CN105573279B - A method of industrial processes are monitored based on sensing data - Google Patents
A method of industrial processes are monitored based on sensing data Download PDFInfo
- Publication number
- CN105573279B CN105573279B CN201511033860.6A CN201511033860A CN105573279B CN 105573279 B CN105573279 B CN 105573279B CN 201511033860 A CN201511033860 A CN 201511033860A CN 105573279 B CN105573279 B CN 105573279B
- Authority
- CN
- China
- Prior art keywords
- data
- curve
- stage
- industrial processes
- monitoring
- 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.)
- Expired - Fee Related
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
Abstract
The invention discloses a kind of methods based on sensing data monitoring industrial processes, comprising the following steps: (1) according to the data characteristics in industrial processes each stage, identifies each stage an of lot data；(2) in identification each phase process of data, the validity of simultaneously flag data is assessed；(3) treatment by stages data mode；(4) regular to data progress for difference existing for course of work total time, and be aligned using specific phase transition point as standard；(5) curve after regular to the multiple batches of identical product is fitted.Realization of the invention is easy, and algorithm is simple, it is only necessary to carry out some simple mathematical operations, this has just been catered under " big data " background, with the trend trend of simple algorithm processing mass data.Even if data volume is bigger, the time of processing is also shorter, applied widely, and the monitoring of most of similar stateful preparation stages and state Restoration stage industrial processes are all suitable for.
Description
Technical field
The present invention relates to field of industrial production, and in particular to a kind of side based on sensing data monitoring industrial processes
Method.
Background technique
Industrial processes especially chemical reaction process is more due to being related to dangerous material quantity, and manufacturing technique requirent is harsh,
And enlargement, serialization and the automation of process units, once accident occurs, consequence will be extremely serious, therefore, safety problem
In occupation of very important position in industrial processes.
Historical experience shows to improve enterprise safety operation level nothing more than two approach: one, carrying out deeply comprehensive safety
Analysis and verification, accomplish to prevent trouble before it happens, that is, establish effective prevention system；Two: when dangerous really generation, making great efforts to improve behaviour
The Ability of emergency management of workmanship establishes online real-time protection system.Prevent with protection be safety in production in two mutually auxiliary phases
At link, effective preventive means can early exclude security risk, and real-time protection means greatly strengthen danger
Ability enterprise emergency when danger occurs and pulled through.
In order to ensure production safety, first having to problems faced is exactly to prevent trouble before it happens.Although a set of good protection body
It is no doubt important, but if it is expected that can analyze, find the problem, it is that people most expect that danger, which was eliminated in the initial period,
As a result, here it is safety evaluation main problems to be solved, therefore in process of production, we must be to the facility of factory
It is monitored in real time, and the technology of this respect also compares shortage at present.
Summary of the invention
In view of this, the present invention proposes a kind of method based on sensing data monitoring industrial processes, it being capable of basis
Factory's sensor generate mass data, the process data of multiple and different batches of identical product will be produced, by alignment, it is regular
A standard value curve is fitted, industrial processes are then monitored according to curve.
Additionally, due in actual production process, although production is identical product, process time but exists certain
Difference, it is impossible to which direct usage history data fit standard value curve, it is necessary to first pre-process to historical data.Base
In this, the invention proposes the regular methods of data, can be with align data with this method.
To achieve the above object, the invention adopts the following technical scheme:
A method of industrial processes are monitored based on sensing data, comprising the following steps:
(1) according to the data characteristics in industrial processes each stage, each stage an of lot data is identified；
(2) in identification each phase process of data, the validity of simultaneously flag data is assessed；
(3) treatment by stages data mode；
(4) regular to data progress for difference existing for course of work total time, and be with specific phase transition point
Standard is aligned；
(5) curve after regular to the multiple batches of identical product is fitted.
Further, in step (1), industrial processes each stage includes non-reaction working condition and reaction work
State, reaction working condition include the state preparation stage, stablize the stage of reaction and state Restoration stage.
Further, the data characteristics in step (1), when being converted between each stage are as follows: non-reaction working condition to state standard
By being approximately equal to 0 raising to a biggish value in the standby stage work slope of curve short time, the state preparation stage reacts to stable
The stage work slope of curve, which is down to, is approximately equal to 0, and the stable stage of reaction is deviated considerably to state Restoration stage working curve to be stablized instead
Answer the standard value in stage, state Restoration stage to non-reaction working condition working curve is close to normal off working state value.
Further, in step (2), when the data to a batch carry out stage Division identification, if can not detect
Expected phase transition feature then can determine that the lot data because data are imperfect and invalid, and marks it to the lot data
Missing content.
Further, extensive in state in state preparation stage monitoring slope of a curve and smoothness in step (3)
The multiple stage monitors the duration in this stage, is stablizing stage of reaction monitoring current sensor numerical value and standard value curve, security interval
The upper limit and security interval lower limit carry out warning note when numerical value exceeds safety margin.
Further, in step (3), the smoothness of state preparation stage refers to that the equipment of industrial product reaches industrial production
Whether the rate that the ability that claimed condition even is realized, i.e. equipment change state is directly proportional to the time.Calculation method is as follows:
1. the quantity for counting all data points of entire temperature-rise period is m, the numerical value of monitoring is b1, b2..., bn；
2. the straight line or curve of a minimal error are fitted according to the data of m point, be denoted as L (majority is straight line,
It is likely to be curve)；
3. setting L to one of monitoring data point biEuclidean distance be di；
4. the average distance for calculating monitoring data point and L is
5. being the index for evaluating smoothness with d.
Further, in step (4), the regular method of data the following steps are included:
1. assuming the data for having n batch, course of work total duration is respectively a1, a2, a3..., anMinute, that is, this
The data of n batch have a respectively1+ 1, a2+ 1, a3+ 1 ..., an+ 1 time series point is (because also include the biography of start time
Sensor numerical value), the time series point of each batch is linked to be curve.
2. setting a as closest to (a1+a2+a3+...+anThe integer of)/n (average value of i.e. each batch total duration), when total
A length of a1Curve with a1/ a is interval sampling time series point, total duration a2Curve with a2/ a is interval sampling time sequence
Column point, and so on, total duration anCurve with an/ a is interval sampling time series point.
3. every curve samples the time series point taken out, and is linked to be curve respectively with equal time interval, in this way
It can obtain that time interval is equal, the number comprising time series point is equal, total duration also equal n curve.
It further, is all to be formed by connecting after a plurality of curve is regular by a+1 point, between points in step (5)
Time interval is equal, so total duration is also equal.If the production curve of a standard is a discrete random process { Xt: t=
0,1,2 ..., a }, t is integer, and 0≤t≤a, the sensor values of t moment are stochastic variable Xt, there is n curve, that is to say, that
This random process has n timed sample sequence, finds out the mean μ of each moment numerical valuetAnd standard deviation sigmat, then can be at n
Between obtain three new time serieses on the basis of sequence samples:
①{μt: t=0,1,2 ..., a } be the process of producing product sensor standard value；
②{μt+3σt: t=0,1,2 ..., a } be the process of producing product sensor number upper safety limit value；
③{μt-3σt: t=0,1,2 ..., a } be the process of producing product sensor number lower safety limit value；
The point of these three time serieses is separately connected into curve, so that it may obtain the process of producing product sensor values
Standard value curve, the security interval upper limit and security interval lower limit.Wherein, between the security interval upper limit and security interval lower limit just
It is safe range.
Further, the industrial processes are chemical reaction process.
Realization of the invention is easy, and algorithm is simple, it is only necessary to carry out some simple mathematical operations, this has just catered to " big
Under data " background, with the trend trend of simple algorithm processing mass data.Even if data volume is bigger, the time of processing also compares
Shorter, the safety issue that this produces industry in real time is extremely important.It is applied widely, for most of similar stateful
The monitoring of preparation stage and state Restoration stage industrial processes is all suitable for.
Detailed description of the invention
Fig. 1 is divided into the schematic diagram in five stages for sensor temperature during chemical reaction according to the time；
Fig. 2 is the time series point curve figure that total duration is 3 minutes；
Fig. 3 is the time series point curve figure that total duration is 5 minutes；
Fig. 4 is that total duration is 3 minutes regular time series point curve figures with after alignment；
Fig. 5 is that total duration is 5 minutes regular time series point curve figures with after alignment；
Fig. 6 be the equal curve matching of a plurality of total duration that is obtained by Time alignment go out standard production value curve, peace
The schematic diagram of full production range.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with attached drawing and specifically
Embodiment technical solution of the present invention is described in detail, in discussion of the invention, for convenience discuss, industrial production
Process setting is chemical reaction process, and the index of sensor monitoring is temperature, but the method is not limited to chemical reaction process temperature
The monitoring of degree evidence can be used for the monitoring of the Various types of data such as pressure in industrial processes, flow, liquid level.
A method of industrial processes are monitored based on sensing data, comprising the following steps:
Step (1) identifies each stage an of lot data according to the data characteristics in industrial processes each stage；
Fig. 1 is please referred to, Fig. 1 is divided into the signal in five stages for sensor temperature during chemical reaction according to the time
Figure, the sensor temperature for producing an a kind of batch of product can be divided into five processes according to the time, and wherein A and E is non-
Working condition, B-C-D are in working condition.B is the state preparation stage, and C is to stablize the stage of reaction, and D is state Restoration stage, and false
If monitoring time is uniformly equally spaced.In actual chemical production process, in order to reach the condition of reaction, chemical plant
Temperature would generally be made to reach temperature required for chemical reaction as early as possible with various methods, so the time of state preparation stage is very
It is short, only 20 minutes or so, stablizes reaction process and be only the actual process for being chemically reacted and being produced product, the time is long
Up to a few hours, for save the cost, after chemical reaction, chemical plant will not actively consume electric power to make equipment be restored to original
Carry out temperature, and equipment spontaneous recovery can be allowed to original temperature, so this process duration is also longer, there are several hours,
And spontaneous recovery also reflects the characteristic of differential responses equipment to the time difference of original temperature.
To the data of a batch, need to distinguish its each stage, to be further processed, when converting between each stage
Data characteristics have:
1. A-B: by being approximately equal to 0 raising to a biggish value in the working curve slope short time
2. B-C: working curve slope, which is down to, is approximately equal to 0
3. C-D: working curve deviates considerably from the standard value of the stable stage of reaction
4. D-E: working curve is close to normal off working state value
Step (2) assesses the validity of simultaneously flag data in identification each phase process of data；
When the data to a batch carry out stage Division identification, if expected phase transition feature can not be detected,
It then can determine that the lot data because data are imperfect and invalid, and marks its missing content to the lot data.
Step (3), treatment by stages data mode；
In state preparation stage monitoring slope of a curve and smoothness, when state Restoration stage monitors this stage
It is long, stablizing stage of reaction monitoring current sensor numerical value and standard value curve, the security interval upper limit and security interval lower limit, when
Numerical value carries out warning note when exceeding safety margin.
The smoothness of state preparation stage refers to that chemical reaction equipment reaches the reality of chemical reaction claimed condition even
Whether the rate that existing ability, i.e. equipment change state is directly proportional to the time.Calculation method is as follows:
1. the quantity for counting all data points of entire temperature-rise period is m, the numerical value b of monitoring1, b2..., bn；
2. the straight line or curve of a minimal error are fitted according to the data of m point, be denoted as L (majority is straight line,
It is likely to be curve)；
3. setting L to one of monitoring data point biEuclidean distance be di；
4. the average distance for calculating monitoring data point and L is
5. being the index for evaluating smoothness with d.
Step (4), it is regular to data progress for difference existing for course of work total time, and with specific phase transition
Point is that standard is aligned；
In the actual production process, sensor measures in regular intervals, and usually measurement in every 1 minute record is primary
Data.Affected by various factors even producing identical product, the total duration of different time batch working reaction can not be completely
Equal, the number for the sensor values for including also differs.In order to by the sensor of the different multiple batches of production process total duration
Data are fitted to a standard curve, propose the regular method of a data here:
1. assuming the data for having n batch, course of work total duration is respectively a1, a2, a3..., anMinute, that is, this
The data of n batch have a respectively1+ 1, a2+ 1, a3+ 1 ..., an+ 1 time series point is (because also include the biography of start time
Sensor numerical value).The time series point of each batch is linked to be curve.
2. setting a as closest to (a1+a2+a3+...+anThe integer of)/n (average value of i.e. each batch total duration), when total
A length of a1Curve with a1/ a is interval sampling time series point, total duration a2Curve with a2/ a is interval sampling time sequence
Column point, and so on, total duration anCurve with an/ a is interval sampling time series point.
3. every curve samples the time series point taken out, and is linked to be curve respectively with equal time interval, in this way
It can obtain that time interval is equal, the number comprising time series point is equal, total duration also equal n curve.
It cites a plain example and is illustrated below；
Referring to figure 2. and the process total duration of Fig. 3, Fig. 2 are 3 minutes, 4 time series points are shared, when the process of Fig. 3 is total
A length of 5 minutes, 6 time series points are shared, the interval of the time series of the two is 1 minute.The point of two time serieses
It is linked to be curve respectively, due to (3+5)/2=4, so the curve of Fig. 2 is sampled using 0.75 (=3/4) minute as time interval,
The curve of Fig. 3 is sampled using 1.25 (=5/4) minutes as time interval, and two curves sample the time series point taken out,
Curve is linked to be respectively with equal time interval again, Fig. 2 corresponding diagram 4, Fig. 3 corresponding diagram 5, this makes it possible to obtain time interval phase
Deng the number comprising time series point is equal, total duration also equal two curves.
Step (5), it is regular to the multiple batches of identical product after curve be fitted；
Fig. 6 is please referred to, the equal curve of a plurality of total duration obtained by Time alignment can fit a standard
Production value curve and the range of a safety in production.
The a plurality of curve obtained after regular is formed by connecting by a+1 point, and time interval between points is equal,
So total duration is also equal.If the production curve of a standard is a discrete random process { Xt: t=0,1,2 ..., a },
T is integer, and 0≤t≤a, the sensor values of t moment are stochastic variable Xt, have n curve, that is to say, that this random process
There is n timed sample sequence, finds out the mean μ of each moment numerical valuetAnd standard deviation sigmat, then can be in n timed sample sequence
On the basis of obtain three new time serieses:
①{μt: t=0,1,2 ..., a } be the process of producing product sensor standard value；
②{μt+3σt: t=0,1,2 ..., a } be the process of producing product sensor number upper safety limit value；
③{μt-3σt: t=0,1,2 ..., a } be the process of producing product sensor number lower safety limit value；
The point of these three time serieses is separately connected into curve, so that it may obtain the process of producing product sensor values
Standard value curve, the security interval upper limit and security interval lower limit, wherein between the security interval upper limit and security interval lower limit just
It is safe range, sensor values fall probability in safe range at least 88.9%, if stochastic variable meets normal state point
Probability is more up to 99.7% if cloth.
This three curves can be used for monitoring chemical reaction process.Under normal circumstances, the sensor number of identical product is produced
The standard curve that value curve should be obtained relatively by the method for the present invention, and the bound peace obtained beyond the method for the present invention
The probability very little of gamut.Therefore, worker can see currently practical numerical curve and this three songs from operating display
Line, and current value and standard value are compared to carry out the adjustment of pid parameter.Once the numerical value of current sensor has been more than peace
The safe range that bound defines between the whole district, system can be recognized and be alarmed automatically, to prevent there is safety accident.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (8)
1. a kind of method based on sensing data monitoring industrial processes, which is characterized in that the method includes following steps
It is rapid:
(1) according to the data characteristics in industrial processes each stage, each stage an of lot data is identified；
(2) in identification each phase process of data, the validity of simultaneously flag data is assessed；
(3) treatment by stages data mode；
(4) regular to data progress for difference existing for course of work total time, and using specific phase transition point as standard
It is aligned；
(5) curve after regular to the multiple batches of identical product is fitted；
In step (4), the regular method of the data the following steps are included:
1. assuming the data for having n batch, course of work total duration is respectively a1, a2, a3..., anMinute, that is, this n batches
Secondary data have a respectively1+ 1, a2+ 1, a3+ 1 ..., anThe time series point of each batch is linked to be song by+1 time series point
Line；
2. setting a as closest to (a1+a2+a3+...+anThe integer of)/n, total duration a1Curve with a1/ a is the interval sampling time
Sequence of points, total duration a2Curve with a2/ a is interval sampling time series point, and so on, total duration anCurve with
an/ a is interval sampling time series point；
3. every curve samples the time series point taken out, and is linked to be curve respectively with equal time interval, thus can
Access that time interval is equal, the number comprising time series point is equal, total duration also equal n curve.
2. the method according to claim 1 based on sensing data monitoring industrial processes, which is characterized in that step
(1) in, industrial processes each stage includes non-reaction working condition and reaction working condition, and reaction working condition includes
The state preparation stage stablizes the stage of reaction and state Restoration stage.
3. the method according to claim 1 based on sensing data monitoring industrial processes, which is characterized in that step
(2) in, when the data to a batch carry out stage Division identification, if expected phase transition feature can not be detected,
It can determine that the lot data because data are imperfect and invalid, and marks its missing content to the lot data.
4. the method according to claim 2 based on sensing data monitoring industrial processes, which is characterized in that step
(3) in, in state preparation stage monitoring slope of a curve and smoothness, when state Restoration stage monitors this stage
It is long, stablizing stage of reaction monitoring current sensor numerical value and standard value curve, the security interval upper limit and security interval lower limit, when
Numerical value carries out warning note when exceeding safety margin.
5. the method according to claim 4 based on sensing data monitoring industrial processes, which is characterized in that described
The smoothness calculation method of state preparation stage is as follows:
1. the quantity for counting all data points of entire temperature-rise period is m, the numerical value b of monitoring1, b2..., bn；
2. fitting the straight line or curve of a minimal error according to the data of m point, it is denoted as L；
3. setting L to one of monitoring data point biEuclidean distance be di；
4. the average distance for calculating monitoring data point and L is
5. being the index for evaluating smoothness with d.
6. the method according to claim 1 based on sensing data monitoring industrial processes, which is characterized in that step
It (5) is all to be formed by connecting in, after a plurality of curve is regular by a+1 point, time interval between points is equal, so total
Duration is also equal, if the production curve of a standard is a discrete random process { Xt: t=0,1,2 ..., a }, t is integer,
0≤t≤a, the sensor values of t moment are stochastic variable Xt, have n curve, that is to say, that this random process has n time
Sequence samples find out the mean μ of each moment numerical valuetAnd standard deviation sigmat, then can be obtained on the basis of n timed sample sequence
The time series new to three:
①{μt: t=0,1,2 ..., a } be the process of producing product sensor standard value；
②{μt+3σt: t=0,1,2 ..., a } be the process of producing product sensor number upper safety limit value；
③{μt-3σt: t=0,1,2 ..., a } be the process of producing product sensor number lower safety limit value；
The point of these three time serieses is separately connected into curve, so that it may obtain the mark of the process of producing product sensor values
Quasi- value curve, the security interval upper limit and security interval lower limit, wherein be exactly to pacify between the security interval upper limit and security interval lower limit
Gamut.
7. -6 any method based on sensing data monitoring industrial processes, feature exist according to claim 1
It can be used for the processing of all kinds of monitoring data of temperature in industrial processes, pressure, flow, liquid level in the method.
8. -6 any method based on sensing data monitoring industrial processes, feature exist according to claim 1
In the industrial processes be chemical reaction process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511033860.6A CN105573279B (en) | 2015-12-31 | 2015-12-31 | A method of industrial processes are monitored based on sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511033860.6A CN105573279B (en) | 2015-12-31 | 2015-12-31 | A method of industrial processes are monitored based on sensing data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105573279A CN105573279A (en) | 2016-05-11 |
| CN105573279B true CN105573279B (en) | 2018-12-21 |
Family
ID=55883533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511033860.6A Expired - Fee Related CN105573279B (en) | 2015-12-31 | 2015-12-31 | A method of industrial processes are monitored based on sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105573279B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753027A (en) * | 2017-11-08 | 2019-05-14 | 阿里巴巴集团控股有限公司 | It is a kind of industry manufacture in parameter monitoring method and device |
| CN110263291B (en) * | 2019-05-29 | 2020-03-31 | 朗坤智慧科技股份有限公司 | Industrial data trend identification method and system |
| CN111898903A (en) * | 2020-07-28 | 2020-11-06 | 北京科技大学 | Method and system for evaluating uniformity and comprehensive quality of steel product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101685059A (en) * | 2009-05-15 | 2010-03-31 | 河海大学 | Method for dynamically detecting rheological property of concrete on construction site |
| CN101963802A (en) * | 2010-08-25 | 2011-02-02 | 江苏大学 | Virtual measurement method in batch manufacture procedure and system therefor |
| CN102636991A (en) * | 2012-04-18 | 2012-08-15 | 国电科学技术研究院 | Method for optimizing running parameters of thermal power unit and based on fuzzy set association rule |
| CN102981893A (en) * | 2012-12-25 | 2013-03-20 | 国网电力科学研究院 | Method and system for dispatching virtual machine |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6484565B2 (en) * | 1999-11-12 | 2002-11-26 | Drexel University | Single riser/single capillary viscometer using mass detection or column height detection |
-
2015
- 2015-12-31 CN CN201511033860.6A patent/CN105573279B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101685059A (en) * | 2009-05-15 | 2010-03-31 | 河海大学 | Method for dynamically detecting rheological property of concrete on construction site |
| CN101963802A (en) * | 2010-08-25 | 2011-02-02 | 江苏大学 | Virtual measurement method in batch manufacture procedure and system therefor |
| CN102636991A (en) * | 2012-04-18 | 2012-08-15 | 国电科学技术研究院 | Method for optimizing running parameters of thermal power unit and based on fuzzy set association rule |
| CN102981893A (en) * | 2012-12-25 | 2013-03-20 | 国网电力科学研究院 | Method and system for dispatching virtual machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105573279A (en) | 2016-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100489870C (en) | Method and multidimensional system for statistical control of a process | |
| CN105573279B (en) | A method of industrial processes are monitored based on sensing data | |
| Wang et al. | Indexing and designing deadbands for industrial alarm signals | |
| CN117251697B (en) | Comprehensive evaluation management system for safety data of intelligent wearable equipment | |
| CN107346388A (en) | Web attack detection methods and device | |
| CN115903659A (en) | Intelligent monitoring method and system for numerical control equipment | |
| CN104808651B (en) | The measuring method of the reasonable alarm limit of chemical plant installations key parameter | |
| CN106525107A (en) | Method for identifying failure of sensor through arbitration | |
| CN117371339A (en) | Transformer operation monitoring system based on Internet of things | |
| CN117318310B (en) | Remote unmanned intelligent monitoring system for explosion-proof power distribution cabinet | |
| CN118072495B (en) | Chemical industry reation kettle operation alarm system based on data analysis | |
| CN106125680B (en) | Industrial stokehold data safety processing method based on industry internet and device | |
| CN103389427B (en) | GIS equipment operational condition online test method and system | |
| CN106199421A (en) | A kind of method for early warning based on the big data of industry and system | |
| CN203658765U (en) | Control system interlocking protection device based on temperature measurement | |
| CN110166972B (en) | Intelligent sensing system with block chain module | |
| CN103207567A (en) | Low-false-alarm-rate improved principal component analysis process monitoring method and system | |
| CN114938287B (en) | Power network abnormal behavior detection method and device integrating service characteristics | |
| CN113778054B (en) | Double-stage detection method for industrial control system attack | |
| CN111007299A (en) | Power grid data acquisition, analysis and processing system | |
| CN114706347A (en) | Fault diagnosis system and method for electrolytic machining tool | |
| CN113608507A (en) | Industrial internet yield real-time monitoring system and method based on SaaS (software as a service) level | |
| CN205619961U (en) | Intelligence parameter measurement device | |
| CN207473792U (en) | Industrial processes parameter warning device | |
| EP3731049A1 (en) | Substation equipment monitoring using a scada system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181221 Termination date: 20211231 |