CN109766912A - A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines - Google Patents
A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines Download PDFInfo
- Publication number
- CN109766912A CN109766912A CN201811492025.2A CN201811492025A CN109766912A CN 109766912 A CN109766912 A CN 109766912A CN 201811492025 A CN201811492025 A CN 201811492025A CN 109766912 A CN109766912 A CN 109766912A
- Authority
- CN
- China
- Prior art keywords
- data
- influence factor
- covering
- period
- ice
- 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.)
- Withdrawn
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a kind of powerline ice-covering appraisal procedure based on Kalman filtering and support vector machines, comprising: obtains the powerline ice-covering influence factor and its corresponding ice coating state historical data of corresponding multiple periods;It is filtered to icing influence factor historical data is got;Using after filtering processing icing influence factor and its corresponding ice coating state data as training sample data, training SVM model;The powerline ice-covering influence factor data of period to be measured are obtained, and are filtered;The SVM model that period powerline ice-covering influence factor data to be measured input after filtering processing has been trained is assessed into the ice coating state of period transmission line of electricity to be measured according to the output of SVM model.Utilize filtering and support vector machines technology, realize that the fusion to multi-data source information relevant to powerline ice-covering optimizes, the limitation of single-sensor can be overcome, the developing direction for preferably transmission line of electricity having occurred event and further trend, makes more objective and accurately describes, assesses or predict.
Description
Technical field
The present invention relates to transmission of electricity security technology area, especially a kind of transmissions of electricity based on Kalman filtering and support vector machines
Transmission line icing
Background technique
It is well known that ice damage is one of threat the most serious in the various natural calamities that electric system is subjected to.With it
He compares accident, and ice damage is even more serious to loss caused by power grid, gently then leads to defeated, transformer equipment flashover tripping, fitting damage,
It is heavy then cause overhead transmission line broken string, shaft tower collapse, or even cause extensive area power grid paralyse.For commenting online for transmission facility
Estimate research it is less, Japanese Koichi Nara et al. establishes the ice-covering-proof Decision-making Expert System of 187kV and 66kV overhead transmission line, it
The meteorologic parameter (such as environment temperature, relative humidity, wind speed, snowfall) arrived using on-line measurement is to current overhead transmission line state
It judges, so which kind of anti-, deicing mode operations staff selects carry out process circuit icing.It studies in this respect very the country, China
It is few.Overhead transmission line icing is influenced by many factors, such as meteorologic factor, height above sea level, diameter of wire, electric field strength and mima type microrelief
Deng there is the complexity of height and non-linear between each factor and icing.Since there are technological deficiency and measuring technique be not smart
The factors such as true, current icing parametric classification method need to constantly improve to improve the accuracy of assessment, studies have shown that power transmission line
Road icing is affected by meteorologic factor, and especially environment temperature and relative humidity are formed with conclusive influence to icing.Cause
This, transmission line icing state not only has uncertainty, but also has the characteristics of multifactor impact.Simple data processing has been difficult to judge
The end-state of transmission line icing.
Summary of the invention
The technical problem to be solved in the present invention is, using filtering and support vector machines technology, realize to transmission line of electricity
The fusion of the relevant multi-data source information of icing optimizes, and the limitation of single-sensor is overcome, preferably to have sent out transmission line of electricity
It makes trouble the developing direction of part and further trend, makes more objective and accurately describe, assess or predict.
The technical scheme adopted by the invention is as follows: a kind of powerline ice-covering appraisal procedure, comprising:
Obtain the powerline ice-covering influence factor and its corresponding ice coating state historical data of corresponding multiple periods;
Each powerline ice-covering influence factor data of the day part got are filtered;
By the powerline ice-covering influence factor of the day part after filtering processing and its corresponding ice coating state data, as
Training sample data;
Utilize training sample data training SVM model;
The powerline ice-covering influence factor data of period to be measured are obtained, and are filtered;
Period powerline ice-covering influence factor data to be measured after filtering processing are inputted to the SVM model trained, are obtained
It is exported to SVM model;
According to the output of SVM model, the ice coating state of period transmission line of electricity to be measured is assessed.
The present invention filters out noise spot, the SVM model that training obtains can be improved by being filtered to sample data
Nicety of grading and reliability further increase the assessment knot of powerline ice-covering state in conjunction with the filtering processing to testing data
Fruit reliability.
Preferably, the powerline ice-covering influence factor include transmission line of electricity pulling force and inclination angle and ambient wind velocity,
Wind direction and atmospheric pressure P.
Preferably, the filtering processing to icing influence factor data includes:
Kalman filtering processing is carried out to the multiple data sequences for corresponding to single influence factor in the single period;
Intermediate value processing is carried out to Kalman filtering treated data sequence;
Average value processing is carried out to intermediate value treated data sequence, obtains the single influence factor data value of corresponding period.
Kalman filtering, median filtering and Mean Filtering Algorithm are combined, wave caused by accidentalia can be both overcome
Dynamic interference, and can have good filtration result to stepwise derivation signal, it can more accurately extract characteristic value.
Preferably, the training sample set (x of icing flashover is giveni,yi), i=1,2 ..., N, N are training sample number, defeated
Enter variable xi=(xi1, xi2..., xil) in include multiple icing influence factor characteristic quantity xij, yiFor corresponding i-th of training sample
Ice coating state amount;
It is described to include: using training sample data training SVM model
Hyperplane of the setting for two classification are as follows:
Wx+b=0
Wherein w is hyperplane method vector, and b is the constant term of hyperplane, and two class intervals, which are calculated, is
Seek optimal solution w using Lagrange multiplier method0And b0, so that Optimal Separating Hyperplane spacing is maximum, Lagrange function
Are as follows:
It is Lagrange multiplier that nonnegative variable a is assisted in formula;
The then dual problem of former quadratic programming problem are as follows:
Obtain optimal solution are as follows:
In formula, (x(s),y(s)) i.e. y(s)=1 corresponding training sample data;
Optimal solution is substituted into hyperplane equation to get optimal separating hyper plane;
Utilize discriminant function sgn (w0·x+b0) determining that ice coating state is classified, SVM output is 0 corresponding transmission line of electricity without covering
Ice, otherwise transmission line of electricity has icing.And then for the powerline ice-covering influence factor data of period to be measured, if by having trained
SVM model output be 0, then period transmission line of electricity to be measured is without icing, and otherwise icing has occurred in transmission line of electricity.It is subsequent can be according to commenting
Estimate the output that result carries out early warning.
Preferably, the period to be measured is present period or future time period, and the powerline ice-covering of period to be measured influences
Factor data is the measured data of present period or the prediction data of future time period.That is, the present invention can both realize to it is current when
Between powerline ice-covering status assessment, can also realize the prediction to the following powerline ice-covering state.To powerline ice-covering
The acquisition of the present period measured data of influence factor can be realized using sensor, be obtained to the prediction data of future time period, then
In combination with the prior art, the following corresponding period is predicted based on present period and historical correlation data.
Invention additionally discloses a kind of powerline ice-covering assessment systems, comprising:
Sample data acquisition module, for obtaining the powerline ice-covering influence factor of corresponding multiple periods and its corresponding
Ice coating state historical data;
Sample data filter module is carried out for each powerline ice-covering influence factor data to the day part got
Filtering processing;
Training sample determining module, for the powerline ice-covering influence factor of the day part after being filtered and its right
The ice coating state data answered, as training sample data;
Support vector machines training module, for utilizing training sample data training SVM model;
Characteristic quantity acquisition module to be measured for obtaining the powerline ice-covering influence factor data of period to be measured, and carries out
Filtering processing;
Icing evaluation module, for the period powerline ice-covering influence factor data to be measured input after being filtered
Trained SVM model obtains the output of SVM model;According to the output of SVM model, the icing shape of period transmission line of electricity to be measured is assessed
State.
Beneficial effect
Compared with prior art, the present invention has the following advantages that and improves:
1) by being filtered to sample data, noise spot is filtered out, the classification for the SVM model that training obtains can be improved
Precision and reliability, in conjunction with the filtering processing to testing data, the assessment result for further increasing powerline ice-covering state can
By property;
3) situation more for the original data volume of sensor monitoring platform online real time collecting, the present invention utilize intermediate value
Interference is fluctuated in method filtering caused by effectively overcoming because of accidentalia, while being made using averaging method to random stepwise derivation signal
The characteristic accuracy that must be extracted is high, can effectively reduce error;
2) for training sample data point it is extremely more in the case where, support vector machines solves classification problem using optimal hyperlane
Advantage embodied, icing discrimination precision can be significantly improved.
Detailed description of the invention
Fig. 1 show the method for the present invention flow diagram;
Fig. 2 show support vector cassification schematic diagram;
Fig. 3 show support vector cassification model schematic.
Specific embodiment
It is further described below in conjunction with the drawings and specific embodiments.
