CN111028487A - Water treatment monitoring method and system - Google Patents
Water treatment monitoring method and system Download PDFInfo
- Publication number
- CN111028487A CN111028487A CN201911377342.4A CN201911377342A CN111028487A CN 111028487 A CN111028487 A CN 111028487A CN 201911377342 A CN201911377342 A CN 201911377342A CN 111028487 A CN111028487 A CN 111028487A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- time
- time window
- alarm
- water treatment
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
- G08B29/188—Data fusion; cooperative systems, e.g. voting among different detectors
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a water treatment monitoring method and a system, which comprises the following steps: setting monitoring points at different nodes of a water treatment process, setting a time window at each monitoring point, and setting the length of the time window, an alarm threshold and monitoring frequency; calculating the relative position of each time window; monitoring data of each monitoring point respectively; moving the position of each monitoring point time window; calculating the alarm state of each monitoring point time window; summarizing the alarm state of each monitoring point time window, analyzing the summarized data, and judging whether alarm logic is met; if yes, generating an alarm; if not, the alarm is suppressed, and the step S130 is skipped, and the method continues to be executed according to the steps S130 to S160. The invention solves the problems of accurately generating the alarm conforming to the process flow of the water treatment scene and effectively inhibiting the false alarm caused by abnormal data.
Description
Technical Field
The invention relates to the field of environmental monitoring, in particular to a water treatment monitoring method and system.
Background
In a rural domestic sewage detection system, a set of sewage treatment facilities is provided with a plurality of measuring points, and each measuring point is respectively dispersed on each process flow node of the treatment facilities and reflects the state of each process flow node or equipment operation data. In order to realize the unattended automatic operation and maintenance target, the measured point data needs to be analyzed in the monitoring system, abnormal working condition data is found in time, and warning information is generated to inform corresponding operation and maintenance personnel. The existing solution is to set a threshold range for one or more measuring points, compare the collected real-time monitoring data of the monitoring points with the respective threshold ranges, and further determine whether to analyze whether to generate an alarm. However, such a method has obvious disadvantages in the practical application process: that is, the monitoring data at a certain measuring point fluctuates with time. In some cases it is likely to fluctuate just around the alarm threshold, resulting in frequent alarm generation. In some cases, instantaneous large fluctuation may occur, resulting in false alarm.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an alarm analysis method and an abnormal alarm suppression method based on hysteresis data, and solves the problems of accurately generating an alarm conforming to the process flow of the water treatment scene and effectively suppressing the false alarm caused by abnormal data.
In order to solve the technical problem, the invention is solved by the following technical scheme:
a water treatment monitoring method comprising the steps of:
step S110, setting monitoring points at different nodes of the water treatment process, setting a time window at each monitoring point, and setting the length of the time window, an alarm threshold and monitoring frequency;
step S120, calculating the relative position of each time window;
step S130, monitoring data of each monitoring point respectively;
step S140, moving the time window position of each monitoring point;
step S150, calculating the alarm state of each monitoring point time window;
step S160, summarizing the alarm state of each monitoring point time window, analyzing the summarized data, and judging whether the alarm logic is met;
if yes, generating an alarm;
if not, the alarm is suppressed, and the step S130 is skipped, and the method continues to be executed according to the steps S130 to S160.
Optionally, in step S150, each monitoring data in the time window is compared with a set alarm threshold, if all the monitoring data exceed the set range of the alarm threshold, the alarm state of the time window is set to True, otherwise, the alarm state of the time window is set to False.
Optionally, the alarm state of the time window at different monitoring points is Xn, where Xn is True or False, and when more than one alarm state is True, an alarm is generated.
Optionally, the time window positions of the monitoring points are synchronously moved according to the update frequency of the monitoring data.
Optionally, the length of the time window is greater than one listening period.
Optionally, a hysteresis duration between the time windows of each monitoring point is calculated, where the hysteresis duration is a time length between the ends of two time windows, and then the method for calculating the relative position of each time window is as follows:
step S210, selecting a monitoring point M2 positioned at the downstream of the water treatment process;
step S220, calculating the starting and stopping time of a time window Win2 corresponding to the monitoring point M2;
and step S230, calculating the start-stop time of a time window Win1 corresponding to the measuring point M1 by combining the time lag length.
Optionally, two time nodes for the start-stop time of Win1 and two time nodes for the start-stop time of Win2 are calculated; and moving the four time nodes according to the update frequency of the monitoring data, and calculating the warning state of a new time window once every time the four time nodes are moved.
Optionally, the length of the time window is set to be 2-5 times of the monitoring period of the monitoring point.
The utility model provides a water treatment monitoring system, includes biochemical pond, elevator pump, circulation pipeline, collector, monitoring center, biochemical pond is connected to the elevator pump, and circulation pipeline connects gradually elevator pump and collector, the collector is gathered and is got into the rivers data in the circulation pipeline through the elevator pump to regularly give the detection center with rivers data transmission through wireless transmission module.
The invention has the beneficial effects that:
the method comprises the steps of respectively setting the time window length and the alarm threshold value of each monitoring point, setting the delay time between every two monitoring point time windows, calculating the starting and stopping time point of each monitoring point time window, calculating all monitoring data in each time window, and identifying the time window as the alarm state True if the time window exceeds the set range of the alarm threshold value. And finally, summarizing the alarm states of all the monitoring point time windows, and judging whether to generate an alarm or not through composite alarm logic analysis.
Monitoring data in a period of time is incorporated into an alarm analysis method; under the same sampling rate, the longer the time window is, the more the data amount in the time window is, and the more accurate the result is; but the longer the time window, the longer the delay in generating the alarm. In order to balance the contradiction between accuracy and alarm delay time, the length of the time window is generally set to be 2-5 times of the sampling period of the measuring point.
And the frequent alarm and the False alarm are effectively inhibited by combining the alarm state (True or False) judgment method of each time window. Meanwhile, the monitoring data relations among the originally independent monitoring points are connected in series through the delay time of each monitoring point by a process flow, and the accuracy of the composite alarm is improved by performing a correlation analysis method on multi-point data based on time delay.
The lag time is the length of time between the ends of the two time windows because the water flow between the process flows creates a delay in each process flow. Therefore, the time window win2 of the downstream point M2 of the process is calculated first, and then the time window win1 of the last monitoring point is calculated through the lag time, so that the monitoring data are more accurate.
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, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a water treatment monitoring method;
FIG. 2 is a diagram of the relative positions of time windows on a time axis;
fig. 3 is a flow chart of relative position calculation for each time window.
Detailed Description
The present invention will be described in further detail with reference to examples, which are illustrative of the present invention and are not to be construed as being limited thereto.
The utility model provides a water treatment monitoring system, includes biochemical pond, elevator pump, circulation pipeline, collector, monitoring center, biochemical pond is connected to the elevator pump, and circulation pipeline connects gradually elevator pump and collector, the collector is gathered and is got into the rivers data in the circulation pipeline through the elevator pump to regularly give the detection center with rivers data transmission through wireless transmission module. There is a water treatment monitoring method according to the water treatment monitoring system, as shown in fig. 1, comprising the steps of:
step S110, setting monitoring points at different nodes of the water treatment process, and setting the time window length, alarm threshold, monitoring frequency and delay duration of each monitoring point;
step S120, calculating the relative position of each time window;
step S130, monitoring data of each monitoring point according to the monitoring frequency;
step S140, synchronously moving the position of the time window;
step S150, calculating the alarm state of each monitoring point time window;
from step S130 to step S150, a plurality of branches are parallel in the water treatment process, the number of the branches is consistent with the number of the monitoring points, and after the same steps are executed by each branch, the monitoring data is summarized to step S160, as shown in the figure, two monitoring branches are parallel;
step S160, judging whether composite alarm logic is satisfied;
if yes, generating a composite alarm;
if not, the alarm is suppressed, and the step S130 is skipped, and the steps S130 to S160 are performed in sequence.
Step S150, a method for calculating the alarm state of each monitoring point time window: and comparing each monitoring data in the time window with a set alarm threshold, if all the monitoring data exceed the set range of the alarm threshold, setting the alarm state of the time window to True, otherwise, setting the alarm state of the time window to False.
In step S140, the time window positions of the monitoring points are synchronously moved according to the relative positions according to the update frequency of the monitoring data.
The alarm state of different monitoring point time windows is Xn, wherein Xn is True or False, and when more than one alarm state is True, an alarm is generated.
The length of the time window must be longer than the sampling period of the corresponding monitoring point, so that the data point in each time window can be ensured to be not less than 2. And the lag time between the two time windows needs to be reasonably set according to the process flow on site.
Because the monitoring points are connected in the process flow, the monitoring data of the measuring points on different nodes have a hysteresis relation, and a time difference exists in the change rule of the monitoring points. Calculating a lag time Offset between the time windows of the monitoring points, wherein the lag time is the time length between the ends of the two time windows, and calculating the relative position of each time window, as shown in fig. 2 and 3: in fig. 2, the x-axis is a time axis, and the y-axis is a monitoring data axis.
Step S210, selecting a monitoring point M2 positioned at the downstream of the water treatment process;
step S220, calculating the starting and stopping time of a time window Win2 corresponding to the monitoring point M2;
step S230, calculating the starting and stopping time of a time window Win1 corresponding to the measuring point M1 by combining the time lag duration Offset;
then, based on the start-stop time of Win1 and the start-stop time of Win2, the relative positions of the two time windows are calculated.
And moving the four time nodes according to the updating frequency of the monitoring data according to a relative position invariant principle after obtaining two time nodes of the start-stop time of Win1 and two time nodes of the start-stop time of Win2, and calculating the warning state of a new time window once every time the four time nodes are moved.
The composite alarm logic of the two monitoring points M1 and M2 is as follows:
the alarm state of the existing monitoring point M1 time window Win1 is AlertStatus (Win 1);
the alarm state of the existing monitoring point M2 time window Win2 is AlertStatus (Win 2);
generating an alarm if AlertStatus (Win1) AND (AlertStatus (Win2) ═ True);
alert status (Win1) AND (Win2) False, no alarm is generated.
If there are 3 watch points, this logic expression can be set as:
the alarm state of the existing monitoring point M3 time window Win3 is AlertStatus (Win 3);
generating an alarm if AlertStatus (Win1) AND (AlertStatus (Win2) OR AlertStatus (Win3)) ═ True;
alert (Win1) AND (alert (Win2) OR alert (Win3)) -False, no alarm is generated.
Or
Generating an alarm if AlertStatus (Win1) AND (AlertStatus (Win2) AND AlertStatus (Win3)) ═ True;
AND if the alarm is False, the alarm is not generated, wherein the alarm is generated by alert status (Win1) AND (alert status (Win2) AND alert status (Win 3)).
Setting a logic expression according to an actual process, and following an alarm principle when more than 2 monitoring points (including) are adopted.
In addition, it should be noted that the specific embodiments described in the present specification may differ in the shape of the components, the names of the components, and the like. All equivalent or simple changes of the structure, the characteristics and the principle of the invention which are described in the patent conception of the invention are included in the protection scope of the patent of the invention. Various modifications, additions and substitutions for the specific embodiments described may be made by those skilled in the art without departing from the scope of the invention as defined in the accompanying claims.
Claims (9)
1. A water treatment monitoring method, comprising the steps of:
step S110, setting monitoring points at different nodes of the water treatment process, setting a time window at each monitoring point, and setting the length of the time window, an alarm threshold and monitoring frequency;
step S120, calculating the relative position of each time window;
step S130, monitoring data of each monitoring point respectively;
step S140, moving the time window position of each monitoring point;
step S150, calculating the alarm state of each monitoring point time window;
step S160, summarizing the alarm state of each monitoring point time window, analyzing the summarized data, and judging whether the alarm logic is met;
if yes, generating an alarm;
if not, the alarm is suppressed, and the step S130 is skipped, and the method continues to be executed according to the steps S130 to S160.
2. The water treatment monitoring method according to claim 1, wherein in step S150, each monitoring data in the time window is compared with a set alarm threshold, and if all monitoring data are out of the range set by the alarm threshold, the alarm state of the time window is set to True, otherwise, the alarm state of the time window is set to False.
3. The water treatment monitoring method according to claim 1 or 2, wherein the alarm states of the time windows of different monitoring points are Xn, wherein Xn is True or False, and when more than one alarm state is True, an alarm is generated.
4. The water treatment monitoring method according to claim 1, wherein the time window positions of the respective monitoring points are synchronously shifted according to the update frequency of the monitoring data.
5. The water treatment monitoring method of claim 1, wherein the time window length is greater than one listening period.
6. The water treatment monitoring method according to claim 1, wherein a lag time between time windows of each monitoring point is calculated, the lag time being a length of time between ends of two time windows, and the relative position calculation method for each time window is:
step S210, selecting a monitoring point M2 positioned at the downstream of the water treatment process;
step S220, calculating the starting and stopping time of a time window Win2 corresponding to the monitoring point M2;
and step S230, calculating the start-stop time of a time window Win1 corresponding to the measuring point M1 by combining the time lag length.
7. The water treatment monitoring method according to claim 6, wherein two time nodes for the start and stop time of Win1 and two time nodes for the start and stop time of Win2 are calculated; and moving the four time nodes according to the update frequency of the monitoring data, and calculating the warning state of a new time window once every time the four time nodes are moved.
8. The water treatment monitoring method according to claim 5, wherein the time window length is set to be 2-5 times of the monitoring period of the monitoring point.
9. The utility model provides a water treatment monitoring system, its characterized in that, includes biochemical pond, elevator pump, circulation pipeline, collector, monitoring center, biochemical pond is connected to the elevator pump, and circulation pipeline connects gradually elevator pump and collector, the collector is gathered and is passed through the rivers data that the elevator pump got into in the circulation pipeline to regularly give the detection center with rivers data transmission through wireless transmission module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911377342.4A CN111028487B (en) | 2019-12-27 | 2019-12-27 | Water treatment monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911377342.4A CN111028487B (en) | 2019-12-27 | 2019-12-27 | Water treatment monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111028487A true CN111028487A (en) | 2020-04-17 |
| CN111028487B CN111028487B (en) | 2021-07-13 |
Family
ID=70196182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911377342.4A Active CN111028487B (en) | 2019-12-27 | 2019-12-27 | Water treatment monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111028487B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114237197A (en) * | 2021-11-22 | 2022-03-25 | 上海电气电站设备有限公司 | Phase modulator multi-factor coupling online diagnosis method |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1076024A (en) * | 1991-12-23 | 1993-09-08 | 蒂特达斯屈托拉仪器股份公司 | Be used for the measurement gas flow velocity and/or by the method and the device of its parameter of deriving |
| JPH1055425A (en) * | 1996-08-08 | 1998-02-24 | Tokyo Electric Power Co Inc:The | Device for monitoring waterway flowing in/out object |
| JP2000276672A (en) * | 1999-03-26 | 2000-10-06 | Osaka Gas Co Ltd | Alarm adapter |
| US7076403B2 (en) * | 2003-07-15 | 2006-07-11 | Honeywell International, Inc. | Apparatus and method for dynamic smoothing |
| CN101016975A (en) * | 2007-02-09 | 2007-08-15 | 郑州大学 | On-line testing method for gas oil pipe leakage based on orienting suction wave identification technology |
| WO2011112673A2 (en) * | 2010-03-09 | 2011-09-15 | Cidra Corporate Services Inc. | Single wrapped sensor flow meter |
| WO2012129101A1 (en) * | 2011-03-18 | 2012-09-27 | Soneter, LLC | Methods and apparatus for fluid flow measurement |
| CN103939749A (en) * | 2014-04-28 | 2014-07-23 | 东北大学 | Oil pipeline network leakage intelligent self-adaptation monitoring system and method based on big data |
| US9324228B2 (en) * | 2014-05-31 | 2016-04-26 | Steelhead Innovations, Llc | Pipe system, and pipe flow monitoring and alerting systems and methods |
| CN106814068A (en) * | 2017-01-24 | 2017-06-09 | 英普（北京）环境科技有限公司 | The rapid assay device and method of monitoring sewage treatment plant running status |
| KR20170143340A (en) * | 2016-06-21 | 2017-12-29 | 현대제철 주식회사 | Diagnostic apparatus and method for ultrasonic flowmeter for blast furnace gas pipe |
| CN108922139A (en) * | 2018-07-23 | 2018-11-30 | 山东科技大学 | A kind of online test method that industry alarm is spread unchecked |
| CN208433092U (en) * | 2018-07-30 | 2019-01-25 | 山东中烟工业有限责任公司 | A kind of online gas detection and alarm control system |
| CN109816940A (en) * | 2019-03-21 | 2019-05-28 | 北京天诚同创电气有限公司 | The fault alarm method and device of sewage treatment plant |
| CN110297018A (en) * | 2019-06-11 | 2019-10-01 | 同济大学 | A kind of method and device that drainage pipeline networks pollutant emission is traced to the source |
-
2019
- 2019-12-27 CN CN201911377342.4A patent/CN111028487B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1076024A (en) * | 1991-12-23 | 1993-09-08 | 蒂特达斯屈托拉仪器股份公司 | Be used for the measurement gas flow velocity and/or by the method and the device of its parameter of deriving |
| JPH1055425A (en) * | 1996-08-08 | 1998-02-24 | Tokyo Electric Power Co Inc:The | Device for monitoring waterway flowing in/out object |
| JP2000276672A (en) * | 1999-03-26 | 2000-10-06 | Osaka Gas Co Ltd | Alarm adapter |
| US7076403B2 (en) * | 2003-07-15 | 2006-07-11 | Honeywell International, Inc. | Apparatus and method for dynamic smoothing |
| CN101016975A (en) * | 2007-02-09 | 2007-08-15 | 郑州大学 | On-line testing method for gas oil pipe leakage based on orienting suction wave identification technology |
| WO2011112673A2 (en) * | 2010-03-09 | 2011-09-15 | Cidra Corporate Services Inc. | Single wrapped sensor flow meter |
| WO2012129101A1 (en) * | 2011-03-18 | 2012-09-27 | Soneter, LLC | Methods and apparatus for fluid flow measurement |
| CN103939749A (en) * | 2014-04-28 | 2014-07-23 | 东北大学 | Oil pipeline network leakage intelligent self-adaptation monitoring system and method based on big data |
| US9324228B2 (en) * | 2014-05-31 | 2016-04-26 | Steelhead Innovations, Llc | Pipe system, and pipe flow monitoring and alerting systems and methods |
| KR20170143340A (en) * | 2016-06-21 | 2017-12-29 | 현대제철 주식회사 | Diagnostic apparatus and method for ultrasonic flowmeter for blast furnace gas pipe |
| CN106814068A (en) * | 2017-01-24 | 2017-06-09 | 英普（北京）环境科技有限公司 | The rapid assay device and method of monitoring sewage treatment plant running status |
| CN108922139A (en) * | 2018-07-23 | 2018-11-30 | 山东科技大学 | A kind of online test method that industry alarm is spread unchecked |
| CN208433092U (en) * | 2018-07-30 | 2019-01-25 | 山东中烟工业有限责任公司 | A kind of online gas detection and alarm control system |
| CN109816940A (en) * | 2019-03-21 | 2019-05-28 | 北京天诚同创电气有限公司 | The fault alarm method and device of sewage treatment plant |
| CN110297018A (en) * | 2019-06-11 | 2019-10-01 | 同济大学 | A kind of method and device that drainage pipeline networks pollutant emission is traced to the source |
Non-Patent Citations (1)
| Title |
|---|
| 李德友: "水泵水轮机驼峰区流动机理及瞬态特性研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114237197A (en) * | 2021-11-22 | 2022-03-25 | 上海电气电站设备有限公司 | Phase modulator multi-factor coupling online diagnosis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111028487B (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898691B (en) | River burst water pollution early warning and tracing method, system, terminal and medium | |
| CN104020724A (en) | Alarm monitoring method and device | |
| CN112149860A (en) | Automatic anomaly detection method and system | |
| CN109470946B (en) | Power generation equipment fault detection method and system | |
| CN103838202A (en) | Parameter control method and parameter control system | |
| CN105488592A (en) | Method for predicting generated energy of photovoltaic power station | |
| US11120350B2 (en) | Multilevel pattern monitoring method for industry processes | |
| US20190164067A1 (en) | Method and device for monitoring a process of generating metric data for predicting anomalies | |
| CN102789676A (en) | Method for designing industrial alarm on basis of alarm evidence fusion | |
| RU2013130664A (en) | METHOD FOR PERFORMING DIAGNOSTIC OF STRUCTURE SUBJECT TO LOADS AND SYSTEM FOR IMPLEMENTATION OF THE MENTIONED METHOD | |
| CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
| CN111028487B (en) | Water treatment monitoring method and system | |
| CN111176226A (en) | Automatic analysis method for alarm threshold of equipment characteristic parameter based on operation condition | |
| CN109613372B (en) | Power grid fault diagnosis method based on multi-element power grid database | |
| CN109087490B (en) | A kind of interference alarm recognition methods based on alarm duration features | |
| JP2011044592A (en) | Reliability determining device, reliability determining method, and computer program for reliability determination | |
| CN117743120A (en) | Network card abnormality detection method based on big data technology | |
| KR101982235B1 (en) | Method and device for similar equipment clustering using feature extraction method based on survival function | |
| CN111125195A (en) | Data anomaly detection method and device | |
| CN115713312A (en) | Combined identification method and device for unfavorable working conditions of hydraulic and hydroelectric engineering environmental quantity | |
| CN101923605B (en) | Wind pre-warning method for railway disaster prevention | |
| CN114970311A (en) | Method for establishing remote module life prediction model and life prediction method | |
| CN106053978B (en) | A kind of satellite aperiodicity telemetering analog quantity interpretation method based on window | |
| CN103425125B (en) | Based on the electrical malfunction diagnostic method of continuous state | |
| CN111400284B (en) | Method for establishing dynamic anomaly detection model based on performance data |
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 |