CN116434478B - Intelligent early warning response method, device and system for geological disasters - Google Patents
Intelligent early warning response method, device and system for geological disasters Download PDFInfo
- Publication number
- CN116434478B CN116434478B CN202211724903.5A CN202211724903A CN116434478B CN 116434478 B CN116434478 B CN 116434478B CN 202211724903 A CN202211724903 A CN 202211724903A CN 116434478 B CN116434478 B CN 116434478B
- Authority
- CN
- China
- Prior art keywords
- disaster
- early warning
- data
- quality
- equipment
- 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
- 230000004044 response Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 67
- 238000005070 sampling Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 12
- 238000013441 quality evaluation Methods 0.000 claims description 11
- 238000013523 data management Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 230000002265 prevention Effects 0.000 abstract description 12
- 230000002159 abnormal effect Effects 0.000 description 7
- 239000008186 active pharmaceutical agent Substances 0.000 description 7
- 238000012806 monitoring device Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000035882 stress Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000036962 time dependent Effects 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
Abstract
The application relates to the technical field of geological monitoring, in particular to an intelligent early warning response method for geological disasters. The method comprises the following steps: receiving disaster sensing data; inputting the disaster sensing data into a disaster quality scoring model to obtain a data credibility score, wherein the data credibility score is calculated based on equipment state, data quality and weight score of early warning error report; when the data credibility score meets the preset credibility, the disaster sensing data is input into a disaster grade pre-judging model to obtain an early warning grade; and performing early warning response based on the disaster processing mode corresponding to the early warning level matching. The application can accurately and timely perform early warning response to disasters so as to ensure the smooth progress of disaster prevention work.
Description
Technical Field
The application relates to the technical field of geological monitoring, in particular to an intelligent early warning response method, device and system for geological disasters.
Background
Geological disasters such as collapse, landslide, mud-rock flow and the like bring great harm to life and property safety of people. In order to reduce the threat and damage caused by geological disasters to life of people, geological disaster monitoring and early warning technologies are also continuously developed, and monitoring equipment and devices for the geological disasters play an important role in the geological disaster monitoring and early warning process.
At present, in order to know the situation of a disaster area and timely perform early warning of abnormal situations, monitoring is performed on a monitoring platform in real time, once the abnormality is found, the early warning mode to be adopted is immediately pre-judged, for example, the contact mode of the corresponding local unit is found, the local unit is informed to perform inspection of the abnormal situation, the field investigation is performed by the searching expert, and the like, the local unit is further used for recording the regional inspection result based on the searching personnel corresponding to the advice, the field investigation is performed by the searching expert, and the like, and the local unit is reported to the monitoring personnel after the disaster situation is determined.
Disclosure of Invention
In order to accurately and timely perform early warning response on disasters and ensure smooth progress of disaster prevention work, the application provides an intelligent early warning response method and system for geological disasters.
The embodiment of the application provides an intelligent early warning response method for geological disasters, which adopts the following technical scheme:
an intelligent early warning response method for geological disasters comprises the following steps: receiving disaster sensing data; inputting the disaster sensing data into a disaster quality scoring model to obtain a data credibility score, wherein the data credibility score is calculated based on equipment state, data quality and weight score of early warning error report; when the data credibility score meets the preset credibility, the disaster sensing data is input into a disaster grade pre-judging model to obtain an early warning grade; and performing early warning response based on the disaster processing mode corresponding to the early warning level matching.
Through adopting above-mentioned technical scheme, through the credibility grade that will receive disaster sensing data input to the model of disaster quality grade, can obtain the credibility grade of data, whether with judging the data credibility, and then can avoid the false alarm of disaster, when the credibility grade of data satisfies the preset credibility, namely when not reporting by mistake, through the input of disaster sensing data to the model of disaster grade prejudgement, can obtain more accurate early warning grade, the rethread early warning grade matches the disaster handling mode that corresponds, can be accurate timely carry out early warning response to the disaster, in order to ensure the smooth progress of disaster prevention work.
Optionally, before the receiving disaster sensing data, the method further includes: acquiring a disaster quality scoring training data set, wherein the disaster quality scoring training data set comprises a plurality of groups of disaster quality evaluation data, and one group of disaster quality evaluation data comprises equipment on-line state, equipment on-line rate, equipment type, data integrity, data coarse-difference duty ratio, sampling interval time, timeliness and false report times; and training an initial disaster quality scoring model by using the disaster quality scoring training data set to obtain the disaster quality scoring model.
By adopting the technical scheme, the disaster quality scoring model for obtaining the data credibility score based on the disaster sensing data can be trained by acquiring the disaster quality scoring training data set, so that false alarm of disasters is avoided.
Optionally, before the receiving disaster sensing data, the method further includes: acquiring a disaster grade training data set, wherein the disaster grade training data set comprises a plurality of groups of early warning grade sensing data, and one group of early warning grade sensing data comprises a sensing data set, a sensing data threshold data set and early warning grades corresponding to the sensing data set; and training an initial disaster grade pre-judging model by using the disaster grade training data set to obtain the disaster grade pre-judging model.
By adopting the technical scheme, the disaster grade pre-judging model capable of carrying out early warning grade division based on disaster sensing data can be trained by acquiring the disaster grade training data set.
Optionally, the data reliability score is calculated by 25% equipment state weight score, 55% data quality weight score and 20% early warning false alarm weight score.
By adopting the technical scheme, more accurate data reliability scores can be obtained through the equipment state weights, the data quality weights and the early warning false alarm weights based on different duty ratios.
Optionally, 25% of the device state weight scores include a 15% device presence weight score and a 10% device type weight score; the equipment is characterized in that the equipment online rate is the proportion of the uploading times of the actual data of the equipment in the statistical period, and the equipment types comprise deformation monitoring equipment, stress monitoring equipment, water level monitoring equipment, temperature monitoring equipment and vibration monitoring equipment.
By adopting the technical scheme, more accurate equipment state weight can be obtained through equipment linear rate weight and equipment type weight based on different duty ratios.
Optionally, 55% of the data quality weight includes a data integrity weight, a 15% coarse fraction weight, a 20% sampling interval weight, and a 20% timeliness weight.
By adopting the technical scheme, more accurate data quality weight can be obtained through the data integrity weight, the coarse difference duty ratio weight, the sampling interval weight and the timeliness weight of different duty ratios.
In a second aspect, another embodiment of the present application provides an intelligent early warning response device for geological disasters, which adopts the following technical scheme:
an intelligent early warning response device for geological disasters, which is implemented in the intelligent early warning response method for geological disasters described in the above embodiment, includes: the disaster sensing data receiving module is used for receiving the disaster sensing data; the grading acquisition module is used for inputting the disaster sensing data into a disaster quality grading model to obtain a data credibility grading, and the data credibility grading is calculated based on equipment state, data quality and weight grading of early warning false alarm; the early warning grade acquisition module is used for inputting the disaster sensing data into a disaster grade pre-judging model to obtain an early warning grade when the data credibility score meets the preset credibility; and the early warning response module is used for carrying out early warning response based on the disaster processing mode corresponding to the early warning grade matching.
Through adopting above-mentioned technical scheme, can receive the calamity sensing data through calamity sensing data receiving module, through the calamity sensing data input that obtains the module in the calamity quality grading model, can obtain the credibility grade of data, whether it is credible to judge data, and then can avoid the false alarm of calamity, when the credibility grade of data satisfies the default credibility promptly and is not the false alarm, through the early warning grade obtaining module with calamity sensing data input to calamity grade prejudgement model, can obtain more accurate early warning grade, the rethread early warning response module carries out early warning response to the calamity based on the calamity handling mode that the early warning grade matches corresponds, in order to ensure the smooth progress of disaster prevention work.
Optionally, an intelligent early warning response device of geological disasters still includes: the system comprises a first training data set acquisition module, a second training data set acquisition module and a first data set analysis module, wherein the first training data set acquisition module is used for acquiring a disaster quality grading training data set, the disaster quality grading training data set comprises a plurality of groups of disaster quality evaluation data, and one group of disaster quality evaluation data comprises equipment on-line state, equipment on-line rate, equipment type, data integrity, data coarse difference duty ratio, sampling interval time, timeliness and false report times; and the scoring model acquisition module is used for training an initial disaster quality scoring model by using the disaster quality scoring training data set to obtain the disaster quality scoring model.
Through adopting above-mentioned technical scheme, can acquire disaster quality score training dataset through first training dataset acquisition module, can train initial disaster quality score model through training score model acquisition module use disaster quality score training dataset, obtain disaster quality score model.
