WO1995009464A1 - Procede permettant de produire des signaux indiquant la nature d'un incident survenu dans un reseau d'alimentation en energie a surveiller - Google Patents

Procede permettant de produire des signaux indiquant la nature d'un incident survenu dans un reseau d'alimentation en energie a surveiller Download PDF

Info

Publication number
WO1995009464A1
WO1995009464A1 PCT/DE1994/001139 DE9401139W WO9509464A1 WO 1995009464 A1 WO1995009464 A1 WO 1995009464A1 DE 9401139 W DE9401139 W DE 9401139W WO 9509464 A1 WO9509464 A1 WO 9509464A1
Authority
WO
WIPO (PCT)
Prior art keywords
neurons
layer
supply network
output
electrical power
Prior art date
Application number
PCT/DE1994/001139
Other languages
German (de)
English (en)
Inventor
Thomas Dalstein
Original Assignee
Siemens Aktiengesellschaft
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens Aktiengesellschaft filed Critical Siemens Aktiengesellschaft
Publication of WO1995009464A1 publication Critical patent/WO1995009464A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
    • H02H1/00—Details of emergency protective circuit arrangements
    • H02H1/0092—Details of emergency protective circuit arrangements concerning the data processing means, e.g. expert systems, neural networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H02J13/00036—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers
    • H02J13/0004—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers involved in a protection system
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
    • H02J3/0012—Contingency detection
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
    • H02H1/00—Details of emergency protective circuit arrangements
    • H02H1/04—Arrangements for preventing response to transient abnormal conditions, e.g. to lightning or to short duration over voltage or oscillations; Damping the influence of dc component by short circuits in ac networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
    • H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
    • H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
    • H02H3/38—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection responsive to both voltage and current; responsive to phase angle between voltage and current
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/30—State monitoring, e.g. fault, temperature monitoring, insulator monitoring, corona discharge

Definitions

  • the invention relates to a method for generating signals characterizing the type of error in an electrical power supply network to be monitored (error type signals) for activating selective protection devices, in which intermediate values derived from the currents and voltages of the electrical power supply network are used in one Evaluation device the type of error signals are generated.
  • Gate arrangement can be created.
  • the gate arrangement consists of gates in a number which corresponds to the possible errors in the power supply network to be monitored. All gates of the gate arrangement are acted upon on the input side with the intermediate values in such a way that only a certain gate is switched through in the event of an error of a certain type.
  • the output signals of the gates thus identify the type of a certain fault in the energy supply network to be monitored.
  • the fault type signals are used to control the static switches of a number of static switches via a diode matrix, via which a specific current and a specific voltage are to be applied to a downstream distance protection device, for example, with regard to the type of fault determined.
  • the invention is based on the object of developing a method of the type mentioned at the outset in such a way that it can be used to obtain error type signals for activating selective protection devices with relatively little effort and quickly and reliably.
  • a single neural network is used as the evaluation device, which contains an input layer, a first and a second intermediate layer and an output layer, the neural network being generated by simulating the currents and voltages under different load states of the electrical power supply network monitors behavior that has been learned in such a way that in each case one neuron of the output layer generates an output signal which is above a predetermined threshold value in the event of errors of any kind;
  • the intermediate values used are the measured values corresponding to the instantaneous values of the currents and voltages of the electrical power supply network, from which rows each having a plurality of successively sampled, standardized values are formed, and the several successively sampled, standardized values of all the rows are simultaneously sent to different neurons of the input layer laid out; the output signals of the neurons of the output layer are monitored for the predetermined threshold value, and if an output signal of a neuron of the output layer exceeds the threshold value, the corresponding type of error signal is generated.
  • An essential advantage of the method according to the invention is seen in the fact that it can be carried out with relatively little effort because the method is practiced using a neural network which can be represented in the form of a processor.
  • the method according to the invention can therefore largely be used to implement a circuit arrangement with a large number of individual electronic components to be dispensed with.
  • the teaching of the neural network which must take place before the method according to the invention is carried out, involves a certain amount of effort, however, this can only be accepted once, because from a learned neural network by "copying" in a relatively simple manner, further new ones ⁇ ronal networks with the same properties can be obtained.
  • Another important advantage of the method according to the invention is that it not only works very reliably, but also provides the type of error signals in a very short time, so that assigned selective protection devices, such as distance protection devices, quickly can be activated, for example, by creating the network sizes specific to the type of error determined.
  • a neural network is used in which a neuron in the starting layer is assigned to every possible type of error in the electrical power supply network. Irrespective of the respective application of the method according to the invention, all possible errors in an electronic device to be monitored can then always be trical power supply network are characterized by the generation of appropriate error type signals.
  • a neural network is used in which an additional neuron is assigned in the output layer to the fault-free state of the electrical power supply network.
  • each row of successively sampled values is obtained from five values forms, and the input layer contains 30 neurons, the first intermediate layer 25 neurons and the second intermediate layer 20 neurons, while the output layer contains 11 neurons.
  • a neural network in which the reworking unit downstream of each neuron of the output layer checks with at least one delay stage and an AND gate whether the output signal of the respective neuron of the output layer has occurred at least one more time.
  • the figure shows an exemplary embodiment of an arrangement which is suitable for carrying out the method according to the invention.
  • the arrangement shown contains a neural network 1 which has an input layer 2 with a total of 30 neurons.
  • the 30 neurons of the input layer 2 are combined into six groups, each with five neurons 3, 4, 5, 6 and 7, of which only three groups 8, 9, 10 are shown in the figure for the sake of clarity.
  • Each of the groups 8, 9 and 10 of neurons of the input layer 2 is preceded by a multiplexer, of which only the multiplexers 11 and 12 are shown in the figure for better clarity.
  • Each multiplexer 11 and 12 has its input at the output of a standardization module 13 or 14, which in turn is preceded by an analog-digital converter 15 or 16.
  • a measured variable J j -> (t) is connected to an input 17 of the analog-digital converter 15 and is obtained in a conventional manner from the current in phase R of a power transmission network to be monitored, not shown, by means of a current converter.
  • further measured variables Jg (t) and J (t) are obtained from the currents in phases S and T by means of further current transformers and in a manner not shown via further analog-digital converters and others
  • Standardization modules and further multiplexers each connected to a group of neurons of the input layer 2.
  • Various neuronal values of the currents J ⁇ .t) to J (t) are thus fed to these neurons in corresponding standardized values.
  • a corresponding procedure is followed with regard to the voltages at the phases R to T of the energy supply network to be monitored, in which a measured variable U ⁇ p (t) is applied to an input 18 of the analog-digital converter 16, which is applied to the voltage in the usual way by means of a voltage converter phase T of the energy supply network is derived.
  • a measured variable U ⁇ p (t) is applied to an input 18 of the analog-digital converter 16, which is applied to the voltage in the usual way by means of a voltage converter phase T of the energy supply network is derived.
  • the neural network 1 also contains a first intermediate layer 20, which consists of 25 Neurons exist, of which only a few are shown in the figure for the sake of clarity. All neurons of the first intermediate layer 20 are connected on the input side to all outputs of the neurons of the input layer 2.
  • the first intermediate layer 20 is followed by a second intermediate layer 21, which has 20 neurons; for reasons of simple illustration, only a few of these 20 neurons of the second intermediate layer 21 are shown in the figure. All neurons of this intermediate view are coupled to all neurons of the first intermediate layer 20.
  • the neural network contains an output layer 22, which has 11 neurons. All neurons of this layer are connected on the input side to all neurons of the second intermediate layer 21.
  • a neuron 23 is connected on the output side to a threshold value detection device 24, which then outputs a signal to a postprocessing device 26 at its output 25 when the output signal A ⁇ of the neuron 23 is one with the threshold value Er ⁇ Detection device 24 exceeds the predetermined threshold.
  • the post-processing device 26 contains a first delay 27, which is connected with its input 28 to the output 25 of the threshold value detection device 24. On the output side, the delay 27 is connected both to an input 29 of an AND gate 30 and to a further delay 31, which is connected on the output side to a further input 32 of the AND gate 30. An additional input 33 of the AND gate 30 is connected directly to the output 25 of the threshold value detection device 24.
  • the neural network 1 uses further, only schematically illustrated outputs of the neurons of the output layer 22, depending on the type of error occurred further signals A2 to generated.
  • the output signals A ⁇ to A- ⁇ Q occur when single-pole faults to earth, two-pole faults with earth contact, two-pole faults without earth contact and three-pole faults with or without earth contact occur.
  • An additional output signal A ⁇ arises when the network to be monitored is working properly.
  • the measured variables are in the analog-digital converters 15 and 16 and corresponding further converters to U ⁇ p (t), for example, sampled at a frequency of 1 kHz.
  • the respectively sampled values are normalized in a normalization module 13 and 14 or corresponding further modules and fed to the respective downstream multiplexer 11 and 12 or further multiplexers, not shown.
  • Each of the multiplexers is provided with a plurality of delay elements such that five of the successively sampled values JRI, JR2 J R3 JR4 and JR5 are present at their outputs at the same time. These values JRI to JR5 are therefore simultaneously present on the input side at a group 8, 9, 10 and further groups (not shown) of five neurons 3 to 7 each of the input layer 2 of the neural network 1.
  • the sampled normalized values are processed in the neural network 1 in a manner that has been taught to the network.
  • teaching was carried out using the NETOMAC network model, which is described in more detail in the magazine "Elektrizticians ocean ⁇ 1979, Issue 1, pages 18 to 23.
  • the teaching was carried out according to the Rumelhart back-propagation algorithm at various load conditions , assuming 1 that the corresponding output signals for the various errors should have the normalized value of 0.9.
  • the remaining output signals (which do not characterize an error) should then in each case be the assume standardized values 0.1.
  • the learning process is carried out in such a way that this signal has the normalized value 0.9 when the power supply network to be monitored is in a faultless state, but assumes the value 0.1 when an error has occurred.
  • the detection of the respectively standardized values of the output signals Ai to An is carried out by means of the threshold value detection devices 24. B. determined that
  • Output signal Ai in the event of a single-pole error in phase R of the power supply network to be monitored has the value 0.9, then the threshold value detection device 24 will emit a signal to the postprocessing device 26.
  • Distance protection device can be connected, for example, to the measured variables of the energy supply network to be monitored, which are to be taken into account in the distance measurement in the case of the type of error determined.

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)
  • Emergency Protection Circuit Devices (AREA)

Abstract

L'invention concerne un procédé permettant de produire des signaux indiquant la nature d'un incident survenu dans un réseau d'alimentation en énergie à surveiller et activant le système de protection sélective correspondant. A cet effet, on utilise un seul et unique réseau neuronal (1) qui contient plusieurs couches (2, 20, 21, et 22). Le réseau neuronal (1) est instruit par simulation des courants et des tensions à différents états de charge du réseau électrique d'alimentation en énergie, de manière à ce qu'en cas d'incident de nature déterminée, un neurone (22, 23) de la couche de sortie (22) produit un signal de sortie (A1 à A10) déterminé, servant à identifier la nature de l'incident (F1).
PCT/DE1994/001139 1993-09-27 1994-09-20 Procede permettant de produire des signaux indiquant la nature d'un incident survenu dans un reseau d'alimentation en energie a surveiller WO1995009464A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE4333258A DE4333258A1 (de) 1993-09-27 1993-09-27 Verfahren zum Erzeugen von die Art eines Fehlers in einem zu überwachenden elektrischen Energieversorgungsnetz kennzeichnenden Signalen
DEP4333258.7 1993-09-27

Publications (1)

Publication Number Publication Date
WO1995009464A1 true WO1995009464A1 (fr) 1995-04-06

Family

ID=6499016

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/DE1994/001139 WO1995009464A1 (fr) 1993-09-27 1994-09-20 Procede permettant de produire des signaux indiquant la nature d'un incident survenu dans un reseau d'alimentation en energie a surveiller

Country Status (2)

Country Link
DE (1) DE4333258A1 (fr)
WO (1) WO1995009464A1 (fr)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4433406C1 (de) * 1994-09-12 1995-12-21 Siemens Ag Distanzschutzeinrichtung
DE19613012C1 (de) * 1996-03-25 1997-08-14 Siemens Ag Verfahren zum Erzeugen von Fehlerklassifizierungssignalen
DE19637651A1 (de) * 1996-09-16 1998-03-19 Abb Patent Gmbh Verfahren zur Prozeßvisualisierung
GB0104763D0 (en) * 2001-02-27 2001-04-18 Smiths Group Plc Arc detection
EP4012864B1 (fr) 2020-12-09 2023-11-01 Siemens Aktiengesellschaft Dispositif de protection et procédé de surveillance d'un réseau d'alimentation électrique
EP4175090A1 (fr) 2021-10-29 2023-05-03 Siemens Aktiengesellschaft Dispositif de protection et procédé de surveillance d'un réseau d'alimentation électrique et produit-programme informatique

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1945802A1 (de) * 1969-09-05 1970-11-12 Siemens Ag Schaltungsanordnung zum selbsttaetigen,wahlweisen Anschliessen einer einzigen Messeinrichtung an einzelne von mehreren Messgroessen

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1945802A1 (de) * 1969-09-05 1970-11-12 Siemens Ag Schaltungsanordnung zum selbsttaetigen,wahlweisen Anschliessen einer einzigen Messeinrichtung an einzelne von mehreren Messgroessen
CH500609A (de) * 1969-09-05 1970-12-15 Siemens Ag Schaltungsanordnung zum selbsttätigen, wahlweisen Anschliessen einer einzigen Messeinrichtung an einzelne von mehreren Messkreisen

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
KANDIL: "Fault identification in an ac-dc transmission system using neural networks", IEEE TRANSACTIONS ON POWER SYSTEMS, vol. 7, no. 2, May 1992 (1992-05-01), NEW YORK US, pages 812 - 819, XP000273090 *

Also Published As

Publication number Publication date
DE4333258A1 (de) 1995-03-30

Similar Documents

Publication Publication Date Title
EP0721684B1 (fr) Procede permettant de generer un signal d'indication d'erreur
WO1997036185A1 (fr) Procede pour generer des signaux de classification d'erreurs
EP0721685B1 (fr) Procede permettant de produire un signal indiquant la direction d'un courant de court-circuit
EP2585841B1 (fr) Dispositif et procédé de surveillance d'une installation photovoltaïque
EP2845286B1 (fr) Détection de défauts dans des réseaux d'alimentation en énergie
DE4333260C2 (de) Verfahren zum Erzeugen eines Anregesignals
DE2915407A1 (de) Verfahren und vorrichtung zum ueberwachen einer digitalen schutzrelaiseinrichtung
EP3639365B1 (fr) Détermination de résistance d'isolation à sécurité intégrée dans une installation photovoltaïque
EP3355073B1 (fr) Production de modèles pour l'identification de cas d'erreur dans des réseaux électriques
DE102013109939A1 (de) Energieverteilungssysteme und Verfahren zum Betrieb eines Energieverteilungssystems
EP1416287A1 (fr) Procédé permettant de produire un signal d'erreur indiquant le court-circuit avec la terre
WO1995009464A1 (fr) Procede permettant de produire des signaux indiquant la nature d'un incident survenu dans un reseau d'alimentation en energie a surveiller
DE69018344T2 (de) Differentialschutzrelais.
DE4433406C1 (de) Distanzschutzeinrichtung
EP2057726A1 (fr) Procédé et système de protection différentielle
EP3527996B1 (fr) Dispositif de mesure et procédé de mesure de signaux électriques
WO2016016086A1 (fr) Contrôle d'un disjoncteur électrique multipolaire
EP4012864B1 (fr) Dispositif de protection et procédé de surveillance d'un réseau d'alimentation électrique
DE69824420T2 (de) Steuer- und Überwachungseinrichtung für die Öffnung oder die Schliessung eines elektrischen Betätigungselementes
DE1537532C3 (de) m-aus-n-Schaltung
DE102021121767A1 (de) Verfahren zum Überwachen eines Hochvoltbordnetzes eines zumindest teilweise elektrisch betriebenen Kraftfahrzeugs, Computerprogrammprodukt, Überwachungssystem sowie Hochvoltbordnetz
DE19518030C1 (de) Anordnung und Verfahren für die Bestimmung der Betriebszustände eines elektrischen Energieversorgungsnetzes
DE102022103029A1 (de) Verfahren, Vorrichtung, Computerprogramm und computerlesbares Speichermedium zur Lokalisierung eines elektrischen Fehlers in einem elektrischen System
DE102022101903A1 (de) Verfahren und Vorrichtung zur Überwachung einer Messkette mit einem Sensor
DE102022133311A1 (de) Testanordnung und verfahren zur emulation der phasen-ströme eines elektromotors für ein prüfen eines leistungs-elektronischen steuergeräts

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): US

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LU MC NL PT SE

121 Ep: the epo has been informed by wipo that ep was designated in this application
122 Ep: pct application non-entry in european phase