CN114299693A - GNSS-based slope monitoring and early warning method - Google Patents
GNSS-based slope monitoring and early warning method Download PDFInfo
- Publication number
- CN114299693A CN114299693A CN202111653395.1A CN202111653395A CN114299693A CN 114299693 A CN114299693 A CN 114299693A CN 202111653395 A CN202111653395 A CN 202111653395A CN 114299693 A CN114299693 A CN 114299693A
- Authority
- CN
- China
- Prior art keywords
- value
- monitoring
- early warning
- time
- current
- 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.)
- Granted
Links
Images
Abstract
The invention provides a slope monitoring and early warning method based on GNSS, comprising the following steps of S1: aiming at historical monitoring data, a dual-exponential smoothing method is used, and a predicted value at the next moment after c monitoring values is estimated based on the c monitoring values before the time sequence each time; taking all the predicted values as training data, and calculating the average value and standard deviation of errors of the training data; step S2: for the current monitoring data, estimating a predicted value of the current moment based on the past c monitoring values by using a bi-exponential smoothing method, calculating an error between the predicted value of the current moment and the monitoring value of the current moment, comparing the error with the average value and the standard deviation of the training data errors in the step S1, judging whether the monitoring value of the current moment is an abnormal value, and establishing a characteristic value sequence; step S3: calculating the current early warning index of the abnormal value according to the characteristic value sequence; step S4: and determining the early warning grade according to the early warning index. The method can effectively avoid the problems of 'missing alarm', 'late alarm' and 'false alarm'.
Description
Technical Field
The invention relates to the technical field of GNSS monitoring, in particular to a slope monitoring and early warning method based on GNSS.
Background
Landslide is one of natural disasters which easily occur in the nature, and great influence is caused on the production and life of human beings. Therefore, an automatic online monitoring system is established for the side slope with potential landslide risk, and timely early warning information is issued through monitoring data, so that the system has important significance for reducing landslide accidents and reducing accident loss.
With the success of networking of Beidou satellites, monitoring of side slope surface displacement by using GNSS (Global Navigation Satellite System) becomes one of the most common side slope displacement monitoring methods at present, GNSS equipment can acquire high-precision three-dimensional space position information all day long, has very high sampling frequency, can realize real-time continuous online monitoring of side slopes, has the advantages of low manufacturing cost, simplicity in maintenance and the like, and has been applied to large-scale engineering.
In engineering practice, GNSS equipment is installed on the surface of a monitored side slope in the open air, and due to the influence of environmental factors such as temperature, humidity and tree shielding, the GNSS monitoring value has certain volatility, wherein gross error data can be mixed, and difficulty is caused to subsequent data analysis and monitoring early warning.
One of the key problems of GNSS monitoring and early warning is how to identify signs of landslide disaster occurrence according to GNSS monitored data, and then issue early warning information, where the accuracy of landslide disaster identification and the timeliness of early warning information issuance are the keys of an early warning algorithm. When the GNSS monitoring data is used to perform landslide early warning on a slope, a common method is to set a threshold judgment condition for a single deformation value, an accumulated deformation value, or a deformation rate value, and send early warning information when the judgment condition is satisfied. In addition, early warning is performed on GNSS monitoring data by a box plot analysis method (quartile method), a local weighted regression method, or the like.
The principle of the threshold judgment early warning method based on the single deformation value, the accumulated deformation value or the deformation rate value is easy to understand, namely, the landslide disaster is caused when the slope has larger deformation in a short time. However, because the short-term fluctuation of the GNSS monitoring data is strong, gross errors or outliers can be mixed in the monitoring data during long-term monitoring, and the method can frequently generate a false alarm phenomenon in actual operation, thereby seriously affecting the operation effect of the monitoring system.
The quartile method is characterized in that the GNSS monitoring data are assumed to be in normal distribution, and a single deformation value, an accumulated deformation value or a deformation rate value are calculated for the monitoring data with abnormal values eliminated, and early warning is carried out. The distribution of GNSS monitoring data is related to the mechanical property of the monitored slope rock soil, and does not necessarily accord with normal distribution, so that the quartile method can remove correct monitoring data to cause 'alarm missing'.
