JPH06201751A - Power transmission line failure segment locating device - Google Patents
Power transmission line failure segment locating deviceInfo
- Publication number
- JPH06201751A JPH06201751A JP38893A JP38893A JPH06201751A JP H06201751 A JPH06201751 A JP H06201751A JP 38893 A JP38893 A JP 38893A JP 38893 A JP38893 A JP 38893A JP H06201751 A JPH06201751 A JP H06201751A
- Authority
- JP
- Japan
- Prior art keywords
- fault
- failure
- section
- transmission line
- 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.)
- Pending
Links
Landscapes
- Locating Faults (AREA)
Abstract
Description
【０００１】[0001]
【産業上の利用分野】本発明は、落雷等による地絡や短
絡の電気的故障が送電線に発生したとき、その故障発生
地点の含まれる区間を標定する送電線故障区間標定装置
に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a transmission line failure section locating device for locating a section including a failure occurrence point when an electrical failure such as a ground fault or a short circuit due to a lightning strike occurs in the transmission line.
【０００２】[0002]
【従来の技術】電力を安定に供給するために送電設備に
は高い信頼性が要求されるが、その設備は完全なもので
はない。そのため、送電線に故障が発生したとき、その
位置を迅速に把握し対処しなければならない。送電線の
故障位置を把握する従来の技術として、（ａ）変電所な
どの送電線の端部で故障サージなどの到達時間を計測
し、故障点までの距離を算出する方法や、（ｂ）送電線
の各所に電流センサを設置し、架空地線に流れる故障電
流を測定して故障位置を求める方法などがある。2. Description of the Related Art High reliability is required for power transmission equipment in order to supply electric power in a stable manner, but the equipment is not perfect. Therefore, when a failure occurs in the power transmission line, it is necessary to quickly grasp the position and deal with it. As a conventional technique for grasping the failure position of the power transmission line, (a) a method of measuring the arrival time such as a failure surge at the end of the power transmission line such as a substation and calculating the distance to the failure point, or (b) There is a method in which a current sensor is installed in each place of the power transmission line and the fault current flowing in the overhead ground wire is measured to find the fault position.
【０００３】特に（ｂ）の方法では、あらゆる故障ケー
スについて模擬計算し、その結果を用いて、故障電流
（電流値および位相差）を入力すると故障位置を出力す
るようなニューラルネットを作成し、これを故障区間の
標定に用いることによって、高い正解率で故障区間を標
定できるもの（例えば、特開平２−２５７０７３号公
報）、さらに進んで故障の種類を分類して、その分類に
応じた学習をさせることにより、正解率を上げるもの
（特開平４−８１６７３号公報）が提案されている。。Particularly, in the method (b), a simulation calculation is performed for every failure case, and the result is used to create a neural network which outputs a failure position when a failure current (current value and phase difference) is input, By using this for locating a fault segment, a fault segment can be locating with a high correct answer rate (for example, Japanese Patent Laid-Open No. 2-257073), and further classifying the types of faults and learning according to the classification It has been proposed that the correct answer rate be increased by doing the above (Japanese Patent Laid-Open No. 4-81673). .
【０００４】[0004]
【発明が解決しようとする課題】しかし、上述した
（ｂ）の従来技術によれば、送電線の変電所での幾何学
的配置が複雑なため、十分な模擬ができず、変電所部送
電線電流の模擬計算が不正確になる。変電所から遠い送
電部電流はこの影響をあまり受けず正確な値となるが、
変電所に近い送電部電流は影響を受けて不正確になる。
模擬故障電流計算が正確でなければ、この計算結果を使
って学習される標定用ニューラルネットは不正確なもの
となり、故障区間を正確に標定できなくなる。However, according to the above-mentioned prior art of (b), since the geometrical arrangement of the transmission line in the substation is complicated, a sufficient simulation cannot be performed, and the substation transmission. Incorrect simulation of wire current. The current of the transmission section far from the substation is not affected by this much and becomes an accurate value.
The current in the transmission section near the substation is affected and becomes inaccurate.
If the simulated fault current calculation is not accurate, the orientation neural network learned using this calculation result will be inaccurate and the fault section cannot be accurately located.
【０００５】このことは、故障の分類をし、その分類に
応じた学習をさせることにより、距離分解能が向上した
としても、幾何学的配置が複雑である場合には、距離検
出が単純にはいかず、しかも故障の種類にかかわらず電
流値及び位相差の両方を入力として模擬計算しているた
め、計算量が膨大となり、自ずとその量も限られること
から精度上の限界がある。This means that even if the distance resolution is improved by classifying the faults and learning according to the class, the distance detection is not easy if the geometrical arrangement is complicated. However, since the simulation calculation is performed with both the current value and the phase difference as inputs regardless of the type of failure, the amount of calculation becomes enormous, and the amount is naturally limited, so there is a limit in accuracy.
【０００６】特に故障の種類が地絡の場合には、模擬故
障計算電流の電流値が幾何学的配置に大きく影響され、
したがって故障区間の標定も送電線の変電所での幾何学
的配置に大きく影響されるため、模擬故障電流の電流値
を使ってニューラルネットを学習すると、該当部で故障
区間標定の正解率が大幅に下がる。送電線の電気的故障
のほとんどが地絡故障であることから、その正解率の低
下は大きな問題となっていた。Particularly when the type of fault is a ground fault, the current value of the simulated fault calculation current is greatly influenced by the geometrical arrangement,
Therefore, the orientation of the fault section is also greatly affected by the geometrical arrangement of the transmission line in the substation, so learning the neural network using the current value of the simulated fault current significantly increases the correct rate of fault section localization in the relevant section. Go down to. Since most of the electrical faults in power transmission lines are ground faults, the reduction of the correct answer rate has been a big problem.
【０００７】本発明の目的は、上述した従来技術の問題
点を解消して、電線の幾何学的配置が複雑であっても故
障区間標定の正解率が低下しない送電線故障区間標定装
置を提供することにある。また、本発明の目的は、故障
の種類が地絡の場合、送電線の変電所での幾何学的配置
に影響されることなく、故障区間標定の正解率が低下し
ない送電線故障区間標定装置を提供することにある。。An object of the present invention is to solve the above-mentioned problems of the prior art, and to provide a transmission line fault section locating device in which the accuracy rate of fault section locating does not decrease even if the geometrical arrangement of electric wires is complicated. To do. Further, an object of the present invention is, when the type of failure is a ground fault, a transmission line failure section locating device in which the accuracy rate of the failure section orientation does not decrease without being affected by the geometrical arrangement of the transmission line in the substation. To provide. .
【０００８】[0008]
【課題を解決するための手段】第１の発明は、送電線の
各所に電流センサを設置し、送電線の各所に電流センサ
を設置し、架空地線に流れる故障電流を測定して故障位
置を求める送電線故障区間標定装置において、故障電流
から得た位相差および電流値に基づいて故障の種類を分
類する故障種類分類部と、故障種類分類部で分類された
故障の種類が地絡故障のとき故障区間を位相差から標定
する地絡故障標定部と、故障種類分類部で分類された故
障の種類が短絡故障のとき故障区間を位相差および電流
値から標定する短絡故障標定部とを備えたものである。According to a first aspect of the present invention, a current sensor is installed in each place of a power transmission line, a current sensor is installed in each place of a power transmission line, and a fault current flowing through an overhead ground wire is measured to determine a fault position. In a transmission line fault section locator that determines the fault type classification unit that classifies the fault types based on the phase difference and current value obtained from the fault current, and the fault types classified by the fault type classification unit are ground faults. In the case of, a ground fault fault locator that locates the fault section from the phase difference, and a short-circuit fault locator that locates the fault section from the phase difference and the current value when the type of fault classified by the fault type classifier is a short-circuit fault. Be prepared.
【０００９】第２の発明は、上記装置を地絡故障の場合
にのみ適用したものであり、送電線の各所に電流センサ
を設置し、架空地線に流れる故障電流を測定して故障位
置を求める送電線故障区間標定装置において、故障電流
から得た位相差および電流値に基づいて故障の種類を分
類する故障種類分類部と、故障種類分類部で分類された
故障の種類が地絡故障のとき故障区間を位相差から標定
する地絡故障標定部とを備えたものである。A second aspect of the present invention is applied to the above device only in the case of a ground fault, in which current sensors are installed at various places of a power transmission line and a fault current flowing through an overhead ground line is measured to determine a fault position. In the transmission line fault section locator to be sought, the fault type classification unit that classifies the types of faults based on the phase difference and the current value obtained from the fault current, and the types of faults classified by the fault type classification unit are ground faults. At this time, a ground fault locator for locating the fault zone from the phase difference is provided.
【００１０】[0010]
【作用】送電線に発生する電気的故障は、地絡および短
絡故障に大別できる。架空地線に流れる電流値（電流振
幅）および位相の線路方向の分布は、典型的なシミュレ
ーション結果として示した図６のように、故障の種類に
応じて特徴あるパターンを示す。地絡故障（Ａ）では故
障点で位相変化が１８０度近く変化することが分り、短
絡故障（Ｂ）では故障点で位相と電流値が共に変化して
いるのが分る。[Operation] Electrical faults occurring in power transmission lines can be broadly classified into ground faults and short circuit faults. The distribution in the line direction of the current value (current amplitude) and the phase flowing through the overhead ground wire shows a characteristic pattern according to the type of failure, as shown in FIG. 6 which is shown as a typical simulation result. It can be seen that in the ground fault (A), the phase change changes by nearly 180 degrees at the fault point, and in the short-circuit fault (B), both the phase and the current value change at the fault point.
【００１１】本発明は、電流値は電線の幾何学的配置に
影響されやすいのに対して位相は電線の幾何学的配置に
影響されにくい点と、上記シミュレーション結果から、
位相は地絡故障の場合故障位置での位相の変化が顕著で
あるが、短絡故障の場合故障位置での位相の変化は地絡
故障ほど顕著でないという点に着目してなされたもので
ある。According to the present invention, the current value is easily influenced by the geometrical arrangement of the electric wires, while the phase is hardly influenced by the geometrical arrangement of the electric wires.
With respect to the phase, the change in the phase at the fault position is remarkable in the case of the ground fault, but the change in the phase at the fault position is not so remarkable in the case of the short-circuit fault as compared with the ground fault.
【００１２】故障が発生すると、送電線の各所に設置さ
れた電流センサで測定された故障電流から電流値と位相
差を取りだして、これらをニューラルネットで構成され
る故障種類分類部に入力する。この故障種類分類部は、
あらゆる故障ケースの模擬故障データを用いて、そのと
きの位相差及び電流値と故障種類との対応関係を予め模
擬学習させておく。したがって、故障発生時の故障電流
が入力された故障種類分類部では、発生した故障が地絡
故障か短絡故障かを分類する。When a failure occurs, the current value and the phase difference are extracted from the failure current measured by the current sensors installed in various places of the power transmission line, and these are input to the failure type classification unit composed of a neural network. This failure type classification unit
By using simulated failure data of all failure cases, the corresponding relationship between the phase difference and current value at that time and the failure type is simulated and learned in advance. Therefore, the failure type classification unit to which the failure current at the time of failure occurrence is input classifies the generated failure as a ground fault or a short-circuit fault.
【００１３】次に故障種類分類部の故障種類の分類結果
に応じて、故障区間を標定するにふさわしい故障標定部
として、地絡故障標定部か短絡故障標定部かが選択され
る。地絡故障標定部は、地絡故障ケースの模擬故障デー
タを用いて、そのときの位相差と故障区間との対応関係
を予め模擬学習させておく。また、短絡故障標定部は、
地絡故障ケースの模擬故障データを用いて、そのときの
位相差及び電流値と故障区間との対応関係を予め模擬学
習させておく。Next, according to the classification result of the fault type of the fault type classification unit, the ground fault fault locating unit or the short circuit fault locating unit is selected as the fault locating unit suitable for locating the fault section. The ground fault locating unit uses the simulated fault data of the ground fault case to preliminarily simulate learn the correspondence relationship between the phase difference at that time and the fault section. In addition, the short-circuit fault locator
Using the simulated fault data of the ground fault case, the corresponding relationship between the phase difference and the current value at that time and the fault section is simulated and learned in advance.
【００１４】ここで、これらの学習に当って、地絡故障
を標定する地絡故障標定部では、不必要な電流値を除き
幾何学的配置に影響されにくい位相差という単純入力だ
けから模擬学習させているため、精度良く模擬学習させ
ることが容易となる。また、短絡故障を標定する短絡故
障標定部では、共に必要な電流値と位相差とから模擬学
習させているため、精度良く模擬学習させることが容易
となる。その結果、該当部での計算値と実測値との誤差
も小さくなる。Here, in these learning, in the ground fault fault locator for locating the ground fault, simulated learning is performed only from a simple input of a phase difference that is not influenced by the geometrical arrangement except unnecessary current values. As a result, it becomes easy to perform simulated learning with high accuracy. Further, in the short-circuit fault locating unit for locating the short-circuit fault, since the simulation learning is performed from both the necessary current value and the phase difference, the simulation learning can be easily performed with high accuracy. As a result, the error between the calculated value and the actually measured value in the relevant part is also reduced.
【００１５】したがって、故障種類分類部が故障を地絡
故障と分類した場合は、地絡故障標定部で位相差から精
度のよい故障区間の標定が行える。また、短絡故障と分
類した場合は、短絡故障標定部で電流値と位相差から精
度のよい故障区間の標定が行える。これにより、送電線
の変電所での幾何学的配置が複雑であっても、故障区間
標定の正解率が下がることがなくなる。Therefore, when the fault type classifying unit classifies the fault as a ground fault, the ground fault fault locating unit can accurately locate the fault section from the phase difference. Further, when the fault is classified as a short-circuit fault, the short-circuit fault locating unit can accurately locate the fault section from the current value and the phase difference. As a result, even if the geometrical layout of the transmission line in the substation is complicated, the accuracy rate of fault section localization does not decrease.
【００１６】[0016]
【実施例】以下、本発明の実施例を図面を用いて説明す
る。図２は本実施例による集中判定装置の構成図、図１
は送電線故障区間標定装置の全体構成図を示し、図３は
故障種類分類用ニューラルネットの構成図、図４は地絡
故障標定用ニューラルネットの構成図、図５は短絡故障
標定用ニューラルネットの構成図をそれぞれ示したもの
である。Embodiments of the present invention will be described below with reference to the drawings. FIG. 2 is a block diagram of the centralized determination device according to this embodiment, and FIG.
Shows an overall configuration diagram of a transmission line fault section locating device, FIG. 3 is a configuration diagram of a fault type classification neural network, FIG. 4 is a configuration diagram of a ground fault fault locating neural network, and FIG. 5 is a short circuit fault locating neural network. The respective configuration diagrams of are shown.
【００１７】図２において、送電線に沿って、鉄塔１１
の数基ごとに電流センサ１２を架空地線１３に取り付
け、故障時に架空地線に流れる電流を測定し、測定した
各所の電流を集中判定装置１４に伝送して電流値及び位
相差からなる電流分布（図６参照）の特徴から故障区間
を標定する。In FIG. 2, a tower 11 is installed along the transmission line.
The current sensor 12 is attached to the overhead ground wire 13 for each of several units, the current flowing through the overhead ground wire is measured at the time of failure, the measured current is transmitted to the centralized determination device 14, and the current consisting of the current value and phase difference The failure section is located based on the characteristics of the distribution (see FIG. 6).
【００１８】各所の電流が伝送されてくる集中判定装置
１４は、図１のように、故障種類分類部２１と地絡故障
標定部２２と短絡故障標定部２３とで構成される。ま
ず、集中判定装置１４に集められた送電線各所の電流値
と位相差とから故障種類分類部２１で故障の種類を地絡
故障と短絡故障にと分類する。次に、その分類結果に応
じて、地絡故障と分類された場合は地絡故障標定部２２
で位相差から故障区間を標定し、短絡故障と分類された
場合は短絡故障標定部２３で電流値と位相差とから故障
区間を標定する。As shown in FIG. 1, the centralized determination device 14 to which the electric current of each place is transmitted is composed of a fault type classification unit 21, a ground fault fault locating unit 22 and a short circuit fault locating unit 23. First, the fault type classification unit 21 classifies the types of faults into ground faults and short-circuit faults based on the current values and phase differences of the power transmission lines collected in the centralized determination device 14. Next, according to the classification result, when the ground fault is classified, the ground fault locator 22
When the fault section is located from the phase difference and is classified as a short-circuit failure, the short-circuit failure locating unit 23 locates the failure section based on the current value and the phase difference.
【００１９】故障種類分類部２１は、地絡と短絡の両方
の故障種類を含む送電線各所の模擬故障データを用い
て、電流値および位相差と故障種類との関係をあらかじ
め学習させたニューラルネットで構成し、故障時の電流
値および位相差を入力すると、その故障について地絡故
障か短絡故障かを分類出力する（図３）。地絡故障標定
部２２は、送電線各所の地絡故障の模擬故障データを用
いて、位相差と故障区間との関係をあらかじめ学習させ
たニューラルネットで構成し、故障時の位相差を入力す
ると、その故障発生地点の属する区間を標定出力する
（図４）。短絡故障標定部２３は、送電線各所の短絡故
障の模擬故障データを用いて、電流値および位相差と故
障区間との関係をあらかじめ学習させたニューラルネッ
トで構成し、故障時の電流値および位相差を入力する
と、その故障発生地点の属する区間を標定出力する（図
５）。The fault type classifying unit 21 uses a simulated fault data of various places of the transmission line including both fault types of ground fault and short circuit, and a neural network in which the relation between the current value and the phase difference and the fault type is learned in advance. When the current value and the phase difference at the time of failure are input, the failure is classified and output as a ground fault or a short circuit failure (FIG. 3). The ground fault locator 22 is configured by a neural network that has learned the relationship between the phase difference and the fault section in advance by using simulated fault data of the ground faults at various places on the transmission line. When the phase difference at the time of fault is input, , The section to which the failure occurrence point belongs is orientated and output (FIG. 4). The short-circuit fault locating unit 23 is configured by a neural network in which the relationship between the current value and the phase difference and the fault section is preliminarily learned by using the simulated fault data of the short-circuit fault at each place of the transmission line, and the current value and the position at the time of the fault When the phase difference is input, the section to which the failure occurrence point belongs is orientated and output (FIG. 5).
【００２０】ここで、各ニューラルネットは、ニューロ
ンの動作をコンピュータで模擬した人工の神経回路網で
ある。この実施例ではそれぞれ３層構造をしており、３
層構造の円は細胞体、線はニューロン間の結合強度を決
めるシナプスを模擬している。模擬学習の結果、電流分
布から故障点を検知するシナプスをみずから決定するよ
うになっている。Here, each neural network is an artificial neural network in which the operation of a neuron is simulated by a computer. In this embodiment, each has a three-layer structure.
Layered circles imitate cell bodies and lines imitate synapses that determine the strength of connections between neurons. As a result of the simulation learning, the synapse for detecting the failure point is determined from the current distribution.
【００２１】本実施例によれば、故障種類分類用のニュ
ーラルネットで故障を分類した上で、故障の種類に合わ
せた最適な入力情報による模擬学習をさせた地絡故障標
定用および短絡故障標定用ニューラルネットにより故障
に応じた標定をするようにしたので、変電所ストラクチ
ャ部近傍の送電部のように幾何学的配置が複雑で、精度
良く模擬計算することが不可能な場合であっても、故障
の種類に合せて計算値と実測値との誤差が小さい入力情
報を使うことによって、故障区間標定の正解率の低下を
防止することができる。According to this embodiment, the faults are classified by the neural network for classifying the faults, and the simulated learning is performed by the optimum input information according to the types of the faults. Even if the geometrical layout is complicated and it is not possible to perform accurate simulation calculations, such as the power transmission section near the substation structure section, it is possible to perform localization according to the failure using the neural network By using the input information with a small error between the calculated value and the measured value according to the type of failure, it is possible to prevent the accuracy rate of the failure section orientation from decreasing.
【００２２】[0022]
（１）請求項１に記載の送電線故障区間標定装置によれ
ば、電線の幾何学的配置が複雑であっても故障区間標定
の正解率が下がらず、高い標定精度を得ることができ
る。(1) According to the transmission line fault section locating device of the first aspect, the accuracy rate of the fault section locating does not decrease even when the geometrical arrangement of the wires is complicated, and high locating accuracy can be obtained.
【００２３】（２）請求項２に記載の送電線故障区間標
定装置によれば、故障の種類が地絡の場合、該当部で故
障区間標定の正解率の低下を有効に防止できる。特に、
送電線の電気的故障のほとんどが地絡故障であることか
ら、その効果は大きい。(2) According to the transmission line fault section locating apparatus of the second aspect, when the type of the fault is a ground fault, it is possible to effectively prevent a decrease in the correct answer rate of the fault section locating in the corresponding part. In particular,
Most of the electrical faults in the transmission line are ground faults, so the effect is great.
【図１】本発明の実施例による送電線故障区間標定装置
を構成する集中判定装置の構成図。FIG. 1 is a configuration diagram of a centralized determination device that constitutes a transmission line fault section locating device according to an embodiment of the present invention.
【図２】本実施例による送電線故障区間標定装置の全体
構成図。FIG. 2 is an overall configuration diagram of a transmission line fault section locating device according to the present embodiment.
【図３】本実施例による集中判定装置を構成する故障種
類分類部のニューラルネットの構成図。FIG. 3 is a configuration diagram of a neural network of a failure type classification unit that constitutes the centralized determination device according to the present embodiment.
【図４】本実施例による集中判定装置を構成する地絡故
障標定部のニューラルネットの構成図。FIG. 4 is a configuration diagram of a neural network of a ground fault fault locating unit that constitutes the centralized determination device according to the present embodiment.
【図５】本実施例による集中判定装置を構成する短絡故
障標定部のニューラルネットの構成図。FIG. 5 is a configuration diagram of a neural network of a short-circuit fault locating unit that constitutes the centralized determination device according to the present embodiment.
【図６】送電線の地絡故障と短絡故障のシミュレーショ
ン結果を示す電流分布図。FIG. 6 is a current distribution diagram showing simulation results of a ground fault and a short circuit fault of a transmission line.
１１ 鉄塔 １２ 電流センサ １３ 架空地線 １４ 集中判定装置 ２１ 故障種類分類部 ２２ 地絡故障標定部 ２３ 短絡故障標定部 11 Steel Tower 12 Current Sensor 13 Overhead Ground Wire 14 Concentrated Judgment Device 21 Failure Type Classification Section 22 Ground Fault Failure Locating Section 23 Short Circuit Failure Locating Section
Claims (2)
地線に流れる故障電流を測定して故障位置を求める送電
線故障区間標定装置において、故障電流から得た位相差
および電流値に基づいて故障の種類を分類するニューラ
ルネットで構成された故障種類分類部と、故障種類分類
部で分類された故障の種類が地絡故障のとき故障区間を
上記位相差から標定するニューラルネットで構成された
地絡故障標定部と、故障種類分類部で分類された故障の
種類が短絡故障のとき故障区間を上記位相差および電流
値から標定するニューラルネットで構成された短絡故障
標定部とを備えたことを特徴とする送電線故障区間標定
装置。1. A transmission line fault section locating device, wherein a current sensor is installed at each position of a transmission line to measure a fault current flowing through an overhead ground line to obtain a fault position, in a phase difference and a current value obtained from the fault current. Consists of a fault type classification unit configured by a neural network that classifies the types of faults based on the above, and a neural network that determines the fault interval from the phase difference when the fault type classified by the fault type classification unit is a ground fault And a short-circuit fault locator composed of a neural network that locates the fault section from the phase difference and the current value when the type of fault classified by the fault type classifier is a short-circuit fault. A transmission line fault section locating device characterized by the above.
地線に流れる故障電流を測定して故障位置を求める送電
線故障区間標定装置において、故障電流から得た位相差
および電流値に基づいて故障の種類を分類する故障種類
検出部と、故障種類検出部で分類された故障の種類が地
絡故障のとき故障区間を上記位相差から標定する地絡故
障標定部とを備えたことを特徴とする送電線故障区間標
定装置。2. A transmission line fault section locating device, wherein a current sensor is installed at each position of a power transmission line to measure a fault current flowing in an overhead ground wire to obtain a fault position, in a phase difference and a current value obtained from the fault current. And a ground fault locator that locates the fault section from the phase difference when the fault class classified by the fault class is a ground fault. A transmission line fault section locating device characterized by:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP38893A JPH06201751A (en) | 1993-01-06 | 1993-01-06 | Power transmission line failure segment locating device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP38893A JPH06201751A (en) | 1993-01-06 | 1993-01-06 | Power transmission line failure segment locating device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPH06201751A true JPH06201751A (en) | 1994-07-22 |
Family
ID=11472425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP38893A Pending JPH06201751A (en) | 1993-01-06 | 1993-01-06 | Power transmission line failure segment locating device |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH06201751A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000017181A (en) * | 1998-08-13 | 2000-03-25 | 맥그로우-에디슨 컴파니 | Current transformer saturation correction using artificial neural networks |
| KR100699221B1 (en) * | 2005-03-31 | 2007-03-27 | 엘에스전선 주식회사 | System for discriminating fault for protecting combined transmission line and method thereof |
| CN104076250A (en) * | 2014-07-24 | 2014-10-01 | 国家电网公司 | Method for analyzing shielding failure and shielding failure trip-out rate of upper-phase conductors of double-circuit lines on same tower |
| CN106990327A (en) * | 2017-05-11 | 2017-07-28 | 国网江苏省电力公司苏州供电公司 | High voltage single-core cable short trouble point detecting method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02257073A (en) * | 1988-12-06 | 1990-10-17 | Hitachi Cable Ltd | Fault section locating device of aerial transmission line |
| JPH0481673A (en) * | 1990-07-25 | 1992-03-16 | Hitachi Cable Ltd | Apparatus for locating faulty section of aerial transmission line |
| JPH04279870A (en) * | 1991-03-08 | 1992-10-05 | Hitachi Cable Ltd | Transmission line failure block location system |
-
1993
- 1993-01-06 JP JP38893A patent/JPH06201751A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02257073A (en) * | 1988-12-06 | 1990-10-17 | Hitachi Cable Ltd | Fault section locating device of aerial transmission line |
| JPH0481673A (en) * | 1990-07-25 | 1992-03-16 | Hitachi Cable Ltd | Apparatus for locating faulty section of aerial transmission line |
| JPH04279870A (en) * | 1991-03-08 | 1992-10-05 | Hitachi Cable Ltd | Transmission line failure block location system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000017181A (en) * | 1998-08-13 | 2000-03-25 | 맥그로우-에디슨 컴파니 | Current transformer saturation correction using artificial neural networks |
| KR100699221B1 (en) * | 2005-03-31 | 2007-03-27 | 엘에스전선 주식회사 | System for discriminating fault for protecting combined transmission line and method thereof |
| CN104076250A (en) * | 2014-07-24 | 2014-10-01 | 国家电网公司 | Method for analyzing shielding failure and shielding failure trip-out rate of upper-phase conductors of double-circuit lines on same tower |
| CN106990327A (en) * | 2017-05-11 | 2017-07-28 | 国网江苏省电力公司苏州供电公司 | High voltage single-core cable short trouble point detecting method |
| CN106990327B (en) * | 2017-05-11 | 2019-10-18 | 国网江苏省电力公司苏州供电公司 | High voltage single-core cable short trouble point detecting method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106443310B (en) | A kind of transformer fault detection method based on SOM neural network | |
| Ayyagari | Artificial neural network based fault location for transmission lines | |
| JP3058564B2 (en) | Transmission line failure section and failure mode evaluation method | |
| CN107561407B (en) | Distributed transformer substation grounding grid detection and evaluation method | |
| Mbamaluikem et al. | An artificial neural network-based intelligent fault classification system for the 33-kV Nigeria transmission line | |
| JPH09145772A (en) | Method and device for locating transmission/distribution line electric wire failure section | |
| CN111062569A (en) | Low-current fault discrimination method based on BP neural network | |
| JPH06201751A (en) | Power transmission line failure segment locating device | |
| Jain et al. | Application of artificial neural networks to transmission line faulty phase selection and fault distance location | |
| Ogar et al. | Protection for 330 kV transmission line and recommendation for Nigerian transmission system: a review | |
| CN113064023B (en) | Fault identification method and system for same-tower multi-circuit power transmission line | |
| CN115184728A (en) | Fault identification method for AC/DC hybrid power distribution network | |
| Jain et al. | Soft computing based fault detection & classification for transmission lines | |
| Dutta et al. | Intelligent control for locating fault in transmission lines | |
| Mazon et al. | Fault location system on double circuit two-terminal transmission lines based on ANNs | |
| JP2768028B2 (en) | Transmission line fault location system | |
| JP2003114249A (en) | Accident section locating method of transmission line | |
| Adebayo et al. | Application of Artificial Neural Network Model for Improved Power System Protection in Port Harcourt 33 kV Network | |
| KR950012286B1 (en) | Error checking method of electric power system | |
| CN113740667B (en) | Power grid fault diagnosis method integrating self-encoder and convolutional neural network | |
| Raval | ANN based classification and location of faults in EHV transmission line | |
| Awelewa et al. | Recent Development of Intelligent Shunt Fault Classifier for Nigeria 33-kV Power Lines | |
| JP2767987B2 (en) | Fault location system for overhead transmission lines | |
| Mazón et al. | Strategies for fault classification in transmission lines, using learning vector quantization neural networks | |
| Awelewa et al. | Intelligent Shunt Fault Classifier for Nigeria 33-kV Power Lines |