CN105703258A - GIS switch equipment action state monitoring system and use method thereof - Google Patents

Abstract

The invention provides a GIS switchgear action state monitoring system and a using method thereof, wherein the GIS switchgear action state monitoring system comprises the following steps: the system comprises a multi-source information acquisition unit, a GIS switching system and a control unit, wherein the multi-source information acquisition unit detects the working state of the GIS switching system and forms a detection signal, and the multi-source information acquisition unit conditions the detection signal into an electric analog signal; the information fusion unit is arranged in the computer terminal and used for receiving the electric analog signal, comparing the electric analog signal with a preset value and judging the working state of the GIS switching system; and the fault decision and prediction unit is used for alarming or predicting according to the comparison result of the electric analog signal and the preset value. Compared with the prior art, the invention has the following beneficial effects: the GIS fault diagnosis can be carried out based on the information acquired by various sensor signals, the diagnosis accuracy is improved, and the occurrence of false alarm is reduced.

Description

GIS switchgear operating state monitoring system and using method thereof

Technical field

Electrical equipment of the present invention, judges electrical equipment GIS switchgear operating state monitoring system and using method thereof more particularly, to one。

Background technology

Cubicle Gas-Insulated Switchgear (GIS, GasInsulatedSwitchgear) as a kind of form of high voltage distribution installation, by all primary equipments except transformator in transformer station, optimized design is organically combined into an entirety, and it is closed in metal-back, filling SF6 gas as arc extinguishing and dielectric, constitute a switchgear, the highest distribution voltage is up to 1100kV。GIS overcomes many restrictions of conventional open style switchgear, has floor space little, and reliability is high, high safety, the advantage of the only small grade of maintenance workload so that high pressure, ehv power transmission are directly entered urban district and are possibly realized, and are used widely in recent years。Along with the needs constantly improved with power system development of GIS, high-tension switch gear selects GIS to become the development trend of All Around The World。GIS develops towards common cylinder, Composite, miniaturization, intellectuality, supertension high capacity direction。GIS critical piece has the critical piece such as chopper, isolation switch, earthed switch, voltage transformer, current transformer, spark gap, sleeve pipe, cable termination, bus, shell, SF6 gas, SF6 density monitoring arrangement, GIS insulator。Wherein the switchgear of chopper, isolation switch, earthed switch general designation GIS, is the core parts of GIS。

High pressure GIS switchgear running status directly affects operation stability and the power supply reliability of power system。Due to the totally-enclosed design of GIS device, operator cannot observe directly the state of equipment, confirms to come judgment device whether opening and closing in place only in accordance with the return signal of auxiliary contact and operator on-the-spot。After switch tool operation, for various reasons, in fact it could happen that monitoring backstage and on-the-spot display deciliter success, but the situation that actual Contact Breaking/Making Operations is not in place, thus causing power grid security event, sizable economic loss and serious social influence are caused。

Switch equipment is the equipment of wink dynamic formula, and its mechanism remains static in properly functioning, the operation carried out occasionally or accident action, and its process is extremely of short duration again and at a high speed, thus brings very big difficulty to monitoring。The experience in past is to set up regular stoppage in transit inspection and repair system, and this preventative maintenance system can not find fault timely, and blindness is big, and excessive inspection operation even also reduces the mechanical life of switch。Circuit breaker failure monitoring object choice principle according to IEEE suggestion; time parameter each in circuit-breaker switching on-off process, metal short circuit time, total kilometres, insertion stroke, overtravel, moving contact speed, divide-shut brake coil current, contact life-span and protection act parameter are monitored; above-mentioned parameter has been done detailed analysis; propose monitoring method and analyze determination methods, it is proposed to the processing scheme after data are out-of-limit。But current technology major part is the measurement for switchgear mechanical property, and being based on the measurement indirectly measured, its validity and reliability need to improve。

It addition, at present power equipment is included primary cut-out implement the device (system) of status monitoring, substantially can be divided into: centralized on-line monitoring system and portable on-line monitoring system。Consistent with theoretical research, in primary cut-out on-line condition monitoring device (system), more situation be for the mechanical property of primary cut-out, mechanical vibration, electrical contact endurance, insulating properties some or several aspect be monitored, the functional reliability of this monitoring device and correctness, need practice confirmation and constantly sum up raising, it is necessary to the problem of consideration includes: reliability, feasibility and economy。Factors above is also the main cause that restriction switchgear repair based on condition of component is universal and develops。

Summary of the invention

For defect of the prior art, it is an object of the invention to provide the GIS switchgear operating state monitoring system of a kind of situation generation increasing the accuracy of diagnosis, minimizing wrong report and using method thereof。

For solving above-mentioned technical problem, a kind of GIS switchgear operating state monitoring system provided by the invention, including: multi-source information acquiring unit, described multi-source information acquiring unit detects the duty of GIS switching system and forms detection signal, and described detection signal condition is become electric analoging signal by described multi-source information acquiring unit again；Information fusion unit, described information fusion unit is arranged in computer terminal, and described information fusion unit receives described electric analoging signal, described electric analoging signal and preset value is compared, it is judged that the duty of GIS switching system；Fault decision-making and forecast unit, described fault decision-making carries out reporting to the police or forecasting according to the comparative result of described electric analoging signal Yu described preset value with forecast unit。

Preferably, interconnective monitor and signal conditioning circuit are set in described multi-source information acquiring unit。

Preferably, described monitor includes relay control circuit state detection module, connects execution high-voltage switch gear state detection module, mechanical mechanism state detection module and the detection module that leaks gas。

Preferably, described information fusion unit includes interconnective data collecting plate card, fault extraction module, information fusion module and fault routine judge module；Described data collecting plate card and described modulate circuit communication。

Preferably, described fault decision-making includes interconnective malfunction fuzzy characteristics storehouse, breakdown judge module and failure prediction module with forecast unit；Described malfunction fuzzy characteristics storehouse communicates with described information fusion module, described breakdown judge module communicates with described malfunction fuzzy characteristics storehouse, described failure prediction module communicates with described fault routine judge module and described breakdown judge module respectively, and described fault routine judge module communicates with described fault routine judge module。

The using method of a kind of GIS switchgear operating state monitoring system, comprises the steps:

Step 1, utilizes the duty of monitor detection GIS switching system and forms detection signal；

Step 2, detection signal condition is become electric analoging signal by signal conditioning circuit；

Step 3, data collecting plate card receives electric analoging signal and converts electric analoging signal to digital signal；

Step 4, becomes fault state vector by digital signal fusion；

Step 5, utilizes pca method to utilize the method for singular value classification to carry out dimension-reduction treatment normal condition vector X, obtains the normal condition vector of dimensionality reduction

Step 6, gas leakage signal and the daily power loss signal of extracting SF6 gas from digital signal form fault routine feature database, carry out fault routine weight computing；

Step 7, malfunction fuzzy characteristics storehouse receives fault state vector and calculates the weights obtaining malfunction；

Step 8, carries out breakdown judge or failure prediction according to the weights of malfunction。

Preferably, step 5 comprises the steps:

Step 5.1, data normalization processes:

Duty X by n the cycle of GIS switching system_mWrite as State Matrix form:

X_m=(X₁,X₂...X_n)

Wherein, X₁,X₂,...,X_nRepresent the 1st duty to the n-th cycle of GIS switching system respectively；The n dimension detection data that the duty in each cycle of GIS switching system collects by monitor are constituted；

By X_mIt is normalized and obtains X:

Wherein,Represent X_mAverage, σ represents X_mStandard deviation；

Step 5.2, utilizes covariance matrix to carry out singular value decomposition:

Wherein, S represents the covariance matrix between data element, σ_i, i=1,2 ..., n, the 1st of representing matrix S is to the n-th singular value respectively, and Λ represents the matrix that singular value is constituted, U and U^TIt it is the representation of singular value decomposition；

Step 5.3, takes pivot element:

Take front k the pivot of matrix Λ as analytical element；And take the P=(u of correspondence₁,u₂...u_k)；Wherein, u_i, i=1,2 ..., k, extremely front kth is vectorial for first 1st of the correspondence analysis element of difference representing matrix U, the vector that front k the vector of P representing matrix U is constituted；

Step 5.4, obtains the form of descending of X

Wherein, T=XP。

Preferably, in step 7, the foundation in malfunction fuzzy characteristics storehouse is based on TS fuzzy model, comprises the steps:

Step 7.1, sets up fuzzy rule:

Article i-th, fuzzy rule RⁱThe contribution component y in (k+1) moment to the output of TS fuzzy modelⁱ(k+1) it is:

Wherein, c is fuzzy rule number, and n is the input variable number of TS fuzzy model, x₁(k),x₂(k),…,x_nK the TS fuzzy model n in () respectively kth moment ties up the regression variable of inputoutput data, x (k)=[x₁(k),x₂(k),…,x_n(k)] for the input vector of kth moment TS fuzzy model；Represent the fuzzy set with linear membership function of n Fuzzy subspaee of corresponding i-th fuzzy rule,It it is the n dimension consequent parameter of i-th fuzzy rule；

Step 7.2, output calculates:

Wherein, β_iIt is the fitness of i-th fuzzy rule, definition

Wherein r=c (n+1), obtains:

Y (k+1)=Φ (k)^TΘ(k)

Wherein, Φ (k) and Θ (k) represents the parameter of the fuzzy rule in the kth moment, θ₁,θ₂,…,θ_rFor the column vector of Θ (k), r represents the sequence number of column vector, r=c (n+1), Θ (k) by ascending sequence number using every c column vector as one group of Column vector groups, p_uvFor the u column vector, u=1～C, v=0～n, p in the Column vector groups that sequence number is v of Θ (k)_uvRepresent the consequent parameter in the kth moment。

Preferably, step 8 comprises the steps:

Step 8.1, sets up fuzzy rule:

Set up the cluster centre vector v of-1 moment of input x (k) in Equation for Calculating TS fuzzy model kth moment and kth corresponding i-th fuzzy rule_i(k-1) distance d '_i(k):

Wherein, x (k)=(x₁(k),x₂(k),...,x_n(k)), x_jK () represents TS fuzzy model kth moment jth input vector, c is fuzzy rule number；

Step 8.2, evaluates input x (k) to each cluster centre v_i(k-1), i=1,2 ..., the degree of membership u ' of c_i(k), wherein v_i(k-1) the cluster centre vector of-1 moment corresponding i-th fuzzy rule of kth is represented,

Wherein, f represents fuzzy factor, and the value of f is more than 1；D '_jK () represents the distance that the cluster centre of-1 moment corresponding j-th strip fuzzy rule of input x (k) and kth in TS fuzzy model kth moment is vectorial；

Step 8.3, revises cluster centre vector:

v_i(k)=v_i(k-1)+λu′_i(k)²[x(k)-v_i(k-1)]

Wherein, λ represents learning rate, the number ranged for less than 1 more than 0 of the value of λ；V_iK () is the cluster centre vector of kth moment corresponding i-th fuzzy rule；

Step 8.4, updates distance d '_i(k) and degree of membership u '_i(k):

Step 8.5, calculates the fitness β that TS fuzzy model is exported by i-th fuzzy rule_i:

Wherein, u_jThe front jth vector of the correspondence analysis element of representing matrix U；

Step 8.6, according to formula y (k+1)=Φ (k)^TΘ (k), utilizes method of least square to obtain Θ (k)=(Φ^TΦ)^-1Φ^TY (k+1)；Wherein y (k+1) represents that the contribution component that TS fuzzy model is exported by fuzzy rule in kth+1 moment, Φ (k) and Θ (k) represent the parameter of the fuzzy rule in the kth moment；

Step 8.7, to not in the same time under Φ (k) and Θ (k) add up, statistics y and yf also sets up the fuzzy rule base of the fuzzy specification storehouse of y and yf；Wherein y represents in dimensionality reduction data modeThe probability broken down in situation, yf represents in dimensionality reduction data modeThe probability that in situation, next operation can break down；

Step 8.8, utilizes y and yf and threshold ratio set in advance relatively to carry out breakdown judge or failure prediction。

Preferably, in step 8.8, y and yf and threshold ratio set in advance is utilized relatively to carry out the step of breakdown judge or failure prediction as follows:

If y value is more than upper limit threshold Au, then judge that this there occurs fault；

If y value is less than lower threshold AL, then judge that this next state is in normal operating conditions, it does not have break down；

If y value is less than or equal to upper limit threshold Au and be more than or equal to lower threshold AL, it is impossible to judge this next state, then enables yf and upper limit threshold Au and lower threshold AL and carry out failure prediction as follows:

If yf value is more than upper limit threshold Au, then judge that next operation can break down；

If yf value is less than lower threshold AL, then judge that next operation will not break down；

If yf value is less than or equal to upper limit threshold Au and be more than or equal to lower threshold AL, then it is assumed that next operation wouldn't break down。

Compared with prior art, beneficial effects of the present invention is as follows: can carry out the diagnosis of GIS fault based on the information of multiple sensors signals collecting, increases the accuracy of diagnosis, and the situation reducing wrong report occurs。According to the current GIS duty switched, the present invention both can judge that this switched whether normal operation, it is also possible to according to whether multi-source information forecast place GIS switch next time can break down, fault serves the effect of forecast。The present invention can also according to the exception of the routine work state of GIS switch, it is judged that the possibility that GIS will break down, and eliminates contingent consequence in advance。Groundwork realizes in software, and hardware requirement is low, significantly saves system cost。

Accompanying drawing explanation

By reading detailed description non-limiting example made with reference to the following drawings, the further feature purpose of the present invention and advantage will become more apparent upon。

Fig. 1 is GIS switchgear operating state of the present invention monitoring system structure schematic diagram；

Fig. 2 is that GIS switchgear operating state of the present invention monitoring system information merges schematic diagram；

Fig. 3 is GIS switchgear operating state faults of monitoring system feature Fuzzy storehouse of the present invention schematic diagram。

Detailed description of the invention

The present invention is described in detail to adopt specific embodiment below。Following example will assist in those skilled in the art and are further appreciated by the present invention, but do not limit the present invention in any form。It should be pointed out that, to those skilled in the art, without departing from the inventive concept of the premise, it is also possible to make some changes and improvements。These broadly fall into protection scope of the present invention。

As it is shown in figure 1, GIS switchgear operating state of the present invention monitoring system, multi-source information acquiring unit, information fusion unit, fault decision-making and forecast unit。

Multi-source information acquiring unit, multi-source information acquiring unit detects the duty of GIS switching system and forms detection signal, and detection signal condition is become electric analoging signal by multi-source information acquiring unit again；Arranging monitor and signal conditioning circuit in multi-source information acquiring unit, monitor includes relay control circuit state detection module, connects execution high-voltage switch gear state detection module, mechanical mechanism state detection module and the detection module that leaks gas。

Multi-source information acquiring unit utilizes multiple sensors technology, the duty of detection GIS switching system, including: relay control circuit state-detection, connection perform high-voltage switch gear state-detection, mechanical mechanism state-detection, other Condition Detections and signal conditioning circuit。

Wherein, relay control circuit detects, and predominantly detects: daily secondary circuit power attenuation detects, and divide-shut brake coil transient current detects, switch motion power detection。

Connect and perform high-voltage switch gear state-detection, predominantly detect: divide-shut brake transient transcendence detects, electric arc Electromagnetic Wave Detection。

Mechanical mechanism state-detection, predominantly detects: the range ability detection of contact, the vibration detection of machinery。

Other Condition Detections, predominantly detect: the gas leakage detection of arc extinguishing dielectric gas SF6。The signal condition that the sensor detects is become the electric analoging signal that signals collecting board is capable of identify that by signal conditioning circuit, and is delivered to data collecting card。

Information fusion unit, information fusion unit is arranged on pcb board, and information fusion unit is arranged in computer terminal by PCI slot, and information fusion unit receives electric analoging signal, electric analoging signal and preset value are compared, it is judged that the duty of GIS switching system；Information fusion unit includes interconnective data collecting plate card, fault extraction module, information fusion module and fault routine judge module；Data collecting plate card and number modulate circuit communication。

Information fusion unit is the information utilizing multi-source information acquiring unit to gather, the module of the feature extracting fault the fusion carrying out information。Specifically include that data collecting plate card, fault extraction module, information fusion unit and fault routine judge module。

Wherein, data collecting plate card gathers the signal of telecommunication of the GIS duty of multi-source information acquiring unit, converts the signal of telecommunication of GIS duty to digital signal and is input in PC。

Fault signature extraction module, utilizes the GIS operating state data that data collecting plate card gathers, and digital signal fusion becomes fault state vector, and the vector classification of normal condition vector with malfunction is delivered in information fusion module。

Fault decision-making and forecast unit, fault decision-making is reported to the police according to the comparative result of electric analoging signal Yu preset value with forecast unit；Fault decision-making includes interconnective malfunction fuzzy characteristics storehouse, breakdown judge module and failure prediction module with forecast unit；Malfunction fuzzy characteristics storehouse communicates with information fusion module, and breakdown judge module communicates with malfunction fuzzy characteristics storehouse, and failure prediction module communicates with fault routine judge module and breakdown judge module respectively。

Information fusion module is to utilize pca method (PCA) to utilize the method for singular value classification to carry out dimension-reduction treatment duty vector X, obtainsFault routine feature, directly records generalized information system according to the gas leakage situation of SF6 gas and the abnormal situation of daily power attenuation and abnormal feature occurs, utilize these two high level information to set up fault routine feature database and can carry out fault routine weight computing。

Fault decision-making and forecast unit, the GIS duty after filtering according to information fusion unitHistorical data is utilized to set up the malfunction fuzzy characteristics storehouse based on TS model, it is possible to calculate the weights obtaining this malfunction, then weights are input to breakdown judge module and carry out the judgement of fault and the forecast of future malfunction。

Judge by the fault routine weights that the fault routine judge module in information fusion module calculates for described fault routine, need not in conjunction with other information, if it occur that gas leakage and daily power can directly judge that generalized information system breaks down extremely, there is limit priority。

Shown in Fig. 2, main employing is PCA pca method, and GIS duty X is carried out dimension-reduction treatment, and specific algorithm is:

Data normalization processes。Multi information acquisition module collects the generalized information system duty in this cycle:

X₁=(x₁,x₂...x_n)^T

Write the state in n cycle as State Matrix form:

X_m=(X₁,X₂...X_n)；Wherein, X₁,X₂,...,X_nRepresent the 1st duty to the n-th cycle of GIS switching system respectively；The n dimension detection data that the duty in each cycle of GIS switching system collects by monitor are constituted；

Xm is normalized and obtains:

Wherein: n represents the dimension of data, T representing matrix transposition,Represent X_mAverage, σ represents X_mStandard deviation；

Singular value decomposition, covariance matrix carries out singular value decomposition:

Wherein,Wherein: S represents the covariance matrix between data element, σ_i, i=1,2 ..., n, the 1st of representing matrix S is to the n-th singular value respectively, and Λ represents the matrix that singular value is constituted, U and U^TIt it is the representation of singular value decomposition；

Take pivot element, take front k the pivot of Λ as analytical element；And take the P=(u of correspondence₁,u₂...u_k)；Wherein, u_i, i=1,2 ..., k, extremely front kth is vectorial for first 1st of the correspondence analysis element of difference representing matrix U, the vector that front k the vector of P representing matrix U is constituted；

Obtain the form of descending of X,Wherein T=XP。

Fig. 3 show the fuzzy library structure figure of fault signature of the present invention。

This module is mainly the fuzzy rule according to TS fuzzy model, and input quantity is carried out Fuzzy processing dominant mechanism is:

(1.1) fuzzy rule。

Article i-th, the contribution component y that system is exported by TS fuzzy ruleⁱ(k+1) " If ... Then " statement can be used to be expressed as follows:

Wherein, c is fuzzy rule number, and n is the input variable number of TS fuzzy model, x₁(k),x₂(k),…,x_nK the TS fuzzy model n in () respectively kth moment ties up the regression variable of inputoutput data, x (k)=[x₁(k),x₂(k),…,x_n(k)] for the input vector of kth moment TS fuzzy model；Represent the fuzzy set with linear membership function of n Fuzzy subspaee of corresponding i-th fuzzy rule,It it is the n dimension consequent parameter of i-th fuzzy rule；

(1.2) output calculates。

Definition β_iFitness for fuzzy rule i, then the model output y (k+1) in (k+1) moment can be calculated by equation below:

Wherein, β_iIt is the fitness of i-th fuzzy rule, definition

Wherein r=c (n+1), it is possible to obtain:

Y (k+1)=Φ (k)^TΘ(k)

Wherein, Φ (k) and Θ (k) represents the parameter of the fuzzy rule in the kth moment, θ₁,θ₂,…,θ_rFor the column vector of Θ (k), r represents the sequence number of column vector, r=c (n+1), Θ (k) by ascending sequence number using every c column vector as one group of Column vector groups, p_uvFor the u column vector, u=1～C, v=0～n, p in the Column vector groups that sequence number is v of Θ (k)_uvRepresent the consequent parameter in the kth moment。

GIS fault signature fuzzy rule base is set up, it is necessary to going out the fuzzy rule two parameter Φ (k) and Θ (k) in the kth moment by the method for system identification according to experimental data identification, concrete flow process is as follows according to above-mentioned fuzzy rule:

(2.1) fault signature statistics

According to a large amount of GIS switch experiment, count in dimensionality reduction data modeThe probability y broken down in situation, and at the probability yf that next operation can break down。Do not test the probability of acquisition, by arriving that multidimensional difference is sent out。

(2.2) fuzzy rule

Cluster centre vector V (1)=[v₁(1),v₂(1),…,v_c(1) initial value] can adopt C clustering algorithm to obtain with the off-line identification of a part of experimental data, is then updated。Acquisition calculates input x (k) and the cluster centre vector v of-1 moment of kth corresponding i-th fuzzy rule by equation below_i(k-1) distance d '_i(k):

Wherein, x (k)=(x₁(k),x₂(k),...,x_n(k)), x_jK () represents TS fuzzy model kth moment jth input vector, c is fuzzy rule number；

Evaluate input x (k) to each cluster centre v_i(k-1), i=1,2 ..., the degree of membership u ' of c_i(k), wherein v_i(k-1) the cluster centre vector of-1 moment corresponding i-th fuzzy rule of kth is represented,Wherein, f represents fuzzy factor, and the value of f is more than 1；D '_jK () represents the distance that the cluster centre of-1 moment corresponding j-th strip fuzzy rule of input x (k) and kth in TS fuzzy model kth moment is vectorial；

Based on degree of membership and the fuzzy rule learning rate in (k-1) moment x (k), utilize equation below correction cluster centre vector V (k-1): v_i(k)=v_i(k-1)+λu′_i(k)²[x(k)-v_i(k-1)]；Wherein λ represents learning rate, the number ranged for less than 1 more than 0 of the value of λ；V_iK () is the cluster centre vector of kth moment corresponding i-th fuzzy rule；

According to the new cluster centre obtained vector, the distance d ' of more newly inputted x (k) and central point_i(k) and degree of membership u '_i(k):

Calculate the fitness β that system is exported by i-th fuzzy rule_i:u_i,u_jIt is by degree of membership u '_iK () tries to achieve vector: wherein, u_jJ vector before the of the correspondence analysis element of representing matrix U；

Calculate when inputting as x (k), the fitness that system is exported by the i-th rule:

Then can in the hope of vector:

Φ (k)=[β₁,…,β_c,β₁x₁(k),…,β_cx₁(k) ..., β₁x_n(k),…,β_cx_n(k)]^T.

According to formula y (k+1)=Φ (k)^TΘ (k), it is known that y (k+1) and Φ (k), utilizes method of least square to obtain Θ (k)=(Φ^TΦ)^-1Φ^TY (k+1)；Wherein y (k+1) represents that the contribution component that system is exported by fuzzy rule in the k+1 moment, Φ (k) and Θ (k) represent the parameter of the fuzzy rule in the k moment。

By above-mentioned steps, just obtained two parameter Φ (k) and Θ (k) of fuzzy rule by the method for system identification, just establish the fuzzy specification storehouse of y。Utilize same method, it is also possible to set up the fuzzy rule base of yf。

(3.1) the judgement overall flow of fault

According to the state that multi-source information acquiring unit gathers, after precision information integrated unit dimensionality reduction, it is input to the weights being calculated obtaining breaking down under this state in the fuzzy rule base set up, carries out judgement and the prediction of fault according to weights。

(3.2) breakdown judge mechanism

As it is shown on figure 3, first y value and upper limit threshold Au compare, if it find that current failure weights have exceeded threshold value, then directly judge that this there occurs fault；

If y value is less than lower threshold AL, then judge that this next state is in normal operating conditions, it does not have break down；

If between y value upper limit threshold Au and lower threshold AL, then utilizing y to cannot be carried out the judgement of fault；Enable yf judgment mechanism and carry out failure prediction after the same method。

The judgement of fault and the forecast of fault can be carried out according to above-mentioned method。

Above specific embodiments of the invention are described。It is to be appreciated that the invention is not limited in above-mentioned particular implementation, those skilled in the art can make a variety of changes within the scope of the claims or revise, and this has no effect on the flesh and blood of the present invention。When not conflicting, embodiments herein and the feature in embodiment can arbitrarily be mutually combined。

Claims (10)

1. a GIS switchgear operating state monitoring system, it is characterised in that including:

Multi-source information acquiring unit, described multi-source information acquiring unit detects the duty of GIS switching system and forms detection signal, and described detection signal condition is become electric analoging signal by described multi-source information acquiring unit again；

Information fusion unit, described information fusion unit is arranged in computer terminal, and described information fusion unit receives described electric analoging signal, described electric analoging signal and preset value is compared, it is judged that the duty of GIS switching system；

Fault decision-making and forecast unit, described fault decision-making carries out reporting to the police or forecasting according to the comparative result of described electric analoging signal Yu described preset value with forecast unit。

2. GIS switchgear operating state according to claim 1 monitoring system, it is characterised in that interconnective monitor and signal conditioning circuit are set in described multi-source information acquiring unit。

3. GIS switchgear operating state according to claim 2 monitoring system, it is characterized in that, described monitor includes relay control circuit state detection module, connects execution high-voltage switch gear state detection module, mechanical mechanism state detection module and the detection module that leaks gas。

4. GIS switchgear operating state according to claim 2 monitoring system, it is characterised in that described information fusion unit includes interconnective data collecting plate card, fault extraction module, information fusion module and fault routine judge module；Described data collecting plate card and described modulate circuit communication。

5. GIS switchgear operating state according to claim 4 monitoring system, it is characterised in that described fault decision-making includes interconnective malfunction fuzzy characteristics storehouse, breakdown judge module and failure prediction module with forecast unit；Described malfunction fuzzy characteristics storehouse communicates with described information fusion module, described breakdown judge module communicates with described malfunction fuzzy characteristics storehouse, described failure prediction module communicates with described fault routine judge module and described breakdown judge module respectively, and described fault routine judge module communicates with described fault routine judge module。

6. the using method of a GIS switchgear operating state monitoring system, it is characterised in that comprise the steps:

Step 1, utilizes the duty of monitor detection GIS switching system and forms detection signal；

Step 2, detection signal condition is become electric analoging signal by signal conditioning circuit；

Step 3, data collecting plate card receives electric analoging signal and converts electric analoging signal to digital signal；

Step 4, becomes fault state vector by digital signal fusion；

Step 5, utilizes pca method to utilize the method for singular value classification to carry out dimension-reduction treatment normal condition vector X, obtains the normal condition vector of dimensionality reduction

Step 6, gas leakage signal and the daily power loss signal of extracting SF6 gas from digital signal form fault routine feature database, carry out fault routine weight computing；

Step 7, malfunction fuzzy characteristics storehouse receives fault state vector and calculates the weights obtaining malfunction；

Step 8, carries out breakdown judge or failure prediction according to the weights of malfunction。

7. the using method of GIS switchgear operating state according to claim 6 monitoring system, it is characterised in that described step 5 comprises the steps:

Step 5.1, data normalization processes:

Duty X by n the cycle of GIS switching system_mWrite as State Matrix form:

X_m=(X₁,X₂...X_n)

Wherein, X₁,X₂,...,X_nRepresent the 1st duty to the n-th cycle of GIS switching system respectively；The n dimension detection data that the duty in each cycle of GIS switching system collects by monitor are constituted；

By X_mIt is normalized and obtains X:

$X=\frac{X_m-\stackrel{\‾}{X}}{\mathrm{\σ}}$

Wherein,Represent X_mAverage, σ represents X_mStandard deviation；

Step 5.2, utilizes covariance matrix to carry out singular value decomposition:

$S=\frac{1}{n-1}{X}^{T}X={\mathrm{U\ΛU}}^T$

Wherein, S represents the covariance matrix between data element, σ_i, i=1,2 ..., n, the 1st of representing matrix S is to the n-th singular value respectively, and Λ represents the matrix that singular value is constituted, U and U^TIt it is the representation of singular value decomposition；

Step 5.3, takes pivot element:

Take front k the pivot of matrix Λ as analytical element；And take the P=(u of correspondence₁,u₂...u_k)；Wherein, u_i, i=1,2 ..., k, extremely front kth is vectorial for first 1st of the correspondence analysis element of difference representing matrix U, the vector that front k the vector of P representing matrix U is constituted；

Step 5.4, obtains the form of descending of X

$\hat{X}={\mathrm{TP}}^T$

Wherein, T=XP。

8. the using method of GIS switchgear operating state according to claim 7 monitoring system, it is characterised in that in described step 7, the foundation in malfunction fuzzy characteristics storehouse is based on TS fuzzy model, comprises the steps:

Step 7.1, sets up fuzzy rule:

Article i-th, fuzzy rule RⁱThe contribution component y in (k+1) moment to the output of TS fuzzy modelⁱ(k+1) it is:

$\begin{array}{c}{R}^i:If{x}_1\left(k\right)is{A}_1^{i}and{x}_2\left(k\right)is{A}_2^{i}and\mathrm{...}and{x}_n\left(k\right)is{A}_n^i\\ Then{y}^i(k+1)=p_0^i+p_1^i{x}_1+\mathrm{...}+p_n^i{x}_n;\end{array},i=1,\mathrm{2...}c$

Wherein, c is fuzzy rule number, and n is the input variable number of TS fuzzy model, x₁(k),x₂(k),…,x_nK the TS fuzzy model n in () respectively kth moment ties up the regression variable of inputoutput data, x (k)=[x₁(k),x₂(k),…,x_n(k)] for the input vector of kth moment TS fuzzy model；Represent the fuzzy set with linear membership function of n Fuzzy subspaee of corresponding i-th fuzzy rule,It it is the n dimension consequent parameter of i-th fuzzy rule；

Step 7.2, output calculates:

$\begin{array}{c}y(k+1)=\underset{i=1}{\overset{c}{\Σ}}{\mathrm{\β}}_i{y}^i(k+1)=\underset{i=1}{\overset{c}{\Σ}}{\mathrm{\β}}_i(p_0^i+p_1^i{x}_1(k)+...+p_n^i{x}_n(k\left)\right)\\ =\underset{i=1}{\overset{c}{\Σ}}(p_0^i+p_1^i+\mathrm{...}+p_n^i){({\mathrm{\β}}_i+{\mathrm{\β}}_i{x}_1(k)+\mathrm{...}+{\mathrm{\β}}_i{x}_n(k\left)\right)}^T\end{array}$

Wherein, β_iIt is the fitness of i-th fuzzy rule, definition

$\left\{\begin{array}{c}\mathrm{\Θ}\left(k\right)={\[{\mathrm{\θ}}_1,{\mathrm{\θ}}_2,\mathrm{...},{\mathrm{\θ}}_r\]}^T={\[p_{10},p_{20},\mathrm{...},p_{c0},p_{11},p_{21},\mathrm{...},p_{c1},\mathrm{...},p_{cn}\]}^T;\\ \mathrm{\Φ}\left(k\right)={\[{\mathrm{\β}}_1,\mathrm{...},{\mathrm{\β}}_c,{\mathrm{\β}}_1{x}_1\left(k\right),\mathrm{...},{\mathrm{\β}}_c{x}_1\left(k\right),\mathrm{...},{\mathrm{\β}}_1{x}_n\left(k\right),\mathrm{...},{\mathrm{\β}}_c{x}_n\left(k\right)\]}^T;\end{array}\right.$

Obtain:

Y (k+1)=Φ (k)^TΘ(k)

Wherein, Φ (k) and Θ (k) represents the parameter of the fuzzy rule in the kth moment, θ₁,θ₂,…,θ_rFor the column vector of Θ (k), r represents the sequence number of column vector, r=c (n+1), Θ (k) by ascending sequence number using every c column vector as one group of Column vector groups, p_uvFor the u column vector, u=1～C, v=0～n, p in the Column vector groups that sequence number is v of Θ (k)_uvRepresent the consequent parameter in the kth moment。

9. the using method of GIS switchgear operating state according to claim 8 monitoring system, it is characterised in that described step 8 comprises the steps:

Step 8.1, sets up fuzzy rule:

Set up the cluster centre vector v of-1 moment of input x (k) in Equation for Calculating TS fuzzy model kth moment and kth corresponding i-th fuzzy rule_i(k-1) distance d '_i(k):

$d_i^{\′}\left(k\right)=\sqrt{\underset{j=1}{\overset{n}{\Σ}}{\[x_j\left(k\right)-v_i(k-1)\]}^2};i=1,2,...,c$

Wherein, x (k)=(x₁(k),x₂(k),...,x_n(k)), x_jK () represents TS fuzzy model kth moment jth input vector, c is fuzzy rule number；

Step 8.2, evaluates input x (k) to each cluster centre v_i(k-1), i=1,2 ..., the degree of membership u ' of c_i(k), wherein v_i(k-1) the cluster centre vector of-1 moment corresponding i-th fuzzy rule of kth is represented,

$u_i^{\′}\left(k\right)={\[\underset{j=1}{\overset{c}{\Σ}}\left(\frac{d_i^{\′}\left(k\right)}{d_j^{\′}\left(k\right)}\right)\]}^{\frac{(f-1)}{2}},i=1,2,...,c$

Wherein, f represents fuzzy factor, and the value of f is more than 1；D '_jK () represents the distance that the cluster centre of-1 moment corresponding j-th strip fuzzy rule of input x (k) and kth in TS fuzzy model kth moment is vectorial；

Step 8.3, revises cluster centre vector:

v_i(k)=v_i(k-1)+λu′_i(k)²[x(k)-v_i(k-1)]

Wherein, λ represents learning rate, the number ranged for less than 1 more than 0 of the value of λ；V_iK () is the cluster centre vector of kth moment corresponding i-th fuzzy rule；

Step 8.4, updates distance d '_i(k) and degree of membership u '_i(k):

$\begin{array}{cc}{d}_i^{\′}\left(k\right)=\sqrt{\underset{j=1}{\overset{n}{\Σ}}{\[x_j\left(k\right)-v_i(k-1)\]}^2};i=1,2,\mathrm{...},c& u_i^{\′}\left(k\right)={\[\underset{j=1}{\overset{c}{\Σ}}\left(\frac{d_i^{\′}\left(k\right)}{d_j^{\′}\left(k\right)}\right)\]}^{\frac{(f-1)}{2}},i=1,2,\mathrm{...},c\end{array};$

Step 8.5, calculates the fitness β that TS fuzzy model is exported by i-th fuzzy rule_i:

${\mathrm{\β}}_i=\underset{j=1}{\overset{c}{\Σ}}\left(\frac{u_i}{u_j}\right),i=1,2,...,c$

Wherein, u_jThe front jth vector of the correspondence analysis element of representing matrix U；

Step 8.6, according to formula y (k+1)=Φ (k)^TΘ (k), utilizes method of least square to obtain Θ (k)=(Φ^TΦ)^-1Φ^TY (k+1)；Wherein y (k+1) represents that the contribution component that TS fuzzy model is exported by fuzzy rule in kth+1 moment, Φ (k) and Θ (k) represent the parameter of the fuzzy rule in the kth moment；

Step 8.7, to not in the same time under Φ (k) and Θ (k) add up, statistics y and yf also sets up the fuzzy rule base of the fuzzy specification storehouse of y and yf；Wherein y represents in dimensionality reduction data modeThe probability broken down in situation, yf represents in dimensionality reduction data modeThe probability that in situation, next operation can break down；

Step 8.8, utilizes y and yf and threshold ratio set in advance relatively to carry out breakdown judge or failure prediction。

10. the using method of GIS switchgear operating state according to claim 9 monitoring system, it is characterised in that in described step 8.8, utilizes y and yf and threshold ratio set in advance relatively to carry out the step of breakdown judge or failure prediction as follows:

If y value is more than upper limit threshold Au, then judge that this there occurs fault；

If y value is less than lower threshold AL, then judge that this next state is in normal operating conditions, it does not have break down；

If y value is less than or equal to upper limit threshold Au and be more than or equal to lower threshold AL, it is impossible to judge this next state, then enables yf and upper limit threshold Au and lower threshold AL and carry out failure prediction as follows:

If yf value is more than upper limit threshold Au, then judge that next operation can break down；

If yf value is less than lower threshold AL, then judge that next operation will not break down；

If yf value is less than or equal to upper limit threshold Au and be more than or equal to lower threshold AL, then it is assumed that next operation wouldn't break down。