CN118466422B - System and method for optimizing and controlling extraction process of agilawood effective components - Google Patents
System and method for optimizing and controlling extraction process of agilawood effective components Download PDFInfo
- Publication number
- CN118466422B CN118466422B CN202410660084.5A CN202410660084A CN118466422B CN 118466422 B CN118466422 B CN 118466422B CN 202410660084 A CN202410660084 A CN 202410660084A CN 118466422 B CN118466422 B CN 118466422B
- Authority
- CN
- China
- Prior art keywords
- extraction
- agilawood
- optimization
- data
- raw material
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 184
- 238000000034 method Methods 0.000 title claims abstract description 105
- 238000005457 optimization Methods 0.000 claims abstract description 102
- 239000002994 raw material Substances 0.000 claims abstract description 93
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 86
- 230000008569 process Effects 0.000 claims abstract description 59
- 239000002904 solvent Substances 0.000 claims abstract description 57
- 238000005516 engineering process Methods 0.000 claims abstract description 47
- 238000012544 monitoring process Methods 0.000 claims abstract description 47
- 230000000694 effects Effects 0.000 claims abstract description 45
- 238000001035 drying Methods 0.000 claims abstract description 41
- 239000004480 active ingredient Substances 0.000 claims abstract description 29
- 238000000926 separation method Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 18
- 239000002699 waste material Substances 0.000 claims abstract description 16
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000004064 recycling Methods 0.000 claims abstract description 10
- 239000012535 impurity Substances 0.000 claims abstract description 9
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 230000007246 mechanism Effects 0.000 claims abstract description 9
- 238000000703 high-speed centrifugation Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 37
- 230000002068 genetic effect Effects 0.000 claims description 37
- 238000011156 evaluation Methods 0.000 claims description 32
- 238000007781 pre-processing Methods 0.000 claims description 21
- 239000012530 fluid Substances 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 230000033228 biological regulation Effects 0.000 claims description 12
- 239000013078 crystal Substances 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 11
- 238000005265 energy consumption Methods 0.000 claims description 11
- 238000002329 infrared spectrum Methods 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 10
- 238000002156 mixing Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 10
- 239000006228 supernatant Substances 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 239000007787 solid Substances 0.000 claims description 8
- 238000004808 supercritical fluid chromatography Methods 0.000 claims description 8
- 238000003384 imaging method Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 5
- 238000002360 preparation method Methods 0.000 claims description 5
- 238000010223 real-time analysis Methods 0.000 claims description 5
- 238000002425 crystallisation Methods 0.000 claims description 4
- 230000008025 crystallization Effects 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 108090000623 proteins and genes Proteins 0.000 claims description 4
- 238000012569 chemometric method Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000011068 loading method Methods 0.000 claims description 3
- 239000012528 membrane Substances 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000000746 purification Methods 0.000 abstract description 11
- 239000007788 liquid Substances 0.000 abstract description 9
- 238000011084 recovery Methods 0.000 abstract description 7
- 238000007726 management method Methods 0.000 abstract description 6
- 238000013523 data management Methods 0.000 abstract description 5
- 238000003889 chemical engineering Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 11
- 239000000463 material Substances 0.000 description 10
- 239000012071 phase Substances 0.000 description 9
- 230000001419 dependent effect Effects 0.000 description 6
- 230000001276 controlling effect Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 239000000047 product Substances 0.000 description 5
- 238000010438 heat treatment Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 239000004615 ingredient Substances 0.000 description 3
- 235000014347 soups Nutrition 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000000692 Student's t-test Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003912 environmental pollution Methods 0.000 description 2
- CDOSHBSSFJOMGT-UHFFFAOYSA-N linalool Chemical compound CC(C)=CCCC(C)(O)C=C CDOSHBSSFJOMGT-UHFFFAOYSA-N 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 230000000144 pharmacologic effect Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 235000013599 spices Nutrition 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012353 t test Methods 0.000 description 2
- 239000001490 (3R)-3,7-dimethylocta-1,6-dien-3-ol Substances 0.000 description 1
- CDOSHBSSFJOMGT-JTQLQIEISA-N (R)-linalool Natural products CC(C)=CCC[C@@](C)(O)C=C CDOSHBSSFJOMGT-JTQLQIEISA-N 0.000 description 1
- 241000271309 Aquilaria crassna Species 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 239000013543 active substance Substances 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000005119 centrifugation Methods 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000004821 distillation Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 239000010720 hydraulic oil Substances 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000002386 leaching Methods 0.000 description 1
- 229930007744 linalool Natural products 0.000 description 1
- 239000007791 liquid phase Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000000874 microwave-assisted extraction Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002808 molecular sieve Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013386 optimize process Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 239000012264 purified product Substances 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- URGAHOPLAPQHLN-UHFFFAOYSA-N sodium aluminosilicate Chemical compound [Na+].[Al+3].[O-][Si]([O-])=O.[O-][Si]([O-])=O URGAHOPLAPQHLN-UHFFFAOYSA-N 0.000 description 1
- 239000002910 solid waste Substances 0.000 description 1
- 238000007614 solvation Methods 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000000194 supercritical-fluid extraction Methods 0.000 description 1
- 230000002936 tranquilizing effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
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)
- Extraction Or Liquid Replacement (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a process optimization control system and a method for extracting active ingredients of agilawood, belonging to the field of chemical engineering and technology, wherein the system analyzes the content of active ingredients of raw materials through image recognition, performs intelligent extraction by utilizing a solvent ratio optimized by machine learning after pretreatment and microwave auxiliary drying, monitors data in real time to dynamically adjust process parameters, triggers an alarm mechanism to ensure safety, stores history and real-time data by a data management unit, the method comprises the steps of training a mixed optimization algorithm, generating an optimization strategy, evaluating an extraction effect in multiple dimensions, optimizing the strategy, removing impurities by a separation and purification module through a high-speed centrifugation and filtration technology, obtaining high-purity effective components, monitoring the whole process by a monitoring and feedback module, managing recovery liquid by a solvent management and recovery unit, and environmentally-friendly treating wastes by a waste treatment and recycling unit.
Description
Technical Field
The invention belongs to the field of chemical engineering and technology, in particular to an extraction process optimization control system and method for agilawood effective components.
Background
The agilawood is taken as a rare traditional Chinese medicinal material and spice, is favored by people in terms of unique aroma and pharmacological actions since ancient times, and the effective components in the agilawood, such as linalool and agalloch eaglealdehyde, have multiple pharmacological effects of resisting inflammation, resisting oxidation, tranquilizing and allaying excitement, and are widely applied to the fields of medicines, spices and cosmetics, however, due to the limited agilawood resources, the traditional extraction method has low efficiency, the purity of the extracted components is not high, and the effective utilization of the agilawood is severely restricted.
In recent years, along with the continuous progress of technology, the extraction process of the active ingredients of agilawood gradually develops towards the directions of high efficiency, environmental protection and automation, the early agilawood extraction mainly depends on traditional distillation, leaching and extraction methods, the methods are simple to operate, but the extraction efficiency is lower, the utilization rate of raw materials is not high, along with the progress of scientific technology, the modern extraction technology related to supercritical fluid extraction, microwave-assisted extraction and molecular sieve adsorption is introduced into the extraction of the active ingredients of agilawood, the method has the advantages of high extraction efficiency, simple and convenient operation and small damage to the raw materials, and gradually becomes the main stream method of agilawood extraction, and meanwhile, the introduction of the automatic and intelligent control technology enables the extraction process to be more accurate and controllable, and the extraction efficiency and the product quality to be improved.
