构成，可同时测定多点的三维位移）、倾角监测、雨量传感器（采用翻斗式雨量传感器）、地下水位传感器（采用水压计）、地表沉降监测仪（内部设置压力感知设备，监测压地表沉降时压力的变化）、温度传感器、雷达传感器（采集边坡的振动情况）等，数据传输主要通过无线传输方式接收监测数据，然后通过LoRa技术进行数据传输。A variety of sensor data are collected by installing sensors at several monitoring points on the ecological landscape slope: including GNSS surface potential monitors (installed equipment at the slope surface monitoring points, the equipment is mainly composed of GNSS antennas, solar panels, main Control case, bracket, etc., which can measure three-dimensional displacement of multiple points at the same time), inclination monitoring, rain sensor (using tipping bucket rain sensor), groundwater level sensor (using water pressure gauge), surface subsidence monitor (internal pressure sensing equipment , monitoring the pressure change during the subsidence of the ground surface), temperature sensor, radar sensor (collecting the vibration of the slope), etc., the data transmission mainly receives the monitoring data through wireless transmission, and then transmits the data through LoRa technology.
将单个传感器记为单维度，单维度中每一采样时间点对应的传感器采集的数据记为单维度数据，将多个传感器记为多维度。A single sensor is recorded as a single dimension, the data collected by the sensor corresponding to each sampling time point in the single dimension is recorded as single-dimensional data, and multiple sensors are recorded as multi-dimensional.
记任意一监测点为关注监测点，记关注监测点中任意一单维度为待插值维度，本实施例以关注监测点为例，以待插值维度的单维度数据作为后续进行自适应插值的传感器数据，关注监测点中其他单维度按照待插值维度处理的方式进行自适应插值处理。Record any monitoring point as the monitoring point of interest, and record any single dimension in the monitoring point of interest as the dimension to be interpolated. This embodiment takes the monitoring point of interest as an example, and uses the single-dimensional data of the dimension to be interpolated as the sensor for subsequent adaptive interpolation For the data, focus on other single dimensions in the monitoring point for adaptive interpolation processing in the same way as the dimensions to be interpolated.
步骤S002、获取待插值维度的若干个目标维度。Step S002, acquiring several target dimensions of the dimensions to be interpolated.
需要说明的是，由于不同维度的数据之间存在一定的联系，即对应的某些维度数据的变化会造成当前维度数据的变化，并且不同维度下的数据的影响程度不同的，因此在对当前维度下进行数据插值的过程中，若仅考虑当前维度自身的相邻时间点下的数据分布特征来获取插值权重，会产生较大的误差。因此本案对单个维度的数据（待插值的维度）进行分析，首先获取与待插值的维度相关的维度数据，在这些维度数据中获取单个维度对待插值的维度的数据获取其影响程度；在对当前数据处理过程中获取目标维度对待插值维度的数据，通过不改变维度对待插值维度的影响程度下，调整维度数据的分布特征，并与当前数据的分布特征计算相似度，来计算维度数据的影响程度来自适应获取数据拟合权重。It should be noted that because there is a certain relationship between data in different dimensions, that is, changes in the corresponding dimension data will cause changes in the current dimension data, and the impact of data in different dimensions is different, so in the current In the process of data interpolation in the dimension, if only the data distribution characteristics at the adjacent time points of the current dimension itself are considered to obtain the interpolation weight, a large error will occur. Therefore, this case analyzes the data of a single dimension (dimension to be interpolated), first obtains the dimensional data related to the dimension to be interpolated, and obtains the data of a single dimension to be interpolated from these dimensional data to obtain its influence; In the process of data processing, the data of the interpolation dimension of the target dimension is obtained, and the distribution characteristics of the dimension data are adjusted without changing the influence of the dimension on the interpolation dimension, and the similarity with the distribution characteristics of the current data is calculated to calculate the influence degree of the dimension data to obtain data fitting weights adaptively.
进一步需要说明的是，在分析待插值的维度的每个时间点的数据拟合权重过程中，由于在所有的维度中仅有部分维度与待插值的维度相关，因此首先需要获取与待插值的维度相关的维度数据，因此本发明通过历史数据来获取与待插值维度相关的维度数据。It should be further noted that, in the process of analyzing the data fitting weight of each time point of the dimension to be interpolated, since only some of the dimensions are related to the dimension to be interpolated, it is first necessary to obtain the Dimension data related to the dimension, so the present invention obtains the dimension data related to the dimension to be interpolated through the historical data.
