CN104019661B - Rotary kiln control system - Google Patents
Rotary kiln control system Download PDFInfo
- Publication number
- CN104019661B CN104019661B CN201410225353.1A CN201410225353A CN104019661B CN 104019661 B CN104019661 B CN 104019661B CN 201410225353 A CN201410225353 A CN 201410225353A CN 104019661 B CN104019661 B CN 104019661B
- Authority
- CN
- China
- Prior art keywords
- rotary kiln
- control
- controlled variable
- quentity controlled
- controlled quentity
- 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
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000003745 diagnosis Methods 0.000 claims abstract description 37
- 238000005457 optimization Methods 0.000 claims description 38
- 238000005516 engineering process Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 15
- 238000003909 pattern recognition Methods 0.000 claims description 12
- 238000002485 combustion reaction Methods 0.000 claims description 10
- 230000008878 coupling Effects 0.000 claims description 10
- 238000010168 coupling process Methods 0.000 claims description 10
- 238000005859 coupling reaction Methods 0.000 claims description 10
- 238000005265 energy consumption Methods 0.000 claims description 6
- 238000005096 rolling process Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000012913 prioritisation Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 15
- 238000001354 calcination Methods 0.000 abstract description 9
- 238000011217 control strategy Methods 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 239000000463 material Substances 0.000 description 9
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 8
- 239000001301 oxygen Substances 0.000 description 8
- 229910052760 oxygen Inorganic materials 0.000 description 8
- 230000001276 controlling effect Effects 0.000 description 6
- 238000012706 support-vector machine Methods 0.000 description 6
- 239000011248 coating agent Substances 0.000 description 5
- 238000000576 coating method Methods 0.000 description 5
- 230000007423 decrease Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000007789 gas Substances 0.000 description 4
- 230000000630 rising effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007935 neutral effect Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000470 constituent Substances 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 235000007926 Craterellus fallax Nutrition 0.000 description 1
- 240000007175 Datura inoxia Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- -1 metallurgy Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000002006 petroleum coke Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000011343 solid material Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000008093 supporting effect Effects 0.000 description 1
Abstract
The invention relates to the technical field of automatic control, in particular to a rotary kiln control system. Aiming at the problems that the existing automatic control schemes of the rotary kiln in the prior art are mostly simple loop control strategies which are mutually independent and the accurate control of the rotary kiln cannot be realized, the invention realizes the multidimensional control of the rotary kiln operation state which integrates multiple control variables and multiple control means by a three-level control structure comprising a three-level diagnosis decision subsystem, and can control a plurality of process parameters of the rotary kiln on the optimal control point by utilizing a plurality of control variables of the rotary kiln, thereby being beneficial to the improvement of the quality and the yield of the rotary kiln calcination products and the reliability, the safety and the effectiveness of the rotary kiln operation.
Description
Technical field
The present invention relates to automatic control technology field, be specifically related to a kind of rotary kiln.
Background technology
In many production industries such as building materials, metallurgy, chemical industry, environmental protection, widely using rotary kiln to solid material carries out machinery, physical or chemical treatment, becomes the nucleus equipment that corresponding enterprise produces.
Rotary kiln is a Great inertia, large time delay, there is the control object of time-varying parameter, even the simplest rotary kiln, the motion process of material in kiln is also nonlinearity, complexity, it not only relates to complicated heat transfer, mechanism of mass transfer, also closely related with the material characteristic of material in kiln.Key process parameter is difficult to measurement accurately and timely, the major part of kiln structure is in turn state, detecting instrument can only be arranged on the two ends of kiln usually, causes the measurement that key process parameter is difficult to accurately and timely, is therefore difficult to quantitative description and closes thermal technology state in kiln.
The ambiguity of this parameter information, makes the difficulty of modeling very large, causes traditional control strategy to be difficult to carry out.Control device variation, between each control device, coupling phenomenon is serious.Its control device comprise rotary kiln rotating speed, feeding coal, negative pressure and two, tertiary air quantity five kinds of regulating measures.Regulating measure is horn of plenty comparatively, is difficult to find regulating measure preferably fitting method simultaneously.The automatic control scheme of the rotary kiln existed at present mostly is separate simple circuit control strategy, and does not realize the accurate control to rotary kiln.
Therefore, existing Rotary Kiln Control scheme can not utilize multiple control variables of rotary kiln well by multiple process parameter controls of rotary kiln on optimum controlling point, thus the Quality and yield of calcined by rotary kiln product, and the reliability of rotary kiln running, security and validity are all restricted.
Summary of the invention
(1) technical problem solved
For the deficiencies in the prior art, the invention provides a kind of rotary kiln, multiple control variables of rotary kiln can be utilized by multiple process parameter controls of rotary kiln on optimum controlling point, thus be conducive to the Quality and yield of calcined by rotary kiln product, and the reliability of rotary kiln running, security and validity raising.
(2) technical scheme
For realizing above object, the invention provides a kind of rotary kiln, comprising:
One-level rotary kiln detection subsystem, for detecting the parameter in rotary kiln combustion process, and is sent to Two-stage control subsystem and three grades of diagnosis decision-making subsystems by described parameter;
Two-stage control subsystem, controls rotary kiln for the controlled quentity controlled variable after the reasoning optimizations that the described parameter that sends according to one-level rotary kiln detection subsystem and three grades of diagnosis decision-making subsystems send;
Three grades of diagnosis decision-making subsystems, carry out reasoning and optimization for the described parameter sent one-level rotary kiln detection subsystem, obtain the controlled quentity controlled variable after reasoning optimization, and the controlled quentity controlled variable after described reasoning optimization is sent to Two-stage control subsystem.
Wherein, described three grades of diagnosis decision-making subsystems comprise:
Pattern recognition module, sets up the knowledge base and control rule sets that describe relation between rotary kiln technology parameter and running status according to the historical data of calcined by rotary kiln state for Land use models recognition technology;
Message processing module, mates for the information described parameter received and described knowledge base and control law concentrated, and is optimized controlled quentity controlled variable according to the target operation state preset, the controlled quentity controlled variable after being optimized;
Whether reasoning and judging module, can match with target operation state for the controlled quentity controlled variable after reasoning and judging optimization, if do not mate, is then again optimized till coupling controlled quentity controlled variable, and to refresh one's knowledge storehouse according to prioritization scheme during coupling.
Controlled quentity controlled variable delivery module, for being sent to Two-stage control subsystem by the controlled quentity controlled variable after reasoning optimization.
Wherein, described pattern recognition module comprises:
History data set sets up unit, for obtaining in Preset Time the historical data characterizing calcined by rotary kiln state, forms history data set;
Dynamic data searches unit, for concentrating the dynamic data searched and describe relation between each technological parameter and running status in described historical data;
Dynamic data division unit, divides described dynamic data for adopting mode identification technology;
Dynamic data demarcates unit, for using sequence number to demarcate ready-portioned dynamic data, and sets up the corresponding relation of itself and rotary kiln running state performance indications;
Construction of knowledge base unit, for building knowledge base and the control rule sets of relation between described description rotary kiln technology parameter and running status according to described corresponding relation.
Preferably, also comprise between the pattern recognition module in described three grades of diagnosis decision-making subsystems and message processing module:
Hand automatic switching module, for switching automatic operation mode and the manual work pattern of three grades of diagnosis decision-making subsystems according to user instruction, by message processing module, controlled quentity controlled variable is optimized under described automatic mode, by external user input, controlled quentity controlled variable is optimized under described manual work pattern.
Wherein, described hand automatic switching module comprises:
Alarm unit, reports to the police when cannot mate target operation state for the controlled quentity controlled variable after reasoning and judging optimization, and switches to manual work pattern after user confirms.
Preferably, described three grades of diagnosis decision-making subsystems also comprise:
Artificial experience load-on module, for the described knowledge base of artificial experience and control rule sets being added into existing knowledge base by user and control law is concentrated, and is applied to the optimization method of artificial experience in described message processing module by user.
Preferably, described three grades of diagnosis decision-making subsystems also comprise:
User interactive module, for receiving the operational order of user, and shows running status and the state of a control information of current rotary kiln to user.
Wherein, described message processing module comprises:
Rolling optimization unit, for the optimum results based on the last time, adopting multidimensional minimum searching method to find, combustion efficiency is best and control point that energy consumption is minimum, and is optimized controlled quentity controlled variable rotary kiln clamper is run on this control point.
Wherein, described rotary kiln adopts the communication mode of industrial bus or Ethernet.
(3) beneficial effect
The present invention at least has following beneficial effect:
The present invention, mainly on the structure of original basic automatization, constructs and carries out the three-stage control system of optimization further for comprehensive various control variable and various control means to original controlled quentity controlled variable.This system is owing to combining the Changing Pattern of each control variables, therefore the simple circuit control strategy of comparing separate has better control effects, namely can utilize multiple control variables of rotary kiln by multiple process parameter controls of rotary kiln on optimum controlling point, thus be conducive to the Quality and yield of calcined by rotary kiln product, and improve the raising of the reliability of rotary kiln running, security and validity.
Certainly, arbitrary product of the present invention is implemented or method might not need to reach above-described all advantages simultaneously.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, simply introduce doing one to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is structure and the workflow schematic diagram of rotary kiln;
Fig. 2 is the structural representation of the rotary kiln in one embodiment of the invention;
Fig. 3 is the structure chart of three grades of diagnosis decision-making subsystems in one embodiment of the invention;
Fig. 4 is the structural representation of rotary kiln pattern-recognition in one embodiment of the invention;
Fig. 5 is the schematic diagram of multidimensional minimum searching method in one embodiment of the invention;
Fig. 6 is the detailed functions configuration diagram of preferred rotary kiln in one embodiment of the invention.
Detailed description of the invention
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Embodiment 1
The embodiment of the present invention proposes a kind of rotary kiln, is its control object clear and definite, first does simple introduction to the operating characteristic of rotary kiln below.
As shown in Figure 1, rotary kiln be obliquely installed and the position of kiln tail 101 higher than kiln hood 105, calcining materials sends into kiln tail 101 by conveyers such as conveyer belts, kiln rotating speed motor 108 controls the rotation of rotary kiln, material enters preheating zone 102 under the rotation of rotary kiln due to Action of Gravity Field, and the rotating speed of rotary kiln is faster, the speed that material advances is also faster; The rotating speed of rotary kiln is slower in contrast, and the speed that material advances is also slower.The material entering rotary kiln is more, and the combustible fugitive constituent provided is more, and then needs overfire air fan and tertiary air machine to send into more air to burn to help fugitive constituent.Overfire air fan 106 is blown to kiln tail 101 direction of rotary kiln, tertiary air machine 107 is blown to kiln hood 105 direction of rotary kiln, control overfire air fan 106 and tertiary air machine 107 is needed to be supplied to the ratio of the air quantity of burning zone 103, thus make burning zone 103 be stabilized between Secondary Air slip ring 109 and tertiary air slip ring 110, to control the length and location of burning zone 103.Kiln rotating speed motor 108 can control the rotating speed of rotary kiln, thus controls the time of staying of petroleum coke in rotary kiln, and then controls the temperature of burning zone 103.Move on through the material of calcining and enter salband 104 and cool, then enter kiln hood 105, and finally enter cooling chamber 111 and cool.Further, be also provided with air-introduced machine 112 at kiln tail 101 rear, air-introduced machine 112 for forming negative pressure in rotary kiln, to control the position of burning zone 104 further.
See Fig. 2, this rotary kiln comprises:
One-level rotary kiln detection subsystem 201, for detecting the parameter in rotary kiln combustion process, and is sent to Two-stage control subsystem 202 and three grades of diagnosis decision-making subsystems 203 by described parameter;
Two-stage control subsystem 202, controls rotary kiln for the controlled quentity controlled variable after the reasoning optimizations that the described parameter that sends according to one-level rotary kiln detection subsystem 201 and three grades of diagnosis decision-making subsystems 203 send;
Three grades of diagnosis decision-making subsystems 203, carry out reasoning and optimization for the described parameter sent one-level rotary kiln detection subsystem 201, obtain the controlled quentity controlled variable after reasoning optimization, and the controlled quentity controlled variable after described reasoning optimization is sent to Two-stage control subsystem 202.
Specifically, parameter in one-level rotary kiln detection subsystem 201 pairs of rotary kiln combustion processes that it is made up of various data sampling sensor detects, these parameters comprise: expansion chamber temperature, expansion chamber pressure, temperature of kiln head, kiln hood pressure, kiln end temperature, kiln tail pressure, calcining belt temperature, cooler dump temperature, remaining oxygen, burning zone kliner coating temperature, burning zone length, burning zone position etc., thus rotary kiln detection subsystem 201 can comprise as infrared kiln swept-volume device accordingly, oxygen content analytical equipment, kiln displacement and kiln body deformability checkout gear, two-tertiary air Wind volume detector, kiln speed detector, air-introduced machine speed detector, temperature-versus-position-the device for detecting length of burning zone, the temperature of kiln hood-kiln tail-expansion chamber and pressure-detecting device etc.Parameter in the rotary kiln combustion process detected is sent to Two-stage control subsystem 202 and three grades of diagnosis decision-making subsystems 203 by one-level rotary kiln detection subsystem 201, three grades of diagnosis decision-making subsystems 203, described parameter for sending one-level rotary kiln detection subsystem 201 carries out reasoning and optimization, obtain the controlled quentity controlled variable after reasoning optimization, and the controlled quentity controlled variable after described reasoning optimization is sent to Two-stage control subsystem 202, Two-stage control subsystem 202, three base level loop (remaining oxygen control loops of Two-stage control subsystem 202 are realized for the controlled quentity controlled variable after the reasoning optimizations that the described parameter that sends according to one-level rotary kiln detection subsystem 201 and three grades of diagnosis decision-making subsystems 203 send, kiln tail vacuum cavitations loop, burning zone mean temperature control loop) real-time control.Two-stage control subsystem 202 can be made up of any existing rotary kiln automaton.Thus can by multiple process parameter controls of rotary kiln on optimum controlling point, thus improve the Quality and yield of calcined by rotary kiln product, and promote the reliability of rotary kiln running, security and validity.
Described three grades of diagnosis decision-making subsystems 203 parameter can carry out fault diagnosis, fuzzy reasoning and Optimization about control parameter by expert system according to the one-level rotary kiln detection subsystem 201 received, and using given as three base level loop inputs of Two-stage control subsystem 202 for the controlled quentity controlled variable after reasoning is optimized.Two-stage control subsystem 202 then can receive remaining oxygen, kiln tail negative pressure after data processing and inductive decision in three grades of diagnosis decision-making subsystems 203 accordingly, burning zone mean temperature three controlled quentity controlled variables are given and control according to this.
Embodiment 2
The embodiment of the present invention proposes a kind of preferred three grades of diagnosis decision-making subsystems, and it comprises:
Pattern recognition module, sets up the knowledge base and control rule sets that describe relation between rotary kiln technology parameter and running status according to the historical data of calcined by rotary kiln state for Land use models recognition technology;
Message processing module, mates for the information described parameter received and described knowledge base and control law concentrated, and is optimized controlled quentity controlled variable according to the target operation state preset, the controlled quentity controlled variable after being optimized;
Whether reasoning and judging module, can match with target operation state for the controlled quentity controlled variable after reasoning and judging optimization, if do not mate, is then again optimized till coupling controlled quentity controlled variable, and to refresh one's knowledge storehouse according to prioritization scheme during coupling.
Controlled quentity controlled variable delivery module, for being sent to Two-stage control subsystem by the controlled quentity controlled variable after reasoning optimization.
That is, as the core controlling organization of rotary kiln, the main function of three grades of diagnosis decision-making subsystems is exactly to set up the corresponding relation of multi-control variable and multi-control method, is optimized controlled quentity controlled variable by a kind of control method considering the overall situation.And the embodiment of the present invention is in the face of this problem, have employed the serial of methods based on mode identification technology, namely first build knowledge base for describing relation between rotary kiln technology parameter and running status and control rule sets with historical data, find the Optimal Control means from current operating state to target operation state more according to this, thus determine how to optimize each controlled quentity controlled variable.
Visible, such method is the equal of play the method for computer intelligence identification mode of operation with a kind of structure construction of similar artificial neural network, thus the implementation of these three grades diagnosis decision-making subsystems and flow process can be carried out with reference to the implementation in this field.
For further illustrating technique scheme, exemplarily show rotary kiln proposed by the invention by with a kind of more preferred three grades of diagnosis decision-making subsystems below.
Embodiment 3
The embodiment of the present invention proposes a kind of preferred pattern recognition module, and as shown in Figure 3, described pattern recognition module comprises:
History data set sets up unit 301, for obtaining in Preset Time the historical data characterizing calcined by rotary kiln state, forms history data set.The related data of calcined by rotary kiln state is all stored into calcination process in rotary kiln database, when setting up history data set, the historical data that 2-3 month characterizes calcined by rotary kiln state is obtained from this calcination process in rotary kiln database, comprising: expansion chamber temperature, expansion chamber pressure, temperature of kiln head, kiln hood pressure, kiln end temperature, kiln tail pressure, calcining belt temperature, cooler dump temperature, remaining oxygen, burning zone kliner coating temperature, burning zone length, burning zone position, negative pressure, remaining oxygen, CO content, other tail gas content, grog real density, carbonaceous scaling loss index etc.
Dynamic data searches unit 302, for concentrating the dynamic data searched and describe relation between each technological parameter and running status in described historical data.Here specifically according to a certain parameter on the particular point in time of variation tendency, observe the variation tendency of burning zone three elements (temperature, position, length), thus find out have rising, decline, first rise decline afterwards, the dynamic data of the trend such as rising afterwards, steady that first declines.
Dynamic data division unit 303, divides described dynamic data for adopting mode identification technology.Namely according to rising, decline, first rise decline afterwards, the trend such as to rise afterwards, steady that first declines divides the dynamic data found out in step S302.Mode identification method can be adopted to divide dynamic data.Here, adopt adaptive resonance theory neutral net II and supporting vector machine mixed intelligent mode identification method to divide dynamic data, it will be understood by those skilled in the art that and other modes also can be adopted to divide data.In the present embodiment, the method dividing dynamic data comprises the steps:
Step S303a: get the kth pattern that dynamic data is concentrated
l and n represents group number and the dimension of sample respectively, and desired output vector is: Z
k=(z
1, z
2..., z
m), namely input pattern k belongs to the i-th class, and m represents classification number.
Step S303b: according to the constraints of SVMs (SVM) with solve formula formula and obtain i-th grader optimal solution, and bring kernel function computing formula into, obtain the output of i-th grader during input amendment Xk, obtain q two-value grader Output rusults, thus complete the operation of SVMs.
Step S303c: enter the operation of ART-2 neutral net, initializes feedforward connection weight and the feedback link power of ART-2 network, by the Output rusults of support vector machine classifier input ART-2 network, each neuron weighted input of computing network output layer and.
Step S303d: the neuronic feedback link weight vector according to winning judges whether that mating given standard limits all possible class, if coupling, classification learning success is described, produce resonance, enter the study adjustment of the amplitude of the long-term memory pattern of network and Pattern Class typical module, if enter into step S303e; If entirely do not met, enter into step S303f.
Step S303e: revise forward connection power and feedback link power.
Step S303f: the class as selected does not reach similarity requirement, then carry out network reset, abandon this Pattern Class, enter into step S303d and find other classification; If all possible classification is not all mated, enter into step S303g.
Step S303g: open up new Pattern Class or abandon this sample.
Complete the division to dynamic data by above-mentioned steps S303a to S303g, wherein relate generally to adaptive resonance theory neutral net ART-2 and SVMs (SVM) hybrid intelligent mode identification method.
Dynamic data demarcates unit 304, for using sequence number to demarcate ready-portioned dynamic data, and sets up the corresponding relation of itself and rotary kiln running state performance indications.Namely by sequence number, ready-portioned dynamic data is demarcated, such as the dynamic data with ascendant trend is demarcated as 1, the dynamic data with downward trend is demarcated as 2, the dynamic data with rear downward trend of first rising is demarcated as 3, by have first decline after the dynamic data of ascendant trend be demarcated as 4, the dynamic data with moderate tone is demarcated as 5 etc.And after carrying out technique demarcation according to classification results, according to the data phenomenon being manually aided with mode identification method classification, to its technique label in addition, and determine its name variable in expert system, by corresponding with the performance indications of rotary kiln for the data phenomenon of classification, and the feature that agriculture products characterizes.
Wherein, the performance indications that rotary kiln normally runs comprise: expansion chamber temperature, expansion chamber pressure, temperature of kiln head, kiln hood pressure, kiln end temperature, kiln tail pressure, calcining belt temperature, cooler dump temperature, remaining oxygen, burning zone kliner coating temperature, burning zone length, burning zone position, negative pressure, remaining oxygen, CO content, other tail gas content, who knows real density, carbonaceous scaling loss index.In order to better reduce the specific energy consumption of rotary kiln, set up two here, tertiary air blower fan, rotary kiln Dayao drive motors and cooling kiln drive motors amount to 6 motor total power consumption functions, as the performance indications of energy ezpenditure simultaneously.
Construction of knowledge base unit 305, for building knowledge base and the control rule sets of relation between described description rotary kiln technology parameter and running status according to described corresponding relation, namely characterize rotary kiln index to build required knowledge base by characteristic parameter feature, and establish corresponding control rule sets.
Visible, based on mode identification technology, above-mentioned pattern recognition module can be analyzed the carrying out of rotary kiln and classify, here, under the prerequisite that raw material feeding capacity is basicly stable to the identification of rotary kiln operating mode, rotary system main technologic parameters is identified, the overall operation state that the change in conjunction with secondary technological parameter obtains.Find by analyzing, cylindrical shell scanning device can reflect the situation of kliner coating in rotary kiln; Kiln end temperature and kiln tail negative pressure can reflect the heating power distribution situation in rotary kiln; Temperature of kiln head, negative pressure reflect whole kiln system state of the art.Therefore, here choose the major parameters such as cylindrical shell scanning temperature, kiln end temperature, kiln tail negative pressure, temperature of kiln head, kiln hood negative pressure and be aided with other minor parameters such as expansion chamber temperature, kiln exhaust gas Body components, classification and identification algorithm is used detected parameters to be carried out to the identification of fault detect and trend type, and the information fusion of multisensor is realized with this, the information fusion identification structure of concrete rotary kiln operating mode is as shown in Figure 4.
By detected parameters such as kliner coating temperature, kiln end temperature, system negative pressure, exhaust gas concentrations after Classification and Identification, obtain their Long-term change trend type, combine the permutation and combination obtaining their polymeric type, different permutation and combination is formulated to the identification number of different operating mode, make correct operating mode classification according to the result identified to operating mode identification number to explain, improve operating mode's switch rule-based knowledge base, thus realize the accurate identification to rotary kiln operating mode.
Embodiment 4
The embodiment of the present invention proposes a kind of preferred rotary kiln, between the message processing module of reasoning and judging module in wherein three grades diagnosis decision-making subsystems in described three grades of diagnosis decision-making subsystems and described controlled quentity controlled variable delivery module, whether can match with target operation state for the controlled quentity controlled variable after reasoning and judging optimization, if do not mate, then again controlled quentity controlled variable is optimized till coupling, and refreshes one's knowledge storehouse according to prioritization scheme during coupling.Specifically, be exactly according to the reasoning results, whether judging and deducing result mates with actual Adjusted Option, if do not mated, if that is the hit rate of rule is lower than the effect threshold value of setting, then repeats above step, again choose the regulation measure of rotary kiln, until the hit rate of rule is more than or equal to the effect threshold value of setting, storehouse of refreshing one's knowledge.
Three grades of diagnosis decision-making subsystems in a kind of preferred rotary kiln that the embodiment of the present invention proposes also comprise:
Hand automatic switching module, between pattern recognition module and message processing module, for switching automatic operation mode and the manual work pattern of three grades of diagnosis decision-making subsystems according to user instruction, by message processing module, controlled quentity controlled variable is optimized under described automatic mode, by external user input, controlled quentity controlled variable is optimized under described manual work pattern.Thus when rotary kiln running is in comparatively stable state, decision system can be switched to automatic operation mode by operating personnel, or is controlled by user when decision system is difficult to realize efficient control effects, remains on manual work pattern.Wherein also comprise an alarm unit, report to the police when cannot mate target operation state for the controlled quentity controlled variable after reasoning and judging optimization, and switch to manual work pattern after user confirms.That is, along with unusual service condition occurs, when Automatic Control Strategy has been difficult to the control of rotary kiln dynamic property, diagnostic and decision making system is reported to the police, remind operating personnel to be switched to manual mode, instruct operating personnel to produce, strengthen flexibility and the security of system.
Artificial experience load-on module, for the described knowledge base of artificial experience and control rule sets being added into existing knowledge base by user and control law is concentrated, and is applied to the optimization method of artificial experience in described message processing module by user.That is, diagnosis decision system comprises the true Sum fanction input function of artificial experience, except mode identification method builds true Sum fanction, the rotary kiln running state evaluation index that artificial field optimizing operation rules produces is better than the evaluation index that mode identification method produces, then Rotary Kiln Control preferably operation rules be loaded automatically in the optimal control parameter set stored in history control procedure early stage, make various burner reach the running status of burning better and better by rolling optimization.
And message processing module specifically comprises a rolling optimization unit, for the optimum results based on the last time, adopting multidimensional minimum searching method to find, combustion efficiency is best and control point that energy consumption is minimum, and is optimized controlled quentity controlled variable rotary kiln clamper is run on this control point.
That is, when rotary system steady-state operation, multidimensional minimum searching method (hereinafter specifically describe) can be adopted to find makes combustion efficiency be the minimum operating condition of best energy consumption, and allows rotary kiln clamper operate in the combustion of best wind than on vacuum cavitations point in, best kiln.For manual mode, artificial experience optimization can be loaded automatically in the optimal control parameter set stored in history control procedure, make various burner reach the running status of burning better and better by rolling optimization.
Next, composition graphs 5 describes multidimensional minimum searching method in detail.Rotary kiln performance indications require that power consumption values is little as much as possible, and therefore can adopt multidimensional minimum searching method to find optimum controling parameters, the method step is specific as follows:
Step S501: the more excellent control point choosing front twice system loads
its objective is that its Search Range is according to formula by two Search Ranges compared with advantage determination multidimensional extreme value
With
Determine, wherein d, α, β are the range parameter according to applied environment setting.
Step S502: according to obtained Search Range, utilize formula
Produce a new control point
wherein
for the random number between [0,1] identical with optimized variable dimension.If
value meet the constraints of Rotary Kiln Control, then carry out step S503, otherwise return step S501.
Step S503: if three grades of diagnosis decision-making subsystems can stable operation under allowed constraints, and the performance indications optimized
be less than
and be less than
then
be labeled as preferably performance indications, and will
be stored into Optimized model to concentrate, and the controling parameters corresponding to it also carries out mark storage, otherwise abandon
wherein W represents the energy consumption of rotary kiln under each control point.
Step S504: and will
with in the optimal control parameter set stored before preferably performance indications compare, get
then circulation II=1 is carried out, 2 ..., new, II represent the record number that Optimized model is concentrated.When
time,
thus end loop.
Since then, the structure to whole preferred rotary kiln is just completed.The detailed functions framework of this system is see Fig. 6, this rotary kiln by combine with technique such as computer, expert system, optimisation technique, data analysis theory, data communication to together, mode identification technology is adopted to the rotary kiln production phase, analyse in depth the Changing Pattern of calcination process in rotary kiln, set up control law model, and utilize the mode loaded from optimizing rolling optimization technology and artificial experience to make rotary kiln clamper to greatest extent on optimum controlling point.For effectively promoting the automatization level at the sector scene, improve equipment reliability of operation, security and validity, improving the quality of products lays the foundation with output.
It should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operating space, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical element.
Above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (8)
1. a rotary kiln, is characterized in that, comprising:
One-level rotary kiln detection subsystem, for detecting the parameter in rotary kiln combustion process, and is sent to Two-stage control subsystem and three grades of diagnosis decision-making subsystems by described parameter;
Two-stage control subsystem, controls rotary kiln for the controlled quentity controlled variable after the reasoning optimizations that the described parameter that sends according to one-level rotary kiln detection subsystem and three grades of diagnosis decision-making subsystems send;
Three grades of diagnosis decision-making subsystems, carry out reasoning and optimization for the described parameter sent one-level rotary kiln detection subsystem, obtain the controlled quentity controlled variable after reasoning optimization, and the controlled quentity controlled variable after described reasoning optimization is sent to Two-stage control subsystem;
Described three grades of diagnosis decision-making subsystems comprise:
Pattern recognition module, sets up the knowledge base and control rule sets that describe relation between rotary kiln technology parameter and running status according to the historical data of calcined by rotary kiln state for Land use models recognition technology;
Message processing module, mates for the information described parameter received and described knowledge base and control law concentrated, and is optimized controlled quentity controlled variable according to the target operation state preset, the controlled quentity controlled variable after being optimized;
Whether reasoning and judging module, can match with target operation state for the controlled quentity controlled variable after reasoning and judging optimization, if do not mate, is then again optimized till coupling controlled quentity controlled variable, and to refresh one's knowledge storehouse according to prioritization scheme during coupling;
Controlled quentity controlled variable delivery module, for being sent to Two-stage control subsystem by the controlled quentity controlled variable after reasoning optimization.
2. rotary kiln according to claim 1, is characterized in that, described pattern recognition module comprises:
History data set sets up unit, for obtaining in Preset Time the historical data characterizing calcined by rotary kiln state, forms history data set;
Dynamic data searches unit, for concentrating the dynamic data searched and describe relation between each technological parameter and running status in described historical data;
Dynamic data division unit, divides described dynamic data for adopting mode identification technology;
Dynamic data demarcates unit, for using sequence number to demarcate ready-portioned dynamic data, and sets up the corresponding relation of itself and rotary kiln running state performance indications;
Construction of knowledge base unit, for building knowledge base and the control rule sets of relation between described description rotary kiln technology parameter and running status according to described corresponding relation.
3. rotary kiln according to claim 1, is characterized in that, also comprises between the pattern recognition module in described three grades of diagnosis decision-making subsystems and message processing module:
Hand automatic switching module, for switching automatic operation mode and the manual work pattern of three grades of diagnosis decision-making subsystems according to user instruction, by message processing module, controlled quentity controlled variable is optimized under described automatic mode, by external user input, controlled quentity controlled variable is optimized under described manual work pattern.
4. rotary kiln according to claim 3, is characterized in that, described hand automatic switching module comprises:
Alarm unit, reports to the police when cannot mate target operation state for the controlled quentity controlled variable after reasoning and judging optimization, and switches to manual work pattern after user confirms.
5. rotary kiln according to claim 1, is characterized in that, described three grades of diagnosis decision-making subsystems also comprise:
Artificial experience load-on module, for the described knowledge base of artificial experience and control rule sets being added into existing knowledge base by user and control law is concentrated, and is applied to the optimization method of artificial experience in described message processing module by user.
6. rotary kiln according to claim 1, is characterized in that, described three grades of diagnosis decision-making subsystems also comprise:
User interactive module, for receiving the operational order of user, and shows running status and the state of a control information of current rotary kiln to user.
7. rotary kiln as claimed in any of claims 1 to 6, is characterized in that, described message processing module comprises:
Rolling optimization unit, for the optimum results based on the last time, adopting multidimensional minimum searching method to find, combustion efficiency is best and control point that energy consumption is minimum, and is optimized controlled quentity controlled variable rotary kiln clamper is run on this control point.
8. rotary kiln according to claim 1, is characterized in that, described rotary kiln adopts the communication mode of industrial bus or Ethernet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410225353.1A CN104019661B (en) | 2014-05-26 | 2014-05-26 | Rotary kiln control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410225353.1A CN104019661B (en) | 2014-05-26 | 2014-05-26 | Rotary kiln control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104019661A CN104019661A (en) | 2014-09-03 |
| CN104019661B true CN104019661B (en) | 2015-10-28 |
Family
ID=51436549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410225353.1A Active CN104019661B (en) | 2014-05-26 | 2014-05-26 | Rotary kiln control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104019661B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159235B (en) * | 2015-01-08 | 2018-12-25 | 北方工业大学 | Calcination process in rotary kiln synthesizes and coordinates control method and system |
| CN106705657B (en) * | 2017-02-15 | 2022-11-11 | 扬州市银焰机械有限公司 | Remote real-time acquisition system for rotary kiln running state data and control method thereof |
| CN107270303B (en) * | 2017-06-28 | 2018-12-18 | 光大环境科技（中国）有限公司 | A kind of rotary kiln method for controlling rotation and its control system |
| CN109034523B (en) * | 2018-06-11 | 2022-06-28 | 湖南工业大学 | Volatilization kiln working condition operation mode optimization method integrating least square support vector machine regression and particle swarm optimization |
| CN111158336A (en) * | 2019-11-22 | 2020-05-15 | 万洲电气股份有限公司 | Industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis |
| CN115115141B (en) * | 2022-08-22 | 2022-12-06 | 朗坤智慧科技股份有限公司 | Rotary kiln energy consumption optimization method based on greedy thought and time sequence classification |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3578298A (en) * | 1969-09-26 | 1971-05-11 | Gen Electric | Method and apparatus for cement kiln control |
| US3751215A (en) * | 1972-06-12 | 1973-08-07 | Honeywell Inc | Deviation proportional analog pulse controlling apparatus |
| US4716532A (en) * | 1985-03-13 | 1987-12-29 | Fives-Cail Babcock | Clinker manufacture control using falling clinker colorific energy measurement |
| US4910684A (en) * | 1987-08-06 | 1990-03-20 | F. L. Smidth & Co. A/B | Method of controlling a rotary kiln during start-up |
| CN1492210A (en) * | 2003-09-18 | 2004-04-28 | 中国铝业股份有限公司 | Intelligent control method for aluminium oxide chamotte sintering rotary kiln |
| JP3567852B2 (en) * | 2000-04-21 | 2004-09-22 | 住友金属工業株式会社 | Rotary kiln |
| CN101261762A (en) * | 2007-03-08 | 2008-09-10 | 原传海 | A temperature measuring method for rotary stove and its process control method |
| CN102226643A (en) * | 2011-03-28 | 2011-10-26 | 宁夏惠冶镁业集团有限公司 | Rotary kiln automatic control system and method |
-
2014
- 2014-05-26 CN CN201410225353.1A patent/CN104019661B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3578298A (en) * | 1969-09-26 | 1971-05-11 | Gen Electric | Method and apparatus for cement kiln control |
| US3751215A (en) * | 1972-06-12 | 1973-08-07 | Honeywell Inc | Deviation proportional analog pulse controlling apparatus |
| US4716532A (en) * | 1985-03-13 | 1987-12-29 | Fives-Cail Babcock | Clinker manufacture control using falling clinker colorific energy measurement |
| US4910684A (en) * | 1987-08-06 | 1990-03-20 | F. L. Smidth & Co. A/B | Method of controlling a rotary kiln during start-up |
| JP3567852B2 (en) * | 2000-04-21 | 2004-09-22 | 住友金属工業株式会社 | Rotary kiln |
| CN1492210A (en) * | 2003-09-18 | 2004-04-28 | 中国铝业股份有限公司 | Intelligent control method for aluminium oxide chamotte sintering rotary kiln |
| CN101261762A (en) * | 2007-03-08 | 2008-09-10 | 原传海 | A temperature measuring method for rotary stove and its process control method |
| CN102226643A (en) * | 2011-03-28 | 2011-10-26 | 宁夏惠冶镁业集团有限公司 | Rotary kiln automatic control system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104019661A (en) | 2014-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104019661B (en) | Rotary kiln control system | |
| Zimmermann | Fuzzy control | |
| CN105241239B (en) | A kind of baked brick tunnel kiln roasting process intelligent optimized control method and device | |
| CN105974793B (en) | A kind of power boiler burning intelligent control method | |
| Zheng et al. | A comparative study of optimization algorithms for low NOx combustion modification at a coal-fired utility boiler | |
| CN104123476B (en) | Forecasting of Gas Concentration method based on extreme learning machine and its device | |
| CN106202946A (en) | Clinker free calcium levels Forecasting Methodology based on degree of depth belief network model | |
| CN104763999A (en) | Power plant pulverized coal boiler combustion performance online optimizing method and system | |
| CN106022377A (en) | Online prediction method for iron ore sintering bed permeability states | |
| Qian et al. | An improved particle swarm optimization with clone selection principle for dynamic economic emission dispatch | |
| CN105864797A (en) | Real-time prediction system and method for boiler entering heat value of circulating fluidized bed household garbage incineration boiler | |
| CN111651931A (en) | Blast furnace fault diagnosis rule derivation method based on deep neural network | |
| WO2020015466A1 (en) | Boiler coal saving control method | |
| CN100582262C (en) | Copper flash smelting operation parameter optimization method | |
| Wang et al. | A hybrid ensemble model based on ELM and improved adaboost. RT algorithm for predicting the iron ore sintering characters. | |
| Zhang et al. | Multi-model based PSO method for burden distribution matrix optimization with expected burden distribution output behaviors | |
| CN112066355B (en) | Self-adaptive adjusting method of waste heat boiler valve based on data driving | |
| Du et al. | Operating mode recognition of iron ore sintering process based on the clustering of time series data | |
| Raghib et al. | Hierarchical multiobjective approach for optimising RFID reader deployment | |
| CN106647279B (en) | A kind of locomotive smart steering optimized calculation method based on fuzzy rule | |
| CN106203526B (en) | Goal behavior mode online classification method based on multidimensional characteristic | |
| CN111199304B (en) | Multi-target combustion optimization method based on data-driven fusion strategy | |
| CN105930936A (en) | Growth prediction method of microorganisms included in food in production circulation process | |
| Santos-Victor et al. | A computer vision system for the characterization and classification of flames in glass furnaces | |
| CN114968997A (en) | Sintering end point forecasting method based on space-time feature extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170116 Address after: 100144 Beijing City, Shijingshan District Jin Yuan Zhuang Road No. 5 Patentee after: Beifang Polytechnic Univ. Patentee after: BEIJING CREID AUTOMATION TECHNOLOGY CO., LTD. Address before: 100144 Beijing City, Shijingshan District Jin Yuan Zhuang Road No. 5 Patentee before: Beifang Polytechnic Univ. |