Embodiment 1
With reference to Fig. 1, the present embodiment is powerline ice-covering appraisal procedure, comprising:
Obtain the powerline ice-covering influence factor and its corresponding ice coating state historical data of corresponding multiple periods;
Each powerline ice-covering influence factor data of the day part got are filtered;
By the powerline ice-covering influence factor of the day part after filtering processing and its corresponding ice coating state data, as
Training sample data;
Utilize training sample data training SVM model;
The powerline ice-covering influence factor data of period to be measured are obtained, and are filtered;
Period powerline ice-covering influence factor data to be measured after filtering processing are inputted to the SVM model trained, are obtained
It is exported to SVM model;
According to the output of SVM model, the ice coating state of period transmission line of electricity to be measured is assessed.
The powerline ice-covering influence factor include transmission line of electricity pulling force and inclination angle and ambient wind velocity, wind direction and
Atmospheric pressure.
The filtering processing to icing influence factor data includes:
Kalman filtering processing is carried out to the multiple data sequences for corresponding to single influence factor in the single period;
Intermediate value processing is carried out to Kalman filtering treated data sequence;
Average value processing is carried out to intermediate value treated data sequence, obtains the single influence factor data value of corresponding period.
Kalman filtering, median filtering and Mean Filtering Algorithm are combined, wave caused by accidentalia can be both overcome
Dynamic interference, and can have good filtration result to stepwise derivation signal, it can more accurately extract characteristic value.
Kalman filtering, median filtering and mean filter are all existing algorithm.
Training sample set (the x of given icing flashoveri,yi), i=1,2 ..., N, N are training sample number, input variable
xi=(xi1, xi2..., xil) in include multiple icing influence factor characteristic quantity xij, yiFor the icing of corresponding i-th of training sample
Quantity of state;
It is described to solve the largest interval between two class data using training sample data training SVM model, it determines optimal
Optimal Separating Hyperplane, comprising:
Hyperplane of the setting for two classification are as follows:
Wx+b=0
Wherein w is hyperplane method vector, and b is the constant term of hyperplane, by:
It is derived by two class intervals are as follows:
With reference to Fig. 2, x in formula1、x2Respectively wxi+ b=-1, yi=-1 and wxi+ b=1, yiAny point on=1;
Based on wxi+ b=1, yi=1, seek optimal solution w using Lagrange multiplier method0And b0, so that Optimal Separating Hyperplane
Spacing is maximum, Lagrange function are as follows:
It is Lagrange multiplier that nonnegative variable a is assisted in formula;
The then dual problem of former quadratic programming problem are as follows:
Dual problem is entirely to be expressed according to training data, and the maximization of function Q (a) only relies upon input pattern point
Long-pending setOptimal solution can be obtained are as follows:
Optimal solution is substituted into hyperplane equation to get optimal separating hyper plane;
Utilize discriminant function sgn (w0·x+b0) determining that ice coating state is classified, SVM output is 0 corresponding transmission line of electricity without covering
Ice, otherwise transmission line of electricity has icing.And then for the powerline ice-covering influence factor data of period to be measured, if by having trained
SVM model output be 0, then period transmission line of electricity to be measured is without icing, and otherwise icing has occurred in transmission line of electricity.It is subsequent can be according to commenting
Estimate the output that result carries out early warning.
, can be first by Nonlinear Mapping to higher dimensional space for lower dimensional space sample, then solve optimal separating hyper plane.
The period to be measured is present period or future time period, the powerline ice-covering influence factor data of period to be measured
For the measured data of present period or the prediction data of future time period.That is, the present invention can both realize the transmission of electricity to current time
Transmission line icing status assessment can also realize the prediction to the following powerline ice-covering state.To powerline ice-covering influence factor
The acquisition of present period measured data can be realized using sensor, the prediction data of future time period is obtained, then in combination with existing
There is technology, the following corresponding period is predicted based on present period and historical correlation data.
Embodiment 2
The present embodiment is a kind of powerline ice-covering assessment system, comprising:
Sample data acquisition module, for obtaining the powerline ice-covering influence factor of corresponding multiple periods and its corresponding
Ice coating state historical data;
Sample data filter module is carried out for each powerline ice-covering influence factor data to the day part got
Filtering processing;
Training sample determining module, for the powerline ice-covering influence factor of the day part after being filtered and its right
The ice coating state data answered, as training sample data;
Support vector machines training module, for utilizing training sample data training SVM model;
Characteristic quantity acquisition module to be measured for obtaining the powerline ice-covering influence factor data of period to be measured, and carries out
Filtering processing;
Icing evaluation module, for the period powerline ice-covering influence factor data to be measured input after being filtered
Trained SVM model obtains the output of SVM model;According to the output of SVM model, the icing shape of period transmission line of electricity to be measured is assessed
State.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The embodiment of the present invention is described in conjunction with attached drawing above, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (6)
1. a kind of powerline ice-covering appraisal procedure, characterized in that include:
Obtain the powerline ice-covering influence factor and its corresponding ice coating state historical data of corresponding multiple periods;
Each powerline ice-covering influence factor data of the day part got are filtered;
By the powerline ice-covering influence factor of the day part after filtering processing and its corresponding ice coating state data, as training
Sample data;
Utilize training sample data training SVM model;
The powerline ice-covering influence factor data of period to be measured are obtained, and are filtered;
Period powerline ice-covering influence factor data to be measured after filtering processing are inputted to the SVM model trained, obtain SVM
Model output;
According to the output of SVM model, the ice coating state of period transmission line of electricity to be measured is assessed.
