CN110780654A - Production process control system for plant extraction - Google Patents
Production process control system for plant extraction Download PDFInfo
- Publication number
- CN110780654A CN110780654A CN201911117683.8A CN201911117683A CN110780654A CN 110780654 A CN110780654 A CN 110780654A CN 201911117683 A CN201911117683 A CN 201911117683A CN 110780654 A CN110780654 A CN 110780654A
- Authority
- CN
- China
- Prior art keywords
- value
- module
- extract
- temperature
- sample data
- 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.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 11
- 238000000605 extraction Methods 0.000 title claims description 70
- 239000000284 extract Substances 0.000 claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000001704 evaporation Methods 0.000 claims abstract description 16
- 238000002791 soaking Methods 0.000 claims abstract description 16
- 239000012535 impurity Substances 0.000 claims abstract description 14
- 238000010438 heat treatment Methods 0.000 claims abstract description 9
- 238000000926 separation method Methods 0.000 claims abstract description 9
- 239000011229 interlayer Substances 0.000 claims description 30
- 239000010410 layer Substances 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 14
- 239000000498 cooling water Substances 0.000 claims description 10
- 239000007788 liquid Substances 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 9
- 238000009835 boiling Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000005406 washing Methods 0.000 claims description 2
- 238000007654 immersion Methods 0.000 claims 1
- 230000008020 evaporation Effects 0.000 abstract description 14
- 239000004480 active ingredient Substances 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000011897 real-time detection Methods 0.000 abstract 1
- 239000002904 solvent Substances 0.000 abstract 1
- 238000004140 cleaning Methods 0.000 description 3
- 238000007598 dipping method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002386 leaching Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000419 plant extract Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The utility model provides a production process control system for plant draws, includes that plant washs module, plant crushing module, soaks and draws module, impurity separation module and evaporation concentration module, the plant washs the module and is used for treating the plant that draws and washs, the plant crushing module is used for smashing the plant after wasing, soak and draw the module and be used for drawing out the active ingredient from the plant after smashing, acquire the extract that contains the active ingredient, the impurity separation module is used for getting rid of impurity in the extract, evaporation concentration module is used for gasifying and detaching some solvent in the extract. The invention has the beneficial effects that: the soaking and extracting module of the system is provided with a heating control system, and the temperature of the extracting solution in the extracting tank is controlled by adopting a PID controller, so that the accurate control of the temperature is realized; the concentration of the extracting solution in the evaporator is detected on line by the evaporation concentration module by adopting a BP neural network, so that the real-time detection of the detected concentration is realized.
Description
Technical Field
The invention relates to the field of plant extraction, in particular to a production process control system for plant extraction.
Background
The plant extraction is an extraction method which is formed by taking plants as raw materials, extracting and separating the plants physically or chemically to obtain one or more active ingredients in the plants without changing the structures of the active ingredients. The plants usually contain heat-sensitive substances, the existing extraction process used in the plant extraction is warm-dipping dynamic extraction, the warm-dipping dynamic extraction is a 'sub-boiling' state which enables the temperature of an extracting solution to be kept close to the boiling point temperature, and the method has the advantages of high extraction rate and reduction of damage of effective components and impurity leaching, but the control precision requirement on the extraction temperature is high, and the traditional control method is difficult to meet the temperature precision control requirement of the warm-dipping dynamic extraction process, so that the key for ensuring the dynamic extraction effect is to adopt a proper control method to accurately control the extraction temperature in the plant extraction process.
In addition, in the process of plant extraction, the concentration section is used for concentrating the plant extract and is an important link of plant extraction. Concentration detection is very critical in concentration control, generally detects as ejection of compact standard in the concentrated later stage, because concentrator internal operating mode is abominable, lacks effectual sensor detection means, and it is more difficult to judge concentration accurately.
Disclosure of Invention
In view of the above problems, the present invention is directed to a production process control system for plant extraction.
The purpose of the invention is realized by the following technical scheme:
the utility model provides a production process control system for plant draws, includes that plant washs module, plant crushing module, soaks and draws module, impurity separation module and evaporation concentration module, plant washing module is used for treating the plant that draws and washs, plant crushing module is used for smashing the plant after wasing, soak and draw the module and be used for drawing effective component out from the plant after smashing, acquire the extract that contains the effective component, impurity separation module is used for getting rid of impurity in the extract, the evaporation concentration module is used for further evaporating the concentration that makes the extract reach predetermined concentration value with soaking the extract that draws the module and obtain.
The beneficial effects created by the invention are as follows: the production process control system for plant extraction is provided, a heating control unit is arranged in a soaking extraction module of the system, and a PID (proportion integration differentiation) controller is adopted to control the temperature of the extraction liquid in an extraction tank, so that the accurate control of the temperature is realized; the concentration of the extracting solution in the evaporator is detected on line by the evaporation concentration module through the BP neural network, so that the concentration of the extracting solution is detected in real time, and the extraction effect and the extraction quality are better.
Drawings
The invention is further described with the aid of the accompanying drawings, in which, however, the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a schematic diagram of the present invention.
Reference numerals:
a plant cleaning module 1; a plant crushing module 2; a soaking extraction module 3; an impurity separation module 4; and an evaporation concentration module 5.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the production process control system for plant extraction of this embodiment includes a plant cleaning module 1, a plant crushing module 2, a soaking extraction module 3, an impurity separation module 4, and an evaporation concentration module 5, where the plant cleaning module 1 is configured to clean a plant to be extracted, the plant crushing module 2 is configured to crush the cleaned plant, the soaking extraction module 3 is configured to extract effective components from the crushed plant to obtain an extract containing the effective components, the impurity separation module 4 is configured to remove impurities from the extract, and the evaporation concentration module 5 is configured to further evaporate the extract obtained by the soaking extraction module to make the concentration of the extract reach a preset concentration value.
The preferred embodiment provides a production process control system for plant extraction, wherein a heating control unit is arranged in a soaking extraction module of the system, and a PID (proportion integration differentiation) controller is adopted to control the temperature of the extraction liquid in an extraction tank, so that the accurate control of the temperature is realized; the concentration of the extracting solution in the evaporator is detected on line by the evaporation concentration module through the BP neural network, so that the concentration of the extracting solution is detected in real time, and the extraction effect and the extraction quality are better.
Preferably, the soaking and extracting module 3 comprises a soaking and extracting device and a heating control system, the soaking and extracting device comprises a cooler, an extracting tank and an outer shell, an interlayer is formed between the extracting tank and the outer shell, the heating control system comprises a controller, an interlayer steam valve, an in-tank steam valve, a cooling water valve and a sensing detection unit, the interlayer steam valve is used for injecting steam into the interlayer of the extracting tank, the in-tank steam valve is used for injecting steam into the extracting tank, the cooling water valve is used for injecting cooling water into the cooler, the sensing detection unit comprises a first pressure sensor which is arranged in the extracting tank and used for detecting the pressure in the extracting tank, a second pressure sensor which is arranged in the interlayer of the extracting tank and used for detecting the steam pressure in the interlayer of the extracting tank, and a temperature sensor which is arranged in the extracting tank and used for detecting the extracting of, the controller controls the temperature of the extracting solution in the extracting tank by adjusting the opening degrees of the interlayer steam valve, the steam valve in the tank and the cooling water valve.
Preferably, the controller of the heating control system adopts a PID controller to control the temperature of the extracting solution in the extracting tank, and the given temperature value T is
rCollecting the temperature of the extracting solution in the extracting tank by using a temperature sensor, correcting the collected temperature value, and comparing the corrected temperature value with a given temperature value T
rComparing, feeding back a comparison result to a PID controller, generating a control quantity by the PID controller according to the size of the feedback deviation value, wherein the control quantity is used for controlling the opening degrees of an interlayer steam valve, a steam valve in a tank and a cooling water valve, setting a temperature value of extracting solution in the tank collected at the moment of a temperature sensor t as y (t), and correcting the temperature value y (t), specifically:
(1) let X
1＝{x
1(t-l+1),x
1(t-l+2),…,x
1(t) is a pressure value sequence in the extraction tank acquired by the first pressure sensor, X
2＝{x
2(t-l+1),x
2(t-l+2),…,x
2(t) is an interlayer steam pressure value sequence acquired by the second pressure sensor, and Y is a temperature value sequence of the extracting solution in the extraction tank acquired by the temperature sensor, wherein l is a sequence X, and Y is a sequence Y (t-l +1), Y (t-l +2), …, Y (t) }
1、X
2And the length of Y, t is the current moment, and the associated step length of the temperature value and the pressure value of the extracting solution is defined
Then
The calculation formula of (2) is as follows:
in the formula (I), the compound is shown in the specification,
is a sequence of pressure values X
1The average value of the pressure values in the middle extraction tank,
is a sequence of pressure values X
2The mean value of the steam pressure value of the middle interlayer,
is a sequence of pressure values X
iWhen i is 1, then
When i is 2, then
x
1(j) Is a sequence of pressure values X
1J-th data in (1), x
2(j) Is a sequence of pressure values X
2J-th data in (1), x
i(j) Is a sequence of pressure values X
iThe (n) th data of (1),
is the average value of the temperature values in the temperature value sequence Y,
is the first in the sequence of temperature values Y
A piece of data;
(2) let y (d) { y (d +1), y (d +2), …, y (d + m) } and
respectively a temperature value sequence Y and a pressure value sequence X
1Wherein d is t-l, t-l +1, …, t-m, and the associated trend index of the temperature value of the extraction liquid and the pressure value in the extraction tank is defined as delta
1Then δ
1The calculation formula of (2) is as follows:
where t is the current time, r
1(d) Is subsequence Y (d) and subsequence X
1(d) And r is
1(d) The calculation formula of (2) is as follows:
wherein y (i) is the i-th data in the subsequence Y (d),
is a subsequence X
1(d) To (1)
Data, m is the subsequences Y (d) and X
1(d) Length of (d);
calculating the associated trend index delta of the temperature value and the interlayer steam pressure value of the extracting solution according to the calculating method
2According to the associated trend index delta
1And delta
2And determining the comprehensive tendency index rho, wherein the expression of rho is as follows:
(3) assuming that y '(t) is the value obtained by correcting temperature value y (t), the formula for calculating y' (t) is:
wherein y (t) is the temperature value of the extracting solution in the extracting tank acquired by the temperature sensor at the time t, x
1(t) and x
2(t) respectively acquiring a pressure value in the extraction tank and an interlayer steam pressure value x at the moment t
1(0) Is a predetermined threshold value, x, of the pressure value in the extraction tank
2(0) Is a preset interlayer steam pressure value threshold value.
In the preferred embodiment, the temperature sensor is used for collecting the temperature of the extracting solution in the extracting tank, and the time lag characteristic exists in the control process of the PID controller, so that the temperature value collected at the current moment and the control quantity generated by the controller have the phenomenon of non-correspondence, thereby seriously influencing the control performance of the system; therefore, the preferred embodiment corrects the acquired temperature value to alleviate the influence of the time lag characteristic on the temperature control precision, and provides a correlation trend index δ of the temperature value of the extracting solution and the pressure value in the extracting tank in consideration of the fact that the pressure value in the extracting tank and the sandwich steam pressure value directly influence the temperature value of the extracting solution in the extracting tank when correcting the temperature value
1Is calculated by correlating the trend index delta
1Directly reflects the associated trend of the temperature of the extracting solution and the pressure value in the extracting tank, and can calculate the associated trend index delta of the temperature value of the extracting solution and the interlayer steam pressure value in the same way
2Correlation tendency index delta
2Directly reflects the correlation trend of the temperature value and the interlayer steam pressure value of the extracting solution, and utilizes the correlation trend index delta
1And delta
2Determining the temperature value of the extracting solution and the comprehensive trend index rho of the pressure value in the extracting tank and the interlayer steam pressure value, and correcting the temperature value acquired at the current moment by using the comprehensive trend index rho and the pressure value in the extracting tank and the interlayer steam pressure value acquired at the current moment, thereby effectively avoiding time difference slow controlThe response process of the system eliminates the influence of time lag characteristics on the temperature control precision; furthermore, because of the time lag characteristic of the PID controller, the preferred embodiment first determines the associated step size when calculating the associated trend index of the temperature value and the steam pressure value of the draw solution
The pressure value sequence for determining the associated trend index is corresponding to the temperature value sequence of the extracting solution in time, so that the accuracy of temperature value correction influenced by time lag characteristics is overcome.
Preferably, the evaporation concentration module 5 is configured to further evaporate the extracting solution obtained by the soaking extraction module 3 to make the concentration of the extracting solution reach a preset concentration value, where the evaporation concentration module 5 includes an evaporator and a concentration detection system, the concentration detection system performs online detection on the concentration of the extracting solution in the evaporator by using a BP neural network, when the concentration of the extracting solution in the evaporator is detected to reach the preset concentration value, the evaporator is stopped to operate, the BP neural network includes an input layer, a hidden layer, and an output layer, input variables of the input layer include a current concentration of the extracting solution in the evaporator, a boiling point of the extracting solution, a flow rate of the extracting solution added into the evaporator, a vacuum degree in the evaporator, a steam pressure in the evaporator, and a liquid level of the extracting solution in the evaporator, and an output value of the output layer is a predicted concentration of the extracting solution.
Preferably, a sample data set D is used to train a BP neural network adopted by the concentration detection system, the BP neural network adopts a single hidden layer structure, and the number of nodes of the hidden layer of the BP neural network is determined by the following steps:
(1) let sample data set D ═ D
jJ ═ 1,2, …,6}, where { D }, in
jJ ═ 1,2, …,6} respectively represent sample data sets of the current concentration of the extract in the evaporator, the boiling point of the extract, the flow rate of the extract to the evaporator, the degree of vacuum in the evaporator, the vapor pressure in the evaporator and the liquid level of the extract in the evaporator, and for sample data set D
jCarrying out pretreatment, specifically:
in the formula, x
jAs a sample data set D
jSample data of (1), y
jIs x
jThe sample data after the pre-processing is carried out,
and
as a sample data set D
jThe maximum value and the minimum value of the sample data in the middle;
(2) set sample data set D
jIs represented as H after pretreatment
jFor sample data set H
jThe sample data in (1) is subjected to data screening to remove the sample data set H
jThe abnormal value in (1), the sample data set H after the abnormal value is removed
jIs represented by K
j；
(3) Statistical sample data set K
jNumerical value of the sample data in
Representing a sample data set K
jThe numerical value of the data appearing in the data, and q represents a sample data set K
jRespectively counting the number of the numerical values appearing in the sample data set K
jA median value of
Number of data of (1), order
Representing a sample data set K
jA median value of
Number of data of (2), construct a set
Wherein the content of the first and second substances,
is a set F
jQ is the set F
jNumber of data points in, will aggregate F
jQ data points in (1)
Are respectively marked on the coordinate axes, wherein,
is an abscissa on the coordinate axis,
is the ordinate on the coordinate axis, q data points of the coordinate axis are connected to form a discount graph, and the peak value p in the discount graph is counted
jThen the number of nodes β for the hidden layer of the neural network is:
in the formula I
jIs a sample data set K
jProperty value of middle data, and when p
j-1>When 0, let l
j＝p
jWhen p is
jWhen-1 is less than 0, let l
jN is 1, { p }
j-1>0, j is the number of peaks of 1,2, …,6 }.
In the preferred embodiment, the number of nodes of the hidden layer of the BP neural network is determined according to the data characteristics of the input variables of the evaporation and concentration module, so that the determined number of the nodes of the hidden layer is suitable for the data characteristics of the input variables of the evaporation and concentration module; in addition, the determination method for the number of hidden layer nodes in the preferred embodiment has higher operation speed and precision, so that the real-time performance and precision of the online detection of the concentration of the extracting solution are improved.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (5)
1. The utility model provides a production process control system for plant draws, characterized by includes that plant washs module, plant crushing module, soaks and draws module, impurity separation module and evaporative concentration module, plant washing module is used for treating the plant that draws and washs, plant crushing module is used for smashing the plant after wasing, soak and draw the module and be used for drawing effective component from the plant after smashing, obtain the extract that contains the effective component, impurity separation module is used for getting rid of impurity in the extract, the evaporative concentration module is used for further evaporating the extract that the module obtained of will soaking and draws makes the concentration of extract reach predetermined concentration value.
2. The production process control system for plant extraction as claimed in claim 1, wherein the soaking extraction module comprises a soaking extraction device and a heating control system, the soaking extraction device comprises a cooler, an extraction tank and an outer shell, an interlayer is formed between the extraction tank and the outer shell, the heating control system comprises a controller, an interlayer steam valve, an in-tank steam valve, a cooling water valve and a sensing detection unit, the interlayer steam valve is used for injecting steam into the interlayer of the extraction tank, the in-tank steam valve is used for injecting steam into the extraction tank, the cooling water valve is used for injecting cooling water into the cooler, the sensing detection unit comprises a first pressure sensor arranged in the extraction tank for detecting the pressure in the extraction tank, a second pressure sensor arranged in the interlayer of the extraction tank for detecting the steam pressure in the interlayer of the extraction tank and a temperature sensor arranged in the extraction tank for detecting the temperature of the extraction liquid in the extraction tank The controller controls the temperature of the extracting solution in the extracting tank by adjusting the opening degrees of the interlayer steam valve, the steam valve in the extracting tank and the cooling water valve.
3. The system as claimed in claim 2, wherein the controller of the heating control system controls the temperature of the liquid extract in the extraction tank by using a PID controller to set the temperature T
rCollecting the temperature of the extracting solution in the extracting tank by using a temperature sensor, correcting the collected temperature value, and comparing the corrected temperature value with a given temperature value T
rComparing, feeding back a comparison result to a PID controller, generating a control quantity by the PID controller according to the size of the feedback deviation value, wherein the control quantity is used for controlling the opening degrees of an interlayer steam valve, a steam valve in a tank and a cooling water valve, setting a temperature value of extracting solution in the tank collected at the moment of a temperature sensor t as y (t), and correcting the temperature value y (t), specifically:
(1) let X
1＝{x
1(t-l+1)，x
1(t-l+2)，...，x
1(t) is a pressure value sequence in the extraction tank acquired by the first pressure sensor, X
2＝{x
2(t-l+1)，x
2(t-l+2)，...，x
2(t) is a steam pressure value sequence of an interlayer of the extraction tank acquired by the second pressure sensor, and Y is a temperature value sequence of an extracting solution in the extraction tank acquired by the temperature sensor, wherein l is a sequence X
1、X
2And Y, t is the current moment, and the associated step length of the temperature value and the pressure value of the extracting solution is defined as
Then
The calculation formula of (2) is as follows:
in the formula (I), the compound is shown in the specification,
is a sequence of pressure values X
1The average value of the pressure values in the middle extraction tank,
is a sequence of pressure values X
2The mean value of the steam pressure value of the middle interlayer,
is a sequence of pressure values X
iWhen i is 1, then
When i is 2, then
Is a sequence of pressure values X
1J-th data in (1), x
2(j) Is a sequence of pressure values X
2J-th data in (1), x
i(j) Is a sequence of pressure values X
iThe (n) th data of (1),
is the average value of the temperature values in the temperature value sequence Y,
is the first in the sequence of temperature values Y
A piece of data;
(2) let y (d) { y (d +1), y (d +2),.., y (d + m) } and
respectively a temperature value sequence Y and a pressure value sequence X
1Chinese character ZhongyuanA subsequence of adjacent elements and d ═ t-l, t-l + 1.., t-m, defining an associated trend index δ for the temperature value of the extraction liquid and for the pressure value inside the extraction tank
1Then δ
1The calculation formula of (2) is as follows:
where t is the current time, r
1(d) Is subsequence Y (d) and subsequence X
1(d) And r is
1(d) The calculation formula of (2) is as follows:
wherein y (i) is the i-th data in the subsequence Y (d),
is a subsequence X
1(d) To (1)
Data, m is the subsequences Y (d) and X
1(d) Length of (d);
calculating the associated trend index delta of the temperature value and the interlayer steam pressure value of the extracting solution according to the calculating method
2According to the associated trend index delta
1And delta
2And determining the comprehensive tendency index rho, wherein the expression of rho is as follows:
(3) assuming that y '(t) is the value obtained by correcting temperature value y (t), the formula for calculating y' (t) is:
wherein y (t) is the extraction tank collected by the temperature sensor at time tTemperature value of the extract, x
1(t) and x
2(t) respectively acquiring a pressure value in the extraction tank and an interlayer steam pressure value x at the moment t
1(0) Is a predetermined threshold value, x, of the pressure value in the extraction tank
2(0) Is a preset interlayer steam pressure value threshold value.
4. The system of claim 3, wherein the evaporative concentration module is configured to evaporate the extract from the immersion extraction module to a predetermined concentration, and the evaporative concentration module comprises an evaporator and a concentration detection system, the concentration detection system uses a BP neural network to detect the concentration of the extract in the evaporator on line, and stops the evaporator when the concentration of the extract in the evaporator reaches the predetermined concentration, the BP neural network comprises an input layer, a hidden layer, and an output layer, the input variables of the input layer include the current concentration of the extract in the evaporator, the boiling point of the extract, the flow rate of the extract into the evaporator, the vacuum level in the evaporator, the vapor pressure in the evaporator, and the liquid level of the extract in the evaporator, the output value of the output layer is the predicted concentration of the extracting solution.
5. The system of claim 4, wherein the BP neural network adopted by the concentration detection system is trained by using a sample data set D, the BP neural network adopts a single hidden layer structure, and the number of nodes of the hidden layer of the BP neural network is determined by adopting the following steps:
(1) let sample data set D ═ D
j1, 2.., 6}, wherein { D }
jJ ═ 1,2, 6} represents a sample data set of the current concentration of the extract in the evaporator, the boiling point of the extract, the flow rate of the extract into the evaporator, the vacuum degree in the evaporator, the vapor pressure in the evaporator and the liquid level of the extract in the evaporator, respectively, and for sample data set D
jCarrying out pretreatment, specifically:
in the formula, x
jAs a sample data set D
jSample data of (1), y
jIs x
jThe sample data after the pre-processing is carried out,
and
as a sample data set D
jThe maximum value and the minimum value of the sample data in the middle;
(2) set sample data set D
jIs represented as H after pretreatment
jFor sample data set H
jThe sample data in (1) is subjected to data screening to remove the sample data set H
jThe abnormal value in (1), the sample data set H after the abnormal value is removed
jIs represented by K
j；
(3) Statistical sample data set K
jNumerical value of the sample data in
Representing a sample data set K
jThe numerical value of the data appearing in the data, and q represents a sample data set K
jRespectively counting the number of the numerical values appearing in the sample data set K
jA median value of
Number of data of (1), order
Representing a sample data set K
jA median value of
Number of data of (2), construct a set
Wherein the content of the first and second substances,
is a set F
jQ is the set F
jNumber of data points in, will aggregate F
jQ data points in (1)
Respectively marking on coordinate axes, connecting q data points of the coordinate axes to form a discount graph, and counting the peak value p in the discount graph
jThen the number of nodes β for the hidden layer of the neural network is:
in the formula I
jIs a sample data set K
jProperty value of middle data, and when p
jWhen-1 is greater than 0, let l
j＝p
jWhen p is
jWhen-1 is less than 0, let l
jN is 1, { p }
j-1 > 0, j ═ 1, 2.., 6} number of peaks.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911117683.8A CN110780654B (en) | 2019-11-15 | 2019-11-15 | Production process control system for plant extraction |
| CN202010660637.9A CN111781904B (en) | 2019-11-15 | 2019-11-15 | BP neural network-based production process control system for plant extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911117683.8A CN110780654B (en) | 2019-11-15 | 2019-11-15 | Production process control system for plant extraction |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010660637.9A Division CN111781904B (en) | 2019-11-15 | 2019-11-15 | BP neural network-based production process control system for plant extraction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110780654A true CN110780654A (en) | 2020-02-11 |
| CN110780654B CN110780654B (en) | 2020-09-25 |
Family
ID=69391494
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911117683.8A Expired - Fee Related CN110780654B (en) | 2019-11-15 | 2019-11-15 | Production process control system for plant extraction |
| CN202010660637.9A Expired - Fee Related CN111781904B (en) | 2019-11-15 | 2019-11-15 | BP neural network-based production process control system for plant extraction |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010660637.9A Expired - Fee Related CN111781904B (en) | 2019-11-15 | 2019-11-15 | BP neural network-based production process control system for plant extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110780654B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111665716A (en) * | 2020-05-27 | 2020-09-15 | 广东工业大学 | Mathematical modeling method for extracting traditional Chinese medicine/natural plant |
| CN111888788A (en) * | 2020-06-15 | 2020-11-06 | 广东工业大学 | Circulating neural network control method and system suitable for traditional Chinese medicine extraction and concentration |
| CN117064956A (en) * | 2023-10-18 | 2023-11-17 | 康源博创生物科技(北京)有限公司 | Pharmaceutical composition with osteoporosis resisting effect and preparation method thereof |
| CN117357928A (en) * | 2023-12-08 | 2024-01-09 | 广州泽力医药科技有限公司 | Plant extraction method and system based on Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103271199A (en) * | 2013-06-08 | 2013-09-04 | 中山市翠山食品有限公司 | Instant psidiumguajava tea and preparation process thereof |
| CN204952350U (en) * | 2015-09-25 | 2016-01-13 | 江西诚志永丰药业有限责任公司 | Constant temperature draws jar |
| CN207614394U (en) * | 2017-11-01 | 2018-07-17 | 商丘爱己爱牧生物科技股份有限公司 | A kind of traditional Chinese medicine extraction device |
| US10166490B2 (en) * | 2015-01-21 | 2019-01-01 | Lisa F. Kinney | Apparatus and method for extracting organic compounds from plant material using carbon dioxide |
| CN208436434U (en) * | 2018-07-16 | 2019-01-29 | 山东华农生物制药有限公司 | A kind of Multifunctional pot for extracting Chinese medicine |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07160661A (en) * | 1993-12-02 | 1995-06-23 | Hitachi Ltd | Automatic teacher data extraction method for neural network, neural network system using the same and plant operation supporting device |
| JP2012177065A (en) * | 2011-02-25 | 2012-09-13 | Shoji Sawada | Method for producing plant aromatic compound |
| CN102109846A (en) * | 2011-03-01 | 2011-06-29 | 南昌弘益科技有限公司 | Intelligent automated control method for traditional Chinese medicine production |
| CN105867129A (en) * | 2016-04-18 | 2016-08-17 | 浙江大学苏州工业技术研究院 | Optimization method for traditional Chinese medicine extraction technology based on data mining technology |
-
2019
- 2019-11-15 CN CN201911117683.8A patent/CN110780654B/en not_active Expired - Fee Related
- 2019-11-15 CN CN202010660637.9A patent/CN111781904B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103271199A (en) * | 2013-06-08 | 2013-09-04 | 中山市翠山食品有限公司 | Instant psidiumguajava tea and preparation process thereof |
| US10166490B2 (en) * | 2015-01-21 | 2019-01-01 | Lisa F. Kinney | Apparatus and method for extracting organic compounds from plant material using carbon dioxide |
| CN204952350U (en) * | 2015-09-25 | 2016-01-13 | 江西诚志永丰药业有限责任公司 | Constant temperature draws jar |
| CN207614394U (en) * | 2017-11-01 | 2018-07-17 | 商丘爱己爱牧生物科技股份有限公司 | A kind of traditional Chinese medicine extraction device |
| CN208436434U (en) * | 2018-07-16 | 2019-01-29 | 山东华农生物制药有限公司 | A kind of Multifunctional pot for extracting Chinese medicine |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111665716A (en) * | 2020-05-27 | 2020-09-15 | 广东工业大学 | Mathematical modeling method for extracting traditional Chinese medicine/natural plant |
| CN111665716B (en) * | 2020-05-27 | 2022-07-05 | 广东工业大学 | Mathematical modeling method for extracting traditional Chinese medicine/natural plant |
| CN111888788A (en) * | 2020-06-15 | 2020-11-06 | 广东工业大学 | Circulating neural network control method and system suitable for traditional Chinese medicine extraction and concentration |
| CN111888788B (en) * | 2020-06-15 | 2021-11-16 | 广东工业大学 | Circulating neural network control method and system suitable for traditional Chinese medicine extraction and concentration |
| CN117064956A (en) * | 2023-10-18 | 2023-11-17 | 康源博创生物科技(北京)有限公司 | Pharmaceutical composition with osteoporosis resisting effect and preparation method thereof |
| CN117357928A (en) * | 2023-12-08 | 2024-01-09 | 广州泽力医药科技有限公司 | Plant extraction method and system based on Internet of things |
| CN117357928B (en) * | 2023-12-08 | 2024-04-12 | 广州泽力医药科技有限公司 | Plant extraction method and system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111781904B (en) | 2021-05-11 |
| CN111781904A (en) | 2020-10-16 |
| CN110780654B (en) | 2020-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111781904B (en) | BP neural network-based production process control system for plant extraction | |
| CN104656692B (en) | System and method for controlling concentration ratio of circulating water using decarbonized and demineralized water as supplementing water | |
| CN105174219B (en) | The system that a kind of use vacuum type Membrane Materials system concentrates watery hydrochloric acid | |
| CN108513633A (en) | A kind of extracts of Chinese herbal medicine concentration intelligent control system | |
| CN107411164A (en) | For loosening and gaining moisture roller rear chamber three-stage priming apparatus and water adding control method | |
| Guo et al. | Fault diagnosis of a semi-batch crystallization process through deep learning method | |
| CN114781249A (en) | High-density clarification tank dosage prediction and control method based on multidimensional scoring model | |
| CN111888788B (en) | Circulating neural network control method and system suitable for traditional Chinese medicine extraction and concentration | |
| DE1808985B2 (en) | DISTILLATION DEVICE | |
| CN208049437U (en) | A kind of crystallizing tank syrup capture automatic control device | |
| CN1679993A (en) | Continuous high-efficiency vacuum concentration process and equipment for Chinese medicine liquid | |
| CN108525338A (en) | Alcohol recycle rectifying device and alcohol recycle rectificating method | |
| CN206198737U (en) | A kind of Acetone Retrieving Unit in isotretinoin production technology | |
| CN205856350U (en) | Ethanol automatic recovery system | |
| CN112795461A (en) | Efficient recovery method of effective components in solid-state fermentation vinegar frying process | |
| CN106631735B (en) | System for depolymerizing paraformaldehyde and method and application thereof | |
| CN110975308B (en) | Solution concentration method | |
| CN212451255U (en) | Methylamine/ethylamine recovery processing system | |
| CN210974612U (en) | Small-size intelligent equipment that draws | |
| CN209451322U (en) | A kind of novel evaporation concentration device | |
| CN203771370U (en) | Pharmaceutical pure-steam generation system with automatic conductivity detection device | |
| CN206642389U (en) | Alcohol recycle rectifying device | |
| CN215842916U (en) | Retrieve alcohol extraction element | |
| CN206142860U (en) | Device is used multipurposely to used heat | |
| CN112516180A (en) | Automatic production system of Uygur medicine |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200925 Termination date: 20211115 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |