CN106128035A - The geological disaster forecasting method merged based on neutral net and multi-parameter information - Google Patents

The geological disaster forecasting method merged based on neutral net and multi-parameter information Download PDF

Info

Publication number
CN106128035A
CN106128035A CN201610504858.0A CN201610504858A CN106128035A CN 106128035 A CN106128035 A CN 106128035A CN 201610504858 A CN201610504858 A CN 201610504858A CN 106128035 A CN106128035 A CN 106128035A
Authority
CN
China
Prior art keywords
geological disaster
disaster
sensor
step
probability
Prior art date
Application number
CN201610504858.0A
Other languages
Chinese (zh)
Other versions
CN106128035B (en
Inventor
李丽敏
温宗周
魏小胜
Original Assignee
西安工程大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 西安工程大学 filed Critical 西安工程大学
Priority to CN201610504858.0A priority Critical patent/CN106128035B/en
Publication of CN106128035A publication Critical patent/CN106128035A/en
Application granted granted Critical
Publication of CN106128035B publication Critical patent/CN106128035B/en

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/10Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes

Abstract

The invention discloses the geological disaster forecasting method merged based on neutral net and multi-parameter information, initially set up the geological disaster forecasting model merged based on neutral net and multi-parameter information;Then set up the relation between geological disaster probability of happening and geological disaster grade;Multiparameter geological disaster monitoring system is finally utilized to carry out data acquisition, it is achieved the forecast of geological disaster.The present invention uses RBF neural to carry out the foundation of forecasting model, geological disaster probability of happening corresponding under conditions present can be calculated, and geological disaster grade can be extrapolated according to probability of happening, such that it is able to the measure of corresponding grade is taked to prevent and reduce the generation of disaster;Take into full account the multiple factors affecting callapsed landslide, Geological Hazards of debris, the decision-making that gives a forecast is provided foundation more accurately, improve quality supervision examining system traditionally and can only gather data and the defect that can not be analyzed.

Description

The geological disaster forecasting method merged based on neutral net and multi-parameter information

Technical field

The invention belongs to geological disaster forecasting technical field, relate to the geology merged based on neutral net and multi-parameter information Damage forecasting method.

Background technology

In recent years, Chinese large-sized geological disaster Frequent Accidents, such as mud-rock flow, callapsed landslide etc., sending out of these geological disasters Raw have randomness and sudden and huge, and it frequently can lead to the most serious casualties and economic loss.China Man of Shi Duo mountain country, a lot of local hidden danger that all there is geological disaster, if can not be by the Resolving probiems of forecast, then geological disaster Also will affect more people.

The conclusion occurring the place of geology disaster accident to obtain after many analyses is as follows: 1) cause of accident is main By Geological Evolution and meteorological effect, the most indivedual accidents are belonging to what anthropic factor caused;2) cause huge The result of casualties and economic loss is primarily due to do not have reliable monitoring device;3) area having is laid with monitoring and sets Standby, owing to there is no suitable forecasting procedure to gather the data come and can not play the effect of its maximum, cause the wave of resource Take.

Through investigation and analysis and research, find that the factor affecting callapsed landslide generation has the most several: rainfall, soil contain Water rate, crack, pore water pressure and sedimentation change etc.;The factor affecting mud-rock flow generation has the most several: rainfall, soil contain Water rate, mud position, mud speed, infrasonic sound and ground sound etc..Data corresponding to these factors can be arrived by sensor acquisition, the heaviest These data are analyzed by work exactly that want, draw the relation between itself and geological disaster probability of happening, if it is possible to logical Geological disaster is forecast by the mode crossing founding mathematical models, then just can enter geological disaster before geological disaster occurs Row early warning, thus avoid serious casualties and economic loss.

Summary of the invention

It is an object of the invention to provide the geological disaster forecasting method merged based on neutral net and multi-parameter information, set up Multiparameter geological disaster monitoring system and geological disaster forecasting model, it is achieved analysis, rule statistics and the geology to multiparameter The early warning of disaster.

The technical solution adopted in the present invention is, the geological disaster forecasting side merged based on neutral net and multi-parameter information Method, specifically implements according to following steps:

Step 1, sets up the geological disaster forecasting model merged based on neutral net and multi-parameter information;

Step 2, sets up the relation between geological disaster probability of happening and geological disaster grade;

Step 3, utilizes multiparameter geological disaster monitoring system to carry out data acquisition, the data input step 1 that will collect With in step 2, it is achieved the forecast of geological disaster.

Inventive feature also resides in,

Process set up by step 1 geological disaster forecasting model:

Step 1.1: training data arranges and the setting of threshold value;

Step 1.2: the foundation of forecasting model based on radial direction base (RBF) neutral net;

The detailed process of step 1.1 is:

There is the relation of the mud-rock flow factor in geological disaster area, landslide factor and the extent of injury in statistics respectively, and will Each parameter factors as training data, selects relevant parameter to measure the maximum range of sensor subsequently, and by 0-maximum range it Between the divided rank of counting of training data is installed, determine the initial relation distribution of each parameter and geological disaster probability of happening, will become Calamity probability is divided into tetra-scopes of 0-5%, 5-2-%, 20-40% and 40-90%, so that it is determined that the threshold value of each parameter.

The mud-rock flow factor includes effective precipitation, soil moisture content, mud position and undersonic frequency;Landslide factor includes that day is comprehensive Rainfall, soil moisture content, pore water pressure and crack displacement.

The detailed process of step 1.2 is:

Forecasting model is divided into input layer, hidden layer and output layer, and its input is multiparameter and corresponding geological disaster generation Probability, calculates the weighting parameter in hidden layer by given input layer, output layer data, thus obtains input and output Between relational expression, concrete formula is as follows:

A{1}=radbas (netprod (dist (net, IW{1,1}, p), net, b{1})) (1)

Wherein a is output--geological disaster probability of happening, and p is input--training data, tries to achieve net;Carry it into subsequently Training pattern formula in Calling MATLAB function library:

Net=newrb (p1, a1) (2)

Wherein, net is the geological disaster forecasting model obtained, and a1 is for exporting current geological disaster probability of happening, and p1 is Input--real-time data collection.

The detailed process of step 2 is:

Suddenly there is loss situation, probability of causing disaster and the extent of injury easily produced that the condition of a disaster causes in foundation geological disaster, Geological disaster grade is divided into level Four: especially severe burst the condition of a disaster is level Four, and geological disaster probability of happening is 40-90%, for red Color early warning, seriousness burst the condition of a disaster is three grades, and geological disaster probability of happening is 20-40%, for orange early warning, large-scale burst the condition of a disaster Being two grades, geological disaster probability of happening is 5-20%, and for yellow early warning, usual property burst the condition of a disaster is one-level, and geological disaster occurs Probability is 0-5%, for blue early warning.

In step 3, multiparameter geological disaster monitoring system includes monitoring terminal, monitoring terminal respectively with sensor, power supply Module, memory module connect, and monitoring terminal is connected by wireless network with Surveillance center, and Surveillance center is with onsite alarming device even Connecing, wherein, monitoring terminal is the minimum system with STM32F103 as core devices, and inside comprises 16 road A/D converters;Sensing Device includes soil moisture content sensor, rainfall amount sensor, mud speed sensor, mud level sensor and ground sound, infrasound sensor, splits Seam sensor, osmotic pressure and sedimentation deformation sensor.

Memory module is K9F2G08UOC-SCBO programmable storage;Power module is that solar panel adds accumulator Power supply mode.

Wireless network is GSM, GPRS or Beidou satellite communication.

The detailed process of step 3 is:

Monitoring terminal in multiparameter geological disaster monitoring system is to soil moisture content sensor, rainfall amount sensor, mud The data that speed sensor, mud level sensor, infrasound sensor, crack sensors, osmotic pressure and sedimentation deformation sensor acquisition arrive It is collected, and the data of collection is stored in the memory module of extension, when Surveillance center is monitored by wireless network requirements Terminal will gather data and send, or monitoring terminal is from the transmission time set arrives when, and monitoring terminal can pass through nothing Collection data are sent to Surveillance center by gauze network, after Surveillance center receives, and the formula being entered in step 1.2 (2), in, obtain geological disaster probability of happening value a, geological disaster grade can be obtained by the method for step 2 subsequently.

The invention has the beneficial effects as follows, use RBF neural to carry out the foundation of forecasting model, it is possible to calculate and work as preceding article Geological disaster probability of happening corresponding under part, and geological disaster grade can be extrapolated according to probability of happening, such that it is able to take The measure of corresponding grade prevents and reduces the generation of disaster;Take into full account that to affect callapsed landslide, Geological Hazards of debris many Individual factor, provides foundation more accurately to the decision-making that gives a forecast, and improves quality supervision examining system traditionally and can only gather data And the defect that can not be analyzed;Adding self-learning function, it is pre-that correction is brought owing to initial threshold setting does not conforms to the actual conditions Report inaccurate problem, improve the accuracy of geological disaster forecasting.

Accompanying drawing explanation

Fig. 1 is the flow chart of the geological disaster forecasting method that the present invention merges based on neutral net and multi-parameter information;

Fig. 2 is multiparameter geology in present invention geological disaster forecasting method based on neutral net and multi-parameter information fusion Disaster monitoring system structural representation.

In Fig. 2,1. monitoring terminal, 2. power module, 3. memory module, 4. Surveillance center, 5. alarm, 6. soil water-containing Rate sensor, 7. rainfall amount sensor, 8. mud speed sensor, 9. mud level sensor, 10. sonic transducer, 11. infrasonic sound sensings Device, 12. crack sensors, 13. osmolarity sensor, 14. sedimentation deformation sensors.

Detailed description of the invention

The present invention is described in detail with detailed description of the invention below in conjunction with the accompanying drawings.

The flow process of the geological disaster forecasting method that the present invention merges based on neutral net and multi-parameter information as it is shown in figure 1, Specifically implement according to following steps:

Step 1, sets up the geological disaster forecasting model merged based on neutral net and multi-parameter information;

Step 1.1: training data arranges and the setting of threshold value;

There is the relation of the mud-rock flow factor in geological disaster area, landslide factor and the extent of injury in statistics respectively, and will Each parameter factors as training data, selects relevant parameter to measure the maximum range of sensor subsequently, and by 0-maximum range it Between the divided rank of counting of training data is installed, determine the initial relation distribution of each parameter and geological disaster probability of happening, will become Calamity probability is divided into tetra-scopes of 0-5%, 5-2-%, 20-40% and 40-90%, so that it is determined that the threshold value of each parameter, wherein, mud The rock glacier factor includes effective precipitation, soil moisture content, mud position and undersonic frequency;Landslide factor includes daily synthetic rainfall, soil Moisture content, pore water pressure and crack displacement.The relation of the mud-rock flow factor, landslide factor and the probability that causes disaster is respectively such as Fig. 1 and Fig. 2 Shown in:

The relation of each factor of table 1 mud-rock flow and the probability that causes disaster

Table 2 comes down each factor and the relation of the probability that causes disaster

Step 1.2: the foundation of forecasting model based on radial direction base (RBF) neutral net;

RBF network can approach arbitrary nonlinear function, the regularity that can resolve with being difficult in processing system, has Good generalization ability, and have study convergence rate quickly, has been successfully applied to that nonlinear function approaches, time series is divided Analysis, data classification, pattern recognition, information processing, image procossing, system modelling, control and fault diagnosis etc., forecasting model is depended on The microcomputer in service station centered by the running environment of torr.

Forecasting model is divided into input layer, hidden layer and output layer, and its input is multiparameter and corresponding geological disaster generation Probability, calculates the weighting parameter in hidden layer by given input layer, output layer data, thus obtains input and output Between relational expression, concrete formula is as follows:

A{1}=radbas (netprod (dist (net, IW{1,1}, p), net, b{1})) (1)

Wherein a is output--geological disaster probability of happening, and p is input--training data, tries to achieve net;Carry it into subsequently Training pattern formula in Calling MATLAB function library:

Net=newrb (p1, a1) (2)

Wherein, net is the geological disaster forecasting model obtained, and a1 is for exporting current geological disaster probability of happening, and p1 is Input--real-time data collection;

After geological disaster model formation (2) is set up, automatically update geological disaster forecasting model based on real time data Self study be achieved in that and gather the real time data of coming, except for analyzing current geological disaster probability of happening every time Outside grade, the part data being additionally operable in the p in the renewal to training data, i.e. formula (1) are replaced by real time data, so After again carry out the training of model with the p after updating, obtain more accurate forecast model.

Step 2, sets up the relation between geological disaster probability of happening and geological disaster grade;

Suddenly there is loss situation, probability of causing disaster and the extent of injury easily produced that the condition of a disaster causes in foundation geological disaster, Geological disaster grade is divided into level Four: the landslide critical forecast grade entering tertiary creep stage middle and late stage is alarm level, especially Serious burst the condition of a disaster is level Four, and geological disaster probability of happening is 40-90%, for red early warning, enters mid-term in tertiary creep stage Landslide critical forecast grade for warning level, seriousness burst the condition of a disaster be three grades, geological disaster probability of happening is 20-40%, for Orange early warning, the landslide critical forecast grade entering initial acceleration creep stage middle and late stage is warning level, and large-scale burst the condition of a disaster is Two grades, geological disaster probability of happening is 5-20%, and for yellow early warning, entering the landslide critical forecast grade in constant rate creeep stage is Noting level, usual property burst the condition of a disaster is one-level, and geological disaster probability of happening is 0-5%, for blue early warning, is specifically shown in Table 3:

Table 3 grade classification

Step 3, utilizes multiparameter geological disaster monitoring system to carry out data acquisition, the data input step 1 that will collect With in step 2, it is achieved the forecast of geological disaster:

Multiparameter geological disaster monitoring system includes monitoring terminal 1, monitoring terminal 1 respectively with sensor, power module 2, Memory module 3 connects, and monitoring terminal 1 is connected by wireless network with Surveillance center 4, and Surveillance center 4 is with onsite alarming device 5 even Connecing, wherein, sensor includes soil moisture content sensor 6, rainfall amount sensor 7, mud speed sensor 8, mud level sensor 9 and ground Sonic transducer 10, infrasound sensor 11, crack sensors 12, osmolarity sensor 13 and sedimentation deformation sensor 14, its structure Schematic diagram is as shown in Figure 2.

Detailed process is: the monitoring terminal in multiparameter geological disaster monitoring system is to soil moisture content sensor, rainfall Quantity sensor, mud speed sensor, mud level sensor, sonic transducer, infrasound sensor, crack sensors, osmotic pressure and sedimentation The data that displacement transducer collects are collected, and the data of collection are stored in the memory module of extension, when in monitoring The heart by wireless network requirements monitoring terminal will gather data send, or monitoring terminal from set send the time arrive time Waiting, collection data can be sent to Surveillance center by wireless network by monitoring terminal, after Surveillance center receives, it is defeated In the formula (2) entered in step 1.2, obtain geological disaster probability of happening value a, geology calamity can be obtained by the method for step 2 subsequently Evil grade.

Wherein, monitoring terminal is the minimum system with STM32F103 as core devices, and inside comprises 16 road A/D converters, This chip has: the Cortex-M3CPU of 32, the highest 72MHZ operating frequency, monocycle multiplication and hardware division, 256K byte FLASH program memory, the feature such as SRAM of 48K byte.Rain sensor should be laid in debris flow formation region and heavy rain thereof The location that in band, surrounding is spacious, smooth and windage is little, also should carry out website laying according to altitudinal gradient when having ready conditions.The soil body Pore water pressure and water content sensor should be laid in the thing that basin middle and upper reaches are easier to start and fine grained is more under heavy showers On the body of source region open slope.In mud-rock flow small watershed, the relatively regular straight location of raceway groove is less, groove gradient is relatively big, the most relatively low ditch Bank has and is silted the danger buried with sapping, and the most contactless mud level sensor, displacement transducer and vibrating sensor should be laid At straight, permeability preferably, in less than fall middle and lower reaches Circulation Area, basin ditch section, with base fixed, be simultaneously in flood peak line with On boulder, basement rock, dykes and dams, debris dam, bridge etc. be advisable.Especially mud level sensor and displacement transducer lays interval river at it Section planted agent is negligible without the supply of other runoffs or increment, and considers downstream construction area according to mud-rock flow movement speed Withdraw the time of required advance alert.All wiring use the aviation patch plug of water proof and dust proof to be attached.Memory module is K9F2G08UOC-SCBO programmable storage;

Data transmission mainly includes short range wireless data transmission and long distance wireless data two parts of transmission, short-distance radio number Include that short range wireless data transmission and relay station, the transmission of long distance wireless data include GPRS, GSM and big-dipper satellite according to transmission equipment Terminal transmission, data transmission system is that data are passed back by effective communication mode, field data simultaneously by early warning signal Transmit and realize reporting to the police to onsite alarming equipment, i.e. scene is analyzed according to sensor acquisition data, after reaching the threshold value set Broadcasted by traffic lights and early warning and realize reporting to the police, gather data simultaneously and can be transmitted by public network or the most indoor number of big-dipper satellite According to central store analysis, the information that scene directly can be carried out after short range wireless communications is invalid early warning by data center is issued. The business little for field data amount, emergency is high, uses short range wireless transmission to transmit early warning signal to onsite alarming equipment, Carrying out early warning in time, short-distance radio early warning propagation distance is within 2 kms, and centre intercepts without big building or mountains and rivers, If there being obstruct to cause receiving data, in addition it is also necessary to set up radio repeater station.For the area having public network to cover, typically should select Group (GSM/GPRS) is carried out with public network;The area that covers fails for public network, general selects Beidou satellite communication mode to carry out group Net, for emphasis monitored area and area with good conditionsi, can be selected for two kinds of different communication modes and gives networking, it is achieved be the most standby Part, the function that automatically switches, it is ensured that information transmission channel unimpeded.

In view of on-the-spot emergency service practical situation, solar panel is all used to add the power supply mode of accumulator, electric power storage Pond uses Li-ion batteries piles, and it has safe and reliable, and volume is little, lightweight, easy to use, and self discharge is little, and it is permanent to use Etc. feature, local solar panel the most with good conditionsi can direct lithium cell charging, the equipment that is available for normally work 10 days with On time, in unconditional place, lithium battery be can be used directly and is powered, lithium battery under full state without charge condition Under be available for equipment and normally work time of more than 3 days.

Claims (10)

1. the geological disaster forecasting method merged based on neutral net and multi-parameter information, it is characterised in that specifically according to following Step is implemented:
Step 1, sets up the geological disaster forecasting model merged based on neutral net and multi-parameter information;
Step 2, sets up the relation between geological disaster probability of happening and geological disaster grade;
Step 3, utilizes multiparameter geological disaster monitoring system to carry out data acquisition, by the data input step 1 collected and step In rapid 2, it is achieved the forecast of geological disaster.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 1, it is special Levying and be, step 1 geological disaster forecasting model is set up process and is:
Step 1.1: training data arranges and the setting of threshold value;
Step 1.2: the foundation of forecasting model based on radial base neural net.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 2, it is special Levying and be, the detailed process of step 1.1 is:
There is the relation of the mud-rock flow factor in geological disaster area, landslide factor and the extent of injury in statistics respectively, and by each ginseng The number factor, as training data, selects relevant parameter to measure the maximum range of sensor subsequently, and will pacify between 0-maximum range The divided rank of counting of dress training data, determines the initial relation distribution of each parameter and geological disaster probability of happening, and will cause disaster machine Rate is divided into tetra-scopes of 0-5%, 5-2-%, 20-40% and 40-90%, so that it is determined that the threshold value of each parameter.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 3, it is special Levying and be, the mud-rock flow factor includes effective precipitation, soil moisture content, mud position and undersonic frequency;Landslide factor includes that day is comprehensive Rainfall, soil moisture content, pore water pressure and crack displacement.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 2, it is special Levying and be, the detailed process of step 1.2 is:
Forecasting model is divided into input layer, hidden layer and output layer, and its input is multiparameter and corresponding geological disaster probability of happening, The weighting parameter in hidden layer is calculated by given input layer, output layer data, thus between being inputted and exporting Relational expression, concrete formula is as follows:
A{1}=radbas (netprod (dist (net, IW{1,1}, p), net, b{1})) (1)
Wherein a is output--geological disaster probability of happening, and p is input--training data, tries to achieve net;Carry it into subsequently and call Training pattern formula in MATLAB function library:
Net=newrb (p1, a1) (2)
Wherein, net is the geological disaster forecasting model obtained, and a1 is for exporting current geological disaster probability of happening, and p1 is defeated Enter--real-time data collection.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 1, it is special Levying and be, the detailed process of step 2 is:
Suddenly there is loss situation, probability of causing disaster and the extent of injury easily produced that the condition of a disaster causes in foundation geological disaster, by ground Matter disaster loss grade is divided into level Four: especially severe burst the condition of a disaster is level Four, and geological disaster probability of happening is 40-90%, pre-for redness Alert, seriousness burst the condition of a disaster is three grades, and geological disaster probability of happening is 20-40%, and for orange early warning, large-scale burst the condition of a disaster is two Level, geological disaster probability of happening is 5-20%, and for yellow early warning, usual property burst the condition of a disaster is one-level, geological disaster probability of happening For 0-5%, for blue early warning.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 1, it is special Levying and be, in step 3, multiparameter geological disaster monitoring system includes monitoring terminal (1), monitoring terminal (1) respectively with sensor, Power module (2), memory module (3) connect, and monitoring terminal (1) is connected by wireless network with Surveillance center (4), Surveillance center (4) being connected with onsite alarming device (5), wherein, monitoring terminal (1) is the minimum system with STM32F103 as core devices, internal Comprise 16 road A/D converters;Sensor includes soil moisture content sensor (6), rainfall amount sensor (7), mud speed sensor (8), mud level sensor (9) and ground sonic transducer (10), infrasound sensor (11), crack sensors (12), osmolarity sensor And sedimentation deformation sensor (14) (13).
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 7, it is special Levying and be, memory module (3) is K9F2G08UOC-SCBO programmable storage;Power module (2) is that solar panel adds storage The power supply mode of battery.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 7, it is special Levying and be, wireless network is GSM, GPRS or Beidou satellite communication.
The geological disaster forecasting method merged based on neutral net and multi-parameter information the most according to claim 1, it is special Levying and be, the detailed process of step 3 is:
Soil moisture content sensor, rainfall amount sensor, mud speed are passed by the monitoring terminal in multiparameter geological disaster monitoring system Sensor, mud level sensor, infrasound sensor, crack sensors, osmotic pressure and sedimentation deformation sensor acquisition to data carry out Collect, and the data of collection are stored in the memory module of extension, when Surveillance center is by wireless network requirements monitoring terminal To gather data to send, or monitoring terminal is from the transmission time set arrives when, monitoring terminal can pass through wireless network Collection data are sent to Surveillance center by network, after Surveillance center receives, in the formula (2) being entered in step 1.2, Obtain geological disaster probability of happening value a, geological disaster grade can be obtained by the method for step 2 subsequently.
CN201610504858.0A 2016-06-30 2016-06-30 The geological disaster forecasting method merged based on neural network and multi-parameter information CN106128035B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610504858.0A CN106128035B (en) 2016-06-30 2016-06-30 The geological disaster forecasting method merged based on neural network and multi-parameter information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610504858.0A CN106128035B (en) 2016-06-30 2016-06-30 The geological disaster forecasting method merged based on neural network and multi-parameter information

Publications (2)

Publication Number Publication Date
CN106128035A true CN106128035A (en) 2016-11-16
CN106128035B CN106128035B (en) 2018-10-02

Family

ID=57467625

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610504858.0A CN106128035B (en) 2016-06-30 2016-06-30 The geological disaster forecasting method merged based on neural network and multi-parameter information

Country Status (1)

Country Link
CN (1) CN106128035B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106658381A (en) * 2016-12-31 2017-05-10 中国铁道科学研究院电子计算技术研究所 Landslide early warning method based on wireless sensor network
CN106683349A (en) * 2017-02-23 2017-05-17 深圳凯达通光电科技有限公司 Comprehensive monitoring system for geological disasters
CN106815971A (en) * 2016-12-21 2017-06-09 西安工程大学 A kind of landslide disaster forecasting procedure based on RBF neural
CN108154651A (en) * 2018-01-29 2018-06-12 西安工程大学 A kind of device and method for landslide disaster Monitoring and forecasting system in real-time
CN108200230A (en) * 2017-12-26 2018-06-22 成都傅立叶电子科技有限公司 A kind of mobile phone satellite communication method based on STM32 platforms
CN108492530A (en) * 2018-03-09 2018-09-04 深圳市宏电技术股份有限公司 A kind of reservoir spillway warning information dissemination method, apparatus and system
JP2018141701A (en) * 2017-02-28 2018-09-13 学校法人加計学園 System for setting disaster prevention weather information announcement standard at dangerous place

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101436264A (en) * 2008-11-28 2009-05-20 北京交通大学 Mine downhole debris flow prediction method based on subsection fuzzy BP neural network
JP2011192037A (en) * 2010-03-15 2011-09-29 Toshiba Corp Information distribution system, method of distributing information, and disaster prevention system utilizing them
CN102651053A (en) * 2012-04-01 2012-08-29 中国科学院地理科学与资源研究所 Evaluation method of debris flow disaster risk based on Bayesian network model
CN102930348A (en) * 2012-10-19 2013-02-13 广东电网公司电力科学研究院 Assessment method for rainstorm disaster risks of sectional power transmission line pole-tower foundation slopes
CN103136446A (en) * 2013-01-31 2013-06-05 南信大影像技术工程(苏州)有限公司 Back propagation (BP) neural network landslide forecasting method based on optimized input layer
CN104299367A (en) * 2014-10-23 2015-01-21 中国科学院、水利部成都山地灾害与环境研究所 Landslide hazard multi-stage comprehensive monitoring and early warning method
CN104331744A (en) * 2014-10-17 2015-02-04 中国科学院、水利部成都山地灾害与环境研究所 Debris flow risk degree evaluation method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101436264A (en) * 2008-11-28 2009-05-20 北京交通大学 Mine downhole debris flow prediction method based on subsection fuzzy BP neural network
JP2011192037A (en) * 2010-03-15 2011-09-29 Toshiba Corp Information distribution system, method of distributing information, and disaster prevention system utilizing them
CN102651053A (en) * 2012-04-01 2012-08-29 中国科学院地理科学与资源研究所 Evaluation method of debris flow disaster risk based on Bayesian network model
CN102930348A (en) * 2012-10-19 2013-02-13 广东电网公司电力科学研究院 Assessment method for rainstorm disaster risks of sectional power transmission line pole-tower foundation slopes
CN103136446A (en) * 2013-01-31 2013-06-05 南信大影像技术工程(苏州)有限公司 Back propagation (BP) neural network landslide forecasting method based on optimized input layer
CN104331744A (en) * 2014-10-17 2015-02-04 中国科学院、水利部成都山地灾害与环境研究所 Debris flow risk degree evaluation method
CN104299367A (en) * 2014-10-23 2015-01-21 中国科学院、水利部成都山地灾害与环境研究所 Landslide hazard multi-stage comprehensive monitoring and early warning method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘欣宇: "人工神经网络在泥石流预测中的应用", 《中国优秀硕士学位论文全文数据库(电子期刊)·基础科学辑》 *
赵星: "贵州省望漠河泥石流自动化监测与预警系统", 《中国优秀硕士学位论文全文数据库(电子期刊)•基础科学辑》 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106815971A (en) * 2016-12-21 2017-06-09 西安工程大学 A kind of landslide disaster forecasting procedure based on RBF neural
CN106815971B (en) * 2016-12-21 2019-11-26 西安工程大学 A kind of landslide disaster forecasting procedure based on RBF neural
CN106658381A (en) * 2016-12-31 2017-05-10 中国铁道科学研究院电子计算技术研究所 Landslide early warning method based on wireless sensor network
CN106658381B (en) * 2016-12-31 2019-08-30 中国铁道科学研究院电子计算技术研究所 A kind of landslide method for early warning based on wireless sensor network
CN106683349A (en) * 2017-02-23 2017-05-17 深圳凯达通光电科技有限公司 Comprehensive monitoring system for geological disasters
JP2018141701A (en) * 2017-02-28 2018-09-13 学校法人加計学園 System for setting disaster prevention weather information announcement standard at dangerous place
CN108200230B (en) * 2017-12-26 2019-12-13 成都傅立叶电子科技有限公司 mobile phone satellite communication method based on STM32 platform
CN108200230A (en) * 2017-12-26 2018-06-22 成都傅立叶电子科技有限公司 A kind of mobile phone satellite communication method based on STM32 platforms
CN108154651A (en) * 2018-01-29 2018-06-12 西安工程大学 A kind of device and method for landslide disaster Monitoring and forecasting system in real-time
CN108492530A (en) * 2018-03-09 2018-09-04 深圳市宏电技术股份有限公司 A kind of reservoir spillway warning information dissemination method, apparatus and system

