CN108719516A - One kind being based on RBF neural tea machine processing control parameter intelligence setting method - Google Patents
One kind being based on RBF neural tea machine processing control parameter intelligence setting method Download PDFInfo
- Publication number
- CN108719516A CN108719516A CN201810493559.0A CN201810493559A CN108719516A CN 108719516 A CN108719516 A CN 108719516A CN 201810493559 A CN201810493559 A CN 201810493559A CN 108719516 A CN108719516 A CN 108719516A
- Authority
- CN
- China
- Prior art keywords
- tea machine
- rbf neural
- processing control
- control parameter
- tea
- 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.)
- Pending
Links
- 241001122767 Theaceae Species 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000001537 neural effect Effects 0.000 title claims abstract description 12
- 238000011478 gradient descent method Methods 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims abstract description 12
- 230000035945 sensitivity Effects 0.000 claims abstract description 4
- 238000005457 optimization Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 abstract description 3
- 238000005520 cutting process Methods 0.000 abstract description 2
- 238000001824 photoionisation detection Methods 0.000 description 30
- 101150056779 rbf-1 gene Proteins 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
- A23F—COFFEE; TEA; THEIR SUBSTITUTES; MANUFACTURE, PREPARATION, OR INFUSION THEREOF
- A23F3/00—Tea; Tea substitutes; Preparations thereof
- A23F3/06—Treating tea before extraction; Preparations produced thereby
-
- 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
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
- G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Automation & Control Theory (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Food Science & Technology (AREA)
- Data Mining & Analysis (AREA)
- Polymers & Plastics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Feedback Control In General (AREA)
- Tea And Coffee (AREA)
Abstract
It is of the invention a kind of based on RBF neural tea machine processing control parameter intelligence setting method, field of intelligent control is processed for tea machine equipment, the cardinal principle of this method is to remove adjustment pid parameter using RBF neural network model, to the related tealeaves status data acquired out of tea machine, with these data, by RBF neural network model, go to be fitted the relationship between tea machine system input and output, the operation of tea machine when simulating cutting parameter change.Control the machined parameters of tealeaves temperature and humidity respectively using cascade PID.According to peaceful outer Jacobian gusts of a RBF neural network model（Sensitivity information of the output of object to control input）Information.Adjustment tri- parameters of P, I, D are gone with gradient descent method, the input of tea machine processing control parameter is obtained with this.Change the adjustment that method makes tea machine processing control parameter be optimized so that the factor of merit of sample tea is stablized and its greatly improved after tea processing.
Description
Technical field
Type of the present invention belongs to tea machine device intelligence control technology field, is related to one kind and going intelligence based on RBF neural network model
The system that processing control parameter can be adjusted
Background technology
With the development of China's mechanization, the technology of tea processing machine manufacture view comparative maturity is basic to realize
Full mechanical processing, but existing small scale.Initial investment is huge, but still can not be detached from manual operation, and subsequent artefacts' cost is without bright
It is aobvious to reduce；Maintenance of machine, the loss that catastrophic discontinuityfailure is brought, cost caused by the culture of the high-tech type talent increase；Machinery
Closed-loop control is cannot achieve, opened loop control is still used, time and the temperature parameter of tea machine are set by worker, is still existed very big
Unstability, it is low to be easy to cause quality of sampling tea.
But currently, there is no technologies or method that tea machine processing control parameter intelligent optimization adjusts aspect.
Invention content
The purpose of the invention is to overcome the processing control parameter that tea machine is arranged by worker's experience, there are great shakinesses
It is qualitative, the disadvantages such as quality of sampling tea is low are be easy to cause, are provided a kind of intelligently excellent based on RBF neural tea machine processing control parameter
Change the method adjusted.
Adjustment pid parameter is removed using RBF neural network model, to the related tealeaves status data acquired out of tea machine, fortune
With these data, by RBF neural network model, the relationship between being fitted tea machine system input and exporting.Simulating cutting is joined
The operation of tea machine when number changes.Control the machined parameters of tealeaves temperature and humidity respectively using cascade PID.According to peaceful one outer
Jacobian gusts of RBF neural network model（Sensitivity information of the output of object to control input）Information.With under gradient
Drop method goes adjustment tri- parameters of P, I, D, and the input of tea machine processing control parameter is obtained with this
By the invention, a kind of intelligent method is provided for the adjustment of tea machine processing control parameter so that finished product after tea processing
The factor of merit of tea is stablized and its is greatly improved.