2. according to the method described in claim 1, it is characterized in that, the powerline ice-covering influence factor includes transmission line of electricity
Pulling force and inclination angle and ambient wind velocity, wind direction and atmospheric pressure.
3. according to the method described in claim 1, it is characterized in that, the filtering processing to icing influence factor data includes:
Kalman filtering processing is carried out to the multiple data sequences for corresponding to single influence factor in the single period;
Intermediate value processing is carried out to Kalman filtering treated data sequence;
Average value processing is carried out to intermediate value treated data sequence, obtains the single influence factor data value of corresponding period.
4. according to the method described in claim 1, it is characterized in that, give training sample set (xi,yi), i=1,2 ..., N, N are
Training sample number, input variable xi=(xi1, xi2..., xil) in include multiple icing influence factor characteristic quantity xij, yiIt is right
Answer the ice coating state amount of i-th of training sample;
It is described to include: using training sample data training SVM model
Hyperplane of the setting for two classification are as follows:
Wx+b=0
Wherein w is hyperplane method vector, and b is the constant term of hyperplane, and two class intervals, which are calculated, is
Seek optimal solution w using Lagrange multiplier method0And b0, so that Optimal Separating Hyperplane spacing is maximum, Lagrange function are as follows:
It is Lagrange multiplier that nonnegative variable a is assisted in formula;
The then dual problem of former quadratic programming problem are as follows:
Obtain optimal solution are as follows:
In formula, (x(s),y(s)) i.e. y(s)=1 corresponding training sample data;
Optimal solution is substituted into hyperplane equation to get optimal separating hyper plane;
Utilize discriminant function sgn (w0·x+b0) determining that ice coating state is classified, SVM output is 0 corresponding transmission line of electricity without icing, no
Then transmission line of electricity has icing.
5. according to the method described in claim 1, it is characterized in that, the period to be measured be present period or future time period, to
The powerline ice-covering influence factor data for surveying the period are the measured data of present period or the prediction data of future time period.
6. a kind of powerline ice-covering assessment system, characterized in that include:
Sample data acquisition module, for obtaining the powerline ice-covering influence factor for corresponding to multiple periods and its corresponding icing
Status history data;
Sample data filter module is filtered for each powerline ice-covering influence factor data to the day part got
Processing;
Training sample determining module, for the powerline ice-covering influence factor of the day part after being filtered and its corresponding
Ice coating state data, as training sample data;
Support vector machines training module, for utilizing training sample data training SVM model;
Characteristic quantity acquisition module to be measured for obtaining the powerline ice-covering influence factor data of period to be measured, and is filtered
Processing;
And icing evaluation module, for the period powerline ice-covering influence factor data to be measured input after being filtered
Trained SVM model obtains the output of SVM model;According to the output of SVM model, the icing shape of period transmission line of electricity to be measured is assessed
State.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811492025.2A CN109766912A (en) | 2018-12-07 | 2018-12-07 | A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811492025.2A CN109766912A (en) | 2018-12-07 | 2018-12-07 | A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109766912A true CN109766912A (en) | 2019-05-17 |
Family
ID=66451287
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811492025.2A Withdrawn CN109766912A (en) | 2018-12-07 | 2018-12-07 | A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109766912A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598932A (en) * | 2019-09-11 | 2019-12-20 | 电子科技大学 | Weather feature fusion-based power transmission corridor icing early warning method |
CN110633851A (en) * | 2019-09-11 | 2019-12-31 | 电子科技大学 | Power transmission corridor icing early warning method based on multi-source data |
CN111652713A (en) * | 2020-07-01 | 2020-09-11 | 中国银行股份有限公司 | Equity wind control modeling method and device |
CN112270327A (en) * | 2020-10-19 | 2021-01-26 | 西安工程大学 | Power transmission conductor icing classification method based on local fusion frequency domain characteristics |
CN113450573A (en) * | 2020-03-25 | 2021-09-28 | 重庆翼动科技有限公司 | Traffic monitoring method and traffic monitoring system based on unmanned aerial vehicle image recognition |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361414A (en) * | 2014-11-24 | 2015-02-18 | 武汉大学 | Power transmission line icing prediction method based on relevance vector machine |
