CN106959662B - A kind of identification of electric melting magnesium furnace unusual service condition and control method - Google Patents
A kind of identification of electric melting magnesium furnace unusual service condition and control method Download PDFInfo
- Publication number
- CN106959662B CN106959662B CN201710324622.3A CN201710324622A CN106959662B CN 106959662 B CN106959662 B CN 106959662B CN 201710324622 A CN201710324622 A CN 201710324622A CN 106959662 B CN106959662 B CN 106959662B
- Authority
- CN
- China
- Prior art keywords
- electric melting
- melting magnesium
- magnesium furnace
- operating condition
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/05—Programmable logic controllers, e.g. simulating logic interconnections of signals according to ladder diagrams or function charts
- G05B19/058—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/10—Plc systems
- G05B2219/14—Plc safety
- G05B2219/14006—Safety, monitoring in general
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Waste-Gas Treatment And Other Accessory Devices For Furnaces (AREA)
Abstract
The present invention provides a kind of identification of electric melting magnesium furnace unusual service condition and control method.The described method includes: obtaining the online data in the predetermined period in electric melting magnesium furnace operating condition；Using similarity mode strategy check in case library whether with the matched case information of online data；If it exists, the identification result that current online data is provided according to matched case information, using identification result as the anomalous identification result of current electric melting magnesium furnace operating condition；Wherein, case library is the case information for the various unusual service conditions established previously according to the historical data of electric melting magnesium furnace operating condition；If matched case information is not present in case library, the online data is analyzed using Bayesian Network Inference model, identification result is obtained, using identification result as the anomalous identification result of current electric melting magnesium furnace operating condition.The above method reduces energy consumption, reduces environmental pollution for the comprehensive utilization ratio of raising mineral resources, promotes safety in production, there is great meaning.
Description
Technical field
The invention belongs to computer technology more particularly to a kind of electric melting magnesium furnace unusual service condition recognition methods and security control sides
Method.
Background technique
Electric-melting magnesium is a kind of important refractory material, it has the advantage that strong insulating properties, high-melting-point, oxidation resistance
Strong and close structure, therefore be widely applied in a variety of industrial productions.The raw material of electric-melting magnesium are magnesite, most
In number situation, raw material grade is low, the complicated multiplicity of mineral composition.
The smelting equipment that electric-melting magnesium uses is three-phase electric melting magnesium furnace, and the current control system of electric melting magnesium furnace tracks different operating conditions
Under current setting value complete fusion process.In practical applications, when the granularity of raw material, ingredient, fusing point etc. change, electricity
The distance between pole bottom and molten bath can generate fluctuation.This unknown fluctuation will lead to the fluctuation of electric current, and electric current before is set
Definite value will no longer be suitable for the operating condition of variation, can generate higher energy consumption at this time, and system performance decline even has safety
It threatens.
By taking abnormal gas exhaust operating condition as an example, when the granularity of raw material changes, electrode movement originally can not make to melt completely
The carbon dioxide gas discharge generated during refining, the i.e. current setting value of exhaust operating condition are no longer applicable in, the pressure in electric melting magnesium furnace
Good general increases, and when pressure increases to a certain extent, high temperature molten slurry will discharge out of the furnace with gas, and the high temperature molten slurry of splashing will
Equipment is caused badly damaged, great threat is caused to the personal safety of operator.Meanwhile during splashing generation,
A large amount of energy loss improves single ton of energy consumption of electric melting magnesium furnace.Due between extraneous strong interference and variable close coupling,
Nonlinear presence understands correlativity between variable, and the model obtained under unusual service condition is very difficult.
Currently, site operation personnel passes through the current information observed, image information and acoustic information and the experience of oneself
Unusual service condition is recognized, according to the unusual service condition of identification, provides corresponding Adjusted Option, most of to pass through manually mode real
It applies, automatization level is lower.Manual identified and operation are sensitive to human error, and operator's energy when handling multi-source information
Power is limited, and often ignores the influence of some variables.Within the limited time, under huge stress, operator
Member is often difficult to make effective decision.The artificial method of adjustment of operator places one's entire reliance upon the respective experience of operator,
It is difficult to ensure that the timeliness and accuracy of decision.If any misoperation, it is negligent of detection or because irresistible natural cause causes
Equipment fault and lead to the accidents such as production disruption, it will bring huge waste and loss to production.
Summary of the invention
For existing technical problem, the present invention provides a kind of identification of electric melting magnesium furnace unusual service condition and control method,
The above method is applied to improve the comprehensive utilization ratio of mineral resources in electric melting magnesium furnace operating condition, reduces energy consumption.
The present invention provides a kind of identification of electric melting magnesium furnace unusual service condition and control method, comprising:
The online data in predetermined period in S1, acquisition electric melting magnesium furnace operating condition；
S2, using similarity mode strategy check in case library whether there is and the matched case information of online data；
S3, if it exists, the identification result of current online data is provided according to matched case information, using identification result as
The anomalous identification result of current electric melting magnesium furnace operating condition；
Wherein, case library is that the case for the various unusual service conditions established previously according to the historical data of electric melting magnesium furnace operating condition is believed
Breath.
Optionally, which comprises if matched case information is not present in S3a, case library, use Bayesian network
Network inference pattern analyzes the online data, identification result is obtained, using identification result as current electric melting magnesium furnace operating condition
Anomalous identification result.