Description of the drawings
Fig. 1 is a kind of scantling plan based on RBF neural tea machine processing control parameter intelligence setting method of the present invention；
In figure：1.RBF3,2.RBF4,3. temperature PID gradient descent method, 4. humidity PID gradient descent methods, 5. temperature PIDs, 6. is wet
Spend PID, 7.RBF1,8.RBF2,11., 12., 13., 14., 15., 16., 17., 18., 21., 22., 23.Temperature, 24.Humidity, 25.Temperature, 26.Humidity
Specific implementation mode
Invention is described in detail with reference to the accompanying drawings and detailed description.
A kind of scantling plan based on RBF neural tea machine processing control parameter intelligence setting method of patent of the present invention is such as
Shown in figure one, including 1.RBF3,2.RBF4,3. temperature PID gradient descent method, 4. humidity PID gradient descent methods, 5. temperature PIDs,
6. humidity PID, 7.RBF1,8.RBF2.
The part 7.RBF1,8.RBF2, principle is identical, this two-part effect is the response for simulating tea machine output to input,
By taking RBF1 as an example.First, it would be desirable to obtain the data of tea machine control system, i.e. two of master control tealeaves temperature and humidity respectively
Control parameterWithAnd after these state modulators tealeaves status data, i.e. tealeaves temperature data and humidity data are protected
Array is saved as,(k) state modulator obtains tealeaves(k) humidity,(k) temperature data, 24.Humidity, 25.Temperature
Degree be RBF1 output, 21.For the input of RBF1.The input X of RBF models is 5 dimensional vectors, including(k),_1(k),_2(k),_1(k),_ 2 (k), wherein_1(k)=(k-1),_2(k)=(k-2),_1(k)
=(k-1),_2(k)=(k-2), (k-1), (k-2) are the state of a control twice before kth secondary control.It is two to export Y
Dimensional vector, including 24.Humidity, 25.Temperature.
The part 1.RBF3,2.RBF4, principle is identical, this two-part effect is to adjust 5. temperature PIDs, 6. humidity for dynamic
PID provides 11., 12., i.e. Jacobian battle arrays of neural network（As sensitivity of the output of object to control input
Information）, by taking RBF3 as an example, the input X of RBF3 models is three-dimensional vector, including, 21., 23.Temperature,_ 1 temperature,
Output Y is one-dimensional vector, is.In the model, radial basis function is using Gaussian function, expression formula：,,=, RBF3
W, b are carried out using gradient descent method, C parameters update, and update mode is： Η is learning rate, α be momentum because
Son.It can be obtained from above：11.=
5. temperature PID, 6. parts humidity PID, in the two PID controls, using increment type PID formula, expression formula is：
3. temperature PID gradient descent method, 4. humidity PID gradient descent methods parts, two kinds of principles are the same, with 3. temperature PID gradients
For descent method, in the gradient descent method, the index of neural network tuned proportion integration differentiation is needed to be：, therefore P,
I, the mode of tri- parameter tunings of D is： ,As 11., 12., point
It is not provided by RBF3 and RBF4.In above-mentioned formula, from PID increment type formula：
,,.The present invention
Patent one kind is divided into two parts based on RBF neural tea machine processing control parameter intelligent optimization setting method carrying out practically process,
First part is trained 7.RBF1 and 8.RBF2 neural network models, goes simulation tea machine control system；Second part is with
Trained 7.RBF1 and 8.RBF2 neural network models go simulation tea machine operation, are using peaceful outer 1.RBF3 and 2.RBF4 networks
Model distinguishes 5. temperature PID of on-line tuning and 6. humidity pid parameters.
First part：The function library that RBF models are carried using MATLAB is trained, and the function used is newrbe
() obtains the model of 7.RBF1 and 8.RBF2 with this.
Second part：Remove control temperature and humidity parameter, such as attached drawing respectively with cascade PID.Used here as 1.RBF3 nets
Network model goes to adjust 5. temperature PID parameters, is gone to adjust 6. humidity pid parameters with 2.RBF4 network models.First from current tealeaves
Temperature starts, and is calculated into 5. temperature PIDs, and processing control parameter 21. is obtained, with 21.Tea machine system is acted on,
RBF1 network models are acted on, 24. can be obtainedHumidity, 25.Temperature, by 24.Humidity be passed through 6. humidity PID into
Row calculates, and obtains processing control parameter 22., 22., tea machine system is acted on, that is, acts on RBF2 network models, can obtain
To 23.Temperature, 26.Humidity, so far, the PID control of a process terminate, it is remaining be exactly it is according to control as a result,
It goes dynamically to adjust tri- parameters of PID, passes through the input 21. of this time, with the output 23. after effectTemperature enters
1.RBF3 network models are calculated, and obtain 11., by 11.It is calculated into 3. temperature PID gradient descent methods,
Obtain 13., 14., 15., 5. temperature PIDs next are substituted into these three values, update pid parameter, similarly,
Pass through the input 22. of this time, with the output 26. after effectHumidity enters 2.RBF4 network models and is calculated,
Obtain 12., by 12.It is calculated, is obtained, 16. into 4. humidity PID gradient descent methods, 17.,
18., 6. humidity PID next are substituted into these three values, update pid parameter, it, can be with according to the principle of gradient descent method
The index adjusted：, it is reduced to arbitrarily small, pid parameter can also be optimal, and be come with this
To optimal 21., 22.Processing control parameter.
21., 22.Two processing control parameters, 21.For heating parameters, heating element is electric furnace heating wire, carborunbum tube,
It is controlled by high-current relay, 22.For parameter of drying, the component that dries is pump drainage air discharging machine.
Claims (5)
1. one kind being based on RBF neural tea machine processing control parameter intelligent optimization setting method, which is characterized in that use RBF
Neural network model removes adjustment pid parameter, and optimal processing control parameter is obtained with this.
2. one kind according to claim 1 is based on RBF neural tea machine processing control parameter intelligent optimization setting method,
It is characterized in that, passing through RBF neural network model with these data to the related tealeaves status data acquired out of tea machine
It goes to learn, the relationship being fitted between tea machine system input and output.
3. one kind according to claim 1 is based on RBF neural tea machine processing control parameter intelligent optimization setting method,
It is characterized in that, controlling tealeaves temperature and humidity parameter respectively using cascade PID.
4. one kind according to claim 3 is based on RBF neural tea machine processing control parameter intelligent optimization setting method,
It is characterized in that, the information of adjustment tri- parameters of P, I, D is by Jacobian gusts of RBF neural network model（The output of object is to control
Make the sensitivity information of input）It provides.
5. one kind according to claim 3 is based on RBF neural tea machine processing control parameter intelligent optimization setting method,
It is characterized in that, when adjustment tri- parameters of P, I, D, adjusted using gradient descent method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810493559.0A CN108719516A (en) | 2018-05-22 | 2018-05-22 | One kind being based on RBF neural tea machine processing control parameter intelligence setting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810493559.0A CN108719516A (en) | 2018-05-22 | 2018-05-22 | One kind being based on RBF neural tea machine processing control parameter intelligence setting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108719516A true CN108719516A (en) | 2018-11-02 |
Family
ID=63937891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810493559.0A Pending CN108719516A (en) | 2018-05-22 | 2018-05-22 | One kind being based on RBF neural tea machine processing control parameter intelligence setting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108719516A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375668A (en) * | 2018-12-22 | 2019-02-22 | 武夷山市通仙茶业有限责任公司 | A kind of wall temperature detection and regulator control system suitable for tea roller fried green process |
| CN110262582A (en) * | 2019-07-30 | 2019-09-20 | 中原工学院 | A kind of barotor temprature control method based on improvement RBF neural |
| CN110554715A (en) * | 2019-10-25 | 2019-12-10 | 攀钢集团攀枝花钢铁研究院有限公司 | RBF neural network-based PID control method for hydrolysis process temperature of titanyl sulfate plus seed crystal |
| CN114241221A (en) * | 2022-02-28 | 2022-03-25 | 湖南工商大学 | Control system based on neural network prediction algorithm |
| CN115009278A (en) * | 2022-08-08 | 2022-09-06 | 潍柴动力股份有限公司 | Cruise control method, device, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393770A (en) * | 2011-11-25 | 2012-03-28 | 任洪娥 | Temperature and humidity control method during a wood drying process based on combination of radial basis function (RBF) nerve network and proportional integral derivative (PID) closed loop control |
| US20130151019A1 (en) * | 2011-12-12 | 2013-06-13 | Vigilent Corporation | Controlling air temperatures of hvac units |
-
2018
- 2018-05-22 CN CN201810493559.0A patent/CN108719516A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393770A (en) * | 2011-11-25 | 2012-03-28 | 任洪娥 | Temperature and humidity control method during a wood drying process based on combination of radial basis function (RBF) nerve network and proportional integral derivative (PID) closed loop control |
| US20130151019A1 (en) * | 2011-12-12 | 2013-06-13 | Vigilent Corporation | Controlling air temperatures of hvac units |
Non-Patent Citations (2)
| Title |
|---|
| 李兵等: "基于模糊PID控制的六安瓜片远红外烘焙机设计", 农机化研究, no. 08, pages 149 * |
| 申超群等: "温室温度控制系统的RBF神经网络PID控制", 控制工程, vol. 24, no. 02, pages 3 - 5 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375668A (en) * | 2018-12-22 | 2019-02-22 | 武夷山市通仙茶业有限责任公司 | A kind of wall temperature detection and regulator control system suitable for tea roller fried green process |
| CN110262582A (en) * | 2019-07-30 | 2019-09-20 | 中原工学院 | A kind of barotor temprature control method based on improvement RBF neural |
| CN110554715A (en) * | 2019-10-25 | 2019-12-10 | 攀钢集团攀枝花钢铁研究院有限公司 | RBF neural network-based PID control method for hydrolysis process temperature of titanyl sulfate plus seed crystal |
| CN114241221A (en) * | 2022-02-28 | 2022-03-25 | 湖南工商大学 | Control system based on neural network prediction algorithm |
| CN115009278A (en) * | 2022-08-08 | 2022-09-06 | 潍柴动力股份有限公司 | Cruise control method, device, equipment and storage medium |
| CN115009278B (en) * | 2022-08-08 | 2022-11-29 | 潍柴动力股份有限公司 | Cruise control method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108719516A (en) | One kind being based on RBF neural tea machine processing control parameter intelligence setting method | |
| CN109597449A (en) | A kind of ultrasonic wave separating apparatus temprature control method neural network based | |
| CN105807632B (en) | A kind of furnace temp controller design method based on improvement dahlin algorithm | |
| CN106647271B (en) | Nonlinear system adaptive proportion integration control method based on neural network theory | |
| DE19501077A1 (en) | Adaptive cross directional decoupling control systems | |
| CN110262582A (en) | A kind of barotor temprature control method based on improvement RBF neural | |
| CN102147613B (en) | Model predictive control method and system for moisture and temperature of tobacco redryer | |
| CN110161841A (en) | A kind of feedforward-fuzzy PID control method suitable for temporarily rushing formula transonic wind tunnel | |
| Hagenmeyer et al. | Robustness analysis with respect to exogenous perturbations for flatness-based exact feedforward linearization | |
| CN108287471A (en) | Inclined methods of self-tuning of the format Non-Model Controller based on systematic error of MIMO | |
| CN110202768B (en) | Temperature control method for charging barrel of injection molding machine | |
| EP3296821B1 (en) | Closed-loop model parameter identification techniques for industrial model-based process controllers | |
| Zhang et al. | Parameter optimization of PID controllers based on genetic algorithm | |
| CN105911862B (en) | A kind of temperature Control of Electric Heater method | |
| CN105892296B (en) | A kind of fractional order dynamic matrix control method of industry heating furnace system | |
| Liu et al. | Nonlinear generalized predictive control of the crystal diameter in CZ-Si crystal growth process based on stacked sparse autoencoder | |
| CN109460890B (en) | Intelligent self-healing method based on reinforcement learning and control performance monitoring | |
| Kempton et al. | Self-organization of weighted networks for optimal synchronizability | |
| CN108932571A (en) | The setting method and device of cigarette primary processing initial technological parameter | |
| CN105334751B (en) | A kind of stability controller design method of batch injection moulding process | |
| CN110531612A (en) | A kind of parameter tuning method of Fractional Order PID Controller | |
| CN110705042A (en) | Steam turbine valve flow characteristic identification method, system and medium based on T-S fuzzy model | |
| Kergus et al. | Frequency-domain data-driven control design in the Loewner framework | |
| CN105279579A (en) | Optimal selection method of PID control parameter of water turbine generator set excitation system | |
| CN107728481A (en) | A kind of closed loop modeling method and device based on Model Predictive Control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181102 |