In a third aspect, another embodiment of the present application provides an intelligent early warning response system for geological disasters, which adopts the following technical scheme:
an intelligent early warning response system for geological disasters, configured to execute the intelligent early warning response method for geological disasters described in the foregoing embodiments, includes: an intelligent early warning platform; a communication network; and the monitoring equipment is in network communication with the intelligent early warning platform through the communication network.
By adopting the technical scheme, the monitoring equipment can carry out network communication with the intelligent early warning platform through the communication network so as to transmit the monitored data to the intelligent early warning platform, so that the intelligent early warning platform can analyze and process the data in time, and can rapidly carry out early warning response on disasters so as to ensure the smooth progress of disaster prevention work.
Optionally, the intelligent early warning platform comprises an image acquisition module, a data management module, an early warning module, a patrol module and a survey evaluation module.
By adopting the technical scheme, the image acquisition of the monitoring site can be realized through the image acquisition module; the data management module can realize collection, management, analysis, output and the like of the monitoring data; the disaster can be subjected to early warning management, expert matching, emergency resource matching, early warning grade classification and the like by arranging the early warning module so as to remind relevant local units of timely preventing the disaster, and further ensure the smooth progress of disaster prevention work; the patrol module can realize the release of patrol tasks, record patrol records and the like; the hidden danger can be investigated, verified, hidden danger points can be managed and the like through the investigation evaluation module, and then the disaster can be accurately and timely subjected to early warning response through the intelligent early warning platform, so that the smooth progress of disaster prevention work is ensured.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the received disaster sensing data is input into the disaster quality scoring model, so that the reliability score of the data can be obtained to judge whether the data is reliable or not, and further false alarm of disasters can be avoided.
2. The disaster quality scoring model for obtaining the data credibility score based on the disaster sensing data can be trained by acquiring the disaster quality scoring training data set, so that false alarm of disasters is avoided.
3. The disaster grade pre-judging model capable of carrying out early warning grade division based on disaster sensing data can be trained by acquiring a disaster grade training data set.
4. More accurate data reliability scores can be obtained through device state weights, data quality weights and early warning false alarm weights based on different duty ratios.
Drawings
FIG. 1 is a schematic flow chart of an intelligent early warning response method for geological disasters according to an embodiment of the application;
FIG. 2 is a schematic flow chart of an intelligent early warning response method for geological disasters according to another embodiment of the present application;
FIG. 3 is a schematic flow chart of an intelligent early warning response method for geological disasters according to another embodiment of the present application;
FIG. 4 is a schematic block diagram of an intelligent early warning response device for geological disasters according to another embodiment of the present application;
FIG. 5 is a schematic structural diagram of an intelligent early warning response system for geological disasters according to another embodiment of the present application;
fig. 6 is a schematic diagram of functional modules of the intelligent early warning platform shown in fig. 5.
Reference numerals illustrate:
210. a disaster sensing data receiving module; 220. a score acquisition module; 230. the early warning grade acquisition module; 240. an early warning response module; 310. an intelligent early warning platform; 311. an image acquisition module; 312. a data management module; 313. an early warning module; 314. a patrol module; 315. a survey evaluation module; 320. a communication network; 330. monitoring equipment.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are illustrated in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," and the like may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the related art, in the aspect of disaster response, monitoring personnel and local unit personnel are complicated in work, and false alarm conditions are unavoidable, so that accurate and timely early warning response cannot be carried out on the disaster, smooth progress of disaster prevention work is not facilitated, and therefore improvement is needed.
Therefore, in order to solve the technical problems, the application discloses an intelligent early warning response method for geological disasters, which can accurately and timely perform early warning response on the disasters so as to ensure the smooth progress of disaster prevention work.
Referring to fig. 1, an embodiment of the application discloses an intelligent early warning response method for geological disasters, which comprises the following steps: s10, receiving disaster sensing data;
one end for receiving disaster sensing data is a monitoring end, and the data monitoring function can be realized by related software installed on a computer end. The disaster sensing data may be sensed and collected by a monitoring device disposed at a collection site, and the disaster sensing data collected thereof may include: the slope angle, rainfall, object acceleration, ground water level, temperature and humidity, etc., of course, are not limited herein, and the relevant technicians may set corresponding sensors for sensing based on actual requirements.
S20, inputting disaster sensing data into a disaster quality scoring model to obtain a data credibility score;
the data reliability score is calculated based on the weight score of the equipment state D, the data quality Q and the early warning false alarm W. The disaster quality scoring model takes the equipment state D, the data quality Q and the early warning false alarm W as parameter conditions to form a certain algorithm rule, and after the disaster sensing data is input, the data reliability score can be input, so that whether the disaster is false alarm or not is judged through the reliability score, the authenticity of the data is ensured, and the possibility of false alarm is reduced.
Specifically, the device state D may include a device presence status DS (whether the device is online), a presence rate DR, a device type DT. The data quality Q may include an integrity QC, a coarse fraction QR, a sampling interval QI, and an aging QT, where the data uploaded by the integrity QC should include key fields such as a key acquisition data item, an acquisition time, etc., in this embodiment, 1 may be taken when the data uploaded is output to be complete, and 0 may be taken when the data uploaded is incomplete; the coarse difference occupancy ratio QR refers to the number of coarse differences/the total number of monitoring data which are removed by the Laida criterion, and the coarse differences refer to errors with absolute values larger than 3 sigma; the sampling interval QI refers to the time interval of two adjacent times of data receiving, and based on different devices, the time interval can be adjusted manually according to the performance of the devices; time-dependent QT is the time difference between the data entry time and the data acquisition time. The early warning false alarm W is the false alarm times WN, and the judgment record is carried out by the early warning feedback result. In this embodiment, the data reliability score uses the online state DS of the device and the integrity QC of the data quality as control conditions, and the rest are quantization indexes, and the algorithm formula in the disaster quality score model can be as follows: ω=k DS ×K QC ×(K DR +K DT +K QR +K QI +K QT +K WN )。
Omega denotes the data confidence score, K denotes the index score value, e.g. K DS Representing presence scoring, K when a device is on-line DS 1 is shown in the specification; when the device is not on-line, K DS Is 0.K (K) QC Indicating whether the uploaded data is complete, and when the data is complete, K QC 1 is shown in the specification; when the data uploading is incomplete, K QC Is 0.K (K) DR Representing the rating score, wherein the rating score is 0.15 when the rating DR is more than or equal to 90%; when DR is 80-DR<At 90, a score of 0.15 was 0.1; when DR is 70-or-less<80, score0.15 to 0.05; when DR is<At 70, the score was 0.15 to 0.K (K) DT Indicating equipment type score, 0.1 score when deformation monitoring in the detection equipment is abnormal, 0.08 score when stress monitoring equipment in the detection equipment is abnormal, 0.1 score when water level monitoring equipment in the detection equipment is abnormal, 0.1 score when temperature monitoring equipment in the detection equipment is abnormal, 0.08 score when vibration monitoring equipment in the detection equipment is abnormal, etc., in this embodiment, K DS 、K QC 、K DR 、K DT And not limited in sequence, with respect to K QR 、K QI 、K QT 、K WN The scoring rules of (2) are not described in detail herein, and can be set by a related technician.
The larger the value of omega is in the range of [0,1], the more reliable the device performance is. Omega is rated as the best in the quality of the equipment at [0.9,1 ]; omega the quality of the device rated good at [0.8,0.9 ]; and omega is qualified in the quality assessment of the equipment at the step 0.6,0.8, and if omega is less than 0.6, the data is judged to be false positive.
S30, inputting disaster sensing data into a disaster grade pre-judging model to obtain an early warning grade when the data credibility score meets the preset credibility;
the preset credibility can be set to be larger than 0.6, and when the data credibility score meets the preset credibility, false alarm can be eliminated. The warning level may include a warning level, an attention level, a warning level, and an alarm level that are sequentially raised, and of course, may be indicated as green, blue, orange, and red, respectively.
And S40, performing early warning response based on disaster processing modes corresponding to the early warning level matching.
Based on the example, the disaster treatment mode corresponding to the attention level reminds surrounding masses to be far away from the disaster place for the local unit; the disaster treatment mode corresponding to the warning level is that the patrol personnel of the local unit carry out multi-time patrol on the site, and warn the masses to be far away from the disaster site; the disaster treatment mode corresponding to the warning level is that local unit personnel pull up a warning line, and expert personnel conduct on-site investigation to conduct research and judge whether safety is achieved; the disaster treatment mode corresponding to the alarm level is used for informing the attribution, the construction department, the monitoring personnel of the property and taking corresponding emergency measures for the local unit.
Referring to fig. 2, in another embodiment, before step S10, a process of establishing a disaster quality scoring model is further included, and the specific steps thereof may be as follows:
s01, acquiring a disaster quality scoring training data set, wherein the disaster quality scoring training data set comprises a plurality of groups of disaster quality scoring data; the disaster quality evaluation data comprise equipment online state (same as online state DS), equipment online rate (same as online rate DR), equipment type (same as online rate DT), data integrity (same as online integrity QC), data gross error duty ratio (same as online rate QR), sampling interval time (same as online rate QI), timeliness (same as online rate QT) and false alarm times (same as online rate WN).
S02, training an initial disaster quality scoring model by using a disaster quality scoring training data set to obtain a disaster quality scoring model.
Referring to fig. 3, in another embodiment, before step S10, a process of establishing a disaster level pre-judging model is further included, and the specific steps thereof may be as follows:
s03, acquiring a disaster grade training data set;
the disaster grade training data set comprises a plurality of groups of early warning grade sensing data, wherein one group of early warning grade sensing data comprises a sensing data set, a sensing data threshold data set and early warning grades corresponding to the sensing data set.
Specifically, one group of early warning level sensing data is data of the same acquisition place, and of course, each acquisition place can be a plurality of groups of early warning level sensing data, and each piece of training data can be generated by a professional based on a sensing data threshold data set corresponding to the early warning level sensing data and combined with the on-site real situation, and the early warning level is obtained.
S04, training the initial disaster grade pre-judging model by using the disaster grade training data set to obtain the disaster grade pre-judging model.
In another embodiment, in step S20, the data reliability score may be calculated from 25% device status weight score, 55% data quality weight score, and 20% pre-warning false alarm weight score.
Wherein, 20% of the pre-warning false alarm weight is divided into 20% of pre-warning false alarm times. In this embodiment, based on different duty ratios of the device status weight score, the data quality weight score, and the early warning false alarm weight score, a more accurate data reliability score may be obtained to accurately determine whether the disaster is a false alarm condition.
In another embodiment, the 25% device status weight score may include a 15% device presence weight score and a 10% device type weight score;
the device online rate is the proportion of the number of times that the actual data of the device should be uploaded in the statistical period, for example, the total device is 100, the number of times that the actual data of the device is uploaded is 78, and the device online rate is 78%. The device types may include deformation monitoring devices, stress monitoring devices, water level monitoring devices, temperature monitoring devices, vibration monitoring devices, etc., wherein the five monitoring devices may be understood as common sensor devices in the related art, and of course, in the present embodiment, other sensor devices may be added based on the actual situation of the monitoring site, without limitation.
In another embodiment, the 55% data quality weight portion includes a data integrity weight portion, a 15% coarse fraction weight portion, a 20% sampling interval weight portion, and a 20% aging weight portion.
The data integrity weight is divided into 1 or 0, when the data is complete, the weight is divided into 1, and when the data is incomplete, the weight is divided into 0; in this embodiment, a more accurate data quality weight score may be obtained by the data integrity weight score and the coarse difference duty cycle weight score, the sampling interval weight score, the timeliness weight score of different duty cycles.
The application further discloses an intelligent early warning response device for geological disasters, which is used for executing the intelligent early warning response method for geological disasters described in the above embodiment, and referring to fig. 4, the intelligent early warning response device for geological disasters comprises a disaster sensing data receiving module 210, a scoring acquisition module 220, an early warning grade acquisition module 230 and an early warning response module 240; the disaster sensing data receiving module 210 is configured to receive disaster sensing data; the score obtaining module 220 is configured to input the disaster sensing data into a disaster quality score model to obtain a data reliability score, where the data reliability score is calculated based on a device state, a data quality and a weight score of early warning false alarm; the early warning level obtaining module 230 is configured to input the disaster sensing data into a disaster level pre-judging model to obtain an early warning level when the data reliability score meets a preset reliability; and the early warning response module 240 is configured to perform early warning response based on the disaster processing mode corresponding to the early warning level matching.
Further, the intelligent early warning response device for the geological disaster further comprises a first training data set acquisition module and a first training model;
the system comprises a first training data set acquisition module, a second training data set acquisition module and a first analysis module, wherein the first training data set acquisition module is used for acquiring a disaster quality grading training data set, the disaster quality grading training data set comprises a plurality of groups of disaster quality evaluation data, and one group of disaster quality evaluation data comprises equipment on-line state, equipment on-line rate, equipment type, data integrity, data coarse-difference duty ratio, sampling interval time, timeliness and false report times; and the first training model is used for training the initial disaster quality scoring model by using the disaster quality scoring training data set to obtain the disaster quality scoring model.