Optionally, before step S2, the method also includes:
S2a, according to the historical data of electric melting magnesium furnace operating condition in preset time period, establish case library；
And historical data and priori knowledge according to electric melting magnesium furnace operating condition in preset time period, it establishes Bayesian network and pushes away
Manage model.
Optionally, step S2a includes:
The information that electric melting magnesium furnace operating condition is abnormal in collected offline preset time period；
According to the information of collection, the relationship in the feature and unusual service condition of unusual service condition between correlated variables is determined, obtain
Historical data establishes case library and Bayesian Network Inference model according to historical data；
Alternatively,
The information that electric melting magnesium furnace operating condition is abnormal in collected offline preset time period；
According to the information of collection, the relationship in the feature and unusual service condition of unusual service condition between correlated variables is determined, obtain
Historical data, is filtered processing to historical data, establishes case library and Bayesian network according to the historical data after filtration treatment
Network inference pattern.
Optionally, the S2a includes:
The information that electric melting magnesium furnace operating condition is abnormal in collected offline preset time period；
According to the relationship in priori knowledge and unusual service condition between correlated variables, the node and knot of Bayesian network are determined
Structure；
According to the historical data of collection and the structure of determination, the parameter of Bayesian network is obtained, to set up Bayes
Network reasoning model.
Optionally, the step S1 further include:
Processing is filtered to the online data of acquisition, to obtain the online data after filtration treatment；
Correspondingly, it is matched using the online data after filtration treatment with the case information in case library in step S2.
Optionally, the method also includes:
S4, according to anomalous identification as a result, determine equipment remaining life time；
According to the relationship between the remaining life time pre-established and adjustment amount, adjustment amount is calculated, obtains security control
Decision information, so that control system adapts to adjust according to safety control strategy information；
Wherein, remaining life time is electric melting magnesium furnace operating condition equipment from state when obtaining online data to completely can not be just
The time often to work；
The adjustment amount is current setting value；Relationship between remaining life time and adjustment amount is what offline mode determined
Relationship.
Optionally, the step S2 includes:
The similarity in online data and case library between the variable of each case is obtained, judges whether the similarity is greater than
Preset threshold, if so, determining that online data case corresponding with the maximum similarity of threshold value is greater than matches.
Optionally, the method also includes:
If it is real that S5, the anomalous identification result obtained by Bayesian Network Inference model are determined as current electric melting magnesium furnace operating condition
Border occur as a result, then using the anomalous identification result as case information, be stored in the case library.
Optionally, the method also includes:
After control system adapts to adjustment according to safety control strategy information, repeat to obtain next in electric melting magnesium furnace operating condition
Online data in predetermined period, according to the deterministic process of the online data, to determine the exception of the online data in step S1
Whether operating condition excludes, if so, terminating, otherwise, repetition obtains the security control decision of the online data in next predetermined period
The process of information.
Electric melting magnesium furnace unusual service condition identification of the invention and control method, can effectively go out according to electric melting magnesium furnace production process
Existing unusual service condition, when matched case information is not present, is used by searching whether there is matching case in case library
Bayesian network model carry out unusual service condition identification, and then according to anomalous identification as a result, formulate security control decision information and
The decision information is applied in control system, is improved the comprehensive utilization ratio of electric melting magnesium furnace operating condition Mineral Resource, is reduced energy consumption.
Detailed description of the invention
Figure 1A is the flow diagram of the identification of electric melting magnesium furnace unusual service condition and control method that one embodiment of the invention provides；
Figure 1B is the process schematic of unusual service condition identification and control method that one embodiment of the invention provides；
Fig. 2 is that control system unusual service condition is shown from the life cycle that slight extent becomes severity in the embodiment of the present invention
It is intended to；
Fig. 3 is the process schematic of current electric melting magnesium furnace technique；
Fig. 4 is the reasoning by cases process schematic proposed in the embodiment of the present invention；
Fig. 5 is the signal for the Bayesian Network Inference established in the embodiment of the present invention for electric melting magnesium furnace abnormal gas exhaust operating condition
Figure；
Fig. 6 is the contrast schematic diagram of abnormal gas exhaust industry and mining city result；
Fig. 7 is the current diagram of electric melting magnesium furnace normal exhaust operating condition；
Fig. 8 is the current diagram of electric melting magnesium furnace exhaust operating condition extremely；
Fig. 9 is the abnormal gas exhaust operating conditions effect diagram of method proposed by the present invention；
Figure 10 is the abnormal gas exhaust operating conditions effect diagram of conventional method.
Specific embodiment
In order to preferably explain the present invention, in order to understand, with reference to the accompanying drawing, by specific embodiment, to this hair
It is bright to be described in detail.
As shown in figure 3, smelting process of electro-fused magnesia furnace mainly includes charging, heating fusing, the operating conditions such as exhaust.It is produced by electric arc
Raw heat melts raw material, obtain final product.By setting different current setting values, current control system passes through tune
Whole electrode tracks the setting value of variation at a distance from molten bath, adjusts the size of electric arc, with energy needed for meeting different operating conditions.
In order to obtain higher economic benefit, it is necessary to keep good operating characteristics and production safety in the production of electric-melting magnesium.
Device involved in method in following embodiment includes: the identification of electric melting magnesium furnace unusual service condition and safety control system
(following abbreviation control systems), host computer, PLC, scene sensing pick-up structure.Wherein sensing pick-up structure in scene includes electric current inspection
Survey instrument, image detection instrument, sound detection instrument etc..Various detection instrument, detector are installed in electric melting magnesium furnace process-field
The signal of acquisition is sent to PLC by Profibus-DP bus by table, and acquisition signal is transmitted to by PLC by Ethernet timing
The data of receiving are transmitted to the identification of electric melting magnesium furnace unusual service condition and safety control system by position machine, host computer, and the system identification is abnormal
Operating condition, and security control decision is formulated for excluding unusual service condition.
The functions of above-mentioned apparatus are briefly described as follows:
1. scene sensing pick-up part: instrument is detected including current detecting, image detection, sound detection etc., by sensor
Composition is responsible for the acquisition and transmission of process data；
2. PLC: being responsible for the signal A/D of acquisition to convert, and transmit signals to host computer by Ethernet.
In the present embodiment, the CPU 414-2 of 400 series of Simens is can be used in the controller of PLC, which has
DP mouthfuls of connection distributed I/Os of Profibus；It is equipped with ethernet communication module for PLC, accesses plc data for host computer；PLC's
Controller and ethernet communication module are placed in the PLC rack in central control room.
3. host computer: collecting local plc data, send the identification of electric melting magnesium furnace unusual service condition and safety control system to.
I7 thinking computer can be selected in host computer the present embodiment, using WINDOW XP operating system.
4. the identification of electric melting magnesium furnace unusual service condition and safety control system identify unusual service condition, and formulate security control
Decision is for excluding unusual service condition.
The identification of electric melting magnesium furnace unusual service condition and safety control system are programmed soft on i7 thinking computer using C#2008
Part, the identification of electric melting magnesium furnace unusual service condition and security control algorithm use Matlab2010a programming software；
PLC and the signal of exception control system transmission software are using C#2008 programming software.
Detection instrument is installed in electric melting magnesium furnace process-field, detection instrument passes the signal of acquisition by Profibus-DP
It is sent in PLC, PLC timing sends acquisition signal to host computer by Ethernet, and received data are transmitted to electric smelting by host computer
The identification of magnesium furnace unusual service condition and safety control system, the system identification unusual service condition, and security control decision is formulated for excluding
It is abnormal.
In conjunction with shown in Figure 1A and Figure 1B, the electric melting magnesium furnace unusual service condition identification of the present embodiment and control method include:
The online data in predetermined period in S1, acquisition electric melting magnesium furnace operating condition.
In practical applications, processing can be filtered to the online data of acquisition, with obtain after filtration treatment in line number
According to.
For example, obtaining the online data of removal noise using the noise of filtering technique removal online data.
S2, using similarity mode strategy check in case library whether there is and the matched case information of online data.
For example, if the online data in step S1 is the online data after filtration treatment, filtration treatment can be used
Online data afterwards is matched with the case information in case library.
In addition, step S2 may particularly include:
Obtain in online data and case library between the variable of each case similarity (for example, by similarity criteria,
Determine similarity), judge whether the similarity is greater than preset threshold, if so, determining online data and the maximum for being greater than threshold value
The corresponding case matching of similarity；If similarity is no more than preset threshold, it is believed that case and online data are equal in case library
It mismatches.
Currently, Euclidean distance is a kind of mode for calculating similarity, and online data variable and offline is calculated in the present embodiment
Euclidean distance, that is, similarity between data variable.Obtain the similarity of each case in online data and case library.
Preset threshold in the present embodiment can be to first pass through the threshold value that expertise or those skilled in the art's knowledge determine in advance.
Particularly, the case library in the step is the various exceptions established previously according to the historical data of electric melting magnesium furnace operating condition
The case information of operating condition.
S3, if it exists, the identification result of current online data is provided according to matched case information, using identification result as
The anomalous identification result of current electric melting magnesium furnace operating condition.
Optionally, during specific implementation, this method may also include following step S4:
S4, according to anomalous identification as a result, determine equipment remaining life time；According to the remaining life time pre-established
Relationship between adjustment amount calculates adjustment amount, security control decision information is obtained, so that control system is according to security control plan
Slightly information adapts to adjustment；That is, security control decision information is applied to control system to be terminated if unusual service condition is excluded.It is no
Then, it repeats the above steps, obtains new unusual service condition regulation measure.
Wherein, above-mentioned remaining life time is electric melting magnesium furnace operating condition equipment from state when obtaining online data to complete
The time that can not work normally；
The adjustment amount is current setting value；Relationship between remaining life time and adjustment amount is what offline mode determined
Relationship.
Wherein, remaining life time is that electric melting magnesium furnace operating condition equipment can continue the time to run well, i.e., equipment is surplus
Remaining life time refers to the time that can not work normally completely since present state to equipment.
In the present embodiment, online data is token state, is changed over time；For electric melting magnesium furnace, adjustment amount is electric current
Setting value, it is an offline amount, and deciding is exactly to immobilize.In the present embodiment, abnormal is because of setting value
It is improper, so to change setting value.
Relationship between above-mentioned remaining life time and adjustment amount is offline just established, intensity of anomaly and residue life
Computation rule between the life time is also offline established；According to ' anomalous identification result ' and ' intensity of anomaly and remaining time
Relationship ', calculate remaining life time；According to ' remaining life time ' and ' pass between remaining life time and adjustment amount
System ', calculate adjustment amount.
In practical applications, it after control system adapts to adjustment according to safety control strategy information, repeats to obtain electric smelting
Online data in magnesium furnaceman's condition in next predetermined period, according to the deterministic process of the online data, to determine in step S1
Whether the unusual service condition of online data excludes, if so, terminating, otherwise, repeats the process for obtaining security control decision information.
Method is by acquiring the online data of current working in the present embodiment, and then phase has been checked whether in case library
Like case, similar cases obtain safety control then using the similar cases as identification result, and then according to identification result if it exists
Decision information processed answers the decision information of acquisition so that control system adapts to adjust according to the security control decision information
For there is the control system of unusual service condition (i.e. the identification of electric melting magnesium furnace unusual service condition and safety control system), if unusual service condition is arranged
It removes, then terminates, otherwise, re-recognize unusual service condition, obtain decision scheme.
Thus it can give some on the spot guidance to the production status of electric melting magnesium furnace, improve efficiency, reduce energy consumption, avoid economic damage
It loses.
In an optional implementation manner, as shown in Figure 1A, if matched case is not present in above-mentioned steps S2 in example library
Example information, at this point, following step S3a can be performed:
If matched case information is not present in S3a, case library, using Bayesian Network Inference model to described online
Data are analyzed, and identification result are obtained, using identification result as the anomalous identification result of current electric melting magnesium furnace operating condition；
And then executable above-mentioned steps S4 and etc..
That is, in step s 2, if the similarity of matched case is less than given threshold value, online data is drawn
It is divided into different intensity grades, and the online data after division intensity grade is input to Bayesian network unit as evidence,
Bayesian Network Inference is carried out, in the result that reasoning obtains, the intensity of anomaly for possessing maximum a posteriori probability is the knowledge of unusual service condition
Other result.
Further, the identification result that Bayesian network provides case new as one after confirming is stored in case library
In, realize case library supplement.
That is, the above method may also include unshowned step S5 in following Figure 1A during specific implementation:
If it is real that S5, the anomalous identification result obtained by Bayesian Network Inference model are determined as current electric melting magnesium furnace operating condition
Border occur as a result, then using the anomalous identification result as case information, be stored in the case library.
The unusual service condition that the present embodiment can effectively occur according to electric melting magnesium furnace production process, passes through reasoning by cases in case library
And Bayesian Network Inference model carry out unusual service condition identification, the concept predicted by remaining life, according to anomalous identification as a result,
Formulate security control decision.
In a particular application, before aforementioned step S2, the above method may also include following step S2a, such as Figure 1B
It is shown.
S2a, according to the historical data of electric melting magnesium furnace operating condition in preset time period, establish case library；
And historical data and priori knowledge according to electric melting magnesium furnace operating condition in preset time period, it establishes Bayesian network and pushes away
Manage model.
For example the step of establishing case library can include:
The information that electric melting magnesium furnace operating condition is abnormal in S2a1, collected offline preset time period；
S2a2, the information according to collection, determine the relationship in the feature and unusual service condition of unusual service condition between correlated variables,
Historical data is obtained, case library and Bayesian Network Inference model are established according to historical data.
Alternatively, in another optional implementation, the step of establishing case library can include:
The information that electric melting magnesium furnace operating condition is abnormal in S2a1 ', collected offline preset time period；
S2a2 ', the information according to collection, determine the pass in the feature and unusual service condition of unusual service condition between correlated variables
System obtains historical data, is filtered processing to historical data, establishes case library and shellfish according to the historical data after filtration treatment
This network reasoning model of leaf.
In the sub-step, to avoid influence of the noise to historical data, using in filtering technique removal historical data
Noise.
By the analysis of electric melting magnesium furnace unusual service condition in history, the pass between the feature and correlated variables of unusual service condition is determined
System.Based on the relationship found, abnormal expression recognition rule, such as；If " _ premise, _ conclusion ".Correlated variables is as rule
Premise then, conclusion of the degree of unusual service condition as case, finally, case library is established.
It illustrates, on-line data analysis is carried out using case-based reasoning in case library in the embodiment of the present invention.
Wherein, reasoning by cases is a kind of artificial intelligence approach, is mainly solved the problems, such as using the similar cases occurred in history new.Mesh
Before, reasoning by cases process may include four basic processes: retrieval is reused, corrects and is saved.Elder generation is needed when retrieving similar cases
Determine similarity calculating method, most common similar measurement mode is to calculate Euclidean distance.
In addition, the step of establishing Bayesian Network Inference model above-mentioned can include:
The information that electric melting magnesium furnace operating condition is abnormal in the first step, collected offline preset time period；
Second step, according to the relationship in priori knowledge and unusual service condition between correlated variables, determine Bayesian network
Node and structure；
Third step, according to the historical data of collection and the structure of determination, the parameter of Bayesian network is obtained, to set up
Bayesian Network Inference model.
Particularly, it when constructing Bayesian network parameters, needs to handle historical data, besides filtering, also
By correlated variables divided rank in all exception informations, the quantity and threshold value of divided rank are determined by expertise or trial-and-error method
It is fixed.According to the data calculating parameter for having divided grade.
Bayesian network in the present embodiment is a kind of expression of uncertain knowledge.The structure of Bayesian network can be with
The correlativity between variable is expressed, parameter indicates the degree of dependence between node variable.It is defeated as evidence when being collected into correlated variables
When entering to established Bayesian Network Inference model, the posterior probability of concern variable can be obtained by inference mechanism.
It is above-mentioned to establish case library using historical data, when new problem occurs, using similarity mode, sought in case library
Similar cases are looked for, when the similarity degree for the case being matched to is greater than given threshold value, provide abnormal knowledge using the case retrieved
Other result；When the similarity degree for the case being matched to is less than given threshold value, unusual service condition identification is carried out using Bayesian network,
Provide identification result.
For security control decision part, the concept of remaining life time is introduced, system spare life time is established and adjusts
Relationship between whole amount.After obtaining identification result, the remaining life time of electric melting magnesium furnace unusual service condition, Jin Erli are calculated first
With the relationship between remaining life time and adjustment amount, adjustment amount is obtained, to realize the security control of electric melting magnesium furnace.
The embodiment of the present invention carries out unusual service condition identification using reasoning by cases and Bayesian network, raw using the residue of equipment
The concept for ordering the time, provides security control scheme.
For the content for being better understood from the above method, carried out specifically below in conjunction with experimental result and technique/operating condition process
It is bright.
The technique of electric melting magnesium furnace is as shown in figure 3, capital equipment includes transformer, current loop, electrode lifting device, three-phase
Electrode and smelting furnace.Smelting process of electro-fused magnesia furnace mainly includes charging, heating fusing, the operating conditions such as exhaust.The heat generated by electric arc
Amount fusing raw material, obtain final product.By setting different current setting values, current control system adjusts electrode and melts
The distance in pond tracks the setting value of variation, adjusts the size of electric arc, with energy needed for meeting different operating conditions.Every 10-15
Minute, into furnace, filler is primary, and Operation mode cycle above carries out, until stove is filled.
Step 01: establishing case library and Bayesian Network Inference model
During electric-melting magnesium melting, a large amount of carbon dioxide gas can be generated, pressure is excessive to be caused to avoid in furnace
Molten slurry is splashed, and needs to adjust the setting value of electric current, current control system follow current setting value adjusts the position of electrode, makes electricity
Pole moves up and down, and makes to generate gap between electrode and raw material, carbon dioxide gas is smoothly discharged.But when the granularity of raw material becomes
When change, if current control system tracks original setting value, the gap between electrode and raw material can not make carbon dioxide gas
It is smoothly discharged, pressure is excessive in furnace, and molten slurry will splash with gas, generates abnormal gas exhaust operating condition.
When unusual service condition identification is exhausted, operator can pay close attention to the information of three aspects: current information, image letter
Breath and acoustic information.When abnormal gas exhaust operating condition occurs, current changing rate and current track error can change；Electrode and molten
Electric arc between pond is main sound-source signal, and when the state in furnace changes, the amplitude and frequency of arcing sounds can be sent out
Changing；When splashing, operator will be observed that high temperature molten slurry sprays outside furnace, therefore image information can be used as auxiliary
Variable recognizes unusual service condition.
Abnormal gas exhaust operating condition is divided into three kinds of degree: slight, moderate and severe.Based on expertise, in misevolution
Different phase have different information and play a major role.In slight abnormal gas exhaust, acoustic information plays a major role；In moderate
When abnormal, acoustic information and current information play a major role；In severe abnormality, current information and image information play main make
With.
Abnormal voice signal is divided into two kinds of degree: slight and severe.It is analyzed, is splashed by Wigner-Ville distribution
Characteristic frequency can be extracted, be 200Hz.When abnormal gas exhaust operating condition is slight and moderate, the amplitude of voice signal can be mentioned
It is high；When abnormal gas exhaust operating condition is severe, due to the release of energy, the amplitude of voice signal can be reduced.Therefore believe for sound
Number, select following characteristic variable: the short-time energy of splashing characteristic frequency and the amplitude of splashing characteristic frequency.
Abnormal current signal is divided into three kinds of degree: slight, moderate and severe.Select current track error and electric current
Change rate is its main feature variable.
Abnormal picture signal is divided into two kinds of degree: slight and severe.When abnormal gas exhaust operating condition is serious, fire door model
Brightness of image in enclosing can improve, and in image procossing, the variation of brightness is embodied with gray scale.In three primary colors of image
In component, red component accounts for main function.Therefore it is directed to picture signal, selects following characteristic variable: the variation of average gray,
The variation of average gray short-time energy, the variation of gray variance, the abundance of gray scale and the variation of red component, wherein gray scale is rich
Degree refers to the ratio more than normal picture average gray.All correlated characteristics are summarized in table 1 in abnormal gas exhaust operating condition.
1. abnormal gas exhaust feature of table and correlativity
To avoid influence of the noise to historical data, the noise in filtering technique removal historical data is used.Pass through exhaust
The feature of the unusual service condition of analysis and the determination of unusual service condition, establishes case library, and form is shown in Table 2.Before feature A-I is as rule
It mentions, result of the degree of abnormal gas exhaust operating condition as case.
The structure of 2. case library of table
To establish Bayesian Network Inference model, need all correlated variables divided ranks, the quantity of divided rank and
Threshold value is determined by expertise or trial-and-error method.By the analysis of expertise and abnormal gas exhaust operating condition, it can determine that exhaust is different
The node and structure of normal Bayesian network.Using data acquisition and pretreatment unit, the condition of Bayesian network can be obtained
Probability tables, the i.e. parameter of Bayesian network, finally, Bayesian network is established, and sees Fig. 5.
Step 2: online unusual service condition identification
Detailed process is as follows:
1) after online data is pretreated, similarity mode is carried out in case library.By similarity criteria, calculate similar
Degree, finds most like case.If the similarity of matched case is greater than given threshold value, abnormal work is carried out using the case
Condition identification.Pass through the size of expertise threshold value.
If 2) similarity of matched case is respectively less than given threshold value, online data is divided into different degree etc.
Grade, the online data for dividing intensity grade are input to Bayesian Network Inference model as evidence, carry out Bayesian Network Inference,
In the result that reasoning obtains, the intensity of anomaly for possessing maximum a posteriori probability is the recognition result of unusual service condition.
3) after obtaining the anomalous identification result of new problem, the serviceability needs of new problem are detected to judge it
Whether can be stored in case library as new case.Similarly, the identification result obtained by Bayesian Network Inference model
It is also required to just be stored in case library by verifying as new case.The detailed process of reasoning by cases is shown in Fig. 4.
The case where similarity of matched case is less than given threshold value is mainly explained below.By analyzing practical situation,
The event that exhaust operating condition may occur is summarized in table 3.
Table 3. is vented the event that operating condition may occur
Each event in table 3 includes 9 variables, and variables A-H is divided into three degree, uses number 1-3 table respectively
Show, meaning is respectively normal, slight abnormality and severely subnormal.Variable I is divided into four kinds of degree, is indicated respectively with number 1-4,
Meaning is respectively normal, slight abnormality, moderate abnormality and severely subnormal.By taking event 10 as an example, the state of feature A-B be it is normal,
The state of feature C-I is severely subnormal.The meaning of other events can be obtained with similar mode.
Event in table 3 will be used as evidence, obtain anomalous identification by the reasoning of Bayesian network as a result, as shown in table 4.
Recognition result of the table 4. for the event in table 3
In table 4, identification result 1-4 represents 4 states of exhaust operating condition: normal, mile abnormality, moderate abnormality and severe are different
Often, by taking event 10 as an example, identification result is severely subnormal.The meaning of the identification result of other events can use similar mode
It obtains.Event in table 3 is sorted by abnormal degree, and the identification result for table 4 is it is found that its identification result is to meet reality
Border unusual service condition recognizes experience.
Method to better illustrate the embodiment of the present invention carries out the scheme of proposition and traditional current information that is used only
Unusual service condition is known method for distinguishing and is compared, as a result as shown in Figure 6.In fig. 6 it can be seen that working as the degree of abnormal gas exhaust operating condition
When for slight and moderate, the scheme of proposition can obtain identification result, and traditional method only ability when intensity of anomaly is serious
Identification result can be obtained.
Step 3: formulating security control decision information.
For electric melting magnesium furnace abnormal gas exhaust, exception control scheme is in exhaust operating condition current setting value y originallyj(t)(j
=1,2,3) on the basis of, offset Δ y is providedj(t), current control system is allowed to track new current setting value yj' (t)=yj
(t)+Δyj(t) (j=1,2,3), wherein j represents three-phase electrode, is gradually recovered unusual service condition.The design of current offset values with
Abnormal degree is related with the remaining life time of system, when system remaining life time more in short-term, abnormal severity
Higher, the offset of electric current is bigger.So by the recognition result of unusual service condition, the remaining life time of computing system.Pass through
The relationship of the remaining life time and adjustment amount that pre-establish calculates the size of adjustment amount.When the abnormal identification result of system comes
When derived from reasoning by cases, remaining life time is calculated using following formula, the evolutionary process of intensity of anomaly is shown in Fig. 2.
In formula, R (t) represents remaining life time.τiRepresent the duration of i-th of abnormality.kiIt (t) is that state is held
The coefficient of continuous time, to express duration of the moment t in i-th of abnormality.I (t) represents the abnormal shape in t moment
State, IiRepresent the lower limit of state i.
When the abnormal identification result of system derives from Bayesian Network Inference model, following formula (3)-(5) are used
Calculate remaining life time
(3) in formula, R (t) indicate the weight of the stateful remaining life time of institute with.After P (X=i) represents i-th of state
Test probability.The remaining time r of each statei(t) it is calculated with formula (4).For the coefficient k of different conditionsi(t) it is calculated with formula (5).
After obtaining remaining life time, need to establish the relationship between remaining life time and adjustment amount.It will row
Adjustment amount when gas intensity of anomaly is slight, moderate and severe is rough to be set as WithWherein j is represented
Three-phase electrode.Following point is selected to carry out fit correlation Δ y=f (R (t)),
(τ1+τ2+τ3, 0) andWhereinThe maximum adjustment amount allowed for technique.These points are connected by straight line, constitutes and divides
The form of section function.
In this way, passing through anomalous identification as a result, calculating remaining life time.By between remaining life time and adjustment amount
Relationship, calculates the size of adjustment amount, that is, provides security control decision.
Normal exhaust operating condition and abnormal exhaust operating condition is set forth in Fig. 7 and Fig. 8.It can be seen from Fig. 8 due to
The setting value of electric current is not adjusted, carbon dioxide gas is not discharged from furnace smoothly, causes the fluctuation of electric current increasing.
Security control scheme is the offset for providing current setting value, so that current control system is tracked new current setting value different to exclude
Normal operating condition.
Step 4: implementation decision excludes unusual service condition
For the unusual service condition that Fig. 8 is generated, the security control decision that the present invention is formulated is applied to control system, and effect is such as
Shown in Fig. 9.It can be seen in figure 9 that current fluctuation exceeds normal range (NR), and this phenomenon continues to hold in the 7th sampled point
It is continuous.After security control decision implement, in the 13rd sampled point, current fluctuation decline, about in the 19th sampled point, abnormal work
Condition is excluded.In order to embody superiority of the invention, the present invention and traditional side that current information is used only and carries out security decision
Method is compared, and the control effect of conventional method is as shown in Figure 10.From fig. 10 it can be seen that in the 7th sampled point current fluctuation
Beyond normal range (NR), and this phenomenon continues for, until the 20th sampled point, when intensity of anomaly becomes serious, tradition side
Method just provides security decision, and system is gradually recovered normally later.
By above example, the method for showing the embodiment of the present invention can identify unusual service condition, and according to identification
Unusual service condition formulate effective safety measure, measure can effectively be such that unusual service condition reverts to normally after implementing, and with
Tradition be used only current information carry out unusual service condition identification compared with the method for security control, method proposed by the present invention more added with
It imitates and there is better performance.Further, the above method reduces energy consumption, subtracts for the comprehensive utilization ratio of raising mineral resources
Few environmental pollution, promotes safety in production, there is great meaning.
The technical principle of the invention is described above in combination with a specific embodiment, these descriptions are intended merely to explain of the invention
Principle shall not be construed in any way as a limitation of the scope of protection of the invention.Based on explaining herein, those skilled in the art
It can associate with other specific embodiments of the invention without creative labor, these modes fall within this hair
Within bright protection scope.
Claims (9)
1. a kind of electric melting magnesium furnace unusual service condition identification and control method characterized by comprising
The online data in predetermined period in S1, acquisition electric melting magnesium furnace operating condition；
S2, using similarity mode strategy check in case library whether there is and the matched case information of online data；
S3, if it exists, the identification result of current online data is provided according to matched case information, using identification result as current
The anomalous identification result of electric melting magnesium furnace operating condition；
Wherein, case library is the case information for the various unusual service conditions established previously according to the historical data of electric melting magnesium furnace operating condition；
If matched case information is not present in S3a, case library, using Bayesian Network Inference model to the online data
It is analyzed, identification result is obtained, using identification result as the anomalous identification result of current electric melting magnesium furnace operating condition.
2. the method according to claim 1, wherein before step S2, the method also includes:
S2a, according to the historical data of electric melting magnesium furnace operating condition in preset time period, establish case library；
And historical data and priori knowledge according to electric melting magnesium furnace operating condition in preset time period, establish Bayesian Network Inference mould
Type.
3. according to the method described in claim 2, it is characterized in that, step S2a includes:
The information that electric melting magnesium furnace operating condition is abnormal in collected offline preset time period；
According to the information of collection, the relationship in the feature and unusual service condition of unusual service condition between correlated variables is determined, obtain history
Data establish case library and Bayesian Network Inference model according to historical data；
Alternatively,
The information that electric melting magnesium furnace operating condition is abnormal in collected offline preset time period；
According to the information of collection, the relationship in the feature and unusual service condition of unusual service condition between correlated variables is determined, obtain history
Data are filtered processing to historical data, establish case library according to the historical data after filtration treatment and Bayesian network pushes away
Manage model.
4. according to the method described in claim 2, it is characterized in that, the S2a includes:
The information that electric melting magnesium furnace operating condition is abnormal in collected offline preset time period；
According to the relationship in priori knowledge and unusual service condition between correlated variables, the node and structure of Bayesian network are determined；
According to the historical data of collection and the structure of determination, the parameter of Bayesian network is obtained, to set up Bayesian network
Inference pattern.
5. the method according to claim 1, wherein the step S1 further include:
Processing is filtered to the online data of acquisition, to obtain the online data after filtration treatment；
Correspondingly, it is matched using the online data after filtration treatment with the case information in case library in step S2.
6. according to any method of claim 2 to 5, which is characterized in that the method also includes:
S4, according to anomalous identification as a result, determine equipment remaining life time；
According to the relationship between the remaining life time pre-established and adjustment amount, adjustment amount is calculated, obtains security control decision
Information, so that control system adapts to adjust according to safety control strategy information；
Wherein, remaining life time is electric melting magnesium furnace operating condition equipment from state when obtaining online data to completely can not normal work
The time of work；
The adjustment amount is current setting value；Relationship between remaining life time and adjustment amount is the pass that offline mode determines
System.
7. according to the method described in claim 6, it is characterized in that, the step S2 includes:
The similarity in online data and case library between the variable of each case is obtained, it is default to judge whether the similarity is greater than
Threshold value, if so, determining that online data case corresponding with the maximum similarity of threshold value is greater than matches.
8. the method according to claim 1, wherein the method also includes:
If S5, the anomalous identification result obtained by Bayesian Network Inference model are determined as the practical hair of current electric melting magnesium furnace operating condition
It is raw as a result, being stored in the case library then using the anomalous identification result as case information.
9. according to the method described in claim 6, it is characterized in that, the step S4 includes:
If anomalous identification is the result is that matched by case library lookup, the following formula one of use calculate remaining life time R
(t)；
Formula one:
Wherein,R (t) represents remaining life time, τiRepresent the duration of i-th of abnormality, ki
(t) be state duration coefficient, to express duration of the moment t in i-th of abnormality, I (t) represent in t
The abnormality at moment, IiRepresent the lower limit of state i；
Alternatively,
If anomalous identification calculates remaining life using following formula two the result is that by the determination of Bayesian Network Inference model
Time；
Formula two:
Wherein,
R (t) indicate the weight of the stateful remaining life time of institute with.P (X=i) represents the posterior probability of i-th of state, ri(t)
Indicate the remaining time of each state, ki(t) indicate that the coefficient for different conditions, I (t) represent the abnormality in t moment,
IiRepresent the lower limit of state i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710324622.3A CN106959662B (en) | 2017-05-10 | 2017-05-10 | A kind of identification of electric melting magnesium furnace unusual service condition and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710324622.3A CN106959662B (en) | 2017-05-10 | 2017-05-10 | A kind of identification of electric melting magnesium furnace unusual service condition and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106959662A CN106959662A (en) | 2017-07-18 |
| CN106959662B true CN106959662B (en) | 2019-03-08 |
Family
ID=59481878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710324622.3A Active CN106959662B (en) | 2017-05-10 | 2017-05-10 | A kind of identification of electric melting magnesium furnace unusual service condition and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106959662B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960256A (en) * | 2018-06-28 | 2018-12-07 | 东软集团股份有限公司 | A kind of determination method, device and equipment of components damage degree |
| CN111385106B (en) * | 2018-12-11 | 2022-03-01 | 华为技术有限公司 | Method, device and equipment for identifying fault root cause |
| CN110059359A (en) * | 2019-03-21 | 2019-07-26 | 江苏东方国信工业互联网有限公司 | System and method for controlling furnace body process based on big data analysis |
| CN111598137A (en) * | 2020-04-24 | 2020-08-28 | 北京金山云网络技术有限公司 | Method and device for providing reasoning service and electronic equipment |
| CN113064390B (en) * | 2021-03-17 | 2022-03-01 | 国网辽宁省电力有限公司辽阳供电公司 | Case reasoning-based active warning method for pollutant emission of cement production enterprise |
| CN113237332B (en) * | 2021-04-14 | 2022-02-25 | 东北大学 | Method for identifying working condition of electro-fused magnesia furnace |
| CN113705601A (en) * | 2021-05-21 | 2021-11-26 | 国网辽宁省电力有限公司鞍山供电公司 | Method for identifying running state of electric smelting magnesium furnace based on random forest |
| CN115354144B (en) * | 2022-08-29 | 2024-01-30 | 湖南华菱涟源钢铁有限公司 | Roller quenching process operation parameter setting method based on case matching |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102637019B (en) * | 2011-02-10 | 2014-04-02 | 武汉科技大学 | Intelligent integrated fault diagnosis method and device in industrial production process |
| CN102765643B (en) * | 2012-05-31 | 2015-06-17 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
| CN104298225B (en) * | 2014-09-25 | 2017-07-04 | 中国石油化工股份有限公司 | Chemical process unusual service condition causality inference pattern is modeled and graphical representation method |
-
2017
- 2017-05-10 CN CN201710324622.3A patent/CN106959662B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106959662A (en) | 2017-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106959662B (en) | A kind of identification of electric melting magnesium furnace unusual service condition and control method | |
| US10027699B2 (en) | Production process knowledge-based intrusion detection for industrial control systems | |
| CN108197011B (en) | Single-index prediction and early warning method based on artificial intelligence big data platform | |
| CN108345723A (en) | A kind of Diagnostic system of motor fault and method based on decision tree and Bayesian network | |
| Li et al. | Abnormal condition identification and safe control scheme for the electro-fused magnesia smelting process | |
| Naso et al. | A fuzzy-logic based optical sensor for online weld defect-detection | |
| Sheikh et al. | Cyber attack and fault identification of hvac system in building management systems | |
| CN108803528A (en) | Process industry system prediction model based on multivariate correlation and time lag | |
| CN109685283A (en) | A kind of mineral hot furnace operating condition prediction technique based on confidence rule base reasoning | |
| CN108265157A (en) | Intelligent arc furnace steelmaking system | |
| CN112424702B (en) | Process controller and method and system thereof | |
| CN115358626A (en) | Safety inspection early warning system for mineral processing production equipment | |
| CN110266735B (en) | Industrial communication protocol white list access control method based on time sequence | |
| CN112508316B (en) | Self-adaptive abnormality determination method and device in real-time abnormality detection system | |
| CN112731827B (en) | Monitoring system for intelligent sensor for power equipment | |
| CN103995515A (en) | Method for detecting operation faults of electro-fused magnesia furnace based on public subspace separation | |
| CN115423134B (en) | Heavy film inflation film manufacturing machine operation detecting system based on artificial intelligence | |
| CN117609861A (en) | BP neural network algorithm and temperature measurement system capable of being used for temperature prediction of electrical equipment of transformer substation | |
| CN112240267B (en) | Fan monitoring method based on wind speed correlation and wind power curve | |
| CN113537658A (en) | Equipment risk assessment and maintenance system and method | |
| CN207380871U (en) | A kind of fired power generating unit Realtime Alerts monitoring system based on system subdivision | |
| CN110264726A (en) | Traffic control method and traffic control system | |
| Li et al. | Abnormal condition identification for the electro-fused magnesia smelting process | |
| CN114518732A (en) | Furnace control system of DCS submerged arc furnace | |
| CN112083693B (en) | Paint production line information management system based on internet of things technology |
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 |