CN112229206B - Method for controlling coal feeding of kiln head of rotary cement kiln - Google Patents

Method for controlling coal feeding of kiln head of rotary cement kiln Download PDF

Info

Publication number
CN112229206B
CN112229206B CN202011121694.6A CN202011121694A CN112229206B CN 112229206 B CN112229206 B CN 112229206B CN 202011121694 A CN202011121694 A CN 202011121694A CN 112229206 B CN112229206 B CN 112229206B
Authority
CN
China
Prior art keywords
case
temperature
kiln head
coal feeding
value
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
Application number
CN202011121694.6A
Other languages
Chinese (zh)
Other versions
CN112229206A (en
Inventor
路士增
李强亚
王孝红
于宏亮
袁铸钢
孟庆金
景绍洪
张强
蒋萍
刘钊
张荣丰
刘化果
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Jinan
Original Assignee
University of Jinan
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Jinan filed Critical University of Jinan
Priority to CN202011121694.6A priority Critical patent/CN112229206B/en
Publication of CN112229206A publication Critical patent/CN112229206A/en
Application granted granted Critical
Publication of CN112229206B publication Critical patent/CN112229206B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F27—FURNACES; KILNS; OVENS; RETORTS
    • F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
    • F27B7/00—Rotary-drum furnaces, i.e. horizontal or slightly inclined
    • F27B7/20—Details, accessories, or equipment peculiar to rotary-drum furnaces
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F27—FURNACES; KILNS; OVENS; RETORTS
    • F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
    • F27B7/00—Rotary-drum furnaces, i.e. horizontal or slightly inclined
    • F27B7/20—Details, accessories, or equipment peculiar to rotary-drum furnaces
    • F27B7/42—Arrangement of controlling, monitoring, alarm or like devices
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F27—FURNACES; KILNS; OVENS; RETORTS
    • F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
    • F27D19/00—Arrangements of controlling devices

Abstract

The invention discloses a method for controlling coal feeding of a kiln head of a rotary cement kiln, which comprises the following steps: obtaining an initial kiln head coal feeding amount set through case reasoning on the basis of actual production data of a cement factory; and judging the trend change of the current sintering working condition according to expert rules based on the deviation of the real-time value of the sintering zone temperature and the expected value of the sintering zone temperature and the temperature change rate of the sintering zone, and correcting and compensating the coal feeding amount at the kiln head. The invention establishes a control device design method for correcting the coal feeding quantity of the kiln head of the given rotary cement kiln based on case reasoning and expert rules, and eliminates the difference of knowledge and experience among different operation engineers.

Description

Method for controlling coal feeding of kiln head of rotary cement kiln
Technical Field
The invention relates to a method for controlling coal feeding of a kiln head of a rotary cement kiln, and belongs to the technical field of cement production control.
Background
The cement industry is one of the prop industries of national economy in China, and the rotary cement kiln becomes the main equipment for calcining cement clinker in modern cement production. The construction of intelligent cement production plants to improve the high automation, integration and greening of cement enterprises has become an important development direction of the cement industry.
Clinker is an intermediate product in cement production, and the quality of the clinker directly determines the final quality of the cement. The calcination process of the cement clinker in the rotary kiln is a key link for determining the quality of the cement clinker.
However, in the current cement enterprises, the control of kiln head coal feeding amount mainly depends on the knowledge and experience of operation engineers, and the firing quality of cement clinker is influenced due to the difference of technical levels of the operation engineers and the fact that operation behaviors are easily subject to subjective intentions.
Disclosure of Invention
In order to solve the problems, the invention provides a rotary cement kiln head coal feeding control method which can eliminate the difference of knowledge and experience among different operation engineers.
The technical scheme adopted for solving the technical problems is as follows:
the embodiment of the invention provides a rotary cement kiln head coal feeding control method, which comprises the following steps:
obtaining an initial kiln head coal feeding amount set through case reasoning on the basis of actual production data of a cement factory;
and judging the trend change of the current sintering working condition according to expert rules based on the deviation of the real-time value of the sintering zone temperature and the expected value of the sintering zone temperature and the temperature change rate of the sintering zone, and correcting and compensating the coal feeding amount at the kiln head.
As a possible implementation manner of this embodiment, the step of obtaining the initial kiln head coal feeding amount set through case reasoning includes:
selecting relevant parameter data of kiln head coal feeding amount for analysis and processing, and creating an initial case library, wherein the relevant parameter data comprises burning zone temperature, kiln host machine current, kiln head cover temperature, online collected data of raw material blanking amount and kiln head coal feeding amount, and offline collected data of raw material ternary value and clinker free calcium;
and calculating the similarity between the target case and the initial case library, and performing case retrieval and matching to obtain an initial kiln head coal feeding amount set.
As a possible implementation manner of this embodiment, the step of creating the initial case base includes:
eliminating abnormal values of the selected related parameter data through a Lauda criterion, and performing mean filtering processing on the parameter data after the abnormal values are eliminated;
observing the trend change of the burning zone temperature per hour by taking the burning zone temperature as a reference, and selecting the highest value, the middle value and the lowest value of the burning zone temperature within one hour;
selecting the values corresponding to the time when the highest value, the middle value and the lowest value of the burning zone temperature generated per hour are the same for the current of the main machine of the kiln, the temperature of a kiln head cover, the raw material blanking amount, the coal feeding amount of the kiln head, the raw material three-rate value and the content of free calcium in clinker to jointly form a source case library Ck。
As a possible implementation manner of this embodiment, the step of removing the abnormal value from the selected related parameter data by using the ralda criterion includes:
will change the variable xiThe average value of the N data:
Figure GDA0003551316240000021
calculating xiDeviation e of terms from the meani：
Figure GDA0003551316240000022
Calculating the standard deviation σ:
Figure GDA0003551316240000023
when data xiDeviation e ofi(1. ltoreq. i. ltoreq.n) satisfies | ei|>3 σ, then x is determinediIf the abnormal value is found, the abnormal value is eliminated.
As a possible implementation manner of this embodiment, the mean filtering formula for processing the parameter data after the abnormal value is removed is as follows:
Figure GDA0003551316240000024
where m is the time window length of the mean filtering.
As a possible implementation manner of this embodiment, the source case library CkExpressed as:
Ck:(Xk；yk),k＝1,2,Λ,p
wherein p is a source case library CkNumber of cases, Xk＝{xk，1,xk，2,xk，3,xk，4,xk，5,xk，6,xk，7,xk，8Respectively represent input variables { burning zone temperature, kiln main machine current, kiln head cover temperature, raw material blanking quantity, raw material three-rate values KH, IM and SM, clinker free calcium content }, ykRepresenting the kiln head coal feeding amount of the output variable.
As a possible implementation manner of this embodiment, the step of performing case retrieval and matching and calculating the similarity between the target case and the initial case base includes:
calculating target case CcurA certain characteristic x ofi(i ═ 1,2, Λ,8) and source case base CkFeature x of the kth casek,iSimilarity function sim (x) of (i ═ 1,2, Λ,8)i,xk,i)：
Figure GDA0003551316240000031
Wherein k is 1,2, Λ, p, i is 1,2, Λ, 8;
calculating target case CcurAnd the kth case C of the source case basekSimilarity function SIM of (k ═ 1,2, Λ, p)k：
Figure GDA0003551316240000032
Where k is 1,2, Λ, p, i is 1,2, Λ,8, λiWeighting factor, weighting factor lambda, representing the property of a feature in a case1～λ8The sum of the values is 1;
SIM (subscriber identity module) for calculating similarity thresholdy1：
Figure GDA0003551316240000033
In the formula, V represents a similarity threshold;
all satisfied SIMs in the source case basek≥SIMy1The cases (2) are arranged in order according to the magnitude of the similarity value.
As a possible implementation manner of this embodiment, the step of determining the trend change of the current firing condition according to the control rule is as follows:
calculating the deviation E (k) between the real-time value of the temperature of the burning zone at the current moment and the expected value of the temperature of the burning zone and the temperature change rate EC (k) of the burning zone:
E(k)＝Tw(k)-Tset(k)
wherein E (k) represents the temperature deviation of the burning zone at the current moment, Tw(k) Representing the mean temperature of the burning zone, T, at the current momentset(k) Representing the expected set value of the burning zone temperature at the current moment;
EC(k)＝Tw(k)-2Tw(k-1)+Tw(k-2)
in the formula, EC (k) represents the rate of change in temperature of the firing zone at the present time, Tw(k-1) represents the mean temperature of the burning zone at the previous moment, Tw(k-2) represents the average value of the temperature of the burning zone at the previous moment;
working condition grading is carried out on the temperature deviation E (k) of the sintering zone and the temperature change rate EC (k) of the sintering zone to form a sintering working condition change rule table;
and (4) combining the firing working condition change rule table and the kiln head coal feeding amount at the previous moment, and removing case solutions which are obtained through case retrieval and matching and are in accordance with the target case similarity conditions but not in accordance with the firing working conditions.
As a possible implementation manner of this embodiment, the step of forming the firing condition variation rule table is as follows:
the fluctuation range of the temperature deviation of the burning zone is between-150 ℃ and +150 ℃, the discourse domain after the working condition is graded is between-2 and-1, 0 and +1 and +2, and the corresponding linguistic variables are { under burning, normal, over burning and over burning };
the variation interval of the temperature change rate of the sintering belt is [ -30, +30], the discourse domain after the working condition is graded is [ -2, -1,0, +1, +2], and the corresponding linguistic variable is { fast drop, slow drop, stability, slow rise and fast rise };
forming a sintering working condition change rule table:
Figure GDA0003551316240000041
in table ci,jAnd (i, j ═ 1,2, Λ,5) represents sintering condition information corresponding to different sintering zone temperature deviations and temperature change rates thereof.
As a possible implementation manner of this embodiment, the removing of the case solution rule which is obtained by case retrieval and matching and which is in accordance with the target case similarity condition but is not in accordance with the firing condition by combining the firing condition change rule table and the kiln head coal feeding amount at the previous moment includes:
and when case retrieval and matching are carried out on the target case and the source case base to obtain a plurality of case solutions which have different values and meet the similarity condition, judging the variation of the obtained firing working condition through the expert rules, comparing the kiln head coal feeding amount of the target case at the current moment, screening a case solution set, and removing the case solution which does not accord with the variation of the current firing working condition.
The technical scheme of the embodiment of the invention has the following beneficial effects:
the method comprises the steps of firstly, obtaining an initial kiln head coal feeding amount set by a case reasoning method on the basis of actual production data of a cement factory; and then, taking the deviation of the temperature real-time value of the burning zone and the temperature expected value of the burning zone and the temperature change rate thereof as the basis, and correcting the kiln head coal feeding amount by utilizing a control rule that experts can judge the change of the burning working condition, thereby forming a control device design method for correcting the kiln head coal feeding amount of the given cement rotary kiln based on case-based reasoning and control rules, further promoting the automation process of cement industrial production, and effectively solving the problem that the burning quality of cement clinker is influenced because the difference of the technical level of an operation engineer and the operation behavior are easily governed by subjective will. By adopting the technical scheme, the design method of the control device for correcting the coal feeding quantity of the kiln head of the given rotary cement kiln based on case-based reasoning combined with control rules is established, and the difference of knowledge and experience among different operation engineers is eliminated.
Description of the drawings:
fig. 1 is a flow chart illustrating a rotary cement kiln head coal feed control method according to an exemplary embodiment.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
in order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
Fig. 1 is a flow chart illustrating a rotary cement kiln head coal feed control method according to an exemplary embodiment. As shown in fig. 1, a method for obtaining a given value of coal feeding at a kiln head in a rotary kiln for cement clinker calcination according to an embodiment of the present invention includes:
obtaining an initial kiln head coal feeding amount set through case reasoning on the basis of actual production data of a cement factory;
and judging the trend change of the current sintering working condition according to expert rules based on the deviation of the real-time value of the sintering zone temperature and the expected value of the sintering zone temperature and the temperature change rate of the sintering zone, and correcting and compensating the coal feeding amount at the kiln head.
The invention aims to solve the problem that the case reasoning method cannot reflect the trend change of the firing parameters when applied to the kiln head coal feeding control in the clinker calcining link of the rotary cement kiln, and eliminates the case solution which is obtained by case retrieval and matching and accords with the similarity condition of the target case but does not accord with the firing working condition.
Optionally, the step of obtaining an initial kiln head coal feeding amount set through a case reasoning method includes:
selecting parameter data related to the kiln head coal feeding amount, including offline data and online data, analyzing and processing the parameter data, and creating an initial case library; selecting online collected data of a burning zone temperature, a kiln main machine current, a kiln head cover temperature, a raw material blanking amount and a kiln head coal feeding amount, and offline collected data of a raw material ternary value and clinker free calcium;
and calculating the similarity between the target case and the initial case library, and performing case retrieval and matching to obtain an initial kiln head coal feeding amount set.
Optionally, the step of creating an initial case base includes:
firstly, removing abnormal values of the selected parameter data through a Lauda criterion, and then carrying out mean value filtering processing on the parameter data after the abnormal values are removed;
and (3) observing the trend change of the burning zone temperature per hour by taking the burning zone temperature as a reference, and selecting the highest value, the middle value and the lowest value of the burning zone temperature within one hour.
Simultaneously, the current of a kiln main machine, the temperature of a kiln head cover, the blanking amount of raw materials, the coal feeding amount of the kiln head, the three-rate value of the raw materials and the content of free calcium in clinker are selected from values corresponding to the same time when the highest value, the middle value and the lowest value of the temperature of a burning zone generated per hour are the same to form a source case library Ck。
Optionally, the step of rejecting outliers according to the ralda criterion includes:
will change the variable xiThe average value of the N data is obtained;
calculating xiDeviation e of terms from the meani；
Calculating a standard deviation sigma;
when data xiDeviation e ofi(1. ltoreq. i. ltoreq.n) satisfies | ei|>3 σ, then x is determinediIf the abnormal value is found, the abnormal value is eliminated.
Optionally, the variable xiThe average value formula of the N data is as follows:
Figure GDA0003551316240000071
optionally, said calculating xiDeviation e of terms from the meaniThe formula is as follows:
Figure GDA0003551316240000072
optionally, the formula of calculating the standard deviation σ is as follows:
Figure GDA0003551316240000073
optionally, the mean filtering formula for processing the parameter data from which the abnormal value is removed is as follows:
Figure GDA0003551316240000074
where m is the time window length of the mean filtering.
Optionally, the source case library CkExpressed as:
Ck:(Xk；yk),k＝1,2,Λ,p
wherein p is the source caseExample library CkNumber of cases, Xk＝{xk，1,xk，2,xk，3,xk，4,xk，5,xk，6,xk，7,xk，8Respectively represent input variables { burning zone temperature, kiln main machine current, kiln head cover temperature, raw material blanking quantity, raw material three-rate values KH, IM and SM, clinker free calcium content }, ykRepresenting the kiln head coal feeding amount of the output variable.
Optionally, the step of calculating the similarity between the target case and the initial case base based on the nearest neighbor algorithm based on the euclidean distance to perform case retrieval and matching includes:
calculating target case CcurA certain characteristic x ofi(i ═ 1,2, Λ,8) and source case base CkFeature x of the kth casek,iSimilarity function sim (x) of (i ═ 1,2, Λ,8)i,xk,i)；
Calculating target case CcurAnd the kth case C of the source case basekSimilarity function SIM of (k ═ 1,2, Λ, p)k；
SIM (subscriber identity Module) with similarity threshold sety1All satisfied SIMs in the source case libraryk≥SIMy1The cases (2) are arranged in order according to the magnitude of the similarity value.
Optionally, the target case C is calculatedcurA certain characteristic x ofi(i ═ 1,2, Λ,8) and source case base CkFeature x of the kth casek,iSimilarity function sim (x) of (i ═ 1,2, Λ,8)i,xk,i) The formula is as follows:
Figure GDA0003551316240000081
where k is 1,2, Λ, p, i is 1,2, Λ, 8.
Optionally, the target case C is calculatedcurAnd the kth case C of the source case basekSimilarity function SIM of (k ═ 1,2, Λ, p)kThe formula is as follows:
Figure GDA0003551316240000082
where k is 1,2, Λ, p, i is 1,2, Λ,8, λiThe weighting coefficients representing the characteristic attributes in the case are used to distinguish the importance of different characteristic parameters, and the values can be obtained according to expert experience. Wherein the weighting coefficient lambda1～λ8The sum of the values being 1, i.e.
Figure GDA0003551316240000083
Optionally, the similarity threshold SIMy1Can be formulated as follows:
Figure GDA0003551316240000084
in the formula, the similarity threshold V may be determined by expert experience.
Optionally, the step of determining the trend change of the firing condition and correcting the kiln head coal feeding amount by combining the control rule is as follows:
selecting the deviation E between the real-time value of the temperature of the burning zone at the current moment and the expected value of the temperature of the burning zone and the temperature change rate EC thereof as input variables of a control rule controller;
working condition grading is carried out on the temperature deviation E of the sintering zone and the temperature change rate EC thereof according to expert experience to form a sintering working condition change rule table;
and (4) combining the firing working condition change rule table and the kiln head coal feeding amount at the previous moment, and removing case solutions which are obtained through case retrieval and matching and are in accordance with the target case similarity conditions but not in accordance with the firing working conditions.
Optionally, the calculation formula of the temperature deviation E of the burning zone and the temperature change rate EC thereof is as follows:
temperature deviation of a burning zone:
E(k)＝Tw(k)-Tset(k)
wherein E (k) represents the temperature deviation of the burning zone at the current moment, Tw(k) Representing the mean temperature of the burning zone, T, at the current momentset(k) Representing the desired setting of the burn zone temperature at the present timeThe value is obtained.
Temperature change rate of fired belt:
EC(k)＝Tw(k)-2Tw(k-1)+Tw(k-2)
in the formula, EC (k) represents the rate of change in temperature of the firing zone at the present time, Tw(k-1) represents the mean temperature of the burning zone at the previous moment, TwAnd (k-2) represents the average value of the temperature of the burning zone at the previous moment.
Optionally, the step of performing working condition grading on the temperature deviation E of the burning zone and the temperature change rate EC thereof according to expert experience includes:
the fluctuation range of the temperature deviation of the burning zone is probably between-150 ℃ and +150 ℃, the discourse domain after the working condition is graded is between-2, -1,0, +1 and +2, and the corresponding linguistic variables are { under burning, normal, over burning and over burning }. Then, the corresponding working condition grading table is:
TABLE 1 burning zone temperature deviation grading table
Figure GDA0003551316240000091
The change interval of the temperature change rate of the sintering belt is approximately between-30 and +30, the discourse domain after the working condition is graded is also set to be between-2 and-1, 0 and +1 and +2, and the corresponding linguistic variable is fast falling, slow falling, stable, slow rising and fast rising. The corresponding working condition is graded as follows:
TABLE 2 sintering belt temperature change rate grading table
Figure GDA0003551316240000092
Optionally, the following firing condition change rule table may be formed according to the firing zone temperature deviation and the temperature change rate grading table thereof and expert experience:
TABLE 3 rule table for sintering condition change
Figure GDA0003551316240000101
In table ci,jAnd (i, j ═ 1,2, Λ,5) represents sintering condition information corresponding to different sintering zone temperature deviations and temperature change rates thereof. For example:
when { sintering zone temperature deviation, sintering zone temperature change rate } is graded into [0, 0]]When the temperature of the burning zone is normal, the temperature changes to be in a stable state. Then, the firing condition c at this time11Represents: the clinker calcination is in a "normal state" at this time, and the "normal state" will be continuously maintained;
when { sintering zone temperature deviation, sintering zone temperature change rate } is graded into [ 0-1]When the temperature of the burning zone is normal, the temperature changes to be in a slow-down state. Then, the firing condition c at this time2,3Represents: at the moment, the clinker is calcined in a normal state, but the forward direction is transited to a less-burnt state;
when { sintering zone temperature deviation, sintering zone temperature change rate } is graded into [0, +1]When the temperature of the burning zone is normal, the temperature changes to be in a slow-rising state. Then, the firing condition c at this time4,3Represents: at the moment, the clinker is calcined in a normal state, but the forward direction is transited to a more over-burnt state;
optionally, the principle of removing the case solution which is obtained by case retrieval and matching and accords with the target case similarity condition but does not accord with the firing working condition by combining the firing working condition change rule table and the kiln head coal feeding amount at the previous moment includes:
and when case retrieval and matching are carried out on the target case and the source case base to obtain a plurality of case solutions which have different values and meet the similarity condition, judging the variation of the obtained firing working condition through the expert rules, comparing the kiln head coal feeding amount of the target case at the current moment, screening a case solution set, and removing the case solution which does not accord with the variation of the current firing working condition. Specifically, the method comprises the following steps:
(1) supposing that the kiln head coal feeding amount W (k-1) at the previous moment is 10.5t/h, the change of the firing working condition at the current moment into a normal state and the transition to a less-firing state are obtained by judging according to a control rule; at the moment, the case solution set obtained by case retrieval and matching is {10.2t/h,10.3t/h,10.5t/h,10.7t/h and 10.8t/h }; according to the process, in order to maintain the stability of the sintering working condition, the relationship between the kiln head coal feeding amount W (k) at the current moment and the kiln head coal feeding amount W (k-1) at the previous moment is as follows: w (k) is more than or equal to W (k-1), namely {10.2t/h,10.3t/h } in the case solution set is removed.
(2) Supposing that the kiln head coal feeding amount W (k-1) at the previous moment is 10.5t/h, the change of the firing working condition at the current moment into a normal state and the transition to a more over-firing state are obtained by judging according to a control rule; at the moment, the case solution set obtained by case retrieval and matching is {10.2t/h,10.3t/h,10.5t/h,10.7t/h and 10.8t/h }; according to the process, in order to maintain the stability of the sintering working condition, the relationship between the kiln head coal feeding amount W (k) at the current moment and the kiln head coal feeding amount W (k-1) at the previous moment is as follows: w (k) is less than or equal to W (k-1), namely {10.7t/h,10.8t/h } in the case solution set is removed.
Optionally, the step of obtaining a case solution by case reuse includes:
suppose that r case sets meeting the similarity threshold condition are retrieved after a certain target case is modified by control rules in a source case library, and the set is marked as { C1,C2,Λ,CrThe corresponding case solution set is Yk＝(y1,y2,Λ,yr) Then, the case solution of the current target case is:
Figure GDA0003551316240000111
in the formula, ωk＝SIMk(k ═ 1,2, Λ, r) is the similarity of the target case to each source case in the set of r cases;
Figure GDA0003551316240000112
and feeding coal to the kiln head at the current moment.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.

Claims (1)

1. A method for controlling coal feeding of a kiln head of a rotary cement kiln is characterized by comprising the following steps:
obtaining an initial kiln head coal feeding amount set through case reasoning on the basis of actual production data of a cement factory;
judging the trend change of the current firing working condition according to expert rules based on the deviation of the real-time value of the firing zone temperature and the expected value of the firing zone temperature and the temperature change rate of the firing zone, and correcting and compensating the coal feeding amount at the kiln head;
the step of obtaining the initial kiln head coal feeding amount set through case reasoning comprises the following steps:
selecting relevant parameter data of kiln head coal feeding amount for analysis and processing, and creating an initial case library, wherein the relevant parameter data comprises burning zone temperature, kiln host machine current, kiln head cover temperature, online collected data of raw material blanking amount and kiln head coal feeding amount, and offline collected data of raw material ternary value and clinker free calcium;
calculating the similarity between the target case and the initial case library, and performing case retrieval and matching to obtain an initial kiln head coal feeding amount set;
the step of creating the initial case base comprises the following steps:
eliminating abnormal values of the selected related parameter data through a Lauda criterion, and performing mean filtering processing on the parameter data after the abnormal values are eliminated;
observing the trend change of the burning zone temperature per hour by taking the burning zone temperature as a reference, and selecting the highest value, the middle value and the lowest value of the burning zone temperature within one hour;
selecting the values corresponding to the time when the highest value, the middle value and the lowest value of the burning zone temperature generated per hour are the same for the current of the main machine of the kiln, the temperature of a kiln head cover, the raw material blanking amount, the coal feeding amount of the kiln head, the raw material three-rate value and the content of free calcium in clinker to jointly form a source case library Ck；
The step of eliminating abnormal values of the selected related parameter data through the Lauda criterion comprises the following steps:
will change the variable xiThe average value of the N data:
Figure FDA0003551316230000011
calculating xiDeviation e of terms from the meani：
Figure FDA0003551316230000012
Calculating the standard deviation σ:
Figure FDA0003551316230000013
when data xiDeviation e ofi(1. ltoreq. i. ltoreq.n) satisfies | ei|>3 σ, then x is determinediRemoving abnormal values;
the mean value filtering formula for processing the parameter data after the abnormal values are removed is as follows:
Figure FDA0003551316230000021
wherein m is the time window length of the mean filtering;
the source case library CkExpressed as:
Ck:(Xk；yk),k＝1,2,Λ,p
wherein p is a source case library CkNumber of cases, Xk＝{xk，1,xk，2,xk，3,xk，4,xk，5,xk，6,xk，7,xk，8Respectively represent input variables { burning zone temperature, kiln main machine current, kiln head cover temperature, raw material blanking quantity, raw material three-rate values KH, IM and SM, clinker free calcium content }, ykRepresenting the output variable kiln head coal feeding amount;
the steps of searching and matching cases and calculating the similarity between the target case and the initial case base are as follows:
calculating target case CcurA certain characteristic x ofi(i ═ 1,2, Λ,8) and source case base CkFeature x of the kth casek,iSimilarity function sim (x) of (i ═ 1,2, Λ,8)i,xk,i)：
Figure FDA0003551316230000022
Wherein k is 1,2, Λ, p, i is 1,2, Λ, 8;
calculating target case CcurAnd the kth case C of the source case basekSimilarity function SIM of (k ═ 1,2, Λ, p)k：
Figure FDA0003551316230000023
Where k is 1,2, Λ, p, i is 1,2, Λ,8, λiWeighting factor, weighting factor lambda, representing the property of a feature in a case1～λ8The sum of the values is 1;
SIM (subscriber identity module) for calculating similarity thresholdy1：
Figure FDA0003551316230000024
In the formula, V represents a similarity threshold;
all satisfied SIMs in the source case basek≥SIMy1The cases are arranged in sequence according to the size of the similarity value;
the step of judging the trend change of the current firing working condition according to the expert rule is as follows:
calculating the deviation E (k) between the real-time value of the temperature of the burning zone at the current moment and the expected value of the temperature of the burning zone and the temperature change rate EC (k) of the burning zone:
E(k)＝Tw(k)-Tset(k)
wherein E (k) represents the temperature deviation of the burning zone at the current moment, Tw(k) Representing the mean temperature of the burning zone, T, at the current momentset(k) Representing the expected set value of the burning zone temperature at the current moment;
EC(k)＝Tw(k)-2Tw(k-1)+Tw(k-2)
in the formula, EC (k) represents the rate of change in temperature of the firing zone at the present time, Tw(k-1) represents the mean temperature of the burning zone at the previous moment, Tw(k-2) represents the average value of the temperature of the burning zone at the previous moment;
working condition grading is carried out on the temperature deviation E (k) of the sintering zone and the temperature change rate EC (k) of the sintering zone to form a sintering working condition change rule table;
combining the firing working condition change rule table with the kiln head coal feeding amount at the previous moment, and removing case solutions which are obtained through case retrieval and matching and conform to the target case similarity conditions but do not conform to the firing working conditions;
the steps of forming the firing condition change rule table are as follows:
the fluctuation range of the temperature deviation of the burning zone is between-150 ℃ and +150 ℃, the discourse domain after the working condition is graded is between-2 and-1, 0 and +1 and +2, and the corresponding linguistic variables are { under burning, normal, over burning and over burning };
the variation interval of the temperature change rate of the sintering belt is [ -30, +30], the discourse domain after the working condition is graded is [ -2, -1,0, +1, +2], and the corresponding linguistic variable is { fast drop, slow drop, stability, slow rise and fast rise };
forming a sintering working condition change rule table:
Figure FDA0003551316230000031
in table ci,j(i, j ═ 1,2, Λ,5) represents sintering condition information corresponding to different sintering zone temperature deviations and temperature change rates thereof;
the method comprises the following steps of combining a firing working condition change rule table and the kiln head coal feeding amount at the previous moment, and eliminating case solution principles which are obtained through case retrieval and matching and are in accordance with the target case similarity conditions but not in accordance with the firing working conditions:
and when case retrieval and matching are carried out on the target case and the source case base to obtain a plurality of case solutions which have different values and meet the similarity condition, judging the variation of the obtained firing working condition through the expert rules, comparing the kiln head coal feeding amount of the target case at the current moment, screening case solution sets, and removing the case solution sets which do not accord with the variation of the current firing working condition.
CN202011121694.6A 2020-10-19 2020-10-19 Method for controlling coal feeding of kiln head of rotary cement kiln Active CN112229206B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011121694.6A CN112229206B (en) 2020-10-19 2020-10-19 Method for controlling coal feeding of kiln head of rotary cement kiln

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011121694.6A CN112229206B (en) 2020-10-19 2020-10-19 Method for controlling coal feeding of kiln head of rotary cement kiln

Publications (2)

Publication Number Publication Date
CN112229206A CN112229206A (en) 2021-01-15
CN112229206B true CN112229206B (en) 2022-04-29

Family

ID=74119089

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011121694.6A Active CN112229206B (en) 2020-10-19 2020-10-19 Method for controlling coal feeding of kiln head of rotary cement kiln

Country Status (1)

Country Link
CN (1) CN112229206B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113343791B (en) * 2021-05-21 2023-06-16 浙江邦业科技股份有限公司 Kiln head fire-viewing video brightness identification method and device based on convolutional neural network
CN115780006B (en) * 2022-11-17 2023-07-18 沈阳盛世五寰科技有限公司 Intelligent control method for material weight of high-pressure roller mill based on case reasoning

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001032581A1 (en) * 1999-11-04 2001-05-10 Pretoria Portland Cement Company Limited Kiln plant control system
CN102654444A (en) * 2012-04-26 2012-09-05 中冶南方工程技术有限公司 Method for measuring pulverized coal granularity of blast furnace coal-injection medium-speed milling system
CN102652925A (en) * 2012-04-26 2012-09-05 中冶南方工程技术有限公司 System for measuring granularity of pulverized coal of blast furnace coal powder injection middle-speed milling system
CN104134120A (en) * 2014-07-30 2014-11-05 东北大学 System and method for monitoring ore-dressing production indexes
CN105022355A (en) * 2014-04-21 2015-11-04 东北大学 Cement rotary kiln intelligent optimization control system
CN109761517A (en) * 2019-03-13 2019-05-17 安徽海螺集团有限责任公司 A method of based on the control clinker production of free calcium prediction data

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001032581A1 (en) * 1999-11-04 2001-05-10 Pretoria Portland Cement Company Limited Kiln plant control system
CN102654444A (en) * 2012-04-26 2012-09-05 中冶南方工程技术有限公司 Method for measuring pulverized coal granularity of blast furnace coal-injection medium-speed milling system
CN102652925A (en) * 2012-04-26 2012-09-05 中冶南方工程技术有限公司 System for measuring granularity of pulverized coal of blast furnace coal powder injection middle-speed milling system
CN105022355A (en) * 2014-04-21 2015-11-04 东北大学 Cement rotary kiln intelligent optimization control system
CN104134120A (en) * 2014-07-30 2014-11-05 东北大学 System and method for monitoring ore-dressing production indexes
CN109761517A (en) * 2019-03-13 2019-05-17 安徽海螺集团有限责任公司 A method of based on the control clinker production of free calcium prediction data

Also Published As

Publication number Publication date
CN112229206A (en) 2021-01-15

Similar Documents

Publication Publication Date Title
CN112229206B (en) Method for controlling coal feeding of kiln head of rotary cement kiln
CN109761517B (en) Method for controlling clinker production based on free calcium prediction data
CN109685283B (en) Method for predicting submerged arc furnace working condition based on confidence rule base reasoning
CN110413601B (en) Generator data screening method based on Gauss naive Bayes and prediction error method
CN115034465B (en) Coke quality prediction method based on artificial intelligence
CN115186996A (en) Rotary kiln process parameter control method and device, electronic equipment and storage medium
CN112066355A (en) Self-adaptive adjusting method of waste heat boiler valve based on data driving
CN114001562A (en) Temperature-regulating PID parameter self-tuning method for cement predecomposition furnace
CN109101683B (en) Model updating method for pyrolysis kettle of coal quality-based utilization and clean pretreatment system
CN111721122A (en) Cement sintering system and automatic optimization searching control system thereof
CN110766234A (en) Cement cooling process grate pressure prediction method based on information fusion
CN111413931A (en) Self-adaptive industrial process monitoring method based on sliding window recursion principal component analysis
KR20180022030A (en) Cement Lime Sintering Process Temperature Prediction System and Method using the Neural Network Learning
CN114066212A (en) Unit lifting load working condition optimizing method based on historical working conditions
CN113657484B (en) Method for dividing and identifying typical working conditions of cement grate cooler
Ziatabari et al. Cement rotary kiln control: A supervised adaptive model predictive approach
JP7466823B2 (en) Process management support device, support method, support program, and support system
CN112183642A (en) Method and system for detecting coal consumption of cement firing based on random forest model
CN113339307A (en) Method for controlling rotating speed of high-temperature fan of rotary cement kiln based on excess air coefficient
Martin et al. Next generation controllers for kiln/cooler and mill applications based on model predictive control and neural networks
Tsamatsoulis et al. PID parameterization of cement kiln precalciner based on simplified modeling
CN112596391A (en) Deep neural network large time lag system dynamic modeling method based on data driving
Hernández et al. Model reference adaptive temperature control of a rotary cement kiln
CN117824372A (en) Multi-working-condition optimizing control method for grate cooler
Blevins et al. Wireless model predictive control applied for dividing wall column control

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