CN109557420A - A kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm - Google Patents
A kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm Download PDFInfo
- Publication number
- CN109557420A CN109557420A CN201811549694.9A CN201811549694A CN109557420A CN 109557420 A CN109557420 A CN 109557420A CN 201811549694 A CN201811549694 A CN 201811549694A CN 109557420 A CN109557420 A CN 109557420A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- subordinate
- failure
- nearest neighbor
- value
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
Abstract
The invention discloses a kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm, the following steps are included: 1) to the failure that judges of needs be subordinate to angle value with the icing for having clear icing classification be subordinate to angle value using k-nearest neighbor algorithm together with training sample, and judge the state of transmission line of electricity, training method are as follows: a little Euclidean distance with known point need to be differentiated by finding out；2) setting judges the upper limit value k1 and lower limit value k2 in section；3) as D (x, y, z) < k1, route is in unfaulty conditions；As k1≤D (x, y, z)≤k2, transmission line of electricity is in incipient fault state；As D (x, y, z) > k2, transmission line of electricity is in malfunction.Compared with prior art, the present invention has many advantages, such as that convenience of calculation, prediction are accurate.
Description
Technical field
The present invention relates to one kind to belong to overhead power transmission more particularly, to a kind of fault distinguishing method of overhead transmission line
The state on_line monitoring technical field of route.
Background technique
Overhead transmission line is all exposed among the Nature, is influenced by environment, meteorology, it may appear that many failures, and ice
Snow disaster evil is one of disaster the most serious in all kinds of harm that electric system is subjected to.Especially the north and high altitude localities,
Ice damage seriously threatens safe operation of power system, and ice insulator is gently then caused to dodge tripping, the tripping of alternate flashover and conducting wire substantially
The period that can the restore electricity shorter major accident such as wave, it is heavy then cause shaft tower inclination even to be collapsed, line hardware it is badly damaged
With conducting wire brittle failure ground connection etc. the period longer serious accident that can restore electricity.Powerline ice-covering accident is destroyed great efforts, is involved
It is wide and suffer heavy losses, heavy losses and influence are caused on national economy.
Extensive concern, such as " instrumental technique " 2016 have been obtained for overhead transmission line accident due to caused by icing
Year 1 is interim, in the content of open " powerline ice-covering monitoring system characteristic extracts research algorithm ", proposes a kind of intermediate value-
The comprehensive algorithm extracted of mean value, interim in " instrumental technique " 2016 1, open " information merges mould under powerline ice-covering state
The Research on classifying method of type characteristic layer " content in, the method for handy BP mind network and support vector machines improves processing data
Accuracy.But on the whole, current icing on-line monitoring technique needs to constantly improve to improve the accuracy of assessment, and
The time for shortening calculation processing mass data judges the failure for again as far as possible, carries out troubleshooting, reduction ice in time
Snow disaster evil bring loss.
Summary of the invention
It is a kind of fast and convenient and accurately to transmission line malfunction the technical problem to be solved by the present invention is to be capable of providing
It carries out sentencing method for distinguishing.
In order to solve the above technical problems, the present invention provides a kind of transmission line of electricity based on k-nearest neighbor algorithm
Fault distinguishing method, comprising the following steps:
1) failure judged needs, which is subordinate to angle value and has the icing of clear icing classification to be subordinate to angle value, utilizes k-nearest
Neighbor algorithm training sample together, and judge the state of transmission line of electricity, training method are as follows: point G (x need to be differentiated by finding outi,
yi,zi) with the Euclidean distance D (x, y, z) of known point；
2) setting judges the upper limit value k1 and lower limit value k2 in section,
3) as D (x, y, z) < k1, route is in unfaulty conditions；
As k1≤D (x, y, z)≤k2, transmission line of electricity is in incipient fault state；
As D (x, y, z) > k2, transmission line of electricity is in malfunction；
Wherein, 0 < k1 < n；0 < k2 < n, n indicate n group data.
According to a kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm above-mentioned, the need
The failure to be judged is subordinate to angle value by obtaining through lower step:
1) using temperature sensor, angular transducer, tension sensor to the conductor temperature of transmission line of electricity, conducting wire inclination angle and
Pulling force is sampled, and calculates corresponding conductor temperature deviation v1(k), conducting wire inclination deviation value v2(l) and wire tension deviation
Value v3(m), k, l, m are respectively the temperature deviation of certain point, conducting wire inclination deviation, wire tension deviation coordinate；
2) according to conductor temperature deviation v1(k), conducting wire inclination deviation value v2(l) and wire tension deviation v3(m) it calculates
It has corresponding failure and is subordinate to angle value, and judges that conductor temperature failure is subordinate to angle value, conducting wire inclination angle failure is subordinate to angle value, wire tension
Failure is subordinate to whether angle value is 0, if it has, then the failure for being not required to judgement is subordinate to angle value, if it has not, being then to need to judge
Failure be subordinate to angle value.