Further, the intelligent early warning response device for the geological disaster further comprises a second training data set acquisition module and a second training model;
the system comprises a first training data set acquisition module, a second training data set acquisition module and a control module, wherein the first training data set acquisition module is used for acquiring a disaster grade training data set, the disaster grade training data set comprises a plurality of groups of early warning grade sensing data, and one group of early warning grade sensing data comprises a sensing data set, a sensing data threshold data set and early warning grades corresponding to the sensing data set; and the second training model is used for training the initial disaster grade pre-judging model by using the disaster grade training data set to obtain the disaster grade pre-judging model.
Further, the data reliability score is calculated by 25% equipment state weight score, 55% data quality weight score and 20% early warning false alarm weight score.
Wherein 25% of the device state weight scores comprise a 15% device online rate weight score and a 10% device type weight score; the equipment is characterized in that the equipment online rate is the proportion of the uploading times of the actual data of the equipment in the statistical period, and the equipment types comprise deformation monitoring equipment, stress monitoring equipment, water level monitoring equipment, temperature monitoring equipment and vibration monitoring equipment.
55% of the data quality weight includes a data integrity weight, a 15% coarse fraction weight, a 20% sampling interval weight, and a 20% timeliness weight.
The method for intelligent early warning response of geological disaster realized by the intelligent early warning response device for geological disaster disclosed in this embodiment is similar to the above embodiment, and therefore will not be described in detail here. Alternatively, each module in the present embodiment and the other operations or functions described above are respectively for realizing the method in the foregoing embodiment.
In another embodiment of the present application, an intelligent early warning response system for geological disasters is disclosed, referring to fig. 5, the system includes: the intelligent early warning platform 310, the communication network 320 and the monitoring equipment 330, the monitoring equipment 330 performs network communication with the intelligent early warning platform 310 through the communication network 320, and monitored data can be transmitted to the intelligent early warning platform 310 for the intelligent early warning platform 310 to collect, interact and monitor and manage in real time, so as to rapidly perform early warning response on disasters, and ensure smooth progress of disaster prevention work.
Further, the intelligent pre-warning platform 310 may include an image acquisition module 311, a data management module 312, a pre-warning module 313, a patrol module 314, and a survey evaluation module 315.
The image acquisition module can be used for acquiring images of the monitoring places, and the monitoring places are not limited to pictures and videos; the data management module can realize collection, management, analysis, output and the like of the monitoring data; the disaster can be warned and managed, expert matched, emergency resource matched, warning grade classified and the like through the arrangement of the warning module, so that related local units are reminded to timely prevent the disaster, further smooth progress of disaster prevention work is ensured, wherein expert matching can be understood as the fact that an expert data database is built in advance, the disaster position and the warning grade can be set and matched, and emergency resource matching can be set and matched based on the disaster warning grade and the disaster position.
The patrol module can realize the release of patrol tasks, record patrol records and the like; the hidden danger can be investigated, verified, hidden danger points can be managed and the like through the investigation evaluation module, and then the disaster can be accurately and timely subjected to early warning response through the intelligent early warning platform, so that the smooth progress of disaster prevention work is ensured. Of course, in this embodiment, the functional module of the intelligent early warning platform is not limited.
The foregoing description of embodiments of the application has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (8)
1. An intelligent early warning response method for geological disasters is characterized by comprising the following steps:
acquiring a disaster quality scoring training data set, wherein the disaster quality scoring training data set comprises a plurality of groups of disaster quality evaluation data, and one group of disaster quality evaluation data comprises equipment on-line state, equipment on-line rate, equipment type, data integrity, data coarse-difference duty ratio, sampling interval time, timeliness and false report times;
training an initial disaster quality scoring model by using the disaster quality scoring training data set to obtain the disaster quality scoring model; receiving disaster sensing data;
inputting the disaster sensing data into a disaster quality scoring model to obtain a data credibility score, wherein the data credibility score is calculated based on equipment state, data quality and weight score of early warning error report;
when the data credibility score meets the preset credibility, the disaster sensing data is input into a disaster grade pre-judging model to obtain an early warning grade;
and performing early warning response based on the disaster processing mode corresponding to the early warning level matching.
2. The intelligent early warning response method of a geological disaster according to claim 1, further comprising, prior to said receiving disaster sensing data:
acquiring a disaster grade training data set, wherein the disaster grade training data set comprises a plurality of groups of early warning grade sensing data, and one group of early warning grade sensing data comprises a sensing data set, a sensing data threshold data set and early warning grades corresponding to the sensing data set;
and training an initial disaster grade pre-judging model by using the disaster grade training data set to obtain the disaster grade pre-judging model.
3. The intelligent early warning response method of a geological disaster according to claim 1, wherein the data credibility score is calculated by 25% equipment state weight score, 55% data quality weight score and 20% early warning false alarm weight score.
4. The intelligent early warning response method of a geological disaster of claim 3, wherein 25% of the device status weight scores comprise a 15% device online rate weight score and a 10% device type weight score;
the equipment is characterized in that the equipment online rate is the proportion of the uploading times of the actual data of the equipment in the statistical period, and the equipment types comprise deformation monitoring equipment, stress monitoring equipment, water level monitoring equipment, temperature monitoring equipment and vibration monitoring equipment.
5. The intelligent early warning response method of a geological disaster of claim 3, wherein 55% of the data quality weight portions comprise a data integrity weight portion, a 15% gross fraction weight portion, a 20% sampling interval weight portion, and a 20% timeliness weight portion.
6. An intelligent early warning response device for a geological disaster, for executing the intelligent early warning response method for a geological disaster according to any one of the above claims 1 to 5, comprising:
the disaster sensing data receiving module is used for receiving the disaster sensing data;
the grading acquisition module is used for inputting the disaster sensing data into a disaster quality grading model to obtain a data credibility grading, and the data credibility grading is calculated based on equipment state, data quality and weight grading of early warning false alarm;
the early warning grade acquisition module is used for inputting the disaster sensing data into a disaster grade pre-judging model to obtain an early warning grade when the data credibility score meets the preset credibility;
the early warning response module is used for carrying out early warning response based on the disaster processing mode corresponding to the early warning grade matching;
the system comprises a first training data set acquisition module, a second training data set acquisition module and a first data set analysis module, wherein the first training data set acquisition module is used for acquiring a disaster quality grading training data set, the disaster quality grading training data set comprises a plurality of groups of disaster quality evaluation data, and one group of disaster quality evaluation data comprises equipment on-line state, equipment on-line rate, equipment type, data integrity, data coarse difference duty ratio, sampling interval time, timeliness and false report times;
and the scoring model acquisition module is used for training an initial disaster quality scoring model by using the disaster quality scoring training data set to obtain the disaster quality scoring model.
7. An intelligent early warning response system for a geological disaster, for executing the intelligent early warning response method for a geological disaster according to any one of the above claims 1 to 5, comprising:
an intelligent early warning platform;
a communication network;
and the monitoring equipment is in network communication with the intelligent early warning platform through the communication network.
8. The intelligent early warning response system of claim 7, wherein the intelligent early warning platform comprises an image acquisition module, a data management module, an early warning module, a patrol module, and a survey evaluation module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211724903.5A CN116434478B (en) | 2022-12-30 | 2022-12-30 | Intelligent early warning response method, device and system for geological disasters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211724903.5A CN116434478B (en) | 2022-12-30 | 2022-12-30 | Intelligent early warning response method, device and system for geological disasters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116434478A CN116434478A (en) | 2023-07-14 |
| CN116434478B true CN116434478B (en) | 2023-11-21 |
Family
ID=87087879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211724903.5A Active CN116434478B (en) | 2022-12-30 | 2022-12-30 | Intelligent early warning response method, device and system for geological disasters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116434478B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977725A (en) * | 2016-10-24 | 2018-05-01 | 广东奥博信息产业有限公司 | Big data Lightning Warning method and its system |
| CN110260774A (en) * | 2019-07-22 | 2019-09-20 | 安徽理工大学 | A kind of inspection of GNSS deformation information and method for early warning based on Pettitt algorithm |
| CN110264672A (en) * | 2019-06-25 | 2019-09-20 | 广州市城市规划勘测设计研究院 | A kind of early warning system of geological disaster |
| CN111666958A (en) * | 2019-03-05 | 2020-09-15 | 中科院微电子研究所昆山分所 | Method, device, equipment and medium for detecting equipment state based on image recognition |
| CN113723446A (en) * | 2021-07-15 | 2021-11-30 | 杭州鲁尔物联科技有限公司 | Ground disaster monitoring and early warning method and device, computer equipment and storage medium |
| CN114333245A (en) * | 2022-01-05 | 2022-04-12 | 中国地质科学院探矿工艺研究所 | Multi-parameter model dynamic early warning method based on landslide three-dimensional monitoring |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3041871A1 (en) * | 2018-05-01 | 2019-11-01 | Royal Bank Of Canada | System and method for monitoring security attack chains |
-
2022
- 2022-12-30 CN CN202211724903.5A patent/CN116434478B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977725A (en) * | 2016-10-24 | 2018-05-01 | 广东奥博信息产业有限公司 | Big data Lightning Warning method and its system |
| CN111666958A (en) * | 2019-03-05 | 2020-09-15 | 中科院微电子研究所昆山分所 | Method, device, equipment and medium for detecting equipment state based on image recognition |
| CN110264672A (en) * | 2019-06-25 | 2019-09-20 | 广州市城市规划勘测设计研究院 | A kind of early warning system of geological disaster |
| CN110260774A (en) * | 2019-07-22 | 2019-09-20 | 安徽理工大学 | A kind of inspection of GNSS deformation information and method for early warning based on Pettitt algorithm |
| CN113723446A (en) * | 2021-07-15 | 2021-11-30 | 杭州鲁尔物联科技有限公司 | Ground disaster monitoring and early warning method and device, computer equipment and storage medium |
| CN114333245A (en) * | 2022-01-05 | 2022-04-12 | 中国地质科学院探矿工艺研究所 | Multi-parameter model dynamic early warning method based on landslide three-dimensional monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116434478A (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109686061B (en) | Bridge monitoring aid decision-making system based on GIS and BIM | |
| CN107332698A (en) | A kind of Security Situation Awareness Systems and method towards bright Great Wall intelligent perception system | |
| CN112925279A (en) | Fault comprehensive analysis system based on MES system | |
| CN106020154A (en) | Safe dynamic health assessment method and assessment system for ethylene production | |
| CN112286771B (en) | Alarm method for monitoring global resources | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN105758661B (en) | Boiler heating surface service life evaluation system and method | |
| US20230162484A1 (en) | Apparatus and method for generating learning data for artificial intelligence model | |
| CN111178828A (en) | Method and system for building fire safety early warning | |
| CN113053063A (en) | Mobile terminal-based disaster online disposal flow implementation method | |
| CN114997682A (en) | Construction site safety monitoring system and method based on big data | |
| CN112326583A (en) | Intelligent toxic gas detection system and method based on Internet of things | |
| CN109916496A (en) | A kind of monitoring method and system of electronic scale | |
| CN111126751A (en) | Intelligent inspection and safety monitoring early warning system and method based on mobile interconnection | |
| CN110728381A (en) | Intelligent power plant inspection method and system based on RFID and data processing | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN114429308A (en) | Enterprise security risk assessment method and system based on big data | |
| CN115864223A (en) | Power grid full-professional differentiated operation and maintenance method based on unmanned aerial vehicle inspection technology | |
| CN115691746A (en) | Organism evaluation management system based on health record | |
| CN108093210A (en) | A kind of transformer oil level warning system and its alarm method | |
| CN111191855A (en) | Water quality abnormal event identification and early warning method based on pipe network multi-element water quality time sequence data | |
| CN110148290A (en) | Information-based big data system is supervised in the early warning of Intellisense Mine Safety in Production and prevention and control | |
| CN116434478B (en) | Intelligent early warning response method, device and system for geological disasters | |
| CN111579001A (en) | Fault detection method and device for robot | |
| CN116468423A (en) | Operation and maintenance emergency coordination method, system and terminal equipment |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231219 Address after: 518023 Taoyuan Road, Luohu District, Shenzhen City, Guangdong Province Patentee after: GEOLOGICAL BUREAU OF SHENZHEN Patentee after: SHENZHEN GEOLOGY & CONSTRUCTION CO. Address before: 518023 Taoyuan Road, Luohu District, Shenzhen City, Guangdong Province Patentee before: GEOLOGICAL BUREAU OF SHENZHEN |