The patent with publication number CN117413950A discloses a system and a method for processing agilawood soup stock, wherein the system comprises the following steps: the device comprises a crushing unit, an extraction unit, a mixing unit, a concentration unit, a forming unit and a packaging unit, and is used for realizing a series of processes of crushing the agilawood raw materials, extracting active ingredients, mixing and concentrating, forming, packaging and the like. The extraction and concentration links adopt an accurate control algorithm, the extraction of active ingredients is realized by a microwave technology, and the concentration process of the mixture is accurately controlled, so that the consistency and high quality of the final product are ensured. In addition, the system utilizes specific environmental conditions, such as temperature and pressure, to optimize extraction. The design of the whole system aims to realize efficient, accurate and controllable agilawood soup base production and provide products with good flavor and quality.
The above prior art has the following problems: 1) The traditional agilawood soup base processing system lacks the support of an accurate control algorithm, so that the control accuracy in the extraction and concentration links is lower; 2) Only depends on the traditional heat extraction method, has lower efficiency and has difficult purity assurance; 3) The support of the internet of things technology, cloud computing and big data technology is lacking, and the running state of equipment and key parameters of the extraction process cannot be monitored in real time; 4) The lack of an effective treatment and resource utilization mechanism for solvents and extracted wastes leads to the problems of resource waste and environmental pollution.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an extraction process optimization control system and method for agilawood active ingredients, which are characterized in that high-purity active ingredients are obtained by screening raw materials of the active ingredients through image recognition, excessive moisture is removed through microwave-assisted drying, solvent proportioning is optimized through machine learning, in the intelligent extraction process, technological parameters are dynamically adjusted through deep learning, temperature, pressure and solvent concentration are monitored in real time, an early warning mechanism is set to ensure safety, a genetic algorithm and a neural network are combined to perform mixed optimization, an extraction strategy is formulated and optimized according to historical and real-time data training verification, an extraction solution is purified through high-speed centrifugation, filtration and supercritical fluid chromatography technology, the high-purity active ingredients are obtained, near infrared spectrum is utilized to perform quality detection, the extraction efficiency and purity of the agilawood active ingredients are improved, and intelligent and accurate control is realized.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the method for optimally controlling the extraction process of the agilawood effective components comprises the following steps:
Step S1: receiving agilawood raw materials, performing preliminary inspection by using a high-resolution imaging technology, automatically screening raw materials containing high-amount effective components by using an image recognition technology, preprocessing the screened agilawood raw materials containing high-amount effective components, removing redundant moisture in the agilawood raw materials by microwave-assisted drying, preparing an extraction solvent according to a solvent ratio obtained by optimizing a machine learning algorithm in advance, debugging and inspecting extraction equipment, and monitoring the running state of the equipment in real time by using an Internet of things technology;
step S2: the method comprises the steps of putting processed agilawood raw materials into intelligent extraction equipment, adding an extraction solvent, dynamically adjusting extraction process parameters by using a deep learning algorithm according to historical data and real-time feedback, extracting according to the extraction process parameters, monitoring the temperature, the pressure and the solvent concentration in the extraction process in real time by using a high-precision sensor, setting an alarm and early warning mechanism, timely processing abnormal conditions, introducing cloud computing and big data technology, and carrying out remote monitoring and real-time analysis on the extraction process;
Step S3: selecting an optimization algorithm based on a genetic algorithm, performing hybrid optimization by combining a neural network, training and verifying the hybrid optimization algorithm by utilizing historical data and real-time data, formulating an optimization strategy according to an output result of the hybrid optimization algorithm, generating a control instruction based on the optimization strategy, performing multi-dimensional evaluation on an extraction effect after the optimization strategy is executed by a control system, and adjusting and optimizing the optimization strategy according to an evaluation result;
Step S4: after the extraction is finished, removing solid residues and impurities by utilizing a high-speed centrifugation and filtration technology, recovering an extracting solution, introducing a supercritical fluid chromatography technology and a crystallization technology, separating and purifying the recovered extracting solution to obtain high-purity agilawood effective components, and detecting the quality of the high-purity agilawood effective components by utilizing a near infrared spectrum;
Step S5: and establishing a complete extraction and separation process database, monitoring and feeding back the whole extraction and separation process, and treating and recycling the solvent and the extracted waste.
Specifically, the specific implementation steps of the step S1 include:
S101: receiving agilawood raw materials, scanning the agilawood raw materials by using high-resolution imaging equipment, obtaining agilawood raw material images, and preprocessing the agilawood raw material images;
S102: loading a trained image recognition model, inputting a preprocessed agilawood raw material image for reasoning, carrying out probability distribution P on a reasoning result, setting a threshold H, comparing the set threshold with the probability value, if P > H, indicating that the raw material in the image contains a high amount of effective components, and screening agilawood raw material containing the high amount of effective components;
s103: and cleaning the screened agilawood raw materials containing high amounts of active ingredients, removing impurities and dirt on the surfaces, and cutting or crushing to obtain the processed agilawood raw materials.
Specifically, the specific implementation step of the step S1 further includes:
S104: placing the treated agilawood raw material into microwave drying equipment, setting microwave power, frequency and drying time, uniformly placing the agilawood raw material on a tray or a conveyor belt of the microwave drying equipment, starting the microwave drying equipment to dry the raw material, monitoring temperature and humidity changes in the drying process, stopping microwave drying when a preset drying degree is reached, and taking out the dried agilawood raw material;
S105: collecting historical data, preprocessing, analyzing the historical data by using a machine learning algorithm, predicting the optimal solvent ratio, and preparing an extraction solvent according to a prediction result;
S106: the extraction equipment is debugged and checked, the extraction equipment is connected to a monitoring system by utilizing the technology of the Internet of things, the running state, the temperature and the pressure of the equipment are monitored in real time, an alarm threshold value is set, and an alarm is given out in time when the state of the equipment is abnormal.
Specifically, the specific implementation step of the step S3 includes:
S301: collecting historical data and real-time data Wherein, Representing the ith extracted process parameter data,Represents the j-th current environmental parameter data,Representing kth current extraction effect data, i representing the number of extracted process parameter data, j representing the number of current environmental parameter data, k representing the number of current extraction effect data;
S302: selecting a multi-layer perceptron neural network structure, designing a genetic algorithm of multi-parameter cascade coding, taking the weight and parameters of the multi-layer perceptron neural network structure as genes of the genetic algorithm, determining an adaptability function of the genetic algorithm, performing iterative optimization of crossover operation and mutation operation on the genetic algorithm according to the adaptability function, using the neural network weight and parameters generated by the genetic algorithm in each iteration to construct the multi-layer perceptron neural network, and performing the iterative optimization on the genetic algorithm The method comprises the steps of dividing the multi-layer perceptron neural network into a training set and a verification set, training the multi-layer perceptron neural network by using the training set, obtaining an evaluation value output by the multi-layer perceptron neural network by using the verification set through forward propagation, and obtaining an output result of a hybrid optimization algorithm by taking the evaluation value as an fitness value of each neural network.
Specifically, the specific implementation step of the step S3 further includes:
S303: according to the output result of the hybrid optimization algorithm, adopting a correlation analysis method to analyze the correlation between the technological parameters and the extraction effect, constructing a mathematical model or a relation diagram between the technological parameters and the extraction effect, and determining constraint conditions for maximizing the extraction efficiency, minimizing the energy consumption and the technological parameters according to the analysis result Representing the minimum value of the process parameter data,Representing the maximum value of the process parameter data;
s304: constructing an optimization model by combining maximized extraction efficiency, minimized energy consumption and constraint conditions, solving the optimization model by using a genetic algorithm to obtain a group of optimal process parameter values, and converting the optimal process parameter values into specific control instructions according to the optimal process parameter values and the characteristics and requirements of a control system;
s305: after the control system executes the optimal process parameter value, collecting real-time data to carry out multidimensional evaluation on the extraction effect, and adjusting and optimizing the optimal process parameter value according to the evaluation result.
Specifically, the constraint conditions in S303 include:
Wherein, Represents extraction efficiency, E min represents the minimum value of extraction efficiency, P (X) represents energy consumption in the extraction process, P max represents the maximum energy consumption in the extraction process,Representing the minimum value of the process parameter data,Representing the maximum value of the process parameter data.
Specifically, the specific implementation step of the step S4 includes:
s401: after the extraction is finished, placing the extracting solution into a high-speed centrifugal machine, setting the centrifugal speed and time, starting the centrifugal machine, enabling solid residues to settle to the bottom of a centrifugal tube under the action of centrifugal force, taking out supernatant, and filtering the supernatant by using a filter membrane;
S402: selecting supercritical fluid as mobile phase, injecting the filtered supernatant into supercritical fluid chromatograph, and starting supercritical fluid chromatograph to make supercritical fluid flow in chromatographic column, according to polarity, molecular weight and interaction force of lignum Aquilariae Resinatum effective components with mobile phase, adjusting type, temperature and pressure conditions of chromatographic column to make different effective components flow out of chromatographic column sequentially, thereby separating effective components to obtain effective component solution;
s403: setting temperature and pressure, concentrating the effective component solution to obtain effective component crystal, filtering, and drying to obtain high-purity lignum Aquilariae Resinatum effective component crystal;
S404: and analyzing the high-purity agilawood effective component crystal by using a near infrared spectrometer to obtain near infrared spectrum data of the high-purity agilawood effective component crystal, and processing and analyzing the near infrared spectrum data by using a chemometric method to obtain content and purity information of the agilawood effective component.
An extraction process optimization control system of agilawood effective components comprises: the device comprises a preprocessing module, an extraction module and a control module;
the preprocessing module is used for shooting an agilawood raw material image through a high-resolution camera, performing preliminary inspection, preprocessing and solvent preparation on the agilawood raw material image, and comprises an image recognition unit and a proportioning unit, wherein the image recognition unit is used for acquiring the agilawood raw material image, configuring a recognition algorithm to recognize and classify the raw material image to form a raw material set, and the proportioning unit is used for acquiring the raw material set and historical data, and generating solvent types and solvent proportions of solvents based on the historical data;
The extraction module is used for adjusting the process parameters and monitoring the extraction process in real time, and comprises a parameter regulation and control unit, wherein a deep learning algorithm is configured in the parameter regulation and control unit and is used for acquiring the types and the proportions of the solvents and dynamically adjusting the extracted process parameters;
The control module is used for formulating an extraction strategy and evaluating and optimizing the execution effect; the control module comprises a mixing unit and a strategy conversion unit, wherein a genetic algorithm is configured in the mixing unit, a mixed optimization model is constructed based on the genetic algorithm and a neural network, a conversion strategy is configured in the strategy conversion unit, the conversion strategy comprises the steps of obtaining the output result of the mixed optimization model, and formulating an optimization strategy based on the output result, and the optimization strategy is used for solving the mixed optimization model and obtaining a control instruction.
The electronic equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the extraction process optimization control method of the agilawood effective components when executing the computer program.
Specifically, a computer readable storage medium having stored thereon computer instructions which, when executed, perform the steps of a method for optimizing control of an extraction process of an active ingredient of eaglewood
Compared with the prior art, the invention has the beneficial effects that:
1. The invention provides an extraction process optimization control system of agilawood effective components, which is optimized and improved in terms of architecture, operation steps and flow, and has the advantages of simple flow, low investment and operation cost and low production and working costs.
2. The invention provides an extraction process optimization control method of agilawood effective components, which realizes high-efficiency and accurate screening of agilawood raw materials through a high-resolution imaging technology and an image recognition technology, performs mixed optimization by utilizing a deep learning algorithm and an optimization algorithm based on a genetic algorithm, dynamically adjusts extraction process parameters according to historical data and real-time feedback, realizes intelligent extraction control, ensures stability and high efficiency of an extraction process, monitors key parameters of temperature, pressure and solvent concentration in the extraction process in real time through a high-precision sensor, sets an alarm and early warning mechanism, timely discovers and processes abnormal conditions, reduces the risk of production accidents, ensures the safety and reliability of the extraction process, introduces an Internet of things technology, cloud computing and a big data technology, realizes remote monitoring and real-time analysis of the extraction process, improves the production efficiency and management level, reduces the production cost, and adopts a supercritical fluid chromatography technology and a crystallization technology to separate and purify an extraction solution, so as to obtain the high-purity agilawood effective components, improves the quality and added value of products, and simultaneously processes and recycles solvents and extracted wastes, and reduces environmental pollution and resource waste.
Drawings
FIG. 1 is a diagram of an optimizing control system for extracting effective components of lignum Aquilariae Resinatum;
FIG. 2 is a schematic diagram of a process optimization control system for extracting active ingredients of agilawood according to the invention;
FIG. 3 is a flowchart of the method for optimizing and controlling the extraction process of the active ingredient of agilawood;
FIG. 4 is a workflow diagram of an optimized control method for the extraction process of the active ingredients of agilawood according to the invention;
FIG. 5 is a flowchart of the implementation of the microwave-assisted drying technique of the optimized control method for the extraction process of the active ingredient of agilawood of the invention;
FIG. 6 is a flowchart of the centrifugation and filtration process optimization control method of the agilawood active ingredient extraction process of the invention.
Detailed Description
Example 1
Referring to fig. 1-2, an embodiment of the present invention is provided: an extraction process optimization control system of agilawood effective components comprises:
the device comprises a preprocessing module, an extraction module and a control module;
The pretreatment module is used for shooting agilawood raw material images through a high-resolution camera, performing preliminary examination, pretreatment and solvent preparation on the agilawood raw material images, and comprises an image recognition unit and a proportioning unit, wherein the image recognition unit is used for acquiring agilawood raw material images, configuring a recognition algorithm to recognize and classify the raw material images to form a raw material set, and the proportioning unit is used for acquiring the raw material set and historical data, and generating solvent types and solvent proportions of solvents based on the historical data;
The extraction module is used for adjusting the process parameters and monitoring the extraction process in real time, and comprises a parameter regulation and control unit, wherein a deep learning algorithm is configured in the parameter regulation and control unit and is used for acquiring the types and the proportions of the solvents and dynamically adjusting the extracted process parameters;
The control module is used for formulating an extraction strategy and evaluating and optimizing the execution effect; the control module comprises a mixing unit and a strategy conversion unit, wherein a genetic algorithm is configured in the mixing unit, a mixed optimization model is constructed based on the genetic algorithm and a neural network, a conversion strategy is configured in the strategy conversion unit, the conversion strategy comprises the steps of obtaining an output result of the mixed optimization model, formulating an optimization strategy based on the output result, and the optimization strategy is used for solving the mixed optimization model and obtaining a control instruction.
The extraction process optimization control system of the agilawood effective components further comprises: the separation and purification module, the monitoring and feedback module; the separation and purification module is used for efficiently separating and purifying the extracting solution to obtain high-purity agilawood effective components, and detecting the quality of the agilawood effective components; and the monitoring and feedback module is used for establishing a database, monitoring and feeding back the whole extraction and separation process, and treating and recycling the solvent and the extracted waste.
The pretreatment module further comprises a pretreatment unit and a microwave auxiliary drying unit, wherein the pretreatment unit is used for cleaning and crushing the screened raw materials; and the microwave auxiliary drying unit is used for removing redundant moisture in the pretreated raw materials by using a microwave heating technology.
The extraction module also comprises an intelligent extraction equipment unit, a monitoring and alarming unit and a remote monitoring and analyzing unit; the intelligent extraction equipment unit is used for placing the processed raw materials into equipment and adding an extraction solvent; the monitoring and alarming unit is used for monitoring the extraction process in real time through the high-precision sensor and setting an alarming and early warning mechanism; and the remote monitoring and analyzing unit is used for remote monitoring and real-time analysis.
The control module also comprises a data management unit, a multidimensional effect evaluation unit and a strategy adjustment and optimization unit; the data management unit is used for collecting historical data and real-time data and training and verifying the hybrid optimization model; the multidimensional effect evaluation unit is used for evaluating the extraction efficiency, purity and energy consumption in multiple dimensions after the optimization strategy is executed; and the strategy adjustment and optimization unit is used for carrying out iterative adjustment on the optimization strategy according to the evaluation result so as to optimize the extraction process.
The separation and purification module comprises a solid-liquid separation unit, a separation and purification unit and a quality detection unit; the solid-liquid separation unit is used for removing solid residues and impurities by utilizing high-speed centrifugation and filtration technology; the separation and purification unit is internally provided with a supercritical fluid chromatographic algorithm, and the recovery extracting solution is crystallized, separated and purified based on the supercritical fluid chromatographic algorithm; the quality detection unit is internally provided with a near infrared spectrum algorithm which is used for detecting the quality of the purified product
The monitoring and feedback module comprises: the system comprises a database unit, a solvent management and recovery unit, a feedback analysis unit and a waste treatment and recycling unit; the database unit is used for collecting, storing and managing various data in the whole extraction and separation process; the solvent management and recovery unit is used for effectively recovering, regenerating or safely disposing the used solvent; the feedback analysis unit is used for providing feedback according to the monitoring data; the waste treatment and recycling unit is used for classifying and treating the solid waste generated in the extraction process.
The specific workflow of each unit corresponding to the pretreatment module, the extraction module, the control module, the separation and purification module, the monitoring and feedback module comprises:
a pretreatment module, an extraction module, a control module, a separation and purification module each corresponding unit in the monitoring and feedback module is interactively linked with the central control system;
The preprocessing module analyzes the raw material image through an image recognition unit by applying an image recognition algorithm, recognizes the content of effective components, transmits a recognition result and raw material data to the preprocessing unit, performs preprocessing operation of cleaning and crushing the raw material according to an output result of the image recognition unit, transmits the preprocessed raw material data to the microwave auxiliary drying unit, removes redundant moisture in the preprocessed raw material through a microwave auxiliary drying technology, transmits the dried raw material data to the proportioning unit, prepares an extraction solvent according to a solvent proportioning obtained in advance through optimization of a machine learning algorithm, and transmits solvent proportioning information to the extraction module;
The extraction module is used for placing the processed agilawood raw materials into intelligent extraction equipment through the intelligent extraction equipment unit, adding an extraction solvent, starting an extraction process according to an instruction and the dried raw material data, transmitting the real-time monitoring data to the parameter regulation and control unit and the remote monitoring and analysis unit, receiving the real-time monitoring data of temperature, pressure and solvent concentration transmitted from the intelligent extraction equipment unit by the parameter regulation and control unit, dynamically adjusting extraction process parameters according to historical data and real-time feedback, transmitting the regulation and control parameters to the monitoring and alarm unit and the remote monitoring and analysis unit in real time, comparing the received regulation and control parameters with a preset threshold value by the monitoring and alarm unit, immediately triggering an alarm mechanism if the received regulation and control parameters exceed the preset threshold value, and feeding back the result to the parameter regulation and control unit, and remotely monitoring and analyzing the extraction process by the remote monitoring and analysis unit in real time;
The data management unit of the control module stores and manages historical data and real-time data, the historical data and the real-time data are transmitted to the mixing unit, the mixing unit constructs a mixed optimization model, the data transmitted by the data management unit is used for training and verifying a mixed optimization algorithm, the output result of the mixed optimization algorithm is transmitted to the strategy conversion unit, the strategy conversion unit formulates a specific optimization strategy according to the output result of the mixed optimization algorithm, the strategy is converted into a control instruction and transmitted to the extraction module, the multi-dimensional effect evaluation unit performs multi-dimensional evaluation on the extraction effect after the extraction module executes the optimization strategy, the evaluation result is transmitted to the strategy adjustment and optimization unit, and the strategy adjustment and optimization unit adjusts and optimizes the optimization strategy according to the evaluation result of the multi-dimensional effect evaluation unit to form a new optimization strategy and enter the next round of circulation;
The separation and purification module judges whether extraction is finished through the solid-liquid separation unit, if so, solid residues and impurities in the extracting solution are removed by utilizing a high-speed centrifugation and filtration technology, pure extracting solution is recovered, the result is transmitted to the separation and purification unit, the solvent management and recovery unit and the waste treatment and recycling unit, the separation and purification unit further separates and purifies the recovered extracting solution to obtain high-purity agilawood effective components, the high-purity agilawood effective components are transmitted to the quality detection unit, and the quality detection unit detects the quality of the purified agilawood effective components;
The monitoring and feedback module monitors and feeds back the whole process through the database unit, feeds back data to the control module and the feedback analysis unit, the solvent management and recovery unit receives the recovered extracting solution obtained by the solid-liquid separation unit, manages and recovers the extracting solution, the feedback analysis unit carries out feedback analysis on the extracting and separating process according to the data provided by the database unit, and transmits the feedback result to the control module, and the waste treatment and recycling unit carries out environmental protection treatment or recycling on waste generated in the extracting and separating process.
Example 2
Referring to fig. 3-6, another embodiment of the present invention is provided: the method for optimally controlling the extraction process of the agilawood effective components comprises the following steps:
Step S1: receiving agilawood raw materials, performing preliminary inspection by using a high-resolution imaging technology, automatically screening raw materials containing high-amount effective components by using an image recognition technology, preprocessing the screened agilawood raw materials containing high-amount effective components, removing redundant moisture in the agilawood raw materials by microwave-assisted drying, preparing an extraction solvent according to a solvent ratio obtained by optimizing a machine learning algorithm in advance, debugging and inspecting extraction equipment, and monitoring the running state of the equipment in real time by using an Internet of things technology;
The microwave assisted drying technology is to utilize microwave energy as a heating source, and make the molecules generate high-frequency friction and heat through the interaction of microwaves and polar molecules in wet materials, so as to achieve the purpose of quickly evaporating water and drying the materials. In addition, microwave drying is an internal heating method, materials directly act with microwaves, polar molecules in the materials absorb the microwaves and change the original molecular structure under the action of the microwaves, the directional arrangement is presented, the polar molecules move in a polar mode along with the change of an external electromagnetic field, and friction and collision are carried out at the same speed as the frequency of the microwaves to generate heat energy, so that the temperature of the materials is quickly increased from the inside in a short time to achieve the heating and drying effects. The invention uses the microwave auxiliary drying technology, has the advantages of high heat conduction speed, energy conservation, high efficiency and uniform drying, and can also reduce the drying time and keep active substances in materials, thereby improving the quality and stability of products.
Step S2: the method comprises the steps of putting processed agilawood raw materials into intelligent extraction equipment, adding an extraction solvent, dynamically adjusting extraction process parameters by using a deep learning algorithm according to historical data and real-time feedback, extracting according to the extraction process parameters, monitoring the temperature, the pressure and the solvent concentration in the extraction process in real time by using a high-precision sensor, setting an alarm and early warning mechanism, timely processing abnormal conditions, introducing cloud computing and big data technology, and carrying out remote monitoring and real-time analysis on the extraction process;
The method for dynamically adjusting the hard conditions of the extraction process parameters by using the deep learning algorithm comprises the following steps: 1) A high quality dataset; 2) Powerful computing resources; 3) Professional deep learning skills; 4) Suitable deep learning frameworks and tools; stable process environment. The method has the advantages that the method can automatically learn and extract the characteristics in the data, dynamically adjust the extraction process parameters according to the real-time data, realize the automatic and intelligent production process, reduce the need of manual intervention, improve the production efficiency and accuracy, simultaneously, can process and analyze the data in real time, dynamically adjust the process parameters according to the real-time feedback in the production process, ensure that the production process is more flexible, can rapidly cope with various changes, and improve the product quality and the production efficiency.
Step S3: selecting an optimization algorithm based on a genetic algorithm, performing hybrid optimization by combining a neural network, training and verifying the hybrid optimization algorithm by utilizing historical data and real-time data, formulating an optimization strategy according to an output result of the hybrid optimization algorithm, generating a control instruction based on the optimization strategy, performing multi-dimensional evaluation on an extraction effect after the optimization strategy is executed by a control system, and adjusting and optimizing the optimization strategy according to an evaluation result;
The specific implementation flow comprises the following steps: 1) Data preparation and preprocessing; 2) Constructing a mixed optimization model; 3) Model training and verification; 4) Making an optimization strategy; 5) Generating and executing control instructions; 6) And (5) extracting effect evaluation and optimizing strategy adjustment.
Step S4: after the extraction is finished, removing solid residues and impurities by utilizing a high-speed centrifugation and filtration technology, recovering an extracting solution, introducing a supercritical fluid chromatography technology and a crystallization technology, separating and purifying the recovered extracting solution to obtain high-purity agilawood effective components, and detecting the quality of the high-purity agilawood effective components by utilizing a near infrared spectrum;
Supercritical fluid chromatography is a chromatographic method using supercritical fluid as mobile phase, the supercritical fluid refers to the state of matter at critical temperature and critical pressure, neither gas nor liquid, but between gas and liquid, and has physical properties of both gas and liquid, in supercritical fluid chromatography, the fluid in this special state is used as mobile phase, and separation and analysis are performed by means of solvation ability of mobile phase. The supercritical fluid chromatography technology is used because the supercritical fluid is easy to control and regulate, and can be connected with any existing liquid-phase or gas-phase detector, and has strong classification capability.
Step S5: and establishing a complete extraction and separation process database, monitoring and feeding back the whole extraction and separation process, and treating and recycling the solvent and the extracted waste.
The specific implementation steps of the step S1 include:
S101: receiving agilawood raw materials, scanning the agilawood raw materials by using high-resolution imaging equipment, obtaining agilawood raw material images, and preprocessing the agilawood raw material images;
s102: loading a trained image recognition model, inputting a preprocessed agilawood raw material image for reasoning, carrying out probability distribution on a reasoning result, setting a threshold value, comparing the set threshold value with the probability value, if the probability value exceeds the set threshold value, indicating that the raw material in the image contains high-quantity effective components, and screening agilawood raw material containing high-quantity effective components;
s103: cleaning the screened agilawood raw materials containing high amounts of active ingredients, removing impurities and dirt on the surfaces, and cutting or crushing to obtain treated agilawood raw materials;
S104: placing the treated agilawood raw material into microwave drying equipment, setting microwave power, frequency and drying time, uniformly placing the agilawood raw material on a tray or a conveyor belt of the microwave drying equipment, starting the microwave drying equipment to dry the raw material, monitoring temperature and humidity changes in the drying process, stopping microwave drying when a preset drying degree is reached, and taking out the dried agilawood raw material;
S105: collecting historical data, preprocessing, analyzing the historical data by using a machine learning algorithm, predicting the optimal solvent ratio, and preparing an extraction solvent according to a prediction result;
the historical data includes solvent ratio, extraction rate, purity, temperature, pressure, time.
S106: the extraction equipment is debugged and checked, the extraction equipment is connected to a monitoring system by utilizing the technology of the Internet of things, the running state, the temperature and the pressure of the equipment are monitored in real time, an alarm threshold value is set, and an alarm is given out in time when the state of the equipment is abnormal.
The process parameters in the step S2 include: the parameters of the multistage collaborative optimization, the dynamic proportion of the solvent, the real-time perceived environmental parameters, the raw material characteristic parameters, the temperature and the pressure, and the real-time perceived environmental parameters comprise: humidity, light, air flow, the present invention considers raw material characteristic parameters because different batches of raw materials have different physical and chemical characteristics, which directly affect the extraction effect.
The optimizing strategy in the step S3 includes: adjusting the process parameter range and setting the process parameter optimization sequence.
The specific implementation steps of the step S3 include:
S301: collecting historical data and real-time data Wherein, Representing the ith extracted process parameter data,Represents the j-th current environmental parameter data,Representing kth current extraction effect data, i representing the number of extracted process parameter data, j representing the number of current environmental parameter data, k representing the number of current extraction effect data;
S302: selecting a multi-layer perceptron neural network structure, designing a genetic algorithm of multi-parameter cascade coding, taking the weight and parameters of the multi-layer perceptron neural network structure as genes of the genetic algorithm, determining an adaptability function of the genetic algorithm, performing iterative optimization of crossover operation and mutation operation on the genetic algorithm according to the adaptability function, using the neural network weight and parameters generated by the genetic algorithm in each iteration to construct the multi-layer perceptron neural network, and performing the iterative optimization on the genetic algorithm Training the multi-layer perceptron neural network by using the training set, obtaining an evaluation value output by the multi-layer perceptron neural network by using the verification set through forward propagation, and taking the evaluation value as an fitness value of each neural network to obtain an output result of a hybrid optimization algorithm;
The multi-parameter cascade coding is to code a plurality of parameters in sequence, the multi-parameter cascade coding is selected to select proper coding length and mode for different parameters, flexibility of parameter coding is improved, in the evolution process of a genetic algorithm, specific structure and characteristics of each parameter are reserved, completeness and effectiveness of understanding are kept, meanwhile, when correlations among parameters are weaker, particularly when one or a few parameters play a main role, main parameters are allowed to play a main role in the genetic algorithm, and auxiliary roles of other parameters are kept, so that searching efficiency and resolution quality of the algorithm are improved.
The iterative optimization method for carrying out the crossover operation and the mutation operation on the genetic algorithm according to the fitness function comprises the following specific steps:
(1) Initializing a population: randomly generating a group of initial solutions as a population of genetic algorithms, each individual representing the weight and parameter configuration of a neural network;
(2) Selection operation: selecting a part of excellent individuals as a parent according to the result of the fitness function for generating the next generation;
(3) Crossover operation: generating a next generation of individuals through cross operation, and reserving part of characteristics of parent individuals;
(4) Mutation operation: and carrying out mutation operation on the generated next generation individuals, introducing new gene information, and increasing the diversity of the population.
The fitness function is used for evaluating the quality of each individual, namely the performance of each neural network structure, for the multi-layer perceptron neural network, the design of the fitness function depends on specific tasks and targets, generally, the fitness function calculates a score according to the performance of the network on a specific data set, the score generally reflects the capability of the network to complete the tasks, such as the accuracy of classification tasks, the mean square error of regression tasks, cross entropy loss, and the calculation of the accuracy, the mean square error of regression tasks and cross entropy loss is the prior art content in the field and is not an inventive scheme of the application.
The specific steps of running the trained neural network on the verification set and calculating the evaluation value include:
(1) Preparation of Inputting each sample in the verification set into a trained multi-layer perceptron neural network, and performing forward propagation to obtain an output of the network, wherein the forward propagation involves passing the input data through each layer of the network until a final output prediction is obtained;
(2) Calculating an evaluation value output by the neural network on the validation set according to a preselected evaluation standard, wherein the selection of the evaluation standard depends on the properties of the task, including accuracy, recall, F1 score, mean Square Error (MSE), cross entropy loss;
(3) The calculated values of the evaluation criteria are recorded and used to evaluate the performance of the neural network as input to the fitness function in the genetic algorithm.
S303: according to the output result of the hybrid optimization algorithm, adopting a correlation analysis method to analyze the correlation between the technological parameters and the extraction effect, constructing a mathematical model or a relation diagram between the technological parameters and the extraction effect, and determining constraint conditions for maximizing the extraction efficiency, minimizing the energy consumption and the technological parameters according to the analysis result Representing the minimum value of the process parameter data,Representing the maximum value of the process parameter data;
The specific steps of analyzing the relevance between the technological parameters and the extraction effect by adopting the relevance analysis method comprise the following steps:
(1) Receiving an output result of a hybrid optimization algorithm, wherein the output result comprises an optimized process parameter combination and corresponding extraction effect data;
(2) Preprocessing the collected output result of the hybrid optimization algorithm, including data cleaning, denoising and standardization, to obtain a hybrid optimization algorithm data set, and dividing the hybrid optimization algorithm data set into a training set, a verification set and a test set;
(3) Carrying out visual display on the relation between the technological parameters and the extraction effect by using a scatter diagram or a box diagram, and primarily judging the relevance between the technological parameters and the extraction effect by observing the trend and the distribution of the diagram;
(4) Calculating a correlation coefficient between a process parameter and an extraction effect by using a pearson correlation coefficient, judging whether the process parameter and the extraction effect are positively correlated or negatively correlated according to the magnitude and the sign of the correlation coefficient, and judging the strength of the correlation degree, wherein a pearson correlation coefficient calculation formula is the prior art in the field and is not an inventive scheme of the application and is not repeated herein;
(5) Constructing a regression model, carrying out regression analysis by taking the process parameters as independent variables and the extraction effect as dependent variables, and analyzing the influence degree and direction of the process parameters on the extraction effect through the coefficient and the significance test of the regression model;
the specific implementation steps of constructing the regression model comprise:
1) Collecting a process parameter and extraction effect relevance dataset, checking missing values, abnormal values or repeated items in the data, performing interpolation, deletion or combination, and performing standardization or normalization treatment on the data;
2) Setting process parameters as independent variables, and extracting effects as independent variables;
3) Whether a linear relation exists between the independent variable and the dependent variable is primarily judged by drawing a scatter diagram or calculating a correlation coefficient, and if the linear relation exists, whether error items of the independent variable and the dependent variable meet the assumption that the mean value is zero, the variance is constant and the self-correlation does not exist is checked;
4) Selecting a polynomial regression model, substituting the selected independent variable and dependent variable into the polynomial regression model, and establishing a regression equation;
5) Estimating coefficients in a regression equation by using a least square method, and calculating a predicted value of the dependent variable by using the estimated coefficients and the self-variable data, wherein the least square method is the prior art in the field and is not an inventive scheme of the present application and is not described in detail herein;
6) Adjusting coefficients in a regression equation, evaluating the fitting degree of the model to data, and checking the normality, the variance alignment and the independence of residual errors to judge whether the model meets the assumption or not;
7) If the assumption is satisfied, a t-test method is used to test the significance of the regression coefficient, i.e. to determine whether the independent variable has significant influence on the dependent variable, and model optimization is performed, wherein the t-test method is the prior art in the field and is not an inventive scheme of the present application, and is not described herein.
(6) Interaction effects between different process parameters, i.e. their effect on the extraction effect when acting together, are analyzed and the significance of the interaction effects is assessed using a multiple regression analysis.
Common process parameter constraints include: 1) Machine and tool limitations: the radius of the arc of the cutter, the feeding amount per rotation, the back cutting amount and the rotating speed of the main shaft; 2) Cutting force constraint: the cutting force is limited by the materials of the machine tool, the cutter and the workpiece, and must be kept within a safe range; 3) Energy consumption constraints: the energy consumed in the production process, such as electric power and hydraulic oil, needs to be controlled within the budget or efficiency requirements; 4) Environmental constraints: controlling pollutant emissions such as exhaust gas, waste liquid, noise and vibration; 5) Material constraint: raw material supply, material properties.
S304: constructing an optimization model by combining maximized extraction efficiency, minimized energy consumption and constraint conditions, solving the optimization model by using a genetic algorithm to obtain a group of optimal process parameter values, and converting the optimal process parameter values into specific control instructions according to the optimal process parameter values and the characteristics and requirements of a control system;
s305: after the control system executes the optimal process parameter value, collecting real-time data to carry out multidimensional evaluation on the extraction effect, and adjusting and optimizing the optimal process parameter value according to the evaluation result.
The specific implementation steps of the step S4 include:
s401: after the extraction is finished, placing the extracting solution into a high-speed centrifugal machine, setting the centrifugal speed and time, starting the centrifugal machine, enabling solid residues to settle to the bottom of a centrifugal tube under the action of centrifugal force, taking out supernatant, and filtering the supernatant by using a filter membrane;
S402: selecting supercritical fluid as mobile phase, injecting the filtered supernatant into supercritical fluid chromatograph, and starting supercritical fluid chromatograph to make supercritical fluid flow in chromatographic column, according to polarity, molecular weight and interaction force of lignum Aquilariae Resinatum effective components with mobile phase, adjusting type, temperature and pressure conditions of chromatographic column to make different effective components flow out of chromatographic column sequentially, thereby separating effective components to obtain effective component solution;
Carbon dioxide is selected as the supercritical fluid in the present invention,
The selection of the chromatographic column is critical to the separation effect, different types of chromatographic columns have different separation capacities for different compounds, the agilawood active ingredients interact with a mobile phase in the chromatographic column, the retention time of the different ingredients in the chromatographic column is different according to the respective chemical properties, and the different ingredients flow out of the chromatographic column successively along with the flow of a supercritical fluid, and the outflow time of the different ingredients is determined according to the signal change of a detector, so that the separation is realized.
S403: setting temperature and pressure, concentrating the effective component solution to obtain effective component crystal, filtering, and drying to obtain high-purity lignum Aquilariae Resinatum effective component crystal;
S404: and analyzing the high-purity agilawood effective component crystal by using a near infrared spectrometer to obtain near infrared spectrum data of the high-purity agilawood effective component crystal, and processing and analyzing the near infrared spectrum data by using a chemometric method to obtain content and purity information of the agilawood effective component.
Example 3
An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the extraction process optimization control method of the agilawood effective components when executing the computer program.
A computer readable storage medium having stored thereon computer instructions which, when executed, perform the steps of a method for optimizing control of a process for extracting active ingredients from agilawood.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and variations, modifications, substitutions and alterations of the above-described embodiments may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the present invention as defined by the claims, which are all within the scope of the present invention.
Claims (7)
1. The method for optimizing and controlling the extraction process of the agilawood effective components is characterized by comprising the following steps of:
Step S1: receiving agilawood raw materials, performing preliminary inspection by using a high-resolution imaging technology, automatically screening raw materials containing high-amount effective components by using an image recognition technology, preprocessing the screened agilawood raw materials containing high-amount effective components, removing redundant moisture in the agilawood raw materials by microwave-assisted drying, preparing an extraction solvent according to a solvent ratio obtained by optimizing a machine learning algorithm in advance, debugging and inspecting extraction equipment, and monitoring the running state of the equipment in real time by using an Internet of things technology;
Step S2: the method comprises the steps of putting processed agilawood raw materials into intelligent extraction equipment, adding an extraction solvent, dynamically adjusting extraction process parameters by using a deep learning algorithm according to historical data and real-time feedback, extracting according to the extraction process parameters, monitoring the temperature, the pressure and the solvent concentration in the extraction process in real time by using a high-precision sensor, setting an alarm and early warning mechanism, timely processing abnormal conditions, introducing cloud computing and big data technology, and carrying out remote monitoring and real-time analysis on the extraction process;
Step S3: selecting an optimization algorithm based on a genetic algorithm, performing hybrid optimization by combining a neural network, training and verifying the hybrid optimization algorithm by utilizing historical data and real-time data, formulating an optimization strategy according to an output result of the hybrid optimization algorithm, generating a control instruction based on the optimization strategy, performing multi-dimensional evaluation on an extraction effect after the optimization strategy is executed by a control system, and adjusting and optimizing the optimization strategy according to an evaluation result;
Step S4: after the extraction is finished, removing solid residues and impurities by utilizing a high-speed centrifugation and filtration technology, recovering an extracting solution, introducing a supercritical fluid chromatography technology and a crystallization technology, separating and purifying the recovered extracting solution to obtain high-purity agilawood effective components, and detecting the quality of the high-purity agilawood effective components by utilizing a near infrared spectrum;
Step S5: establishing a complete extraction and separation process database, monitoring and feeding back the whole extraction and separation process, and treating and recycling the solvent and the extracted waste;
the specific implementation steps of the step S1 include:
S101: receiving agilawood raw materials, scanning the agilawood raw materials by using high-resolution imaging equipment, obtaining agilawood raw material images, and preprocessing the agilawood raw material images;
S102: loading a trained image recognition model, inputting a preprocessed agilawood raw material image for reasoning, carrying out probability distribution P on a reasoning result, setting a threshold H, comparing the set threshold with the probability value, and if so, carrying out the analysis on the training result The method includes the steps that the raw materials in the image contain high-content effective components, and agilawood raw materials containing the high-content effective components are screened out;
s103: cleaning the screened agilawood raw materials containing high amounts of active ingredients, removing impurities and dirt on the surfaces, and cutting or crushing to obtain treated agilawood raw materials;
The specific implementation step of the step S1 further includes:
S104: placing the treated agilawood raw material into microwave drying equipment, setting microwave power, frequency and drying time, uniformly placing the agilawood raw material on a tray or a conveyor belt of the microwave drying equipment, starting the microwave drying equipment to dry the raw material, monitoring temperature and humidity changes in the drying process, stopping microwave drying when a preset drying degree is reached, and taking out the dried agilawood raw material;
S105: collecting historical data, preprocessing, analyzing the historical data by using a machine learning algorithm, predicting the optimal solvent ratio, and preparing an extraction solvent according to a prediction result;
S106: debugging and checking the extraction equipment, connecting the extraction equipment to a monitoring system by utilizing the internet of things technology, monitoring the running state, temperature and pressure of the equipment in real time, setting an alarm threshold value, and sending out an alarm in time when the state of the equipment is abnormal;
the specific implementation steps of the step S4 include:
s401: after the extraction is finished, placing the extracting solution into a high-speed centrifugal machine, setting the centrifugal speed and time, starting the centrifugal machine, enabling solid residues to settle to the bottom of a centrifugal tube under the action of centrifugal force, taking out supernatant, and filtering the supernatant by using a filter membrane;
S402: selecting supercritical fluid as mobile phase, injecting the filtered supernatant into supercritical fluid chromatograph, and starting supercritical fluid chromatograph to make supercritical fluid flow in chromatographic column, according to polarity, molecular weight and interaction force of lignum Aquilariae Resinatum effective components with mobile phase, adjusting type, temperature and pressure conditions of chromatographic column to make different effective components flow out of chromatographic column sequentially, thereby separating effective components to obtain effective component solution;
s403: setting temperature and pressure, concentrating the effective component solution to obtain effective component crystal, filtering, and drying to obtain high-purity lignum Aquilariae Resinatum effective component crystal;
S404: and analyzing the high-purity agilawood effective component crystal by using a near infrared spectrometer to obtain near infrared spectrum data of the high-purity agilawood effective component crystal, and processing and analyzing the near infrared spectrum data by using a chemometric method to obtain content and purity information of the agilawood effective component.
2. The method for optimizing and controlling the extraction process of the active ingredient of agilawood according to claim 1, wherein the specific implementation step of step S3 comprises:
S301: collecting historical data and real-time data Wherein, the method comprises the steps of, wherein,Representing the ith extracted process parameter data,Represents the j-th current environmental parameter data,Representing kth current extraction effect data, i representing the number of extracted process parameter data, j representing the number of current environmental parameter data, k representing the number of current extraction effect data;
S302: selecting a multi-layer perceptron neural network structure, designing a genetic algorithm of multi-parameter cascade coding, taking the weight and parameters of the multi-layer perceptron neural network structure as genes of the genetic algorithm, determining an adaptability function of the genetic algorithm, performing iterative optimization of crossover operation and mutation operation on the genetic algorithm according to the adaptability function, using the neural network weight and parameters generated by the genetic algorithm in each iteration to construct the multi-layer perceptron neural network, and performing the iterative optimization on the genetic algorithm The method comprises the steps of dividing the multi-layer perceptron neural network into a training set and a verification set, training the multi-layer perceptron neural network by using the training set, obtaining an evaluation value output by the multi-layer perceptron neural network by using the verification set through forward propagation, and obtaining an output result of a hybrid optimization algorithm by taking the evaluation value as an fitness value of each neural network.
3. The method for optimizing and controlling the extraction process of the active ingredient of agilawood according to claim 2, wherein the specific implementation step of step S3 further comprises:
S303: according to the output result of the hybrid optimization algorithm, adopting a correlation analysis method to analyze the correlation between the technological parameters and the extraction effect, constructing a relation diagram between the technological parameters and the extraction effect, and determining constraint conditions for maximizing the extraction efficiency, minimizing the energy consumption and the technological parameters according to the analysis result;
S304: constructing an optimization model by combining constraint conditions, solving the optimization model by using a genetic algorithm to obtain a group of optimal technological parameter values, and converting the optimal technological parameter values into specific control instructions according to the optimal technological parameter values and the characteristics and requirements of a control system;
s305: after the control system executes the optimal process parameter value, collecting real-time data to carry out multidimensional evaluation on the extraction effect, and adjusting and optimizing the optimal process parameter value according to the evaluation result.
4. The method for optimizing control of an extraction process of an active ingredient of agilawood according to claim 3, wherein the constraint conditions in S303 include:
；
Wherein, The extraction efficiency is represented by the number of extraction steps,Represents the minimum value of the extraction efficiency,Represents the energy consumption in the extraction process,Representing the maximum energy consumption in the extraction process,Representing the minimum value of the process parameter data,Representing the maximum value of the process parameter data.
5. The process optimization control system for extracting the active ingredients of agilawood, which is realized based on the process optimization control method for extracting the active ingredients of agilawood as claimed in any one of claims 1-4, and is characterized by comprising the following steps: the device comprises a preprocessing module, an extraction module and a control module;
the preprocessing module is used for shooting an agilawood raw material image through a high-resolution camera, performing preliminary inspection, preprocessing and solvent preparation on the agilawood raw material image, and comprises an image recognition unit and a proportioning unit, wherein the image recognition unit is used for acquiring the agilawood raw material image, configuring a recognition algorithm to recognize and classify the raw material image to form a raw material set, and the proportioning unit is used for acquiring the raw material set and historical data, and generating solvent types and solvent proportions of solvents based on the historical data;
The extraction module is used for adjusting the process parameters and monitoring the extraction process in real time, and comprises a parameter regulation and control unit, wherein a deep learning algorithm is configured in the parameter regulation and control unit and is used for acquiring the types and the proportions of the solvents and dynamically adjusting the extracted process parameters;
The control module is used for formulating an extraction strategy and evaluating and optimizing the execution effect; the control module comprises a mixing unit and a strategy conversion unit, wherein a genetic algorithm is configured in the mixing unit, a mixed optimization model is constructed based on the genetic algorithm and a neural network, a conversion strategy is configured in the strategy conversion unit, the conversion strategy comprises the steps of obtaining the output result of the mixed optimization model, and formulating an optimization strategy based on the output result, and the optimization strategy is used for solving the mixed optimization model and obtaining a control instruction.
6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the method for optimizing and controlling the extraction process of the active ingredient of agilawood according to any one of claims 1 to 4 when the processor executes the computer program.
7. A computer-readable storage medium having stored thereon computer instructions which, when executed, perform the steps of the method for optimizing control of the extraction process of the active ingredient of agilawood according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410660084.5A CN118466422B (en) | 2024-05-24 | 2024-05-24 | System and method for optimizing and controlling extraction process of agilawood effective components |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410660084.5A CN118466422B (en) | 2024-05-24 | 2024-05-24 | System and method for optimizing and controlling extraction process of agilawood effective components |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118466422A CN118466422A (en) | 2024-08-09 |
| CN118466422B true CN118466422B (en) | 2024-10-18 |
Family
ID=92151480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410660084.5A Active CN118466422B (en) | 2024-05-24 | 2024-05-24 | System and method for optimizing and controlling extraction process of agilawood effective components |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118466422B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118938841B (en) * | 2024-08-29 | 2025-02-11 | 苏州茂可科技有限公司 | Intelligent purification process control system for biopharmaceuticals based on big data |
| CN119202598A (en) * | 2024-09-10 | 2024-12-27 | 菏泽中禾健元生物科技有限公司 | A method and system for extracting and analyzing neuraminic acid based on multi-source data prediction |
| CN119626360A (en) * | 2024-12-13 | 2025-03-14 | 连云港福瑞生物科技有限公司 | A monitoring system for podophyllotoxin extraction process based on data analysis |
| CN119398717B (en) * | 2025-01-03 | 2025-03-18 | 天津联博化工股份有限公司 | Intelligent detection method and device for purity of food-grade carbon dioxide |
| CN119668094B (en) * | 2025-02-20 | 2025-04-29 | 北京春风药业有限公司 | Dynamic adjustment method and system for traditional Chinese medicine extraction device |
| CN119992431B (en) * | 2025-04-17 | 2025-07-01 | 中煤科工集团重庆智慧城市科技研究院有限公司 | A method and system for identifying alum bloom on sewage surface |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116381107A (en) * | 2022-10-27 | 2023-07-04 | 浙江中医药大学 | Method for ultrasonically extracting effective components of astragalus root safflower medicament by using natural eutectic solvent |
| CN117630265A (en) * | 2023-11-28 | 2024-03-01 | 哈尔滨工业大学 | A rapid, automated method for distinguishing components in mixture solutions based on TLC-SERS technology |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3059236B1 (en) * | 2016-11-25 | 2019-05-17 | Plant Advanced Technologies Pat | EXTRACTS FROM PLANTS OF THE GENUS TAGETES AND USES THEREOF |
| CN117787743A (en) * | 2023-12-27 | 2024-03-29 | 江西理工大学 | An intelligent evaluation method and system for blast furnace conditions based on big data |
| CN117899134A (en) * | 2024-01-24 | 2024-04-19 | 张北艾业健康科技有限公司 | Microwave-assisted extraction process of wormwood fat-soluble active ingredients |
-
2024
- 2024-05-24 CN CN202410660084.5A patent/CN118466422B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116381107A (en) * | 2022-10-27 | 2023-07-04 | 浙江中医药大学 | Method for ultrasonically extracting effective components of astragalus root safflower medicament by using natural eutectic solvent |
| CN117630265A (en) * | 2023-11-28 | 2024-03-01 | 哈尔滨工业大学 | A rapid, automated method for distinguishing components in mixture solutions based on TLC-SERS technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118466422A (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118466422B (en) | System and method for optimizing and controlling extraction process of agilawood effective components | |
| Zhang et al. | Synthesis optimization and adsorption modeling of biochar for pollutant removal via machine learning | |
| Rego et al. | Optimization of sugarcane bagasse pretreatment using alkaline hydrogen peroxide through ANN and ANFIS modelling | |
| CN118398942B (en) | Chain type power battery disassembly and recovery system and method | |
| CN117263464A (en) | Energy-saving industrial sewage treatment system and sewage treatment method | |
| CN101995891B (en) | Online analysis method for moisture of solid mother material recovery system in aromatic acid production | |
| CN119285041B (en) | Pickling waste liquid recycling system and method | |
| Peng et al. | Implementation of near-infrared spectroscopy and convolutional neural networks for predicting particle size distribution in fluidized bed granulation | |
| CN106406257B (en) | A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning | |
| US12083560B2 (en) | Sorting-based garbage classification method and device | |
| CN1570629A (en) | On-line soft measurement modeling method for 4-CBA content based on least square algorithm of restricted memory part | |
| CN112907107B (en) | Fishery accident emergency treatment system and method based on multisource information fusion | |
| CN101413882A (en) | Method and apparatus for detecting chlorine and hydrogen chloride in PVC production | |
| CN118820724A (en) | Water quality stabilization method for filtration equipment based on multi-parameter fusion control | |
| Sevindik et al. | Investigation of the effectiveness of edible oils as solvent in reactive extraction of some hydroxycarboxylic acids and modeling with multiple artificial intelligence models | |
| CN118384234A (en) | Hair-growing and hair-blacking composition and preparation equipment control method | |
| CN118420012A (en) | Urban sewage treatment aeration control system and method | |
| CN212159541U (en) | System equipment for detecting gas-phase substances in spectrum cooperation mode | |
| CN119294795B (en) | Fully automatic flow control method and device based on industrial production | |
| CN117217633A (en) | Process industry digital model based on artificial intelligence and construction method thereof | |
| JP2916893B2 (en) | Waste treatment apparatus and control method | |
| Xu et al. | Data driven control of underflow slurry concentration in deep cone thickener | |
| CN118762769B (en) | Plastic bag material recycling system | |
| Fathi Vajargah et al. | Monitoring a Two-Stage Process Using Adaptive Control Charts with a Markov-Monte Carlo Chain Approach | |
| CN112666908A (en) | Aluminum product recovery pretreatment wastewater treatment system and working method thereof |
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 |