CN108613820A - A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning - Google Patents
A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning Download PDFInfo
- Publication number
- CN108613820A CN108613820A CN201810537045.0A CN201810537045A CN108613820A CN 108613820 A CN108613820 A CN 108613820A CN 201810537045 A CN201810537045 A CN 201810537045A CN 108613820 A CN108613820 A CN 108613820A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- gis
- signal
- allophone
- data
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning, algorithm is made of front end allophone inline diagnosis algorithm and main website server platform fault diagnosis algorithm.Sonic data when front end allophone inline diagnosis algorithm receives GIS device operation, quick kernel independent component analysis and double-spectrum analysis technology is respectively adopted filter is carried out to data and makes an uproar and feature extraction, tentatively judge whether the signal is fault-signal by this feature vector, if so, executing lossless compression, preserving data and back delivery operations.Main website server platform fault diagnosis algorithm receives suspected malfunctions signal, its intrinsic mode function Energy-Entropy is calculated after decompression, then by the fault diagnosis algorithm of the trained learning machine that transfinites based on online sequence of Energy-Entropy input, secondary diagnosis is carried out to suspected malfunctions signal.The algorithm of proposition can utilize the GIS holography sound database update algorithm parameters of constantly improve, and the accuracy and practicability of fault diagnosis algorithm can be improved.
Description
Technical field：
The present invention discloses a kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning, the algorithm
Voice data when GIS device operation can be handled, stored and diagnosed, and suspected malfunctions signal is returned, to build
GIS holography audio databases, can be measured in real time the major failure point of different substation and early warning, improve substation's fortune
The safety and reliability of dimension.
Background technology：
GIS is a kind of totally enclosed combination of power equipment, has that rate of breakdown is low, trouble hunting is difficult and fault restoration
The features such as period is long.The method for diagnosing faults of manual inspection can not usually acquire the working signal of GIS device real-time continuously, past
It is past to be difficult to find the hidden failure of early stage, and even if having collected some suspected malfunctions signals, the maintenance to its fault point is also
One very difficult work.In addition, GIS device mechanical fault diagnosis analytical technology is left to be desired both at home and abroad at present, in recent years
The detection and analysis technology based on audible voice to propose also remains in laboratory stage, can not put into engineer application
In.
Signature analysis based on GIS device abnormal sound voice signal carries out fault diagnosis and is at home and abroad showed no Research Literature,
Therefore lack holographic audio database when GIS device operation, can not judge the correctness and standard of existing fault diagnosis algorithm
Exactness.And the fault message that manual inspection is acquired does not have representativeness, can not establish comprehensive and systematic GIS holographies voice data
Library.Therefore, it is the operating status for obtaining GIS device in time, discovering device mechanical breakdown that may be present as early as possible, while ensuring to examine
The non-faulting element of equipment will not be damaged or generate secondary secondary defect during repairing, develop a kind of GIS live detections and
The needs of line monitoring method are increasingly urgent to.
In consideration of it, patent of the present invention provides a kind of online allophone prison being used for GIS bulk mechanicals defect diagonsis and positioning
Method of determining and calculating, the algorithm can realize the foundation of the on-line real time monitoring and database to each major failure hidden danger point of different substation,
Main problem present in current power industry GIS bulk mechanicals defect diagonsis and position fixing process can be solved, ensure that substation
The work safety of internal staff, improves production management efficiency, reduces operation maintenance cost.
Patent of invention content：
Being designed to provide for patent of the present invention is a kind of for GIS bulk mechanicals defect diagonsis and the online allophone of positioning prison
Method of determining and calculating, the algorithm are combined with hardware systems such as sensor, communication modules, receive the GIS device acoustic signals of acquisition first,
Filter is carried out using quick kernel independent component analysis technology to acoustic signals to make an uproar, extracting order Probability Structure by double-spectrum analysis is used as
Feature vector, and calculate the departure degree of this feature vector and feature vector under normal condition；Secondly judged according to departure degree
Whether signal is suspected malfunctions signal, and the defeated of learning machine that transfinited using the intrinsic mode function Energy-Entropy of signal as online sequence
Enter, fault diagnosis algorithm is built with this；The fault diagnosis algorithm for finally utilizing the learning machine that transfinites based on online sequence, to doubtful
Fault-signal carries out secondary diagnosis, and builds GIS holography audio databases, is improved while promoting fault diagnosis model performance
The accuracy rate of fault diagnosis.
Technical solution is used by patent of the present invention solves its technical problem：
A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning is examined online by front end allophone
Disconnected algorithm and main website server platform fault diagnosis algorithm composition.Front end allophone inline diagnosis algorithm provides a kind of for receiving
The interface of sonic data when GIS device works, and pretreatment and tentative diagnosis are carried out to signal, it makes up based on acoustic signals point
The problem of analysing the signal acquisition and on-line monitoring field blank of GIS initial failures.Main website server platform fault diagnosis algorithm is used
Judge whether suspected malfunctions signal is fault-signal in secondary.
Front end allophone inline diagnosis algorithm mainly comprises the following steps：
The first step receives the sonic data when GIS device operation of binary channels allophone acquisition sensor acquisition；
Second step carries out filter to the sonic data of acquisition using quick kernel independent component analysis technology and makes an uproar, the specific steps are：
(1) one group of observation data vector x is inputted1, x2..., xn, and with the optimal radial base gaussian kernel function of classifying quality
As kernel function used herein；
(2) centralization and whitening processing are carried out to observation data, observation data is made to meet zero-mean and unit variance vector
Characteristic；
(3) the Hessian matrixes of object function are estimated using incomplete Choleskydecomposition method；
(4) it utilizes Newton method to obtain the optimal solution of object function, obtains separation matrix；
(5) signal in comparison separation signal and template library.
Third walks, and the GIS acoustic signals after making an uproar to filter carry out double-spectrum analysis, obtains the graphics for characterizing its signal characteristic,
Two-dimensional matrix is built using the graphics, as the feature vector of acoustic signals, the bispectrum at matrix element value, that is, respective coordinates
Amplitude.Then feature recognition is carried out to the bispectrum feature vector of extraction, whether the preliminary sonic data for judging acquisition is failure letter
Number；
4th step is compressed suspected malfunctions signal by a kind of lossless compression algorithm based on LZO algorithms, is protected simultaneously
Its original sound data and various characteristics are deposited to Compact Flash, to be GIS holographies audio database in main website server
Initial data is provided；
5th step, by compressed data by 4G or WIFI be back to main website server platform it is for further analysis and
Diagnosis.
Main website server platform fault diagnosis algorithm mainly comprises the following steps：
The first step, the suspected malfunctions signal data that receiving front-end allophone inline diagnosis algorithm sends over；
Second step, decompression, which contracts, calculates the intrinsic mode function Energy-Entropy of reception signal, calculates step and is：
(1) EMD decomposition is carried out to 50-3000Hz in-band signals, chooses preceding 5 IMF components；
(2) ENERGY E of this 5 IMF components is calculatedi=∫ | ci(t)|2The gross energy of dt, i=1,2 ... 5 and they
(3) intrinsic mode function Energy-Entropy is calculatedWherein pi=Ei/ E indicate each IMF components with it is whole
The energy ratio of a signal.
Third walks, using the Energy-Entropy that second step is calculated as the fault diagnosis for the learning machine that transfinited based on online sequence
The input vector of algorithm, the output of algorithm are secondary diagnosis and analysis to GIS suspected malfunctions signals.Wherein, it is based in line sequence
The fault diagnosis algorithm for the learning machine that transfinites is arranged in training and update, using intrinsic mode function Energy-Entropy as input, with characterization
The bivector of signal fault probability is as output；When detecting, the intrinsic mode function Energy-Entropy input fault of signal is examined
The output of disconnected algorithm, algorithm represents diagnostic result.The specific steps of algorithm can be described as：
(1) assume initial training sample setWherein xiIt is input vector, tiIt is object vector.If one
It is a to haveThe feedforward neural networks with single hidden layer of a hidden node can approach training with the non-zero training error of zero error or very little
Data then must satisfySo, we can be by solving a linear system | | H0β-T0| | minimum value obtain
Network exports the initial value of weight, and the initial value for exporting weight is represented by β(0)=(K0)-1H0 TT0, wherein
Wherein, H0InIndicate hidden node weight andIndicate the biasing of hidden node.
(2) weight of fixed hidden node and biasing carry out the output weight of network using the data sample newly to arrive
Update.Specifically it can be described as：WithThe training sample data block currently to arrive is indicated, then output power
The renewal process of weight β is equivalent to solution linear systemMinimum value, wherein
(3) by deriving, more new model is represented by：
(4) it enablesThen update β(k+1)Formula can write：
As the size N of sample data blockk+1When ≡ 1, above formula becomes
Wherein
From above-mentioned steps as can be seen that when meeting condition of the initial training sample size more than the number of hidden nodes, online
Transfinite learning machine and signal wire learning machine of sequence can reach same performance, can farthest approach training data, structure
Build the non-linear relation model between input and output.Patent of the present invention is using known a small amount of GIS acoustic signals as training
Sample, building online sequence transfinites learning machine network model, and suspected malfunctions signal is further analyzed and is diagnosed.
4th step, gradual perfection GIS holography audio databases, and be based on come constantly training using the database of constantly improve
The failure of online Sequence Learning machine chops algorithm off, makes the accuracy of fault pre-alarming and diagnosis and comprehensive continuous promotion.
It can be seen from the above technical scheme that Patent design of the present invention is a kind of to be used for GIS bulk mechanical defect diagonsis
With the online allophone monitoring algorithm of positioning, which is diagnosed by front end allophone inline diagnosis algorithm and main website server platform fault
Algorithm forms.Front end allophone inline diagnosis algorithm and main website server platform fault diagnosis algorithm complement each other, the former can adopt
Voice data when collection, processing and tentative diagnosis GIS device are run, and abundant GIS holography audio databases are provided for the latter,
Algorithm performance is set constantly to be promoted；The latter can be further analyzed and diagnose to suspected malfunctions signal, flat to build and improve
GIS holography audio databases in platform server, and improve the fault diagnosis based on online Sequence Learning machine using the database
The performance of algorithm is had a good application prospect with realizing the real-time monitoring and early warning of substation's major failure point.
The advantageous effect of patent of the present invention is：
A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning of Patent design of the present invention, one
Aspect can monitor the data of acquisition in real time, be made and tentatively being examined by the sonic data of the main hidden danger point of acquisition substation
Disconnected, the GIS holography audio databases improved in main website server of on the other hand enriching constantly further promote main station failure diagnosis
The improvement of algorithm improves the accuracy and reliability of fault diagnosis, this sets for developing a set of GIS suitable for Practical
Standby method for diagnosing faults has facilitation.
Description of the drawings：
Patent of the present invention is further illustrated with embodiment below in conjunction with the accompanying drawings：
Fig. 1 is the algorithm flow chart of patent of the present invention.
Fig. 2 is the system construction drawing of patent of the present invention.
Fig. 3 is the simulation result diagram of patent of the present invention.
Specific implementation mode：
Below by way of specific example, the present invention is described in detail.
Fig. 1 is the algorithm flow chart of patent of the present invention, and algorithm is put down by front end allophone inline diagnosis algorithm and main website server
Platform fault diagnosis algorithm is constituted.Front end allophone inline diagnosis algorithm provides a kind of sound wave number for receiving when GIS device work
According to interface, and to signal carry out pretreatment and tentative diagnosis, make up based on acoustic signals analyze GIS initial failures signal adopt
The problem of collection and on-line monitoring field blank.Main website server platform fault diagnosis algorithm is used for secondary judgement suspected malfunctions signal
Whether it is fault-signal.
When the GIS device that allophone inline diagnosis algorithm in front end receives the acquisition sensor acquisition of binary channels allophone first is run
Sonic data；Secondly it carries out filter to the sonic data of acquisition using quick kernel independent component analysis technology to make an uproar, using double-spectrum analysis
Signal after making an uproar to filter carries out feature extraction, and carries out feature recognition to signal by the bispectrum feature vector of extraction, tentatively sentences
Whether the sonic data of disconnected acquisition is fault-signal；Suspected malfunctions are believed again by the lossless compression algorithm based on LZO algorithms
It number is compressed, while preserving its original sound data and various characteristics to Compact Flash, so as in main website server
GIS holography audio databases provide initial data；Compressed data are finally back to main website server by 4G or WIFI
Platform is for further analysis and diagnoses.
Main website server platform fault diagnosis algorithm receiving front-end allophone inline diagnosis algorithm first sends over doubtful
Fault-signal data；Secondly it is unziped it, and calculates the intrinsic mode function Energy-Entropy for receiving signal；Again, training
The fault diagnosis algorithm of the learning machine that transfinites based on online sequence is obtained, and the Energy-Entropy being the previously calculated is defeated as its
Incoming vector, secondary diagnosis and analysis of the output i.e. to GIS suspected malfunctions signals.The GIS holography sound of constantly improve is utilized simultaneously
Database is updated the weight of the algorithm.
Fig. 2 is the system construction drawing of patent of the present invention, which is based on disclosed by the invention a kind of for GIS bulk mechanicals
The online allophone monitoring algorithm of defect diagonsis and positioning is taken by front end allophone online acquisition equipment, multi-mode communication module and main website
Business device platform software is constituted.Front end allophone online acquisition equipment is by data acquisition module, signal pre-processing module, lossless compression mould
Block and CF storage cards composition.Multi-mode communication module is made of 4G wireless communication modules and WIFI module, wherein 4G radio communication molds
Block selects the ME3860 modules of Zhong Xing companies, WIFI module to select TaiWan, China Realtek companies RTL8188CUS-U chips.It should
Module is mainly used for the suspected malfunctions signal of front end being sent to main website server.Main website server platform software is based in line sequence
The learning machine Technology design signal analysis and processing software that transfinites is arranged, which passes through the natural mode of vibration letter for calculating signal in special frequency channel
Number Energy-Entropies, obtain the feature vector of suspected malfunctions signal, and the input for the learning machine that transfinites as online sequence.
Fig. 3 is the simulation result diagram of patent of the present invention, and red black circle is to use front end designed by the present invention in figure
The GIS bulk mechanicals defect diagonsis of allophone inline diagnosis algorithm and the online allophone monitoring algorithm of positioning, black triangle are not
Using the algorithm performance in the case of the allophone inline diagnosis algorithm of front end.It can be seen from the figure that with the increase of data volume, use
The accuracy rate of the signal fault diagnosis algorithm of front end allophone inline diagnosis algorithm is constantly promoted, on the contrary, not using front end allophone
Accuracy rate is lower and lower in the case of inline diagnosis algorithm.In conclusion the on-line monitoring algorithm that patent of the present invention proposes can be real
When continuously GIS equipment sonic datas are monitored, diagnosed and analyzed, and enrich and improve GIS holography voice datas constantly
Library compensates for the shortcomings that traditional signal fault diagnosis method based on acoustic characteristic lacks fault data, helps to improve biography
The accuracy and practicability of system fault diagnosis algorithm.
Claims (3)
1. a kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning, which is characterized in that different by front end
Sound inline diagnosis algorithm and main website server platform fault diagnosis algorithm composition.Front end allophone inline diagnosis algorithm provides a kind of use
The interface of sonic data when receiving GIS device work, and pretreatment and tentative diagnosis are carried out to signal, it makes up based on sound wave
Signal analyzes the problem of signal acquisition and on-line monitoring field blank of GIS initial failures.Main website server platform fault diagnoses
Algorithm judges whether suspected malfunctions signal is fault-signal for secondary.The present invention can to the data of acquisition carry out in real time monitoring and
Diagnosis, while the GIS holography audio databases improved in main website server of enriching constantly, improve the accuracy of fault diagnosis algorithm
And reliability, this has facilitation for developing a set of GIS device method for diagnosing faults suitable for Practical.
2. the online allophone monitoring algorithm according to claim 1 for GIS bulk mechanicals defect diagonsis and positioning, special
Sign is that allophone inline diagnosis algorithm in front end is received first when the GIS device that binary channels allophone acquisition sensor acquires is run
Sonic data；Secondly it carries out filter to the sonic data of acquisition using quick kernel independent component analysis technology to make an uproar, using double-spectrum analysis
Signal after making an uproar to filter carries out feature extraction, and carries out feature recognition to signal by the bispectrum feature vector of extraction, tentatively sentences
Whether the sonic data of disconnected acquisition is fault-signal；Again by the lossless compression algorithm based on LZO to suspected malfunctions signal into
Row compression, while preserving its original sound data and various characteristics to Compact Flash, so as to for GIS in main website server it is complete
It ceases audio database and initial data is provided；Compressed data are finally back to main website server platform by 4G or WIFI to make
Further analysis and diagnosis.
3. the online allophone monitoring algorithm according to claim 1 for GIS bulk mechanicals defect diagonsis and positioning, special
Sign is that main website server platform fault diagnosis algorithm receiving front-end allophone inline diagnosis algorithm first sends over doubtful former
Hinder signal data；Secondly it is unziped it, and calculates the intrinsic mode function Energy-Entropy for receiving signal；Again, trained
Transfinited to one based on online sequence the fault diagnosis algorithm of learning machine, and is inputted the Energy-Entropy being the previously calculated as it
Vector, secondary diagnosis and analysis of the output i.e. to GIS suspected malfunctions signals.The GIS holography sound numbers of constantly improve are utilized simultaneously
The weight of the algorithm is updated according to library, further promotes the accuracy and reliability of fault diagnosis algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810537045.0A CN108613820A (en) | 2018-05-22 | 2018-05-22 | A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810537045.0A CN108613820A (en) | 2018-05-22 | 2018-05-22 | A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108613820A true CN108613820A (en) | 2018-10-02 |
Family
ID=63664329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810537045.0A Pending CN108613820A (en) | 2018-05-22 | 2018-05-22 | A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108613820A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109883747A (en) * | 2019-03-25 | 2019-06-14 | 国网宁夏电力有限公司电力科学研究院 | GIS method for diagnosing faults based on sound intensity cloud atlas |
| CN110849645A (en) * | 2019-09-23 | 2020-02-28 | 红相股份有限公司 | Initial diagnosis method for GIS mechanical fault |
| CN111397726A (en) * | 2020-03-23 | 2020-07-10 | 深圳供电局有限公司 | Fault detection system based on acoustic imaging |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1811474A (en) * | 2004-07-25 | 2006-08-02 | 天水长城电力仪器设备厂 | Transformer dynamic stability state parameter tester and diagnostic software |
| CN102368634A (en) * | 2011-09-14 | 2012-03-07 | 文存润 | Unified information platform system for state monitoring of intelligent transformer substation |
-
2018
- 2018-05-22 CN CN201810537045.0A patent/CN108613820A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1811474A (en) * | 2004-07-25 | 2006-08-02 | 天水长城电力仪器设备厂 | Transformer dynamic stability state parameter tester and diagnostic software |
| CN102368634A (en) * | 2011-09-14 | 2012-03-07 | 文存润 | Unified information platform system for state monitoring of intelligent transformer substation |
Non-Patent Citations (1)
| Title |
|---|
| 李建鹏等: "基于双谱和希尔伯特-黄变换的断路器故障诊断方法", 《电力自动化设备》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109883747A (en) * | 2019-03-25 | 2019-06-14 | 国网宁夏电力有限公司电力科学研究院 | GIS method for diagnosing faults based on sound intensity cloud atlas |
| CN110849645A (en) * | 2019-09-23 | 2020-02-28 | 红相股份有限公司 | Initial diagnosis method for GIS mechanical fault |
| CN110849645B (en) * | 2019-09-23 | 2021-04-23 | 红相股份有限公司 | Initial diagnosis method for GIS mechanical fault |
| CN111397726A (en) * | 2020-03-23 | 2020-07-10 | 深圳供电局有限公司 | Fault detection system based on acoustic imaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110766277B (en) | Health assessment and diagnosis system and mobile terminal for nuclear industry field | |
| CN110514957A (en) | Substation's automatic detecting method and platform | |
| CN112990656B (en) | Health evaluation system and health evaluation method for IT equipment monitoring data | |
| CN112949715A (en) | SVM (support vector machine) -based rail transit fault diagnosis method | |
| CN111507376A (en) | Single index abnormality detection method based on fusion of multiple unsupervised methods | |
| CN108613820A (en) | A kind of online allophone monitoring algorithm for GIS bulk mechanicals defect diagonsis and positioning | |
| CN113847950A (en) | Intelligent ship equipment state monitoring system based on cloud computing and information interaction method | |
| CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN111666978B (en) | Intelligent fault early warning system for IT system operation and maintenance big data | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN110020637A (en) | A kind of analog circuit intermittent fault diagnostic method based on more granularities cascade forest | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN114066163A (en) | Power equipment state analysis method and device based on three-layer architecture mode | |
| CN115600695A (en) | Fault diagnosis method of metering equipment | |
| CN112286987B (en) | Electric power internet of things abnormal alarm compression method based on Apriori algorithm | |
| CN112860527A (en) | Fault monitoring method and device of application server | |
| CN114442543A (en) | Computer monitoring method suitable for early warning of hydropower station fault | |
| CN111200315B (en) | Transformer substation monitoring background fault diagnosis system and method | |
| CN112132819A (en) | Communication network management monitoring method based on artificial intelligence | |
| CN109257206A (en) | A kind of method of data inputting and evaluation diagnostic message feedback | |
| Zhang et al. | Fault diagnosis of on-board equipment in ctcs-3 based on cnn-lstm model | |
| CN114183299B (en) | Operation method of SCADA system of double-loop type wind power station | |
| CN117591893A (en) | Fault wave recording waveform identification system and method based on rapid template matching | |
| CN114611891A (en) | Method for processing production data of bent cap in full life cycle |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181002 |