CN114047705A - Single-phase earth fault detection constant value self-adaptive setting method and system - Google Patents
Single-phase earth fault detection constant value self-adaptive setting method and system Download PDFInfo
- Publication number
- CN114047705A CN114047705A CN202111485796.0A CN202111485796A CN114047705A CN 114047705 A CN114047705 A CN 114047705A CN 202111485796 A CN202111485796 A CN 202111485796A CN 114047705 A CN114047705 A CN 114047705A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- phase earth
- tree
- earth fault
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000009826 distribution Methods 0.000 claims abstract description 48
- 230000007935 neutral effect Effects 0.000 claims description 24
- 230000003044 adaptive effect Effects 0.000 claims description 21
- 230000001629 suppression Effects 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000002955 isolation Methods 0.000 claims 1
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Locating Faults (AREA)
Abstract
A single-phase earth fault detection fixed value self-adaptive setting method and a system are characterized in that data related to a single-phase earth fault of a power distribution network are collected and judged, key system parameters are calculated after invalid data are cleaned and removed, a fault type identification model is built by utilizing a calculation result, distribution network wave recording data are collected in real time, the data are input into the fault type identification model to be subjected to fault type identification, typical fault characteristics are found, and then single-phase earth fault detection fixed value self-adaptive setting and field switch equipment control are carried out. The method and the device realize differential setting and self-adaptive setting of the line protection constant value, effectively improve the detection level of the single-phase earth fault, and further powerfully ensure the power supply reliability and safety of the power distribution network.
Description
Technical Field
The invention relates to the field of single-phase earth fault detection constant value setting of a power distribution network, in particular to a method and a system for self-adaptively setting a single-phase earth fault detection constant value.
Background
The safety and stability of the power system are closely related to the production and life quality of people. Compared with a high-voltage transmission network, the medium-voltage distribution network has higher probability of faults, and particularly, single-phase earth faults occur more frequently. Statistics show that single-phase earth faults account for about 80% of the total number of faults in the distribution network. When a single-phase earth fault occurs in a power distribution network with a neutral point non-effective earth operation mode, a short circuit loop cannot be formed, and only small earth fault current is caused by distributed capacitance of a system, so that the power distribution network is also called as a small-current earth fault. At the moment, the line voltage between three phases of the system is basically kept unchanged, the load power supply is not influenced, and the system can operate for a period of time with a fault so as to take treatment measures and avoid the influence on users caused by sudden interruption of the power supply. Early protocols provided that the run could be continued for 1-2 hours. When the scale of an early distribution network is small, the grounding current is small when transient grounding faults occur, and most of grounding electric arcs can be automatically extinguished, or the grounding electric arcs can be automatically extinguished under the assistance of arc suppression coils. However, with the development of urban power distribution networks, the proportion of cable lines in the power grid is increased, more and more mixed lines of cables and overhead lines are provided, the zero capacitance current of the power distribution network with single-phase earth fault is large, arc extinction is difficult, overvoltage caused by the zero capacitance current is easy to cause the second point earthing of the insulation weak point of a non-fault phase, so that the accident is enlarged, and huge economic loss and severe social influence are further brought.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a method and a system for self-adaptive setting of a single-phase earth fault detection fixed value.
The invention adopts the following technical scheme:
a single-phase earth fault detection constant value self-adaptive setting method is characterized by comprising the following steps:
step 1, collecting data related to the judgment of the single-phase earth fault of the power distribution network;
step 2, cleaning the data collected in the step 1 to remove invalid data;
step 3, calculating key system parameters including capacitance current IC, arc suppression coil compensation degree v and branch line current three-phase unbalance degree U according to the data cleaned in the step 2fIThree-phase unbalance degree U of bus voltagefV;
Step 4, constructing a fault type identification model, and inputting the result of the step 3 into the fault type identification model for model training to obtain a trained fault type identification model;
step 5, calculating typical earth fault characteristics under different scenes;
step 6, collecting distribution network wave recording data in real time, and judging whether the distribution network wave recording data is abnormal or not; if the fault is abnormal, inputting the recording data and the real-time external data into the fault type identification model in the step 4 for fault type identification, finding p typical fault characteristics by using the method in the step 5, and entering the step 7; otherwise, continuously acquiring the wave recording data of the distribution network in real time;
step 7, self-adaptive setting of a single-phase earth fault detection fixed value;
and 8, controlling the field switching equipment according to the result of the step 7.
In step 1, the data related to the judgment of the single-phase earth fault of the power distribution network comprises wave recording data and external data acquired by a fault indicator installed in the power distribution network system within a set time period; the external data includes environmental data and weather data.
In step 4, the method for constructing the fault type identification model includes:
judging the type of the tree to be constructed according to the input data set, and constructing a classification tree if the tree is discrete data; if the data is continuous data, constructing a regression tree; if the fault type identification result is a classification tree, the fault type identification result can be directly obtained through the classification tree; if it is a regression tree, all regression trees constitute a set of regression trees, which is specific to the ith data xiSatisfies the following relation:
wherein the content of the first and second substances,representing regression Tree set for ith data xiK represents the number of trees, fk(xi) Representing the use of kth tree for ith data xiF represents all regression tree spaces, w represents all regression tree node weight sets, q represents all regression tree node sets, and T represents the total number of all regression tree nodes;representing an m-dimensional real vector space,representing a one-dimensional real vector space;
if the classification tree is used, the classified tree can directly distinguish the fault type;
if a regression tree is used, the s-type data with the maximum judgment value obtained by descending order has relevance with the fault type.
The objective function of the regression tree set in the fault type identification model is as follows:
wherein, yiRepresenting data xiThe original label of (a) is a convex loss function which can be derived, gamma and lambda are respectively a first bias term and a second bias term, and the adjustment and setting can be carried out by a person skilled in the art according to the output result of the regression tree set; w is ajIs the weight of the jth node of the kth regression tree.
The weight of the jth node of the kth regression tree satisfies the following relation:
Step 5 comprises the following steps:
step 5.1, dividing single-phase earth fault scenes;
and 5.2, calculating typical characteristics under different single-phase earth fault scenes.
Step 5.1 comprises the following:
step 5.1.1, the process is carried out according to the neutral point grounding mode of a low-current grounding systemLine division, by M respectively1、M2、M3To indicate that the neutral point is not grounded, the neutral point is grounded through a small resistor and the neutral point is grounded through an arc suppression coil;
step 5.1.2, subdividing single-phase earth fault types generated by different neutral point earthing modes respectivelyThe small current grounding system with ungrounded neutral point is subjected to single-phase grounding fault types such as intermittent arc grounding, stable arc grounding and the like, wherein n1Representing the number of single-phase earth fault types that may occur in a low-current earth system with the neutral point ungrounded; then use Mi,jAnd representing the divided specific fault scene.
Step 5.2 comprises the following steps:
step 5.2.1, finding out the corresponding key system parameters under each fault scene, and finding out the time sequences A and B of each parameter under a normal scene and a fault scene;
step 5.2.2, calculating the Euclidean distance between every two points in the time sequences A and B, and storing the result into a matrix D;
step 5.2.3, find D (a) of slave D in matrix D1,b1) To D (a)fn,bfn) Shortest path of (a)1,b1) Representing the Euclidean distance between the first point of the time series A and the first point of the time series B; d (a)fn,bfn) Representing the Euclidean distance between the last point of the time series A and the last point of the time series B;
if the current node is D (a)i,bi) Then the next node must be at D (a)i+1,bi)、D(ai,bi+1)、D(ai+1,bi+1) And each selection path must be the shortest;
step 5.2.4, accumulating matrix element values, namely Euclidean distances, related to the shortest path to obtain the typical degree between A, B sequences;
and 5.2.5, setting the nn characteristics with the maximum representativeness in the scene as the representative characteristics of the scene.
In step 7, the method for adaptively setting the single-phase earth fault detection fixed value comprises the following steps:
the selected section trips, and after the instantaneous ground fault is avoided, the fault is quickly isolated nearby; short-circuit current value I when the tail end of the protected line is short-circuited under different fault scenes0Multiplying the reliability factor of the current protection I sectionObtaining a current self-adaptive quick-break protection setting value under each fault scene, wherein the current self-adaptive quick-break protection setting value meets the following relational expression:
in step 8, fitting the mapping relation between the characteristics and the system parameters and the self-adaptive current outage protection setting value under each fault scene;
fitting M based on multi-layer perceptron MLP modeli,jIn a fault scene, the mapping relationship between the characteristics and the system parameters and the adaptive current outage protection setting value is shown as the following formula:
then withComparing, if:the field switch equipment acts and is quickly isolated nearby after the instantaneous ground fault is avoided; if it isThe field switching device does not act.
The invention also discloses a single-phase earth fault detection constant value self-adaptive setting system which comprises a data acquisition and cleaning module, a key system parameter calculation module, a fault type identification model construction module, a typical earth fault characteristic calculation module, a distribution network wave recording data judgment module, a single-phase earth fault detection constant value self-adaptive setting module and a field switch equipment control module;
the data acquisition and cleaning module acquires data related to the judgment of the single-phase earth fault of the power distribution network, and the data comprises wave recording data and weather data acquired by a fault indicator installed in the power distribution network system within a set time period; after the invalid data are cleaned, inputting the cleaned data into a key system parameter calculation module and a fault type identification model module;
the key system parameter calculation module calculates capacitance current, arc suppression coil compensation degree, branch line current three-phase unbalance degree and bus voltage three-phase unbalance degree according to the received data, and inputs the calculation result to the fault type identification model construction module and the field switch equipment control module;
the fault type identification model building module judges the type of the tree to be built according to the input data set, and if the type of the tree is discrete data, a classification tree is built; if the data is continuous data, constructing a regression tree;
the typical ground fault feature calculation module divides single-phase ground fault scenes and calculates typical features under different single-phase ground fault scenes;
the distribution network wave recording data judgment module collects distribution network wave recording data in real time and judges whether the distribution network wave recording data is abnormal or not; if the fault is abnormal, inputting the recording data and the real-time external data into a model constructed by a fault type identification model construction module for fault type identification, inputting the result into a typical earth fault feature calculation module for calculation to obtain the current typical fault feature, and inputting the result into a single-phase earth fault detection fixed value self-adaptive setting module and a field switching equipment control module;
the single-phase earth fault detection constant value self-adaptive setting module adjusts the current quick-break protection constant value of each fault scene according to the input identification result and the typical characteristics, and inputs the calculated current quick-break protection constant value of each fault scene to the field switch equipment control module;
and the field switching equipment control module controls the field switching equipment to act according to the received data.
The fault type identification model constructed by the fault type identification model construction module meets the following conditions:
if the constructed classification tree is the classification tree, the fault type identification result is directly obtained through the classification tree; if a regression tree is constructed, all regression trees constitute a set of regression trees that are applied to the ith data xiSatisfies the following relation:
wherein the content of the first and second substances,representing regression Tree set for ith data xiK represents the number of trees, fk(xi) Representing the use of kth tree for ith data xiF represents all regression tree spaces, w represents all regression tree node weight sets, q represents all regression tree node sets, and T represents the total number of all regression tree nodes;representing an m-dimensional real vector space,representing a one-dimensional real vector space;
if the classification tree is used, the classified tree can directly distinguish the fault type;
if a regression tree is used, the s-type data with the maximum judgment value obtained by descending order has relevance with the fault type.
13. The fixed-value adaptive tuning system for single-phase ground fault detection according to claim 12,
the objective function of the regression tree set in the fault type identification model is as follows:
wherein, yiRepresenting data xiThe original label of (a) is a convex loss function which can be derived, gamma and lambda are respectively a first bias term and a second bias term, and the adjustment and setting can be carried out by a person skilled in the art according to the output result of the regression tree set; w is ajIs the weight of the jth node of the kth regression tree.
Compared with the prior art, the invention has the beneficial effects that:
1. differential setting and self-adaptive setting of line protection fixed values are realized, and the detection level of single-phase earth faults is effectively improved, so that the power supply reliability and safety of the power distribution network are powerfully guaranteed;
2. the provided typical fault feature method has development, the provided regression tree set target function has higher robustness, and the accuracy of a judgment result is higher.
Drawings
FIG. 1 is an overall flow chart of a single-phase earth fault detection constant value self-adaptive setting method according to the present invention;
FIG. 2 is a flow chart of the operation of an on-line control field switching device of the single-phase earth fault detection fixed value self-adaptive setting method of the present invention;
FIG. 3 is a typical degree-of-mean graph of fault characteristics of a single-phase ground fault detection constant value adaptive setting method of the present invention;
FIG. 4 is a typical degree visualization diagram of a single-phase earth fault detection constant value adaptive setting method according to the present invention;
fig. 5 is a three-layer MLP structure diagram of a single-phase ground fault detection constant value adaptive setting method of the present invention.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
A single-phase earth fault detection constant value self-adaptive setting method and a system thereof are disclosed, the flow of which is shown in figure 1, and the method specifically comprises the following steps:
step 1, collecting data related to the judgment of the single-phase earth fault of the power distribution network;
in this embodiment, the data related to determining the single-phase earth fault of the power distribution network includes wave recording data and weather data acquired by a fault indicator installed in the power distribution network system within a set time period;
step 2, cleaning the data collected in the step 1 to remove invalid data;
specifically, the invalid data may be data other than positive and negative standard deviations, and a data type in which more than 90% of the data collected within a set time period is zero; the person skilled in the art can specify the criteria of invalid data according to the actual situation;
step 3, calculating key system parameters including capacitance current I according to the data cleaned in the step 2CCompensation degree v of arc suppression coil and three-phase unbalance degree U of branch line currentfIThree-phase unbalance degree U of bus voltagefV;
Capacitance current IcThe following relation is satisfied:
Ic=(IL-I0)
I0=I*k
IL: compensating a current value by an arc suppression coil;
i: secondary side fault steady state current value;
I0: a primary side fault steady state current value;
k: the first and second transformation ratio coefficients of the equipment;
the compensation degree v of the arc suppression coil satisfies the following relational expression:
three-phase unbalance degree U of branch line currentfIThe following relation is satisfied:
Imax: maximum value of three-phase current effective values of the branch line;
Imin: the minimum value of the three-phase current effective values of the branch lines;
bus voltage three-phase unbalance degree UfVThe following relation is satisfied:
Umax: the maximum value of the three-phase voltage effective values of the bus;
Umin: the minimum value of the three-phase voltage effective values of the bus;
step 4, constructing a fault type identification model, and inputting the result of the step 3 into the fault type identification model for model training to obtain a trained fault type identification model;
those skilled in the art can select the fault type identification model according to actual situations, and those skilled in the art should know that the fault type identification model provided in the present embodiment is only a preferred embodiment.
Preferably, the fault type identification model is constructed by the following steps:
judging the type of the tree to be constructed according to the input data set, and constructing a classification tree if the tree is discrete data; such asIf the data is continuous data, constructing a regression tree; if the fault type identification result is a classification tree, the fault type identification result can be directly obtained through the classification tree; if it is a regression tree, all regression trees constitute a set of regression trees, which is specific to the ith data xiSatisfies the following relation:
wherein the content of the first and second substances,representing regression Tree set for ith data xiK represents the number of trees, fk(xi) Representing the use of kth tree for ith data xiF represents all regression tree spaces, w represents all regression tree node weight sets, q represents all regression tree node sets, and T represents the total number of all regression tree nodes;representing an m-dimensional real vector space,representing a one-dimensional real vector space;
the objective function of the tree set is:
wherein, yiRepresenting data xiIs an original label, l is an original label that can be evaluatedThe derived convex loss function, gamma and lambda are respectively a first bias term and a second bias term, and those skilled in the art can adjust and set according to the output result of the regression tree set; w is ajThe weight of the jth node of the kth regression tree satisfies the following relation:
if the classification tree is used, the classified tree can directly distinguish the fault type;
if a regression tree is used, the s-type data with the maximum judgment value obtained by descending order has relevance with the fault type.
Step 5, calculating typical earth fault characteristics under different scenes;
step 5.1, dividing single-phase earth fault scenes;
step 5.1.1, dividing according to the neutral point grounding mode of the low-current grounding system, and respectively using M1、M2、M3To indicate that the neutral point is not grounded, the neutral point is grounded through a small resistor and the neutral point is grounded through an arc suppression coil;
step 5.1.2, subdividing single-phase earth fault types generated by different neutral point earthing modes respectivelyThe small current grounding system with ungrounded neutral point is subjected to single-phase grounding fault types such as intermittent arc grounding, stable arc grounding and the like, wherein n1Single phase earthing possible with low current earthing system with ungrounded neutral pointThe number of barrier types; by analogy thereto, useSingle-phase earth fault type indicating that a low-current earth system in which a neutral point is earthed via a small resistance may occur, usingThe single-phase grounding fault type which can occur in a small-current grounding system with a neutral point grounded through an arc suppression coil is represented;
to this end, Mi,jRepresenting the divided specific fault scene;
step 5.2, calculating typical characteristics under different single-phase earth fault scenes;
step 5.2.1, finding out the corresponding key system parameters under each fault scene, and finding out the time sequences A and B of each parameter under a normal scene and a fault scene;
step 5.2.2, calculating the Euclidean distance between every two points in the time sequences A and B, and storing the result into a matrix D;
step 5.2.3, find D (a) of slave D in matrix D1,b1) To D (a)fn,bfn) Shortest path of (a)1,b1) Representing the Euclidean distance between the first point of the time series A and the first point of the time series B; d (a)fn,bfn) Representing the Euclidean distance between the last point of the time series A and the last point of the time series B;
if the current node is D (a)i,bi) Then the next node must be at D (a)i+1,bi)、D(ai,bi+1)、D(ai+1,bi+1) And each selection path must be the shortest. From D (a)1,b1) To D (a)fn,bfn) The visualization of the shortest path of (2) is shown in fig. 4.
Step 5.2.4, accumulating matrix element values, namely Euclidean distances, related to the shortest path to obtain the typical degree between A, B sequences;
step 5.2.5, setting the nn characteristics with the maximum representativeness in the scene as the representative characteristics of the scene;
in the embodiment, the feature types of the historical fault samples in the same fault scene are the same. Averaging the typical degrees of the same feature calculated by different samples, and obtaining p features with the maximum typical degree under the fault scene through descending order, wherein the p features are the typical fault features under the fault scene if the p features are less than the total number 196 of the features under the fault scene. In fault scenario M11For example, first, the typical degree results of the same features of different samples are averaged, as shown in fig. 3, and 10 typical fault features under the fault scenario are obtained through descending order arrangement, and the results are shown in table 1:
TABLE 1 Fault scenario M1110 typical failure characteristics
Step 6, collecting distribution network wave recording data in real time, and judging whether the distribution network wave recording data is abnormal or not; if the fault is abnormal, inputting the recording data and the real-time external data into the fault type identification model in the step 4 for fault type identification, finding p typical fault characteristics by using the method in the step 5, and entering the step 7; otherwise, continuously acquiring the wave recording data of the distribution network in real time;
step 7, self-adaptive setting of a single-phase earth fault detection fixed value;
the single-phase earth fault detection setting is according to the principle: the selected section trips, and after the instantaneous ground fault is avoided, the fault is quickly isolated nearby; short-circuit current value I when the tail end of the protected line is short-circuited under different fault scenes0Multiplying the reliability factor of the current protection I sectionObtaining the current self-adaptive quick-break protection setting value under each fault scene, and obtaining the current self-adaptive quick-break protection setting value under the general conditionValue range ofThe enclosure is as follows: 1.1 to 1.3. The calculation formula is as follows:
step 8, controlling the field switch equipment according to the result of the step 7;
fitting the mapping relation between the characteristics and system parameters and the self-adaptive current outage protection setting value under each fault scene;
current quick-break protection constant value according to each fault sceneAnd combining p typical fault characteristics of each fault scene summarized in the step 5: x is the number of1、x2、…、xpAnd system parameters: capacitance current ICCompensation degree v of arc suppression coil and three-phase unbalance degree U of branch circuit currentfIAnd bus voltage three-phase unbalance degree UfV. Fitting M based on a multilayer perceptron (MLP) modeli,jIn a fault scene, the mapping relationship between the characteristics and the system parameters and the adaptive current outage protection setting value is shown as the following formula:
then withComparing, if:the field switch equipment acts and is quickly isolated nearby after the instantaneous ground fault is avoided; if it isThe field switching device does not act.
The invention also discloses a single-phase earth fault detection constant value self-adaptive setting system which comprises a data acquisition and cleaning module, a key system parameter calculation module, a fault type identification model construction module, a typical earth fault characteristic calculation module, a distribution network wave recording data judgment module, a single-phase earth fault detection constant value self-adaptive setting module and a field switch equipment control module;
the data acquisition and cleaning module acquires data related to the judgment of the single-phase earth fault of the power distribution network, and the data comprises wave recording data and weather data acquired by a fault indicator installed in the power distribution network system within a set time period; after the invalid data are cleaned, inputting the cleaned data into a key system parameter calculation module and a fault type identification model module;
the key system parameter calculation module calculates capacitance current, arc suppression coil compensation degree, branch line current three-phase unbalance degree and bus voltage three-phase unbalance degree according to the received data, and inputs the calculation result to the fault type identification model construction module and the field switch equipment control module;
the fault type identification model building module judges the type of the tree to be built according to the input data set, and if the type of the tree is discrete data, a classification tree is built; if the data is continuous data, constructing a regression tree;
the typical ground fault feature calculation module divides single-phase ground fault scenes and calculates typical features under different single-phase ground fault scenes;
the distribution network wave recording data judgment module collects distribution network wave recording data in real time and judges whether the distribution network wave recording data is abnormal or not; if the fault is abnormal, inputting the recording data and the real-time external data into a model constructed by a fault type identification model construction module for fault type identification, inputting the result into a typical earth fault feature calculation module for calculation to obtain the current typical fault feature, and inputting the result into a single-phase earth fault detection fixed value self-adaptive setting module and a field switching equipment control module;
the single-phase earth fault detection constant value self-adaptive setting module adjusts the current quick-break protection constant value of each fault scene according to the input identification result and the typical characteristics, and inputs the calculated current quick-break protection constant value of each fault scene to the field switch equipment control module;
and the field switching equipment control module controls the field switching equipment to act according to the received data.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.
Claims (13)
1. A single-phase earth fault detection constant value self-adaptive setting method is characterized by comprising the following steps:
step 1, collecting data related to the judgment of the single-phase earth fault of the power distribution network;
step 2, cleaning the data collected in the step 1 to remove invalid data;
step 3, calculating key system parameters including capacitance current I according to the data cleaned in the step 2CCompensation degree v of arc suppression coil and three-phase unbalance degree U of branch line currentfIThree-phase unbalance degree U of bus voltagefV;
Step 4, constructing a fault type identification model, and inputting the result of the step 3 into the fault type identification model for model training to obtain a trained fault type identification model;
step 5, calculating typical earth fault characteristics under different scenes;
step 6, collecting distribution network wave recording data in real time, and judging whether the distribution network wave recording data is abnormal or not; if the fault is abnormal, inputting the recording data and the real-time external data into the fault type identification model in the step 4 for fault type identification, finding p typical fault characteristics by using the method in the step 5, and entering the step 7; otherwise, continuously acquiring the wave recording data of the distribution network in real time;
step 7, self-adaptive setting of a single-phase earth fault detection fixed value;
and 8, controlling the field switching equipment according to the result of the step 7.
2. The fixed-value adaptive setting method for single-phase earth fault detection according to claim 1,
in the step 1, the data related to the judgment of the single-phase earth fault of the power distribution network comprises wave recording data and external data acquired by a fault indicator installed in the power distribution network system within a set time period; the external data includes environmental data and weather data.
3. The fixed-value adaptive setting method for single-phase earth fault detection according to claim 1,
in step 4, the method for constructing the fault type identification model includes:
judging the type of the tree to be constructed according to the input data set, and constructing a classification tree if the tree is discrete data; if the data is continuous data, constructing a regression tree; if the fault type identification result is a classification tree, the fault type identification result can be directly obtained through the classification tree; if it is a regression tree, all regression trees constitute a set of regression trees, which is specific to the ith data xiSatisfies the following relation:
wherein the content of the first and second substances,representing regression Tree set for ith data xiIs a decision value of K representsNumber of trees, fk(xi) Representing the use of kth tree for ith data xiF represents all regression tree spaces, w represents all regression tree node weight sets, q represents all regression tree node sets, and T represents the total number of all regression tree nodes;representing an m-dimensional real vector space,representing a one-dimensional real vector space;
if the classification tree is used, the classified tree can directly distinguish the fault type;
if a regression tree is used, the s-type data with the maximum judgment value obtained by descending order has relevance with the fault type.
4. The single-phase earth fault detection constant value adaptive setting method according to claim 1 or 3,
the objective function of the regression tree set in the fault type identification model is as follows:
wherein, yiRepresenting data xiThe original label of (a) is a convex loss function which can be derived, gamma and lambda are respectively a first bias term and a second bias term, and the adjustment and setting can be carried out by a person skilled in the art according to the output result of the regression tree set; w is ajIs the weight of the jth node of the kth regression tree.
6. The fixed-value adaptive setting method for single-phase earth fault detection according to claim 1,
the step 5 comprises the following steps:
step 5.1, dividing single-phase earth fault scenes;
and 5.2, calculating typical characteristics under different single-phase earth fault scenes.
7. The fixed-value adaptive setting method for single-phase earth fault detection according to claim 6,
the step 5.1 comprises the following steps:
step 5.1.1, dividing according to the neutral point grounding mode of the low-current grounding system, and respectively using M1、M2、M3To indicate that the neutral point is not grounded, the neutral point is grounded through a small resistor and the neutral point is grounded through an arc suppression coil;
step 5.1.2, subdividing single-phase earth fault types generated by different neutral point earthing modes by using M11、M12…The small current grounding system with ungrounded neutral point is subjected to single-phase grounding fault types such as intermittent arc grounding, stable arc grounding and the like, wherein n1Representing the number of single-phase earth fault types that may occur in a low-current earth system with the neutral point ungrounded; then use Mi,jAnd representing the divided specific fault scene.
8. The fixed-value adaptive setting method for single-phase earth fault detection according to claim 6,
the step 5.2 comprises the following steps:
step 5.2.1, finding out the corresponding key system parameters under each fault scene, and finding out the time sequences A and B of each parameter under a normal scene and a fault scene;
step 5.2.2, calculating the Euclidean distance between every two points in the time sequences A and B, and storing the result into a matrix D;
step 5.2.3, find D (a) of slave D in matrix D1,b1) To D (a)fn,bfn) Shortest path of (a)1,b1) Representing the Euclidean distance between the first point of the time series A and the first point of the time series B; d (a)fn,bfn) Representing the Euclidean distance between the last point of the time series A and the last point of the time series B;
if the current node is D (a)i,bi) Then the next node must be at D (a)i+1,bi)、D(ai,bi+1)、D(ai+1,bi+1) And each selection path must be the shortest;
step 5.2.4, accumulating matrix element values, namely Euclidean distances, related to the shortest path to obtain the typical degree between A, B sequences;
and 5.2.5, setting the nn characteristics with the maximum representativeness in the scene as the representative characteristics of the scene.
9. The single-phase earth fault detection constant value adaptive setting method according to claim 1 or 4,
in step 7, the method for adaptively setting the single-phase earth fault detection fixed value includes:
the selected section trips, and after the instantaneous ground fault is avoided, the fault is quickly isolated nearby; short-circuit current value I when the tail end of the protected line is short-circuited under different fault scenes0Multiplying the reliability factor of the current protection I sectionObtaining a current self-adaptive quick-break protection setting value under each fault scene, wherein the current self-adaptive quick-break protection setting value meets the following relational expression:
10. the single-phase earth fault detection constant value adaptive tuning method according to claim 1 or 9,
in the step 8, fitting a mapping relation between the characteristics and the system parameters and the adaptive current outage protection setting value under each fault scene;
fitting M based on multi-layer perceptron MLP modeli,jIn a fault scene, the mapping relationship between the characteristics and the system parameters and the adaptive current outage protection setting value is shown as the following formula:
11. A single-phase earth fault detection constant value adaptive setting system based on a single-phase earth fault detection constant value adaptive setting method according to any one of claims 1 to 10,
the single-phase earth fault detection constant value self-adaptive setting system comprises a data acquisition and cleaning module, a key system parameter calculation module, a fault type identification model construction module, a typical earth fault characteristic calculation module, a distribution network wave recording data judgment module, a single-phase earth fault detection constant value self-adaptive setting module and a field switch equipment control module;
the data acquisition and cleaning module acquires data related to the judgment of the single-phase earth fault of the power distribution network, and the data comprises wave recording data and weather data acquired by a fault indicator arranged in the power distribution network system within a set time period; after the invalid data are cleaned, inputting the cleaned data into a key system parameter calculation module and a fault type identification model module;
the key system parameter calculation module calculates capacitance current, arc suppression coil compensation degree, branch line current three-phase unbalance degree and bus voltage three-phase unbalance degree according to the received data, and inputs calculation results to the fault type identification model construction module and the field switch equipment control module;
the fault type identification model building module judges the type of the tree to be built according to the input data set, and if the type of the tree is discrete data, a classification tree is built; if the data is continuous data, constructing a regression tree;
the typical earth fault feature calculation module divides single-phase earth fault scenes and calculates typical features under different single-phase earth fault scenes;
the distribution network wave recording data judgment module collects distribution network wave recording data in real time and judges whether the distribution network wave recording data is abnormal or not; if the fault is abnormal, inputting the recording data and the real-time external data into a model constructed by a fault type identification model construction module for fault type identification, inputting the result into a typical earth fault feature calculation module for calculation to obtain the current typical fault feature, and inputting the result into a single-phase earth fault detection fixed value self-adaptive setting module and a field switching equipment control module;
the single-phase earth fault detection constant value self-adaptive setting module adjusts the current quick-break protection constant value of each fault scene according to the input identification result and the typical characteristics, and inputs the calculated current quick-break protection constant value of each fault scene to the field switch equipment control module;
and the field switching equipment control module controls the field switching equipment to act according to the received data.
12. The fixed-value adaptive tuning system for single-phase ground fault detection according to claim 11,
the fault type identification model constructed by the fault type identification model construction module meets the following conditions:
if the constructed classification tree is the classification tree, the fault type identification result is directly obtained through the classification tree; if the regression tree is constructed, all the regression trees form a regression tree set, and the judgment result of the ith data xi meets the following relational expression:
wherein the content of the first and second substances,representing regression Tree set for ith data xiIs a decision value, K tableNumber of display trees, fk(xi) Representing the use of kth tree for ith data xiF represents all regression tree spaces, w represents all regression tree node weight sets, q represents all regression tree node sets, and T represents the total number of all regression tree nodes;representing an m-dimensional real vector space,representing a one-dimensional real vector space;
if the classification tree is used, the classified tree can directly distinguish the fault type;
if a regression tree is used, the s-type data with the maximum judgment value obtained by descending order has relevance with the fault type.
13. The fixed-value adaptive tuning system for single-phase ground fault detection according to claim 12,
the objective function of the regression tree set in the fault type identification model is as follows:
wherein, yiRepresenting data xiThe original label of (a) is a convex loss function which can be derived, gamma and lambda are respectively a first bias term and a second bias term, and the adjustment and setting can be carried out by a person skilled in the art according to the output result of the regression tree set; w is ajIs the weight of the jth node of the kth regression tree.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111485796.0A CN114047705A (en) | 2021-12-07 | 2021-12-07 | Single-phase earth fault detection constant value self-adaptive setting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111485796.0A CN114047705A (en) | 2021-12-07 | 2021-12-07 | Single-phase earth fault detection constant value self-adaptive setting method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114047705A true CN114047705A (en) | 2022-02-15 |
Family
ID=80212527
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111485796.0A Pending CN114047705A (en) | 2021-12-07 | 2021-12-07 | Single-phase earth fault detection constant value self-adaptive setting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114047705A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115932484A (en) * | 2023-02-15 | 2023-04-07 | 重庆大学 | Method and device for identifying and ranging faults of power transmission line and electronic equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20020076413A (en) * | 2001-03-28 | 2002-10-11 | 학교법인 성균관대학 | Fault Classification of Power System using Neuro-Fuzzy Network and method for judgement thereof |
CN105140897A (en) * | 2015-09-26 | 2015-12-09 | 中国石油大学(华东) | Protection method suitable for low resistance grounding system single phase grounding fault |
CN108152651A (en) * | 2017-12-27 | 2018-06-12 | 重庆水利电力职业技术学院 | Transmission line malfunction integrated recognition method based on GMAPM and SOM-LVQ-ANN |
-
2021
- 2021-12-07 CN CN202111485796.0A patent/CN114047705A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20020076413A (en) * | 2001-03-28 | 2002-10-11 | 학교법인 성균관대학 | Fault Classification of Power System using Neuro-Fuzzy Network and method for judgement thereof |
CN105140897A (en) * | 2015-09-26 | 2015-12-09 | 中国石油大学(华东) | Protection method suitable for low resistance grounding system single phase grounding fault |
CN108152651A (en) * | 2017-12-27 | 2018-06-12 | 重庆水利电力职业技术学院 | Transmission line malfunction integrated recognition method based on GMAPM and SOM-LVQ-ANN |
Non-Patent Citations (6)
Title |
---|
S. A. M. JAVADIAN: "A Fault Location and Protection Scheme for Distribution Systems in presence of DG Using MLP Neural Networks", 《2009 IEEE POWER & ENERGY SOCIETY GENERAL MEETING》, 2 October 2009 (2009-10-02), pages 1932 - 5517 * |
XIAO-DAN ZENG: "Machine-learning-based single-phase-to-ground fault detection in distribution systems", 《 2017 IEEE CONFERENCE ON ENERGY INTERNET AND ENERGY SYSTEM INTEGRATION (EI2)》, 4 January 2018 (2018-01-04) * |
YONG-LIANG LIANG: "Typical Fault Cause Recognition of Single-Phase-to-Ground Fault for Overhead Lines in Nonsolidly Earthed Distribution Networks", 《 IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS》, 31 August 2020 (2020-08-31), pages 6298, XP011817734, DOI: 10.1109/TIA.2020.3020526 * |
李宗峰: "基于融合模型的单相接地故障类型辨识方法", 《重庆大学学报》, 30 September 2022 (2022-09-30), pages 61 - 71 * |
林雨丰: "基于多故障特征量提取的配电网单相接地故障类型识别", 《供用电》, 30 June 2020 (2020-06-30), pages 40 - 47 * |
陈广鑫: "基于免疫聚类的配电网故障分类识别方法研究", 《工程科技Ⅱ辑》, 31 January 2015 (2015-01-31), pages 042 - 824 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115932484A (en) * | 2023-02-15 | 2023-04-07 | 重庆大学 | Method and device for identifying and ranging faults of power transmission line and electronic equipment |
CN115932484B (en) * | 2023-02-15 | 2023-07-18 | 重庆大学 | Power transmission line fault identification and fault location method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN1047887C (en) | Device for differentially protecting a power transformer | |
Nascimento et al. | An adaptive overcurrent protection system applied to distribution systems | |
Abu-Elanien et al. | A non-communication based protection algorithm for multi-terminal HVDC grids | |
CN110488154B (en) | Low-current grounding line selection method for dispatching master station end | |
CN112285601B (en) | Monopole ground fault line selection method for multi-terminal small-current grounding flexible direct current system | |
CN110865278B (en) | Ground fault positioning method based on transient mutation energy capturing method | |
CN106129975B (en) | A kind of differential protecting method based on active power fault component criterion | |
CN100387999C (en) | Circuit fault directional detecting and protecting method for power supply system | |
Fernandez et al. | A novel approach using a FIRANN for fault detection and direction estimation for high-voltage transmission lines | |
Ashok et al. | Fault diagnosis scheme for cross-country faults in dual-circuit line with emphasis on high-impedance fault syndrome | |
Akorede et al. | Wavelet transform based algorithm for high-impedance faults detection in distribution feeders | |
CN114047705A (en) | Single-phase earth fault detection constant value self-adaptive setting method and system | |
CN109884436B (en) | Online monitoring method for power capacitor complete equipment | |
JP3213304B2 (en) | Distribution line accident diagnosis method and device | |
CN113625123A (en) | Single-phase earth fault positioning method for power distribution network | |
Abu-Elanien | An artificial neural network based technique for protection of HVDC grids | |
CN206096341U (en) | Be applied to fault line recognition device under distribution network single -phase fault ground connection operating mode | |
CN112924813A (en) | Power distribution network short-circuit fault monitoring method and device based on electrical data | |
CN116068333B (en) | Multi-criterion fusion fault line selection device and line selection method based on fuzzy theory | |
CN108599116B (en) | Direct-current line protection method suitable for alternating-current and direct-current hybrid power distribution network | |
Abu-Elanien et al. | An ANN-based protection technique for MTDC systems with multiple configurations | |
CN111880035B (en) | Power distribution network fault monitoring system and method based on multi-source measurement data | |
CN114355099A (en) | Power distribution network single-phase earth fault detection method based on field wave recording data analysis | |
CN114113884A (en) | Overvoltage active early warning method and system based on multi-source information fusion | |
Adewole | Investigation of methodologies for fault detection and diagnosis in electric power system protection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |