CN115906639A - Line operation fault rate prediction method and device based on line operation working conditions - Google Patents
Line operation fault rate prediction method and device based on line operation working conditions Download PDFInfo
- Publication number
- CN115906639A CN115906639A CN202211482188.9A CN202211482188A CN115906639A CN 115906639 A CN115906639 A CN 115906639A CN 202211482188 A CN202211482188 A CN 202211482188A CN 115906639 A CN115906639 A CN 115906639A
- Authority
- CN
- China
- Prior art keywords
- line
- fault rate
- condition
- working condition
- model
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012549 training Methods 0.000 claims description 43
- 238000009826 distribution Methods 0.000 claims description 34
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 15
- 238000007476 Maximum Likelihood Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 239000002131 composite material Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 230000005540 biological transmission Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013077 scoring method Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- APTZNLHMIGJTEW-UHFFFAOYSA-N pyraflufen-ethyl Chemical compound C1=C(Cl)C(OCC(=O)OCC)=CC(C=2C(=C(OC(F)F)N(C)N=2)Cl)=C1F APTZNLHMIGJTEW-UHFFFAOYSA-N 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of line monitoring, in particular to a line operation fault rate prediction method and a device based on line operation working conditions, which comprises the steps of obtaining historical data of a plurality of line operation working conditions; classifying the historical data of the line operation condition by using a condition classifier; establishing a normal working condition line fault rate model and a severe working condition line fault rate model by using the proportional risk model and the classified line operation working condition historical data; inputting the operation condition data of the line to be predicted to a condition classifier, and determining the operation condition of the line to be predicted; and predicting the operation fault rate of the line to be predicted by using the line fault rate model corresponding to the working condition. According to the invention, the fault rate model of the normal working condition line and the fault rate model of the severe working condition line are established by utilizing the proportional risk model and the classified historical data of the line operating conditions, and the fault rate prediction is carried out on the lines under different working conditions by utilizing the line fault rate models under different working conditions in a targeted manner, so that the prediction accuracy is effectively improved.
Description
Technical Field
The invention relates to the technical field of line monitoring, in particular to a line operation fault rate prediction method and device based on line operation working conditions.
Background
The distribution network is closely connected with users, and the operation safety of the distribution network has great influence on social order and people's life. At present, the permeability of distributed renewable energy sources in the power distribution network is continuously improved, the load demand is rapidly increased, the structure of the power distribution network is more and more complex, and the accurate calculation of the fault rate of the power distribution line is carried out, so that the method has important significance for the operation safety management of the power distribution network.
The distribution line contains a plurality of components, and the type is various, and some component state change of circuit probably produces the chain effect to will influence the fault rate of circuit, and its operational environment is complicated changeable moreover, and various external force factors also probably make circuit operating condition take place the time variant.
In actual engineering, a scoring method is often adopted to determine the state of the line. The scoring method for evaluating the operation fault probability of the line by scoring the operation state of the component elements of the overhead transmission line according to DL/T1249-2013 'overhead transmission line operation state evaluation technical guide' and Q/GDW 173-2014 'overhead transmission line state evaluation guide' is simple in operation and clear in conclusion, but depends on experience of evaluation personnel, and has strong subjectivity.
Disclosure of Invention
The invention provides a line operation fault rate prediction method and device based on line operation working conditions, overcomes the defects of the prior art, and can effectively solve the problems of strong subjectivity and low efficiency of the existing manual line state grading and determining mode.
One of the technical schemes of the invention is realized by the following measures: a line operation fault rate prediction method based on line operation conditions comprises the following steps:
obtaining historical data of a plurality of line operating conditions;
classifying historical data of the line operation condition by using a condition classifier, wherein the classification type comprises a normal condition and a severe condition, and the condition classifier is obtained by training and learning by using a line condition sample set;
establishing a normal working condition line fault rate model and a severe working condition line fault rate model by using the proportional risk model and the classified line operation working condition historical data;
inputting the operation condition data of the line to be predicted to a condition classifier, and determining the operation condition of the line to be predicted;
and predicting the operation fault rate of the line to be predicted by using the line fault rate model corresponding to the working condition according to the operation working condition classification result of the line to be predicted.
The following is further optimization or/and improvement of the technical scheme of the invention:
the above-mentioned line operation operating mode historical data after utilizing proportion risk model and classification, establish normal operating mode line fault rate model and abominable operating mode line fault rate model, include:
establishing a line fault rate model based on a proportional risk model and in combination with the line load rate and the influence of meteorological factors;
wherein, beta, gamma 1 、γ 2 Is a parameter to be estimated; z 1 Is the load factor; z 2 Is a composite effect of weather conditions; eta is the expected service life of the distribution line; t is the current moment;
training the classified historical data of the line operating conditions on a line fault rate model, and establishing a normal condition line fault rate model and a severe condition line fault rate model as shown below;
the normal working condition line fault rate model is as follows:
wherein, beta a 、γ 1a 、γ 2a Obtaining estimation parameters by adopting a maximum likelihood estimation method according to historical data of the line operation working conditions under normal working conditions;
the fault rate model of the line under the severe working condition is as follows:
wherein, beta b 、γ 1b 、γ 2b And obtaining estimation parameters by adopting a maximum likelihood estimation method according to the historical data of the line operation working conditions under the severe working conditions.
The above-mentioned operating mode classifier of establishing includes:
multi-source data of a power distribution system are fused, feature variables are extracted by adopting a feature subset based on the correlation degree, an initial training sample set is established, the sample number ratio of normal working conditions and severe working conditions is adjusted by adopting an SMOTE algorithm, and the training sample set is updated;
establishing a working condition classifier based on a neural network;
and training the working condition classifier established based on the neural network by using the training sample set, and outputting the trained working condition classifier.
The method also comprises the step of reversely adjusting parameters in the normal working condition line fault rate model and the bad working condition line fault rate model according to the result of predicting the operation fault rate of the line to be predicted by utilizing the line fault rate model of the corresponding working condition.
The second technical scheme of the invention is realized by the following measures: a line operation fault rate prediction device based on line operation conditions comprises:
the data acquisition unit is used for acquiring historical data of a plurality of line operating conditions;
the classification unit is used for classifying the historical data of the line operation working conditions by using a working condition classifier, wherein the classification type comprises normal working conditions and severe working conditions, and the working condition classifier is obtained by training and learning by using a line working condition sample set;
the model establishing unit is used for establishing a normal working condition line fault rate model and a severe working condition line fault rate model by utilizing the proportional risk model and the classified line operation working condition historical data;
the working condition identification unit inputs the operating working condition data of the line to be predicted to the working condition classifier and determines the operating working condition of the line to be predicted;
and the fault rate prediction unit is used for predicting the operation fault rate of the line to be predicted by using the line fault rate model corresponding to the working condition according to the operation working condition classification result of the line to be predicted.
The following is further optimization or/and improvement of the technical scheme of the invention:
the classification unit includes:
the system comprises a sample set establishing module, a data processing module and a data processing module, wherein the sample set establishing module is used for fusing multi-source data of a power distribution system, extracting characteristic variables by adopting a characteristic subset based on correlation, establishing an initial training sample set, adjusting the sample number ratio of normal working conditions and severe working conditions by adopting an SMOTE algorithm, and updating the training sample set;
the classifier establishing module is used for establishing a working condition classifier based on a neural network;
and the classifier training module is used for training the working condition classifier established based on the neural network by using the training sample set and outputting the trained working condition classifier.
The model building unit includes:
the first establishing module is used for establishing a line fault rate model based on a proportional risk model and combined with the line load rate and the influence of meteorological factors;
wherein, beta, gamma 1 、γ 2 Is a parameter to be estimated; z 1 Is the load factor; z 2 Is a composite effect of weather conditions; eta is the expected service life of the distribution line; t is the current time;
the second establishing module is used for training the line fault rate model according to the classified historical data of the line operating conditions, and establishing a normal-condition line fault rate model and a severe-condition line fault rate model as shown in the specification;
the normal working condition line fault rate model is as follows:
wherein, beta a 、γ 1a 、γ 2a Obtaining an estimation parameter by adopting a maximum likelihood estimation method according to the historical data of the line operating condition under the normal condition;
the fault rate model of the line under the severe working condition is as follows:
wherein, beta b 、γ 1b 、γ 2b And obtaining an estimation parameter by adopting a maximum likelihood estimation method according to the historical data of the line operating conditions under the severe conditions.
The method is suitable for short-term prediction of the operation state of the distribution line under the non-extreme weather condition, a normal working condition line fault rate model and a severe working condition line fault rate model are established by using the proportional risk model and the classified line operation condition historical data, and the fault rates of the lines under different working conditions are predicted by using the line fault rate models under different working conditions in a targeted manner, so that the prediction accuracy is effectively improved.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
FIG. 2 is a schematic flow chart of a method for establishing a normal condition line fault rate model and a severe condition line fault rate model in the invention.
FIG. 3 is a flow chart of a method for establishing a condition classifier according to the present invention.
Fig. 4 is a schematic flow chart of a method for implementing the SMOTE algorithm in the present invention.
FIG. 5 is a schematic diagram of the apparatus of the present invention.
FIG. 6 is a schematic diagram of the structure of the sorting unit of the present invention.
Fig. 7 is a schematic structural diagram of a model building unit according to the present invention.
Detailed Description
The present invention is not limited by the following examples, and specific embodiments may be determined according to the technical solutions and practical situations of the present invention.
The invention is further described with reference to the following examples and figures:
example 1: as shown in fig. 1, an embodiment of the present invention discloses a line operation fault rate prediction method based on line operation conditions, including:
step S101, obtaining historical data of a plurality of line operation conditions;
step S102, classifying historical data of line operating conditions by using a condition classifier, wherein classification types comprise normal conditions and severe conditions, and the condition classifier is obtained by training and learning by using a line condition sample set;
step S103, establishing a normal working condition line fault rate model and a severe working condition line fault rate model by using the proportional risk model and the classified line operation working condition historical data;
step S104, inputting the operation condition data of the line to be predicted to a condition classifier, and determining the operation condition of the line to be predicted;
and S105, predicting the operation fault rate of the line to be predicted by using the line fault rate model corresponding to the working condition according to the operation working condition classification result of the line to be predicted.
The method also comprises the step of reversely adjusting parameters in the normal working condition line fault rate model and the severe working condition line fault rate model according to the result of predicting the operation fault rate of the line to be predicted by utilizing the line fault rate model of the corresponding working condition. The line fault rate prediction is more accurate.
The method is suitable for short-term prediction of the distribution line operation state under the non-extreme weather condition, a normal working condition line fault rate model and a severe working condition line fault rate model are established by utilizing the proportional risk model and the classified line operation condition historical data, and the fault rate prediction is performed on the lines under different working conditions by utilizing the line fault rate models under different working conditions in a targeted manner, so that the prediction accuracy is effectively improved.
Example 2: as shown in fig. 2, the embodiment of the present invention discloses a method for predicting a line operation fault rate based on line operation conditions, wherein a proportional risk model and classified historical data of line operation conditions are used to establish a normal condition line fault rate model and a severe condition line fault rate model, and the method further comprises:
step S201, establishing a line fault rate model based on a proportional risk model and combined with the line load rate and the influence of meteorological factors;
wherein, beta, gamma 1 、γ 2 Is a parameter to be estimated; z is a linear or branched member 1 Is the load factor; z 2 Is a composite effect of weather conditions; eta is the expected life of the distribution line; t is the current time;
in this step, a line fault rate model is established, which includes:
(1) Establishing a basic proportion risk model (PHM) shown as the following formula; PHM was proposed by d.r.cox in 1972, and widely applied to the field of economics and failure modeling of mechanical parts, and is also gradually applied to reliability evaluation of power transmission and transformation equipment of power systems in recent years.
Wherein t is the current moment; h is 0 (t) is a reference function; n is a historical data variable dimension; gamma ray i Is a covariate coefficient; z i (t) is a covariate merit function.
(2) Under extreme weather conditions such as snowstorm and thunderbolt, external force such as municipal construction and artificial destruction, distribution lines fault rate will increase by a wide margin, and line fault rate model will evolve into single factor model, therefore this embodiment is to the transition probability of circuit running state under the non-extreme weather condition, selects fault rate benchmark function to be distribution lines ageing Weibull distribution model, as shown in following formula:
wherein β is a function shape parameter; eta is the expected service life of the distribution line, and the expected service life of the distribution line is defined as a constant according to the reliability index of power transmission and distribution equipment in China.
(3) The fault rate short-term prediction is carried out on the distribution line, the influence of the equipment health state change on the fault rate is not large, so the influence of the line load rate and meteorological factors is considered emphatically, and a line fault rate model is established by combining the formula as shown in the specification.
Wherein, beta, gamma 1 、γ 2 The parameters to be estimated can be estimated according to historical operating data of the distribution line; z 1 The load factor is specifically as follows:
Z 1 ＝l
in the formula, l is the load rate of the line and is given by the operation scheduling plan of the distribution line.
Z 2 The comprehensive influence of weather conditions is shown in the following formula:
wherein λ is j Is the jth meteorological factor x in the sample j The corresponding weight can be determined by solving the Pearson correlation coefficient according to historical statistical data; the weather data can be obtained by inquiring weather forecast.
Step S202, training a line fault rate model by using the classified historical data of the line operation conditions, and establishing a normal condition line fault rate model and a severe condition line fault rate model as shown in the following;
the normal working condition line fault rate model is as follows:
wherein, beta a 、γ 1a 、γ 2a Obtaining estimation parameters by adopting a maximum likelihood estimation method according to historical data of the line operation working conditions under normal working conditions;
the fault rate model of the line under the severe working condition is as follows:
wherein, beta b 、γ 1b 、γ 2b And obtaining estimation parameters by adopting a maximum likelihood estimation method according to the historical data of the line operation working conditions under the severe working conditions.
Example 3: as shown in fig. 3, the embodiment of the present invention discloses a line operation fault rate prediction method based on line operation conditions, wherein the establishment of a condition classifier further includes:
step S301, fusing multi-source data of a power distribution system, extracting characteristic variables by adopting characteristic subsets based on correlation, establishing an initial training sample set, adjusting the sample number ratio of normal working conditions and severe working conditions by adopting an SMOTE algorithm, and updating the training sample set;
the multi-source data of the fusion power distribution system comprises ledger data, fault data, load rate data, weather data and the like. After multi-source data of the power distribution system are fused, the data can be preprocessed, wherein the preprocessing comprises cleaning and conversion. Thereby greatly improving data integrity and usability.
Because the time length of the distribution line in the normal state is far longer than that in the fault state, namely the number of samples in the normal working condition in the initial sample is far longer than that in the severe working condition, the initial sample has obvious unbalance, and the unbalance can weaken the classification capability of the neural network model, so that the prediction accuracy of the distribution line running state is reduced. Therefore, the imbalance of the data needs to be handled, in this embodiment, the SMOTE algorithm is used to adjust the ratio of the number of samples in the normal operating condition and the severe operating condition, and the sample balance is improved, and the specific steps of the SMOTE algorithm are shown in fig. 4.
Step S302, establishing a working condition classifier based on a neural network;
the method specifically comprises the following steps:
a feedforward neural network structure is arranged, and signals are propagated in a single direction from an input layer to an output layer. Wherein, the input layer is an m-dimensional feature vector X which is extracted according to the sample feature subset and used for describing the line working condition i The output layer is the classification result y of the line working condition i I.e. normal or severe conditions. Namely, a history sample set formed by the line working condition characteristic variables is as follows:
(X,y)＝(X 1 ,y 1 ),(X 2 ,y 2 ),...,(X n ,y n )y i ∈{0,1}
the information transmission process of the neural network is as follows:
y＝g(WX+B)
wherein W is a weight matrix of the line characteristic variable, B is a bias matrix, and g is an activation function.
The activation function of the hidden unit selects a RELU activation function, and defines a vector α = WX + B, that is:
RELU(α c )＝max(0,α c )
wherein alpha is c Is the c-th element of the vector alpha.
The weight matrix W and the bias matrix B in the network are learned through a gradient descent method of the following formula, and efficient calculation of the gradient is achieved through a back propagation algorithm.
Where ε is the learning rate.
The optimization method of the training process adopts a random gradient descent method (SGD) shown in the following formula.
▽L(θ)＝▽L(f(X (m) ；θ),y (m) )
The output unit is defined as a Sigmod unit, i.e.:
the Sigmod output unit uses the following cross entropy loss function.
Wherein, y (m) In order to be a real label, the label,
for predicting the label, M is the total number of samples in the initial training set.
And step S303, training the working condition classifier established based on the neural network by using the training sample set, and outputting the trained working condition classifier.
In the embodiment, the precision of the neural network classifier of the operating condition is improved by extracting the characteristic variables of the operating condition and improving the sample balance, and a foundation is laid for the accuracy of prediction.
Example 4: as shown in fig. 5, an embodiment of the present invention discloses a line operation fault rate prediction apparatus based on line operation conditions, including:
the data acquisition unit is used for acquiring historical data of a plurality of line operating conditions;
the classification unit is used for classifying the historical data of the line operating conditions by using a condition classifier, wherein the classification type comprises normal conditions and severe conditions, and the condition classifier is obtained by training and learning by using a line condition sample set;
the model establishing unit is used for establishing a normal working condition line fault rate model and a severe working condition line fault rate model by utilizing the proportional risk model and the classified line operation working condition historical data;
the working condition identification unit inputs the operating working condition data of the line to be predicted to the working condition classifier and determines the operating working condition of the line to be predicted;
and the fault rate prediction unit is used for predicting the operation fault rate of the line to be predicted by using the line fault rate model corresponding to the working condition according to the operation working condition classification result of the line to be predicted.
In this embodiment, as shown in fig. 6, the classification unit includes:
the system comprises a sample set establishing module, a correlation degree-based feature subset extraction feature variable, an initial training sample set, a SMOTE algorithm adjustment sample number ratio of normal working conditions and severe working conditions, and a training sample set updating module, wherein the sample set establishing module is used for fusing multi-source data of a power distribution system, extracting feature variables by adopting the feature subset based on the correlation degree, and updating the training sample set;
the classifier establishing module is used for establishing a working condition classifier based on a neural network;
and the classifier training module is used for training the working condition classifier established based on the neural network by utilizing the training sample set and outputting the trained working condition classifier.
In this embodiment, as shown in fig. 7, the model building unit includes:
the first establishing module is used for establishing a line fault rate model based on a proportional risk model and combined with the line load rate and the influence of meteorological factors;
wherein, beta, gamma 1 、γ 2 Is a parameter to be estimated; z is a linear or branched member 1 Is the load factor; z 2 Is a composite effect of weather conditions; eta is the expected service life of the distribution line; t is the current moment;
the second establishing module is used for training the line fault rate model according to the classified historical data of the line operating conditions, and establishing a normal-condition line fault rate model and a severe-condition line fault rate model as shown in the specification;
the normal working condition line fault rate model is as follows:
wherein, beta a 、γ 1a 、γ 2a Line transportation according to normal working conditionsEstimating parameters of historical data of the operating conditions by adopting a maximum likelihood estimation method;
the fault rate model of the line under the severe working condition is as follows:
wherein beta is b 、γ 1b 、γ 2b And obtaining estimation parameters by adopting a maximum likelihood estimation method according to the historical data of the line operation working conditions under the severe working conditions.
Example 5: the embodiment of the invention discloses a storage medium, wherein a computer program capable of being read by a computer is stored on the storage medium, and the computer program is set to execute a power grid weak link identification method based on extreme ice disasters when running.
The storage medium may include, but is not limited to: u disk, read-only memory, removable hard disk, magnetic or optical disk, etc. various media capable of storing computer programs.
Example 6: the embodiment of the invention discloses electronic equipment which comprises a processor and a memory, wherein a computer program is stored in the memory and loaded and executed by the processor to realize a power grid weak link identification method based on extreme ice disasters.
The processor may be a central processing unit CPU, general purpose processor, digital signal processor DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. Or a combination that performs a computing function, e.g., comprising one or more microprocessors, DSPs, and microprocessors, etc. The memory may include, but is not limited to: u disk, read-only memory, removable hard disk, magnetic or optical disk, etc. various media capable of storing computer programs.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The solution in the embodiment of the present application may be implemented by using various computer languages, for example, object-oriented programming language Java and transliteration scripting language JavaScript, etc.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
The above technical features constitute the best embodiment of the present invention, which has strong adaptability and best implementation effect, and unnecessary technical features can be increased or decreased according to actual needs to meet the requirements of different situations.
Claims (9)
1. A line operation fault rate prediction method based on line operation conditions is characterized by comprising the following steps:
obtaining historical data of a plurality of line operating conditions;
classifying historical data of the line operation condition by using a condition classifier, wherein the classification type comprises a normal condition and a severe condition, and the condition classifier is obtained by training and learning by using a line condition sample set;
establishing a normal working condition line fault rate model and a severe working condition line fault rate model by using the proportional risk model and the classified line operation working condition historical data;
inputting the operation condition data of the line to be predicted to a condition classifier, and determining the operation condition of the line to be predicted;
and predicting the operation fault rate of the line to be predicted by using the line fault rate model corresponding to the working condition according to the operation working condition classification result of the line to be predicted.
2. The line operation fault rate prediction method based on the line operation condition according to claim 1, wherein the establishing of the normal condition line fault rate model and the severe condition line fault rate model by using the proportional risk model and the classified line operation condition historical data comprises:
establishing a line fault rate model based on a proportional risk model and by combining the line load rate and the influence of meteorological factors;
wherein, beta, gamma 1 、γ 2 Is a parameter to be estimated; z is a linear or branched member 1 Is the load factor; z 2 Is a composite effect of weather conditions; eta is the expected service life of the distribution line; t is the current time;
training the classified historical data of the line operating conditions on a line fault rate model, and establishing a normal condition line fault rate model and a severe condition line fault rate model as shown in the following;
the normal working condition line fault rate model is as follows:
wherein, beta a 、γ 1a 、γ 2a Obtaining estimation parameters by adopting a maximum likelihood estimation method according to historical data of the line operation working conditions under normal working conditions;
the fault rate model of the line under the severe working condition is as follows:
wherein beta is b 、γ 1b 、γ 2b And obtaining estimation parameters by adopting a maximum likelihood estimation method according to the historical data of the line operation working conditions under the severe working conditions.
3. The line operation fault rate prediction method based on the line operation condition according to claim 1 or 2, wherein the establishing of the condition classifier comprises:
multi-source data of a power distribution system are fused, feature subsets based on correlation degree are adopted to extract feature variables, an initial training sample set is established, SMOTE algorithm is adopted to adjust the sample number ratio of normal working conditions and severe working conditions, and the training sample set is updated;
establishing a working condition classifier based on a neural network;
and training the working condition classifier established based on the neural network by using the training sample set, and outputting the trained working condition classifier.
4. The line operation fault rate prediction method based on the line operation conditions according to any one of claims 1 to 3, characterized by further comprising the step of reversely adjusting parameters in the normal condition line fault rate model and the severe condition line fault rate model in combination with the result of predicting the line operation fault rate to be predicted by using the line fault rate model of the corresponding condition.
5. A line operation fault rate prediction device based on line operation conditions by applying the method of any one of claims 1 to 4, characterized by comprising:
the data acquisition unit is used for acquiring historical data of a plurality of line operating conditions;
the classification unit is used for classifying the historical data of the line operation working conditions by using a working condition classifier, wherein the classification type comprises normal working conditions and severe working conditions, and the working condition classifier is obtained by training and learning by using a line working condition sample set;
the model establishing unit is used for establishing a normal working condition line fault rate model and a severe working condition line fault rate model by utilizing the proportional risk model and the classified line operation working condition historical data;
the working condition identification unit inputs the operating working condition data of the line to be predicted to the working condition classifier and determines the operating working condition of the line to be predicted;
and the fault rate prediction unit is used for predicting the operation fault rate of the line to be predicted by using the line fault rate model corresponding to the working condition according to the operation working condition classification result of the line to be predicted.
6. The line operation failure rate prediction device according to claim 5, wherein the classification unit includes:
the system comprises a sample set establishing module, a correlation degree-based feature subset extraction feature variable, an initial training sample set, a SMOTE algorithm adjustment sample number ratio of normal working conditions and severe working conditions, and a training sample set updating module, wherein the sample set establishing module is used for fusing multi-source data of a power distribution system, extracting feature variables by adopting the feature subset based on the correlation degree, and updating the training sample set;
the classifier establishing module is used for establishing a working condition classifier based on a neural network;
and the classifier training module is used for training the working condition classifier established based on the neural network by utilizing the training sample set and outputting the trained working condition classifier.
7. The line operating condition-based line operating failure rate prediction device according to claim 5 or 6, wherein the model building unit includes:
the first establishing module is used for establishing a line fault rate model based on a proportional risk model and combined with the line load rate and the influence of meteorological factors;
wherein, beta, gamma 1 、γ 2 Is a parameter to be estimated; z is a linear or branched member 1 Is the load factor; z is a linear or branched member 2 Is a composite effect of weather conditions; eta is the expected service life of the distribution line; t is the current time;
the second establishing module is used for training the line fault rate model by using the classified historical data of the line operating conditions, and establishing a normal condition line fault rate model and a severe condition line fault rate model as shown in the following;
the normal working condition line fault rate model is as follows:
wherein beta is a 、γ 1a 、γ 2a Obtaining an estimation parameter by adopting a maximum likelihood estimation method according to the historical data of the line operating condition under the normal condition;
the fault rate model of the line under the severe working condition is as follows:
wherein, beta b 、γ 1b 、γ 2b And obtaining estimation parameters by adopting a maximum likelihood estimation method according to the historical data of the line operation working conditions under the severe working conditions.
8. A storage medium having stored thereon a computer program readable by a computer, the computer program being arranged to execute the method of predicting line operation fault rate based on line operating conditions according to any one of claims 1 to 4 when running.
9. An electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded by the processor and executed to implement the method for predicting line operation fault rate according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211482188.9A CN115906639A (en) | 2022-11-24 | 2022-11-24 | Line operation fault rate prediction method and device based on line operation working conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211482188.9A CN115906639A (en) | 2022-11-24 | 2022-11-24 | Line operation fault rate prediction method and device based on line operation working conditions |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115906639A true CN115906639A (en) | 2023-04-04 |
Family
ID=86478365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211482188.9A Withdrawn CN115906639A (en) | 2022-11-24 | 2022-11-24 | Line operation fault rate prediction method and device based on line operation working conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115906639A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204779A (en) * | 2023-04-19 | 2023-06-02 | 中能建数字科技集团有限公司 | Method, system and readable storage medium for judging operation state of energy storage salt cavern |
-
2022
- 2022-11-24 CN CN202211482188.9A patent/CN115906639A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204779A (en) * | 2023-04-19 | 2023-06-02 | 中能建数字科技集团有限公司 | Method, system and readable storage medium for judging operation state of energy storage salt cavern |
| CN116204779B (en) * | 2023-04-19 | 2023-09-05 | 中能建数字科技集团有限公司 | Method, system and readable storage medium for judging operation state of energy storage salt cavern |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A hierarchical self-adaptive data-analytics method for real-time power system short-term voltage stability assessment | |
| CN109297689B (en) | Large-scale hydraulic machinery intelligent diagnosis method introducing weight factors | |
| Wang et al. | Decision tree based online stability assessment scheme for power systems with renewable generations | |
| CN107292502B (en) | Power distribution network reliability assessment method | |
| CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
| Welte et al. | Models for lifetime estimation: an overview with focus on applications to wind turbines | |
| CN111178585A (en) | Fault reporting amount prediction method based on multi-algorithm model fusion | |
| CN109740727A (en) | A kind of hydraulic turbine shaft state monitoring method neural network based and system | |
| CN113486291B (en) | Petroleum drilling machine micro-grid fault prediction method based on deep learning | |
| CN114021848A (en) | Generating capacity demand prediction method based on LSTM deep learning | |
| CN116614177A (en) | Optical fiber state multidimensional parameter monitoring system | |
| CN115906639A (en) | Line operation fault rate prediction method and device based on line operation working conditions | |
| CN118469352B (en) | Deep learning driven power grid line loss dynamic prediction and optimization control method | |
| Liu et al. | A fatigue reliability assessment approach for wind turbine blades based on continuous time Bayesian network and FEA | |
| CN117391674A (en) | Reliability-based preventive maintenance optimization method and device for electrical equipment | |
| Huang et al. | Risk assessment models of power transmission lines undergoing heavy ice at mountain zones based on numerical model and machine learning | |
| Guo et al. | Wind speed forecasting of genetic neural model based on rough set theory | |
| CN116415724A (en) | Photovoltaic power station operation maintenance time prediction method and device | |
| US12100950B2 (en) | Net load forecasting method and apparatus for new energy electric power market | |
| CN116307028A (en) | Short-term power load prediction method and system based on improved decision tree | |
| CN113240098B (en) | Fault prediction method and device based on hybrid gated neural network and storage medium | |
| Angadi et al. | An ensemble based data mining model for contingency analysis of power system under STLO | |
| CN109359781A (en) | The prediction technique and device in longevity more than a kind of intelligent manufacturing system | |
| CN113392575B (en) | Fan main shaft fault prediction method based on sliding window characteristics | |
| Zhang et al. | Research on Early Warning of Hoist Failure based on Big Data and Parallel Simulation |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230404 |
|
| WW01 | Invention patent application withdrawn after publication |