The local weighted regression method is to use the data in the previous and next time windows of the current data to calculate the average value, and then to analyze and warn with the smoothed GNSS monitoring value. The local weighted regression method needs to average the data in the time windows before and after the data acquisition, so that the problem of 'late alarm' exists.
In summary, there is an urgent need for a slope monitoring and early warning method based on GNSS to solve the problems in the prior art.
Disclosure of Invention
The invention aims to provide a slope monitoring and early warning method based on GNSS, which aims to solve the problems of false alarm, missed alarm and late alarm in the existing early warning method, and the specific technical scheme is as follows:
a slope monitoring and early warning method based on GNSS comprises the following steps:
step S1: aiming at historical monitoring data, a dual-exponential smoothing method is used, and a predicted value at the next moment after c monitoring values is estimated based on the c monitoring values before the time sequence each time; taking all the predicted values as training data, and calculating the average value and standard deviation of errors of the training data;
step S2: for the current monitoring data, estimating a predicted value of the current moment based on the past c monitoring values by using a bi-exponential smoothing method, calculating an error between the predicted value of the current moment and the monitoring value of the current moment, comparing the error with the average value and the standard deviation of the training data errors in the step S1, judging whether the monitoring value of the current moment is an abnormal value, and establishing a characteristic value sequence;
step S3: calculating the current early warning index of the abnormal value according to the characteristic value sequence;
step S4: and determining the early warning grade according to the early warning index.
In the above technical solution, preferably, the step S1 of estimating the predicted value of the c monitoring values at the next time based on the c monitoring values before the time series each time and the step S2 of estimating the predicted value of the current time based on the past c monitoring values each time perform recursive calculation according to formulas 1) to 3):
si＝α·xi+(1-α)·(si-1+τi-1) Formula 1) below,
τi＝β·(si-si-1)+(1-β)·τi-1formula 2) below is given,
wherein x isiIs the monitored value at time i, siIs the level at time i, si-1Is the level at time i-1, τiIs the trend at time i, τi-1Is the trend at time i-1,
is the predicted value at time i +1, α is the horizontal smoothing constant, and β is the trend smoothing constant.
Preferably, in the above technical solution, the mean and standard deviation of the training data errors in step S1 are calculated according to equations 4) and 5):
wherein the content of the first and second substances,
is the jth predictor, x, in the training datajIs the monitoring value corresponding to the jth predicted value, n is the total number of training data, E is the average value of the errors of the training data, and σ is the standard deviation of the errors of the training data.
In the above aspect, preferably, in step S2, if one of the two conditions in equation 6) is satisfied, the current monitored value is marked as an abnormal value,
wherein r is a positive integer and has a value range of [2,3 ]; e is the mean of the training data errors and σ is the standard deviation of the training data errors.
Preferably, in the above technical solution, the establishing of the characteristic value sequence in step S2 specifically includes: if the monitoring value at the current moment is an abnormal value, the numerical value inserted in the corresponding characteristic value sequence is the error of the current moment; otherwise, 0 is inserted.
In the above technical solution, preferably, in the step S3, if the mth term in the characteristic value sequence corresponds to an abnormal value, the first m terms of the current characteristic value sequence are taken to calculate the early warning index, the power law distribution function is used to calculate the current early warning index,
where e is a natural constant, γ is a real number greater than 0, dkIs the value of the k-th term of the sequence of characteristic values, tkIs the time difference between the monitored value k and the monitored value m.
Preferably, in the above technical solution, in the step S4, if the current early warning index f is greater than or equal to f0If yes, issuing a yellow early warning;
if the current early warning index f is more than or equal to f1Issuing an orange early warning;
if the current early warning index f is more than or equal to f2Issuing a red early warning;
wherein f is0Yellow early warning threshold, f1Orange early warning threshold, f2Is a red early warning threshold.
The technical scheme of the invention has the following beneficial effects:
according to the method, the abnormal monitoring data can be rapidly and accurately identified when the GNSS monitoring data is greatly deformed by adopting a double-index smoothing method; generating a predicted value and obtaining training data by a double-exponential smoothing method aiming at historical monitoring data, and counting the mean value and standard deviation of errors of the training data; and aiming at the current monitoring data, generating a predicted value at the current moment by a double-exponential smoothing method, calculating an error between the predicted value and a monitoring value at the current moment, and identifying abnormal data by calculating the error in a probability interval of the training data (namely comparing the error at the current moment with the average value and standard deviation of the error of the training data).
Because the GNSS data are time sequence data and have correlation in time, the early warning index at each moment can be calculated by introducing a time-distance attenuation function, and when the early warning index exceeds a set threshold value, the early warning information is sent in time. Meanwhile, the method for calculating the early warning index by combining the time-distance attenuation method can effectively eliminate the influence of gross error data and effectively avoid the problems of 'missed warning', 'late warning' and 'false warning'.
In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of the early warning method of the present invention;
FIG. 2 is a graph illustrating historical monitoring data and training data in a test case;
FIG. 3 is a schematic diagram of oscillation-type monitoring data and corresponding characteristic values in a test case;
FIG. 4 is a schematic diagram of oscillation-type monitoring data and corresponding early warning indexes in a test case;
FIG. 5 is a graph showing linear variation type monitoring data and corresponding characteristic values in the test case;
fig. 6 shows the linear variation type monitoring data and the corresponding pre-warning index in the test case.
Detailed Description
In order that the invention may be more fully understood, a more particular description of the invention will now be rendered by reference to specific embodiments thereof that are illustrated in the appended drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Example 1:
when using GNSS monitoring side slope, because the deformation of the side slope of monitoring has 3 stages: initial acceleration deformation stage, uniform speed deformation stage and acceleration deformation stage. The early warning is needed only in the acceleration deformation stage, the slope is usually in the first two stages during monitoring, most of data monitored by GNSS are normal data, and abnormal data generated during landslide are almost zero. However, the deformation is one of the important characteristics of landslide, and once the side slope is in the accelerated deformation stage, early warning information must be issued in time to avoid personnel and property loss caused by landslide accidents.
The early warning method of the embodiment trains the machine learning model through the normal value monitored by the GNSS, identifies whether the current state of the slope is stable or dangerous according to the normal GNSS monitoring data, and whether the slope is in a temporary slip stage (accelerated deformation stage), and carries out early warning in time according to the conclusion of model analysis. The early warning method of the embodiment comprises the following steps: generating training data, predicting a model, screening abnormal values, analyzing and early warning, and sending early warning information.
The abnormal value is data which does not conform to the change rule of the historical monitoring data, namely data which has larger change compared with the historical data, landslide information is contained in the abnormal value, but not all the abnormal values need to be pre-warned, and the abnormal monitoring value is possibly generated due to external environment change or internal component damage, so that analysis is needed according to the abnormal value to judge whether the abnormal value is a piece of data which needs to be pre-warned or is rough. The deformation of the side slope is a continuous process in time and space, and according to the first law of geography: anything is related to something, but something close to it is more closely related. Therefore, the method of the embodiment analyzes the abnormal data based on the time-distance attenuation rule.
Referring to fig. 1, a slope monitoring and early warning method based on GNSS includes the following steps:
step S1: aiming at historical monitoring data, a dual-exponential smoothing method is used, and a predicted value at the next moment after c monitoring values is estimated based on the c monitoring values before the time sequence each time; taking all the predicted values as training data, and calculating the average value and standard deviation of errors of the training data;
preferably, in step S1, the predicted value at the time after the c monitoring values is estimated based on the c monitoring values before the time series each time, specifically, the recursive calculation is performed according to formula 1) to formula 3), and the value of c is set manually:
si＝α·xi+(1-α)·(si-1+τi-1) Formula 1) below,
τi＝β·(si-si-1)+(1-β)·τi-1formula 2) below is given,
wherein x isiIs at time iMonitoring value, siIs the level at time i, si-1Is the level at time i-1, τiIs the trend at time i, τi-1Is the trend at time i-1,
is the predicted value at time i +1, α is the horizontal smoothing constant, and β is the trend smoothing constant. (for the convenience of understanding the method of this embodiment, the recursive computation in step S1 is illustrated here, assuming that the time series of the historical monitoring data is {. b.. g. }, c monitoring values are counted from b time to g time, b ≦ i ≦ g in the recursive computation, estimating the predicted value at g +1 time by using the monitoring values from b time to g time, where g +1 time includes the predicted value and the monitoring value, the set of predicted values obtained by analogy is the training data, where the difference between the predicted value and the monitoring value at the same time is the error, and further the average value and the standard deviation of the training data error can be obtained; the value of c is set manually, and c is greater than or equal to 3 and less than the total number of terms in the time series of the historical monitoring data)
Preferably, the mean and standard deviation of the error of the training data in step S1 are calculated according to equations 4) and 5):
wherein the content of the first and second substances,
is the jth predictor, x, in the training datajIs the monitor value corresponding to the jth predicted value, n is the total number of training data (i.e., the number of predicted values obtained from the historical data), E is the average of the training data errors, and σ is the standard deviation of the training data errors.
Step S2: for the current monitoring data, estimating a predicted value of the current moment based on the past c monitoring values by using a bi-exponential smoothing method, calculating an error between the predicted value of the current moment and the monitoring value of the current moment, comparing the error with the average value and the standard deviation of the training data errors in the step S1, judging whether the monitoring value of the current moment is an abnormal value, and establishing a characteristic value sequence;
estimating the predicted value of the current time based on the past c monitored values in step S2 is also based on formula 1) -formula 3), and performing recursive computation (for convenience of understanding the method of the present embodiment, the recursive computation in step S2 is exemplified here, assuming that the time series of the monitored values is {..... w }, where the time w is the current time, then estimating the predicted value of the time w based on the monitored values from the time w-c to the time w-1, where in the recursive computation, i is not less than w-1, and the difference between the predicted value and the monitored value at the time w is the error of the current time).
Preferably, in step S2, if one of the two conditions in equation 6) is satisfied, the current monitored value is marked as an abnormal value,
wherein r is a positive integer with a value range of [2,3]](ii) a E is the mean of the errors of the training data, and σ is the standard deviation of the errors of the training data; those skilled in the art can understand that in equation 6)
Expressed as the predicted value at the current time, xi+1The values are the monitoring values of the current time, and the corner marks i and i +1 represent the previous time and the next time.
The step S2 is executed to establish a sequence of eigenvalues { … di+1… } are specifically: if the monitored value at the current moment is an abnormal value, the numerical value inserted in the corresponding characteristic value sequence is the error of the current moment, namely
Otherwise insert 0, i.e. di+1＝0。
Step S3: calculating the current early warning index of the abnormal value according to the characteristic value sequence;
in step S3, if the mth term in the feature value sequence (the mth term in the actual calculation is the current term) corresponds to an abnormal value, the first mth term of the current feature value sequence is taken to calculate an early warning index, the power law distribution function is used to calculate the current early warning index,
where e is a natural constant, γ is a real number greater than 0, 0<γ<The attenuation speed of abnormal value, gamma, is reduced at 1>1 accelerates the decay rate of the abnormal value, dkIs the value of the k-th term of the sequence of characteristic values, tkIs the time difference between the monitored value k and the monitored value m, tk≥0。
Step S4: according to the early warning index, determining the early warning grade, specifically:
if the current early warning index f is more than or equal to f0If yes, issuing a yellow early warning;
if the current early warning index f is more than or equal to f1Issuing an orange early warning;
if the current early warning index f is more than or equal to f2Issuing a red early warning;
wherein f is0Yellow early warning threshold, f1Orange early warning threshold, f2A red early warning threshold; preferred in this embodiment f0>0，f1>f0，f2>f1。
Preferably, the monitored values in this embodiment refer to GNSS monitored values.
The concrete test cases applying the early warning method in the embodiment are as follows:
referring to fig. 2, 1400 pieces of GNSS monitored data are simulated by using random data, the fluctuation range of the monitored data value is [0,4], the unit is mm, the predicted value is calculated by a double-exponential smoothing method, training data is obtained, α is set to 0.05, β is set to 0.01, the mean value E of errors is calculated to 1.02371226, and the standard deviation σ of errors is set to 0.58563665.
And simulating 1500 data sets of monitoring data series1, inserting 60 monitoring data sets with the mean value of 5mm and the standard deviation of 0.5 after the 300 th data set, and inserting 60 monitoring data sets with the mean value of-1.5 mm and the standard deviation of 0.5 after the 420 th data set, so as to simulate the GNSS monitoring data with 'oscillation' change.
Simulation monitor data series2, for a total of 1500 data, insert 100 linearly increasing data after 1200 th data, simulate "linearly" varying GNSS monitor data.
Carrying out abnormal data identification and early warning judgment on the two kinds of simulation monitoring data, predicting by using a bi-exponential smoothing method, setting alpha to be 0.05 and beta to be 0.01, calculating the error between a predicted value and a monitored value at the current time, comparing the error with error data (namely E and sigma) generated by training data, and if the error data is not the error data, judging whether the error data is abnormal data or not
Or
The data is marked as anomalous data.
Referring to fig. 3 to 6, for the two types of analog monitoring data, a characteristic value sequence is generated according to the monitoring data and the abnormal data, an early warning index at each monitoring time is calculated, γ is set to be 0.0333, if f is greater than 15, a yellow early warning is issued, if f is greater than 20, an orange early warning is issued, and f is greater than 25, and a red early warning is issued.
As can be seen from fig. 3 and 5, the method of the present embodiment can accurately monitor the points with large deformation changes, including the gross error points and the real trend change points, so that the method will not "miss alarm". As can be seen from fig. 4 and 6, the time-distance decay algorithm can enhance the early warning index of the real trend change point, so that an obvious boundary is generated between the early warning index of the rough difference point and the early warning index of the real trend change point, and a false alarm is effectively avoided.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A slope monitoring and early warning method based on GNSS is characterized by comprising the following steps:
step S1: aiming at historical monitoring data, a dual-exponential smoothing method is used, and a predicted value at the next moment after c monitoring values is estimated based on the c monitoring values before the time sequence each time; taking all the predicted values as training data, and calculating the average value and standard deviation of errors of the training data;
step S2: for the current monitoring data, estimating a predicted value of the current moment based on the past c monitoring values by using a bi-exponential smoothing method, calculating an error between the predicted value of the current moment and the monitoring value of the current moment, comparing the error with the average value and the standard deviation of the training data errors in the step S1, judging whether the monitoring value of the current moment is an abnormal value, and establishing a characteristic value sequence;
step S3: calculating the current early warning index of the abnormal value according to the characteristic value sequence;
step S4: and determining the early warning grade according to the early warning index.
2. The GNSS-based slope monitoring and early warning method according to claim 1, wherein the step S1 of estimating the predicted value of the c monitoring values at the next moment based on the c monitoring values before the time sequence and the step S2 of estimating the predicted value of the current moment based on the past c monitoring values each time are recursively calculated according to formula 1) -formula 3):
si＝α·xi+(1-α)·(si-1+τi-1) Formula 1) below,
τi＝β·(si-si-1)+(1-β)·τi-1formula 2) below is given,
wherein x isiIs time iA monitored value of siIs the level at time i, si-1Is the level at time i-1, τiIs the trend at time i, τi-1Is the trend at time i-1,
is the predicted value at time i +1, α is the horizontal smoothing constant, and β is the trend smoothing constant.
3. The GNSS based slope monitoring and warning method according to claim 2, wherein the mean and standard deviation of the error of the training data in the step S1 are calculated according to the following equations 4) and 5):
wherein the content of the first and second substances,
is the jth predictor, x, in the training datajIs the monitoring value corresponding to the jth predicted value, n is the total number of training data, E is the average value of the errors of the training data, and σ is the standard deviation of the errors of the training data.
4. The GNSS-based slope monitoring and early warning method according to claim 3, wherein in step S2, if one of the two conditions in equation 6) is satisfied, the monitored value at the current time is marked as an abnormal value,
wherein r is a positive integer and has a value range of [2,3 ]; e is the mean of the training data errors and σ is the standard deviation of the training data errors.
5. The GNSS-based slope monitoring and early warning method according to claim 4, wherein the step S2 of establishing the eigenvalue sequence specifically comprises: if the monitoring value at the current moment is an abnormal value, the numerical value inserted in the corresponding characteristic value sequence is the error of the current moment; otherwise, 0 is inserted.
6. The GNSS-based slope monitoring and warning method according to any of claims 1-5, wherein in step S3, if the mth term in the eigenvalue sequence corresponds to an abnormal value, the top m terms of the current eigenvalue sequence are taken to calculate a warning index, the power law distribution function is used to calculate the current warning index,
where e is a natural constant, γ is a real number greater than 0, dkIs the value of the k-th term of the sequence of characteristic values, tkIs the time difference between the monitored value k and the monitored value m.
7. The GNSS-based slope monitoring and early warning method according to claim 6, wherein in the step S4, if the current early warning index f is larger than or equal to f0If yes, issuing a yellow early warning;
if the current early warning index f is more than or equal to f1Issuing an orange early warning;
if the current early warning index f is more than or equal to f2Issuing a red early warning;
wherein f is0Yellow early warning threshold, f1Orange early warning threshold, f2Is a red early warning threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111653395.1A CN114299693B (en) | 2021-12-30 | 2021-12-30 | GNSS-based slope monitoring and early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111653395.1A CN114299693B (en) | 2021-12-30 | 2021-12-30 | GNSS-based slope monitoring and early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114299693A true CN114299693A (en) | 2022-04-08 |
| CN114299693B CN114299693B (en) | 2023-07-04 |
Family
ID=80973118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111653395.1A Active CN114299693B (en) | 2021-12-30 | 2021-12-30 | GNSS-based slope monitoring and early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299693B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424415A (en) * | 2022-08-30 | 2022-12-02 | 安徽省新近纪防灾科技有限公司 | Landslide disaster intelligent early warning method based on GNSS real-time monitoring |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108195283A (en) * | 2017-12-04 | 2018-06-22 | 千寻位置网络有限公司 | GNSS real-time deformations monitoring method and system based on seamless transitions |
| CN108332696A (en) * | 2018-01-27 | 2018-07-27 | 中国地质科学院探矿工艺研究所 | landslide monitoring method selection method |
| 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 |
| CN110865425A (en) * | 2019-11-28 | 2020-03-06 | 中国有色金属长沙勘察设计研究院有限公司 | Rain gauge gross error detection method based on prior information |
| CN111784070A (en) * | 2020-07-09 | 2020-10-16 | 中国地质环境监测院 | Intelligent landslide short-term early warning method based on XGboost algorithm |
| CN111881127A (en) * | 2020-08-11 | 2020-11-03 | 华能澜沧江水电股份有限公司 | River basin bank slope detection data verification method and system based on polynomial coupling |
| CN112581725A (en) * | 2020-12-08 | 2021-03-30 | 重庆邮电大学 | Mountain landslide early warning monitoring system based on NBIOT and LoRa dual-mode communication |
| CN214308582U (en) * | 2020-12-24 | 2021-09-28 | 湖南省交通科学研究院有限公司 | Utilize side slope stability monitoring devices of difference in temperature power supply |
| CN113625645A (en) * | 2021-08-19 | 2021-11-09 | 福州大学 | Intelligent monitoring method and management system for rockfill concrete dam |
-
2021
- 2021-12-30 CN CN202111653395.1A patent/CN114299693B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108195283A (en) * | 2017-12-04 | 2018-06-22 | 千寻位置网络有限公司 | GNSS real-time deformations monitoring method and system based on seamless transitions |
| CN108332696A (en) * | 2018-01-27 | 2018-07-27 | 中国地质科学院探矿工艺研究所 | landslide monitoring method selection method |
| 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 |
| CN110865425A (en) * | 2019-11-28 | 2020-03-06 | 中国有色金属长沙勘察设计研究院有限公司 | Rain gauge gross error detection method based on prior information |
| CN111784070A (en) * | 2020-07-09 | 2020-10-16 | 中国地质环境监测院 | Intelligent landslide short-term early warning method based on XGboost algorithm |
| CN111881127A (en) * | 2020-08-11 | 2020-11-03 | 华能澜沧江水电股份有限公司 | River basin bank slope detection data verification method and system based on polynomial coupling |
| CN112581725A (en) * | 2020-12-08 | 2021-03-30 | 重庆邮电大学 | Mountain landslide early warning monitoring system based on NBIOT and LoRa dual-mode communication |
| CN214308582U (en) * | 2020-12-24 | 2021-09-28 | 湖南省交通科学研究院有限公司 | Utilize side slope stability monitoring devices of difference in temperature power supply |
| CN113625645A (en) * | 2021-08-19 | 2021-11-09 | 福州大学 | Intelligent monitoring method and management system for rockfill concrete dam |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424415A (en) * | 2022-08-30 | 2022-12-02 | 安徽省新近纪防灾科技有限公司 | Landslide disaster intelligent early warning method based on GNSS real-time monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114299693B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108508863A (en) | A kind of electromechanical equipment method for diagnosing faults based on gray model | |
| CN112348237B (en) | Abnormal trend detection method for dynamic drilling data | |
| CN102449645B (en) | Product inspection device and product inspection method | |
| CN114241741B (en) | Comprehensive early warning method and system applied to safety monitoring field | |
| CN104392122A (en) | Probabilistic life evaluation method based on crack detection probability model | |
| Wu et al. | Optimal np control chart with curtailment | |
| CN102393299A (en) | Method for quantitatively calculating operational reliability of rolling bearing | |
| CN114492980B (en) | Intelligent prediction method for corrosion risk of urban gas buried pipeline | |
| CN114299693A (en) | GNSS-based slope monitoring and early warning method | |
| CN109507992A (en) | A kind of failure prediction method, device and the equipment of locomotive braking system component | |
| CN106855990B (en) | Nuclear power unit instrument channel measurement error demonstration method | |
| CN117268455B (en) | Monitoring system of engineering construction quality detection equipment | |
| CN113962253B (en) | Bearing residual life prediction method and system based on depth wavelet extreme learning machine | |
| US20090024429A1 (en) | Graphical risk-based performance measurement and benchmarking system and method | |
| CN103134433A (en) | Method of identifying slip factors causing slope instability by utilizing displacement monitoring | |
| CN114693114A (en) | Monitoring method and device for underground space structure, computer equipment and storage medium | |
| CN113295212B (en) | Landslide overall stability safety early warning system applying multi-monitoring point synergistic effect | |
| CN101382474B (en) | Alarming method for bridge structure safety | |
| CN117132064A (en) | Liquid crystal display produces line operation management system based on thing networking | |
| CN116562437A (en) | Track circuit compensation capacitor fault prediction method and device | |
| CN111125965A (en) | Method and system for evaluating reliability of emergency regulation and control equipment under disaster-causing factor condition | |
| CN103376465A (en) | System and method for earthquake real-time analysis of building floor and storage medium | |
| Daniels et al. | Detection, localization, and quantification of single-source methane emissions on oil and gas production sites using point-in-space continuous monitoring systems | |
| Yadav et al. | Dynamic PRA with component aging and degradation modeled utilizing plant risk monitoring data | |
| Sharma et al. | Real-time prediction of extreme ambient carbon monoxide concentrations due to vehicular exhaust emissions using univariate linear stochastic models |
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 |