[go: up one dir, main page]

CN119962815A - A method and system for assessing the potential dangers of urban lifeline subsidence based on DNN - Google Patents

A method and system for assessing the potential dangers of urban lifeline subsidence based on DNN Download PDF

Info

Publication number
CN119962815A
CN119962815A CN202510015764.6A CN202510015764A CN119962815A CN 119962815 A CN119962815 A CN 119962815A CN 202510015764 A CN202510015764 A CN 202510015764A CN 119962815 A CN119962815 A CN 119962815A
Authority
CN
China
Prior art keywords
urban
settlement
area
feature
city
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202510015764.6A
Other languages
Chinese (zh)
Other versions
CN119962815B (en
Inventor
徐建
王庆
郭杨
李兰娟
许九靖
许少怡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Province Urban Water Supply Security Support Center
Original Assignee
Jiangsu Province Urban Water Supply Security Support Center
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 Jiangsu Province Urban Water Supply Security Support Center filed Critical Jiangsu Province Urban Water Supply Security Support Center
Priority to CN202510015764.6A priority Critical patent/CN119962815B/en
Publication of CN119962815A publication Critical patent/CN119962815A/en
Application granted granted Critical
Publication of CN119962815B publication Critical patent/CN119962815B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明公开了一种基于DNN的城市生命线沉降隐患评估方法、系统，涉及城市沉降监测技术领域，所述评估方法包括以下步骤：对城市的若干个区域进行沉降监测，对任意区域进行城市信息采集，进行数据处理得到一组特征参数集合；对任意特征参数进行筛选得到城市变形环境特征集合；获取任意区域的沉降监测结果，搭建深度神经网络模型进行训练，生成沉降隐患评估模型，对任意区域进行沉降程度评估；对任意区域的沉降情况进行周期性评估，对影响沉降程度评估结果的影响特征进行提取，得到任意影响特征所产生的影响幅度；对任意待评估城市的各个目标区域进行沉降程度评估；绘制城市变形监测易发性图，对存在异常隐患区域进行识别。

The present invention discloses a method and system for assessing the hidden danger of settlement of urban lifelines based on DNN, and relates to the technical field of urban settlement monitoring. The assessment method comprises the following steps: monitoring the settlement of several areas of a city, collecting urban information of any area, and performing data processing to obtain a set of characteristic parameter sets; screening any characteristic parameters to obtain a set of urban deformation environment characteristics; obtaining the settlement monitoring results of any area, building a deep neural network model for training, generating a settlement hidden danger assessment model, and assessing the settlement degree of any area; periodically assessing the settlement of any area, extracting the influencing features that affect the settlement degree assessment results, and obtaining the influence amplitude generated by any influencing features; assessing the settlement degree of each target area of any city to be assessed; drawing a city deformation monitoring susceptibility map, and identifying areas with abnormal hidden dangers.

Description

DNN-based urban lifeline settlement hidden danger assessment method and system
Technical Field
The invention relates to the technical field of urban settlement monitoring, in particular to a DNN-based urban lifeline settlement hidden danger assessment method and system.
Background
However, with various urban activities, urban settlement is difficult to avoid, and urban lifeline settlement hidden dangers refer to safety risks caused by ground settlement or other geological changes in urban infrastructures, and the hidden dangers can seriously affect the normal operation of the cities and the safety of residents;
Therefore, the method is crucial for urban settlement monitoring, and the increasingly complex urban environment makes ground settlement prediction more difficult and complicated, while the traditional method adopts a machine learning method such as an ELM model, an SOM model and the like to fit the model, has lower robustness and accuracy, can not well evaluate urban lifelines accurately, and can not guarantee the safety of urban infrastructure.
Disclosure of Invention
The invention aims to provide a DNN-based urban lifeline settlement hidden danger assessment method and system, which are used for solving the problems in the prior art.
In order to achieve the purpose, the invention provides the technical scheme that the urban lifeline settlement hidden danger assessment method based on DNN comprises the following steps:
Step 100, carrying out settlement monitoring on a plurality of areas of a city, carrying out city information acquisition on any area through an information acquisition device, and carrying out data processing on the acquired city information to obtain a group of characteristic parameter sets;
Step 200, acquiring a settlement monitoring result of any region, building a deep neural network model based on a city deformation environment characteristic set, and performing model training to generate a settlement hidden danger assessment model;
Step 300, periodically evaluating the sedimentation condition of any area, analyzing the urban deformation environment characteristic difference of the area in different periods, and extracting the influence characteristic influencing the sedimentation degree evaluation result;
Step 400, extracting urban deformation environment feature sets of any city to be evaluated, evaluating the sedimentation degree of each target area of the city to be evaluated, drawing a city deformation monitoring vulnerability graph based on the sedimentation degree evaluation result of each target area, and identifying the areas with abnormal hidden danger.
Further, step S100 includes the steps of:
Step S101, monitoring a city by using a Beidou satellite navigation system and an interference synthetic aperture radar, and fusing the monitored data with a city map to generate a city deformation monitoring vulnerability distribution grid diagram, setting each pixel grid in the city deformation monitoring vulnerability distribution grid diagram as an area of the city, reading deformation in any area and setting the deformation as tag data to obtain a tag data set Y= { Y (1),. The first place, Y (c),. The second place, Y (M) }, wherein Y (c) is the c-th tag data, and M is the total number of tag data in the tag data set;
Step S102, randomly selecting an area, respectively acquiring urban digital elevation model information, geological information and rail transit distribution information of the area, carrying out quantization processing on all acquired information to obtain a plurality of characteristic data, and generating a characteristic data set X= { X (1),. The first place, X (a),. The first place, X (N) }, wherein X (a) is the a-th characteristic data, N is the total number of characteristic data in the characteristic data set, the urban digital elevation model information comprises elevation values, resolution, gradient and slope directions, the geological information comprises distribution, thickness, lithologic physical and mechanical characteristics and hydrogeological parameters of stratum, and the rail transit distribution information comprises road information and station information;
Step S103, randomly extracting the feature data set, setting the random feature data set extracted to contain n1 feature data as x1= { X '(1),…,x'(r),…,x' (n 1) }, wherein if the r-th feature data X ' (r) data is missing in the random feature data set, randomly rearranging n2 feature data from the feature data set, setting the value of the b-th feature data as z b, and according to the formula:
Calculating an average value z ave of random n2 pieces of characteristic data, and supplementing the deletion value of the r-th characteristic data x ' (r) by the obtained average value z ave;
step S104, after supplementing all the missing values in the characteristic data set, according to the formula:
The method comprises the steps of obtaining a characteristic data set, wherein z a is the numerical value of the a characteristic data in the characteristic data set, calculating to obtain the average value x ave and standard deviation sigma of the characteristic data set, randomly obtaining the numerical value z a of the a characteristic data from the characteristic data set, setting the a characteristic data as abnormal data if |z a-xave | >3σ, and eliminating the a characteristic data from the characteristic data set;
Step S105, performing dimensionless treatment on the processed characteristic data set by using a z-score standardization method, converting each characteristic data into dimensionless pure values, removing unit limitations in the data set, converting the unit limitations into dimensionless pure values, enhancing the reliability of model training, setting any characteristic data as a random variable X (Y) and any tag data as a random variable Y (X), and according to the formula:
Wherein p (X, Y) is the probability of simultaneous occurrence of the random variable X (Y) and Y (X), p (X) is the probability of independent occurrence of the random variable X (Y), p (Y) is the probability of independent occurrence of the random variable Y (X), mutual information I (X; Y) and I (Y; X) between any feature data and tag data are calculated, a mutual information threshold I max is set, if I (X; Y) > I max, the feature data are set as urban deformation environment features, and an urban deformation environment feature set is obtained after all feature data are compared.
Further, step S200 includes the steps of:
Step S201, acquiring a tag data set Y= { Y (1),. The right, Y (c),. The right, Y (M) } and a feature data set X= { X (1),. The right, X (a),. The right, X (N) }, constructing a deep neural network model by using the two data sets, extracting an urban deformation environment feature set, taking any urban deformation environment feature as input data of the deep neural network model, dividing the deep neural network model into a plurality of layers, calculating the weight, the bias and the activation function to obtain the output of each layer, and obtaining the output of each layer according to the formula:
αj＝δ(Wjαj-1+βj);
wherein W j is the output weight of the j-th layer, beta j is the output bias of the j-th layer, alpha j-1 is the output value of the j-1-th layer, delta () is the model output function;
Step S202, selecting a mean square error As a loss function, wherein alpha ' is a predicted output result of the deep neural network model, y is any tag data in a tag data set, a loss value E between any tag data and the predicted output result is calculated, back propagation is carried out through a gradient descent method, and a weight W and a bias beta in each layer of output formula are carried out, so that the obtained loss value is minimum, and a settlement hidden danger assessment model is generated;
The method comprises the steps of optimizing a deep neural network model through an improved longhorn beetle whisker search algorithm, mainly dividing the deep neural network model into a deep neural network part and a longhorn beetle whisker search algorithm optimizing part, firstly preparing data of a deep neural network module, determining parameters of the deep neural network, then repeatedly iterating according to error values of deep neural network training, searching for an optimal initial weight, retraining the deep neural network by using the optimal initial weight, establishing an urban lifeline settlement hidden danger assessment model, optimizing the deep neural network by using the improved longhorn beetle whisker search algorithm, effectively preventing the model from sinking into local optimal solutions, accelerating the convergence rate of the model and improving the calculation efficiency;
Step 203, randomly selecting an area, extracting a set of urban deformation environment characteristics in the area, performing dimensionless processing on the urban deformation environment characteristics, inputting the set of urban deformation environment characteristics into a settlement hidden danger assessment model, and outputting a settlement evaluation value score of the area, wherein the settlement evaluation value is a standardized predicted value, the range is between 0 and 1, and the score value reflects the possibility of settlement of the area.
Further, step S300 includes the steps of:
Step 301, extracting urban deformation environment feature sets of any area every other unit period to respectively obtain sedimentation evaluation values of the area in each unit period, setting sedimentation degree evaluation performed in any unit period as one evaluation record, randomly selecting two adjacent evaluation records and respectively extracting the urban deformation environment feature sets of the two evaluation records;
Step S302, comparing any urban deformation environmental characteristic in the previous evaluation record with the urban deformation environmental characteristic set in the next evaluation record, and if the urban deformation environmental characteristic does not exist in the urban deformation environmental characteristic set in the next evaluation record, setting the urban deformation environmental characteristic as an influence characteristic to obtain an influence characteristic set; environmental characteristics contained in the previous evaluation record but not in the latter evaluation record are briefly identified, so that deviation exists in sedimentation degree evaluation, but the environmental characteristics are not actually existing, and therefore, the environmental characteristics need to be eliminated to obtain a more accurate evaluation result;
step S303, acquiring a set evaluation rule from a settlement hidden danger evaluation model to obtain the numerical value duty ratio of any urban deformation environment characteristic, acquiring the numerical value difference among the rest urban deformation environment characteristics except for an influence characteristic set in the twice evaluation record, setting the numerical value difference of the kth urban deformation environment characteristic as delta data k, and according to the formula:
calculating to obtain a difference value of the kth city deformation environment characteristic to be a ratio eta k;
Step S304, obtaining an evaluation difference value delta score by respectively obtaining sedimentation evaluation values of two evaluation records, and calculating an evaluation difference value duty ratio tau=delta score/score be, wherein score be is a sedimentation evaluation value of the previous evaluation record:
θs＝ηs×τ;
and calculating the influence amplitude theta s of the s-th influence characteristic.
Further, step S400 includes the steps of:
Step S401, dividing a city to be evaluated into a plurality of target areas, extracting urban deformation environment characteristics in any e-th target area, and comparing the urban deformation environment characteristics with influence characteristics to obtain a plurality of influence characteristics contained in the e-th target area;
Step S402, inputting all urban deformation environment characteristics in the e-th target area into a settlement hidden danger assessment model, outputting a settlement evaluation value score e of the e-th target area, setting the influence amplitude of the S1-th influence characteristic in the e-th target area as theta s1, and according to a formula:
The num e is the number of influencing features contained in the e-th target area, and calculates an actual sedimentation evaluation value score ' e of the e-th target area;
Step S403, obtaining an actual settlement evaluation value of any target area in the city to be evaluated, drawing a city deformation monitoring susceptibility graph, setting a settlement evaluation threshold score max, judging the e-th target area as an abnormal hidden danger area if the score ' e＞scoremax, and marking and presenting the e-th target area in the city deformation monitoring susceptibility graph.
In order to better realize the method, the system for evaluating the potential sedimentation hazards of the urban lifeline is also provided, and comprises an urban information analysis module, a hidden danger model analysis module, a model deviation analysis module and an abnormal hidden danger judgment module;
The urban information analysis module is used for carrying out settlement monitoring on a plurality of areas of the city, carrying out urban information acquisition on any area through the information acquisition equipment, and carrying out data processing on the acquired urban information to obtain a group of characteristic parameter sets;
The hidden danger model analysis module is used for acquiring a settlement monitoring result of any region, constructing a deep neural network model based on a city deformation environment characteristic set, and performing model training to generate a settlement hidden danger assessment model;
The model deviation analysis module is used for periodically evaluating the sedimentation condition of any area, analyzing the urban deformation environment characteristic difference of the area in different periods, and extracting the influence characteristic influencing the sedimentation degree evaluation result;
The system comprises an abnormal hidden danger judging module, a city deformation monitoring vulnerability graph and a city deformation monitoring vulnerability graph, wherein the abnormal hidden danger judging module is used for extracting a city deformation environment feature set of any city to be evaluated, evaluating the sedimentation degree of each target area of the city to be evaluated, and drawing a city deformation monitoring vulnerability graph based on the sedimentation degree evaluation result of each target area to identify the region with the abnormal hidden danger.
Further, the city information analysis module comprises a city data acquisition unit and a characteristic parameter screening unit;
The urban information processing system comprises an urban data acquisition unit, a characteristic parameter screening unit and an urban deformation environment characteristic collection unit, wherein the urban data acquisition unit is used for carrying out settlement monitoring on a plurality of areas of a city, carrying out urban information acquisition on any area through an information acquisition device, and carrying out data processing on acquired urban information to obtain a group of characteristic parameter sets, and the characteristic parameter screening unit is used for carrying out correlation analysis on any characteristic parameter and screening to obtain the urban deformation environment characteristic sets.
Further, the hidden danger model analysis module comprises a hidden danger model construction unit and an urban hidden danger assessment unit;
The system comprises a hidden danger model construction unit, a hidden danger assessment unit and a city hidden danger assessment unit, wherein the hidden danger model construction unit is used for acquiring a settlement monitoring result of any region, constructing a deep neural network model based on a city deformation environment characteristic set and carrying out model training to generate a settlement hidden danger assessment model, and the city hidden danger assessment unit is used for assessing the settlement degree of the region according to the settlement hidden danger assessment model.
Further, the model deviation analysis module comprises an influence characteristic extraction unit and an influence amplitude calculation unit;
The system comprises an influence characteristic extraction unit, an influence amplitude calculation unit and a control unit, wherein the influence characteristic extraction unit is used for periodically evaluating the sedimentation condition of any area, analyzing the urban deformation environment characteristic difference of the area in different periods, extracting the influence characteristic of an influence sedimentation degree evaluation result, and obtaining the influence amplitude generated by any influence characteristic based on the sedimentation degree evaluation difference of the area in different periods.
Further, the abnormal hidden danger judging module comprises an evaluation result analyzing unit and an abnormal hidden danger identifying unit;
The system comprises an evaluation result analysis unit, an abnormal hidden danger identification unit and a judgment unit, wherein the evaluation result analysis unit is used for extracting urban deformation environment feature sets of any city to be evaluated, carrying out sedimentation degree evaluation on each target area of the city to be evaluated, and the abnormal hidden danger identification unit is used for drawing a city deformation monitoring vulnerability graph and identifying areas with abnormal hidden danger based on sedimentation degree evaluation results of each target area.
Compared with the prior art, the invention has the beneficial effects that:
1. the method utilizes a mutual information method to screen the characteristics highly related to the target variable and constructs a training data set, adopts an improved BAS optimized deep neural network model and combines the urban deformation environment characteristics to carry out training optimization, the constructed urban settlement monitoring and evaluating model can accurately evaluate the settlement degree of the area to be evaluated and output the settlement possibility value, thereby providing scientific and reliable hidden danger evaluation basis for urban planning and construction, and being stable and reliable and high in accuracy;
2. According to the invention, the conventional deep neural network model is optimized, the hidden danger situation of the city is accurately estimated through the settlement hidden danger estimation model obtained through optimization, meanwhile, the estimation result influenced by the environmental factors is corrected by considering the short-term influence of the environmental factors on the estimation process, the accuracy of the estimation result is further improved, and the follow-up judgment reliability is facilitated.
Drawings
FIG. 1 is a schematic diagram of steps of a DNN-based urban lifeline settlement risk assessment method;
FIG. 2 is a schematic structural diagram of a DNN-based urban lifeline settlement risk assessment system;
FIG. 3 is a flow chart of a DNN-based urban lifeline settlement risk assessment method;
FIG. 4 is a flow chart of the construction of an urban lifeline settlement risk assessment model;
Fig. 5 is a graph of urban deformation monitoring vulnerability.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention provides a DNN-based urban lifeline settlement hidden danger assessment method, which comprises the following steps of:
Step 100, carrying out settlement monitoring on a plurality of areas of a city, carrying out city information acquisition on any area through an information acquisition device, and carrying out data processing on the acquired city information to obtain a group of characteristic parameter sets;
wherein, step S100 includes the following steps:
Step S101, monitoring a city by using a Beidou satellite navigation system and an interference synthetic aperture radar, and fusing the monitored data with a city map to generate a city deformation monitoring vulnerability distribution grid diagram, setting each pixel grid in the city deformation monitoring vulnerability distribution grid diagram as an area of the city, reading deformation in any area and setting the deformation as tag data to obtain a tag data set Y= { Y (1),. The first place, Y (c),. The second place, Y (M) }, wherein Y (c) is the c-th tag data, and M is the total number of tag data in the tag data set;
step S102, randomly selecting an area, respectively acquiring urban digital elevation model information, geological information and rail traffic distribution information of the area, and carrying out quantization processing on all acquired information to obtain a plurality of characteristic data, so as to generate a characteristic data set X= { X (1),. The first, X (a),. The second, X (N) }, wherein X (a) is the a-th characteristic data, and N is the total number of the characteristic data in the characteristic data set;
the embodiment 1 comprises the steps of acquiring key data in a settlement monitoring area, wherein the key data comprise urban digital elevation model information, geological information, rail traffic distribution information and the like, the urban digital elevation model information comprises key parameters such as an elevation value H, a resolution ratio R, a gradient theta, a slope alpha and the like, the key parameters can reflect basic characteristics of urban topography, the geological information comprises distribution D, thickness T, lithology of strata such as sandstone S, shale Sh, limestone LS and the like and physical mechanical characteristics, the physical mechanical characteristics comprise volume weight gamma, elastic modulus E, poisson ratio v, cohesive force c, internal friction angle phi and the like, the key parameters comprise hydrogeological parameters such as a permeability coefficient K, a water supply degree mu, a water release coefficient S, a water pouring coefficient omega and the like, and the rail traffic distribution information comprises road information such as road width W, road type T, station information such as station position P and station scale S;
Step S103, randomly extracting the feature data set, setting the random feature data set extracted to contain n1 feature data as x1= { X '(1),…,x'(r),…,x' (n 1) }, wherein if the r-th feature data X ' (r) data is missing in the random feature data set, randomly rearranging n2 feature data from the feature data set, setting the value of the b-th feature data as z b, and according to the formula:
Calculating an average value z ave of random n2 pieces of characteristic data, and supplementing the deletion value of the r-th characteristic data x ' (r) by the obtained average value z ave;
step S104, after supplementing all the missing values in the characteristic data set, according to the formula:
The method comprises the steps of obtaining a characteristic data set, wherein z a is the numerical value of the a characteristic data in the characteristic data set, calculating to obtain the average value x ave and standard deviation sigma of the characteristic data set, randomly obtaining the numerical value z a of the a characteristic data from the characteristic data set, setting the a characteristic data as abnormal data if |z a-xave | >3σ, and eliminating the a characteristic data from the characteristic data set;
step S105, performing dimensionless treatment on the processed characteristic data set by using a z-score standardization method, converting each characteristic data into dimensionless pure numerical values, setting any characteristic data as a random variable X (Y) and any tag data as a random variable Y (X), and according to the formula:
Wherein, p (X, Y) is the probability of the simultaneous occurrence of the random variable X (Y) and Y (X), p (X) is the probability of the independent occurrence of the random variable X (Y), p (Y) is the probability of the independent occurrence of the random variable Y (X), the mutual information I (X; Y) and I (Y; X) between any characteristic data and the tag data are obtained by calculation, a mutual information threshold I max is set, and if I (X; Y) > I max, the characteristic data are set as urban deformation environment characteristics, and an urban deformation environment characteristic set is obtained after all the characteristic data are compared;
In the embodiment, the improved longhorn beetle whisker search algorithm IBAS is utilized to optimize the initial weight of the DNN neural network, so that the convergence speed of the DNN neural network is greatly improved, the learning capacity is enhanced, meanwhile, the Monte Carlo criterion in the simulated annealing algorithm SA is adopted to optimize and improve the IBAS, local optimum is obtained, the stability is greatly improved, and the improved IBAS is applied to urban life line hidden danger monitoring.
Step 200, acquiring a settlement monitoring result of any region, building a deep neural network model based on a city deformation environment characteristic set, and performing model training to generate a settlement hidden danger assessment model;
wherein, step S200 includes the following steps:
Step S201, acquiring a tag data set Y= { Y (1),. The right, Y (c),. The right, Y (M) } and a feature data set X= { X (1),. The right, X (a),. The right, X (N) }, constructing a deep neural network model by using the two data sets, extracting an urban deformation environment feature set, taking any urban deformation environment feature as input data of the deep neural network model, dividing the deep neural network model into a plurality of layers, calculating the weight, the bias and the activation function to obtain the output of each layer, and obtaining the output of each layer according to the formula:
αj＝δ(Wjαj-1+βj);
wherein W j is the output weight of the j-th layer, beta j is the output bias of the j-th layer, alpha j-1 is the output value of the j-1-th layer, delta () is the model output function;
Step S202, selecting a mean square error As a loss function, wherein alpha ' is a predicted output result of the deep neural network model, y is any tag data in a tag data set, a loss value E between any tag data and the predicted output result is calculated, back propagation is carried out through a gradient descent method, and a weight W and a bias beta in each layer of output formula are carried out, so that the obtained loss value is minimum, and a settlement hidden danger assessment model is generated;
Step S203, randomly selecting an area, extracting a city deformation environment feature set in the area, performing dimensionless processing on each city deformation environment feature, inputting the dimensionless processing to a settlement hidden danger evaluation model, and outputting a settlement evaluation value score of the area.
Step 300, periodically evaluating the sedimentation condition of any area, analyzing the urban deformation environment characteristic difference of the area in different periods, and extracting the influence characteristic influencing the sedimentation degree evaluation result;
wherein, step S300 includes the following steps:
Step 301, extracting urban deformation environment feature sets of any area every other unit period to respectively obtain sedimentation evaluation values of the area in each unit period, setting sedimentation degree evaluation performed in any unit period as one evaluation record, randomly selecting two adjacent evaluation records and respectively extracting the urban deformation environment feature sets of the two evaluation records;
Step S302, comparing any urban deformation environmental characteristic in the previous evaluation record with the urban deformation environmental characteristic set in the next evaluation record, and if the urban deformation environmental characteristic does not exist in the urban deformation environmental characteristic set in the next evaluation record, setting the urban deformation environmental characteristic as an influence characteristic to obtain an influence characteristic set;
step S303, acquiring a set evaluation rule from a settlement hidden danger evaluation model to obtain the numerical value duty ratio of any urban deformation environment characteristic, acquiring the numerical value difference among the rest urban deformation environment characteristics except for an influence characteristic set in the twice evaluation record, setting the numerical value difference of the kth urban deformation environment characteristic as delta data k, and according to the formula:
calculating to obtain a difference value of the kth city deformation environment characteristic to be a ratio eta k;
Step S304, obtaining an evaluation difference value delta score by respectively obtaining sedimentation evaluation values of two evaluation records, and calculating an evaluation difference value duty ratio tau=delta score/score be, wherein score be is a sedimentation evaluation value of the previous evaluation record:
θs＝ηs×τ;
and calculating the influence amplitude theta s of the s-th influence characteristic.
Step 400, extracting a city deformation environment feature set of any city to be evaluated, and evaluating the sedimentation degree of each target area of the city to be evaluated;
wherein, step S400 includes the following steps:
Step S401, dividing a city to be evaluated into a plurality of target areas, extracting urban deformation environment characteristics in any e-th target area, and comparing the urban deformation environment characteristics with influence characteristics to obtain a plurality of influence characteristics contained in the e-th target area;
Step S402, inputting all urban deformation environment characteristics in the e-th target area into a settlement hidden danger assessment model, outputting a settlement evaluation value score e of the e-th target area, setting the influence amplitude of the S1-th influence characteristic in the e-th target area as theta s1, and according to a formula:
The num e is the number of influencing features contained in the e-th target area, and calculates an actual sedimentation evaluation value score ' e of the e-th target area;
Step S403, obtaining an actual settlement evaluation value of any target area in the city to be evaluated, drawing a city deformation monitoring susceptibility graph, setting a settlement evaluation threshold score max, judging the e-th target area as an abnormal hidden danger area if the score ' e＞scoremax, and marking and presenting the e-th target area in the city deformation monitoring susceptibility graph.
The urban lifeline settlement hidden danger assessment system comprises an urban information analysis module, a hidden danger model analysis module, a model deviation analysis module and an abnormal hidden danger judgment module;
The urban information analysis module is used for carrying out settlement monitoring on a plurality of areas of the city, carrying out urban information acquisition on any area through the information acquisition equipment, and carrying out data processing on the acquired urban information to obtain a group of characteristic parameter sets;
The hidden danger model analysis module is used for acquiring a settlement monitoring result of any region, constructing a deep neural network model based on a city deformation environment characteristic set, and performing model training to generate a settlement hidden danger assessment model;
The model deviation analysis module is used for periodically evaluating the sedimentation condition of any area, analyzing the urban deformation environment characteristic difference of the area in different periods, and extracting the influence characteristic influencing the sedimentation degree evaluation result;
The system comprises an abnormal hidden danger judging module, a city deformation monitoring vulnerability graph and a city deformation monitoring vulnerability graph, wherein the abnormal hidden danger judging module is used for extracting a city deformation environment feature set of any city to be evaluated, evaluating the sedimentation degree of each target area of the city to be evaluated, and drawing a city deformation monitoring vulnerability graph based on the sedimentation degree evaluation result of each target area to identify the region with the abnormal hidden danger.
The city information analysis module comprises a city data acquisition unit and a characteristic parameter screening unit;
The urban information processing system comprises an urban data acquisition unit, a characteristic parameter screening unit and an urban deformation environment characteristic collection unit, wherein the urban data acquisition unit is used for carrying out settlement monitoring on a plurality of areas of a city, carrying out urban information acquisition on any area through an information acquisition device, and carrying out data processing on acquired urban information to obtain a group of characteristic parameter sets, and the characteristic parameter screening unit is used for carrying out correlation analysis on any characteristic parameter and screening to obtain the urban deformation environment characteristic sets.
The hidden danger model analysis module comprises a hidden danger model construction unit and an urban hidden danger assessment unit;
The system comprises a hidden danger model construction unit, a hidden danger assessment unit and a city hidden danger assessment unit, wherein the hidden danger model construction unit is used for acquiring a settlement monitoring result of any region, constructing a deep neural network model based on a city deformation environment characteristic set and carrying out model training to generate a settlement hidden danger assessment model, and the city hidden danger assessment unit is used for assessing the settlement degree of the region according to the settlement hidden danger assessment model.
The model deviation analysis module comprises an influence characteristic extraction unit and an influence amplitude calculation unit;
The system comprises an influence characteristic extraction unit, an influence amplitude calculation unit and a control unit, wherein the influence characteristic extraction unit is used for periodically evaluating the sedimentation condition of any area, analyzing the urban deformation environment characteristic difference of the area in different periods, extracting the influence characteristic of an influence sedimentation degree evaluation result, and obtaining the influence amplitude generated by any influence characteristic based on the sedimentation degree evaluation difference of the area in different periods.
The abnormal hidden danger judging module comprises an evaluation result analyzing unit and an abnormal hidden danger identifying unit;
The system comprises an evaluation result analysis unit, an abnormal hidden danger identification unit and a judgment unit, wherein the evaluation result analysis unit is used for extracting urban deformation environment feature sets of any city to be evaluated, carrying out sedimentation degree evaluation on each target area of the city to be evaluated, and the abnormal hidden danger identification unit is used for drawing a city deformation monitoring vulnerability graph and identifying areas with abnormal hidden danger based on sedimentation degree evaluation results of each target area.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims (10)

1.一种基于DNN的城市生命线沉降隐患评估方法，其特征在于：所述评估方法包括以下步骤：1. A method for assessing the subsidence hazards of urban lifelines based on DNN, characterized in that the method comprises the following steps: 步骤S100：对城市的若干个区域进行沉降监测，通过信息采集设备对任意区域进行城市信息采集，对采集到的城市信息进行数据处理得到一组特征参数集合；对任意特征参数进行相关性分析，筛选得到城市变形环境特征集合；Step S100: monitoring the settlement of several areas of the city, collecting urban information from any area through information collection equipment, and processing the collected urban information to obtain a set of characteristic parameter sets; performing correlation analysis on any characteristic parameters to screen and obtain a set of urban deformation environment characteristics; 步骤S200：获取任意区域的沉降监测结果，基于城市变形环境特征集合，搭建深度神经网络模型并进行模型训练，生成沉降隐患评估模型；根据沉降隐患评估模型对所述区域进行沉降程度评估；Step S200: Obtain settlement monitoring results of any area, build a deep neural network model and perform model training based on a set of urban deformation environment characteristics, and generate a settlement risk assessment model; and assess the settlement degree of the area according to the settlement risk assessment model; 步骤S300：对任意区域的沉降情况进行周期性评估，分析所述区域在不同周期里的城市变形环境特征差异，对影响沉降程度评估结果的影响特征进行提取；基于所述区域在不同周期里的沉降程度评估差异，得到任意影响特征所产生的影响幅度；Step S300: periodically evaluate the settlement of any area, analyze the differences in the characteristics of the urban deformation environment of the area in different periods, and extract the influencing features that affect the settlement assessment results; based on the differences in the settlement assessments of the area in different periods, obtain the impact amplitude of any influencing features; 步骤S400：对任意待评估城市的城市变形环境特征集合进行提取，对所述待评估城市的各个目标区域进行沉降程度评估；基于各个目标区域的沉降程度评估结果，绘制城市变形监测易发性图，对存在异常隐患区域进行识别。Step S400: extracting a set of urban deformation environment features of any city to be evaluated, and evaluating the settlement degree of each target area of the city to be evaluated; based on the settlement degree evaluation results of each target area, drawing an urban deformation monitoring susceptibility map, and identifying areas with abnormal hidden dangers. 2.根据权利要求1所述的一种基于DNN的城市生命线沉降隐患评估方法，其特征在于：所述步骤S100包括以下步骤：2. According to the DNN-based urban lifeline settlement hazard assessment method of claim 1, it is characterized in that: the step S100 comprises the following steps: 步骤S101：利用北斗卫星导航系统和干涉合成孔径雷达对城市进行监测，并将监测得到的数据与城市地图进行融合，生成城市变形监测易发性分布栅格图；将所述城市变形监测易发性分布栅格图中的每个像素栅格设定为城市的一个区域；读取任意区域中的变形量并设定为标签数据，得到一个标签数据集Y＝{y(1),…,y(c),…,y(M)}，其中，y(c)为第c个标签数据，M为标签数据集中的标签数据总数；Step S101: monitor the city using the Beidou satellite navigation system and interferometric synthetic aperture radar, and fuse the monitored data with the city map to generate a city deformation monitoring susceptibility distribution grid map; set each pixel grid in the city deformation monitoring susceptibility distribution grid map as an area of the city; read the deformation amount in any area and set it as label data to obtain a label data set Y = {y(1), ..., y(c), ..., y(M)}, where y(c) is the cth label data and M is the total number of label data in the label data set; 步骤S102：任意选取一个区域，分别采集所述区域的城市数字高程模型信息、地质信息和轨道交通分布信息，将采集到所有信息进行量化处理得到若干特征数据，生成一个特征数据集X＝{x(1),…,x(a),…,x(N)}，其中，x(a)为第a个特征数据，N为特征数据集中的特征数据总数；Step S102: arbitrarily select an area, collect urban digital elevation model information, geological information and rail transit distribution information of the area respectively, quantify all the collected information to obtain a number of feature data, and generate a feature data set X = {x(1), ..., x(a), ..., x(N)}, where x(a) is the ath feature data and N is the total number of feature data in the feature data set; 步骤S103：对特征数据集进行随机抽取，设定抽取到包含有n1个特征数据的随机特征数据集为X1＝{x’(1),…,x’(r),…,x’(n1)}，其中，若随机特征数据集中存在第r个特征数据x’(r)数据缺失，则重新从特征数据集中随机n2个特征数据，设定其中第b个特征数据的数值为zb，根据公式：Step S103: randomly extract the feature data set, and set the random feature data set containing n1 feature data to be X1={x ' (1),...,x ' (r),...,x ' (n1)}, wherein, if the rth feature data x ' (r) is missing in the random feature data set, then randomly extract n2 feature data from the feature data set, and set the value of the bth feature data to zb , according to the formula: 计算得到随机n2个特征数据的平均值zave；将得到的平均值zave对第r个特征数据x’(r)进行缺失值补充；Calculate the average value z ave of random n2 feature data; use the obtained average value z ave to supplement the missing value of the rth feature data x ' (r); 步骤S104：当对特征数据集中的所有缺失值进行补充后，根据公式：Step S104: After all missing values in the feature data set are supplemented, according to the formula: 其中，za为特征数据集中第a个特征数据的数值；计算得到特征数据集的平均值xave和标准差σ；从特征数据集中任意获取第a个特征数据的数值za，若|za-xave|＞3σ，则将第a个特征数据设定为异常数据，并将第a个特征数据从特征数据集中剔除；Wherein, za is the value of the ath feature data in the feature data set; the average value x ave and the standard deviation σ of the feature data set are calculated; the value za of the ath feature data is obtained arbitrarily from the feature data set, and if | za -x ave |＞3σ, the ath feature data is set as abnormal data and the ath feature data is removed from the feature data set; 步骤S105：使用z-score标准化法对处理后的特征数据集进行无量纲化，将各个特征数据转换成无量纲的纯数值；设定任意特征数据为随机变量X(Y)和任意标签数据为随机变量Y(X)，根据公式：Step S105: Use the z-score normalization method to non-dimensionalize the processed feature data set, and convert each feature data into a dimensionless pure value; set any feature data as a random variable X(Y) and any label data as a random variable Y(X), according to the formula: 其中，p(x,y)为随机变量X(Y)和Y(X)同时发生的概率，p(x)为随机变量X(Y)单独发生的概率，p(y)为随机变量Y(X)单独发生的概率；计算得到任意特征数据与标签数据之间的互信息I(x；y)和I(y；x)；设定一个互信息阈值Imax，若I(x；y)＞Imax，则将所述特征数据设定为城市变形环境特征；对所有特征数据进行比对后得到一个城市变形环境特征集合。Among them, p(x,y) is the probability of random variables X(Y) and Y(X) occurring simultaneously, p(x) is the probability of random variable X(Y) occurring alone, and p(y) is the probability of random variable Y(X) occurring alone; the mutual information I(x;y) and I(y;x) between any feature data and label data are calculated; a mutual information threshold I max is set, and if I(x;y)＞I max , the feature data is set as the urban deformation environment feature; and a set of urban deformation environment features is obtained after comparing all feature data. 3.根据权利要求2所述的一种基于DNN的城市生命线沉降隐患评估方法，其特征在于：所述步骤S200包括以下步骤：3. The method for assessing the subsidence hazard of urban lifeline based on DNN according to claim 2 is characterized in that: the step S200 comprises the following steps: 步骤S201：获取标签数据集Y＝{y(1),…,y(c),…,y(M)}和特征数据集X＝{x(1),…,x(a),…,x(N)}，利用两个数据集搭建深度神经网络模型；提取城市变形环境特征集合，将任意城市变形环境特征作为深度神经网络模型的输入数据，将深度神经网络模型划分若干层，通过权值、偏置、激活函数的计算得到每一层的输出，根据公式：Step S201: Obtain a label data set Y = {y(1), ..., y(c), ..., y(M)} and a feature data set X = {x(1), ..., x(a), ..., x(N)}, and use the two data sets to build a deep neural network model; extract a set of urban deformation environment features, use any urban deformation environment features as input data of the deep neural network model, divide the deep neural network model into several layers, and obtain the output of each layer by calculating the weight, bias, and activation function, according to the formula: αj＝δ(Wjαj-1+βj)；α j =δ(W j α j-1 +β j ); 其中，Wj为第j层的输出权值，βj为第j层的输出偏置，αj-1为第j-1层的输出值，δ()为模型输出函数；计算得到第j层的输出值αj；Wherein, W j is the output weight of the j-th layer, β j is the output bias of the j-th layer, α j-1 is the output value of the j-1-th layer, and δ() is the model output function; the output value α j of the j-th layer is calculated; 步骤S202：选取均方误差作为损失函数，其中，α’为深度神经网络模型的预测输出结果，y为标签数据集中的任意标签数据，计算得到任意标签数据与预测输出结果之间的损失值E，通过梯度下降法进行反向传播，对每一层输出公式中的权值W和偏置β，使得得到的损失值最小，生成沉降隐患评估模型；Step S202: Select mean square error As the loss function, α' is the predicted output result of the deep neural network model, y is any label data in the label data set, and the loss value E between any label data and the predicted output result is calculated. Back propagation is performed through the gradient descent method, and the weight W and bias β in the output formula of each layer are used to minimize the obtained loss value, thus generating a settlement hazard assessment model; 步骤S203：任意选取一个区域，提取所述区域中的城市变形环境特征集合，对各个城市变形环境特征进行无量纲化处理并输入到沉降隐患评估模型中，输出得到所述区域的沉降评价值score。Step S203: arbitrarily select a region, extract a set of urban deformation environment characteristics in the region, perform dimensionless processing on each urban deformation environment characteristic and input it into a settlement hazard assessment model, and output a settlement evaluation value score of the region. 4.根据权利要求3所述的一种基于DNN的城市生命线沉降隐患评估方法，其特征在于：所述步骤S300包括以下步骤：4. The method for assessing the hidden danger of urban lifeline subsidence based on DNN according to claim 3 is characterized in that: the step S300 comprises the following steps: 步骤S301：每隔一个单位周期提取任意区域的城市变形环境特征集合，分别得到所述区域在各个单位周期里的沉降评价值；设定任意一个单位周期所进行的沉降程度评估为一次评估记录，任意选取相邻两次评估记录并分别提取所述两次评估记录的城市变形环境特征集合；Step S301: extracting an urban deformation environment feature set of any area every other unit period, and obtaining the settlement evaluation value of the area in each unit period respectively; setting the settlement degree evaluation performed in any unit period as one evaluation record, arbitrarily selecting two adjacent evaluation records and extracting the urban deformation environment feature sets of the two evaluation records respectively; 步骤S302：将前一次评估记录中的任意城市变形环境特征与后一次评估记录中的城市变形环境特征集合进行比对，若后一次评估记录的城市变形环境特征集合中不存在所述城市变形环境特征，则将所述城市变形环境特征设定为影响特征，得到一个影响特征集合；Step S302: Compare any urban deformation environment feature in the previous evaluation record with the urban deformation environment feature set in the next evaluation record. If the urban deformation environment feature does not exist in the urban deformation environment feature set in the next evaluation record, set the urban deformation environment feature as an influencing feature to obtain an influencing feature set. 步骤S303：从沉降隐患评估模型中获取所设置的评估规则，得到任意一个城市变形环境特征的数值占比；获取两次评估记录中除去影响特征集合外，其余城市变形环境特征之间数值差，设定第k个城市变形环境特征的数值差为Δdatak，根据公式：Step S303: Obtain the set assessment rules from the settlement hazard assessment model to obtain the numerical proportion of any urban deformation environment feature; obtain the numerical difference between the remaining urban deformation environment features excluding the influencing feature set in the two assessment records, and set the numerical difference of the k-th urban deformation environment feature as Δdata k , according to the formula: 计算得到第k个城市变形环境特征的差值占比ηk；Calculate the difference ratio η k of the k-th city deformation environment characteristics; 步骤S304：分别获取两次评估记录的沉降评估值得到评估差值Δscore，计算得到评估差值占比τ＝Δscore/scorebe，其中，scorebe为前一次评估记录的沉降评估值；从影响特征集合中任意选取第s个影响特征，设定所述第s个影响特征的差值占比为ηs，根据公式：Step S304: Obtain the settlement assessment values of the two assessment records respectively to obtain the assessment difference Δscore, and calculate the assessment difference ratio τ=Δscore/score be , where score be is the settlement assessment value of the previous assessment record; arbitrarily select the sth influencing feature from the influencing feature set, and set the difference ratio of the sth influencing feature to η s , according to the formula: θs＝ηs×τ；θ s =η s ×τ; 计算得到所述第s个影响特征的影响幅度θs。The influence amplitude θ s of the s-th influencing feature is calculated. 5.根据权利要求4所述的一种基于DNN的城市生命线沉降隐患评估方法，其特征在于：所述步骤S400包括以下步骤：5. The method for assessing the subsidence hazard of urban lifeline based on DNN according to claim 4 is characterized in that: the step S400 comprises the following steps: 步骤S401：将待评估城市划分为若干个目标区域，对任意第e个目标区域中城市变形环境特征进行提取，将任意城市变形环境特征与影响特征进行比对，得到所述第e个目标区域中所包含的若干个影响特征；Step S401: Divide the city to be evaluated into several target areas, extract the urban deformation environment characteristics in any e-th target area, compare the urban deformation environment characteristics with the impact characteristics, and obtain several impact characteristics contained in the e-th target area; 步骤S402：将所述第e个目标区域中的所有城市变形环境特征输入到沉降隐患评估模型中，输出得到所述第e个目标区域的沉降评价值scoree；设定所述第e个目标区域中的第s1个影响特征的影响幅度为θs1，根据公式：Step S402: input all the urban deformation environment characteristics in the e-th target area into the settlement hazard assessment model, and output the settlement evaluation value score e of the e-th target area; set the influence amplitude of the s1-th influencing feature in the e-th target area to θ s1 , according to the formula: 其中，nume为所述第e个目标区域所包含的影响特征数量；计算得到所述第e个目标区域的实际沉降评价值score’ e；Wherein, num e is the number of influencing features contained in the e-th target area; the actual settlement evaluation value score ' e of the e-th target area is calculated; 步骤S403：获取所述待评估城市中任意目标区域的实际沉降评价值，绘制城市变形监测易发性图，设定一个沉降评价阈值scoremax，若score’ e＞scoremax，则判断所述第e个目标区域为异常隐患区域，并在城市变形监测易发性图中进行标记呈现。Step S403: obtaining the actual settlement evaluation value of any target area in the city to be evaluated, drawing a city deformation monitoring susceptibility map, setting a settlement evaluation threshold score max , if score ' e > score max , then judging the e-th target area as an abnormal hidden danger area, and marking it in the city deformation monitoring susceptibility map. 6.一种城市生命线沉降隐患评估系统，用于执行权利要求1-5中任一项所述的一种基于DNN的城市生命线沉降隐患评估方法，其特征在于：所述评估系统包括城市信息分析模块、隐患模型分析模块、模型偏差分析模块和异常隐患判断模块；6. A city lifeline settlement hazard assessment system, used to execute a DNN-based city lifeline settlement hazard assessment method according to any one of claims 1 to 5, characterized in that: the assessment system comprises a city information analysis module, a hazard model analysis module, a model deviation analysis module and an abnormal hazard judgment module; 所述城市信息分析模块，用于对城市的若干个区域进行沉降监测，通过信息采集设备对任意区域进行城市信息采集，对采集到的城市信息进行数据处理得到一组特征参数集合；对任意特征参数进行相关性分析，筛选得到城市变形环境特征集合；The urban information analysis module is used to monitor the settlement of several areas in the city, collect urban information from any area through information collection equipment, and process the collected urban information to obtain a set of characteristic parameter sets; perform correlation analysis on any characteristic parameters to screen and obtain a set of urban deformation environment characteristics; 所述隐患模型分析模块，用于获取任意区域的沉降监测结果，基于城市变形环境特征集合，搭建深度神经网络模型并进行模型训练，生成沉降隐患评估模型；根据沉降隐患评估模型对所述区域进行沉降程度评估；The hidden danger model analysis module is used to obtain the settlement monitoring results of any area, build a deep neural network model and perform model training based on the urban deformation environment feature set, and generate a settlement hidden danger assessment model; and assess the settlement degree of the area according to the settlement hidden danger assessment model; 所述模型偏差分析模块，用于对任意区域的沉降情况进行周期性评估，分析所述区域在不同周期里的城市变形环境特征差异，对影响沉降程度评估结果的影响特征进行提取；基于所述区域在不同周期里的沉降程度评估差异，得到任意影响特征所产生的影响幅度；The model deviation analysis module is used to periodically evaluate the settlement of any area, analyze the differences in the characteristics of the urban deformation environment of the area in different periods, and extract the influencing features that affect the settlement assessment results; based on the differences in the settlement assessment of the area in different periods, the impact amplitude of any influencing feature is obtained; 所述异常隐患判断模块，用于对任意待评估城市的城市变形环境特征集合进行提取，对所述待评估城市的各个目标区域进行沉降程度评估；基于各个目标区域的沉降程度评估结果，绘制城市变形监测易发性图，对存在异常隐患区域进行识别。The abnormal hidden danger judgment module is used to extract the urban deformation environment feature set of any city to be evaluated, and evaluate the settlement degree of each target area of the city to be evaluated; based on the settlement degree evaluation results of each target area, draw an urban deformation monitoring susceptibility map to identify areas with abnormal hidden dangers. 7.根据权利要求6所述的一种城市生命线沉降隐患评估系统，其特征在于：所述城市信息分析模块包括城市数据采集单元和特征参数筛选单元；7. The urban lifeline subsidence hazard assessment system according to claim 6, characterized in that: the urban information analysis module includes an urban data acquisition unit and a characteristic parameter screening unit; 所述城市数据采集单元，用于对城市的若干个区域进行沉降监测，通过信息采集设备对任意区域进行城市信息采集，对采集到的城市信息进行数据处理得到一组特征参数集合；所述特征参数筛选单元，用于对任意特征参数进行相关性分析，筛选得到城市变形环境特征集合。The urban data acquisition unit is used to monitor the settlement of several areas in the city, collect urban information from any area through information acquisition equipment, and process the collected urban information to obtain a set of characteristic parameter sets; the characteristic parameter screening unit is used to perform correlation analysis on any characteristic parameters to screen and obtain a set of urban deformation environment characteristics. 8.根据权利要求6所述的一种城市生命线沉降隐患评估系统，其特征在于：所述隐患模型分析模块包括隐患模型构建单元和城市隐患评估单元；8. The urban lifeline subsidence hazard assessment system according to claim 6, characterized in that: the hazard model analysis module includes a hazard model construction unit and an urban hazard assessment unit; 所述隐患模型构建单元，用于获取任意区域的沉降监测结果，基于城市变形环境特征集合，搭建深度神经网络模型并进行模型训练，生成沉降隐患评估模型；所述城市隐患评估单元，用于根据沉降隐患评估模型对所述区域进行沉降程度评估。The hidden danger model construction unit is used to obtain the settlement monitoring results of any area, build a deep neural network model and perform model training based on the urban deformation environment feature set, and generate a settlement hidden danger assessment model; the urban hidden danger assessment unit is used to assess the settlement degree of the area according to the settlement hidden danger assessment model. 9.根据权利要求6所述的一种城市生命线沉降隐患评估系统，其特征在于：所述模型偏差分析模块包括影响特征提取单元和影响幅度计算单元；9. The urban lifeline settlement hazard assessment system according to claim 6, characterized in that: the model deviation analysis module includes an impact feature extraction unit and an impact amplitude calculation unit; 所述影响特征提取单元，用于对任意区域的沉降情况进行周期性评估，分析所述区域在不同周期里的城市变形环境特征差异，对影响沉降程度评估结果的影响特征进行提取；所述影响幅度计算单元，用于基于所述区域在不同周期里的沉降程度评估差异，得到任意影响特征所产生的影响幅度。The influencing feature extraction unit is used to perform periodic evaluation on the settlement of any area, analyze the differences in urban deformation environment characteristics of the area in different periods, and extract the influencing features that affect the settlement degree evaluation results; the influencing amplitude calculation unit is used to obtain the influence amplitude generated by any influencing feature based on the differences in settlement degree evaluation of the area in different periods. 10.根据权利要求6所述的一种城市生命线沉降隐患评估系统，其特征在于：所述异常隐患判断模块包括评估结果分析单元和异常隐患识别单元；10. The urban lifeline subsidence hazard assessment system according to claim 6, characterized in that: the abnormal hazard judgment module includes an assessment result analysis unit and an abnormal hazard identification unit; 所述评估结果分析单元，用于对任意待评估城市的城市变形环境特征集合进行提取，对所述待评估城市的各个目标区域进行沉降程度评估；所述异常隐患识别单元，用于基于各个目标区域的沉降程度评估结果，绘制城市变形监测易发性图，对存在异常隐患区域进行识别。The assessment result analysis unit is used to extract the urban deformation environment feature set of any city to be assessed, and to assess the settlement degree of each target area of the city to be assessed; the abnormal hidden danger identification unit is used to draw an urban deformation monitoring susceptibility map based on the settlement degree assessment results of each target area, and to identify areas with abnormal hidden dangers.
CN202510015764.6A 2025-03-31 2025-03-31 DNN-based urban lifeline settlement hidden danger assessment method and system Active CN119962815B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510015764.6A CN119962815B (en) 2025-03-31 2025-03-31 DNN-based urban lifeline settlement hidden danger assessment method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510015764.6A CN119962815B (en) 2025-03-31 2025-03-31 DNN-based urban lifeline settlement hidden danger assessment method and system

Publications (2)

Publication Number Publication Date
CN119962815A true CN119962815A (en) 2025-05-09
CN119962815B CN119962815B (en) 2025-09-12

Family

ID=95589036

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510015764.6A Active CN119962815B (en) 2025-03-31 2025-03-31 DNN-based urban lifeline settlement hidden danger assessment method and system

Country Status (1)

Country Link
CN (1) CN119962815B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9454785B1 (en) * 2015-07-30 2016-09-27 Palantir Technologies Inc. Systems and user interfaces for holistic, data-driven investigation of bad actor behavior based on clustering and scoring of related data
KR20230134317A (en) * 2022-03-14 2023-09-21 이화여자대학교 산학협력단 Perceived urban decline rating method and method for generating perceived urban decline rating model using machine learning
CN119199044A (en) * 2024-11-27 2024-12-27 上海市园林科学规划研究院 An intelligent monitoring and evaluation system and method for urban green space carbon sink
CN119517440A (en) * 2025-01-15 2025-02-25 山东中医药大学附属医院 Abnormal breathing recognition method and system based on AI

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9454785B1 (en) * 2015-07-30 2016-09-27 Palantir Technologies Inc. Systems and user interfaces for holistic, data-driven investigation of bad actor behavior based on clustering and scoring of related data
KR20230134317A (en) * 2022-03-14 2023-09-21 이화여자대학교 산학협력단 Perceived urban decline rating method and method for generating perceived urban decline rating model using machine learning
CN119199044A (en) * 2024-11-27 2024-12-27 上海市园林科学规划研究院 An intelligent monitoring and evaluation system and method for urban green space carbon sink
CN119517440A (en) * 2025-01-15 2025-02-25 山东中医药大学附属医院 Abnormal breathing recognition method and system based on AI

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李吟;周新邵;: "基于RS与GIS的区域景观格局动态演变研究", 湖南城市学院学报(自然科学版), no. 03, 15 May 2017 (2017-05-15) *

Also Published As

Publication number Publication date
CN119962815B (en) 2025-09-12

Similar Documents

Publication Publication Date Title
CN110059963A (en) A kind of tunnel risk evaluating method based on fuzzy polymorphism Bayesian network
CN113779880A (en) Tunnel surrounding rock two-dimensional quality evaluation method based on advanced drilling data
CN114494865B (en) A CSET approach to future scenarios of mountain ecosystems
CN117035418A (en) Tunnel construction comprehensive risk evaluation method and device based on multi-source data fusion
CN113191642B (en) Regional landslide sensitivity analysis method based on optimal combination strategy
CN118196662B (en) Coal mine digital twin model building method based on Bayesian network algorithm
CN115270598A (en) A non-landslide sample selection method and computer equipment for susceptibility modeling
CN110598999B (en) Traffic travel analysis method, system and storage medium based on individual data
CN118245561B (en) Urban and rural planning and mapping result generation method and system
CN114638300A (en) Method, device and storage medium for identifying desserts of shale oil and gas reservoir
CN119471851A (en) Advanced geological prediction method and system for tunnel engineering based on multi-source information fusion
CN117151464A (en) A tunnel collapse risk assessment and prediction method based on PSO-RBF neural network
CN119514887B (en) Geological investigation optimization method and system based on big data analysis
CN119005695B (en) Construction method based on dynamic evaluation model of petroleum engineering safety risk
CN119962815B (en) DNN-based urban lifeline settlement hidden danger assessment method and system
CN116484266B (en) Fine urban land type recognition model training method
CN118781749A (en) A landslide disaster warning method and system
CN111026790A (en) Structure safety assessment and forecasting method based on data mining
CN117307249A (en) A real-time intelligent early warning method and device for tunnel rock bursts
Cheng et al. Fuzzy weights of evidence method implemented in GeoDAS GIS for information extraction and integration for prediction of point events
CN110807399A (en) A detection method of potential collapse points based on single-class support vector machine
Lai et al. Rapid coseismic landslide susceptibility assessment via Newmark analysis, the decision tree algorithm, and a web-based display system
CN120125038B (en) A landslide hazard assessment method and system
van den Akker Earthquake prediction: a MLP and SVM comparison
Tan et al. Correlation between ground motion based shaking intensity estimates and actual building damage

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