Urban toughness comprehensive evaluation method and system based on multi-dimensional power data fusion

Through the fusion of multi-dimensional power data, the contribution parameters, stability parameters and fluctuation parameters of various fields of the city are calculated, and combined with the third-order factor method, a urban resilience evaluation model is established, which solves the problem that the existing technology cannot achieve urban resilience evaluation and realizes urban resilience Accurate assessment of risks and scientific decision-making.

CN118966783APending Publication Date: 2024-11-15STATE GRID SICHUAN ELECTRIC POWER CORP ELECTRIC POWER RES INST
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411158215.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing urban resilience evaluation technology cannot achieve comprehensive urban resilience evaluation. It unilaterally evaluates urban resilience from a certain field, and cannot fully understand the city's ability to resist multiple disaster risks.

Method used

The comprehensive urban resilience evaluation method based on multi-dimensional power data fusion is adopted. By obtaining multiple dimension historical data in various fields of the city, the contribution parameters, the stationary parameters and the fluctuation parameters are calculated, and the urban resilience evaluation model is established, and risk judgment is carried out by combining the third-order factor method. .

Benefits of technology

It has achieved a comprehensive evaluation of urban resilience, provided more reliable technical support and reference, provided scientific basis for urban governance, and can accurately and quickly complete urban resilience risk assessment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966783A_ABST
    Figure CN118966783A_ABST
Patent Text Reader

Abstract

The invention discloses an urban toughness comprehensive evaluation method and system based on multi-dimensional power data fusion, and relates to the technical field of urban toughness evaluation. According to the method, the power data of multiple dimensions of each field of the city is acquired, indexes, including contribution parameters, stationary parameters and fluctuation parameters of the data of multiple dimensions, reflecting the city toughness in the data of multiple dimensions are mined based on the power data, and the city toughness evaluation model is established according to the index parameters, so that the city toughness evaluation accuracy is improved. And on the basis of the established city toughness evaluation model, predicting the city toughness in the future by adopting a three-order factor method, and comparing a predicted value with a city toughness value calculated by utilizing the city toughness evaluation model so as to judge whether the city toughness is abnormal or not. The method provides more reliable technical support for urban governance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of urban resilience evaluation, and specifically to a comprehensive urban resilience evaluation method and system based on multi-dimensional power data fusion. Background Art

[0002] Cities are facing the impact of multiple disaster risks, and resilient cities emphasize the city's ability to resist shocks. Therefore, establishing an effective urban resilience assessment model is a hot topic in current research. Carrying out urban resilience evaluation can guide urban development strategies, urban planning and resource allocation, and provide a scientific basis for urban governance.

[0003] At present, most evaluations of urban resilience are unilateral evaluations of the resilience of a certain area of ​​the city, such as urban disaster resilience, urban medical emergency resilience, etc., which cannot achieve the evaluation of urban resilience. Summary of the invention

[0004] In order to solve the problem that existing urban resilience evaluation technologies cannot realize urban resilience evaluation, this application proposes a comprehensive urban resilience evaluation method and system based on multi-dimensional power data fusion. This application is based on the power data of multiple dimensions in various fields of the city, and analyzes it to establish the relationship between power data and resilience in multiple fields of the city, thereby comprehensively evaluating urban resilience and providing a technical basis and reference for urban governance.

[0005] This application is implemented through the following technical solutions:

[0006] A comprehensive evaluation method for urban resilience based on multi-dimensional power data fusion, the method comprising:

[0007] Obtain multi-dimensional historical data in various fields of the city;

[0008] Based on the multiple dimensional historical data, the contribution parameters, stable parameters and fluctuation parameters of the multiple dimensional data are calculated;

[0009] Establish an urban resilience evaluation model based on the contribution parameters, stable parameters and fluctuation parameters of multiple dimensional data;

[0010] Based on the urban resilience evaluation model and combined with the three-order factor method, the urban resilience risk is judged.

[0011] In some embodiments, the multiple dimensional historical data include 12 fields, namely economy, education, energy, medical health, safety, public activities, communications, transportation, food production, environment, and industrial parks, and each field includes two dimensional power data, for a total of 24 dimensional data;

[0012] For each dimension of data, the corresponding time series data is collected according to the preset period to obtain 24 dimensions of time series data.

[0013] In some embodiments, the contribution parameter calculation process includes:

[0014] Calculate the mean of the time series data in each dimension;

[0015] Normalize the means of multiple dimensions;

[0016] The weight of each dimension is calculated based on the mean of multiple dimensions after normalization;

[0017] According to the mean values ​​and corresponding weights of the multiple dimensions after normalization, contribution parameters of the multiple dimensional data are calculated, and the contribution parameters are equal to the weighted sum of the mean values ​​of all dimensions.

[0018] In some implementations, the weight calculation process for each dimension includes:

[0019] Based on the average of multiple dimensions after normalization, the proportion of each dimension is calculated;

[0020] Based on the weight of each dimension, the corresponding information effective value is calculated;

[0021] According to the effective values ​​of information in multiple dimensions, the weight of each dimension is calculated, and the weight of each dimension is equal to the ratio of its corresponding effective value of information to the sum of the effective values ​​of information in all dimensions.

[0022] In some embodiments, the calculation of the stable parameters and the fluctuating parameters specifically includes:

[0023] Performing neighborhood normalization processing on the multiple dimensional historical data;

[0024] Perform singular value decomposition on the multi-dimensional data after neighborhood standardization to obtain the stationary parameters of the multi-dimensional data;

[0025] According to the singular value decomposition results, the fluctuation parameters of multi-dimensional data are obtained.

[0026] In some implementations, the neighborhood normalization process includes:

[0027] Performing local mean processing on the multiple dimensional historical data in the time domain to obtain the local expectation of the data in each dimension;

[0028] According to the local expectation of the data in each dimension, the local variance of the data in each dimension is calculated;

[0029] According to the local expectation and local variance of the data in each dimension, the original data in each dimension is normalized in the time domain by the nearest neighbor.

[0030] In some implementations, the urban resilience evaluation model established is:

[0031]

[0032] Among them, R (n) is the city resilience value, Q (n) is the fluctuation parameter, I (n) is a stable parameter, G n To contribute parameters.

[0033] In some implementations, the urban resilience risk assessment process includes:

[0034] The third-order factor method was used to obtain the predicted value of urban resilience;

[0035] Using the urban resilience evaluation model to calculate the urban resilience value;

[0036] Calculate the absolute value of the difference between the predicted city resilience value and the calculated city resilience value;

[0037] The absolute value of the difference is compared with a threshold value to determine whether there is a risk in urban resilience.

[0038] On the other hand, the present application proposes a comprehensive evaluation system for urban resilience based on multi-dimensional power data fusion, the system comprising:

[0039] A data acquisition module, which is used to acquire historical data of multiple dimensions in various fields of the city;

[0040] A feature extraction module, wherein the feature extraction module calculates contribution parameters, stable parameters and fluctuation parameters of the multiple dimensional data based on the multiple dimensional historical data;

[0041] A model building module, wherein the model building module establishes an urban resilience evaluation model according to contribution parameters, stable parameters and fluctuation parameters of multiple dimensional data;

[0042] And, a risk judgment module, which judges the urban resilience according to the urban resilience evaluation model and combined with the third-order factor method.

[0043] In some embodiments, the risk determination module further includes:

[0044] A prediction unit, wherein the prediction unit uses a third-order factor method to obtain a prediction value of urban resilience;

[0045] A resilience value calculation unit, wherein the resilience value calculation unit calculates the city resilience value using the city resilience evaluation model;

[0046] And, a comparison unit, which compares the city resilience prediction value with the calculated city resilience value to determine whether there is a risk in city resilience.

[0047] This application proposes a comprehensive evaluation method and system for urban resilience based on multi-dimensional power data fusion, which obtains multi-dimensional power data in various fields of the city, and mines out indicators reflecting urban resilience in multi-dimensional data based on this, including contribution parameters, stable parameters and fluctuation parameters of multi-dimensional data, and establishes an urban resilience evaluation model based on these indicator parameters. On the basis of the established urban resilience evaluation model, combined with the third-order factor method, a comprehensive judgment of urban resilience risk is achieved;

[0048] This application proposes a comprehensive urban resilience evaluation method and system based on multi-dimensional power data fusion, which can accurately and quickly complete urban resilience risk assessment and provide more reliable technical support and technical reference for urban governance and construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings described herein are used to provide a further understanding of the embodiments of the present application, constitute a part of the present application, and do not constitute a limitation on the embodiments of the present application. In the drawings:

[0050] Figure 1 A flow chart of a method according to an embodiment of the present application;

[0051] Figure 2 This is a system principle block diagram of an embodiment of the present application;

[0052] Figure 3 This is an example of the urban resilience value and predicted value calculated by the model in the embodiments of the present application. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with examples and drawings. The illustrative implementation scheme of the present application and its description are only used to explain the present application and are not intended to limit the present application.

[0054] Example:

[0055] Most of the existing technologies for evaluating urban resilience are to unilaterally evaluate the resilience of a certain area of ​​the city, and cannot achieve a comprehensive evaluation of urban resilience. Urban resilience involves multiple fields such as economy, communication, environment, education, and medical care, and each field has a certain connection with power data. Based on this, this application proposes a comprehensive evaluation method for urban resilience based on multi-dimensional power data fusion. This application establishes a connection between power data and the resilience of multiple areas of the city to achieve a comprehensive evaluation of urban resilience, providing a more reliable technical basis for urban governance.

[0056] like Figure 1 As shown, the method proposed in this embodiment specifically includes the following steps:

[0057] Step 100, obtaining multi-dimensional historical data of various fields in the city.

[0058] This step 100 uses the relevant data of the power infrastructure in various fields of the city as input to evaluate the comprehensive resilience of the city from multiple aspects. Optionally, according to the urban field classification standard, the multi-dimensional historical data obtained in this step 100 includes 12 aspects (fields): economy, education, energy, medical health, safety, public activities, communications, transportation, food production, environment, disasters, industrial parks, etc. Each aspect includes two sub-dimensions, namely X i =[x i,1 ,x i,2 ] T , a total of 24 dimensions of data. Among them, X i represents the historical data of the ith aspect, x i,1 ,x i,2 Represent the historical data of the first dimension and the second dimension of the i-th aspect respectively.

[0059] Among them, the two dimensions of economic data are: electricity consumed per 100 million yuan of economic value (x 1,1 ); Electricity consumption of the city / total value of the city's economy (in months); Growth rate of urban electricity consumption / growth rate of urban economy (x 1,2 ).

[0060] The two dimensions of education data are: per capita student electricity consumption rate (x 2,1 ); Number of teaching hours lost due to electricity in education (x 2,2 ).

[0061] The two dimensions of energy are: the number of diversified electricity sources (x 3,1 ); The percentage of electricity supply capacity to peak electricity demand (x 3,2 ).

[0062] The two dimensions of medical and health data are: the percentage of hospitals equipped with emergency power supplies (x4,1 ); Hospital electricity consumption growth rate (x 4,2 ).

[0063] The two dimensions of safety data are: the proportion of power timely response to local disasters (x 5,1 ); Number of power facilities damaged by disasters (x 5,2 ).

[0064] The two dimensions of public events are: the ratio of the number of large events not affected by electricity to the total number of events (x 6,1 ); Hours of power outages due to major events (x 6,2 ).

[0065] The data of two dimensions in communication are: the growth rate of communication power consumption (x 7,1 ); the number of communication interruptions and power drops (x 7,2 ).

[0066] The two dimensions of traffic data are: the growth rate of new energy vehicle electricity consumption (x 8,1 ); the number of power outages caused by traffic disruptions (x 8,2 ).

[0067] The two dimensions of grain production data are: Electricity consumed per unit of grain: Electricity consumed by grain / Total grain production (x 9,1 ); The impact of electricity on food production: the reduction in food production caused by insufficient electricity supply / the electricity consumed by food (x 9,2 ).

[0068] The two dimensions of environmental data are: power consumption of production equipment and pollution control equipment (x 10,1 ); electricity consumption data and air pollution index (x 10,2 ).

[0069] The two dimensions of disaster data are: the number of power outages caused by disasters (x 11,1 ); Time for restoration of disaster power outage (x 11,2 ).

[0070] The two dimensions of data for industrial parks are: the ratio of enterprise economic growth to electricity growth (x 12,1 ); the ratio of enterprise safety level to electricity growth rate (x 12,2 ).

[0071] In this step, for each dimension, the corresponding time series data is collected according to the preset period. Specifically, the corresponding time series data can be obtained in a weekly period:

[0072]

[0073] in, Represents the value of the kth week in the i-th row and j-th column.

[0074] The resilience data of the cities in 24 dimensions in the previous n weeks are obtained, expressed as:

[0075]

[0076] Step 200, based on the historical data of multiple dimensions, calculate the contribution parameters, stable parameters and fluctuation parameters of the data of multiple dimensions.

[0077] This step 200 obtains contribution parameters of multiple dimensional data by analyzing the acquired multiple dimensional historical data. The specific process is as follows:

[0078] Step 2011, calculate and obtain the mean of the time series data of each dimension.

[0079] This step 2011 calculates the mean of the time series data of each dimension, which is specifically expressed as:

[0080]

[0081] The mean of 24 dimensions is obtained, expressed as:

[0082]

[0083] Step 2012, normalize the means of multiple dimensions.

[0084] In step 2012, the means of the 24 dimensions are normalized to obtain the normalized means of the 24 dimensions, which is expressed as:

[0085]

[0086] This step 2012 adopts but is not limited to the maximum and minimum normalization method to normalize the mean values ​​of the above 24 dimensions. The specific processing method is:

[0087]

[0088] in, represents the original mean, represents the normalized mean, min(u (n) ) represents the minimum value in the original mean, max(u (n) ) represents the maximum value among the original means.

[0089] Step 2013, the weight of each dimension is calculated based on the average of multiple dimensions after normalization.

[0090] The step 2013 specifically includes the following process:

[0091] First, based on the average of multiple dimensions after normalization, the proportion of each dimension is calculated as follows:

[0092]

[0093] Among them, sum() means sum.

[0094] Then, based on the weight of each dimension, the corresponding information effective value is calculated to obtain the information effective value of multiple dimensions, which is expressed as:

[0095]

[0096] The specific calculation method of the effective value of information is:

[0097]

[0098] Finally, according to the effective value of information in multiple dimensions, the weight of each dimension is calculated. The specific calculation formula is:

[0099]

[0100] Step 2014, calculating contribution parameters of the multiple dimensional data according to the normalized means of the multiple dimensions and the weights of the multiple dimensions.

[0101] In step 2014, contribution parameters of multiple dimensional data are calculated specifically by the following formula:

[0102]

[0103] Based on the historical data of multiple dimensions, the process of calculating the stable parameters and fluctuation parameters of multiple dimensions of data includes:

[0104] Step 2021, perform neighborhood normalization processing on historical data of multiple dimensions.

[0105] Specifically, the data in each dimension of the resilience data of the 24 dimensional cities in the previous n weeks are processed by neighborhood normalization. First, the historical data of multiple dimensions are processed by local mean in the time domain to reduce the impact of time correlation in the same dimension. The details are as follows:

[0106] Among them, calculation local expectations.

[0107] (1) For k ≥ 6, the local expectation is calculated using the following formula:

[0108]

[0109] (2) For k < 6, the local expectation is calculated using the following formula:

[0110]

[0111] Then, based on the local expectation, calculate the local variance.

[0112] (1) For k ≥ 6, the local variance is calculated using the following formula:

[0113]

[0114] (2) For k < 6, the local variance is calculated using the following formula:

[0115]

[0116] Finally, based on the local expectation and local variance, perform time-domain nearest neighbor normalization on to obtain:

[0117]

[0118] Perform neighborhood normalization on the 24-dimensional data X (n) according to the above process to obtain the matrix

[0119]

[0120] Step 2022: Perform singular value decomposition on the multi-dimensional data after neighborhood normalization to obtain the stationary parameters of multiple dimensional data. The specific process is as follows:

[0121] Perform singular value decomposition on the multi-dimensional data after neighborhood normalization which is expressed as:

[0122]

[0123] where U (n) is a 24×24 unitary matrix, S (n) is a 24×n diagonal matrix, and V (n) T is an n×n orthogonal transformation matrix.

[0124] Let Z (n) = U (n) S (n) Then Z (n) is a 24×n matrix. Take the first r (r < n) columns of Z (n) to obtain the matrix P (r) where P (r) is a 24×r matrix. Take V (n)TThe first r rows, get the matrix Q (n) , Q (n) For an r×n matrix, we have:

[0125] Y (n) =PQ

[0126] Among them, Y (n) for Approximate matrix, let the error between the two be E (n) , then:

[0127]

[0128] Then we can get the stable parameters of multiple dimensional data as:

[0129]

[0130] in, for The transposed matrix, S (n)-1 Indicates S (n) Find the inverse.

[0131] Step 2023, based on the singular value decomposition results, obtain the fluctuation parameters of multiple dimensional data.

[0132] Fluctuation parameter Q (n) The calculation formula is:

[0133]

[0134] Step 300, establishing a city resilience evaluation model based on contribution parameters, stable parameters and fluctuation parameters of multiple dimensional data.

[0135] That is, the contribution parameter represents the main information of urban resilience; the stable parameter is the stable part of the multidimensional information, which is equivalent to the statistical mean; the fluctuation parameter reflects the fluctuation of the multidimensional information, that is, the degree of deviation from the multidimensional information; therefore, this embodiment modifies the contribution parameter through the fluctuation parameter and the stable parameter, so as to obtain a more accurate comprehensive evaluation of urban resilience. The urban resilience evaluation model established in step 300 is:

[0136]

[0137] Step 400, judging the urban resilience risk based on the urban resilience evaluation model and combined with the third-order factor method.

[0138] The step 400 specifically includes the following process:

[0139] Step 401, using the third-order factor method to obtain the predicted value of urban resilience.

[0140] Among them, the predicted value of urban resilience in week n+k is obtained by the third-order factor method, and the process is as follows:

[0141]

[0142]

[0143]

[0144] When n<1, Here, α is a weight value, which is usually between 0 and 1, and preferably 0.6.

[0145] The predicted value of urban resilience in week n+k is:

[0146]

[0147] Among them, a n 、b n 、c n All are factor coefficients, and the calculation formula is:

[0148]

[0149]

[0150]

[0151] Step 402: Calculate the city resilience value using the city resilience evaluation model.

[0152] The urban resilience value of the n+k week calculated using the urban resilience evaluation model is R (n+k) .

[0153] Step 403, compare the predicted value of urban resilience with the calculated value of urban resilience to determine whether there is a risk in urban resilience.

[0154] In step 403, the absolute value ER of the difference between the predicted urban resilience value and the calculated urban resilience value is first calculated. It can be expressed as:

[0155]

[0156] Then, the absolute value of the difference is compared with the threshold to determine whether there is a risk in urban resilience. If the absolute value of the difference is greater than the threshold, it means that the urban resilience is poor, otherwise it is good.

[0157] The method proposed in this embodiment obtains power data of multiple dimensions in various fields of the city, and based on this, mines out indicators that reflect urban resilience in the data of multiple dimensions, including contribution parameters, stable parameters and fluctuating parameters of the data of multiple dimensions, and establishes an urban resilience evaluation model based on these indicator parameters. Based on the established urban resilience evaluation model, the third-order factor method is used to predict future urban resilience, and the predicted value is compared with the urban resilience value calculated using the urban resilience evaluation model to determine whether there is any abnormality in urban resilience.

[0158] Based on the same technical concept as above, this embodiment also proposes a comprehensive evaluation system for urban resilience based on multi-dimensional power data fusion, such as Figure 2 As shown, the system proposed in this embodiment specifically includes:

[0159] The data acquisition module is used to acquire the multi-dimensional historical data of various fields in the city. The historical data acquisition process is as described in the above step 100, which will not be described in detail here.

[0160] The feature extraction module calculates the contribution parameters, stable parameters and fluctuation parameters of the multi-dimensional data based on the multi-dimensional historical data.

[0161] A model building module is used to build a city resilience evaluation model based on the contribution parameters, stable parameters and fluctuation parameters of multiple dimensional data. The model built is as described in step 300 above, and will not be described in detail here.

[0162] And, a risk judgment module, which judges the urban resilience risk based on the urban resilience evaluation model and combined with the third-order factor method.

[0163] Furthermore, the feature extraction module also includes:

[0164] The first parameter calculation unit calculates the contribution parameters of the multiple dimensional data based on the multiple dimensional historical data. The specific calculation process is as described in the above steps 2011 to 2014, which will not be repeated here.

[0165] And, a second parameter calculation unit, which calculates the stable parameters and fluctuation parameters of the multiple dimensional data based on the multiple dimensional historical data. The specific calculation process is as described in the above steps 2021 to 2023, and will not be repeated here.

[0166] Furthermore, the risk judgment module also includes:

[0167] The prediction unit uses the third-order factor method to obtain the predicted value of urban resilience. The specific process is as described in step 401 and will not be described in detail here.

[0168] The resilience value calculation unit calculates the city resilience value using the city resilience evaluation model. The specific process is as described in step 402 and will not be described in detail here.

[0169] And, a comparison unit, which compares the predicted value of urban resilience with the calculated value of urban resilience to determine whether there is a risk in urban resilience. The specific process is as described in step 403, and will not be described in detail here.

[0170] This example takes XX city as an example and uses the above method to evaluate the resilience of the city. Figure 3 The urban resilience values ​​(i.e. actual values) from week 22 to week 33 in 2023 calculated using the urban resilience evaluation model and the predicted values ​​obtained using the third-order factor method are given.

[0171] As can be seen from the figure, the actual value in the 28th week is quite different from the estimated value, and the difference is greater than 4 (threshold). It can be determined that the resilience of XX city in the 28th week is relatively poor.

[0172] In practice, heavy rains in the city in week 28 caused urban waterlogging and some traffic terminations, which led to a decrease in the city’s resilience. This is consistent with the conclusions obtained using this method.

[0173] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0174] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0175] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0177] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation method of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A comprehensive evaluation method for urban resilience based on multi-dimensional power data fusion, characterized in that: The method comprises: Obtain multi-dimensional historical data in various fields of the city; Based on the multiple dimensional historical data, the contribution parameters, stable parameters and fluctuation parameters of the multiple dimensional data are calculated; Establish an urban resilience evaluation model based on the contribution parameters, stable parameters and fluctuation parameters of multiple dimensional data; Based on the urban resilience evaluation model and combined with the three-order factor method, the urban resilience risk is judged.

2. According to claim 1, a comprehensive evaluation method for urban resilience based on multi-dimensional power data fusion is characterized in that: The multiple dimensional historical data include 12 fields, namely economy, education, energy, medical health, safety, public activities, communications, transportation, food production, environment, and industrial parks, and each field includes two dimensional power data, for a total of 24 dimensional data; For each dimension of data, the corresponding time series data is collected according to the preset period to obtain 24 dimensions of time series data.