CN105160599A (en) * | 2015-09-17 | 2015-12-16 | 上海电力学院 | Power line icing assessment method based on filtering and support vector machine |
CN108133225A (en) * | 2017-10-23 | 2018-06-08 | 南京南瑞集团公司 | A kind of icing flashover fault early warning method based on support vector machines |
-
2018
- 2018-12-07 CN CN201811492025.2A patent/CN109766912A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361414A (en) * | 2014-11-24 | 2015-02-18 | 武汉大学 | Power transmission line icing prediction method based on relevance vector machine |
CN105160599A (en) * | 2015-09-17 | 2015-12-16 | 上海电力学院 | Power line icing assessment method based on filtering and support vector machine |
CN108133225A (en) * | 2017-10-23 | 2018-06-08 | 南京南瑞集团公司 | A kind of icing flashover fault early warning method based on support vector machines |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110598932A (en) * | 2019-09-11 | 2019-12-20 | 电子科技大学 | Weather feature fusion-based power transmission corridor icing early warning method |
CN110633851A (en) * | 2019-09-11 | 2019-12-31 | 电子科技大学 | Power transmission corridor icing early warning method based on multi-source data |
CN110598932B (en) * | 2019-09-11 | 2022-04-19 | 电子科技大学 | Weather feature fusion-based power transmission corridor icing early warning method |
CN110633851B (en) * | 2019-09-11 | 2022-04-19 | 电子科技大学 | Power transmission corridor icing early warning method based on multi-source data |
CN113450573A (en) * | 2020-03-25 | 2021-09-28 | 重庆翼动科技有限公司 | Traffic monitoring method and traffic monitoring system based on unmanned aerial vehicle image recognition |
CN111652713A (en) * | 2020-07-01 | 2020-09-11 | 中国银行股份有限公司 | Equity wind control modeling method and device |
CN111652713B (en) * | 2020-07-01 | 2024-02-27 | 中国银行股份有限公司 | Equity wind control modeling method and device |
CN112270327A (en) * | 2020-10-19 | 2021-01-26 | 西安工程大学 | Power transmission conductor icing classification method based on local fusion frequency domain characteristics |
CN112270327B (en) * | 2020-10-19 | 2023-03-14 | 西安工程大学 | Power transmission conductor icing classification method based on local fusion frequency domain characteristics |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109766912A (en) | A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines | |
US20190285517A1 (en) | Method for evaluating health status of mechanical equipment | |
EP3422518B1 (en) | A method for recognizing contingencies in a power supply network | |
CN107765347A (en) | A kind of Gaussian process returns and the short-term wind speed forecasting method of particle filter | |
CN103487682A (en) | Method for early warning of sensitive client electric energy experience quality under voltage dip disturbance | |
EP3422517B1 (en) | A method for recognizing contingencies in a power supply network | |
CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
CN108562821B (en) | Method and system for determining single-phase earth fault line selection of power distribution network based on Softmax | |
CN112187528B (en) | Industrial control system communication flow online monitoring method based on SARIMA | |
CN104899135A (en) | Software defect prediction method and system | |
CN106656669B (en) | A kind of device parameter abnormality detection system and method based on threshold adaptive setting | |
CN103941131A (en) | Transformer fault detecting method based on simplified set unbalanced SVM (support vector machine) | |
CN113821938B (en) | Short-term prediction method and device for metering error state of mutual inductor | |
CN102495949A (en) | Fault prediction method based on air data | |
CN106649755A (en) | Threshold self-adaption setting abnormity detection method for multi-dimensional real-time power transformation device data | |
US20230118175A1 (en) | Event analysis in an electric power system | |
CN111311027A (en) | Wind speed prediction method for power transmission line | |
CN105488335A (en) | Lyapunov exponent based power system load prediction method and apparatus | |
CN111639583A (en) | Method and system for identifying power quality disturbance of power grid | |
CN106291236A (en) | Current limiter fault detection method based on transient fault row ripple | |
Liu et al. | Dynamic security assessment of western Danish power system based on ensemble decision trees | |
CN106787180B (en) | A kind of analysis method and device of power transmission and transformation Condition Monitoring Data | |
CN104730384A (en) | Power disturbance identification and localization method based on incomplete S transformation | |
CN107271024A (en) | A kind of load ratio bridging switch diagnostic method and device | |
CN117494026B (en) | Method, system and storage medium for positioning icing fault of power transmission line under cold and tidal weather |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190517 |