Earthquake intensity prediction method and device based on earthquake destructive power

Abstract

The invention relates to the technical field of seismic intensity prediction, in particular to a seismic intensity prediction method and device based on seismic destructive power, and the method comprises the following steps: obtaining seismic destructive power data of a target area; and inputting the earthquake destructive power data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station, thereby realizing accurate prediction of the earthquake intensity according to the building damage condition. Wherein the earthquake destructive power data is the proportion of all the damage states of all types of building disaster-bearing bodies and the proportion of all the damage states of the whole building disaster-bearing bodies, and the earthquake intensity prediction model is obtained by training a machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive power. The target area is an area adjacent to the target station.

Description

Technical Field

[0001] The present invention relates to the technical field of earthquake intensity prediction, and in particular to a method and device for predicting earthquake intensity based on earthquake destructive force. Background Art

[0002] Earthquake activity is considered one of the most destructive natural disasters in the world. Earthquake intensity indicates the strength of the impact of an earthquake on the surface and engineering buildings (or the degree of earthquake impact and damage). It is a macro scale determined by people's feelings during an earthquake or the degree of reaction of objects after an earthquake, the degree of damage or destruction of engineering buildings, and the changes in the surface of the earth without instrumental records. However, existing methods generally use earthquake parameters to predict earthquake intensity, and do not consider the impact of building damage on earthquake intensity in the actual prediction process.

[0003] Currently, when an earthquake occurs, buildings in the target area are often destroyed. Since existing methods do not consider the impact of building damage on earthquake intensity, it is impossible to accurately predict earthquake intensity based on building damage. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for predicting earthquake intensity based on earthquake destructive force, so as to solve the problem that earthquake intensity cannot be accurately predicted according to building damage.

[0005] An embodiment of the present invention provides an earthquake intensity prediction method based on earthquake destructive force, the method comprising the following steps: obtaining earthquake destructive force data of a target area, the earthquake destructive force data being the ratio between various damage states of various types of building disaster-bearing bodies and the ratio between various damage states of the building disaster-bearing bodies as a whole; inputting the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of a target station, the earthquake intensity prediction model being obtained by training a machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive force; wherein the target area is an area adjacent to the target station.

[0006] Optionally, obtaining earthquake destructive force data of the target area includes: obtaining measured seismic motion data of the target station; inputting the measured seismic motion data into a pre-established building earthquake damage analysis model of the target area to obtain measured earthquake response data of the target area; obtaining the damage state of each building disaster-bearing body according to the measured earthquake response data and earthquake damage state judgment criteria; and calculating the earthquake destructive force data of the target area according to the damage state of each building disaster-bearing body.

[0007] Optionally, the method further includes: obtaining historical seismic data of the target station and building attribute data of the building disaster-bearing body model of the target area; and constructing the building earthquake damage analysis model based on the historical seismic data, the building attribute data and the urban seismic elastoplastic analysis method.

[0008] Optionally, the method further comprises: constructing the building disaster-prone body model according to the building statistical law data of the target area; wherein the building statistical law data comprises the statistical law of the building structure type, the construction year and the number of building floors.

[0009] Optionally, the method also includes: obtaining historical earthquake intensity data and historical earthquake destructive force data of the target area; converting the historical earthquake destructive force data into a first characteristic matrix as the input of the earthquake intensity prediction model, converting the historical earthquake intensity data into a one-dimensional vector as the output of the earthquake intensity prediction model, and constructing the earthquake intensity prediction model by training historical data using a K-nearest neighbor algorithm; wherein the historical data includes the historical earthquake intensity data and the historical earthquake destructive force data of the target area, the first characteristic matrix is ​​an i×j×k matrix, i is the type of the damage state, j is the number of structural types of the building disaster-bearing body plus one, k is the number of groups of the historical data, and the one-dimensional vector is a 1×k vector.

[0010] Optionally, the inputting the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station includes: converting the earthquake destructive force data into a second characteristic matrix and inputting it into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station; wherein the second characteristic matrix is ​​an i×j matrix, and the earthquake intensity of the target station is a 1×1 vector.

[0011] Optionally, the structural types of the building disaster-bearing body include frame structure, frame-shear structure, unfortified masonry structure, fortified masonry and civil structure; the damage states include intact, slight damage, moderate damage, severe damage and collapse damage.

[0012] Optionally, the earthquake response data includes an inter-story displacement angle, and the earthquake damage state judgment criterion is to divide the damage state of each of the building disaster-bearing bodies according to the inter-story displacement angle.

[0013] Compared with the prior art, the earthquake intensity prediction method based on earthquake destructive force provided by the present invention has the following beneficial effects:

[0014] The earthquake intensity prediction method based on earthquake destructive force provided by the embodiment of the present invention obtains earthquake destructive force data of the target area; inputs the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station, thereby accurately predicting the earthquake intensity according to the building damage. The earthquake destructive force data is the ratio between various damage states of various types of building disaster-bearing bodies and the ratio between various damage states of the building disaster-bearing body as a whole. The earthquake intensity prediction model is obtained by training a machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive force. The target area is an area adjacent to the target station.

[0015] An embodiment of the present invention also provides an earthquake intensity prediction device based on earthquake destructive force, which is used to implement the above-mentioned earthquake intensity prediction method based on earthquake destructive force, and the device includes: an acquisition module, which is used to obtain earthquake destructive force data of a target area, and the earthquake destructive force data is the ratio between various damage states of various types of building disaster-bearing bodies and the ratio between various damage states of the building disaster-bearing body as a whole; a prediction module, which is used to input the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station, and the earthquake intensity prediction model is obtained by training a machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive force; wherein, the target area is an area adjacent to the target station.

[0016] The earthquake intensity prediction device based on earthquake destructive force provided by the present invention has the beneficial effect of being able to achieve the same technical effect as the above-mentioned earthquake intensity prediction method based on earthquake destructive force, and will not be described again here to avoid repetition.

[0017] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the above-mentioned earthquake intensity prediction method based on earthquake destructive force is implemented.

[0018] The computer-readable storage medium provided by the present invention has the beneficial effect of being able to achieve the same technical effect as the above-mentioned earthquake intensity prediction method based on earthquake destructive force, and will not be described again here to avoid repetition. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0020] Figure 1A schematic flow chart of a method for predicting earthquake intensity based on earthquake destructive force provided by an embodiment of the present invention;

[0021] Figure 2 Schematic diagram of the K-nearest neighbor algorithm model in an embodiment of the present invention;

[0022] Figure 3 A schematic flow chart of a method for predicting earthquake intensity based on a K-nearest neighbor algorithm and earthquake destructive force provided in an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of a confusion matrix corresponding to a prediction result of an earthquake intensity prediction model in an embodiment of the present invention;

[0024] Figure 5 Schematic diagram of comparison of earthquake intensity prediction accuracy in an embodiment of the present invention;

[0025] Figure 6 A schematic structural diagram of an earthquake intensity prediction device based on earthquake destructive force provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0027] The embodiment of the present invention provides a method for predicting earthquake intensity based on earthquake destructive force, see Figure 1 A schematic flow chart of a method for predicting earthquake intensity based on earthquake destructive force is shown, the method comprising the following steps:

[0028] S110, obtaining earthquake destructive force data of the target area.

[0029] The earthquake destructive force data are the ratios between various damage states of various types of building disaster-bearing bodies and the ratios between various damage states of the building disaster-bearing body as a whole.

[0030] Optionally, the above step S110 includes: obtaining measured seismic motion data of the target station; inputting the above seismic motion data into a pre-established building earthquake damage analysis model of the above target area to obtain seismic response data of the target area; obtaining the damage state of each building disaster-bearing body according to the above measured seismic response data and earthquake damage state judgment criteria; and calculating the earthquake destructive force data of the above target area according to the damage state of each building disaster-bearing body.

[0031] S120, inputting the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station.

[0032] Among them, the above-mentioned earthquake intensity prediction model is obtained by training the machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive power. The above-mentioned target area is the area adjacent to the above-mentioned target station. It should be noted that the above-mentioned historical earthquake intensity data can be obtained from the earthquake intensity map.

[0033] Optionally, the above step S120 includes: converting the earthquake destructive force data into a second characteristic matrix and inputting it into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station.

[0034] Among them, the above-mentioned second characteristic matrix is ​​an i×j matrix, i is the type of damage state, and j is the number of structural types of the building disaster-bearing body plus one; the earthquake intensity of the above-mentioned target station is a 1×1 vector, which is equivalent to a number.

[0035] The earthquake intensity prediction method based on earthquake destructive force provided in an embodiment of the present invention obtains earthquake destructive force data of a target area; inputs the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of a target station, thereby accurately predicting the earthquake intensity according to the building damage situation; wherein the earthquake destructive force data are the ratios between various damage states of various types of building disaster-sustaining bodies and the ratios between various damage states of the building disaster-sustaining bodies as a whole; the earthquake intensity prediction model is obtained by training a machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive force; and the target area is an area adjacent to the target station.

[0036] Optionally, the above method also includes: obtaining historical seismic motion data of the target station and building attribute data of the building disaster-bearing body model of the target area; constructing a building earthquake damage analysis model of the above target area based on the above historical seismic motion data, the above building attribute data and the urban seismic elastoplastic analysis method.

[0037] Optionally, the method further comprises: constructing a building disaster-prone body model according to the building statistical law data of the target area.

[0038] The above-mentioned building statistical law data include the statistical laws of building structure type, construction year and number of building floors.

[0039] Optionally, the above method also includes: obtaining historical earthquake intensity data and historical earthquake destructive power data of the target area; converting the above historical earthquake destructive power data into a first characteristic matrix as the input of the earthquake intensity prediction model, converting the above historical earthquake intensity data into a one-dimensional vector as the output of the earthquake intensity prediction model, and using the K nearest neighbor algorithm to train the historical data to construct the above earthquake intensity prediction model.

[0040] The above historical data include historical earthquake intensity data and historical earthquake destructive force data of the target area. The above historical earthquake intensity data can be obtained from publicly released earthquake intensity maps. The above first characteristic matrix is ​​an i×j×k matrix, i is the type of the above damage state, j is the number of structural types of the building disaster-bearing body plus one, k is the number of groups of historical data, and the above one-dimensional vector is a 1×k vector.

[0041] Exemplarily, the historical earthquake destructive power data corresponding to each group of historical data are written into the corresponding classification elements to form a first characteristic matrix, and the above-mentioned first characteristic matrix is ​​used as the input of the earthquake intensity prediction model, and the above-mentioned input is a variable screened according to the permutation importance method; the above-mentioned one-dimensional vector is a 1×k vector, and the historical earthquake intensity data corresponding to each group of historical data are written into the corresponding classification elements to form a one-dimensional vector, and the above-mentioned one-dimensional vector is used as the output of the earthquake intensity prediction model. In addition, the above-mentioned first characteristic matrix and the above-mentioned one-dimensional vector can be transposed as needed.

[0042] It should be noted that the above K nearest neighbor algorithm was selected based on the principle of the highest prediction accuracy after comparison with random forest, support vector machine, logistic regression and other algorithms. Figure 2 The schematic diagram of the K-nearest neighbor algorithm model shown in the figure. The principle of the K-nearest neighbor algorithm model is that in the feature space, if most of the k nearest neighbors (i.e., the closest neighbors in the feature space) of a sample belong to a certain category, then the sample is also judged to belong to this category, that is, Figure 2 The middle circle is the feature space of the sample, and the sample with the largest number of black dots is determined to belong to the category of black dots. By way of example, in an embodiment of the present invention, the type of damage state can be used as the horizontal coordinate, and the number of building structure types plus one can be used as the vertical coordinate to construct the feature space corresponding to the K nearest neighbor algorithm model. In addition, since an earthquake contains multiple seismic motions, and each historical seismic motion can determine a set of historical data, multiple training sample points can be determined in the feature space in an earthquake to realize the training of the earthquake intensity prediction model. In the process of earthquake intensity prediction, the measured sample point can be determined to belong to a certain earthquake intensity category based on the fact that most of the k nearest neighbor training sample points near the measured sample point belong to this earthquake intensity category.

[0043] Optionally, the structural types of the above-mentioned building disaster-bearing bodies include frame structures, frame-shear structures, unfortified masonry structures, fortified masonry and civil structures; the above-mentioned damage states include intact, slight damage, moderate damage, severe damage and collapse damage.

[0044] Optionally, the earthquake response data include inter-story displacement angles, and the earthquake damage state judgment criterion is to divide the damage state of each building disaster-bearing body according to the inter-story displacement angles.

[0045] It should be noted that the earthquake response also includes floor acceleration and velocity. Based on the above floor acceleration and velocity, and then according to the pre-constructed damage state judgment criteria, the damage state of each building can be obtained.

[0046] The embodiment of the present invention also provides a method for predicting earthquake intensity based on the K nearest neighbor algorithm and earthquake destructive force, see Figure 3 A schematic flow chart of a method for predicting earthquake intensity based on a K-nearest neighbor algorithm and earthquake destructive force is shown, and the method mainly comprises the following steps:

[0047] Step S302, obtain the strong earthquake record of the station, construct a building disaster-bearing body model that conforms to the statistical law of buildings in the target area, and use urban seismic elastoplastic analysis to calculate and determine the seismic destructive force of the strong earthquake here.

[0048] It should be noted that the strong motion records of the above-mentioned stations are completed strong motion time series, including seismic acceleration time series data in the east-west and north-south horizontal directions.

[0049] Specifically, the above-mentioned construction of a building disaster-bearing body model that conforms to the statistical laws of buildings in the target area is to generate a virtual building disaster-bearing body model that conforms to the statistical laws of the target building according to the statistical laws of the building structure type, construction age, and number of floors in the target area; the above-mentioned earthquake destructive force refers to the proportion of five damage states of buildings of each structural type calculated under a given strong vibration record of the building disaster-bearing body and the proportion of five damage states of the building as a whole; the five structural types of building damage states of the above-mentioned building disaster-bearing body are specifically divided into: intact, slight damage, moderate damage, severe damage, and collapse damage; the proportion of the overall damage state of the above-mentioned building disaster-bearing body is the proportion of each damage state to the overall building disaster-bearing body.

[0050] Step S304, inputting the earthquake destructive force into the earthquake intensity prediction model to obtain the earthquake intensity at the station output by the earthquake intensity prediction model.

[0051] Specifically, the characteristics of earthquake destructive power and earthquake intensity are extracted, and the proportions of various structural types of buildings and various overall damage states under each specific earthquake motion constitute a set of feature matrices input into the earthquake intensity prediction model, and the station earthquake intensity constitutes a one-dimensional vector as the output of the earthquake intensity prediction model; the above-mentioned earthquake intensity prediction model is obtained by training with the K nearest neighbor algorithm based on sample data of historical earthquake destructive power and historical earthquake intensity; the above-mentioned historical earthquake destructive power and historical earthquake intensity sample data sets are divided into data sets, with a part of the data used as a training set and the rest as a test set.

[0052] The earthquake intensity prediction model is trained using the training set, and the prediction performance of the earthquake intensity prediction model obtained by the training is tested using the test set to obtain test results. The test results are comprehensive evaluation indicators of the earthquake intensity prediction model based on the K nearest neighbor algorithm and earthquake destructive force. If the comprehensive evaluation indicators obtained meet expectations, the prediction results can accurately predict the earthquake intensity within the allowable error range.

[0053] Finally, based on the K nearest neighbor algorithm and the earthquake intensity prediction model of earthquake destructive force, the earthquake intensity of the target station is predicted.

[0054] It should be noted that the comprehensive evaluation indicators of the earthquake intensity prediction model include: Precision, Recall, F1-score, MacroAvg and WeightedAvg. The above comprehensive evaluation indicators are used to evaluate the prediction ability of the earthquake intensity prediction model.

[0055] Specifically, the calculation formula of the above comprehensive evaluation index is:

[0056] Precision = TP / (TP+FP) (1)

[0057] Recall = TP / (TP+FN) (2)

[0058] F1-score(F1 score)=2*(Precision*Recall) / (Precision+Recall) (3)

[0059]

[0060] Among them, TP represents the number of samples that belong to the category and are correctly predicted as the category, FP represents the number of samples that do not belong to the category but are incorrectly predicted as the category, FN represents the number of samples that belong to the category but are incorrectly predicted as other categories, and Precision i represents the accuracy of category i, N i Represents the number of samples of category i.

[0061] Exemplarily, Table 1 is a case data set in an embodiment of the present invention. The earthquake intensity prediction method based on earthquake destructive force provided in the embodiment of the present invention is applicable to but not limited to the earthquake cases in Table 1.

[0062] Table 1

[0063]

[0064] It should be noted that for each earthquake, multiple stations measure seismic data, and for each earthquake, multiple seismic motion data can be measured in a certain area.

[0065] Illustratively, Table 2 shows the comprehensive evaluation index results of the earthquake intensity prediction model for a case in an embodiment of the present invention.

[0066] Table 2

[0067]

[0068]

[0069] For example, see Figure 4 The schematic diagram of the confusion matrix of the prediction results of the earthquake intensity prediction model shown in the figure shows that only 6 samples out of 32 have wrong prediction results, which indicates that the prediction results obtained by the earthquake intensity prediction method based on earthquake destructive force provided by the embodiment of the present invention are reliable.

[0070] For example, see Figure 5 The schematic diagram of earthquake intensity prediction accuracy comparison is shown, in which the accuracy of the earthquake intensity prediction method based on earthquake destructive force provided by the embodiment of the present invention is higher than the accuracy of the traditional earthquake intensity prediction method directly using seismic motion parameters.

[0071] The earthquake intensity prediction method based on the K nearest neighbor algorithm and earthquake destructive force provided by the embodiment of the present invention can construct a building disaster-bearing body model that conforms to the statistical law of buildings in the target area based on the building types in the target area, use urban seismic elastoplastic analysis to calculate and determine the earthquake destructive force of strong vibrations here, and establish a mapping relationship between ground motion destructive force and earthquake intensity through the K nearest neighbor algorithm to predict the earthquake intensity of the target station. Compared with the existing earthquake intensity prediction method, the present invention takes into account the impact of building damage on earthquake intensity, can effectively improve the accuracy of earthquake intensity prediction at the target station, and reflects the impact of building damage on earthquake intensity.

[0072] The embodiment of the present invention also provides an earthquake intensity prediction device based on earthquake destructive force, which is used to implement the earthquake intensity prediction method based on earthquake destructive force, see Figure 6 The structure diagram of a device for predicting earthquake intensity based on earthquake destructive force is shown in FIG. 1 , and the device comprises:

[0073] The acquisition module 602 is used to acquire earthquake destructive force data of the target area.

[0074] The earthquake destructive force data are the ratios between various damage states of various types of building disaster-bearing bodies and the ratios between various damage states of the building disaster-bearing body as a whole.

[0075] The prediction module 604 is used to input the above earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station.

[0076] Among them, the above-mentioned earthquake intensity prediction model is obtained by training the machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive power, and the above-mentioned target area is the area adjacent to the above-mentioned target station.

[0077] The earthquake intensity prediction device based on earthquake destructive force provided by the present invention has the beneficial effect of being able to achieve the same technical effect as the above-mentioned earthquake intensity prediction method based on earthquake destructive force, and will not be described again here to avoid repetition.

[0078] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the earthquake intensity prediction method based on earthquake destructive force is implemented.

[0079] The computer-readable storage medium provided by the present invention has the beneficial effect of being able to achieve the same technical effect as the above-mentioned earthquake intensity prediction method based on earthquake destructive force, and will not be described again here to avoid repetition.

[0080] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the control device through a computer, and the program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the above-mentioned method embodiments, wherein the storage medium may be a memory, a disk, an optical disk, etc.

[0081] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0082] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0083] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined by the claims.

Claims

1. A method for predicting earthquake intensity based on earthquake destructive force, characterized in that: The method comprises the following steps: Acquire earthquake destructive force data of the target area, wherein the earthquake destructive force data is the ratio between various damage states of various types of building disaster-bearing bodies and the ratio between various damage states of the building disaster-bearing body as a whole; Inputting the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station, wherein the earthquake intensity prediction model is obtained by training a machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive force; The target area is an area adjacent to the target station.

2. The earthquake intensity prediction method based on earthquake destructive force according to claim 1, characterized in that: The step of obtaining earthquake destructive force data of the target area includes: Acquiring measured ground motion data of the target station; Inputting the measured seismic data into a pre-established building earthquake damage analysis model of the target area to obtain the measured earthquake response data of the target area; According to the measured earthquake response data and earthquake damage state judgment criteria, the damage state of each building disaster-bearing body is obtained; According to the damage status of each of the building disaster-bearing bodies, earthquake destructive force data of the target area is calculated.

3. The earthquake intensity prediction method based on earthquake destructive force according to claim 2, characterized in that: The method further comprises: Acquiring historical seismic data of the target station and building attribute data of a building disaster-bearing body model in the target area; The building earthquake damage analysis model is constructed based on the historical earthquake motion data, the building attribute data and the urban earthquake resistance elastoplastic analysis method.

4. The earthquake intensity prediction method based on earthquake destructive force according to claim 3, characterized in that: The method further comprises: Constructing the disaster-bearing building model according to the building statistical law data of the target area; The building statistical law data include the statistical laws of building structure type, construction year and number of building floors.

5. The earthquake intensity prediction method based on earthquake destructive force according to claim 1, characterized in that: The method further comprises: Acquiring historical earthquake intensity data and historical earthquake destructive force data of the target area; The historical earthquake destructive force data is converted into a first characteristic matrix as the input of the earthquake intensity prediction model, the historical earthquake intensity data is converted into a one-dimensional vector as the output of the earthquake intensity prediction model, and the earthquake intensity prediction model is constructed by training the historical data using a K nearest neighbor algorithm; Among them, the historical data includes the historical earthquake intensity data and the historical earthquake destructive force data of the target area, the first characteristic matrix is ​​an i×j×k matrix, i is the type of the damage state, j is the number of structural types of the building disaster-sustaining body plus one, k is the number of groups of the historical data, and the one-dimensional vector is a 1×k vector.

6. The earthquake intensity prediction method based on earthquake destructive force according to claim 5, characterized in that: The step of inputting the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station includes: Converting the earthquake destructive force data into a second characteristic matrix and inputting it into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station; The second characteristic matrix is ​​an i×j matrix, and the seismic intensity of the target station is a 1×1 vector.

7. The earthquake intensity prediction method based on earthquake destructive force according to claim 1, characterized in that: The structural types of the building disaster-bearing body include frame structure, frame-shear structure, unfortified masonry structure, fortified masonry and civil structure; The damage conditions include intact, slight damage, moderate damage, severe damage and collapse damage.

8. The earthquake intensity prediction method based on earthquake destructive force according to claim 2, characterized in that: The earthquake response data includes an inter-story displacement angle, and the earthquake damage state judgment criterion is to divide the damage state of each of the building disaster-bearing bodies according to the inter-story displacement angle.

9. An earthquake intensity prediction device based on earthquake destructive force, characterized in that: The device is used to implement the earthquake intensity prediction method based on earthquake destructive force as described in any one of claims 1 to 8, comprising: An acquisition module is used to acquire earthquake destructive force data of a target area, wherein the earthquake destructive force data is the ratio between various damage states of various types of building disaster-bearing bodies and the ratio between various damage states of the building disaster-bearing body as a whole; A prediction module, used for inputting the earthquake destructive force data into a pre-established earthquake intensity prediction model to obtain the earthquake intensity of the target station, wherein the earthquake intensity prediction model is obtained by training a machine learning algorithm based on historical earthquake intensity data and historical earthquake destructive force; The target area is an area adjacent to the target station.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images