CN111338892A - Time sequence rise abnormity identification method under extreme operation condition - Google Patents
Time sequence rise abnormity identification method under extreme operation condition Download PDFInfo
- Publication number
- CN111338892A CN111338892A CN202010097025.3A CN202010097025A CN111338892A CN 111338892 A CN111338892 A CN 111338892A CN 202010097025 A CN202010097025 A CN 202010097025A CN 111338892 A CN111338892 A CN 111338892A
- Authority
- CN
- China
- Prior art keywords
- data
- maximum value
- average value
- value
- time 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method for recognizing abnormal rise of a time sequence under an extreme operation condition, which comprises the steps of dividing time units in a training stage, calculating the maximum value and the average value of training data in each time unit, traversing all the time units, and acquiring the maximum value and the maximum average value as a discrimination base number; in the early warning stage, acquiring real-time monitoring data, calculating the maximum value and the average value of the data in the current time unit, and calculating a jump index; judging whether the jump index is larger than a jump threshold value, if so, judging that the current time unit jumps; otherwise, further adjusting the discrimination cardinality; and analyzing adjacent time units, and if the number of the time units with jumping exceeds a number threshold value, sending out an alarm signal. The invention only occupies little memory during operation and has high operation speed. Meanwhile, the method has higher robustness, and can filter the condition of false rise caused by data jitter increase or integral migration.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a time sequence rise abnormity identification method under an extreme operation condition.
Background
Aiming at some specific fields, especially in the aspect of equipment abnormity monitoring, certain state information collected by a monitoring equipment sensor according to a fixed time interval is analyzed in real time, and once the state information is discovered to be abnormal, an alarm signal is sent out in time to carry out manual intervention so as to reduce loss to the maximum extent. Among the device status information anomalies, rising anomalies are the most common. If the state information is stable in the earlier stage, but the state information rises at a certain moment, an abnormal phenomenon of the equipment is necessarily reflected, and an early warning signal needs to be sent to equipment maintenance personnel in time.
There are various types of existing anomaly identification methods, which generally include: model-based methods, distance-based methods, and deep learning-based methods. However, due to the particularity of some special equipment, only limited storage space and computational power can be reserved for the monitoring algorithm, and the requirement on reaction time is high, and the method in the prior art cannot be well applied to equipment which runs under extreme running conditions (small memory space and high running speed); the specific analysis is as follows:
first, model-based methods generally consider data to satisfy a certain statistical rule, conforming to a certain statistical model, and when data does not satisfy the statistical model that should exist, it is considered to be abnormal. However, in the actual operation process, because the things processed by the instrument are different each time, the use habits of operators are different, and the temperature and humidity of the environment where the instrument is located are different, and other uncertain factors exist, various indexes of the instrument often cannot meet a specific statistical rule, and the instrument is difficult to be applied to a scene under an extreme operation condition.
Second, distance-based methods typically compute a local factor by the distance relationship between the outlier and its surrounding data points, and identify noise by the local factor. The algorithm needs to calculate local factor values of all data firstly, and then finds out the maximum or minimum part of data by sequencing the factor values, obviously cannot meet the timeliness, cannot monitor in real time, and is also difficult to adapt to extreme operating conditions.
In addition, the anomaly identification method based on deep learning is to complete the identification task by embedding anomaly identification into a neural network. However, the deep learning algorithm occupies a large space, and meanwhile, most of the abnormal recognition methods based on deep learning are supervised, a large amount of training data is needed, and most of historical data needs to meet the requirement of having a similar distribution rule.
Equipment operating under extreme operating conditions accomplishes highly complex tasks, and each time the equipment is operated, index distributions with different forms are generated, so that sufficient training data cannot be provided for training.
Therefore, it is an urgent problem to be solved by those skilled in the art to provide a time series rising abnormality identification method that can be applied to extreme operating conditions.
Disclosure of Invention
In view of this, the present invention provides a method for identifying a time series rising anomaly under an extreme operating condition, which only occupies little memory during operation, and has a fast operating speed, and the method has high robustness, and can effectively filter the false rising condition caused by large data jitter or overall migration.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for recognizing abnormal rise of a time sequence under an extreme operation condition comprises a training stage and an early warning stage;
the training phase comprises the following:
dividing a training data set into n time units, sequentially calculating the maximum value and the average value of the training data in each time unit, traversing all the time units, and acquiring the maximum value and the maximum average value as a discrimination base number;
the early warning stage comprises the following steps:
s1, acquiring real-time monitoring data, calculating the maximum value and the average value of the data in the current time unit, and calculating the jump index of the current time unit according to the maximum value and the average value of the data in the current time unit;
s2, if the jump index is larger than the jump threshold value and the maximum value and the average value of the data in the current time unit are both larger than the judgment base number, judging that the current time unit jumps;
if the jump index is smaller than the jump threshold value and the maximum value and the average value of the data in the current time unit are both larger than the judgment base number, further adjusting the judgment base number;
and S3, analyzing adjacent time units, and if the number of the time units with jumping exceeds a number threshold value, sending an alarm signal.
Preferably, before the training phase, a training time duration is determined, and the number of time units required by the training data set is calculated according to the training time duration, wherein the storage space required by each time unit is dc.
Preferably, the obtaining the discrimination bases specifically includes the following steps:
sequentially calculating the maximum value and the average value of the training data in each time unit, and only storing the current maximum value and the current maximum average value;
after traversing all time units, acquiring the maximum value and the maximum average value in all training data as the discrimination base number of the early warning stage;
the computation complexity of the maximum value and the average value of the training data in the time unit is o (dc), and the required storage space is dc +2, wherein dc storage spaces store the data in the current time unit, and 2 storage spaces are used for storing the discrimination cardinality.
Preferably, in S1, after acquiring the real-time monitoring data, when the data size is enough to a time unit, the maximum value and the average value of the data in the current time unit are calculated.
Preferably, the specific calculation method of the jump index is as follows:
within the current time unitMaximum and mean values of data and top m1Respectively comparing the maximum value and the average value of the data in each time unit, and increasing the jump index by a and m when the maximum value and the average value are greater than the maximum value1And after all the time units are compared, the final accumulated value is the jump index of the current time unit.
Preferably, the jump threshold is specifically set to m1/b。
Preferably, the method for adjusting the discrimination base number includes:
for the maximum value: firstly, calculating the difference between the maximum value of the data in the current time unit and the maximum value in the original judgment base number and calling the difference as the maximum value difference, and further calculating the sum of the a-time maximum value difference and the maximum value in the original judgment base number;
for the mean values: firstly, the difference value between the average value of the data in the current time unit and the average value in the original judgment base number is calculated and called as the average value difference value, and then the sum of the average value difference value of a times and the average value in the original judgment base number is calculated.
Preferably, the specific contents of S3 include the following:
analysis of adjacent m2A time unit of m2>m1If the number of the time units with jumping exceeds the number threshold value, the real-time monitoring data shows a rising trend, and an alarm signal is sent out.
It should be noted that: m is2And m1Are all hyper-parameters.
Compared with the prior art, the invention discloses a method for identifying the time series rising abnormity under the extreme operation condition, and the method has the following beneficial effects:
(1) the memory occupies little: the total memory space occupied by the invention is about m2Time units that are insignificant or even negligible relative to the entire data set;
(2) the operation speed is fast: the calculation operation of each time of the invention only occurs in m2On each time unit, and does not adopt any complex mathematical calculation formula,therefore, the running speed is very fast;
(3) high robustness: data jitter becomes large and overall migration is a common false rising condition, wherein the data jitter becomes large and only the range of data is enlarged due to the fact that the amplitude of the data becomes large, and the data overall migration is that the data moves upwards at a certain time node; both of these cases cause the upper bound of data to become large, but no ascending trend occurs; when the data is monitored, whether the data is falsely increased or not is continuously judged, and if the data is falsely increased, the judgment base number is adjusted, so that the occurrence of misjudgment is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for recognizing a time-series rising abnormality under an extreme operating condition according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a method for recognizing abnormal rise of a time sequence under an extreme operation condition, which comprises a training stage and an early warning stage as shown in figure 1;
the training phase includes the following:
dividing a training data set into a plurality of time units, sequentially calculating the maximum value and the average value of the training data in each time unit, traversing all the time units, and acquiring the maximum value and the maximum average value as a discrimination base number;
the early warning stage comprises the following contents:
s1, acquiring real-time monitoring data, calculating the maximum value and the average value of the data in the current time unit, and calculating the jump index of the current time unit according to the maximum value and the average value of the data in the current time unit;
s2, if the jump index is larger than the jump threshold value and the maximum value and the average value of the data in the current time unit are both larger than the discrimination base number, judging that the current time unit jumps;
if the jump index is smaller than the jump threshold value and the maximum value and the average value of the data in the current time unit are both larger than the discrimination base number, further adjusting the discrimination base number;
and S3, analyzing adjacent time units, and if the number of the time units with jumping exceeds a number threshold value, sending an alarm signal.
In order to further realize the technical scheme, before the training stage, the training time duration is determined, and the number of time units needed by the training data set is calculated according to the training time duration, wherein the storage space needed by each time unit is dc.
In order to further implement the above technical solution, the obtaining of the discrimination base specifically includes the following contents:
sequentially calculating the maximum value and the average value of the training data in each time unit, and only storing the current maximum value and the current maximum average value;
after traversing all time units, acquiring the maximum value and the maximum average value in all training data as the discrimination base number of the early warning stage;
the computation complexity of the maximum value and the average value of the training data in the time unit is o (dc), and the required storage space is dc +2, wherein dc storage spaces store the data in the current time unit, and 2 storage spaces are used for storing the discrimination cardinality.
In order to further implement the above technical solution, in S1, after the real-time monitoring data is acquired, when the data size is a time unit, the maximum value and the average value of the data in the current time unit are calculated.
In order to further realize the technical scheme, the specific calculation method of the jump index comprises the following steps:
and respectively comparing the maximum value and the average value of the data in the current time unit with the maximum value and the average value of the data in the previous 5 time units, increasing the jump index by 0.5 when the maximum value and the average value are greater than the maximum value and the average value, and after the comparison with the 5 time units is completed, taking the final accumulated value as the jump index of the current time unit.
In order to further implement the above technical solution, the jump threshold is specifically set to 5/2.
It should be noted that: 5/2 indicate that more than 50% of the values have increased.
In order to further realize the technical scheme, the method for adjusting the discrimination cardinality comprises the following steps:
for the maximum value: firstly, calculating the difference between the maximum value of the data in the current time unit and the maximum value in the original judgment base number and calling the difference as the maximum value difference, and further calculating the sum of the maximum value difference of 0.5 times and the maximum value in the original judgment base number;
for the mean values: firstly, the difference value between the average value of the data in the current time unit and the average value in the original judgment base number is calculated and called as the average value difference value, and then the sum of the average value difference value which is 0.5 times and the average value in the original judgment base number is calculated.
It should be noted that:
the specific calculation formula is as follows:
train_mean＝train_mean+0.5*(mean-train_mean)
train_max＝train_max+0.5*(max-train_max)
in order to further implement the above technical solution, S3 specifically includes the following contents:
and analyzing 20 adjacent time units, wherein 20>5, and if the number of the time units with jumping exceeds a number threshold value, indicating that the real-time monitoring data has a rising trend, and sending an alarm signal.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A time sequence rise abnormity identification method aiming at extreme operation conditions is characterized by comprising a training stage and an early warning stage;
the training phase comprises the following:
dividing a training data set into n time units, sequentially calculating the maximum value and the average value of the training data in each time unit, traversing all the time units, and acquiring the maximum value and the maximum average value as a discrimination base number;
the early warning stage comprises the following steps:
s1, acquiring real-time monitoring data, calculating the maximum value and the average value of the data in the current time unit, and calculating the jump index of the current time unit according to the maximum value and the average value of the data in the current time unit;
s2, if the jump index is larger than the jump threshold value and the maximum value and the average value of the data in the current time unit are both larger than the judgment base number, judging that the current time unit jumps;
if the jump index is smaller than the jump threshold value and the maximum value and the average value of the data in the current time unit are both larger than the judgment base number, further adjusting the judgment base number;
and S3, analyzing adjacent time units, and if the number of the time units with jumping exceeds a number threshold value, sending an alarm signal.
2. The method of claim 1, wherein a training time period is determined before the training phase, and the number of time units required for the training data set is calculated based on the training time period, wherein the storage space required for each time unit is dc.
3. The method according to claim 2, wherein the obtaining of the discrimination base specifically includes the following steps:
sequentially calculating the maximum value and the average value of the training data in each time unit, and only storing the current maximum value and the current maximum average value;
after traversing all time units, acquiring the maximum value and the maximum average value in all training data as the discrimination base number of the early warning stage;
the computation complexity of the maximum value and the average value of the training data in the time unit is o (dc), and the required storage space is dc +2, wherein dc storage spaces store the data in the current time unit, and 2 storage spaces are used for storing the discrimination cardinality.
4. The method for recognizing the time-series ascending abnormality under the extreme operating condition as recited in claim 1, wherein in S1, after the real-time monitoring data is acquired, the maximum value and the average value of the data in the current time unit are calculated after the data size reaches a time unit.
5. The method for recognizing the time-series rising abnormality under the extreme operating condition as recited in claim 1, wherein the jump index is calculated by:
the maximum value and the average value of the data in the current time unit and the previous m are compared1Respectively comparing the maximum value and the average value of the data in each time unit, and increasing the jump index by a and m when the maximum value and the average value are greater than the maximum value1And after all the time units are compared, the final accumulated value is the jump index of the current time unit.
6. Method for identifying time-series rising anomalies for extreme operating conditions, in accordance with claim 5, characterized in that said jump threshold is specifically set to m1/b。
7. The method for identifying the time-series rising abnormality under the extreme operating condition as recited in claim 6, wherein the method for adjusting the discrimination bases comprises the following steps:
for the maximum value: firstly, calculating the difference between the maximum value of the data in the current time unit and the maximum value in the original judgment base number and calling the difference as the maximum value difference, and further calculating the sum of the a-time maximum value difference and the maximum value in the original judgment base number;
for the mean values: firstly, the difference value between the average value of the data in the current time unit and the average value in the original judgment base number is calculated and called as the average value difference value, and then the sum of the average value difference value of a times and the average value in the original judgment base number is calculated.
8. The method for recognizing the time-series rising anomaly in the extreme operating condition according to claim 5, wherein S3 specifically comprises the following contents:
analysis of adjacent m2A time unit of m2>m1If the number of the time units with jumping exceeds the number threshold value, the real-time monitoring data shows a rising trend, and an alarm signal is sent out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010097025.3A CN111338892B (en) | 2020-02-17 | 2020-02-17 | Time sequence rise abnormity identification method under extreme operation condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010097025.3A CN111338892B (en) | 2020-02-17 | 2020-02-17 | Time sequence rise abnormity identification method under extreme operation condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111338892A true CN111338892A (en) | 2020-06-26 |
| CN111338892B CN111338892B (en) | 2022-02-15 |
Family
ID=71183487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010097025.3A Active CN111338892B (en) | 2020-02-17 | 2020-02-17 | Time sequence rise abnormity identification method under extreme operation condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111338892B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129525A (en) * | 2011-03-24 | 2011-07-20 | 华北电力大学 | Method for searching and analyzing abnormality of signals during vibration and process of steam turbine set |
| CN103793601A (en) * | 2014-01-20 | 2014-05-14 | 广东电网公司电力科学研究院 | Turbine set online fault early warning method based on abnormality searching and combination forecasting |
| CN103823980A (en) * | 2014-02-26 | 2014-05-28 | 浙江水利水电学院 | Method for detecting abnormal dam monitoring data based on entropy theory |
| CN106296435A (en) * | 2016-08-18 | 2017-01-04 | 西安科技大学 | A kind of mine gas monitoring disorder data recognition method |
| CN107341444A (en) * | 2017-06-07 | 2017-11-10 | 北京星网锐捷网络技术有限公司 | Data exception method for early warning and device |
| US9886559B1 (en) * | 2012-02-24 | 2018-02-06 | Cerner Innovation, Inc. | Assessing fitness by entropy and bispectral analysis |
| CN108829535A (en) * | 2018-06-08 | 2018-11-16 | 上海擎创信息技术有限公司 | Data processing method, terminal and computer readable storage medium |
| CN110286656A (en) * | 2019-05-07 | 2019-09-27 | 清华大学 | A kind of the false-alarm filter method and device of wrong data tolerance |
-
2020
- 2020-02-17 CN CN202010097025.3A patent/CN111338892B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129525A (en) * | 2011-03-24 | 2011-07-20 | 华北电力大学 | Method for searching and analyzing abnormality of signals during vibration and process of steam turbine set |
| US9886559B1 (en) * | 2012-02-24 | 2018-02-06 | Cerner Innovation, Inc. | Assessing fitness by entropy and bispectral analysis |
| CN103793601A (en) * | 2014-01-20 | 2014-05-14 | 广东电网公司电力科学研究院 | Turbine set online fault early warning method based on abnormality searching and combination forecasting |
| CN103823980A (en) * | 2014-02-26 | 2014-05-28 | 浙江水利水电学院 | Method for detecting abnormal dam monitoring data based on entropy theory |
| CN106296435A (en) * | 2016-08-18 | 2017-01-04 | 西安科技大学 | A kind of mine gas monitoring disorder data recognition method |
| CN107341444A (en) * | 2017-06-07 | 2017-11-10 | 北京星网锐捷网络技术有限公司 | Data exception method for early warning and device |
| CN108829535A (en) * | 2018-06-08 | 2018-11-16 | 上海擎创信息技术有限公司 | Data processing method, terminal and computer readable storage medium |
| CN110286656A (en) * | 2019-05-07 | 2019-09-27 | 清华大学 | A kind of the false-alarm filter method and device of wrong data tolerance |
Non-Patent Citations (1)
| Title |
|---|
| 张瑾: "序列异常技术在异常数据挖掘中的应用", 《企业天地》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111338892B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3552067B1 (en) | Methods and systems for discovery of prognostic subsequences in time series | |
| CN108731923B (en) | Fault detection method and device for rotary mechanical equipment | |
| CN110738255A (en) | device state monitoring method based on clustering algorithm | |
| KR102272657B1 (en) | Diagnosis apparatus of partial discharge | |
| CN111262750B (en) | Method and system for evaluating baseline model | |
| CN110727257A (en) | Equipment operation diagnosis method and device based on K-means clustering algorithm | |
| CN110474862B (en) | Network traffic anomaly detection method and device | |
| CN117131110B (en) | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis | |
| CN116308300B (en) | Power equipment state monitoring evaluation and command method and system | |
| KR20190082715A (en) | Data classification method based on correlation, and a computer-readable storege medium having program to perform the same | |
| CN115146726A (en) | KPI abnormity early warning method in intelligent operation and maintenance based on machine learning | |
| CN115619778A (en) | Power equipment defect identification method and system, readable storage medium and equipment | |
| CN117749409A (en) | Large-scale network security event analysis system | |
| CN111338892B (en) | Time sequence rise abnormity identification method under extreme operation condition | |
| CN117093944B (en) | Time sequence data template self-adaptive abnormal mode identification method and system | |
| CN113918433A (en) | Adaptive intelligent network equipment performance index abnormity detection device and method | |
| CN113569656A (en) | Examination room monitoring method based on deep learning | |
| CN116433034B (en) | Virtual power plant operation risk detection method based on machine learning | |
| KR20150027178A (en) | Data classification method based on correlation, and a computer-readable storege medium having program to perform the same | |
| CN115901004A (en) | Health monitoring system and method for zinc pot induction heater of hot galvanizing production line | |
| CN114803763A (en) | Variable speed goods elevator abnormity detection method based on neural network | |
| CN118017698B (en) | Power consumption terminal monitoring system, method, electronic equipment and storage medium | |
| CN118193959B (en) | Surge energy monitoring method and system | |
| CN116610535B (en) | Method and system for processing operation and maintenance monitoring data of machine room | |
| WO2022091248A1 (en) | Degradation detection device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |