CN115237180B - Intelligent control method for crude product preparation in methyl ester production - Google Patents

Intelligent control method for crude product preparation in methyl ester production Download PDF

Info

Publication number
CN115237180B
CN115237180B CN202211161702.9A CN202211161702A CN115237180B CN 115237180 B CN115237180 B CN 115237180B CN 202211161702 A CN202211161702 A CN 202211161702A CN 115237180 B CN115237180 B CN 115237180B
Authority
CN
China
Prior art keywords
reactor
methyl ester
air pressure
cluster
production process
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
CN202211161702.9A
Other languages
Chinese (zh)
Other versions
CN115237180A (en
Inventor
孔意
韩绍滋
隗浩
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.)
Jinan Mingxin Pharmaceutical Co ltd
Original Assignee
Jinan Mingxin Pharmaceutical Co ltd
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 Jinan Mingxin Pharmaceutical Co ltd filed Critical Jinan Mingxin Pharmaceutical Co ltd
Priority to CN202211161702.9A priority Critical patent/CN115237180B/en
Publication of CN115237180A publication Critical patent/CN115237180A/en
Application granted granted Critical
Publication of CN115237180B publication Critical patent/CN115237180B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D23/00Control of temperature
    • G05D23/19Control of temperature characterised by the use of electric means
    • G05D23/20Control of temperature characterised by the use of electric means with sensing elements having variation of electric or magnetic properties with change of temperature
    • CCHEMISTRY; METALLURGY
    • C07ORGANIC CHEMISTRY
    • C07CACYCLIC OR CARBOCYCLIC COMPOUNDS
    • C07C67/00Preparation of carboxylic acid esters
    • C07C67/39Preparation of carboxylic acid esters by oxidation of groups which are precursors for the acid moiety of the ester
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Chemical & Material Sciences (AREA)
  • Organic Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Organic Low-Molecular-Weight Compounds And Preparation Thereof (AREA)

Abstract

The invention relates to the technical field of methyl ester production control, in particular to an intelligent control method for crude product preparation in methyl ester production, which is based onNDetermining the stability index of the esterification reaction by the temperature value and the pressure value corresponding to each moment of the reactor in the production process of the methyl ester, further determining the difference distance corresponding to the reactor in the production process of any two times of the methyl ester, and according to the difference distanceNThe production of methine esters is divided into two clusters; determining similar indexes of the corresponding air pressure change of the reactor in any two methyl ester production processes in each cluster, and further determining membership degrees; and acquiring a corresponding air pressure fitting curve of the reactor, determining an upper air pressure limit envelope curve and a lower air pressure limit envelope curve corresponding to each cluster, acquiring a pressure value corresponding to each moment of a future set time period of the reactor, and regulating and controlling corresponding equipment in the methyl ester production process. The invention solves the problem of poor accuracy of the control and adjustment result of the existing methyl ester production, and improves the accuracy of the methyl ester production control.

Description

Intelligent control method for crude product preparation in methyl ester production
Technical Field
The invention relates to the technical field of methyl ester production control, in particular to an intelligent control method for crude product preparation in methyl ester production.
Background
With the increase of the demand of methyl acrylate and the decrease of the price of propylene, many manufacturers promote the industrial development of the synthesis of methyl acrylate by using the low-price, large-scale and easily-controlled air oxidation method. Under the influence of the chemical characteristics of methyl acrylate, other products are generated in the reaction process of methyl acrylate, and in order to ensure that the production of methyl acrylate is developed towards the expected direction, the variables of relevant equipment in the production process of methyl acrylate need to be controlled so as to ensure that the esterification reaction conditions are in a proper state and ensure the production quality.
In order to accurately control the relevant data of the reaction environment in the production process of methyl ester and ensure the quality of the produced products, the method and the device for controlling the production of the PBT (Polybutylene terephthalate) composite material with the publication number of CN113041978A are provided at present. According to the method, the rotating speed is adjusted through the acquired temperature data information, so that the control of the temperature data in the production process is realized, but the method only considers the temperature data in the methyl ester production process, does not consider the change of the reaction degree, considers fewer related production factors, and causes incomplete control of the methyl ester production, so that the final control regulation and control result is not ideal. In addition, temperature data in the production process of methyl ester is constantly changed, and the temperatures corresponding to different reaction progress degrees have fluctuation differences, so that adjustment according to the current data has a certain delay, and the problems of untimely control and inaccurate adjustment result are easily caused, thereby further influencing the subsequent progress of methyl ester production.
Disclosure of Invention
In order to solve the technical problem of low accuracy of the existing methyl ester production control adjustment result, the invention aims to provide an intelligent control method for crude product preparation in methyl ester production, and the adopted technical scheme is as follows:
one embodiment of the invention provides an intelligent control method for crude product preparation in methyl ester production, which comprises the following steps:
obtainingNThe temperature and pressure values corresponding to each moment of the reactor in the process of producing the methine ester, andNthe feeding amount and the alcohol acid ratio corresponding to a reactor for producing the methyl hypoxide;
according toNDetermining the temperature value and the pressure value corresponding to each moment of the reactor in the production process of the methyl hypoxideNThe stable index of the esterification reaction corresponding to the reactor in the production process of the methyl hypoxide;
according to any two methyl ester production processesThe stable index of the esterification reaction corresponding to the reactor and the temperature value corresponding to each moment are determined, the difference distance corresponding to the reactor in the production process of methyl ester in any two times is determined, and the difference distance is calculated according to the difference distanceNThe production of the methine ester is divided into two clusters, wherein the two clusters are a normal cluster and an abnormal cluster;
determining a similar index of the corresponding air pressure change of the reactor in the production process of the methyl ester in any two times in each cluster according to the pressure value corresponding to each moment of the reactor in the production process of the methyl ester in any two times in each cluster and the ratio of the corresponding feeding amount of the reactor to the alcohol acid, and determining the corresponding membership degree of the reactor in each production process of the methyl ester in each cluster according to the similar index of the air pressure change;
acquiring a corresponding air pressure fitting curve of a reactor in each methyl ester production process in each cluster, and determining an upper air pressure limit envelope line and a lower air pressure limit envelope line corresponding to each cluster according to the corresponding air pressure fitting curve and membership degree of the reactor;
inputting the pressure value corresponding to each moment of the current set time period of the reactor and the feeding amount and alcohol acid ratio value corresponding to the reactor, which are obtained in real time, into a pre-constructed and trained pressure prediction neural network to obtain the pressure value corresponding to each moment of the future set time period of the reactor;
and regulating and controlling corresponding equipment in the methyl ester production process according to the pressure value corresponding to each moment of the future set time period of the reactor and the air pressure upper limit envelope line and the air pressure lower limit envelope line corresponding to each cluster.
Further, determiningNThe method for stabilizing the esterification reaction index corresponding to the reactor in the production process of the methine comprises the following steps:
according toNDetermining a temperature suitable index corresponding to the reactor in each preset time period according to the temperature value corresponding to each moment of the reactor in the process of producing the methyl ester;
according toNDetermining the pressure value corresponding to each moment of the reactor in the production process of the methyl ester and the suitable temperature index corresponding to the preset time periodNThe stable index of the esterification reaction corresponding to the reactor in the production process of the methyl hypoxide and the calculation formula thereofComprises the following steps:
Figure 368803DEST_PATH_IMAGE002
wherein the content of the first and second substances,Kis composed ofNThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,
Figure DEST_PATH_IMAGE003
is a sequence formed by the temperature suitability indexes corresponding to the reactors in each preset time period,Apis composed ofNA sequence of pressure values corresponding to each moment of the reactor in the process of producing the methine ester,Ap std is a standard pressure sequence for reactors in the methyl ester production process,
Figure 735063DEST_PATH_IMAGE004
in order to correct the coefficients of the coefficients,mean() In order to perform the averaging function, the average value,tanh() Is a function of the tangent of a hyperbola,DTW() To find a similarity distance function.
Further, the step of determining the temperature suitability index corresponding to the reactor in each preset time period comprises:
according toNAt each moment of the reactor in the process of the production of the hypomethyl ester, theNDividing each moment of the reactor in the production process of the secondary methyl ester into a plurality of preset time periods, and further calculating the temperature mean value and the temperature variance corresponding to the reactor in each preset time period;
obtaining a standard temperature value corresponding to a reactor in the production process of methyl ester, and determining a temperature suitability index corresponding to the reactor in each preset time period according to the temperature mean value and the temperature variance corresponding to the reactor in each preset time period and the standard temperature value corresponding to the reactor, wherein the calculation formula of the temperature suitability index is as follows:
Figure 947869DEST_PATH_IMAGE006
wherein the content of the first and second substances,Hthe corresponding temperature suitable index of the reactor in each preset time period,Tis a sequence of temperature values corresponding to each moment of time of the reactor in each preset time interval,t std is a standard temperature value corresponding to a reactor in the production process of the methyl ester,
Figure DEST_PATH_IMAGE007
in order to correct the coefficients of the coefficients,exp() Is an exponential function with a natural constant as the base,abs() In order to solve the function of the absolute value,mean() In order to perform the averaging function, the average value,Var() To find the variance function.
Further, the step of determining the corresponding differential distance between the reactors in any two methyl ester production processes comprises:
calculating the difference value of the esterification reaction stability indexes corresponding to the reactors in the methyl ester production processes of any two times according to the esterification reaction stability indexes corresponding to the reactors in the methyl ester production processes of any two times;
calculating the similar distance between the temperature value sequences of the reactors in the methyl ester production process of any two times according to the temperature value corresponding to each moment of the reactors in the methyl ester production process of any two times;
determining the difference distance corresponding to the reactor in any two times of methyl ester production processes according to the similar distance between the esterification reaction stability index difference value corresponding to the reactor in any two times of methyl ester production processes and the temperature value sequence, wherein the calculation formula is as follows:
Figure DEST_PATH_IMAGE009
wherein the content of the first and second substances,R(A,B) Is as followsASecond and thirdBThe corresponding differential distance of the reactor in the process of producing the methyl hypoxide,K A is a firstAThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,K B is a firstBThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,
Figure 902925DEST_PATH_IMAGE010
is as followsAProduction of hypomethylesterThe temperature values corresponding to each moment of the reactor in the process form a sequence,
Figure DEST_PATH_IMAGE011
is as followsBA sequence of temperature values corresponding to each moment of the reactor during the production of the methine ester,exp() Is an exponential function with a natural constant as the base,DTW() To find a similarity distance function.
Further, the calculation formula for determining the similar index of the corresponding air pressure change of the reactor in any two methyl ester production processes in each cluster is as follows:
Figure DEST_PATH_IMAGE013
wherein the content of the first and second substances,u(A,B) For the first in each clusterASecond and thirdBThe corresponding air pressure change of the reactor in the production process of the methyl hypoxide has similar indexes,Ap A is as followsAA sequence of pressure values corresponding to each moment of the reactor during the production of the hypomethylester,Ap B is as followsBA sequence of pressure values corresponding to each moment of the reactor during the production of the hypomethylester,m A is as followsAThe corresponding feeding amount of the reactor in the production process of the methyl hypo-ester,m B is as followsBThe corresponding feeding amount of the reactor in the production process of the methyl hypo-ester,n A is as followsAThe ratio of the corresponding alcohol acid in the reactor in the production process of the methyl hypoxide,n B is as followsBThe ratio of the corresponding alcohol acid in the reactor in the production process of the methyl hypoxide,exp() Is an exponential function with a natural constant as the base,Range() In order to find the function of the pole difference,MSD() In order to find the function of the distance of the morphological difference,abs() As a function of absolute value.
Further, determining the membership corresponding to the reactor in each methyl ester production process in each cluster according to the similar index of the air pressure change, wherein the method comprises the following steps:
according to the similar indexes of the air pressure change corresponding to the reactors in the methyl ester production process of any two times in each cluster, determining a plurality of similar indexes of the air pressure change corresponding to the reactors in the methyl ester production process of each time in each cluster, calculating the accumulated value of the plurality of similar indexes of the air pressure change, and taking the accumulated value as the membership corresponding to the reactors in the methyl ester production process of each time.
Further, the step of determining the corresponding air pressure upper limit envelope line and air pressure lower limit envelope line of each cluster includes:
determining a preset number of target membership degrees in each cluster according to the corresponding membership degree of the reactor in each methyl ester production process in each cluster;
determining an air pressure fitting curve corresponding to the preset number of target membership degrees in each cluster according to the preset number of target membership degrees in each cluster and the air pressure fitting curve corresponding to the reactor in each methyl ester production process;
determining the maximum value and the minimum value of the air pressure corresponding to each moment in the air pressure fitting curves corresponding to the preset number of target membership degrees in each cluster according to the air pressure fitting curves corresponding to the preset number of target membership degrees in each cluster;
and determining the air pressure upper limit envelope line and the air pressure lower limit envelope line corresponding to each cluster according to the air pressure maximum value and the air pressure minimum value corresponding to each moment.
Further, the step of regulating and controlling corresponding equipment in the methyl ester production process comprises:
if the pressure value corresponding to a certain moment of the future set time period of the reactor is higher than the upper limit envelope of the air pressure corresponding to any cluster, reducing the pressure value corresponding to the moment of the reactor, and if the pressure value corresponding to the certain moment of the future set time period of the reactor is lower than the lower limit envelope of the air pressure corresponding to any cluster, increasing the pressure value corresponding to the moment of the reactor until the pressure value corresponding to the moment of the reactor is at the preset position of the interval corresponding to the upper limit envelope and the lower limit envelope of the air pressure corresponding to the normal cluster, wherein the interval is formed by constructing the upper limit envelope and the lower limit envelope of the air pressure.
The invention has the following beneficial effects:
the invention provides an intelligent control method for crude product preparation in methyl ester production, aiming at determiningNThe reaction conditions and states of the reactor during the production of the hypomethylester are determined by comparing the obtainedNCarrying out data analysis on the temperature value and the pressure value corresponding to each moment of the reactor in the production process of the methyl ester to obtain an esterification reaction stability index corresponding to the reactor, wherein the index comprises two factors: the temperature and the pressure are beneficial to improving the referability of the stable index of the esterification reaction, and the relevant factors of the methyl ester production are comprehensively considered, so that the subsequent analysis of the difference between any two methyl ester production processes is facilitated; determining the difference distance corresponding to the reactor in the methyl ester production process of any two times according to the esterification reaction stability index corresponding to the reactor in the methyl ester production process of any two times and the temperature value corresponding to each moment, and taking each difference distance as the index for dividing the cluster, which is beneficial to increasing the accuracy of the dividing result and facilitating the subsequent adjustment of relevant parameters of the esterification reaction based on the dividing result; the method comprises the steps of determining the similar indexes of the air pressure change corresponding to the reactors in the methyl ester production process of any two times in each cluster, and determining the membership degree corresponding to the reactors in the methyl ester production process of each time in each cluster according to the similar indexes of the air pressure change, wherein the membership degree is an important index for determining the air pressure upper limit envelope and the air pressure lower limit envelope corresponding to each cluster, so that the calculation amount during envelope determination is reduced, and the timeliness and the efficiency of methyl ester production control are improved. Corresponding equipment in the methyl ester production process is regulated and controlled based on the pressure value corresponding to each moment of the reactor in the future set time period and the air pressure upper limit envelope line and the air pressure lower limit envelope line corresponding to each cluster, so that the relevant data of methyl ester production can be timely regulated, the accuracy of the methyl ester production data regulation result is improved, and the quality of crude product preparation in the methyl ester production is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of an intelligent control method for crude product preparation in methyl ester production according to the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the technical solutions according to the present invention will be given with reference to the accompanying drawings and preferred embodiments. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
This example provides an intelligent control method for crude product preparation in methyl ester production, as shown in fig. 1, the method comprises the following steps:
(1) ObtainingNThe temperature and pressure values corresponding to each moment of the reactor during the production of the methine ester, anNReactor for the production of the methine ester corresponds to the feed rate and the alkyd ratio.
It should be noted that the esterification reaction of methyl ester is a reversible reaction, so the temperature, pressure, catalyst and reactant ratio in the production process of methyl ester can all affect the direction and rate of the esterification reaction, and the temperature value of the reactor can change when a large amount of reactants remained in the reactor are recovered, which can also affect the progress of the esterification reaction. Therefore, in order to improve the comprehensiveness and accuracy of the methyl ester production control, the crude product preparation in the methyl ester production is subjected to production control analysis based on the temperature value, pressure value, feed amount and alkyd ratio of the reactor.
(1-1) obtainingNFor each moment of the reactor in the process of producing hypomethylesterA temperature value. In this embodiment, before the esterification reaction, the reactor is heated by a preheater to reach a suitable temperature, which is about 75 ℃.NBy the production of methine estersNThe complete process for the secondary production of methyl ester,Nmay be set to 10. The conventional digital thermometer is adopted to collect the temperature value corresponding to each moment of the reactor in the production process of 10 times of methyl ester, and the sampling frequency of the temperature is 1HzI.e. collecting a temperature value every second, and recording the temperature value ast
(1-2) obtainingNThe pressure value corresponding to each moment of the reactor during the production of the methine ester. Since the boiling point of methanol is about 65 ℃ and the temperature of the esterification reaction in the reactor is 78 ℃, methanol exists in the form of gas. The pressure in the reactor influences the shift of the equilibrium of the esterification reaction, and further influences the change of the temperature value in the reactor. Placing a barometer in the reactor for collectionNThe sampling frequency of the pressure is 1HzI.e. once per second, the pressure values are recordedap
(1-3) obtainingNReactor for the production of the methine ester corresponds to the feed rate and the alkyd ratio. In the esterification reaction process, not only alcohol and acid added from the outside but also unreacted alcohol and acid exist in the reactor, which can cause the total amount and proportion of reactants to be improper, and other byproducts can be generated when the esterification reaction is carried out based on the improper proportion of the reactants, thereby reducing the quality of the product produced from the methyl ester, so that the corresponding feeding amount of the reactor and the ratio of the alcohol to the acid during the production of the methyl ester need to be determined. Before esterification reaction, the opening size and the feeding time of a feeding hole of the reactor are obtained, the feeding amount corresponding to the opening size is multiplied by the feeding time to obtain the total amount of reactants, and then the ratio of the alcohol acid in the reactor is determined according to the total amount of the reactants, wherein the opening size refers to the rotating angle of the disc plate.
(2) According toNDetermining the temperature value and the pressure value corresponding to each moment of the reactor in the production process of the methineNEsterification reaction corresponding to reactor in production process of methyl hypoxideA stability indicator comprising the steps of:
(2-1) according toNThe method comprises the following steps of determining a temperature suitable index corresponding to a reactor in each preset time period by using a temperature value corresponding to each moment of the reactor in the production process of the methyl ester, wherein the temperature suitable index comprises the following steps:
(2-1-1) according toNAt each moment of the reactor in the process of the production of the hypomethyl ester, theNAnd dividing each moment of the reactor in the production process of the secondary methyl ester into a plurality of preset time periods, and further calculating the corresponding temperature mean value and temperature variance of the reactor in each preset time period.
In the present embodiment, based onNAt each moment of the reactor in the production of methine, a construction window of 30 was establishedsThe sliding window is utilized to carry out sliding window processing on the temperature value corresponding to each moment, and the sliding window slides backwards for one moment every one secondNEach time of the reactor in the process of producing the methine ester is divided into a plurality of sliding window areas, and the sliding window areas are compared with the preset time period, so that the embodiment canNEach time of the reactor in the process of producing the methyl ester is divided into a plurality of preset time periods, and each preset time period has 30 temperature value data. In order to facilitate the subsequent determination of the temperature suitability index corresponding to the reactor in each preset time period, the temperature mean value and the temperature variance corresponding to the reactor in each preset time period are calculated based on the temperature value corresponding to each moment in the preset time period. The process of calculating the temperature mean and the temperature variance is prior art and is not within the scope of the present invention, and will not be described in detail herein.
(2-1-2) obtaining a standard temperature value corresponding to the reactor in the methyl ester production process, and determining a temperature suitability index corresponding to the reactor in each preset time period according to the temperature mean value and the temperature variance corresponding to the reactor in each preset time period and the standard temperature value corresponding to the reactor.
In this embodiment, the standard temperature value corresponding to the reactor in the methyl ester production process is obtained to facilitate determining a difference between a temperature mean value corresponding to the preset time period and the standard temperature value, and the temperature variance may reflect a fluctuation condition of the temperature value in the preset time period, and a suitable temperature index corresponding to the reactor in the preset time period is analyzed from two angles, so that a referenceable property of the suitable temperature index can be improved, where the suitable temperature index refers to a suitable condition of the temperature in the reactor in the preset time period, and a calculation formula of the suitable temperature index is as follows:
Figure 294549DEST_PATH_IMAGE006
wherein the content of the first and second substances,Hthe corresponding temperature suitable index of the reactor in each preset time period,Tis a sequence formed by temperature values corresponding to each moment in each preset time interval of the reactor,t std is a standard temperature value corresponding to a reactor in the production process of methyl ester,
Figure 944842DEST_PATH_IMAGE007
in order to correct the coefficients of the coefficients,exp() Is an exponential function with a natural constant as the base,abs() In order to solve the function of the absolute value,mean() In order to perform the averaging function, the average value,Var() To find the variance function.
It should be noted that, in the present embodiment, the standard temperature value is set to 78 ℃, and the correction coefficient is set
Figure 226918DEST_PATH_IMAGE007
Set to 0.1, in the calculation formula for the temperature suitability index
Figure 646267DEST_PATH_IMAGE014
The approximation degree of the temperature mean value corresponding to the preset time period and the standard temperature value is shown, the standard temperature value can also be called as an appropriate temperature, when the temperature mean value is closer to the appropriate temperature, the temperature suitability of the preset time period corresponding to the temperature mean value is relatively strong, then the temperature suitability index corresponding to the reactor is relatively large,
Figure 355597DEST_PATH_IMAGE014
andHis a negative correlation. In the calculation formula of the temperature suitability index
Figure DEST_PATH_IMAGE015
The centralized stability of the temperature value data in the preset time period is shown, when the temperature variance is smaller, the more stable the temperature value change in the preset time period corresponding to the temperature variance is, the more appropriate the temperature value of the reactor is, the larger the appropriate temperature index corresponding to the reactor is,
Figure 867088DEST_PATH_IMAGE015
andHis a negative correlation.
(2-2) according toNThe pressure value corresponding to each moment of the reactor in the production process of the methenyl ester and the temperature suitable index corresponding to the preset time interval are determinedNThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide.
Firstly, it should be noted that two main factors influencing the change of the esterification reaction in the reactor are temperature value and pressure value, when the temperature and the air pressure in the reactor are normal, the esterification reaction condition in the reactor is stable, and when the esterification reaction condition is stable, the quality of the produced methyl ester product is higher.
To determine the degree of stability of the esterification reaction conditions corresponding to the reactor each time a methyl ester is produced, based onNObtaining a standard air pressure sequence of the reactor in the methyl ester production process by using a pressure value corresponding to each moment of the reactor in the methyl ester production process and a temperature suitable index corresponding to a preset time period, wherein the number of the pressure values in the standard air pressure sequence is the same as that of the pressure values corresponding to each moment of the reactor in the methyl ester production process, and calculatingNThe stable index of the esterification reaction corresponding to the reactor in the production process of the methyl hypoxide, and the calculation formula of the stable index of the esterification reaction is as follows:
Figure 687276DEST_PATH_IMAGE002
wherein the content of the first and second substances,Kis composed ofNThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,
Figure 757869DEST_PATH_IMAGE003
is a sequence formed by the temperature suitability indexes corresponding to the reactors in each preset time period,Apis composed ofNA sequence of pressure values corresponding to each moment of the reactor during the production of the hypomethylester,Ap std is a standard pressure sequence of the reactor in the methyl ester production process,
Figure 638101DEST_PATH_IMAGE004
in order to correct the coefficients of the coefficients,mean() In order to perform the averaging function, the average value,tanh() Is a function of the tangent of a hyperbola,DTW() To find a similarity distance function.
It should be noted that the present embodiment corrects the coefficient
Figure 268845DEST_PATH_IMAGE004
Setting as 0.3, the hyperbolic tangent function in the calculation formula of the stability index of the esterification reactiontanh() Can be used for normalization, which is helpful for the calculation of the stability index of the esterification reaction. In the calculation formula
Figure 423883DEST_PATH_IMAGE016
The similar distance between the pressure value sequence and the standard gas pressure sequence is shown, the larger the similar distance value is, the more dissimilar the two sequences are, on the contrary, the more similar the two sequences are, and the stable esterification reaction condition is shown when the two sequences are similar. In the calculation formula
Figure DEST_PATH_IMAGE017
The average value of the suitable temperature indexes corresponding to the reactor in each preset time period is shown, and the larger the average value of the suitable temperature indexes is, the more stable the esterification reaction conditions corresponding to the reactor in the methyl ester production process is.
(3) Determining the difference distance corresponding to the reactor in the methyl ester production process for any two times according to the esterification reaction stability index corresponding to the reactor in the methyl ester production process for any two times and the temperature value corresponding to each moment, and determining the difference distance according to the difference distanceNThe methine production is divided into two clusters, a normal cluster and an abnormal cluster.
Because methyl ester production is continuous process, there are the step of feeding and ejection of compact many times in this process, the feeding all has corresponding ejection of compact every time, the process of feeding to the ejection of compact is methyl ester production once, the reactor environment in methyl ester production process all can change every time, on the basis of the stable index of the esterification reaction that the reactor in arbitrary twice methyl ester production process corresponds and the temperature value that every moment corresponds, carry out comparative analysis to the state of methyl ester production at every turn, its step includes:
(3-1) determining the difference distance corresponding to the reactor in the methyl ester production process for any two times according to the esterification reaction stability index corresponding to the reactor in the methyl ester production process for any two times and the temperature value corresponding to each moment, wherein the step comprises the following steps:
(3-1-1) calculating the difference value of the esterification reaction stability indexes corresponding to the reactors in the methyl ester production process for any two times according to the esterification reaction stability indexes corresponding to the reactors in the methyl ester production process for any two times.
In this embodiment, in order to facilitate subsequent determination of the difference distance corresponding to the reactor in any two methyl ester production processes, the esterification stability indicators corresponding to the reactors in any two methyl ester production processes are subtracted from each other, so as to obtain the esterification stability indicator difference corresponding to the reactors in any two methyl ester production processes.
(3-1-2) calculating the similar distance between the temperature value sequences of the reactors in the methyl ester production process for any two times according to the temperature value corresponding to each moment of the reactors in the methyl ester production process for any two times.
In this embodiment, since the reactor temperature fluctuates significantly due to the feeding and discharging in the methyl ester production process, in order to facilitate the subsequent determination of the differential distance corresponding to the reactor in any two methyl ester production processes, the dynamic time warping algorithm is used to calculate the similarity distance between the temperature value sequences of the reactors in any two methyl ester production processes based on the sequence formed by the temperature values corresponding to each moment of the reactors in any two methyl ester production processes. The implementation process of the dynamic time warping algorithm is the prior art and is not within the scope of the present invention, and will not be elaborated herein.
(3-1-3) determining the difference distance corresponding to the reactor in any two methyl ester production processes according to the similar distance between the esterification reaction stability index difference value and the temperature value sequence corresponding to the reactor in any two methyl ester production processes.
In this embodiment, in order to facilitate subsequent determination of the normal cluster and the abnormal cluster, based on the similarity distance between the difference value of the stability index of the esterification reaction and the temperature value sequence calculated in the step (3-1-1) and the step (3-1-2), the difference distance corresponding to the reactor in any two methyl ester production processes is calculated, and the calculation formula is as follows:
Figure DEST_PATH_IMAGE019
wherein, the first and the second end of the pipe are connected with each other,R(A,B) Is a firstASecond and thirdBThe corresponding differential distance of the reactor in the process of producing the methyl hypoxide,K A is a firstAThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,K B is a firstBThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,
Figure 817824DEST_PATH_IMAGE010
is as followsAA sequence of temperature values corresponding to each moment of the reactor during the production of the methine ester,
Figure 118225DEST_PATH_IMAGE011
is as followsBA sequence of temperature values corresponding to each moment of the reactor during the production of the methine ester,exp() Is an exponential function with a natural constant as the base,DTW() To find a similarity distance function.
Note that in the difference distance calculation formula
Figure 777876DEST_PATH_IMAGE020
The square difference of the stable index of the esterification reaction is positively correlated with the difference distance, and the larger the square difference is, the two are shownThe difference between the stability of the esterification reaction corresponding to the reactors in the production process of the methyl ester is larger, so that the difference distance between the reactors in the production process of the two methyl esters is larger. In formula for calculating difference distance
Figure DEST_PATH_IMAGE021
The method shows whether the working temperature control of the preheater in the two methyl ester production processes is similar or not, and the larger the similar distance between the two temperature sequences is, the larger the difference distance between the reactors in the methyl ester production processes corresponding to the two temperature sequences is.
(3-2) according to the difference distanceNThe methine production is divided into two clusters, a normal cluster and an abnormal cluster.
In this embodiment, two clustering centroids are set, and a k-means clustering algorithm is used to pairNAnd clustering and grouping the different distances corresponding to the reactors in the production process of the methyl hypo-acetate to obtain two clusters. Because the preheater power is not regulated to the right position and the amounts of the recovered acid and the recovered alcohol are different, the temperature change in the final reaction process is also different, so that two different clusters can be formed, and the number of the clustering mass centers is set to be two in the embodiment.
To facilitate the discrimination of the two clusters, the amount and composition of each product methyl acrylate within the two clusters can be analyzed, and the properties of the two clusters, i.e., normal and abnormal clusters, can be determined based on the final analysis results. For example, a mass spectrometer is used for analyzing the product methyl acrylate corresponding to each methyl ester production process in the two clusters to obtain the molecular weight, the functional group, the fragments generated by molecular breakage and the relationship among the fragments corresponding to the product methyl acrylate obtained by methyl ester production each time, and the component values corresponding to the product methyl acrylate obtained by methyl ester production each time are compared with the standard map of the known methyl acrylate, so that the normal cluster and the abnormal cluster can be distinguished, specifically: the clusters with high similarity to the standard map are normal clusters, and the clusters with low similarity to the standard map are abnormal clusters. Of course, there are many ways to distinguish between abnormal clusters and normal clusters, and detailed description thereof is omitted.
(4) Determining similar indexes of the air pressure change corresponding to the reactors in the methyl ester production process of any two times in each cluster according to the pressure value corresponding to each moment of the reactors in the methyl ester production process of any two times in each cluster and the feeding quantity and the alcohol acid ratio corresponding to the reactors, and determining the membership corresponding to the reactors in the methyl ester production process of each time in each cluster according to the similar indexes of the air pressure change, wherein the method comprises the following steps:
(4-1) determining similar indexes of the corresponding air pressure change of the reactor in any two methyl ester production processes in each cluster according to the pressure value corresponding to each moment of the reactor in any two methyl ester production processes in each cluster and the corresponding feeding amount and alkyd ratio of the reactor.
In the esterification reaction process, most of gas exists in a gaseous form of methanol, part of methanol is consumed in the reaction process to generate ester compounds, the process of generating the ester compounds is an exothermic reaction process, along with the reaction, the change process of the air pressure in the reactor is complex, the air pressure change trends in different production states in each cluster need to be compared and analyzed, namely the similar indexes of the air pressure change corresponding to the reactor in the production process of methyl ester in any two times in each cluster are determined, and the calculation formula of the similar indexes of the air pressure change is as follows:
Figure 126818DEST_PATH_IMAGE022
wherein the content of the first and second substances,u(A,B) For the first in each clusterASecond and thirdBThe corresponding pressure change of the reactor in the production process of the methyl hypoxide has similar indexes,Ap A is as followsAA sequence of pressure values corresponding to each moment of the reactor in the process of producing the methine ester,Ap B is as followsBA sequence of pressure values corresponding to each moment of the reactor during the production of the hypomethylester,m A is as followsAThe corresponding feeding amount of the reactor in the production process of the methyl hypo-ester,m B is as followsBReactor feed in the production of methine estersThe amount of the compound (A) is,n A is as followsAThe ratio of the corresponding alcohol acid in the reactor in the production process of the methyl hypoxide,n B is a firstBThe ratio of the corresponding alcohol acid in the reactor in the production process of the methyl hypoxide,exp() Is an exponential function with a natural constant as the base,Range() In order to find the function of the pole difference,MSD() In order to find the function of the distance of the morphological difference,abs() As a function of absolute value.
It should be noted that the formula for calculating the similar index of the air pressure variation
Figure DEST_PATH_IMAGE023
For comparison ofASecond and thirdBThe difference distance between the pressure change sequences corresponding to the second methyl ester production process is smaller, and the two pressure change sequences are more similar when the form difference distance of the two pressure change sequences is smaller, so that the air pressure change similarity indexes corresponding to the two pressure change sequences are larger.
Figure 516211DEST_PATH_IMAGE024
For obtaining the firstAThe data change range of the methyl ester production process is large, and if the absolute value of the difference value of the pressure range values corresponding to the two methyl ester production processes is smaller, the pressure change trends in the two methyl ester production processes are more similar. When the ratio of the feeding amount to the alkyd in the two methyl ester production processes is similar, that is to say
Figure DEST_PATH_IMAGE025
And
Figure 925195DEST_PATH_IMAGE026
the smaller the pressure fluctuations in the two methyl ester production processes will be the closer.
(4-2) determining the membership corresponding to the reactor in each methyl ester production process in each cluster according to the similar index of the air pressure change, wherein the method comprises the following steps:
according to the similar indexes of the air pressure change corresponding to the reactors in the methyl ester production process in any two times in each cluster, determining a plurality of similar indexes of the air pressure change corresponding to the reactors in each methyl ester production process in each cluster, calculating the accumulated value of the plurality of similar indexes of the air pressure change, and taking the accumulated value as the membership degree corresponding to the reactors in each methyl ester production process.
In this embodiment, in order to more accurately evaluate the pressure variation trend corresponding to each methyl ester production process in each cluster, and facilitate subsequent determination of the pressure upper limit envelope and the pressure lower limit envelope corresponding to each cluster, based on the pressure variation similar indexes corresponding to the reactors in any two methyl ester production processes in each cluster, the pressure variation similar indexes corresponding to the reactors in any one methyl ester production process in each cluster and the reactors in other methyl ester production processes in the cluster are obtained, that is, a plurality of pressure variation similar indexes corresponding to the reactors in each methyl ester production process in each cluster are obtained, the plurality of pressure variation similar indexes are added, the added numerical value is used as the membership degree corresponding to the corresponding reactor, and the calculation formula for determining the membership degree corresponding to the reactor in each methyl ester production process is as follows:
Figure 524673DEST_PATH_IMAGE028
wherein the content of the first and second substances,L A for the first in each clusterAThe degree of membership corresponding to the reactor in the process of producing the methyl ester,u(A,X) For the first in each clusterAThe reactor in the production process of the hypo-methyl ester corresponds to the secondXThe pressure change is similar to the index.
It is to be noted that the first in a clusterAThe reactor in the production process of the hypo-methyl ester corresponds to the secondXThe similar index of the air pressure change refers to the first index in the clusterAReactor and the second stage in the production of methineXThe pressure change calculated by the reactor in other methyl ester production processes is similar to the index, and other methyl ester production processes do not comprise the methyl ester production process. For example, there are a total of 4 methyl ester-forming processes in any cluster, denoted as: (a1,a2,a3,a4) Each methyl ester production process has 3 other methyl ester production processes corresponding to the methyl ester production process,a1 pair ofThe 3 other methyl ester production processes area2、a3 anda4。
(5) And acquiring a corresponding air pressure fitting curve of the reactor in each methyl ester production process in each cluster, and determining the corresponding air pressure upper limit envelope line and the corresponding air pressure lower limit envelope line of each cluster according to the corresponding air pressure fitting curve and the membership degree of the reactor.
In the present embodiment, based onNAnd (3) carrying out curve fitting treatment on the pressure value corresponding to each moment of the reactor in each methyl ester production process in each cluster to obtain the air pressure fitting curve corresponding to the reactor in each methyl ester production process in each cluster.
Since the esterification reaction process is complicated and the amount of methanol involved in the reaction is different, the pressure fluctuation corresponding to the reactor for producing methyl ester is obviously different from the standard expected pressure, and the difference may change when producing methyl ester again, therefore, the present embodiment determines the fluctuation range of the reactor pressure according to the pressure fitting curve and the membership degree corresponding to the reactor in each methyl ester production process in each cluster. The method specifically comprises the following steps: determining the corresponding upper envelope curve and lower envelope curve of the air pressure limit and the corresponding lower envelope curve of each cluster according to the corresponding air pressure fitting curve and membership degree of the reactor, wherein the method comprises the following steps:
(5-1) determining a preset number of target membership degrees in each cluster according to the corresponding membership degree of the reactor in each methyl ester production process in each cluster.
In order to improve the accuracy of the subsequently determined air pressure upper limit envelope line and the air pressure lower limit envelope line, for a normal cluster, the maximum first 5 membership degrees in the normal cluster are used as target membership degrees, for an abnormal cluster, the minimum first 5 membership degrees in the abnormal cluster are used as target membership degrees, the preset number is set to be 5, and an implementer can set the method according to the specific actual situation. It should be noted that, in this embodiment, reference is made to membership data corresponding to the abnormal cluster, which is to facilitate subsequent determination of a safety lower limit and a safety upper limit in the methyl ester production process, and if a pressure value at a certain time is lower than the safety lower limit or higher than the safety upper limit, it is indicated that the reactor is in a fault and needs to be shut down for inspection.
And (5-2) determining the air pressure fitting curve corresponding to the preset number of target membership degrees in each cluster according to the preset number of target membership degrees in each cluster and the air pressure fitting curve corresponding to the reactor in each methyl ester production process.
It should be noted that, the reactor in each methyl ester production process has its corresponding membership degree and air pressure fitting curve, and based on the preset number of target membership degrees, the air pressure fitting curve corresponding to the preset number of target membership degrees, that is, the preset number of air pressure fitting curves corresponding to each cluster, is determined.
And (5-3) determining the maximum air pressure value and the minimum air pressure value corresponding to each moment in the air pressure fitting curves corresponding to the preset number of target membership degrees in each cluster according to the air pressure fitting curves corresponding to the preset number of target membership degrees in each cluster.
In this embodiment, a preset number of air pressure fitting curves corresponding to each cluster are collected on one graph, and a maximum pressure value and a minimum pressure value corresponding to each time of the preset number of air pressure fitting curves are screened out to obtain a maximum air pressure value and a minimum air pressure value corresponding to each time of the preset number of target membership degrees in each cluster, that is, to obtain a maximum pressure value and a minimum pressure value corresponding to each time of the preset number of air pressure fitting curves corresponding to each cluster.
And (5-4) determining the corresponding air pressure upper limit envelope line and the corresponding air pressure lower limit envelope line of each cluster according to the corresponding air pressure maximum value and air pressure minimum value at each moment.
In this embodiment, according to the maximum value and the minimum value of the air pressure corresponding to each time in the air pressure fitting curves corresponding to the preset number of target membership degrees in each cluster, the upper limit envelope and the lower limit envelope corresponding to the preset number of air pressure fitting curves are drawn, and each cluster has the corresponding upper limit envelope and lower limit envelope.
(6) And inputting the pressure value corresponding to each moment of the current set time period of the reactor and the feeding amount and alcohol acid ratio value corresponding to the reactor, which are obtained in real time, into a pre-constructed and trained pressure prediction neural network to obtain the pressure value corresponding to each moment of the future set time period of the reactor.
It should be noted that, based on the constructed and trained pressure prediction neural network, the pressure of the current esterification reactor is predicted, the abnormal fluctuation condition of the pressure is found as early as possible, the abnormal fluctuation degree of the pressure is judged, and the pressure change of the esterification reactor is controlled by adopting corresponding measures.
Firstly, a pressure prediction neural Network is constructed and trained, the pressure prediction neural Network can be used for predicting the air pressure at a future moment, the air pressure is a pressure value, and the pressure prediction neural Network is a TCN (Temporal Convolutional Network) Network. The specific training process of the pressure prediction neural network comprises the following steps: the method comprises the steps of obtaining a training sample set, wherein the training sample set is a pressure value corresponding to each moment of a reactor in the historical methyl ester production process, the training samples comprise input samples and label samples, and a damage function of a pressure prediction neural network is an MSE (Mean Squared Error) loss function. The process of constructing and training the pressure prediction neural network is prior art and is not within the scope of the present invention, and will not be described in detail herein.
Then, inputting a pressure value corresponding to each moment of the current set time period of the reactor, which is obtained in real time, and a feeding amount and an alcohol acid ratio value corresponding to the reactor into a pre-constructed and trained pressure prediction neural network, wherein the current set time period can be 1 minute, each moment can be every second, and the pre-constructed and trained pressure prediction neural network outputs a pressure value corresponding to each second in the next 1 minute. To this end, the present embodiment obtains a pressure value corresponding to each time of a future set period of the reactor.
(7) And regulating and controlling corresponding equipment in the methyl ester production process according to the pressure value corresponding to each moment of the future set time period of the reactor and the air pressure upper limit envelope line and the air pressure lower limit envelope line corresponding to each cluster.
If the pressure value corresponding to a certain moment of the future set time period of the reactor is higher than the upper limit envelope of the air pressure corresponding to any cluster, reducing the pressure value corresponding to the moment of the reactor, and if the pressure value corresponding to the certain moment of the future set time period of the reactor is lower than the lower limit envelope of the air pressure corresponding to any cluster, increasing the pressure value corresponding to the moment of the reactor until the pressure value corresponding to the moment of the reactor is at the preset position of the interval corresponding to the upper limit envelope and the lower limit envelope of the air pressure corresponding to the normal cluster, wherein the interval is formed by the upper limit envelope and the lower limit envelope of the air pressure.
In this embodiment, the pressure value corresponding to each time of the future set time period of the reactor is compared with the upper limit envelope and the lower limit envelope of the air pressure corresponding to each cluster, specifically:
(7-1) if the air pressure value corresponding to a certain future time output by the pressure prediction neural network is higher than the air pressure upper limit envelope curve corresponding to the normal cluster, opening an exhaust valve above the esterification reactor, wherein the esterification reactor is the reactor, reducing the pressure value corresponding to the reactor until the pressure value returns to the position of 60% between the air pressure upper limit envelope curve corresponding to the normal cluster and the air pressure lower limit envelope curve corresponding to the normal cluster, and thus, the target pressure value is adjusted
Figure DEST_PATH_IMAGE029
Wherein, in the step (A),
Figure 960463DEST_PATH_IMAGE030
the pressure value at the position of the envelope curve of the lower air pressure limit of the corresponding normal cluster at the moment,
Figure DEST_PATH_IMAGE031
the pressure value at the position of the air pressure upper limit envelope line of the corresponding normal cluster at the moment.
(7-2) if the air pressure value corresponding to a certain future time output by the pressure prediction neural network is lower than the air pressure lower limit envelope curve corresponding to the normal cluster, improving the temperature value of the esterification reactor, and simultaneously properly adjusting the feeding amount and the alcohol acid ratio corresponding to the reactor to improve the pressure value corresponding to the time of the reactor. In order to ensure the suitability for the esterification reaction, the temperature was adjusted to within 5 ℃.
(7-3) if the air pressure value corresponding to a certain time in the future output by the pressure prediction neural network is higher than the air pressure upper limit envelope line corresponding to the abnormal cluster, compared with (7-1), controlling an exhaust valve with a larger opening degree, and reducing the corresponding pressure value of the reactor to ensure that the pressure value is stabilized in the air pressure upper limit envelope line and the air pressure lower limit envelope line interval corresponding to the normal cluster. And if the air pressure value still continues to rise and exceeds 5% of the air pressure upper limit envelope curve corresponding to the abnormal cluster, stopping the esterification reaction detection in order to ensure the safety of the esterification reaction.
(7-4) if the pressure value corresponding to a certain future time output by the pressure prediction neural network is lower than the lower limit envelope curve of the pressure corresponding to the abnormal cluster, checking whether an exhaust valve of the esterification reactor is in a closed state, and simultaneously adding a proper amount of preheated methanol to improve the pressure value corresponding to the time of the reactor. If the air pressure value is still continuously reduced and is lower than 5% of the air pressure lower limit envelope curve corresponding to the abnormal cluster, the esterification reaction detection is stopped in order to ensure the safety of the esterification reaction.
(7-5) if the air pressure upper limit envelope line and the air pressure lower limit envelope line corresponding to the normal cluster and the abnormal cluster are approximately coincident in a certain time period, allowing the air pressure value corresponding to each moment in the time period to fluctuate within the range of about 3% of the median position of the four air pressure envelope lines, wherein the fluctuation is higher or lower than the range, and the air pressure value in the time period is abnormal.
It should be noted that, if the pressure value corresponding to a certain time in the future is in the section corresponding to the normal cluster, the pressure value corresponding to the time is kept unchanged, the pressure value corresponding to the time generally does not intersect with the section corresponding to the abnormal cluster, the section corresponding to the upper pressure limit envelope and the lower pressure limit envelope corresponding to the normal cluster is simply referred to as the section corresponding to the normal cluster, but the pressure value corresponding to the time is in the section corresponding to the abnormal cluster, and the section corresponding to the normal cluster inevitably intersects with the section corresponding to the normal cluster. Therefore, adjustment is performed in different ranges to different degrees, so as to improve the accuracy of the control adjustment result of the methyl ester production.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; the modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present application, and are included in the protection scope of the present application.

Claims (3)

1. An intelligent control method for crude product preparation in methyl ester production is characterized by comprising the following steps:
obtainingNThe temperature and pressure values corresponding to each moment of the reactor during the production of the methine ester, anNThe feeding amount and the alcohol acid ratio corresponding to a reactor for producing the methyl hypoxide;
according toNAt each moment of the reactor in the process for the production of methine esters, theNDividing each moment of the reactor in the production process of the secondary methyl ester into a plurality of preset time periods, and further calculating the temperature mean value and the temperature variance corresponding to the reactor in each preset time period;
obtaining a standard temperature value corresponding to a reactor in the production process of methyl ester, and determining a temperature suitability index corresponding to the reactor in each preset time period according to the temperature mean value and the temperature variance corresponding to the reactor in each preset time period and the standard temperature value corresponding to the reactor, wherein the calculation formula of the temperature suitability index is as follows:
Figure DEST_PATH_IMAGE001
wherein the content of the first and second substances,Hthe corresponding temperature suitable index of the reactor in each preset time period,Tis a sequence of temperature values corresponding to each moment of time of the reactor in each preset time interval,t std is a standard temperature value corresponding to a reactor in the production process of methyl ester,
Figure 683560DEST_PATH_IMAGE002
in order to correct the coefficients of the coefficients,exp() Is an exponential function with a natural constant as the base,abs() In order to solve the function of the absolute value,mean() In order to perform the averaging function, the average value,Var() Calculating a variance function;
according toNDetermining the pressure value corresponding to each moment of the reactor in the production process of the methyl ester and the suitable temperature index corresponding to the preset time periodNThe method comprises the following steps of (1) obtaining an esterification reaction stability index corresponding to a reactor in the production process of the methyl hypoxide, wherein the calculation formula of the esterification reaction stability index is as follows:
Figure 435615DEST_PATH_IMAGE003
wherein the content of the first and second substances,Kis composed ofNThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,
Figure 461340DEST_PATH_IMAGE004
is a sequence formed by the temperature suitability indexes corresponding to the reactors in each preset time period,Apis composed ofNA sequence of pressure values corresponding to each moment of the reactor during the production of the hypomethylester,Ap std is a standard pressure sequence for reactors in the methyl ester production process,
Figure 993952DEST_PATH_IMAGE005
in order to correct the coefficients of the coefficients,mean() In order to perform the averaging function, the average value,tanh() Is a function of the tangent of a hyperbola,DTW() Calculating a similarity distance function;
calculating the difference value of the esterification reaction stability indexes corresponding to the reactors in the methyl ester production processes of any two times according to the esterification reaction stability indexes corresponding to the reactors in the methyl ester production processes of any two times;
calculating the similar distance between the temperature value sequences of the reactors in the methyl ester production process of any two times according to the corresponding temperature value of the reactor in the methyl ester production process of any two times at each moment;
determining the difference distance corresponding to the reactor in any two methyl ester production processes according to the similar distance between the esterification reaction stability index difference value corresponding to the reactor in any two methyl ester production processes and the temperature value sequence, wherein the calculation formula of the difference distance is as follows:
Figure 396115DEST_PATH_IMAGE006
wherein the content of the first and second substances,R(A,B) Is as followsASecond and thirdBThe corresponding differential distance of the reactor in the process of producing the methyl hypoxide,K A is a firstAThe esterification reaction stability index corresponding to the reactor in the production process of the methyl hypoxide,K B is as followsBThe stable index of the esterification reaction corresponding to the reactor in the production process of the methyl hypoxide,
Figure 205939DEST_PATH_IMAGE007
is as followsAA sequence of temperature values corresponding to each moment of the reactor during the production of the methine ester,
Figure 402565DEST_PATH_IMAGE008
is as followsBA sequence of temperature values corresponding to each moment of the reactor during the production of the methine ester,exp() Is an exponential function with a natural constant as the base,DTW() Calculating a similarity distance function;
according to the difference distanceNThe production of the methylene ester is divided into two clusters, the methyl ester amount and the methyl ester component in the two clusters are analyzed, the properties of the two clusters are determined based on the analysis result, and the two clusters are divided into a normal cluster and an abnormal cluster;
determining a similar index of the corresponding air pressure change of the reactor in any two times of methyl ester production processes in each cluster according to the pressure value corresponding to each moment of the reactor in any two times of methyl ester production processes in each cluster and the feeding amount and the alkyd ratio corresponding to the reactor, wherein the calculation formula of the similar index of the air pressure change is as follows:
Figure 422474DEST_PATH_IMAGE009
wherein the content of the first and second substances,u(A,B) For the first in each clusterASecond and thirdBThe corresponding pressure change of the reactor in the production process of the methyl hypoxide has similar indexes,Ap A is as followsAA sequence of pressure values corresponding to each moment of the reactor during the production of the hypomethylester,Ap B is as followsBA sequence of pressure values corresponding to each moment of the reactor during the production of the hypomethylester,m A is as followsAThe corresponding feeding amount of the reactor in the production process of the methyl hypo-ester,m B is as followsBThe corresponding feeding amount of the reactor in the production process of the methyl hypo-ester,n A is as followsAThe ratio of the corresponding alcohol acid in the reactor in the production process of the methyl hypoxide,n B is as followsBThe ratio of the corresponding alcohol acid in the reactor in the production process of the methyl hypoxide,exp() Is an exponential function with a natural constant as the base,Range() In order to find the function of the pole difference,MSD() In order to solve the function of the distance of the morphological difference,abs() To solve the absolute value function;
determining a plurality of similar indicators of air pressure change corresponding to the reactor in each methyl ester production process in each cluster according to the similar indicators of air pressure change corresponding to the reactors in any two methyl ester production processes in each cluster, calculating the accumulated value of the plurality of similar indicators of air pressure change, and taking the accumulated value as the membership corresponding to the reactor in each methyl ester production process;
acquiring a corresponding air pressure fitting curve of a reactor in each methyl ester production process in each cluster, and determining an upper air pressure limit envelope line and a lower air pressure limit envelope line corresponding to each cluster according to the corresponding air pressure fitting curve and membership degree of the reactor;
inputting the pressure value corresponding to each moment of the current set time period of the reactor and the feeding amount and the alcohol acid ratio value corresponding to the reactor, which are acquired in real time, into a pre-constructed and trained pressure prediction neural network to obtain the pressure value corresponding to each moment of the future set time period of the reactor;
and regulating and controlling corresponding equipment in the methyl ester production process according to the pressure value corresponding to each moment of the future set time period of the reactor and the air pressure upper limit envelope line and the air pressure lower limit envelope line corresponding to each cluster.
2. The intelligent control method for crude product preparation in methyl ester production according to claim 1, wherein the step of determining the corresponding upper and lower envelope of atmospheric pressure for each cluster comprises:
determining a preset number of target membership degrees in each cluster according to the corresponding membership degree of the reactor in each methyl ester production process in each cluster;
determining the air pressure fitting curve corresponding to the preset number of target membership degrees in each cluster according to the preset number of target membership degrees in each cluster and the air pressure fitting curve corresponding to the reactor in each methyl ester production process;
determining the maximum value and the minimum value of the air pressure corresponding to each moment in the air pressure fitting curves corresponding to the preset number of target membership degrees in each cluster according to the air pressure fitting curves corresponding to the preset number of target membership degrees in each cluster;
and determining the air pressure upper limit envelope line and the air pressure lower limit envelope line corresponding to each cluster according to the air pressure maximum value and the air pressure minimum value corresponding to each moment.
3. The intelligent control method for crude product preparation in methyl ester production according to claim 1, wherein the step of regulating and controlling corresponding equipment in the methyl ester production process comprises:
if the pressure value corresponding to a certain moment of the future set time period of the reactor is higher than the upper limit envelope of the air pressure corresponding to any cluster, reducing the pressure value corresponding to the moment of the reactor, and if the pressure value corresponding to the certain moment of the future set time period of the reactor is lower than the lower limit envelope of the air pressure corresponding to any cluster, increasing the pressure value corresponding to the moment of the reactor until the pressure value corresponding to the moment of the reactor is at the preset position of the interval corresponding to the upper limit envelope and the lower limit envelope of the air pressure corresponding to the normal cluster, wherein the interval is formed by constructing the upper limit envelope and the lower limit envelope of the air pressure.
CN202211161702.9A 2022-09-23 2022-09-23 Intelligent control method for crude product preparation in methyl ester production Active CN115237180B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211161702.9A CN115237180B (en) 2022-09-23 2022-09-23 Intelligent control method for crude product preparation in methyl ester production

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211161702.9A CN115237180B (en) 2022-09-23 2022-09-23 Intelligent control method for crude product preparation in methyl ester production

Publications (2)

Publication Number Publication Date
CN115237180A CN115237180A (en) 2022-10-25
CN115237180B true CN115237180B (en) 2022-12-06

Family

ID=83667375

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211161702.9A Active CN115237180B (en) 2022-09-23 2022-09-23 Intelligent control method for crude product preparation in methyl ester production

Country Status (1)

Country Link
CN (1) CN115237180B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115713625A (en) * 2022-11-18 2023-02-24 盐城众拓视觉创意有限公司 Method for rapidly combining teaching real-recorded video and courseware background into film

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10337780A1 (en) * 2003-08-14 2005-03-24 Zimmer Ag Continuous production of polymers by 3-stage melt condensation, e.g. polyethylene terephthalate, involves taking some of the product from at least one of the reactors and adding it to preceding or following reactors
WO2014052823A1 (en) * 2012-09-27 2014-04-03 Yale University System and method for separating lipid based products from biomass
WO2014105110A2 (en) * 2012-12-28 2014-07-03 Dow Global Technologies Llc Method to reduce the crystallization temperature of carboxylic acid comonomer at elevated pressures, and to improve the copolymerization of the same
CN104629021A (en) * 2015-02-15 2015-05-20 张家港美景荣化学工业有限公司 Polytrimethylene terephthalate and production method thereof
CN108273464A (en) * 2018-04-11 2018-07-13 吉林工程技术师范学院 A kind of polyacrylamide polymerization reaction kettle and its control method
CN110559966A (en) * 2019-09-17 2019-12-13 台州道致科技股份有限公司 multi-mode combined control method and system for reaction kettle
CN111925279A (en) * 2020-06-30 2020-11-13 南京工业大学 Intelligent optimization control method for device for preparing dimethyl ether by methanol gas phase dehydration
CN112102890A (en) * 2020-07-28 2020-12-18 浙江中控技术股份有限公司 MCS synthesis device reaction temperature prediction method based on machine learning model
CN114103707A (en) * 2021-12-06 2022-03-01 黄淮学院 Intelligent energy control method and system based on artificial intelligence and Internet of things
CN114214122A (en) * 2021-12-21 2022-03-22 常州市金坛区维格生物科技有限公司 Method for preparing low-sulfur fatty acid methyl ester from high-acid-value waste oil by medium-low pressure method
CN114399080A (en) * 2021-12-14 2022-04-26 卫星化学股份有限公司 Intelligent control method and system for acrylate production equipment

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8606527B2 (en) * 2009-02-27 2013-12-10 Bio-Rad Laboratories, Inc. SNP detection by melt curve clustering
US20140259886A1 (en) * 2013-03-13 2014-09-18 Rockwell Automation Technologies, Inc. Advanced process control of a biodiesel plant
CN109508835B (en) * 2019-01-01 2020-11-24 中南大学 Smart power grid short-term power load prediction method integrating environmental feedback
CN113836756B (en) * 2021-11-29 2022-03-18 山东华尚电气有限公司 Intelligent monitoring method and system for annealing process of three-dimensional wound core transformer
CN114925943B (en) * 2022-07-22 2022-09-30 江苏布罗信息技术有限公司 Transformer abnormal state prediction method based on power internet of things

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10337780A1 (en) * 2003-08-14 2005-03-24 Zimmer Ag Continuous production of polymers by 3-stage melt condensation, e.g. polyethylene terephthalate, involves taking some of the product from at least one of the reactors and adding it to preceding or following reactors
WO2014052823A1 (en) * 2012-09-27 2014-04-03 Yale University System and method for separating lipid based products from biomass
WO2014105110A2 (en) * 2012-12-28 2014-07-03 Dow Global Technologies Llc Method to reduce the crystallization temperature of carboxylic acid comonomer at elevated pressures, and to improve the copolymerization of the same
CN104629021A (en) * 2015-02-15 2015-05-20 张家港美景荣化学工业有限公司 Polytrimethylene terephthalate and production method thereof
CN108273464A (en) * 2018-04-11 2018-07-13 吉林工程技术师范学院 A kind of polyacrylamide polymerization reaction kettle and its control method
CN110559966A (en) * 2019-09-17 2019-12-13 台州道致科技股份有限公司 multi-mode combined control method and system for reaction kettle
CN111925279A (en) * 2020-06-30 2020-11-13 南京工业大学 Intelligent optimization control method for device for preparing dimethyl ether by methanol gas phase dehydration
CN112102890A (en) * 2020-07-28 2020-12-18 浙江中控技术股份有限公司 MCS synthesis device reaction temperature prediction method based on machine learning model
CN114103707A (en) * 2021-12-06 2022-03-01 黄淮学院 Intelligent energy control method and system based on artificial intelligence and Internet of things
CN114399080A (en) * 2021-12-14 2022-04-26 卫星化学股份有限公司 Intelligent control method and system for acrylate production equipment
CN114214122A (en) * 2021-12-21 2022-03-22 常州市金坛区维格生物科技有限公司 Method for preparing low-sulfur fatty acid methyl ester from high-acid-value waste oil by medium-low pressure method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于粒子群优化算法的反应釜温度预测控制研究与应用;黄昌远;《中国优秀硕士学位论文全文数据库》;20140815;全文 *
高酸价油脂制备生物柴油的研究;李俊雄;《生物质化学工程》;20071125(第06期);第29-32页 *

Also Published As

Publication number Publication date
CN115237180A (en) 2022-10-25

Similar Documents

Publication Publication Date Title
CN115237180B (en) Intelligent control method for crude product preparation in methyl ester production
CN111199016A (en) DTW-based improved K-means daily load curve clustering method
CN116340795B (en) Operation data processing method for pure oxygen combustion heating furnace
CN111352408B (en) Multi-working-condition process industrial process fault detection method based on evidence K nearest neighbor
CN116757553B (en) Agricultural organic waste resource utilization digital information management system
CN116414076B (en) Intelligent monitoring system for recovered alcohol production data
Maestri et al. A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes
CN102925602B (en) Furnace profile maintenance method for blast furnace operation
CN107622279A (en) The sorting technique of blast furnace internal state
CN112199829A (en) Multi-working-condition multi-stage batch process monitoring method based on density peak clustering and instant learning
CN109102035B (en) Clustering analysis-based coking coal multi-dimensional index similarity refined classification method
CN113407896B (en) Optimal stress and sample distribution determining method in nuclear power valve accelerated life test
Jiang et al. Rapid identification of fermentation stages of bioethanol solid-state fermentation (SSF) using FT-NIR spectroscopy: comparisons of linear and non-linear algorithms for multiple classification issues
CN112434739A (en) Chemical process fault diagnosis method of support vector machine based on multi-core learning
CN108563913B (en) Method and system for predicting energy consumption of reduction process of polycrystalline silicon reduction furnace
CN111647698A (en) Active state detection method and device for blast furnace hearth
CN115203903A (en) Temperature state evaluation method based on billet target temperature rise process
CN115049123A (en) Prediction method for silicon content of molten iron in blast furnace based on GA-XGboost model
CN101859103A (en) On-line calculation and self-adaptation nonlinear prediction control method of catalytic cracking reaction depth
CN111914206B (en) Process monitoring method based on dynamic neighbor preserving embedding algorithm
CN111222738B (en) Method for predicting power and optimizing parameters of wind power cluster
Wang et al. Machine learning and ensemble learning for transcriptome data: principles and advances
Zhang et al. Reliable multi-objective on-line re-optimisation control of a fed-batch fermentation process using bootstrap aggregated neural networks
CN113205121B (en) Primary tower sampling data coarse difference discrimination method based on local characteristic anomaly factors
CN117874445B (en) Enzyme preparation production monitoring method for real-time online monitoring data analysis

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
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: An intelligent control method for crude product preparation in methyl ester production

Effective date of registration: 20230217

Granted publication date: 20221206

Pledgee: Weihai commercial bank Limited by Share Ltd. Ji'nan branch

Pledgor: JINAN MINGXIN PHARMACEUTICAL Co.,Ltd.

Registration number: Y2023980032845

PE01 Entry into force of the registration of the contract for pledge of patent right
PC01 Cancellation of the registration of the contract for pledge of patent right

Granted publication date: 20221206

Pledgee: Weihai commercial bank Limited by Share Ltd. Ji'nan branch

Pledgor: JINAN MINGXIN PHARMACEUTICAL Co.,Ltd.

Registration number: Y2023980032845

PC01 Cancellation of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: An intelligent control method for crude product preparation in methyl ester production

Granted publication date: 20221206

Pledgee: Weihai commercial bank Limited by Share Ltd. Ji'nan branch

Pledgor: JINAN MINGXIN PHARMACEUTICAL Co.,Ltd.

Registration number: Y2024980005646

PE01 Entry into force of the registration of the contract for pledge of patent right