CN116663752B - Geological disaster intelligent early warning system based on big data analysis - Google Patents
Geological disaster intelligent early warning system based on big data analysis Download PDFInfo
- Publication number
- CN116663752B CN116663752B CN202310944285.3A CN202310944285A CN116663752B CN 116663752 B CN116663752 B CN 116663752B CN 202310944285 A CN202310944285 A CN 202310944285A CN 116663752 B CN116663752 B CN 116663752B
- Authority
- CN
- China
- Prior art keywords
- collapse
- data
- module
- scale level
- density
- 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.)
- Active
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 15
- 238000009499 grossing Methods 0.000 claims abstract description 46
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 50
- 238000000034 method Methods 0.000 claims description 34
- 230000009469 supplementation Effects 0.000 claims description 9
- 238000002864 sequence alignment Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Mathematical Optimization (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Environmental & Geological Engineering (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Computer Security & Cryptography (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Geology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
Abstract
The application belongs to the technical field of data processing, and provides a geological disaster intelligent early warning system based on big data analysis, which comprises the following steps: the system comprises a data acquisition and storage module, a data processing module, a prediction module and an early warning module; the data acquisition and storage module is used for acquiring and storing P-wave data and historical collapse data; the data processing module is used for accessing and processing the P-wave data and the historical collapse data and comprises a data preprocessing sub-module, a collapse period density computing sub-module, a collapse scale level density computing sub-module, a collapse predictable coefficient computing sub-module and a smoothing factor computing sub-module; the prediction module is used for carrying out short-term prediction on the P wave data according to the smoothing factors, and then calculating according to the P wave short-term prediction data to obtain a predicted collapse scale level; the early warning module is used for carrying out grading early warning according to the grade of the predicted collapse scale. The smoothing factor obtained by the system provided by the application is more in line with the collapse characteristic, so that the accuracy of collapse prediction is improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an intelligent geological disaster early warning system based on big data analysis.
Background
The intelligent early warning system for the geological disasters is a comprehensive application system based on modern information technology and advanced prediction algorithm, and can realize automatic monitoring and real-time early warning of the geological disasters to a certain extent. The method generally comprises the steps of firstly acquiring geological data through a sensor, then processing the geological data through an intelligent algorithm model, judging the occurrence possibility of geological disasters according to the data model, and providing early warning and prediction services.
The implementation of the intelligent early warning system is dependent on various modern information technologies and algorithms, such as internet of things technology, big data analysis, machine learning, artificial intelligence and the like, and real-time adjustment and optimization are required to be carried out by combining the actual conditions of the site. The traditional geological disaster early warning method comprises an early warning method based on a sensor and an early warning method based on a mathematical model, wherein the early warning method based on the sensor carries out geological disaster early warning by installing the sensor in a geological disaster area and monitoring related geological data, has the characteristics of strong instantaneity and high precision, but needs to deploy a large number of sensors, and has higher cost; the early warning method based on the mathematical model can solve the problem of limited coverage range of the sensor by establishing the model for analyzing the geological disaster data, but needs to continuously debug the model, and has higher requirements on the integrity and accuracy of the data.
Therefore, a geological disaster early warning system is needed to realize comprehensive and accurate early warning of geological disasters.
Disclosure of Invention
The application provides an intelligent geological disaster early warning system based on big data analysis, which is used for solving the technical problems.
The utility model provides a geological disaster intelligent early warning system based on big data analysis, the system includes: the system comprises a data acquisition and storage module, a data processing module, a prediction module and an early warning module; wherein:
the data acquisition and storage module is used for acquiring and storing P-wave data and historical collapse data, wherein the historical collapse data comprises time data and collapse scale level data;
the data processing module is configured with a geological disaster early warning analysis model and is used for accessing and processing the P-wave data and the historical collapse data, and comprises a data preprocessing sub-module, a collapse period density computing sub-module, a collapse scale level density computing sub-module, a collapse predictable coefficient computing sub-module and a smoothing factor computing sub-module;
the prediction module is used for carrying out short-term prediction on the P wave data by using an exponential moving average method according to a smoothing factor to obtain P wave short-term prediction data, then calculating according to a collapse scale level calculation formula according to the P wave short-term prediction data to obtain a predicted collapse scale level, and sending the predicted collapse scale level to the collapse disaster early warning module;
and the early warning module is used for carrying out grading early warning according to the predicted collapse scale level.
In some embodiments of the application, the P-wave data and the historical collapse data are stored in a large-scale distributed storage system, including Hadoop, noSQL, or data warehouse.
In some embodiments of the present application, the data preprocessing submodule is configured to perform missing value supplementation on the P-wave data and the historical collapse data and perform sequence alignment on different time-series data, where a method of the sequence alignment is a DTW algorithm, and a method of the missing value supplementation includes mean filling, mode filling, and nearest neighbor interpolation.
In some embodiments of the present application, the collapse cycle density calculation submodule configures a collapse cycle density calculation model to obtain a collapse time sequence according to the time data, performs first order difference and sequence on the collapse time sequence to obtain a collapse cycle sequence, calculates according to the collapse cycle sequence to obtain a collapse cycle density, and the calculation method of the collapse cycle density is as follows:
，
wherein ,representing collapse cycle density, ++>Representing the maximum value of the collapse cycle sequence,/->Representing collapse cycle sequence length, < >>Representing the first of the sequence of collapse cyclesiValue of individual element->The standard deviation of the collapse cycle sequence is shown.
In some embodiments of the present application, the collapse scale level density calculation submodule is configured with a collapse scale level density calculation model, to obtain a collapse scale level sequence according to the collapse scale level data, and calculate a collapse scale level density according to the collapse scale level sequence, where the method for calculating the collapse scale level density is as follows:
，
wherein ,represents collapse Scale Density, ++>Representing collapse Scale level sequence Length, +.>Representing the first of the collapse Scale level sequencesiValue of individual element->Representing the first of the collapse Scale level sequencesiValues of +1 elements, +.>Standard deviation of sequences representing collapse scale, +.>Representing the Hurst index calculated from the collapse scale level sequence.
In some embodiments of the present application, the collapse prediction coefficient calculation submodule is configured with a collapse prediction coefficient calculation model, and is configured to calculate and obtain a collapse prediction coefficient according to the collapse cycle density and the collapse scale level density, and the calculation method of the collapse prediction coefficient is as follows:
，
wherein ,representing the collapse predictability factor,/->Represents collapse Scale Density, ++>Representing the collapse cycle density.
In some embodiments of the present application, the smoothing factor calculation submodule is configured with a smoothing factor calculation model, and is configured to calculate and obtain a smoothing factor according to the collapse scale level data and the collapse predictability coefficient, where the calculating method of the smoothing factor is as follows:
，
wherein ,representing a smoothing factor->Indicating that the element in brackets is normalized using the Z_score method,/for>Represents the average collapse size level, +.>Representing the collapse predictability factor.
In some embodiments of the present application, the hierarchical early warning includes a first early warning, a second early warning, and a third early warning, wherein the third early warning is performed when the predicted collapse scale level is small and medium, the second early warning is performed when the predicted collapse scale level is large, and the first early warning is performed when the predicted collapse scale level is super-large and above.
As can be seen from the above embodiments, the geological disaster intelligent early warning system based on big data analysis provided by the embodiment of the application has the following beneficial effects:
according to the method, the collapse period density and the collapse scale level density are respectively constructed through analysis of the collapse period, the collapse predictive coefficient is constructed based on the collapse period density and the collapse scale level density, the collapse occurrence regularity is integrally reflected, the dependency degree of historical data and latest observed data when the collapse wave data are predicted by using an index moving average method is determined, the smoothing factor is calculated based on the combination of the average collapse scale level density and the collapse scale level density, the collapse characteristic is more consistent, and the prediction effect is more accurate when the collapse early warning is performed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a schematic diagram of basic components of an intelligent geological disaster early warning system based on big data analysis according to an embodiment of the present application.
Description of sequence number: the system comprises a 10-data acquisition and storage module, a 20-data processing module, a 30-prediction module, a 40-early warning module, a 21-data preprocessing sub-module, a 22-collapse period density computing sub-module, a 23-collapse scale level density computing sub-module, a 24-collapse predictable coefficient computing sub-module and a 25-smoothing factor computing sub-module.
Detailed Description
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without creative efforts, based on the embodiments of the present application are included in the protection scope of the present application.
The following describes in detail a geological disaster intelligent early warning system based on big data analysis provided in this embodiment with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of basic components of an intelligent geological disaster early warning system based on big data analysis according to an embodiment of the present application, and as shown in fig. 1, the system mainly includes: the system comprises a data acquisition and storage module 10, a data processing module 20, a prediction module 30 and an early warning module 40.
Specifically, the data acquisition and storage module 10 is configured to acquire and store P-wave data and historical collapse data.
P-wave data are acquired through a collapse monitor, historical collapse data are acquired from a national collapse science data center website, and the historical collapse data comprise time data of occurrence of historical collapse and collapse scale level data. And then the acquired data are stored in a large-scale distributed storage system, such as Hadoop, noSQL or a data warehouse, so that the intelligent algorithm and the model can be accessed and processed. Furthermore, the application can select to store the collected related data in the Hadoop distributed storage system.
The data processing module 20 is configured with a geological disaster early warning analysis model for accessing and processing P-wave data and historical collapse data, and comprises a data preprocessing sub-module 21, a collapse period density computing sub-module 22, a collapse scale level density computing sub-module 23, a collapse predictability coefficient computing sub-module 24 and a smoothing factor computing sub-module 25.
Further, the data preprocessing sub-module 21 is configured to supplement the missing values of the P-wave data and the historical collapse data and to sequence the different time series data.
The missing value supplementation is performed on the P-wave data and the historical collapse data, and because the obtained P-wave data and the historical collapse data possibly have abnormal conditions such as missing values, the missing value supplementation is required to be performed on the data, and common missing value supplementation methods comprise mean value supplementation, mode supplementation, nearest neighbor interpolation and the like. The nearest neighbor interpolation method is a known technology, and the application is not repeated.
The sequence alignment is performed on different time series data, because the collected P-wave data and the historical collapse data are derived from a plurality of data sources, the corresponding collection time of each data may be different, so that the time difference needs to be eliminated for facilitating the mutual comparison of the data, the model error is reduced, the accuracy of the model is improved, and the sequence alignment is performed on the different time series data. In the embodiment of the application, the time series data of different data sources are aligned in sequence by using a DTW algorithm to obtain aligned time series data, wherein the DTW algorithm is a known technology, and the specific process of the DTW algorithm is not repeated.
In the exponential moving average method, the size of the smoothing factor is one of the key parameters affecting the average calculation result. The larger the smoothing factor is, the larger the weight corresponding to the latest observed value is when calculating the average value, the quicker the response to the latest observed value is; the smaller the smoothing factor, the larger the weight corresponding to the historical data is, and the larger the influence of the historical data is, the slower the corresponding response to the latest observed value is, resulting in larger hysteresis of the average value. In the traditional exponential moving average method, the smoothing factor is usually determined according to the size of a selected time window, and the characteristic of occurrence of the collapse is required to be reflected by the smoothing factor due to the specificity of the collapse data and the harm caused by the collapse, so that the collapse data is predicted more accurately, and the collapse predictable coefficient is constructed based on the periodicity of the collapse, so that the smoothing factor with the characteristic of occurrence of the collapse is obtained. For convenience of description, the embodiment of the application takes the collapse disaster intelligent early warning system of the A land as an example for analysis.
The collapse predictability coefficient is calculated by calculating the collapse cycle density and the collapse scale level density of the land a. Based on the historical collapse data of the A land (comprising the collapse occurrence time and the grade number of the land collapse scale), the occurrence regularity of the collapse can be analyzed, the stronger the regularity is, the stronger the predictability is, the weaker the regularity is, the weaker the predictability is, and the collapse predictability coefficient can be constructed according to the data.
First, the collapse period density is calculated by the collapse period density calculation sub-module 22.
The collapse period density calculation sub-module 22 configures a collapse period density calculation model to obtain a collapse time sequence according to the time data, performs first order difference and arrangement on the collapse time sequence to obtain a collapse period sequence, and calculates according to the collapse period sequence to obtain the collapse period density.
The collapse cycle density calculation sub-module 22 configures a collapse cycle density calculation model, obtains a collapse time series by reading time data of the occurrence of the historical collapse of the A-land stored in the data acquisition and storage module 10, and then obtains the collapse time series based on the time data, performs first order difference on the collapse time series, and performs first order difference result according to the first order difference resultOrdering according to the order from small to large to obtain a collapse period sequenceThe element in the sequence is the historical occurrence time of the A-land collapse, and the collapse period density can be calculated according to the following calculation formula:
，
wherein ,representing collapse cycle density, ++>Representing the maximum value of the collapse cycle sequence,/->Representing collapse cycle sequence length, < >>The value representing the i-th element of the collapse cycle sequence,/->The standard deviation of the collapse cycle sequence is shown.
In the collapse period sequence, the smaller the difference between each element of the sequence and the maximum value is, the weaker the collapse period fluctuation is, and the larger the collapse period density is; the larger the difference between each element of the sequence and the maximum value, the stronger the fluctuation of the collapse period, the smaller the collapse period density. The larger the standard deviation of the collapse period sequence is, the larger the fluctuation degree of the collapse period is, and the smaller the collapse period density is; the smaller the standard deviation of the collapse cycle sequence, the smaller the fluctuation degree, and the larger the collapse cycle density.
Then, the collapse scale level density is calculated by the collapse scale level density calculating sub-module 23.
The collapse scale level density calculation sub-module 23 is configured with a collapse scale level density calculation model for obtaining a collapse scale level sequence from the collapse scale level data and obtaining a collapse scale level density from the collapse scale level sequence calculation.
The collapse scale level density calculation sub-module 23, configured with a collapse scale level density calculation model, can calculate the collapse scale level density by reading the collapse scale level data of the a-land history collapse occurrence stored in the data acquisition and storage module 10, and then arranging the collapse scale level data in order from small to large to obtain a collapse scale level sequence, the calculation formula of which is as follows:
，
wherein ,represents collapse Scale Density, ++>Representing collapse Scale level sequence Length, +.>Representing the first of the collapse Scale level sequencesiValue of individual element->Representing the first of the collapse Scale level sequencesiValues of +1 elements, +.>Standard deviation of sequences representing collapse scale, +.>Representing the Hurst index calculated from the collapse scale level sequence. The calculation of the Hurst index is a well-known technique, and the specific process is not repeated in the present application.
In the collapse scale level sequence, the larger the difference between elements in the sequence is, the larger the standard deviation is, which indicates that the collapse scale level is more dispersed, the closer the Hurst index is to 0, the stronger the random volatility of the collapse sequence is, and the smaller the corresponding collapse scale level density is; the smaller the difference between the elements in the sequence, the smaller the standard deviation, indicating that the collapse scale level is more dispersed, the closer the Hurst index is to 1, indicating that the longer-term trend of the collapse sequence is stronger, and the corresponding collapse scale level density is greater.
Thereafter, the collapse predictors are calculated by the collapse predictors calculation submodule 24.
The collapse prediction coefficient calculation sub-module 24 is configured with a collapse prediction coefficient calculation model for obtaining the collapse prediction coefficient from the collapse cycle density and the collapse scale level density calculation.
The collapse period density and the collapse scale level density have been obtained by the foregoing submodules, and the collapse predictability coefficient can be constructed by a collapse predictability coefficient calculation model according to the collapse period density and the collapse scale level density. The method for calculating the collapse predictability coefficient comprises the following steps:
，
wherein ,representing the collapse predictability factor,/->Represents collapse Scale Density, ++>Representing the collapse cycle density.
The greater the collapse cycle density, the more stable the collapse cycle, the more predictable the collapse cycle, and the greater the corresponding collapse predictability factor; the smaller the collapse cycle density, the less stable the collapse cycle, the less predictable the collapse cycle, and the smaller the corresponding collapse predictability factor. The greater the density of the collapse scale level, the more similar the historical collapse scale level is, the stronger the predictability of the collapse scale level is, and the greater the corresponding collapse predictability coefficient is; the smaller the collapse scale level density, the greater the difference in historical collapse scale levels, the weaker the predictability of the collapse scale levels, and the smaller the corresponding collapse predictability coefficient.
Finally, the smoothing factor is calculated by the smoothing factor calculation sub-module 25.
The smoothing factor calculation sub-module 25 is configured with a smoothing factor calculation model for calculating a smoothing factor based on the collapse scale level data and the collapse predictors.
The closer the time difference between the current time and the previous collapse is to the collapse period, the greater the possibility of the collapse of the current time is, and when the index moving average method is used for predicting the collapse data, the latest observation data should be sensitive, namely the corresponding smoothing factor should be larger; the longer the time difference between the current time and the previous collapse is from the period of the collapse, the smaller the possibility of the collapse of the current time is, and when the index moving average method is used for predicting the collapse data, the higher the dependency degree on the historical data is, namely the corresponding smoothing factor is smaller.
The smoothing factor calculation sub-module 25 calculates a smoothing factor based on the collapse predictability coefficient by:
，
wherein ,representing a smoothing factor->Indicating that the element in brackets is normalized using the Z_score method,/for>Represents the average collapse size level, +.>Representing the collapse predictability factor.
The larger the collapse predictability coefficient is, the more stable the collapse period is, the more effective the predictability of the collapse period is, and the smoothing factor calculated based on the collapse period is, at the moment, historical data is paid attention to, namely the dependency on the historical data is stronger, the dependency on the latest observed data is relatively weaker, so that the corresponding smoothing factor is smaller; the smaller the collapse predictability coefficient is, the less stable the collapse period is, the weaker the predictability of the collapse period is, the less effective the smoothing factor calculated based on the time difference is, and the more recent observed data, that is, the more dependence on the more recent observed data should be paid attention to, and the larger the corresponding smoothing factor is. The larger the average collapse scale level is, the more obvious the change of the collapse wave is, and the more attention should be paid to the latest observed data at the moment, and the larger the corresponding smoothing factor is; the smaller the average collapse scale level, the less obvious the change of the collapse wave, and the stronger the dependency on the historical data, the smaller the corresponding smoothing factor.
The prediction module 30 is configured to perform short-term prediction on the P-wave data by using an exponential moving average method according to the smoothing factor to obtain P-wave short-term prediction data, calculate a predicted collapse scale level according to the P-wave short-term prediction data by using a collapse scale level calculation formula, and send the predicted collapse scale level to the collapse disaster warning module 40.
Short-term predictions of collapse data were made using an exponential moving average method. The smoothing factor calculated by the smoothing factor calculation sub-module 25 uses an exponential moving average method to perform short-term prediction on the P-wave, i.e. predict P-wave data within 10 seconds in the future, so as to obtain P-wave short-term prediction data. The smoothing factor combines the collapse periodicity of the A land with the collapse scale level, so that the collapse data predicted by using the index moving average method more accords with the collapse characteristic of the A land, the accuracy of collapse prediction is improved, the propagation speed of the P wave in the ground surface is fastest, and the damage caused by the collapse can be avoided to a greater extent through the monitoring and prediction of the P wave.
And then obtaining a predicted collapse scale level according to the P-wave short-term prediction data by using a collapse scale level calculation formula, and sending the predicted collapse scale level to a collapse disaster early warning module 40, namely a collapse disaster early warning center of the site A.
The early warning module 40 is used for carrying out hierarchical early warning according to the level of the predicted collapse scale.
The collapse disaster early warning center carries out grading early warning of different degrees according to different prediction collapse scale levels transmitted in the system. The grading early warning comprises a first grade early warning, a second grade early warning and a third grade early warning. When the level of the collapse scale is small, medium and small, the collapse is not felt or is very weak, and the three-level early warning is carried out by informing through a mobile phone short message and other ways; when the collapse scale level is predicted to be large, signs such as furniture shaking, window ringing and the like can appear, but obvious damage cannot be caused, and secondary early warning is carried out through mobile phone short messages and various social platforms for notification; when the collapse scale is predicted to be extremely large or above, various disasters such as building damage, water source interruption, power failure short circuit, fire disaster and the like can occur, the collapse scale has high destructiveness, and the collapse scale is required to be notified through various platforms such as telephones, networks, speakers, mobile phone short messages, various social platforms and the like, primary early warning is carried out, the public is timely reminded to take corresponding emergency measures, and disasters caused by the collapse are reduced to the greatest extent.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
It should be noted that unless otherwise specified and limited, terms such as "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such article or apparatus. Without further limitation, the statement "comprises one … …" does not exclude that an additional identical element is present in an article or device that comprises the element. In addition, the term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (4)
1. Geological disaster intelligent early warning system based on big data analysis, characterized in that the system includes: the system comprises a data acquisition and storage module (10), a data processing module (20), a prediction module (30) and an early warning module (40); wherein:
the data acquisition and storage module (10) is used for acquiring and storing P-wave data and historical collapse data, wherein the historical collapse data comprises time data and collapse scale level data;
the data processing module (20) is configured with a geological disaster early warning analysis model, and is used for accessing and processing the P-wave data and the historical collapse data, and comprises a data preprocessing sub-module (21), a collapse period density computing sub-module (22), a collapse scale level density computing sub-module (23), a collapse predictable coefficient computing sub-module (24) and a smoothing factor computing sub-module (25);
the prediction module (30) is configured to perform short-term prediction on the P-wave data by using an exponential moving average method according to a smoothing factor to obtain P-wave short-term prediction data, then calculate according to a collapse scale level calculation formula according to the P-wave short-term prediction data to obtain a predicted collapse scale level, and send the predicted collapse scale level to the collapse disaster early warning module (40);
the early warning module (40) is used for carrying out grading early warning according to the predicted collapse scale level;
the collapse period density calculation sub-module (22) is configured with a collapse period density calculation model, and is used for obtaining a collapse time sequence according to the time data, performing first-order difference and side-order on the collapse time sequence to obtain a collapse period sequence, and calculating according to the collapse period sequence to obtain the collapse period density, wherein the calculation method of the collapse period density comprises the following steps:
，
wherein ,representing collapse cycle density, ++>Representing the maximum value of the collapse cycle sequence,/->Representing collapse cycle sequence length, < >>Representing the first of the sequence of collapse cyclesiValue of individual element->Standard deviation representing collapse cycle sequence;
the collapse scale level density calculation sub-module (23) is configured with a collapse scale level density calculation model, and is used for obtaining a collapse scale level sequence according to the collapse scale level data, and obtaining the collapse scale level density according to the collapse scale level sequence calculation, wherein the calculation method of the collapse scale level density comprises the following steps:
，
wherein ,represents collapse Scale Density, ++>Representing collapse Scale level sequence Length, +.>Representing the first of the collapse Scale level sequencesiValue of individual element->Representing the first of the collapse Scale level sequencesiValues of +1 elements, +.>Standard deviation of sequences representing collapse scale, +.>Representing the Hurst index calculated from the collapse scale level sequence;
the collapse prediction coefficient calculation sub-module (24) is configured with a collapse prediction coefficient calculation model for calculating and obtaining a collapse prediction coefficient according to the collapse cycle density and the collapse scale level density, and the calculation method of the collapse prediction coefficient is as follows:
，
wherein ,representing the collapse predictability factor,/->Represents collapse Scale Density, ++>Representing collapse cycle density;
the smoothing factor calculation sub-module (25) is configured with a smoothing factor calculation model, and is used for calculating and obtaining a smoothing factor according to the collapse scale level data and the collapse predictability coefficient, and the calculating method of the smoothing factor is as follows:
，
wherein ,representing a smoothing factor->Indicating that the element in brackets is normalized using the Z_score method,/for>Represents the average collapse size level, +.>Representing the collapse predictability factor.
2. The big data analysis based geological disaster intelligent early warning system of claim 1, wherein the P-wave data and the historical collapse data are stored in a large-scale distributed storage system comprising Hadoop, noSQL or data warehouse.
3. The geological disaster intelligent early warning system based on big data analysis according to claim 1, wherein the data preprocessing sub-module (21) is used for carrying out missing value supplementation on the P-wave data and the historical collapse data and carrying out sequence alignment on different time sequence data, the sequence alignment method is a DTW algorithm, and the missing value supplementation method comprises mean value filling, mode filling and nearest neighbor interpolation.
4. The intelligent geological disaster warning system based on big data analysis according to claim 1, wherein the hierarchical warning comprises a first level warning, a second level warning and a third level warning, wherein the third level warning is performed when the predicted collapse scale level is a medium or small size, the second level warning is performed when the predicted collapse scale level is a large size, and the first level warning is performed when the predicted collapse scale level is an extra large size or more.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310944285.3A CN116663752B (en) | 2023-07-31 | 2023-07-31 | Geological disaster intelligent early warning system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310944285.3A CN116663752B (en) | 2023-07-31 | 2023-07-31 | Geological disaster intelligent early warning system based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116663752A CN116663752A (en) | 2023-08-29 |
| CN116663752B true CN116663752B (en) | 2023-10-10 |
Family
ID=87710095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310944285.3A Active CN116663752B (en) | 2023-07-31 | 2023-07-31 | Geological disaster intelligent early warning system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116663752B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7251589B1 (en) * | 2005-05-09 | 2007-07-31 | Sas Institute Inc. | Computer-implemented system and method for generating forecasts |
| WO2012161606A1 (en) * | 2011-05-20 | 2012-11-29 | Атокс Канада Инкорпорэйтид | Method for predicting a seismic event |
| CN105741498A (en) * | 2016-04-28 | 2016-07-06 | 成都理工大学 | Method and device for monitoring and performing early warning on geological hazards |
| JP2018054348A (en) * | 2016-09-27 | 2018-04-05 | 富士防災警備株式会社 | Earthquake forecasting method and earthquake forecasting system |
| CN111445670A (en) * | 2020-03-16 | 2020-07-24 | 深圳市城市公共安全技术研究院有限公司 | Geological disaster early warning system and method |
| CN113869710A (en) * | 2021-09-26 | 2021-12-31 | 华北电力大学 | Extreme precipitation trend analysis method based on large-scale climate anomaly |
| CN114548479A (en) * | 2021-12-17 | 2022-05-27 | 杭州安脉盛智能技术有限公司 | Time sequence data prediction method based on exponential smoothing |
| KR20220134421A (en) * | 2021-03-26 | 2022-10-05 | 한국과학기술정보연구원 | Method for predicting earthquake damage in buildings based on artificial intelligence and apparatus implementing the same method |
| CN115391736A (en) * | 2022-06-28 | 2022-11-25 | 中国地震局地震预测研究所 | Ten-year-scale major fault strong earthquake occurrence probability prediction method |
| CN116182952A (en) * | 2023-03-06 | 2023-05-30 | 江苏融智绘地理信息科技有限公司 | Intelligent acquisition method for geological disaster investigation information |
| CN116485269A (en) * | 2023-04-28 | 2023-07-25 | 交通运输部公路科学研究所 | Method, system, device and medium for evaluating seismic disaster toughness of grade highway section |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018039142A1 (en) * | 2016-08-22 | 2018-03-01 | Rapidsos, Inc. | Predictive analytics for emergency detection and response management |
-
2023
- 2023-07-31 CN CN202310944285.3A patent/CN116663752B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7251589B1 (en) * | 2005-05-09 | 2007-07-31 | Sas Institute Inc. | Computer-implemented system and method for generating forecasts |
| WO2012161606A1 (en) * | 2011-05-20 | 2012-11-29 | Атокс Канада Инкорпорэйтид | Method for predicting a seismic event |
| CN105741498A (en) * | 2016-04-28 | 2016-07-06 | 成都理工大学 | Method and device for monitoring and performing early warning on geological hazards |
| JP2018054348A (en) * | 2016-09-27 | 2018-04-05 | 富士防災警備株式会社 | Earthquake forecasting method and earthquake forecasting system |
| CN111445670A (en) * | 2020-03-16 | 2020-07-24 | 深圳市城市公共安全技术研究院有限公司 | Geological disaster early warning system and method |
| KR20220134421A (en) * | 2021-03-26 | 2022-10-05 | 한국과학기술정보연구원 | Method for predicting earthquake damage in buildings based on artificial intelligence and apparatus implementing the same method |
| CN113869710A (en) * | 2021-09-26 | 2021-12-31 | 华北电力大学 | Extreme precipitation trend analysis method based on large-scale climate anomaly |
| CN114548479A (en) * | 2021-12-17 | 2022-05-27 | 杭州安脉盛智能技术有限公司 | Time sequence data prediction method based on exponential smoothing |
| CN115391736A (en) * | 2022-06-28 | 2022-11-25 | 中国地震局地震预测研究所 | Ten-year-scale major fault strong earthquake occurrence probability prediction method |
| CN116182952A (en) * | 2023-03-06 | 2023-05-30 | 江苏融智绘地理信息科技有限公司 | Intelligent acquisition method for geological disaster investigation information |
| CN116485269A (en) * | 2023-04-28 | 2023-07-25 | 交通运输部公路科学研究所 | Method, system, device and medium for evaluating seismic disaster toughness of grade highway section |
Non-Patent Citations (2)
| Title |
|---|
| Marios Filippoupolitis，Carl Hopkins.Experimental Validation of Finite Element Models for Reinforced Concrete Beams with Discontinuities That Form Dowel-Type Joints.vibration.2021,第4卷(第32期),537-550. * |
| 胡华 ; 谢金华 ; .以速率为参量的GM(1,1)滑坡时间预报模型研究.长江科学院院报.2018,(第10期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116663752A (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ezzat et al. | Spatio-temporal short-term wind forecast: A calibrated regime-switching method | |
| CN110348472B (en) | Data detection rule generation method, device, computer equipment and storage medium | |
| CN110570030A (en) | Wind power cluster power interval prediction method and system based on deep learning | |
| CN114091683A (en) | Submarine cable state monitoring method and device, computer equipment and storage medium | |
| CN114330934A (en) | Model parameter self-adaptive GRU new energy short-term power generation power prediction method | |
| CN114323153B (en) | Offshore wind power foundation scouring and structural state monitoring and safety early warning method and device | |
| CN109449923A (en) | A kind of the quantitative analysis method and Related product of active distribution system operational flexibility | |
| CN117117819A (en) | Photovoltaic power generation short-term power prediction method, system, equipment and medium | |
| CN116663752B (en) | Geological disaster intelligent early warning system based on big data analysis | |
| CN114138601A (en) | Service alarm method, device, equipment and storage medium | |
| CN116663747B (en) | Intelligent early warning method and system based on data center infrastructure | |
| CN116235125A (en) | Detecting and managing anomalies in subsurface sensors for agricultural applications | |
| Safari et al. | Tidal current and level uncertainty prediction via adaptive linear programming | |
| CN116316617B (en) | Multi-station intelligent fusion new energy generation power region prediction method and system | |
| CN116311829A (en) | Remote alarm method and device for data machine room | |
| CN116485237A (en) | Method, system, equipment and medium for evaluating asset value of power regulation and control data | |
| Tellier et al. | Predicting drowning from sea and weather forecasts: development and validation of a model on surf beaches of southwestern France | |
| CN115689067A (en) | Solar irradiance prediction method, device and storage medium | |
| CN114462710A (en) | Short-term prediction method, device and medium for fan generated power | |
| CN115577903A (en) | Method, device, equipment and medium for evaluating influence of new energy on power grid peak regulation | |
| CN114743703A (en) | Reliability analysis method, device, equipment and storage medium for nuclear power station unit | |
| Karvelis et al. | Short Time Wind Forecasting with Uncertainty | |
| Patanè et al. | Model transferability for wave height prediction | |
| CN116978191B (en) | Ocean disaster prediction and early warning method and system | |
| Wang et al. | Water level prediction based on improved WMCP-ARIMA model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |