CN112149823A - Combined implementation method for filtering alarm information - Google Patents
Combined implementation method for filtering alarm information Download PDFInfo
- Publication number
- CN112149823A CN112149823A CN202010843632.XA CN202010843632A CN112149823A CN 112149823 A CN112149823 A CN 112149823A CN 202010843632 A CN202010843632 A CN 202010843632A CN 112149823 A CN112149823 A CN 112149823A
- Authority
- CN
- China
- Prior art keywords
- alarm
- data
- filtering
- mutant
- information
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000000737 periodic effect Effects 0.000 claims abstract description 31
- 238000012216 screening Methods 0.000 claims abstract description 17
- 230000008859 change Effects 0.000 claims abstract description 6
- 230000003252 repetitive effect Effects 0.000 claims abstract description 4
- 238000012544 monitoring process Methods 0.000 claims description 52
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000630 rising effect Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 239000007789 gas Substances 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a combined implementation method for screening and filtering alarm information, which comprises the following steps: acquiring alarm data in real time and analyzing the alarm data; when the alarm data rapidly rises and exceeds a preset threshold and falls back to a normal value in a very short time, judging to be a mutant alarm, and filtering mutant alarm data by adopting a mutant alarm information filtering method; when the alarm data has periodic change at a relatively fixed time interval or a certain fixed time period, the periodic alarm is judged to be periodic alarm, and a periodic alarm information filtering method is adopted to filter the periodic alarm data; if the alarm is a periodic alarm caused by the same event, only information reminding and pushing are carried out on the first alarm; if the alarm data continues to rise and exceeds the set time length, upgrading and alarming are carried out, otherwise, only the alarm information is recorded, and push reminding is not carried out; and if the events are repetitive mutant alarms caused by the same event, filtering mutant alarm data by a mutant alarm information filtering method.
Description
Technical Field
The invention belongs to the field of safety monitoring and early warning, and particularly relates to a combined implementation method for screening and filtering alarm information.
Background
With the continuous improvement of the automation degree, the online safety monitoring and early warning system becomes one of the important means of safety management of industrial and mining enterprises. The safety operation state of an enterprise site is sensed in real time through online monitoring of safety parameters such as temperature, pressure, flow, liquid level, combustible gas concentration and toxic gas concentration in the technological process. When the real-time monitoring data of the safety parameters exceed the preset alarm threshold value of the system, the system can automatically form alarm information, and timely remind safety management personnel to take necessary emergency management and control measures by means of on-site audible and visual alarm, remote information notification and the like, so that further deterioration of the safety state is avoided, and accidents are effectively prevented.
In the working process of the existing safety monitoring and early warning system, when the safety parameter value monitored on line by a front-end detector or a monitoring system exceeds a preset alarm threshold value, alarm information and record can be automatically generated, and all the alarm information is reminded indiscriminately.
However, in the actual safety management work in the field, frequent alarm or false alarm without practical significance can be caused due to field environment factors, operation process factors, external environment interference factors or equipment self fault factors (for example, unstable wind flow blows gas at a normal discharge port to a nearby detector, or gas generated by normal process sampling operation is dissipated, electromagnetic interference caused by starting and stopping of nearby large-scale equipment, data drift caused by equipment component aging and the like). If the alarm information is pushed without screening and filtering, a large amount of unnecessary alarm reminding can be brought to managers to form information bombing, so that the effect of effective early warning cannot be achieved, the field safety production work can be seriously influenced, and troubles are brought to field managers.
In order to solve the above existing problems, people have been searching for a suitable solution.
Disclosure of Invention
In order to solve the above problem, it is necessary to provide a combined implementation method of alarm information filtering.
The first aspect of the present invention provides a combined implementation method for screening and filtering alarm information, which includes:
acquiring alarm data in real time and analyzing the alarm data;
when the alarm data rapidly rises and exceeds a preset threshold and falls back to a normal value in a very short time, judging to be a mutant alarm, and filtering mutant alarm data by adopting a mutant alarm information filtering method;
when the alarm data has periodic change at a relatively fixed time interval or a certain fixed time period, the periodic alarm is judged to be periodic alarm, and a periodic alarm information filtering method is adopted to filter the periodic alarm data;
if the alarm is a periodic alarm caused by the same event, only information reminding and pushing are carried out on the first alarm; if the alarm data continues to rise and exceeds the set time length, upgrading and alarming are carried out, otherwise, only the alarm information is recorded, and push reminding is not carried out; and if the events are repetitive mutant alarms caused by the same event, filtering mutant alarm data by a mutant alarm information filtering method.
Based on the above, the mutant alarm data filtering method is rising rate super-threshold filtering:
presetting a rising rate threshold
Where range L is the range of the sensor providing this alarm information, T90Under experimental conditions, the sensor has response time reaching 90% of the maximum measuring range value;
when the monitoring data exceeds the limit, calculating the rising rate of the monitoring data
Wherein, XmIn order to monitor the overrun data,Xm-1for the data monitored immediately preceding the overrun data, TmTime of overrun data monitored, Tm-1Monitoring the time of the data for a bit preceding the overrun data;
comparison VmAnd YThreshold(s)Magnitude of the value, if Vm＞YThreshold(s)If the alarm data is judged to be invalid alarm, the alarm information is not pushed; if Vm≤YThreshold(s)And if the alarm data is effective, pushing alarm information according to the existing alarm flow.
Based on the above, the mutant alarm data filtering method is to perform filtering by judging whether to rapidly rise and rapidly recover:
defining the upper and lower alarm limit values of a certain monitoring parameter as a and b respectively, and when the monitoring value is XmB or X is not more thanmWhen the value is more than or equal to a, the alarm pushing processing is not carried out temporarily;
if Xm+1And XmSimultaneously has Xm+1B or X is not more thanm+1When a is more than or equal to a, judging XmFor effective alarming, the alarming information is pushed according to the existing flow; otherwise, determine XmAnd if the alarm is invalid, pushing the alarm information.
Based on the above, the mutant alarm data filtering method adopts a three-layer BP neural network model for filtering:
acquiring monitoring historical data under the same type scene, wherein the monitoring historical data comprises normal monitoring data, mutant alarm data needing filtering and normal over-limit alarm data to form a learning sample set;
and (3) performing model training on the provided learning sample set by adopting a Levenberg-Marquardt algorithm as a nonlinear fitting training function:
define input vector X ═ X1，x2，x3，…，xn，)TThe hidden layer output quantity is Y ═ Y1，y2，y3，…，ym，)TOutput vector O ═ O1，o2，o3，…，o1，)TDesired output D ═ D (D)1，d2，d3，…，dl，)TThe weight value from the input layer to the hidden layer is represented by V, and the weight value from the hidden layer to the output layer is represented by W;
when the output quantity O is not equal to the desired quantity D, there is a deviation E,
the error is spread out to a hidden layer,
further spread out to the input layer and then,
then, the weight value V from the input layer to the hidden layer and the weight value W from the hidden layer to the output layer are adjusted to continuously reduce the deviation E,
the error signals of the output layer and the hidden layer are defined,
obtaining a calculation formula of weight value adjustment of a learning algorithm of the neural network:
when the change rule of the real-time monitoring data accords with the filtering model, the alarm can be marked as invalid alarm, and the alarm information is not pushed.
Based on the above, the periodic alarm information filtering method is to perform manual labeling on the monitored point location, define the overrun alarm in the operation time period as the normal operation alarm, record only the alarm data, and not perform information reminding and pushing.
A second aspect of the present invention provides a monitoring system, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the combined implementation method of the alarm information filtering when executing the computer program.
A third aspect of the present invention provides a computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, perform the steps of the combined implementation method of alarm information screening filtering.
Compared with the prior art, the invention has prominent substantive characteristics and remarkable progress, particularly: according to the invention, through summarizing and summarizing the common characteristics of alarm data, a set of combination method capable of effectively filtering abnormal alarm information of the safety monitoring and early warning system is developed, so that frequent alarms and false alarms which are not of practical significance and are caused by field environment factors, operation process factors, external environment interference factors or equipment self fault factors and the like can be screened and filtered according to field requirements, the accuracy and reliability of the alarm information are greatly improved, and the reliability of a supervisor on the system is enhanced. Meanwhile, the interference of unnecessary alarm information can be effectively avoided, the supervision personnel can pay attention to important alarm, and the major risks can be effectively prevented and solved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a graph showing a monitoring curve of a mutation type alarm message in the method of the present invention.
FIG. 2 is a graph showing the monitoring of periodic alarm information in the method of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Example 1
The embodiment provides a combined implementation method for alarm information screening and filtering, which comprises the following steps:
and acquiring and analyzing alarm data in real time. Through the research and summary of a large amount of monitoring data, false alarm information or unnecessary alarm information can be classified into the following three categories: mutant alarm information; second, periodic alarm information is given; and thirdly, repeating the alarm information for a plurality of times in the same event.
Mutant alarm message filtering
As shown in fig. 1, when the alarm data rapidly rises and exceeds a predetermined threshold and falls back to a normal value within a very short time, a monitoring curve shows a shape of a spike, and is judged to be a mutant alarm, and a mutant alarm data filtering method is adopted to filter the mutant alarm data; such alarm data is not in excess of the threshold value of conventional monitoring data. The conventional monitoring data exceeds the threshold value and is required to be reduced to a normal monitoring range after a certain time, and a certain gradient exists on the rising edge and the falling edge of a monitoring curve. The reason for the formation of the spurt-shaped alarm data is the influence of impurity gas interference in the field environment or electromagnetic pulse interference caused by starting and stopping of large-scale electrical equipment on the one hand, and the influence of data drift caused by the aging of the monitoring equipment components on the other hand.
In this embodiment, the mutant alarm data filtering method may be a rising rate super-threshold filtering method:
presetting a rising rate threshold
Where range L is the range of the sensor providing this alarm information, T90Under experimental conditions, the sensor has response time reaching 90% of the maximum measuring range value;
when the monitoring data exceeds the limit, calculating the rising rate of the monitoring data
Wherein, XmFor monitored overrun data, Xm-1For the data monitored immediately preceding the overrun data, TmTime of overrun data monitored, Tm-1Monitoring the time of the data for a bit preceding the overrun data;
comparison VmAnd YThreshold(s)Magnitude of the value, if Vm＞YThreshold(s)If the alarm data is judged to be invalid alarm, the alarm information is not pushed; if Vm≤YThreshold(s)And if the alarm data is effective, pushing alarm information according to the existing alarm flow.
In this embodiment, the mutant alarm data filtering method may also be filtering by determining whether to quickly rise and quickly recover:
defining the upper and lower alarm limit values of a certain monitoring parameter as a and b respectively, and when the monitoring value is XmB or X is not more thanmWhen the value is more than or equal to a, the alarm pushing processing is not carried out temporarily;
if Xm+1And XmSimultaneously has Xm+1B or X is not more thanm+1When a is more than or equal to a, judging XmFor effective alarming, the alarming information is pushed according to the existing flow; otherwise, determine XmAnd if the alarm is invalid, pushing the alarm information.
In this embodiment, the mutant alarm data filtering method may further adopt a three-layer BP neural network model for filtering:
acquiring monitoring historical data under the same type scene, wherein the monitoring historical data comprises normal monitoring data, mutant alarm data needing filtering and normal over-limit alarm data to form a learning sample set;
and (3) performing model training on the provided learning sample set by adopting a Levenberg-Marquardt algorithm as a nonlinear fitting training function:
define input vector X ═ X1，x2，x3，…，xn，)TThe hidden layer output quantity is Y ═ Y1，y2，y3，…，ym，)TOutput vector O ═ O1，o2，o3，…，ol，)TDesired output D ═ D (D)1，d2，d3，…，dl，)TThe weight value from the input layer to the hidden layer is represented by V, and the weight value from the hidden layer to the output layer is represented by W;
when the output quantity O is not equal to the desired quantity D, there is a deviation E,
the error is spread out to a hidden layer,
further spread out to the input layer and then,
then, the weight value V from the input layer to the hidden layer and the weight value W from the hidden layer to the output layer are adjusted to continuously reduce the deviation E,
the error signals of the output layer and the hidden layer are defined,
obtaining a calculation formula of weight value adjustment of a learning algorithm of the neural network:
when the change rule of the real-time monitoring data accords with the filtering model, the alarm can be marked as invalid alarm, and the alarm information is not pushed.
TABLE 1
In this embodiment, the comparison of the three mutant alarm information filtering methods is shown in table 1, and when the method is specifically used, the method can be combined and used according to the actual working condition of operation and the filtering precision required by the field:
when the sensor is required to alarm in real time on site and cannot accept time delay, the filtering method 1 is selected for filtering;
when the time sensitivity of the on-site alarm to the sensor is general, the time delay of 1 acquisition step length can be accepted, but the time delay of more than 10 acquisition step lengths can not be accepted, the filtering method 1 and the filtering method 2 are selected for filtering;
when the system is deployed in the initial stage and no abundant sample set is provided for the system to perform machine learning, the filtering method 1 and the filtering method 2 are selected for filtering, and when the system runs for a period of time and has abundant sample sets, the filtering method 3 is added, so that the filtering effect is improved.
When a rich sample set can be provided on site for system learning and more than 10 acquisition step lengths of delay can be accepted, filtering method 1+ filtering method 2+ filtering method 3 are selected for filtering.
Periodic alarm information filtering
When the alarm data periodically changes at a relatively fixed time interval or within a certain fixed time period, as shown in fig. 2, the alarm is determined to be a periodic alarm, and a periodic alarm information filtering method is adopted to filter the periodic alarm data;
such alarms can be classified into two categories according to the cause of the scene: one is the alarm caused by normal periodic operation; the other is an alarm caused by abnormal operation.
The system provides manual tagging functions for normal operations, such as periodic equipment verification, periodic inspection of process operations, etc. Before the related operation, the related monitoring point locations are manually marked, the overrun alarm in the operation time period is defined as the normal operation alarm, the system records the alarm data, and information reminding and pushing are not carried out. Filtering alarm information caused by normal operation by manually marking in advance;
if the periodic alarm caused by abnormal operation is detected, the system executes the current alarm process until a field supervisor finds out the alarm cause and implements the adjustment and modification measures.
Filtering of repeated alarm information of same event
If the alarm is a periodic alarm caused by the same event, only information reminding and pushing are carried out on the first alarm; if the alarm data continues to rise and exceeds the set time length, upgrading and alarming are carried out, otherwise, only the alarm information is recorded, and push reminding is not carried out; and if the events are repetitive mutant alarms caused by the same event, filtering mutant alarm data by a mutant alarm information filtering method.
Example 2
The embodiment provides a monitoring system, which includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the steps of the combined implementation method of the alarm information screening and filtering when executing the computer program.
It should be understood that in the present embodiment, the Processor may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and provides instructions and data to the processor. Some or all of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
The memory stores a computer program that is executable on the processor. And the processor implements the steps in the embodiment of the combined implementation method of the alarm information screening and filtering when executing the computer program.
Example 3
The present embodiment provides a computer-readable storage medium, on which computer instructions are stored, which, when executed by a processor, implement the steps of the combined implementation method of the alarm information screening filtering.
The present embodiment provides a computer program product, which when running on a monitoring system device, enables the monitoring system device to implement the steps of the alarm information screening and filtering combination implementation method in the foregoing embodiments when executed.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative algorithmic steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or as a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed monitoring system and method may be implemented in other ways. For example, the monitoring system embodiments described above are merely illustrative.
The computer readable medium may include: any entity or device capable of carrying the above-described computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier signal, telecommunications signal, software distribution medium, and the like.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (7)
1. A combined implementation method for alarm information screening and filtering is characterized by comprising the following steps:
acquiring alarm data in real time and analyzing the alarm data;
when the alarm data rapidly rises and exceeds a preset threshold and falls back to a normal value in a very short time, judging to be a mutant alarm, and filtering mutant alarm data by adopting a mutant alarm information filtering method;
when the alarm data has periodic change at a relatively fixed time interval or a certain fixed time period, the periodic alarm is judged to be periodic alarm, and a periodic alarm information filtering method is adopted to filter the periodic alarm data;
if the alarm is a periodic alarm caused by the same event, only information reminding and pushing are carried out on the first alarm; if the alarm data continues to rise and exceeds the set time length, upgrading and alarming are carried out, otherwise, only the alarm information is recorded, and push reminding is not carried out; and if the events are repetitive mutant alarms caused by the same event, filtering mutant alarm data by a mutant alarm information filtering method.
2. The combined implementation method of alarm information screening filtering of claim 1, wherein the mutant alarm data filtering method is an increase rate super-threshold filtering:
presetting a rising rate threshold
Where range L is the range of the sensor providing this alarm information, T90Under experimental conditions, the sensor has response time reaching 90% of the maximum measuring range value;
when the monitoring data exceeds the limit, calculating the rising rate of the monitoring data
Wherein, XmFor monitored overrun data, Xm-1For the data monitored immediately preceding the overrun data, TmTime of overrun data monitored, Tm-1Monitoring the time of the data for a bit preceding the overrun data;
comparison VmAnd YThreshold(s)Magnitude of the value, if Vm＞YThreshold(s)If the alarm data is judged to be invalid alarm, the alarm information is not pushed; if Vm≤YThreshold(s)And if the alarm data is effective, pushing alarm information according to the existing alarm flow.
3. The combined implementation method for alarm information screening and filtering according to claim 1, wherein the mutant alarm data filtering method is filtering by determining whether to rapidly rise and rapidly recover:
defining the upper and lower alarm limit values of a certain monitoring parameter as a and b respectively, and when the monitoring value is XmB or X is not more thanmWhen the value is more than or equal to a, the alarm pushing processing is not carried out temporarily;
if Xm+1And XmSimultaneously has Xm+1B or X is not more thanm+1When a is more than or equal to a, judging XmFor effective alarming, the alarming information is pushed according to the existing flow; otherwise, determine XmAnd if the alarm is invalid, pushing the alarm information.
4. The combined implementation method of alarm information screening and filtering of claim 1, wherein the mutant alarm data filtering method employs filtering based on a three-layer BP neural network model:
acquiring monitoring historical data under the same type scene, wherein the monitoring historical data comprises normal monitoring data, mutant alarm data needing filtering and normal over-limit alarm data to form a learning sample set;
and (3) performing model training on the provided learning sample set by adopting a Levenberg-Marquardt algorithm as a nonlinear fitting training function:
define input vector X ═ X1，x2，x3，…，xn，)TThe hidden layer output quantity is Y ═ Y1，y2，y3，…，ym，)TOutput vector O ═ O1，o2，o3，…，ol，)TDesired output D ═ D (D)1，d2，d3，…，dl，)TThe weight value from the input layer to the hidden layer is represented by V, and the weight value from the hidden layer to the output layer is represented by W;
when the output quantity O is not equal to the desired quantity D, there is a deviation E,
the error is spread out to a hidden layer,
further spread out to the input layer and then,
then, the weight value V from the input layer to the hidden layer and the weight value W from the hidden layer to the output layer are adjusted to continuously reduce the deviation E,
the error signals of the output layer and the hidden layer are defined,
obtaining a calculation formula of weight value adjustment of a learning algorithm of the neural network:
when the change rule of the real-time monitoring data accords with the filtering model, the alarm can be marked as invalid alarm, and the alarm information is not pushed.
5. The alarm information screening and filtering combined implementation method of claim 1, wherein the periodic alarm information filtering method is to manually label a monitoring point location, define an overrun alarm in an operation time period as a normal operation alarm, record only alarm data, and not perform information reminding and pushing.
6. A monitoring system comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that: the steps of the combined implementation method of the alert information screening filtering of any one of claims 1-5 are implemented when the computer program is executed by the processor.
7. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, perform the steps of the combined implementation method of alarm information screening filtering of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010843632.XA CN112149823A (en) | 2020-08-20 | 2020-08-20 | Combined implementation method for filtering alarm information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010843632.XA CN112149823A (en) | 2020-08-20 | 2020-08-20 | Combined implementation method for filtering alarm information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112149823A true CN112149823A (en) | 2020-12-29 |
Family
ID=73888400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010843632.XA Pending CN112149823A (en) | 2020-08-20 | 2020-08-20 | Combined implementation method for filtering alarm information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149823A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205666A (en) * | 2021-05-06 | 2021-08-03 | 广东鹰视能效科技有限公司 | Early warning method |
| CN116088381A (en) * | 2023-01-31 | 2023-05-09 | 惠州市海葵信息技术有限公司 | Equipment alarm data processing method, controller and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436720A (en) * | 2011-09-28 | 2012-05-02 | 清华大学 | Repeated alarm processing method based on data filtering |
| CN104932978A (en) * | 2015-06-29 | 2015-09-23 | 北京宇航时代科技发展有限公司 | System running fault self-detection and self-recovery method and system |
| CN105389595A (en) * | 2015-12-02 | 2016-03-09 | 中国石油大学(北京) | Radar monitoring method and device for long-term security risk of chemical equipment |
| CN105743220A (en) * | 2016-03-21 | 2016-07-06 | 国网天津静海供电有限公司 | Dispatching automation monitoring information analyzing and processing system and method |
| CN106787180A (en) * | 2016-12-08 | 2017-05-31 | 北京国网富达科技发展有限责任公司 | The analysis method and device of a kind of power transmission and transformation Condition Monitoring Data |
| CN107096899A (en) * | 2017-05-17 | 2017-08-29 | 安徽工业大学 | The crystallizer bleedout prediction electric thermo system that a kind of logic-based judges |
| CN107564231A (en) * | 2017-09-15 | 2018-01-09 | 山东建筑大学 | Building fire early warning and fire disaster situation assessment system and method based on Internet of Things |
| CN108492539A (en) * | 2018-05-21 | 2018-09-04 | 浙江工业大学 | A kind of statistical method of safety supervision system alarm number |
| CN109271378A (en) * | 2018-09-28 | 2019-01-25 | 四川能投云电科技有限公司 | A method of filtering scheduling system signal is frequently alarmed |
| CN210574253U (en) * | 2019-11-12 | 2020-05-19 | 深圳市无眼界科技有限公司 | Gas monitoring short message alarm system |
-
2020
- 2020-08-20 CN CN202010843632.XA patent/CN112149823A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436720A (en) * | 2011-09-28 | 2012-05-02 | 清华大学 | Repeated alarm processing method based on data filtering |
| CN104932978A (en) * | 2015-06-29 | 2015-09-23 | 北京宇航时代科技发展有限公司 | System running fault self-detection and self-recovery method and system |
| CN105389595A (en) * | 2015-12-02 | 2016-03-09 | 中国石油大学(北京) | Radar monitoring method and device for long-term security risk of chemical equipment |
| CN105743220A (en) * | 2016-03-21 | 2016-07-06 | 国网天津静海供电有限公司 | Dispatching automation monitoring information analyzing and processing system and method |
| CN106787180A (en) * | 2016-12-08 | 2017-05-31 | 北京国网富达科技发展有限责任公司 | The analysis method and device of a kind of power transmission and transformation Condition Monitoring Data |
| CN107096899A (en) * | 2017-05-17 | 2017-08-29 | 安徽工业大学 | The crystallizer bleedout prediction electric thermo system that a kind of logic-based judges |
| CN107564231A (en) * | 2017-09-15 | 2018-01-09 | 山东建筑大学 | Building fire early warning and fire disaster situation assessment system and method based on Internet of Things |
| CN108492539A (en) * | 2018-05-21 | 2018-09-04 | 浙江工业大学 | A kind of statistical method of safety supervision system alarm number |
| CN109271378A (en) * | 2018-09-28 | 2019-01-25 | 四川能投云电科技有限公司 | A method of filtering scheduling system signal is frequently alarmed |
| CN210574253U (en) * | 2019-11-12 | 2020-05-19 | 深圳市无眼界科技有限公司 | Gas monitoring short message alarm system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205666A (en) * | 2021-05-06 | 2021-08-03 | 广东鹰视能效科技有限公司 | Early warning method |
| CN116088381A (en) * | 2023-01-31 | 2023-05-09 | 惠州市海葵信息技术有限公司 | Equipment alarm data processing method, controller and storage medium |
| CN116088381B (en) * | 2023-01-31 | 2024-02-06 | 惠州市海葵信息技术有限公司 | Equipment alarm data processing method, controller and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11308786B2 (en) | Method and apparatus for real-time data analysis of water pipe network | |
| CN116246407B (en) | Agriculture and forestry area fire early warning supervisory systems based on artificial intelligence | |
| CN116859857B (en) | Intelligent management system of fuel pump assembly production line based on remote control | |
| CN112348237B (en) | Abnormal trend detection method for dynamic drilling data | |
| CN112149823A (en) | Combined implementation method for filtering alarm information | |
| CN111179591B (en) | Road network traffic time sequence characteristic data quality diagnosis and restoration method | |
| CN113488901B (en) | Safety monitoring system and method for intelligent power distribution cabinet | |
| JP6417343B2 (en) | Time-series data abnormality monitoring apparatus and time-series data abnormality monitoring method | |
| CN114282788A (en) | Enterprise risk early warning method and device, electronic equipment and readable storage medium | |
| CN107276808A (en) | A kind of optimization method of Traffic Anomaly monitoring | |
| CN114429308A (en) | Enterprise security risk assessment method and system based on big data | |
| US11853053B2 (en) | Dynamic prediction of risk levels for manufacturing operations through leading risk indicators: dynamic exceedance probability method and system | |
| CN117670028A (en) | Dust removal system risk dynamic assessment and grading early warning method based on Internet of things monitoring | |
| Brown et al. | Demonstration of a method for automated steady-state identification in multivariable systems | |
| US20240085878A1 (en) | Dynamic Prediction of Risk Levels for Manufacturing Operations through Leading Risk Indicators: Dynamic Risk Pattern Match Method and System | |
| CN116681307B (en) | River four-disorder supervision traceability display method and system based on multi-terminal fusion feedback | |
| CN107609330B (en) | Access log mining-based internal threat abnormal behavior analysis method | |
| CN101782763B (en) | Method for monitoring statistical process control | |
| CN111207306B (en) | Heating power pipe network leakage monitoring method based on digital pressure signal processing | |
| JPH04152220A (en) | Method and device for failure sensing | |
| CN112579665A (en) | Energy equipment control method and device and energy equipment | |
| CN116069596A (en) | Situation awareness method, system, equipment and storage medium | |
| JPH0217511A (en) | Plant monitoring device | |
| JPH07200960A (en) | False-alarm prevention method and fire alarm equipment | |
| CN110930035A (en) | Harmonic hazard assessment method based on interval statistic |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201229 |
|
| RJ01 | Rejection of invention patent application after publication |