将多维度中除待插值维度以外的任意一单维度记为对比维度，获取待插值维度与对比维度的所有相同采样时间点，以相同采样时间点对待插值维度与对比维度进行划分，得到若干个划分时间段数据，将任意一时间段数据记为目标时间段，将待插值维度在目标时间段内的相邻时间采样点的单维度数据进行直线连接，对应将对比维度在目标时间段内的相邻时间采样点的单维度数据进行直线连接，在目标时间段中以待插值维度与对比维度对应的时间采样点的值为分段直线的值，获取目标时间段的相关系数，获取所有划分时间段数据的相关系数的均值，记为待插值维度与对比维度的相关程度。Record any single dimension in the multi-dimension except the dimension to be interpolated as the comparison dimension, obtain all the same sampling time points of the dimension to be interpolated and the comparison dimension, divide the interpolation dimension and the comparison dimension at the same sampling time point, and obtain several Divide the time period data, record the data of any time period as the target time period, and connect the single-dimensional data of the adjacent time sampling points with the dimension to be interpolated within the target time period in a straight line, corresponding to the comparison dimension within the target time period The single-dimensional data of adjacent time sampling points are connected by a straight line. In the target time period, the value of the time sampling point corresponding to the dimension to be interpolated and the comparison dimension is the value of the segmented line, and the correlation coefficient of the target time period is obtained, and all divisions are obtained. The average value of the correlation coefficient of the time period data is recorded as the degree of correlation between the dimension to be interpolated and the dimension to be compared.
预设相关程度阈值
至此，得到每一单维度的若干个目标维度。So far, several target dimensions of each single dimension have been obtained.
步骤S003、获取待插值维度散点图，获取待插值维度上每一采样时间点的数据波动程度，获取待插值维度上每一单维度数据的若干个数据对并获取每一数据对的数据变化差异及间隔时间，根据待插值维度上每一单维度数据的数据对的个数及每一数据对的数据变化差异、间隔时间获取待插值维度上每一单维度数据的第一影响权重。Step S003, obtain the scatter diagram of the dimension to be interpolated, obtain the degree of data fluctuation at each sampling time point on the dimension to be interpolated, obtain several data pairs of each single-dimensional data on the dimension to be interpolated, and obtain the data change of each data pair Difference and interval time, according to the number of data pairs of each single-dimensional data on the dimension to be interpolated, the data change difference of each data pair, and the interval time to obtain the first influence weight of each single-dimensional data on the dimension to be interpolated.
需要说明的是，对当前数据的目标维度和对应当前的数据进行影响程度的分析，由于不同维度的数据之间存在一定的联系，即对应的某些维度数据的变化会造成当前维度数据的变化，并且不同维度下的数据的影响程度不同的，因此在对当前维度下进行数据插值的过程中需要同时分析自身的相邻时间点下的数据分布特征，还需要考虑目标维度的数据的影响，但是目标维度对数据的影响程度不同，因此在分析每个时间点的受到影响权重值时需要进行综合分析。It should be noted that when analyzing the influence degree of the target dimension of the current data and the corresponding current data, there is a certain connection between the data of different dimensions, that is, the change of the corresponding dimension data will cause the change of the current dimension data , and the influence of data in different dimensions is different. Therefore, in the process of data interpolation in the current dimension, it is necessary to analyze the data distribution characteristics of its own adjacent time points at the same time, and also need to consider the influence of data in the target dimension. However, the target dimension has different influences on the data, so a comprehensive analysis is required when analyzing the affected weight value at each time point.
由于待插值维度的数据波动程度不同，若某个时间段的待插值维度的数据波动程度较小，则每个时间点的待插值维度的数据变化较小，则对应的该时间段内的待插值维度的数据较为稳定，则该时间段待插值维度受到的影响主要是自身相邻时间点下的数据分布特征的影响；若该时间段的待插值维度的数据波动程度较大，则每个时间点的待插值维度的数据变化较大，则对应的该时间段待插值维度受到的影响主要是目标维度的数据分布特征的影响。Due to the different degrees of data fluctuation in the dimension to be interpolated, if the data fluctuation degree of the dimension to be interpolated in a certain time period is small, the data of the dimension to be interpolated at each time point has a small change, and the corresponding time period in the dimension to be interpolated If the data of the interpolation dimension is relatively stable, the impact on the dimension to be interpolated during this period is mainly the influence of the data distribution characteristics at its adjacent time points; if the data of the dimension to be interpolated fluctuates greatly during this period, then each If the data of the dimension to be interpolated at the time point changes greatly, the impact on the dimension to be interpolated in the corresponding time period is mainly the influence of the data distribution characteristics of the target dimension.
在获取目标维度的数据分布特征的影响过程中，由于目标维度中的数据分布特征与目标维度中每一单维度的数据分布特征存在一定的相似性，若仅根据目标维度和待插值维度的相关程度作为影响程度，会造成的较大的影响误差，因此本发明在对当前数据处理过程中获取目标维度对待插值维度的数据，通过不改变维度对待插值维度的影响程度下，调整维度数据的分布特征，并与当前数据的分布特征计算相似度来对步骤S002中计算得到的相关程度进行校正，来计算维度数据的受到影响权重值来自适应获取数据拟合权重。In the process of obtaining the influence of the data distribution characteristics of the target dimension, due to the similarity between the data distribution characteristics of the target dimension and the data distribution characteristics of each single dimension in the target dimension, if only based on the correlation between the target dimension and the dimension to be interpolated As the degree of influence, it will cause a large influence error. Therefore, the present invention acquires the data of the target dimension and treats the interpolation dimension in the current data processing process, and adjusts the distribution of dimension data without changing the degree of influence of the dimension on the interpolation dimension. feature, and calculate the similarity with the distribution feature of the current data to correct the degree of correlation calculated in step S002, to calculate the affected weight value of the dimension data to adaptively obtain the data fitting weight.
以每一单维度的每一采样时间点为横坐标，每一采样时间点对应的单维度数据为纵坐标，得到每一单维度散点图。Taking each sampling time point of each single dimension as the abscissa, and the single-dimensional data corresponding to each sampling time point as the vertical coordinate, a scatter diagram of each single dimension is obtained.
记待插值维度的任意一采样时间点为关注时间点，将待插值维度中关注时间点对
应的单维度数据为关注数据，设定范围长度
在待插值维度散点图中将关注数据的前局部范围、关注数据的后局部范围及关注数据中相邻采样时间点对应的散点进行连线，获取每一连线的斜率值，获取所有斜率值的方差，记为关注时间点的数据波动程度，获取待插值维度中每一关注时间点的数据波动程度，进行线性归一化处理。In the scatter diagram of the dimension to be interpolated, connect the front local range of the concerned data, the rear local range of the concerned data, and the scattered points corresponding to the adjacent sampling time points in the concerned data, and obtain the slope value of each connection, and obtain all The variance of the slope value is recorded as the degree of data fluctuation at the time point of interest, and the degree of data fluctuation at each time point of interest in the dimension to be interpolated is obtained for linear normalization.
至此，得到待插值维度上每一采样时间点的数据波动程度。So far, the degree of data fluctuation at each sampling time point on the dimension to be interpolated is obtained.
记关注数据的前局部范围内的任意一数据为目标数据，记目标数据与关注数据的采样时间点间隔为目标间隔，将关注数据的后局部范围内与关注数据的采样时间点间隔为目标间隔的数据记为目标数据的对比数据，将目标数据与对比数据记为关注数据的数据对。Record any data in the front partial range of the concerned data as the target data, mark the interval between the target data and the sampling time point of the concerned data as the target interval, and record the interval between the sampling time points between the rear partial range of the concerned data and the concerned data as the target interval Record the data of the target data as the comparative data of the target data, and record the target data and the comparative data as the data pair of the concerned data.
若关注数据的前局部范围内的数据个数与后局部范围内的数据个数不相等，当关注数据的前局部范围内的数据个数小于后局部范围内的数据个数，此时记关注数据的前局部范围内与关注数据的采样时间点间隔最大的数据为第一待判断数据，将关注数据的后局部范围内，与关注数据的采样时间点间隔大于等于第一待判断数据与关注数据的采样时间点间隔的数据记为第一待判断数据的对比数据，将第一待判断数据与第一待判断数据的所有对比数据记为关注数据的数据对；当关注数据的前局部范围内的数据个数大于后局部范围内的数据个数，此时记关注数据的后局部范围内与关注数据的采样时间点间隔最大的数据为第二待判断数据，将关注数据的前局部范围内，与关注数据的采样时间点间隔大于等于第二待判断数据与关注数据的采样时间点间隔的数据记为第二待判断数据的对比数据，将第二待判断数据与第二待判断数据的所有对比数据记为关注数据的数据对。If the number of data in the front local range of the concerned data is not equal to the number of data in the back local range, when the number of data in the front local range of the concerned data is less than the number of data in the back local range, record attention at this time The data with the largest interval between the sampling time point of the data to be judged and the data to be judged in the front local range of the data is the first data to be judged, and the data to be judged in the back local range of the data to be concerned with, the interval between the sampling time point of the data to be judged is greater than or equal to the first data to be judged and the data to be judged The data at the sampling time interval of the data is recorded as the comparison data of the first data to be judged, and all the comparative data between the first data to be judged and the first data to be judged are recorded as the data pairs of the concerned data; when the front local range of the concerned data The number of data in is greater than the number of data in the back local range. At this time, the data with the largest interval between the back local range of the concerned data and the sampling time point of the concerned data is the second data to be judged, and the front local range of the concerned data will be In , the data whose sampling time point interval with the concerned data is greater than or equal to the sampling time point interval between the second data to be judged and the concerned data is recorded as the comparison data of the second data to be judged, and the second data to be judged and the second data to be judged All comparative data of are recorded as the data pairs of the data of interest.
记关注数据的任意一数据对为关注数据对，将关注数据对中属于关注数据的前局部范围的数据记为关注数据对的前范围，将关注数据对中属于关注数据的后局部范围内的数据记为关注数据对的后范围，将前范围内每一数据与后范围内每一数据的差值的绝对值的均值记为关注数据对的数据变化差异；获取关注数据对中每一单维度数据与关注数据的采样时间点的差值的绝对值，记为关注数据对的间隔时间。Record any data pair of the concerned data as the concerned data pair, record the data in the concerned data pair that belongs to the front local range of the concerned data as the concerned data pair’s front range, and record the concerned data pair that belongs to the concerned data’s rear local range The data is recorded as the back range of the concerned data pair, and the mean value of the absolute value of the difference between each data in the front range and each data in the back range is recorded as the data change difference of the concerned data pair; The absolute value of the difference between the sampling time points of the dimension data and the concerned data is recorded as the interval time of the concerned data pair.
至此，得到待插值维度上每一单维度数据的数据对，得到待插值维度上每一单维度数据的每一数据对的数据变化差异及间隔时间。So far, the data pair of each single-dimensional data on the dimension to be interpolated is obtained, and the data change difference and interval time of each data pair of each single-dimensional data on the dimension to be interpolated are obtained.
具体的，以待插值维度的第
其中，
至此，得到待插值维度上每一单维度数据的第一影响权重。So far, the first influence weight of each single-dimensional data on the dimension to be interpolated is obtained.
步骤S004、获取待插值维度的每一目标维度的目标维度频次散点图，根据目标维度频次散点图获取待插值维度的任意两个目标维度的若干个匹配点对并获取每一匹配点对的待调整程度，根据待调整程度得到待插值维度的每一调整后的目标维度，获取待插值维度上每一采样时间点的若干个待分析目标维度并获取待插值维度上每一采样时间点在每一待分析目标维度上的第二影响权重；获取待插值维度的每一单维度数据的影响权重值。Step S004, obtain the target dimension frequency scatter diagram of each target dimension of the dimension to be interpolated, obtain several matching point pairs of any two target dimensions of the dimension to be interpolated according to the target dimension frequency scatter diagram, and obtain each matching point pair According to the degree of adjustment to be adjusted, each adjusted target dimension of the dimension to be interpolated is obtained, and several target dimensions to be analyzed at each sampling time point on the dimension to be interpolated are obtained and each sampling time point on the dimension to be interpolated is obtained The second influence weight on each target dimension to be analyzed; obtain the influence weight value of each single-dimensional data of the dimension to be interpolated.