Also Published As

Publication number Publication date
CN106128035B (en) 2018-10-02

Similar Documents

Publication Publication Date Title
CN106205061B (en) A kind of geological hazards prediction system
Badoux et al. A debris-flow alarm system for the Alpine Illgraben catchment: design and performance
CN103678910B (en) Cloud system structure pre-warning system and method for riverway type reservoir tributary bay water bloom
CN101270997B (en) Floating car dynamic real-time traffic information processing method based on GPS data
CN101452629B (en) Remote monitoring system for disaster of mountain massif coast
CN102629294B (en) Probability evaluation method of failure caused by typhoon to power transmission line
Mergili et al. Regional-scale analysis of lake outburst hazards in the southwestern Pamir, Tajikistan, based on remote sensing and GIS
CN104236626B (en) The integrated on-line monitoring system of drainage pipeline liquid level and flow
Wu et al. An evaluation of the impacts of land surface modification, storm sewer development, and rainfall variation on waterlogging risk in Shanghai
CN104408900A (en) Dynamic optimization based neural network flood warning device and method
CN201993108U (en) On-line intelligent monitoring system of tailing pond
CN104092750B (en) A kind of flood control rainwater feelings wireless monitor station and its monitoring method
CN103278842B (en) Earthquake predicting and pre-warning system based on ground source ultrasonic wave monitoring and analysis
CN104111091B (en) A kind of mud-rock flow mechanics parameter monitoring method and debris flow early-warning method
CN103345208B8 (en) Urban Storm Flood prevents and treats intelligence control system and control method
CN105223937B (en) Hydropower Stations ecological regulation and control intelligence control system and method
Cools et al. An early warning system for flash floods in hyper-arid Egypt
CN104898183A (en) Modeling evaluation method for urban heavy rain inundation
CN101872533B (en) Pre-warning method and system for mud-rock flow
CN103743441B (en) The polynary of a kind of side slope safety is coupling in line monitoring system and method
CN201839317U (en) Tunnel safety quick detection system based on wireless sensor network
CN103088806B (en) A kind of high-fill roadbed and earth and rockfill dam are out of shape wireless real time monitoring system
CN101477207A (en) Intelligent geological calamity synthetic monitoring system and multi-stage prediction analysis method
CN103968913A (en) Intelligent on-line liquid level monitoring and early warning system
CN203490806U (en) Debris flow pre-disaster early warning system based on wireless sensor network

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20190729

Address after: 710000 No. 3, No. 7 Science and Technology Road, Xi'an High-tech Zone, Shaanxi Province

Patentee after: Xi'an Tianhuiyuan Tong Water Conservancy Information Technology Co., Ltd.

Address before: 710048 Shaanxi city of Xi'an Province Jinhua Road No. 19

Patentee before: Xi'an Engineering Univ.

TR01 Transfer of patent right