3. The comprehensive evaluation method of urban resilience based on multi-dimensional power data fusion according to claim 2 is characterized in that: The contribution parameter calculation process includes: Calculate the mean of the time series data in each dimension; Normalize the means of multiple dimensions; The weight of each dimension is calculated based on the mean of multiple dimensions after normalization; According to the mean values ​​and corresponding weights of the multiple dimensions after normalization, contribution parameters of the multiple dimensional data are calculated, and the contribution parameters are equal to the weighted sum of the mean values ​​of all dimensions.

4. The comprehensive evaluation method of urban resilience based on multi-dimensional power data fusion according to claim 3 is characterized in that: The weight calculation process of each dimension includes: Based on the average of multiple dimensions after normalization, the proportion of each dimension is calculated; Based on the weight of each dimension, the corresponding information effective value is calculated; According to the effective values ​​of information in multiple dimensions, the weight of each dimension is calculated, and the weight of each dimension is equal to the ratio of its corresponding effective value of information to the sum of the effective values ​​of information in all dimensions.

5. A comprehensive evaluation method for urban resilience based on multi-dimensional power data fusion according to any one of claims 2 to 4, characterized in that: The calculation of the stable parameters and the fluctuating parameters specifically includes: Performing neighborhood normalization processing on the multiple dimensional historical data; Perform singular value decomposition on the multi-dimensional data after neighborhood standardization to obtain the stationary parameters of the multi-dimensional data; According to the singular value decomposition results, the fluctuation parameters of multi-dimensional data are obtained.

6. The comprehensive evaluation method of urban resilience based on multi-dimensional power data fusion according to claim 5 is characterized in that: The neighborhood standardization process includes: Performing local mean processing on the historical data of the multiple dimensions in the time domain to obtain the local expectation of the data in each dimension; According to the local expectation of the data in each dimension, the local variance of the data in each dimension is calculated; According to the local expectation and local variance of the data in each dimension, the original data in each dimension is normalized in the time domain by the nearest neighbor.

7. The comprehensive evaluation method of urban resilience based on multi-dimensional power data fusion according to claim 5 is characterized in that: The urban resilience evaluation model established is: Among them, R (n) is the city resilience value, Q (n) is the fluctuation parameter, I (n) is a stable parameter, G n To contribute parameters.

8. The comprehensive evaluation method of urban resilience based on multi-dimensional power data fusion according to claim 5 is characterized in that: The urban resilience risk assessment process includes: The third-order factor method was used to obtain the predicted value of urban resilience; Using the urban resilience evaluation model to calculate the urban resilience value; Calculate the absolute value of the difference between the predicted city resilience value and the calculated city resilience value; The absolute value of the difference is compared with a threshold value to determine whether there is a risk in urban resilience.

9. A comprehensive evaluation system for urban resilience based on multi-dimensional power data fusion, characterized in that: The system comprises: A data acquisition module, which is used to acquire historical data of multiple dimensions in various fields of the city; A feature extraction module, wherein the feature extraction module calculates contribution parameters, stable parameters and fluctuation parameters of the multiple dimensional data based on the multiple dimensional historical data; A model building module, wherein the model building module establishes an urban resilience evaluation model according to contribution parameters, stable parameters and fluctuation parameters of multiple dimensional data; And, a risk judgment module, which judges the urban resilience according to the urban resilience evaluation model and combined with the third-order factor method.

10. The comprehensive evaluation system for urban resilience based on multi-dimensional power data fusion according to claim 9 is characterized in that: The risk judgment module also includes: A prediction unit, wherein the prediction unit uses a third-order factor method to obtain a prediction value of urban resilience; A resilience value calculation unit, wherein the resilience value calculation unit calculates the city resilience value using the city resilience evaluation model; And, a comparison unit, which compares the city resilience prediction value with the calculated city resilience value to determine whether there is a risk in city resilience.

Citation Information

Cited By

  • Urban vitality evaluation system based on multi-source dynamic big data fusion analysis

    CN119863163A