The above-mentioned kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm,
The Euclidean distance of k-nearest neighbor algorithm are as follows:
D (x, y, z) is Euclidean distance；(xi,yi,zi) it is i-th point of coordinate；X is conductor temperature deviation coordinate, and y is
Conducting wire inclination deviation value coordinate, z are wire tension deviation coordinate, wherein xn, yn, znFor wait judge a coordinate, remaining is
Know state point coordinate.
Compared with prior art, beneficial effect of the present invention is: the present invention is theoretical mature, and actual algorithm is realized more
It is easy that not only there is uncertainty due to transmission line icing state, but also has the characteristics of multifactor impact, the present invention is online with transmission line of electricity
Based on monitoring system, comprehensively considers environment temperature, route pulling force and tilt angle parameter, propose based on k-nearest
The transmission line malfunction method of discrimination of neighbor algorithm, transmission line wire monitoring system can timely obtain the shape of route
State information, calculating process is simple, but processing result accuracy significantly improves, and the timely early warning before transmission line malfunction occurs is given
Staff goes process circuit problem more times, can be effectively reduced the incidence of line fault, improves the benefit of equipment
With rate, computer disposal efficiency can be substantially saved.
Detailed description of the invention
Fig. 1 is that the present invention is based on the transmission line status assessment models block diagrams of k-nearest neighbor algorithm；
Fig. 2 is present invention assessment design cycle.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
As shown in Figure 1, transmission line status assessment models are using k-nearest neighbor algorithm training local fault
It is subordinate to angle value, and is classified by calculating distance, and provide the end-state of line fault, state outcome is fault-free, dives
In failure, failure.
A kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm, as shown in Fig. 2, method packet
Include following steps:
1) conductor temperature of transmission line of electricity, conducting wire inclination angle and pulling force are sampled, and it is inclined to calculate corresponding conductor temperature
Difference v1(k), conducting wire inclination deviation value v2(l) and wire tension deviation v3(m)；
2) according to conductor temperature deviation v1(k), conducting wire inclination deviation value v2(l) and wire tension deviation v3(m) it calculates
It has corresponding failure and is subordinate to angle value, and judges that conductor temperature failure is subordinate to angle value, conducting wire inclination angle failure is subordinate to angle value, wire tension
Failure is subordinate to whether angle value is 0, if it has not, thening follow the steps 3), if it has, then return step 1)；
3) failure judged needs, which is subordinate to angle value and has the icing of clear icing classification to be subordinate to angle value, utilizes k-nearest
Neighbor algorithm training sample together, and judge the state of transmission line of electricity, training method are as follows: point G (x need to be differentiated by finding outi,
yi,zi) with the Euclidean distance of known point；
Wherein, the Euclidean distance of k-nearest neighbor algorithm are as follows:
D (x, y, z) is Euclidean distance；(xi, yi, zi) it is i-th point of coordinate；X is conductor temperature deviation coordinate, and y is
Conducting wire inclination deviation value coordinate, z are wire tension deviation coordinate, wherein xn, yn, znFor wait judge a coordinate, remaining is
Know state point coordinate；
By taking Euclidean distance as an example, then need to differentiate point G (xi, yi, zi) at a distance from known point be
Setting judges the upper limit value k1 and lower limit value k2 in section,
As D (x, y, z) < k1, route is in unfaulty conditions；
As k1≤D (x, y, z)≤k2, transmission line of electricity is in incipient fault state；
As D (x, y, z) > k2, transmission line of electricity is in malfunction,
Wherein, 0 < k1 < n；0 < k2 < n, n indicate n group data.
In the step 2), the failure of conductor temperature is subordinate to angle value are as follows:
μ(V1)=u [v1(k)-D1]
Wherein: u [] is unit jump function, D1For the decision threshold of conductor temperature；
The decision threshold D of conductor temperature1Value range be -40 DEG C to 40 DEG C.
The failure at conducting wire inclination angle is subordinate to angle value are as follows:
μ(V2)=u [v2(l)-D2]
Wherein: D2For the decision threshold at conducting wire inclination angle；The decision threshold D at conducting wire inclination angle2Value range be 0-360 degree.
The failure of wire tension is subordinate to angle value are as follows:
μ(V3)=u [v3(m)-D3]
Wherein: D3For the decision threshold of wire tension.The decision threshold D of wire tension3Value range be D3 > 0.
Above-mentioned 3 decision thresholds are determined according to the specification of conducting wire.Table 1 is that the training of k-nearest neighbor algorithm is sentenced
Other table.
Table 1
In table 1, temperature, pulling force, inclination angle constitutes a three-dimensional space, D1, D2Deng being all known point in space, icing
Classification is it is known that DnFor the point of state to be judged, icing classification is unknown.By giving specific k1, k2 value, and thus differentiate to
Seek ice coating state a little.
Since line fault is affected by many factors, it is difficult to establish specific analytic modell analytical model between influence factor and failure.
Single factors assessment accuracy rate is not high, and in order to improve the accuracy rate of Guangdong power system status assessment, the present invention is with transmission line of electricity
Based on on-line monitoring system, the multi-sensor monitorings parameters such as temperature signal, dip angle signal, pulling force signal are comprehensively considered, propose
Transmission line status assessment models based on k-nearest neighbor algorithm.Pretreatment meter is carried out to monitoring data first
It calculates local fault and is subordinate to angle value, k- is then inputted by the angle value that is subordinate to for being subordinate to angle value and state to be measured of known state
Nearest neighbor algorithm, which calculates training and finds out, differentiates distance k1, k2, finally, complex reasoning goes out the malfunction of route.
Intelligent transmission line status assessment may be implemented in this method, and assessment result efficiency greatly improves.
The above is only the preferred embodiment for the present invention, it is noted that those of ordinary skill in the art is come
It says, under the premise of not departing from the technology of the present invention principle, several improvement and deformations can also be made, these improvement and deformations should also regard
For the scope of the present invention.
Claims (7)
1. a kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm, comprising the following steps:
1) failure judged needs, which is subordinate to angle value and has the icing of clear icing classification to be subordinate to angle value, utilizes k-nearest
Neighbor algorithm training sample together, and judge the state of transmission line of electricity, training method are as follows: point G (x need to be differentiated by finding outi,
yi,zi) with the Euclidean distance D (x, y, z) of known point；
2) setting judges the upper limit value k1 and lower limit value k2 in section,
3) as D (x, y, z) < k1, route is in unfaulty conditions；
As k1≤D (x, y, z)≤k2, transmission line of electricity is in incipient fault state；
As D (x, y, z) > k2, transmission line of electricity is in malfunction；
Wherein, 0 < k1 < n；0 < k2 < n, n indicate n group data.
2. a kind of transmission line malfunction differentiation side based on k-nearest neighbor algorithm according to claim 1
Method, it is characterised in that: described that the failure judged is needed to be subordinate to angle value by obtaining through lower step:
1) using temperature sensor, angular transducer, tension sensor to the conductor temperature of transmission line of electricity, conducting wire inclination angle and pulling force
It is sampled, and calculates corresponding conductor temperature deviation v1(k), conducting wire inclination deviation value v2(l) and wire tension deviation v3
(m), k, l, m are respectively the temperature deviation of certain point, conducting wire inclination deviation, wire tension deviation coordinate；
2) according to conductor temperature deviation v1(k), conducting wire inclination deviation value v2(l) and wire tension deviation v3(m) it calculates pair
The failure answered is subordinate to angle value, and judges that conductor temperature failure is subordinate to angle value, conducting wire inclination angle failure is subordinate to angle value, wire tension failure
It is subordinate to whether angle value is 0, if it has, then the failure for being not required to judgement is subordinate to angle value, if it has not, the event then judged for needs
Barrier is subordinate to angle value.
3. the according to claim a kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm,
It is characterized by:
The Euclidean distance of k-nearest neighbor algorithm are as follows:
D (x, y, z) is Euclidean distance；(xi,yi,zi) it is i-th point of coordinate；X is conductor temperature deviation coordinate, and y is conducting wire
Inclination deviation value coordinate, z are wire tension deviation coordinate, wherein xn, yn, znFor wait judge a coordinate, remaining is known shape
State point coordinate.
4. the according to claim 2 kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm,
It is characterized by: the failure of conductor temperature is subordinate to angle value in the step 2) are as follows:
μ(V1)=u [v1(k)-D1]
Wherein: u [] is unit jump function, D1For the decision threshold of conductor temperature；
The failure at conducting wire inclination angle is subordinate to angle value are as follows:
μ(V2)=u [v2(l)-D2]
Wherein: D2For the decision threshold at conducting wire inclination angle；
The failure of wire tension is subordinate to angle value are as follows:
μ(V3)=u [v3(m)-D3]
Wherein: D3For the decision threshold of wire tension.
5. the according to claim 4 kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm,
It is characterized by: the decision threshold D of conductor temperature1Value range be -40 DEG C to 40 DEG C.
6. the according to claim 4 kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm,
It is characterized by: the decision threshold D at conducting wire inclination angle2Value range be 0-360 degree.
7. the according to claim 4 kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm,
It is characterized by: the decision threshold D of wire tension3Value range be D3 > 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549694.9A CN109557420A (en) | 2018-12-18 | 2018-12-18 | A kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549694.9A CN109557420A (en) | 2018-12-18 | 2018-12-18 | A kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109557420A true CN109557420A (en) | 2019-04-02 |
Family
ID=65870503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811549694.9A Pending CN109557420A (en) | 2018-12-18 | 2018-12-18 | A kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109557420A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062569A (en) * | 2019-11-15 | 2020-04-24 | 南京天能科创信息科技有限公司 | Low-current fault discrimination method based on BP neural network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318485A (en) * | 2014-09-30 | 2015-01-28 | 上海电力学院 | Power transmission line fault identification method based on nerve network and fuzzy logic |
| CN108008252A (en) * | 2017-11-29 | 2018-05-08 | 广东电网有限责任公司电力科学研究院 | A kind of transmission line malfunction type diagnostic method and apparatus |
-
2018
- 2018-12-18 CN CN201811549694.9A patent/CN109557420A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318485A (en) * | 2014-09-30 | 2015-01-28 | 上海电力学院 | Power transmission line fault identification method based on nerve network and fuzzy logic |
| CN108008252A (en) * | 2017-11-29 | 2018-05-08 | 广东电网有限责任公司电力科学研究院 | A kind of transmission line malfunction type diagnostic method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 姚旭 等: "面向智能变电站的输电线路综合故障定位方法研究", 《电力系统保护与控制》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062569A (en) * | 2019-11-15 | 2020-04-24 | 南京天能科创信息科技有限公司 | Low-current fault discrimination method based on BP neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105353268B (en) | One kind is used for the judgement of transmission line of electricity distribution traveling wave fault and localization method | |
| CN104977930B (en) | High pressure same tower double back transmission line unmanned plane inspection barrier-avoiding method based on electric field strength change rate | |
| CN102435912B (en) | Method for positioning fault disturbance point in power grid | |
| CN104217253B (en) | Distribution line load reliability analyzing method under typhoon weather | |
| CN109655713B (en) | Single-phase earth fault positioning method and system | |
| CN104898696A (en) | Unmanned-plane routing-inspection obstacle avoidance method for high-voltage common-tower single-circuit transmission line based on change rate of intensity of electric field | |
| CN104578053B (en) | Power system transient stability Forecasting Methodology based on disturbed voltage trace bunch feature | |
| CN104820168A (en) | Lightning stroke fault determination method based on waveform difference degree and lightning stroke fault sample database | |
| CN109214675A (en) | A kind of powerline ice-covering methods of risk assessment | |
| CN104808088A (en) | Lightning shielding failure and counterattack recognition method based on lightning positioning system records and circuit travelling wave data | |
| CN105403807A (en) | Intelligent method for fault section recognition of three-segment cable mixed direct current power transmission line | |
| CN109766912A (en) | A kind of powerline ice-covering appraisal procedure and system based on Kalman filtering and support vector machines | |
| CN106485333A (en) | A kind of transmission line of electricity running status appraisal procedure | |
| CN112881855A (en) | High-voltage direct-current transmission line lightning stroke interference identification method based on generalized S transformation | |
| CN111126672A (en) | High-voltage overhead transmission line typhoon disaster prediction method based on classification decision tree | |
| CN105738772A (en) | Compulsory disturbance source positioning method based on power and frequency fluctuation phase | |
| CN109557420A (en) | A kind of transmission line malfunction method of discrimination based on k-nearest neighbor algorithm | |
| CN105162094A (en) | Ultra-high voltage DC line pilot protection method by using electrode line fault current curve family main component analysis | |
| CN107179473A (en) | A kind of power transmission line fault locating method | |
| CN111797545A (en) | Wind turbine generator yaw reduction coefficient calculation method based on measured data | |
| CN103364669A (en) | Online detecting method and system for GIS (Gas Insulated Switchgear) device operating state | |
| CN105160594A (en) | Power transmission line icing status evaluation method | |
| CN114371364A (en) | Short-circuit fault judgment method based on load end positive sequence voltage amplitude variation | |
| CN110380389B (en) | Novel hybrid compensation line transient state quantity direction protection method based on two-dimensional judgment plane | |
| CN113689053A (en) | Strong convection weather overhead line power failure prediction method based on random forest |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |
|
| RJ01 | Rejection of invention patent application after publication |