对待插值维度的每一目标维度上的所有单维度数据进行线性归一化处理，记待插值维度的任意一目标维度为第一待对比维度，统计第一待对比维度中每一单维度数据出现的次数，以待对比数据中由小到大的每一单维度数据为横坐标，以每一单维度数据出现的次数为纵坐标建立直角坐标系，得到第一待对比维度频次散点图，对第一待对比维度频次散点图进行曲线拟合，得到第一待对比维度频次曲线，记待插值维度的目标维度中除第一待对比维度外的任意一单维度为第二待对比维度，以第一待对比维度频次曲线的获取方式获取第二待对比维度频次曲线，利用DTW算法对第一待对比维度频次曲线与第二待对比维度频次曲线进行匹配，获取所有匹配点对，记为第一待对比维度与第二待对比维度的匹配点对；需要说明的是，每一匹配点对中一个点属于第一待对比维度频次曲线，另一个点属于第二待对比维度频次曲线，DTW算法为现有技术。Perform linear normalization processing on all single-dimensional data on each target dimension of the interpolation dimension, record any target dimension of the interpolation dimension as the first dimension to be compared, and count the occurrence of each single-dimensional data in the first dimension to be compared The number of times of each single-dimensional data from small to large in the data to be compared is taken as the abscissa, and the number of occurrences of each single-dimensional data is used as the vertical coordinate to establish a rectangular coordinate system to obtain the frequency scatter diagram of the first dimension to be compared. Perform curve fitting on the frequency scatter diagram of the first dimension to be compared to obtain the frequency curve of the first dimension to be compared, and record any single dimension in the target dimension of the dimension to be compared except the first dimension to be compared as the second dimension to be compared , obtain the frequency curve of the second dimension to be compared by the acquisition method of the frequency curve of the first dimension to be compared, use the DTW algorithm to match the frequency curve of the first dimension to be compared with the frequency curve of the second dimension to be compared, obtain all matching point pairs, record is the pair of matching points between the first dimension to be compared and the second dimension to be compared; it should be noted that one point in each pair of matching points belongs to the frequency curve of the first dimension to be compared, and the other point belongs to the frequency curve of the second dimension to be compared , the DTW algorithm is a prior art.
记任意一匹配点对为关注点对，记关注点对中属于第一待对比维度频次曲线的点为第一关注点，记关注点对中属于第二待对比维度频次曲线的点为第二关注点，获取第一关注点与第二待对比维度频次曲线匹配的点的个数记为第一关注点的匹配个数，获取第二关注点与第一待对比维度频次曲线匹配的点的个数记为第二关注点的匹配个数，将第一关注点的匹配个数与第二关注点的匹配个数的最大值记为关注点对的重复匹配次数，若第一关注点的匹配个数大于等于第二关注点的匹配个数，记第一关注点与第二待对比维度频次曲线匹配的点的欧式距离均值为关注点对的匹配距离，若第一关注点的匹配个数小于第二关注点的匹配个数，记第二关注点与第一待对比维度频次曲线匹配的点的欧式距离均值为关注点对的匹配距离。Record any pair of matching points as a pair of attention points, remember that the point in the attention point pair that belongs to the frequency curve of the first dimension to be compared is the first attention point, and remember the point in the attention point pair that belongs to the frequency curve of the second dimension to be compared is the second Concern points, get the number of points matching the first point of interest and the frequency curve of the second dimension to be compared, and record it as the number of matches of the first point of interest, and obtain the number of points matching the second point of interest and the frequency curve of the first dimension to be compared The number is recorded as the matching number of the second attention point, and the maximum value of the matching number of the first attention point and the matching number of the second attention point is recorded as the repeated matching times of the attention point pair. The number of matches is greater than or equal to the number of matches of the second point of interest. The average Euclidean distance between the first point of interest and the point matching the frequency curve of the second dimension to be compared is the matching distance of the pair of points of interest. If the number of matches of the first point of interest If the number is less than the matching number of the second attention point, record the average Euclidean distance between the second attention point and the matching point of the frequency curve of the first dimension to be compared as the matching distance of the attention point pair.
至此，得到待插值维度的任意两个目标维度的匹配点对，得到每一匹配点对的重复匹配次数与匹配距离。So far, the matching point pairs of any two target dimensions of the dimension to be interpolated are obtained, and the repeated matching times and matching distance of each matching point pair are obtained.
具体的，以待插值维度的第
其中，
若待插值维度的第
至此，得到待插值维度的任意两个目标维度的匹配点对的待调整程度。So far, the degree to be adjusted of the matching point pairs of any two target dimensions of the dimension to be interpolated is obtained.
设定调整阈值
由于需保证进行调整后的数据分布特征不发生较大变化，因此将需要调整的点进
行步长为0.05进行迭代调整，获取待插值维度的调整后的每一目标维度与每一目标维度的
DTW距离，对DTW距离使用exp函数进行反向归一化，即
至此，得到待插值维度的调整后的目标维度。So far, the adjusted target dimension of the dimension to be interpolated is obtained.
记待插值维度的任意一采样时间点为目标时间点，获取所有含有目标时间点的待插值维度的调整后的目标维度，记为待插值维度的待分析目标维度，记待分析目标维度中任意一调整后的目标维度为目标对比维度，获取目标对比维度的在目标时间点前的所有数据与待插值维度在目标时间点前的所有数据的DTW距离，记为待插值维度的每一采样时间点在目标对比维度上的第二影响权重，对待插值维度的每一采样时间点在待分析目标维度中所有调整后的目标维度的第二影响权重进行线性归一化处理。Record any sampling time point of the dimension to be interpolated as the target time point, obtain all the adjusted target dimensions of the dimension to be interpolated containing the target time point, record it as the target dimension to be analyzed of the dimension to be interpolated, record any of the target dimensions to be analyzed The adjusted target dimension is the target comparison dimension, and the DTW distance between all the data in the target comparison dimension before the target time point and all the data in the dimension to be interpolated before the target time point is obtained, and recorded as each sampling time of the dimension to be interpolated The second influence weight of the point on the target comparison dimension is linearly normalized to the second influence weights of all adjusted target dimensions in the target dimension to be analyzed at each sampling time point of the dimension to be interpolated.
至此，得到待插值维度上每一采样时间点在每一待分析目标维度上的第二影响权重。So far, the second influence weight of each sampling time point on each target dimension to be analyzed on the dimension to be interpolated is obtained.
具体的，以待插值维度的第
其中，
若
至此，得到待插值维度的每一单维度数据的影响权重值。So far, the influence weight value of each single-dimensional data of the dimension to be interpolated is obtained.
步骤S005、根据待插值维度的每一单维度数据的影响权重值得到的插值结果进行边坡监测。Step S005 , perform side slope monitoring according to the interpolation result obtained from the influence weight value of each single-dimensional data of the dimension to be interpolated.
根据上述计算得到的影响权重值，对待插值维度进行自适应插值：其中插值的结
果采用偏最小二乘法进行数据插值，并根据受到影响权重值的大小对插值结果进行校正，
使得在考虑自身相邻的数据分布特征的基础上，还考虑到其他目标维度的影响，第
对上述处理后的每一单维度的单维度数据进行进一步处理，由于边坡发生变化属于整体的变化，因此为了准确的进行边坡监测，计算所有监测点的同一单维度的数据变化。The single-dimensional data of each single dimension after the above processing is further processed. Since the change of the slope belongs to the overall change, in order to accurately monitor the slope, the data change of the same single dimension of all monitoring points is calculated.
本实施例以GNSS地表位仪监测仪采集的位移量维度为例，将位移量维度作为待插值维度，根据不同监测点的位移量维度中数据的相似性进行边坡异常监测，由于为了避免边坡上地层结构的影响以及传感器灵敏度的影响，本实施例采用STL时间序列分割算法得到不同监测点的位移量维度的数据趋势项序列，STL时间序列分割算法为现有技术，本实施例不再过多赘述，由于数据趋势项序列体现数据趋势特征，即数据总体的趋势变化，本实施例根据数据趋势项序列进行数据相似性分析，即计算不同监测点的位移量维度的数据变化趋势是否相近。In this embodiment, the displacement dimension collected by the GNSS surface potential monitor is taken as an example, and the displacement dimension is used as the dimension to be interpolated, and the abnormal monitoring of the slope is carried out according to the similarity of the data in the displacement dimension of different monitoring points. The influence of stratum structure on the slope and the influence of sensor sensitivity, this embodiment uses the STL time series segmentation algorithm to obtain the data trend item sequence of the displacement dimension of different monitoring points, the STL time series segmentation algorithm is a prior art, and this embodiment no longer To repeat too much, because the data trend item sequence reflects the data trend characteristics, that is, the trend change of the overall data, this embodiment performs data similarity analysis based on the data trend item sequence, that is, calculates whether the data trend of the displacement dimension of different monitoring points is similar .
记任意两个监测点的位移量维度为第一位移量维度与第二位移量维度，使用DTW算法获取第一位移量维度的数据趋势项序列与第二位移量维度的数据趋势项序列的DTW距离。Record the displacement dimensions of any two monitoring points as the first displacement dimension and the second displacement dimension, and use the DTW algorithm to obtain the DTW of the data trend item sequence of the first displacement dimension and the data trend item sequence of the second displacement dimension distance.
具体的，以第一位移量维度
其中，
记任意一监测点的位移量维度为目标位移量维度，以监测点序号为横坐标，以每
一监测点的位移量维度与目标位移量维度的相似性为纵坐标，构建直角坐标系，构建相似
性散点图，使用LOF算法在直角坐标系中进行异常检测，本实施例设定LOF算法中K=5，将LOF
值大于
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of the present invention. within the scope of protection.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504922.5A CN116222670B (en) | 2023-05-08 | 2023-05-08 | A monitoring method for ecological landscape slopes used in urban green space planning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504922.5A CN116222670B (en) | 2023-05-08 | 2023-05-08 | A monitoring method for ecological landscape slopes used in urban green space planning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116222670A true CN116222670A (en) | 2023-06-06 |
| CN116222670B CN116222670B (en) | 2023-07-21 |
Family
ID=86587632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310504922.5A Active CN116222670B (en) | 2023-05-08 | 2023-05-08 | A monitoring method for ecological landscape slopes used in urban green space planning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116222670B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975503A (en) * | 2023-09-22 | 2023-10-31 | 临沂大学 | Soil erosion information management method and system |
| CN117235548A (en) * | 2023-11-15 | 2023-12-15 | 山东济宁运河煤矿有限责任公司 | Coal quality data processing method and intelligent system based on laser firing |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080027690A1 (en) * | 2004-03-31 | 2008-01-31 | Philip Watts | Hazard assessment system |
| CN110826715A (en) * | 2019-11-08 | 2020-02-21 | 江西理工大学 | Improved space-time Kriging interpolation algorithm for encrypting slope monitoring data |
| CN111797079A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Data processing method, device, storage medium and electronic device |
| CN113936228A (en) * | 2021-09-02 | 2022-01-14 | 中国葛洲坝集团第一工程有限公司 | High slope monitoring and early warning system based on UAV data check |
| CN114333249A (en) * | 2022-01-14 | 2022-04-12 | 四川九洲北斗导航与位置服务有限公司 | Landslide warning method and device |
| CN115311821A (en) * | 2022-08-09 | 2022-11-08 | 武汉易特兰瑞科技有限公司 | Geological disaster intelligent monitoring cloud platform based on digital twin technology |
| WO2022242259A1 (en) * | 2021-05-17 | 2022-11-24 | 北京车和家信息技术有限公司 | Data processing method and apparatus, device, and medium |
| CN115987294A (en) * | 2023-03-17 | 2023-04-18 | 北京悦知未来科技有限公司 | Multidimensional data processing method of Internet of things |
| CN116013087A (en) * | 2023-03-27 | 2023-04-25 | 东莞市城建规划设计院 | Traffic flow statistical method based on urban moving vehicle detection |
-
2023
- 2023-05-08 CN CN202310504922.5A patent/CN116222670B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080027690A1 (en) * | 2004-03-31 | 2008-01-31 | Philip Watts | Hazard assessment system |
| CN111797079A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | Data processing method, device, storage medium and electronic device |
| CN110826715A (en) * | 2019-11-08 | 2020-02-21 | 江西理工大学 | Improved space-time Kriging interpolation algorithm for encrypting slope monitoring data |
| WO2022242259A1 (en) * | 2021-05-17 | 2022-11-24 | 北京车和家信息技术有限公司 | Data processing method and apparatus, device, and medium |
| CN113936228A (en) * | 2021-09-02 | 2022-01-14 | 中国葛洲坝集团第一工程有限公司 | High slope monitoring and early warning system based on UAV data check |
| CN114333249A (en) * | 2022-01-14 | 2022-04-12 | 四川九洲北斗导航与位置服务有限公司 | Landslide warning method and device |
| CN115311821A (en) * | 2022-08-09 | 2022-11-08 | 武汉易特兰瑞科技有限公司 | Geological disaster intelligent monitoring cloud platform based on digital twin technology |
| CN115987294A (en) * | 2023-03-17 | 2023-04-18 | 北京悦知未来科技有限公司 | Multidimensional data processing method of Internet of things |
| CN116013087A (en) * | 2023-03-27 | 2023-04-25 | 东莞市城建规划设计院 | Traffic flow statistical method based on urban moving vehicle detection |
Non-Patent Citations (2)
| Title |
|---|
| 郭帅杰;宋绪国;隋孝民;庄仲欣;张磊;: "长昆客运专线铁路路堑边坡监测数据预处理方法", 铁道标准设计, no. 04 * |
| 闫可;程文芳;: "海洋水文观测数据聚类", 计算机应用与软件, no. 11 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116975503A (en) * | 2023-09-22 | 2023-10-31 | 临沂大学 | Soil erosion information management method and system |
| CN116975503B (en) * | 2023-09-22 | 2023-12-05 | 临沂大学 | Soil erosion information management method and system |
| CN117235548A (en) * | 2023-11-15 | 2023-12-15 | 山东济宁运河煤矿有限责任公司 | Coal quality data processing method and intelligent system based on laser firing |
| CN117235548B (en) * | 2023-11-15 | 2024-02-27 | 山东济宁运河煤矿有限责任公司 | Coal quality data processing method and intelligent system based on laser firing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116222670B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116222670A (en) | A monitoring method for ecological landscape slopes used in urban green space planning | |
| CN109034244B (en) | Line loss abnormity diagnosis method and device based on electric quantity curve characteristic model | |
| CN107038717B (en) | A Method for Automatically Analyzing 3D Point Cloud Registration Errors Based on Stereo Grid | |
| CN103631681B (en) | A kind of method of online reparation abnormal data of wind power plant | |
| CN114022035B (en) | Method for evaluating carbon emission of building in urban heat island effect | |
| CN112966856A (en) | Mountain torrent risk prediction method and prediction system | |
| CN119691412B (en) | River channel measurement data preprocessing method based on artificial intelligence | |
| CN109727226A (en) | An automatic generation method of location table based on machine learning | |
| CN118608552A (en) | Building feature line extraction method based on 3D point cloud | |
| CN115455706A (en) | Regional Rock Mass Quality Assessment Method and Related Components Considering Unloading Fracture Effect | |
| CN119716843B (en) | Multi-rainy-area airport bird condition monitoring method and system based on bird detection radar | |
| CN107944219B (en) | Method and device for representing drought and waterlogging disaster-causing characteristics at different time periods | |
| CN112529003A (en) | Instrument panel digital identification method based on fast-RCNN | |
| CN118656773B (en) | Roadbed compaction quality intelligent monitoring method, device and system | |
| CN119785534A (en) | A water level series data monitoring and early warning method based on big data | |
| CN110991730A (en) | Coastal nuclear power station marine disaster physical quantity estimation method based on neural network | |
| CN119247517A (en) | A spatiotemporal prediction method for rainfall kinetic energy based on dual-polarization weather radar observation parameters | |
| CN118644689A (en) | A method and system for correcting forest and grass wetland map patch monitoring data | |
| CN118823243A (en) | Three-dimensional modeling evaluation system and method based on multimodal fusion | |
| CN117809161A (en) | Star-masking refractive index profile data quality evaluation system based on multi-source data | |
| CN116910901A (en) | Intelligent design method for building | |
| CN114049199A (en) | A risk assessment method and system implementation based on consumer credit scenarios | |
| CN115130496A (en) | Anomaly detection method of pipeline pressure signal based on bagging and RM-LOF ensemble single classifier | |
| CN119538164B (en) | Suspended load sediment monitoring precision optimization method | |
| CN119884627B (en) | Positioning data cleaning method and system based on data analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |