CN114186590A - Power distribution network single-phase earth fault identification method based on wavelet and deep learning - Google Patents

Power distribution network single-phase earth fault identification method based on wavelet and deep learning Download PDF

Info

Publication number
CN114186590A
CN114186590A CN202111505119.0A CN202111505119A CN114186590A CN 114186590 A CN114186590 A CN 114186590A CN 202111505119 A CN202111505119 A CN 202111505119A CN 114186590 A CN114186590 A CN 114186590A
Authority
CN
China
Prior art keywords
wavelet
fault
entropy
deep learning
distribution network
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
Application number
CN202111505119.0A
Other languages
Chinese (zh)
Inventor
宋殷冠
邹宇
池小兵
苏一峰
谢振俊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qinzhou Power Supply Bureau of Guangxi Power Grid Co Ltd
Original Assignee
Qinzhou Power Supply Bureau of Guangxi Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qinzhou Power Supply Bureau of Guangxi Power Grid Co Ltd filed Critical Qinzhou Power Supply Bureau of Guangxi Power Grid Co Ltd
Priority to CN202111505119.0A priority Critical patent/CN114186590A/en
Publication of CN114186590A publication Critical patent/CN114186590A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention discloses a method for identifying a single-phase earth fault of a power distribution network based on wavelet and deep learning. And then, a deep learning network is built, and the learning samples are input into the deep learning network for learning. The trained deep learning model carries out fault recognition on the working condition data of the selected time period under the selected bus to determine whether a fault occurs; and performing multi-working-condition type identification on the working condition data which is determined to have faults by utilizing a pre-trained decision tree. The method helps the dispatching personnel to quickly position the single-phase grounding of the power distribution network, forms an operable result, and provides a basis for improving the fault processing efficiency of the dispatching personnel and guaranteeing the operation stability of the power distribution network.

Description

Power distribution network single-phase earth fault identification method based on wavelet and deep learning
Technical Field
The invention belongs to the technical field of power distribution network line fault identification, and particularly relates to a wavelet algorithm and deep learning based neural network combined power distribution network single-phase earth fault identification research method.
Background
The medium voltage distribution network in China widely adopts a neutral point non-effective grounding operation mode, and mainly comprises a neutral point non-grounding mode and an arc suppression coil grounding mode. Compared with a high-voltage transmission network, the probability of faults of a medium-voltage distribution network is much higher, particularly single-phase earth faults occur frequently, and statistics show that the single-phase earth faults account for about 80% of the total faults of 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. Because the line voltage between the three phases of the system is basically kept unchanged, the load power supply is not influenced, and theoretically, the system can operate for a period of time with a fault. However, due to the non-fault phase-to-ground voltage rise during grounding, especially intermittent arc grounding faults, arc overvoltage can be generated, and system insulation and equipment safety are seriously damaged. Meanwhile, an overvoltage may cause a ground fault to be converted into an interphase short-circuit fault, so that a line trips, and a user is powered off. Therefore, an effective single-phase earth fault determination method becomes an important means for solving the existing problems.
Disclosure of Invention
The invention aims to research and determine the fault type problem of a power distribution network during single-phase grounding, and provides a single-phase grounding fault studying and judging method based on the combination of wavelet transformation and deep learning.
In order to achieve the above purpose, the invention adopts the following technical scheme: a judgment method based on the combination of wavelet transformation and a deep learning neural network comprises the following steps: constructing a distribution network fault model of metallic grounding, high-resistance grounding, excessive resistance grounding, uniformly-spaced arc grounding and non-uniformly-spaced arc grounding, and setting different fault initial phase angles, fault positions and different excessive resistances at equal intervals; a large amount of fault waveform data is obtained. Further, binary discrete wavelet transform is adopted to process signals, fault data are processed, and fault features are extracted to carry out combined processing on the fault features.
The specific combination mode of the fault characteristics is as follows: wavelet band energy and energy entropy, wavelet frequency entropy and entropy weight, wavelet packet band energy and energy entropy, and wavelet packet frequency entropy and entropy weight. Different fault types have different entropy values after wavelet transformation.
Further, a deep learning model is built, the deep learning model is shown in fig. 1, and the training method of the deep learning model is as follows: pre-training the deep learning model by using training set data to obtain parameters of a convolution layer and a full connection layer in the deep learning model; and setting the maximum iteration times of the network, a training error threshold value and a learning factor. Based on the setting, the deep network is trained, a method that only one sample is calculated every time the weight is updated is adopted, and iteration is repeated.
Further, the method further comprises a step of verifying the result of the deep learning model, and specifically comprises the following steps:
introducing a fault identification rate as an identification evaluation index, wherein the calculation method comprises the following steps:
Fault＝(C/T)*100％
in the formula: t is an input known fault test sample set; c is the number of correctly identified samples in the set; and judging whether the network error meets the requirement. And when the error reaches the preset precision or the learning times are greater than the set maximum times, ending the algorithm. Otherwise, selecting the next learning sample and the corresponding expected output, returning to the third step, and entering the next round of learning.
The present invention also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the wavelet and deep learning based single-phase ground fault discrimination method as provided in the above technical solution.
Compared with the prior product, the invention has the following beneficial effects: the invention discloses a single-phase earth fault identification method based on wavelet and deep learning, wherein wavelet transformation is adopted to process fault voltage and current to obtain characteristic values. And then, identifying the fault characteristic value by using a fault identification method of deep learning. The method and the system assist the dispatcher to accurately identify the single-phase earth fault of the power distribution network so as to form an operable result, improve the fault processing efficiency of the dispatcher and ensure the operation stability of the power distribution network.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of single-phase earth fault simulation of a 10KV neutral point ungrounded system;
FIG. 3 is a diagram of a deep learning neural network architecture;
fig. 4 is a diagram of a deep learning neural network architecture.
Detailed Description
The invention is described in detail below with reference to the figures and the specific embodiments.
Referring to fig. 1 to 4: a distribution network single-phase earth fault identification method based on wavelets and deep learning is disclosed. Referring to FIG. one, the method includes the steps of: step one, acquiring a large amount of fault waveform data by utilizing fault simulation. Step two, performing wavelet transformation on the acquired fault voltage and current data, extracting fault characteristic quantities, and performing combined processing on the characteristic quantities, wherein the specific combination mode is as follows: wavelet band energy and energy entropy, wavelet frequency entropy and entropy weight, wavelet packet band energy and energy entropy, and wavelet packet frequency entropy and entropy weight. And step three, constructing a deep learning network, taking the combined characteristic quantity as a learning sample, and identifying the single-phase earth fault of the distribution network by using the deep learning network after training.
The specific implementation way of the first step is as follows: referring to fig. 2, a schematic diagram of a 10KV distribution network fault model is shown, wherein a distribution network fault model with metallic grounding, high resistance grounding, excessive resistance grounding, uniformly spaced arc grounding and non-uniformly spaced arc grounding is set, and different fault initial phase angles, fault positions and different excessive resistances are set at equal intervals; a large amount of fault data is obtained. The line data of the fault model is referenced in table 1.
TABLE 1 distribution network line positive/negative/zero sequence parameters
Figure BDA0003402940490000041
The specific implementation manner of the second step is as follows: the binary discrete wavelet transform is adopted, and the mathematical process is as follows:
Figure BDA0003402940490000042
wherein τ is a translation factor; a is a scaling factor; t is sampling time; m is the number of layers of wavelet decomposition;
Figure BDA0003402940490000043
is a mother wavelet; f (t) is the signal to be analyzed; wf (m, n) is a wavelet transform coefficient. When a is 2 and T is 1, the transform is a binary discrete wavelet transform. Extracting db4 wavelet as wavelet basis function, extracting zero sequence current at certain sampling frequency, decomposing wavelet signal by 10 layers, reconstructing signal after decomposition, and performing dimensionless treatment to its coefficient to obtain entropy of each layer of reconstruction coefficient, expressed by formula:
Figure BDA0003402940490000044
in the formula qj,kResult after dimensionless processing, NjIs the data length of the detail coefficient of the j-th layer signal. Based on the mathematical definition of wavelet entropy, the wavelet entropy weight can be obtained.
Figure BDA0003402940490000045
The formula (1) m is the number of layers of wavelet decomposition; max (E)fej) For the maximum value of the j layer frequency entropy of the reconstructed signal, combining (2) and (3) to calculate the entropy weight of the wavelet single branch reconstruction coefficient of the signal to be analyzed on different frequency bandsSimilar to the entropy, the wavelet packet entropy weight and the entropy can also be calculated.
The entropy weight and the entropy value obtained after the calculation in the process are the characteristic quantities of fault voltage, current, zero sequence voltage and current, and different fault types have different characteristic quantities.
Referring to fig. 3, the third step is implemented as follows: the deep learning network structure shown has 3 layers of hidden deep networks, and except for the input nodes, the stimulus received by each neuron is the sum of the products of the previous layer of network and the corresponding weight. Taking hidden layer 1 as an example, then hidden layer 1 is obtained, and the excitation obtained by the jth neuron is:
Figure BDA0003402940490000051
wherein the term with subscript 0 represents the network bias term, and the activation output value of the jth neuron of the hidden layer is set as h1jThen, there are:
Figure BDA0003402940490000052
the same can be said of the stimulus and activation output values obtained by the jth neuron of hidden layer 2. The j-th neuron of the output layer receives the excitation as follows:
Figure BDA0003402940490000053
setting the activation output value obtained by the output layer as yjThen, there are:
Figure BDA0003402940490000054
the function f (x) in the formula is the activation function of the deep network.
And selecting a Log-sigmoid function as an activation function. The number of the selected deep network hidden layers is 3. The number of network input nodes based on the wavelet and wavelet packet feature quantities is 22 and 16, respectively. The number of the output nodes is 6, each output node corresponds to a fault, and the node with the maximum output value represents the identification result of the current input sample
The maximum iteration number of the network is set to be l000, the training error threshold value is set to be 0.0001, and the learning factor is set to be 0.001. Based on the setting, the deep network is trained, and a method that only one sample is calculated every time the weight is updated is adopted, so that the training efficiency can be improved, and the model can jump out of local optimum. Based on the weight modification principle of gradient descent and back propagation, iteration is carried out repeatedly, the network can adaptively adjust the weights of all layers until the error is lower than the artificially set threshold, and the network training is finished.
The performance of the first set of feature quantity network training process is shown in fig. 4.
According to the model and the classifier formed in the three steps, incoming waveforms are matched and analyzed one by one, steady-state data of a real-time system are simultaneously superposed to perform multi-algorithm normalization analysis, fault identification results obtained by classifying in the steps 1 and 2 are adopted, and comprehensive analysis is performed by utilizing steady-state information such as voltage, current, network topological relation and the like to form a fault interval and an operable fault processing strategy, so that all fault studying and judging logics are completed.
The specific analysis method is as follows:
a) obtaining fault indicator waveform files collected by a power distribution automation system
b) Identifying fault by using fault model for waveform file, classifying fault conditions by using fast classifier, and
and acquiring standard fault waveforms of corresponding categories.
c) And performing topology analysis according to the fault indicators with the fault waveforms, and analyzing a topology model of the communication area where the equipment is located (starting from the main network bus, forming a topological upstream-downstream connection relation of all the fault indicators where the communication area is located).
d) And acquiring waveform files of all fault indicators under the same bus (if the files exist, the equipment is eliminated if the files do not exist), and identifying and classifying the faults of the waveform files of all fault indicators under the bus.
e) And classifying all the equipment with fault waveforms according to fault types, acquiring the classification with the largest action number as a total classification for judging faults, and recording other classification results as suspected classification results.
f) The equipment with fault waveform is used as a fault signal, and the current earth fault is positioned, analyzed and analyzed
The principle is that the traditional positioning logic (dyeing principle) is adopted for positioning (as shown in figure 4), and a final fault positioning interval is formed.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (7)

1. A method for identifying a single-phase earth fault of a power distribution network based on wavelets and deep learning is characterized by comprising the following steps: the method comprises the following steps:
s1, simulating the faults of the power distribution network under various fault conditions to acquire a large amount of fault data;
s2, processing the collected signals, extracting fault characteristic quantities, and combining the characteristic quantities;
s3, constructing a deep learning neural network, and training the combined characteristic quantity as a sample to obtain a training model;
and S4, identifying the single-phase earth faults of different fault types according to the trained model.
2. The wavelet and deep learning-based power distribution network single-phase ground fault identification method according to claim 1, wherein faults under various fault conditions are simulated in the step S1, a large amount of fault data are obtained, specifically, a distribution network fault model of metallic grounding, high resistance grounding, excessive resistance grounding, interval uniform arc grounding and interval nonuniform arc grounding is built, and different fault initial phase angles, fault positions and different excessive resistances are set at equal intervals; a large amount of fault data is obtained.
3. The wavelet and deep learning-based power distribution network single-phase earth fault identification method as claimed in claim 1, wherein in step S2, fault feature quantities are extracted, specifically: the method comprises the steps of processing signals by adopting binary discrete wavelet transform, integrating functions obtained by translating and stretching and translating mother wavelets and collected fault voltage and current signals to obtain wavelet basis functions, then performing 10-layer wavelet decomposition on the collected zero sequence voltage, performing single reconstruction on the signals after decomposition, performing non-dimensionalization on coefficients of the signals, calculating frequency entropy values of the single reconstruction coefficients at each layer, and calculating entropy weight. And analyzing the wavelet packet on the basis of wavelet transformation to obtain the entropy value and entropy weight of the wavelet packet.
4. The method for identifying the single-phase earth fault of the power distribution network based on the wavelet and the deep learning of claim 1, wherein the characteristic quantities are combined in step S2, and the specific combination manner is as follows: wavelet band energy and energy entropy, wavelet frequency entropy and entropy weight, wavelet packet band energy and energy entropy, and wavelet packet frequency entropy and entropy weight.
5. The method for identifying the single-phase earth fault of the power distribution network based on the wavelet and the deep learning of claim 1, wherein the step S3 is to construct a deep learning neural network as shown in fig. 1, the neurons in each layer of the deep network are fully connected only with the neurons in the adjacent layer, no connection exists between the neurons in the same layer, the deep learning model has 3 hidden layers, the combination mentioned in the above 4 is the name of the input node and the variable of the deep network, the maximum iteration number of the network is set to 1000, the training error threshold is 0.0001, the learning factor is set to 0.001, the deep network is trained based on the above setting, a method of calculating only one sample for updating the weight value every time is adopted, so as to improve the training efficiency, also help the model to jump out the local optimum, and repeatedly iterate based on the weight value modification principle of gradient descent and back propagation, the network can self-adaptively adjust the weight values of all layers until the error is lower than the artificially set threshold value, and the network training is finished.
6. The wavelet and deep learning-based power distribution network single-phase ground fault identification method as claimed in claim 1, wherein the step S4 is characterized in that the training model obtained in the step S3 is used to perform fault discrimination on the single-phase ground fault.
7. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Figure RE-FDA0003441402410000021
Wherein τ is a translation factor; a is a scaling factor; t is sampling time; m is the number of layers of wavelet decomposition;
Figure RE-FDA0003441402410000022
(t) is a mother wavelet; f (t) is the signal to be analyzed; wf (m, n) is a wavelet transform coefficient, when a is 2 and T is 1, the wavelet transform is binary discrete wavelet transform, db4 wavelet is extracted as wavelet basis function, zero sequence voltage at fault is extracted at a certain sampling frequency, 10 layers of wavelet decomposition are performed on wavelet signal, signal is reconstructed in single branch after decomposition, the coefficient is subjected to non-dimensionalization processing, entropy of each layer of the reconstruction coefficient can be calculated, and the formula is represented as:
Figure RE-FDA0003441402410000031
in the formula qj,kResult after dimensionless processing, NjThe data length of the detail coefficient of the j-th layer signal can obtain the wavelet entropy weight based on the mathematical definition of the wavelet entropy,
Figure RE-FDA0003441402410000032
the formula (1) m is the number of layers of wavelet decomposition; max (E)fej) For the maximum value of the j-th layer frequency entropy of the reconstructed signal, the entropy weight and the entropy value of the wavelet single branch reconstruction coefficient of the signal to be analyzed on different frequency bands can be calculated by combining the (2) and the (3), and the wavelet packet entropy weight and the entropy value can also be calculated in the same way.
CN202111505119.0A 2021-12-10 2021-12-10 Power distribution network single-phase earth fault identification method based on wavelet and deep learning Pending CN114186590A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111505119.0A CN114186590A (en) 2021-12-10 2021-12-10 Power distribution network single-phase earth fault identification method based on wavelet and deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111505119.0A CN114186590A (en) 2021-12-10 2021-12-10 Power distribution network single-phase earth fault identification method based on wavelet and deep learning

Publications (1)

Publication Number Publication Date
CN114186590A true CN114186590A (en) 2022-03-15

Family

ID=80604258

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111505119.0A Pending CN114186590A (en) 2021-12-10 2021-12-10 Power distribution network single-phase earth fault identification method based on wavelet and deep learning

Country Status (1)

Country Link
CN (1) CN114186590A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116087692A (en) * 2023-04-12 2023-05-09 国网四川省电力公司电力科学研究院 Distribution network tree line discharge fault identification method, system, terminal and medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116087692A (en) * 2023-04-12 2023-05-09 国网四川省电力公司电力科学研究院 Distribution network tree line discharge fault identification method, system, terminal and medium

Similar Documents

Publication Publication Date Title
CN111239549A (en) Power distribution fault rapid positioning method based on discrete wavelet transform
CN106203531A (en) A kind of transmission line fault sorting technique based on the sparse autocoder of convolution
Decanini et al. Robust fault diagnosis in power distribution systems based on fuzzy ARTMAP neural network-aided evidence theory
CN110543921A (en) cable early fault identification method based on waveform learning
CN112051480A (en) Neural network power distribution network fault diagnosis method and system based on variational modal decomposition
CN102279358A (en) MCSKPCA based neural network fault diagnosis method for analog circuits
Gowrishankar et al. Transmission line fault detection and classification using discrete wavelet transform and artificial neural network
CN113222036B (en) Automatic defect identification method and device for high-voltage cable grounding system
CN109142851A (en) A kind of novel power distribution network internal overvoltage recognition methods
CN112180217A (en) Power distribution network single-phase earth fault section positioning method and system
CN113466634B (en) Ground fault waveform identification method based on fault indicator
CN116524200A (en) High-voltage circuit breaker fault diagnosis method based on image recognition
Bhattacharya Fault detection on a ring-main type power system network using artificial neural network and wavelet entropy method
Chi et al. A CNN recognition method for early stage of 10 kV single core cable based on sheath current
CN114186590A (en) Power distribution network single-phase earth fault identification method based on wavelet and deep learning
CN112381667B (en) Distribution network electrical topology identification method based on deep learning
CN113092899B (en) Transformer electrical fault identification method, system, terminal and readable storage medium
CN113945862A (en) Method, device and equipment for identifying high-resistance grounding fault of power distribution network
CN111695543B (en) Method for identifying hidden danger discharge type of power transmission line based on traveling wave time-frequency characteristics
Wang et al. Transmission line fault diagnosis based on wavelet packet analysis and convolutional neural network
CN116224158A (en) CNN-LSTM-Attention-based multi-terminal flexible direct current transmission line monopole grounding fault positioning method
CN114062832A (en) Method and system for identifying short-circuit fault type of power distribution network
CN114252725A (en) HHT and ResNet 18-based single-phase earth fault type comprehensive identification method
Zhu et al. Fault Phase Identification Method Based on Convolutional Neural Network for Double Circuit Transmission Lines
Lopes et al. Harmonic selection-based analysis for high impedance fault location using Stockwell transform and random forest

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