CN112327098A - Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit - Google Patents
Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit Download PDFInfo
- Publication number
- CN112327098A CN112327098A CN202011170748.8A CN202011170748A CN112327098A CN 112327098 A CN112327098 A CN 112327098A CN 202011170748 A CN202011170748 A CN 202011170748A CN 112327098 A CN112327098 A CN 112327098A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- voltage distribution
- low
- neural network
- monitoring unit
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
Abstract
The invention provides a power distribution network fault section positioning method based on a low-voltage distribution network comprehensive monitoring unit, which is based on a topology dynamic change power distribution network fault section positioning and isolation model system architecture of an improved genetic algorithm, acquires historical operation data of the low-voltage distribution network as sample data by meshing the low-voltage distribution network, trains a BP neural network by combining the genetic algorithm to obtain the BP neural network for predicting the fault of the low-voltage distribution network comprehensive monitoring unit, and transmits the real-time operation data of the low-voltage distribution network comprehensive monitoring unit into the BP neural network to accurately predict and position whether the low-voltage distribution network comprehensive monitoring unit is in fault or not, so that the rapid calculation and positioning of the power distribution network fault section are realized, and technical support is provided for panoramic intelligent isolation decision making and the like of the low-voltage distribution network fault recurrence and the self-determination.
Description
Technical Field
The invention relates to a power distribution network fault section positioning method based on a low-voltage distribution network comprehensive monitoring unit, and belongs to the field of electrical engineering science.
Background
The low-voltage distribution network is an important link in the operation of the power grid, plays a role in connecting the whole power grid operation and maintenance system, and the realization of the intellectualization of the low-voltage distribution network is an important way for realizing the intelligent power grid. Based on the development demand of present smart power grids construction, wisdom low voltage distribution network should possess and include: the fault section positioning capability under the complex operation and maintenance environment is realized, namely, a fault area is awakened or isolated through continuous evaluation self-test, and the site is recovered to the greatest extent; the system has strong resistance to attacks inside and outside the environment, actively prevents physical attacks from inside and outside the environment through various ways such as encryption identification, attack early warning and the like, and effectively reduces loss caused by external threats; the method has compatible interactivity for various scenes, is oriented to various application scenes, has compatibility for heterogeneous networks, coordinates power wholesale and retail markets, and realizes multidimensional attributes such as benefit maximization.
The existing distribution fault positioning method mainly comprises matrix method positioning based on distribution network faults and fault positioning adopting an intelligent algorithm. The method is mainly characterized in that a power distribution network fault positioning matrix method is based on correctness of fault information installed and uploaded on a power distribution network, on the basis, power distribution network topology, multiple power supplies and algorithm efficiency improvement are taken as main research focuses, but if the power distribution network is installed incompletely or not installed on a line, the method is not applicable at all, and the method is too large in limitation for actual field application; for the fault location of the power distribution network by adopting an intelligent algorithm, the fault location algorithm based on protection and circuit breaker information suitable for the power transmission network is improved, the actual situation of the power distribution network is not fully considered, the research focus is on how to distinguish error information, how to make accurate probability-based inference under the condition of incomplete information, and fault information returned by various monitoring terminals in the power distribution network is not based, so the algorithm is rigorous in theory and strict in logic, but the practicability is not strong.
Disclosure of Invention
The invention adopts the following technical scheme for solving the technical problems: a power distribution network fault section positioning method based on a low-voltage distribution network comprehensive monitoring unit is provided, a BP neural network model for monitoring whether a low-voltage distribution network has a fault is obtained through steps 1 to 3, and for a target low-voltage distribution network, a prediction result of whether the target low-voltage distribution network has the fault is obtained by inputting operation data of the low-voltage distribution network obtained in real time into the BP neural network model;
step 1, collecting data of a preset proportion in historical operation data of a target low-voltage distribution network as training sample data, using the remaining data as test sample data, firstly determining a topological structure of a BP neural network, obtaining an initial weight and an initial threshold of the BP neural network, coding the initial weight and the initial threshold of the BP neural network to obtain a weight and a threshold of the coded BP neural network, and then entering step 2;
step 2, decoding the weight and the threshold of the BP neural network, training the neural network by using training sample data to obtain a BP neural network model, testing the BP neural network by using test sample data, taking the obtained prediction error as an individual fitness value in a typical genetic algorithm, and then entering step 3;
step 3, carrying out self-adaptive adjustment on the weight and the threshold of the BP neural network by using a typical genetic algorithm to obtain the weight and the threshold of the BP neural network after updating, judging whether an ending condition is met, if so, decoding the weight and the threshold of the BP neural network output by the genetic algorithm to obtain the optimal weight and threshold of the BP neural network, namely obtaining a BP neural network model for monitoring whether a low-voltage distribution network has faults; if not, returning to the step 2.
As a preferred technical scheme of the invention: the historical operating data of the target low-voltage distribution network comprises fault data and non-fault data.
As a preferred technical scheme of the invention: the historical operation data of the target low-voltage distribution network is preprocessed and then used for training the BP neural network, and the preprocessing step comprises the step of removing missing values and obviously wrong values.
As a preferred technical scheme of the invention: before training the BP neural network and predicting the faults of the target low-voltage distribution network, firstly, grid division is carried out on the target low-voltage distribution network to divide the target low-voltage distribution network into all the comprehensive monitoring unit areas, and the prediction result of whether the target low-voltage distribution network has the faults or not is obtained by inputting the operation data of the low-voltage distribution network in the comprehensive monitoring unit areas obtained in real time into a BP neural network model aiming at all the comprehensive monitoring unit areas, so that the fault section where the target low-voltage distribution network comprehensive monitoring unit is located is quickly positioned.
As a preferred technical scheme of the invention: the sample data extracted from the integrated monitoring unit after grid division comprises power loss, impedance parameters, voltage drop, environmental information and leakage protection.
As a preferred technical scheme of the invention: when the comprehensive monitoring unit after grid division comprises the transformer and the controller, the extracted sample data also comprises the state of the transformer and the state of the reactive power controller.
Compared with the prior art, the technical scheme is adopted, the low-voltage distribution network is subjected to gridding division, historical operation data of the low-voltage distribution network are obtained and used as sample data, the BP neural network is trained by combining a genetic algorithm, the BP neural network used for predicting the faults of the comprehensive monitoring unit of the low-voltage distribution network is obtained, and the data of real-time operation of the comprehensive monitoring unit of the low-voltage distribution network is transmitted into the BP neural network, so that whether the comprehensive monitoring unit of the low-voltage distribution network is in fault or not is accurately predicted and positioned, and therefore the rapid calculation and positioning of the fault section of the distribution network are achieved, and technical support is provided for panoramic low-voltage distribution network fault recurrence, autonomous intelligent isolation decision making.
Drawings
FIG. 1 is a schematic diagram of a positioning and isolation model architecture;
FIG. 2 is a logic diagram of an improved genetic algorithm for fusing BP neural network mechanisms.
Detailed Description
The following description will explain embodiments of the present invention in further detail with reference to the accompanying drawings.
The invention designs a power distribution network fault section positioning method based on a low-voltage distribution network comprehensive monitoring unit, and in practical application, as shown in figure 1, the scheme comprises that a power distribution network fault section positioning and isolation model system architecture is divided into a holographic data perception sub-model, a fault section data rapid calculation and positioning sub-model, a fault panoramic reproduction and autonomous intelligent isolation decision sub-model, a cross-platform man-machine interaction sub-model and the like, wherein the holographic data perception sub-model rapidly perceives and temporarily stores multidimensional data such as a transformer state, a reactive power controller state, power loss, impedance parameters, voltage drop, environmental information, leakage protection and the like by means of a data fusion algorithm embedded with Storm current calculation; the fault section data rapid calculation and positioning sub-model utilizes the historical operation and maintenance data of the power distribution network to carry out targeted training on the BP neural network, collects the prediction error of the training data and maps the prediction error into an individual fitness value, and utilizes a classical genetic algorithm to carry out self-adaptive adjustment on the weight and the threshold of the BP neural network; the fault panoramic reproduction and autonomous intelligent isolation decision submodel captures an optimal individual by using a BP neural network, assigns a network initial weight and a threshold value, and outputs a target result by means of a positioning and isolation function; and the cross-platform man-machine interaction layer realizes the autonomous decision of the operation and maintenance strategy and the friendly man-machine interaction under the cross-platform application system.
According to the scheme, a typical genetic algorithm is improved and optimized, the logic schematic diagram of an internal control flow is shown in fig. 2, the typical genetic algorithm replaces the backward feedback process of the original BP neural network, the problems of positioning and isolating of the fault section of the distribution network with topology dynamic change can be effectively solved, and the functions of the real-time property of the topology dynamic change of the distribution network, the fault tolerance under the constraint of multi-dimensional parameters of heterogeneous equipment of the distribution network, the search convergence speed and the like are improved. Firstly, a BP neural network model for monitoring whether a low-voltage distribution network has faults is obtained through the following steps 1 to 3, and then in the actual operation process, the operation data of the low-voltage distribution network in the area of the comprehensive monitoring unit obtained in real time is input into the BP neural network model to obtain the prediction result of whether the target low-voltage distribution network has the faults, so that the fault section where the target low-voltage distribution network comprehensive monitoring unit is located is quickly positioned. The detailed steps are as follows:
step 1, firstly, grid division is carried out on a target low-voltage distribution network, the distribution network is divided into all comprehensive monitoring unit areas, then, in a large data magnitude distribution network fault section positioning and isolation shared data resource pool, after missing numerical values and obviously wrong numerical values are recorded and removed, 2000 groups of input and output data are obtained, 1900 groups of input and output data are randomly selected as training sample data for network training, 100 groups of input and output data are used as test sample data, the input sample data comprise power loss, impedance parameters, voltage drop, environmental information and leakage protection data, when the comprehensive monitoring units after grid division comprise a transformer and a controller, the extracted sample data further comprise a transformer state and a reactive power controller state, firstly, according to the input and output data, the topological structure of a BP neural network is determined, and the initial weight and the initial threshold of the BP neural network are obtained, coding the initial weight and the initial threshold of the BP neural network to obtain the weight and the threshold of the BP neural network after coding, and then entering the step 2;
decoding the weight value and the threshold value of the BP neural network, training the neural network by using training sample data to obtain a BP neural network model, testing the BP neural network by using test sample data, and taking the obtained prediction error as an individual fitness value in a typical genetic algorithm, wherein the prediction error is obtained by the following formulas (1) to (4):
where ρ isβ(s) is the calculation step size, E is the expectation operator, Qμ(s, μ (s)) represents the expected value of the return obtained using the μ policy to select actions in the s state,
based on the above formula, an evaluation function representing the superior and inferior performances of the low-voltage distribution network fault section autonomous perception and autonomous generation isolation strategy μ under the topology dynamic change situation is as follows:
L(θ)＝Es,a,r,s′[(Q*(s,a|θ)-y)2] (2)
l (theta) is the mean square error of the network output Q and the algorithm calculation output y, a BP neural network structure certainty strategy formula is given based on the formula (2), because the BP neural network structure adopts a randomness strategy, the probability distribution of an optimal strategy needs to be sampled to obtain the current action, and in the iteration process, each step needs to integrate the whole action space, so the calculation amount is large, the certainty strategy is adopted based on the target neural network, an action is directly determined through a function mu according to the action, and mu can be understood as an optimal action strategy at＝μ(st|θμ) Then quantified BP neural network
The structure determination model can be characterized as follows:
considering the instability of the formula (3) in the multidimensional competition environment, the first-order derivation processing is performed on the formula (3), so that the optimal generation mechanism of the BP neural network structure can be represented as a formula (4), the compatibility is high, the automatic real-time perception and fusion of the multidimensional equipment fault information in the power distribution station area and the isolation strategy autonomous decision generation mechanism in the multidimensional equipment fault operation and maintenance state can be realized through self-learning.
Is J (mu)θ) To muθWill converge to make the mean square error J (μ)θ) The minimum solution is reached.
Then entering step 3;
step 3, carrying out self-adaptive adjustment on the weight and the threshold of the BP neural network by using a typical genetic algorithm to obtain the weight and the threshold of the updated BP neural network, setting an ending condition that the iteration times reach 1000 times, judging whether the ending condition is met, if so, decoding the weight and the threshold of the BP neural network output by the genetic algorithm to obtain the optimal weight and the threshold of the BP neural network, namely obtaining a BP neural network model for monitoring whether the low-voltage distribution network has faults; if not, returning to the step 2.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (6)
1. The method for positioning the fault section of the power distribution network based on the low-voltage distribution network comprehensive monitoring unit is characterized in that a BP neural network model for monitoring whether the low-voltage distribution network has faults or not is obtained through steps 1 to 3, and for a target low-voltage distribution network, a prediction result of whether the target low-voltage distribution network has faults or not is obtained by inputting operation data of the low-voltage distribution network obtained in real time into the BP neural network model;
step 1, collecting data of a preset proportion in historical operation data of a target low-voltage distribution network as training sample data, using the remaining data as test sample data, firstly determining a topological structure of a BP neural network, obtaining an initial weight and an initial threshold of the BP neural network, coding the initial weight and the initial threshold of the BP neural network to obtain a weight and a threshold of the coded BP neural network, and then entering step 2;
step 2, decoding the weight and the threshold of the BP neural network, training the neural network by using training sample data to obtain a BP neural network model, testing the BP neural network by using test sample data, taking the obtained prediction error as an individual fitness value in a typical genetic algorithm, and then entering step 3;
step 3, carrying out self-adaptive adjustment on the weight and the threshold of the BP neural network by using a typical genetic algorithm to obtain the weight and the threshold of the BP neural network after updating, judging whether an ending condition is met, if so, decoding the weight and the threshold of the BP neural network output by the genetic algorithm to obtain the optimal weight and threshold of the BP neural network, namely obtaining a BP neural network model for monitoring whether a low-voltage distribution network has faults; if not, returning to the step 2.
2. The method for locating the fault section of the power distribution network based on the low-voltage distribution network comprehensive monitoring unit as recited in claim 1, wherein historical operation data of a target low-voltage distribution network comprises fault data and non-fault data.
3. The method for locating the fault section of the power distribution network based on the low-voltage distribution network comprehensive monitoring unit as claimed in claim 1, wherein the historical operating data of the target low-voltage distribution network is preprocessed and then used for training a BP neural network, and the preprocessing step comprises removing missing values and obviously wrong values.
4. The method for locating the distribution network fault section based on the low-voltage distribution network comprehensive monitoring unit is characterized in that before a BP neural network is trained and a target low-voltage distribution network is subjected to fault prediction, a target low-voltage distribution network is firstly subjected to grid division and divided into all comprehensive monitoring unit areas, and for all the comprehensive monitoring unit areas, a prediction result of whether a fault exists in the target low-voltage distribution network is obtained by inputting real-time operation data of the low-voltage distribution network in the comprehensive monitoring unit areas into a BP neural network model, so that the fault section where the target low-voltage distribution network comprehensive monitoring unit is located is rapidly located.
5. The method for locating the fault section of the power distribution network based on the low-voltage distribution network integrated monitoring unit is characterized in that sample data extracted from the integrated monitoring unit after grid division comprises power loss, impedance parameters, voltage drop, environmental information and leakage protection.
6. The method for locating the fault section of the power distribution network based on the low-voltage distribution network comprehensive monitoring unit as claimed in claim 5, wherein when the comprehensive monitoring unit after grid division comprises a transformer and a controller, the extracted sample data further comprises a transformer state and a reactive controller state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011170748.8A CN112327098A (en) | 2020-10-28 | 2020-10-28 | Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011170748.8A CN112327098A (en) | 2020-10-28 | 2020-10-28 | Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112327098A true CN112327098A (en) | 2021-02-05 |
Family
ID=74295983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011170748.8A Pending CN112327098A (en) | 2020-10-28 | 2020-10-28 | Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112327098A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113759204A (en) * | 2021-11-10 | 2021-12-07 | 成都高斯电子技术有限公司 | Power line loss testing device and method |
| CN116223971A (en) * | 2023-02-24 | 2023-06-06 | 合肥威标科技有限公司 | Auxiliary positioning system for fault area of power distribution network based on multi-source information |
| CN116559598A (en) * | 2023-07-10 | 2023-08-08 | 武汉创星空间科技发展有限公司 | Smart distribution network fault positioning method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103411970A (en) * | 2013-07-17 | 2013-11-27 | 同济大学 | Alternating current transmission line insulator contamination condition detection method based on infrared thermography |
| CN106650022A (en) * | 2016-11-25 | 2017-05-10 | 天津津航计算技术研究所 | Method for predicting fault of complex electronic device |
| CN109165764A (en) * | 2018-06-26 | 2019-01-08 | 昆明理工大学 | A kind of line loss calculation method of genetic algorithm optimization BP neural network |
| CN109459671A (en) * | 2018-09-27 | 2019-03-12 | 国网浙江省电力有限公司湖州供电公司 | A kind of switch cabinet state monitoring method of the improvement neural network based on genetic algorithm |
| US20190242936A1 (en) * | 2018-02-05 | 2019-08-08 | Wuhan University | Fault diagnosis method for series hybrid electric vehicle ac/dc converter |
| CN110533549A (en) * | 2019-07-12 | 2019-12-03 | 杭州电子科技大学 | One kind optimizing RS-BP neural network electric network fault localization method based on GA |
| CN111143173A (en) * | 2020-01-02 | 2020-05-12 | 山东超越数控电子股份有限公司 | Server fault monitoring method and system based on neural network |
-
2020
- 2020-10-28 CN CN202011170748.8A patent/CN112327098A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103411970A (en) * | 2013-07-17 | 2013-11-27 | 同济大学 | Alternating current transmission line insulator contamination condition detection method based on infrared thermography |
| CN106650022A (en) * | 2016-11-25 | 2017-05-10 | 天津津航计算技术研究所 | Method for predicting fault of complex electronic device |
| US20190242936A1 (en) * | 2018-02-05 | 2019-08-08 | Wuhan University | Fault diagnosis method for series hybrid electric vehicle ac/dc converter |
| CN109165764A (en) * | 2018-06-26 | 2019-01-08 | 昆明理工大学 | A kind of line loss calculation method of genetic algorithm optimization BP neural network |
| CN109459671A (en) * | 2018-09-27 | 2019-03-12 | 国网浙江省电力有限公司湖州供电公司 | A kind of switch cabinet state monitoring method of the improvement neural network based on genetic algorithm |
| CN110533549A (en) * | 2019-07-12 | 2019-12-03 | 杭州电子科技大学 | One kind optimizing RS-BP neural network electric network fault localization method based on GA |
| CN111143173A (en) * | 2020-01-02 | 2020-05-12 | 山东超越数控电子股份有限公司 | Server fault monitoring method and system based on neural network |
Non-Patent Citations (1)
| Title |
|---|
| 黄宜林: "配电网故障定位算法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113759204A (en) * | 2021-11-10 | 2021-12-07 | 成都高斯电子技术有限公司 | Power line loss testing device and method |
| CN116223971A (en) * | 2023-02-24 | 2023-06-06 | 合肥威标科技有限公司 | Auxiliary positioning system for fault area of power distribution network based on multi-source information |
| CN116223971B (en) * | 2023-02-24 | 2023-12-12 | 合肥威标科技有限公司 | Auxiliary positioning system for fault area of power distribution network based on multi-source information |
| CN116559598A (en) * | 2023-07-10 | 2023-08-08 | 武汉创星空间科技发展有限公司 | Smart distribution network fault positioning method and system |
| CN116559598B (en) * | 2023-07-10 | 2023-09-15 | 武汉创星空间科技发展有限公司 | Smart distribution network fault positioning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112327098A (en) | Power distribution network fault section positioning method based on low-voltage distribution network comprehensive monitoring unit | |
| CN105785231B (en) | A kind of linear integer programming method of the online fault tolerance positioning of power distribution network | |
| CN102638100A (en) | District power network equipment abnormal alarm signal association analysis and diagnosis method | |
| CN102549513A (en) | Reliability calculation for substation automation systems | |
| CN101958536A (en) | Distribution network failure isolation and quick power service restoration decision support system | |
| CN107944657A (en) | A kind of electric power multi-source information fault location and pre-judging method | |
| CN111060815B (en) | GA-Bi-RNN-based high-voltage circuit breaker fault diagnosis method | |
| CN106503439A (en) | A kind of method of the collection fault early warning system based on data mining | |
| CN105974232B (en) | A kind of electric network failure diagnosis method suitable for grid | |
| CN111697566A (en) | Reliability assessment method for active power distribution network information physical system considering information failure | |
| CN101739025A (en) | Immunity genetic algorithm and DSP failure diagnostic system based thereon | |
| CN105425768A (en) | Electric power secondary equipment monitoring device and method | |
| CN113505458A (en) | Cascading failure key trigger branch prediction method, system, equipment and storage medium | |
| CN105337314B (en) | A kind of multi-source based on distributed power source black starting-up technology coordinates control fault handling method | |
| CN116865258A (en) | Hierarchical distributed power supply intelligent power grid construction method | |
| CN104407577A (en) | Intelligent check anti-maloperation method based on real-time trend | |
| CN114744616A (en) | Power recovery auxiliary decision-making method for power distribution network | |
| CN104050377A (en) | Method for determining probability of time-varying equipment failures | |
| CN201666923U (en) | Device for processing DSP failure diagnosis of electric power system by using immune genetic algorithm | |
| CN109740770A (en) | Unit exception processing method, device, computer equipment and storage medium | |
| Teng et al. | On-line fault diagnosis technology and application based on deep learning of fault characteristic of power grid | |
| CN111061152A (en) | Attack recognition method based on deep neural network and intelligent energy power control device | |
| Liu et al. | Artificial intelligence and computational intelligence: a challenge for power system engineers | |
| CN115827579A (en) | Distributed energy storage informatization control and operation platform architecture | |
| CN103390249B (en) | Based on the distribution scheduling aid decision method of various dimensions |
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 |