CN110262582A - A kind of barotor temprature control method based on improvement RBF neural - Google Patents
A kind of barotor temprature control method based on improvement RBF neural Download PDFInfo
- Publication number
- CN110262582A CN110262582A CN201910696867.8A CN201910696867A CN110262582A CN 110262582 A CN110262582 A CN 110262582A CN 201910696867 A CN201910696867 A CN 201910696867A CN 110262582 A CN110262582 A CN 110262582A
- Authority
- CN
- China
- Prior art keywords
- temperature
- indicate
- control
- formula
- dye liquor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000001537 neural effect Effects 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000006872 improvement Effects 0.000 title claims description 11
- 238000005070 sampling Methods 0.000 claims abstract description 66
- 230000008859 change Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 57
- 210000002569 neuron Anatomy 0.000 claims description 38
- 238000004364 calculation method Methods 0.000 claims description 34
- 230000006870 function Effects 0.000 claims description 34
- 238000005457 optimization Methods 0.000 claims description 9
- 238000011478 gradient descent method Methods 0.000 claims description 6
- 238000002791 soaking Methods 0.000 claims description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 2
- 238000009790 rate-determining step (RDS) Methods 0.000 claims description 2
- 210000005036 nerve Anatomy 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 10
- 241001584775 Tunga penetrans Species 0.000 abstract description 6
- 230000003044 adaptive effect Effects 0.000 abstract description 6
- 239000010410 layer Substances 0.000 description 52
- 238000004422 calculation algorithm Methods 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 13
- 239000004753 textile Substances 0.000 description 11
- 239000004744 fabric Substances 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000001276 controlling effect Effects 0.000 description 3
- 238000004043 dyeing Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000004218 nerve net Anatomy 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 229920000742 Cotton Polymers 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000009123 feedback regulation Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 230000008844 regulatory mechanism Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06B—TREATING TEXTILE MATERIALS USING LIQUIDS, GASES OR VAPOURS
- D06B23/00—Component parts, details, or accessories of apparatus or machines, specially adapted for the treating of textile materials, not restricted to a particular kind of apparatus, provided for in groups D06B1/00 - D06B21/00
- D06B23/20—Arrangements of apparatus for treating processing-liquids, -gases or -vapours, e.g. purification, filtration or distillation
- D06B23/22—Arrangements of apparatus for treating processing-liquids, -gases or -vapours, e.g. purification, filtration or distillation for heating
-
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D23/00—Control of temperature
- G05D23/19—Control of temperature characterised by the use of electric means
-
- 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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Textile Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a kind of based on the barotor temprature control method for improving RBF neural, includes the following steps: S1, establishes dye liquor temperature change curve model；S2 calculates temperature control deviation and given threshold according to the dye liquor temperature in the actual measured value of dye liquor temperature and the dye liquor temperature change curve model of corresponding sampling instant；S3 is respectively adopted PD control device, PID controller according to the relationship of temperature control deviation and given threshold and/or carries out Discrete control to dye liquor temperature based on the PID controller for improving RBF neural, until the numerical value of temperature control deviation is zero.The present invention has been implemented in combination with self adaptive control and adjustment to dye jigger temperature control system under severe application environment using feature learning method and PID controller based on improved RBF neural, it ensure that the high-precision and high efficiency of control process, and the control adjustment period is short, and control efficiency is high.
Description
Technical field
The present invention relates to textile industry dye gigging process automation fields, more particularly to one kind is based on improvement RBF nerve net
The barotor temprature control method of network.
Background technique
Dye gigging link is the indispensable link of process of textile production, and quality of textile products is controlled and managed most important.?
During dye gigging, guarantee that dye liquor temperature accurately controls and directly affect fabric dye gigging quality, is in control system for dye jigger design
Core work.It is neural network based with the high speed development of automatic control technology and deepening continuously for control algolithm research
Control algolithm has been more and more widely used in industrial control field, is replaced with control algolithm neural network based
State modulator precision not only can be improved for traditional control algorithm, but also feedback regulation speed can be improved, to improve control
System entirety control efficiency reduces the irregular phenomenon of textile dyeing, promotes fabric quality, is conducive to the development of China's textile technology and spins
Fabric it is for export.
Mainly based on pid control algorithm, such control algolithm includes the existing algorithm for dye jigger control field
Ratio, integral and 3 class of differential control component, and PID controller is ratio, the product of the difference by preset value and real output value
Divide and the linear combination of differential controls controlled device as comprehensive control amount.[bibliography [1]: Mahmood Q A,
Nawaf AT,Esmael M N,et al.PID Temperature Control of Demineralized Water Tank
[J].IOP ConferenceSeries Materials Science and Engineering,2018,454:012031.]
In the use process of PID control system, the parameter determination of pid control algorithm is difficult point.In practical applications, these parameter meetings
It is influenced by specific works environment, is asked so that conventional PID controllers there are parameters coarse, bad adaptability and control effect be not good enough etc.
Topic, it is difficult to adapt to complicated operating condition.Using conventional PID controller, there is system rejection to disturbance ability is poor, for different mathematics
The problems such as system suitability of model is poor, and overshoot is big [bibliography [2]: El-Samahy A A, Shamseldin M
A.Brushless DC motor tracking control using self-tuning fuzzy PID control and
model reference adaptive control[J].Ain Shams Engineering Journal,2016:
S209044791630003X.]。
For this problem, by fuzzy control in conjunction with PID control, Fuzzy Adaptive PID Control algorithm is proposed, is utilized
The parameter of fuzzy rule on-line tuning PID, then temperature adjusting is carried out by controller.It is small to have reached fast response time, overshoot, it is right
In the system of different mathematics, adaptable effect [bibliography [3]: Du Wen, Ding. (2010) .The
Resistance-heated Furnace Temperature Control Based on CMAC-Fuzzy Immune PID
Control.Applied Mechanics and Materials.29-32.10.4028/www.scientific.net/
AMM.29-32.407.].Although such algorithm calculates link to control parameter and adjusted, control efficiency increases,
It is that algorithm control precision is not high, and still continues to use the multiple feed-back regulatory mechanism of PID, fails fundamentally to shorten control week
Phase.
The algorithm proposed at present has reached the target of self adaptive control to a certain extent, but there are still many problems not
It is resolved, it would be highly desirable to which further research: 1) with the development of textile technology, fabric is many kinds of, fabric texture multiplicity, dyer
Skill is different (for example: cotton, silk quality, staple fibre etc.), therefore should establish respectively dye liquor temperature control to different fabrics
Simulation realizes the Precise control of dye gigging process；2) as textile technology continues to develop, textile industry dog-eat-dog, how
Control reaction speed is further increased, the fabric loss during dye gigging is reduced, improves textile production efficiency, and be badly in need of solution
Problem of industry certainly.3) existing control algolithm needs multiple feedback adjustment process, and control adjustment excessive cycle, control efficiency is not
Height, and with the development of textile technology, is gradually increased temperature controlled requirement, and precision is limited is difficult to for existing control algolithm control
Reach higher production requirement.
In recent years, feature learning algorithm development neural network based is rapid, hands in intelligent information, intelligent medical, intelligence
The fields such as logical, industrial production are widely used.Such algorithm passes through a large amount of priori datas being collected into and extracts control ginseng
Number variation characteristic, corrective networks weight, training network model realize the real-time of control parameter as control parameter core algorithm
Quickly adjustment.Even if fabric category multiplicity, control process is complicated, and control algolithm neural network based can also be according to practical feelings
Condition switches different weight models, and different application scene is adaptively adjusted in realization, has good self adaptive control characteristic.
[bibliography [3]: Liu Y., Wang J., Yang J., Li Q. (2018) An Improved PID Algorithm
Based on BP Neural Network of Ambient Temperature Controller.In:Qiao F.,
Patnaik S.,Wang J.(eds)Recent Developments in Mechatronics and Intelligent
Robotics.ICMIR 2017.Advances in Intelligent Systems and Computing,vol
690.Springer, Cham] and [bibliography [4]: FlavioSanchez E N,Xia Y,et al.Real-
time neural inverse optimal control for indoor air temperature and humidity
in a direct expansion(DX)air conditioning(A/C)system[J].International Journal
Of Refrigeration, 2017,79.] control algolithm neural network based is applied to greenhouse temperature to control and vapour
Vehicle manufacturing field has reached good control effect.However for dye liquor during dye gigging under textile industry high temperature and high pressure environment
The neural network control technique of temperature parameter need to be furtherd investigate.
Summary of the invention
The technical issues of not being able to satisfy production requirement for the control precision of existing control method, the present invention is based on BP mind
Network structure is improved on the basis of dye jigger temperature control technology through network, uses improved radial basis function neural network
(Radical Basis Function, RBF) replaces BP network, proposes a kind of high based on the high temperature for improving RBF neural
Press dye jigger temprature control method.By temperature control deviation value, empirically threshold value divides the present invention, combines and improves RBF
Two kinds of algorithms of neural network and Kind of Integration Separation PID Controller's carry out Discrete controls, improved RBF neural in learning ability and
BP neural network is superior on learning rate, and improved RBF neural has very linear and nonlinear change curve
Good Approximation effect, so that the technology can realize the efficient of dye liquor temperature during to dye gigging while taking into account computation complexity
Rate high-precision control.
In order to achieve the above object, the technical scheme of the present invention is realized as follows:
A kind of barotor temprature control method based on improvement RBF neural, its step are as follows:
S1: dye liquor temperature change curve model is established；
According to energy superposition principle, dye liquor heat exchange process is analyzed, and considers the factors such as heat is wandering and convection current radiates
Influence, establish dye liquor temperature change curve model；
S2: temperature control deviation and given threshold are calculated；
S2.1: according in the actual measured value of dye liquor temperature and the dye liquor temperature change curve model of corresponding sampling instant
Dye liquor temperature calculates temperature control deviation | e (n) |；
S2.2: according to specific application environment and dyeing experience, given threshold ε1And ε2, and ε1< ε2；
S3: according to temperature control deviation | e (n) | size to practical dye liquor temperature carry out Discrete control；
By temperature control deviation | e (n) | with threshold epsilon1And ε2It is compared, when | e (n) | > ε2, using PD control device to dye
Liquid temperature is controlled；Work as ε1< | e (n) |≤ε2, dye liquor temperature is controlled using PID controller；As 0 < | e (n) |≤
ε1, dye liquor temperature is controlled using based on the PID controller for improving RBF neural；
S4: PD control device, PID controller or the PID controller based on improvement RBF neural obtained according to step S3
Dye liquor temperature control output valve and practical dye liquor temperature calculate temperature control deviation, update temperature control deviation | e (n) |, follow
Ring step S3-S4, until | e (n) |=0.
Preferably, in step sl, further include first preset temperature controlling curve, establish dye liquor further according to temperature control curve
Temperature variation curve model；The temperature control curve include at least one warming-up section, at least one temperature descending section and at least one
Soaking zone.
Preferably, in step sl, the dye liquor temperature change curve model are as follows:
In formula, u indicates that the steam flow rate in dye vat, T indicate that dye liquor temperature, t indicate the time；
Solution formula (1):
In formula, C1Indicate dye liquor initial temperature.
Preferably, in step s3, the calculation formula of the PD control device are as follows:
In formula, kP,kDRespectively indicate scale parameter and differential parameter, TsIndicate the sampling interval of training sample, e (n) is indicated
Training sample controls difference in the temperature of n-th of sampling instant, and e (n-1) indicates training sample in the temperature of (n-1)th sampling instant
Degree control difference, u (n) indicate that the dye liquor temperature of n-th of sampling instant PD control device controls output valve.
Preferably, in step s3, the calculation formula of the PID controller are as follows:
In formula, TsIndicate the sampling interval of training sample, kP,kI,kDIndicate the feedback control loop using PID controller
Control parameter, e (n) indicate training sample n-th of sampling instant temperature control difference, e (n-1) indicate training sample exist
The temperature of (n-1)th sampling instant controls difference, and u (n) indicates that the dye liquor temperature control of n-th of sampling instant PID controller is defeated
It is worth out, e (m) indicates that training sample controls difference, m=1 in the temperature of m-th of sampling instant, and 2 ... n, n indicate sampling instant
Number.
Preferably, in step s3, the rate-determining steps based on the PID controller for improving RBF neural are as follows:
S3.1: according to the control parameter for improving RBF neural calculating PID controller；
S3.1.1: way of realization of the Gaussian function as radial basis function, the output of hidden layer are selectedCalculation formula are as follows:
In formula, i=1,2 ... M, M indicate the number of hidden layer neuron, j=1, and 2 ... N, N indicate the training of input layer
Sample number, ci(n) i-th of neuron of hidden layer center selected by the n-th moment, e are indicatedj(n) j-th of training sample is indicated
Difference, d are controlled in the temperature of n-th of sampling instantmMaximum distance between expression center；
Wherein, maximum distance dmIt is related to number M and variances sigma, the calculation formula of variances sigma are as follows:
S3.1.2: minimum is reached as training objective using objective optimization function ξ (n), realizes network using gradient descent method
The network of training, corresponding output layer exports yk(n) calculation formula are as follows:
In formula, wi(n) weight of expression i-th of the neuron of hidden layer in n-th of moment hidden layer to output layer, k=1,
The neuron number of 2 ..., L, L expression output layer；
S3.1.3: network parameter values are calculated using gradient descent method, i-th of neuron of hidden layer is from hidden layer to output layer
Weight wi(n) calculation formula are as follows:
In formula,Indicate the Gaussian function of i-th of neuron of hidden layer；
The more new formula of formula (10) are as follows:
In formula, η indicates that pace of learning, α indicate factor of momentum, wi(n+1) indicate i-th of neuron of hidden layer (n+1)th
Weight of a moment hidden layer to output layer, wi(n-1) indicate that i-th of neuron of hidden layer is arrived in (n-1)th moment hidden layer
The weight of output layer；
S3.1.4: the central value c of radial basis function is calculatedi(n), calculation formula are as follows:
In formula, σi(n) indicate i-th of neuron of hidden layer in the Gaussian function variance yields at n-th of moment；
The more new formula of formula (12) are as follows:
In formula, ci(n+1) i-th of neuron of hidden layer center selected by the (n+1)th moment, c are indicatedi(n-1) indicate hidden
Hide i-th of neuron of layer center selected by the (n-1)th moment；
S3.1.5: Gaussian function variance yields σ is calculatedi(n), calculation formula are as follows:
The more new formula of formula (14) are as follows:
In formula, σi(n+1) Gaussian function variance yields of i-th of the neuron of hidden layer (n+1)th moment, σ are indicatedi(n-1)
Indicate i-th of neuron of hidden layer in the Gaussian function variance yields at (n-1)th moment；
S3.1.6: according to objective optimization function ξ (n), central value ci(n), variance yields σi(n) and weight wi(n), net is calculated
Network output are as follows:
In formula, KP,KI,KDFor using based on the pid control parameter for improving RBF neural generation；
S3.2: the pid control parameter generated according to RBF neural adjusts dye liquor temperature using PID controller.
Preferably, in step S3.2, the PID controller adjusts the calculation formula of dye liquor temperature are as follows:
In formula, TsIndicate the sampling interval of training sample, KP,KI,KDIndicate the PID generated using RBF neural is improved
Control parameter, e (n) indicate that training sample controls difference in the temperature of n-th of sampling instant, and e (n-1) indicates training sample the
The temperature of n-1 sampling instant controls difference, and u (n) indicates that n-th of sampling instant is based on RBF neural and uses PID control
The dye liquor temperature control output valve of device, temperature control difference of e (m) the expression training sample in m-th of sampling instant, m=1,
The number of 2 ... n, n expression sampling instant.
Preferably, the calculation formula of the objective optimization function ξ (n) are as follows:
In formula, j=1,2 ... N, N indicate the number of training of input layer, ej(n) indicate j-th of training sample at n-th
The temperature at moment controls difference.
Preferably, in step s3, described using PD control device, PID controller and based on improvement RBF neural
The calculation formula of dye liquor temperature control output valve u (n) of PID controller are as follows:
In formula, kP,kI,kDIndicate the control parameter using pid feedback control loop, TsBetween the sampling for indicating training sample
Every e (n) indicates that training sample controls difference in the temperature of n-th of sampling instant, and e (n-1) indicates training sample at (n-1)th
The temperature of sampling instant controls difference, and u (n) indicates that the dye liquor temperature of n-th of sampling instant controller controls output valve, KP,KI,
KDIndicate that the pid control parameter generated using improved RBF neural, e (m) indicate training sample in m-th of sampling instant
Temperature control difference, m=1,2 ... n, n indicate sampling instant number.
Beneficial effects of the present invention:
The present invention relates to the dye liquor temperature control methods in barotor, using based on improved RBF nerve net
The feature learning method and pid control algorithm of network are realized adaptive under severe application environment to dye jigger temperature control system
Control and adjustment；The present invention is by establishing temperature control curve to different fabrics, according to the foundation pair of dye liquor temperature changing rule
The dye liquor temperature change curve model answered collects the weight system that a large amount of priori datas realize each interlayer of improved RBF neural
Several pre-corrected obtains being cut in real time for the network model under different application scene according to dye gigging material and concrete application scene
Switching network model has effectively achieved the high-precision control under high temperature and high pressure environment during entire dye gigging to dye liquor temperature variation,
And the theory of Discrete control and simulation modelling is used, it not only ensure that the high-precision and high efficiency of control process, but also control
The adjustment period is short, and control efficiency is high, and in addition the present invention is applicable not only to the control to constant parameter, the acceleration and deceleration to parameter variation
Process also may be implemented to be accurately controlled.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is workflow schematic diagram of the invention.
Fig. 2 is Ameliorative RBF Neural Networks structure chart of the invention.
Fig. 3 is the control algolithm response curve comparison diagram of the invention based on different neural networks.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under that premise of not paying creative labor
Embodiment shall fall within the protection scope of the present invention.
A kind of barotor temprature control method based on improvement RBF neural, as shown in Figure 1, its step
It is as follows:
S1: dye liquor temperature change curve model is established.
S1.1: preset temperature controlling curve, and temperature control curve is segmented according to fabric type, temperature control is bent
It include at least one warming-up section, at least one soaking zone and at least one temperature descending section in line, and every section of time span and temperature become
Change speed to be not quite similar.
S1.2: according to energy superposition principle, analyzing dye liquor heat exchange process, and considers heat is wandering and convection current radiates etc.
The influence of factor calculates dye liquor temperature, the calculation formula of dye liquor temperature T are as follows:
In formula, u indicates that steam flow rate in cylinder, T indicate that dye liquor temperature, t indicate the time；
(1) formula of solution obtains:
In formula, C1Indicate dye liquor initial temperature, in the present embodiment, C1≈200887069.2857；
The steam flow rate and in the case where dye liquor initial temperature in known cylinder, can acquire corresponding dye liquor temperature, in conjunction with pre-
If temperature control curve establishes dye liquor temperature change curve model.
S1.3: dye liquor temperature change curve model is established in conjunction with preset temperature controlling curve.
S2: temperature control deviation is calculated | e (n) | and given threshold.
S2.1: temperature control deviation | e (n) | calculation formula are as follows:
| e (n) |=| r (n)-T |； (3)
In formula, r (n) indicates the actual measured value of the dye liquor temperature of n-th of sampling instant, and T indicates that dye liquor temperature variation is bent
In line model with the dye liquor temperature value of the same sampling instant of the r (n).
S2.2: according to specific application environment and previous dyeing experience, given threshold ε1And ε2, and ε1< ε2。
S3: in conjunction with dye liquor temperature change curve model, and respectively for warming-up section, soaking zone and temperature descending section according to temperature control
Deviation processed | e (n) | size to practical dye liquor temperature r (n) carry out Discrete control.
S3.1: by temperature control deviation | e (n) | with threshold epsilon1And ε2It is compared；When temperature control deviation | e (n) | >
ε2, execute step S4 and dye liquor temperature controlled using PD control device, to ensure to control speed；As temperature control deviation ε1< |
e(n)|≤ε2, execute step S5 and dye liquor temperature controlled using PID controller, to adjust control precision；When temperature controls
0 < of deviation | e (n) |≤ε1, execute step S6 and the PID controller based on improvement RBF neural used to carry out dye liquor temperature
Fine tuning, to further increase control precision.
S3.2: it is obtained according to using PD control device, PID controller or based on the PID controller for improving RBF neural
Dye liquor temperature controls output valve u (n) and practical dye liquor temperature r (n) calculates temperature control deviation | e (n) |=| r (n)-u (n) |,
Update temperature control deviation | e (n) |, circulation execute step S3.1, until | e (n) |=0, at this time practical dye liquor temperature r (n) and
The dye liquor temperature that sampling instant is corresponded in dye liquor temperature change curve model is consistent.
S4: dye liquor temperature is controlled using PD control device；
It executes PD control device and adjusts dye liquor temperature, input as e (n), the calculation formula of PD control device are as follows:
In formula, kP,kDRespectively indicate scale parameter and differential parameter, TsIndicate the sampling time section of training sample, e (n) table
Show that training sample controls difference in the temperature of n-th of sampling instant, e (n-1) indicates training sample in (n-1)th sampling instant
Temperature controls difference, and u (n) indicates that the dye liquor temperature of n-th of sampling instant PD control device controls output valve.
S5: coarse adjustment is carried out to dye liquor temperature using PID controller；
It executes PID controller and adjusts dye liquor temperature, input as e (n), the calculation formula of PID controller are as follows:
In formula, TsIndicate the sampling interval of training sample, e (n) indicates training sample in the temperature control of n-th of sampling instant
Difference processed, e (n-1) indicate that training sample controls difference, m=1 in the temperature of (n-1)th sampling instant, and 2 ... n, n indicate sampling
The number at moment, u (n) indicate that the dye liquor temperature of n-th of sampling instant PID controller controls output valve, and e (m) indicates training sample
This controls difference, k in the temperature of m-th of sampling instantP,kI,kDIndicate the control of the feedback control loop using PID controller
Parameter, these three control parameters are, as fixed values preset according to priori.
S6: the control parameter of PID controller is calculated based on RBF neural is improved, and combines PID controller to dye liquor temperature
Degree carries out fine tuning；
S6.1: based on the control parameter for improving RBF neural calculating PID controller；
As shown in Fig. 2, the RBF neural includes input layer, hidden layer and output layer, the input of input layer is e
(n), the output of hidden layer isThe output of output layer is yk(n)；
In formula, ci(n) central point selected by i-th of neuron of hidden layer, e are indicatedj(n) indicate that j-th of training sample exists
The temperature at n-th of moment controls difference；
S6.1.1 selects way of realization of the Gaussian function as radial basis function, the output of hidden layerCalculation formula are as follows:
In formula, i=1,2 ... M, M indicate the number of hidden layer neuron, j=1, and 2 ... N, N indicate the training of input layer
Sample number, dmMaximum distance between expression center；
Wherein, maximum distance dmIt is related with variances sigma to number M, the calculation formula of variances sigma are as follows:
S6.1.2 reaches minimum as training objective using objective optimization function, and realizes that network is instructed using gradient descent method
Practice, the network of corresponding output layer exports yk(n) calculation formula are as follows:
In formula, k=1,2 ..., L, L indicate the neuron number of output layer, wi(n) indicate i-th of neuron of hidden layer from
Weight of the hidden layer to output layer；
S6.1.3 selection target majorized function, the calculation formula of objective optimization function ξ (n) are as follows:
S6.1.4 calculates network parameter values using gradient descent method, and i-th of neuron of hidden layer is from hidden layer to output layer
Weight wi(n) calculation formula are as follows:
In formula,Indicate the Gaussian function of i-th of neuron of hidden layer；
The more new formula of formula (10) are as follows:
In formula, η indicates that pace of learning, α indicate factor of momentum, wi(n+1) indicate i-th of neuron of hidden layer (n+1)th
Weight of the hidden layer at a moment to output layer, wi(n-1) i-th of neuron of hidden layer hiding (n-1)th moment is indicated
Layer arrives the weight of output layer；
The central value c of S6.1.5 calculating radial basis functioni(n), calculation formula are as follows:
In formula, σi(n) indicate i-th of neuron of hidden layer in the Gaussian function variance yields at n-th of moment；
The more new formula of formula (12) are as follows:
In formula, ci(n+1) i-th of neuron of hidden layer central point selected by (n+1)th moment, c are indicatedi(n-1) table
Show i-th of neuron of hidden layer central point selected by (n-1)th moment；
The variance yields σ of S6.1.6 calculating Gaussian functioni(n), calculation formula are as follows:
The more new formula of formula (14) are as follows:
In formula, σi(n+1) Gaussian function variance yields of i-th of the neuron of hidden layer (n+1)th moment, σ are indicatedi(n-1)
Indicate i-th of neuron of hidden layer in the Gaussian function variance yields at (n-1)th moment；
S6.1.7 is according to objective optimization function ξ (n), central value ci(n), variance yields σi(n) and weight wi(n), network is obtained
Output are as follows:
KP,KI,KDIt indicates using based on the control parameter for improving the PID controller that RBF neural generates；
S6.2: according to the control parameter for improving the PID controller that RBF neural generates, using PID controller to dye liquor
Temperature is adjusted, the calculation formula of PID controller are as follows:
In formula, TsIndicate the sampling interval of training sample, m=1,2 ... n, n indicate the number of sampling instant, and e (n) is indicated
Training sample controls difference in the temperature of n-th of sampling instant, and e (n-1) indicates training sample in the temperature of (n-1)th sampling instant
Degree control difference, u (n) indicate that the dye liquor temperature of n-th of sampling instant PID controller controls output valve, and e (m) indicates training sample
This controls difference, K in the temperature of m-th of sampling instantP,KI,KDIndicate the control of the feedback control loop using PID controller
Parameter, these three control parameters are, as fixed values preset according to priori.
As shown in figure 3, the present invention is superior to other neural network structures in learning ability and learning rate, and improved
RBF network has good Approximation effect for linear and nonlinear change curve, so that the technology is taking into account computation complexity
While can realize to during dye gigging dye liquor temperature high-efficiency high-precision control.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of based on the barotor temprature control method for improving RBF neural, which is characterized in that its step is such as
Under:
S1: dye liquor temperature change curve model is established；
According to energy superposition principle, dye liquor temperature change curve model is established；
S2: temperature control deviation and given threshold are calculated；
S2.1: according to the dye liquor in the actual measured value of dye liquor temperature and the dye liquor temperature change curve model of corresponding sampling instant
Temperature computation temperature control deviation | e (n) |；
S2.2: given threshold ε1And ε2, and ε1< ε2；
S3: according to temperature control deviation | e (n) | size to practical dye liquor temperature carry out Discrete control；
By temperature control deviation | e (n) | with threshold epsilon1And ε2It is compared, when | e (n) | > ε2, using PD control device to dye liquor temperature
Degree is controlled；Work as ε1< | e (n) |≤ε2, dye liquor temperature is controlled using PID controller；As 0 < | e (n) |≤ε1, adopt
Dye liquor temperature is controlled with based on the PID controller for improving RBF neural；
S4: PD control device, PID controller or the dye based on the PID controller for improving RBF neural obtained according to step S3
Liquid temperature controls output valve and practical dye liquor temperature calculates temperature control deviation, updates temperature control deviation | e (n) |, circulation step
Rapid S3-S4, until | e (n) |=0.
2. it is according to claim 1 based on the barotor temprature control method for improving RBF neural, it is special
Sign is, further includes first preset temperature controlling curve in step sl, establishes dye liquor temperature variation further according to temperature control curve
Curve model；The temperature control curve includes at least one warming-up section, at least one temperature descending section and at least one soaking zone.
3. the barotor temprature control method according to claim 1 or 2 based on improvement RBF neural,
It is characterized in that, in step sl, the dye liquor temperature change curve model are as follows:
In formula, u indicates that the steam flow rate in dye vat, T indicate that dye liquor temperature, t indicate the time；
Solution formula (1):
In formula, C1Indicate dye liquor initial temperature.
4. it is according to claim 1 based on the barotor temprature control method for improving RBF neural, it is special
Sign is, in step s3, the calculation formula of the PD control device are as follows:
In formula, kP,kDRespectively indicate scale parameter and differential parameter, TsIndicate the sampling interval of training sample, e (n) indicates training
Sample controls difference in the temperature of n-th of sampling instant, and e (n-1) indicates training sample in the temperature control of (n-1)th sampling instant
Difference processed, u (n) indicate that the dye liquor temperature of n-th of sampling instant PD control device controls output valve.
5. it is according to claim 1 based on the barotor temprature control method for improving RBF neural, it is special
Sign is, in step s3, the calculation formula of the PID controller are as follows:
In formula, TsIndicate the sampling interval of training sample, kP,kI,kDIndicate the control of the feedback control loop using PID controller
Parameter, e (n) indicate that training sample controls difference in the temperature of n-th of sampling instant, and e (n-1) indicates training sample (n-1)th
The temperature of a sampling instant controls difference, and u (n) indicates that the dye liquor temperature of n-th of sampling instant PID controller controls output valve, e
(m) indicate that training sample controls difference, m=1 in the temperature of m-th of sampling instant, 2 ... n, n indicate the number of sampling instant.
6. it is according to claim 1 based on the barotor temprature control method for improving RBF neural, it is special
Sign is that in step s3, the rate-determining steps based on the PID controller for improving RBF neural are as follows:
S3.1: according to the control parameter for improving RBF neural calculating PID controller；
S3.1.1: way of realization of the Gaussian function as radial basis function, the output of hidden layer are selected's
Calculation formula are as follows:
In formula, i=1,2 ... M, M indicate the number of hidden layer neuron, j=1, and 2 ... N, N indicate the training sample of input layer
Number, ci(n) i-th of neuron of hidden layer center selected by the n-th moment, e are indicatedj(n) indicate j-th of training sample n-th
The temperature of a sampling instant controls difference, dmMaximum distance between expression center；
Wherein, maximum distance dmIt is related to number M and variances sigma, the calculation formula of variances sigma are as follows:
S3.1.2: reaching minimum as training objective using objective optimization function ξ (n), realize network training using gradient descent method,
The network of corresponding output layer exports yk(n) calculation formula are as follows:
In formula, wi(n) weight of expression i-th of the neuron of hidden layer in n-th of moment hidden layer to output layer, k=1,2 ...,
The neuron number of L, L expression output layer；
S3.1.3: network parameter values, power of i-th of the neuron of hidden layer from hidden layer to output layer are calculated using gradient descent method
Weight wi(n) calculation formula are as follows:
In formula,Indicate the Gaussian function of i-th of neuron of hidden layer；
The more new formula of formula (10) are as follows:
In formula, η indicates that pace of learning, α indicate factor of momentum, wi(n+1) indicate i-th of neuron of hidden layer (n+1)th moment
Weight of the hidden layer to output layer, wi(n-1) indicate i-th of neuron of hidden layer in (n-1)th moment hidden layer to output layer
Weight；
S3.1.4: the central value c of radial basis function is calculatedi(n), calculation formula are as follows:
In formula, σi(n) indicate i-th of neuron of hidden layer in the Gaussian function variance yields at n-th of moment；
The more new formula of formula (12) are as follows:
In formula, ci(n+1) i-th of neuron of hidden layer center selected by the (n+1)th moment, c are indicatedi(n-1) hidden layer is indicated
I-th of neuron center selected by the (n-1)th moment；
S3.1.5: Gaussian function variance yields σ is calculatedi(n), calculation formula are as follows:
The more new formula of formula (14) are as follows:
In formula, σi(n+1) Gaussian function variance yields of i-th of the neuron of hidden layer (n+1)th moment, σ are indicatedi(n-1) it indicates
Gaussian function variance yields of i-th of the neuron of hidden layer (n-1)th moment；
S3.1.6: according to objective optimization function ξ (n), central value ci(n), variance yields σi(n) and weight wi(n), it is defeated to calculate network
Out are as follows:
In formula, KP,KI,KDFor using based on the pid control parameter for improving RBF neural generation；
S3.2: the pid control parameter generated according to RBF neural adjusts dye liquor temperature using PID controller.
7. it is according to claim 6 based on the barotor temprature control method for improving RBF neural, it is special
Sign is, in step S3.2, the PID controller adjusts the calculation formula of dye liquor temperature are as follows:
In formula, TsIndicate the sampling interval of training sample, KP,KI,KDIndicate the PID control generated using RBF neural is improved
Parameter, e (n) indicate that training sample controls difference in the temperature of n-th of sampling instant, and e (n-1) indicates training sample (n-1)th
The temperature of a sampling instant controls difference, m=1, and 2 ... n, n indicate the number of sampling instant, and u (n) indicates n-th of sampling instant
Output valve is controlled based on RBF neural and using the dye liquor temperature of PID controller, e (m) indicates that training sample is adopted at m-th
The temperature at sample moment controls difference.
8. it is according to claim 6 based on the barotor temprature control method for improving RBF neural, it is special
Sign is, the calculation formula of the objective optimization function ξ (n) are as follows:
In formula, j=1,2 ... N, N indicate the number of training of input layer, ej(n) indicate j-th of training sample n-th of moment
Temperature control difference.
9. based on the barotor temperature for improving RBF neural according to claim 1 or described in any one of 4-8
Spend control method, which is characterized in that in step s3, described using PD control device, PID controller and based on improvement RBF nerve
The calculation formula of dye liquor temperature control output valve u (n) of the PID controller of network are as follows:
In formula, kP,kI,kDIndicate the control parameter using pid feedback control loop, TsIndicate the sampling interval of training sample, e
(n) indicate that training sample controls difference in the temperature of n-th of sampling instant, e (n-1) indicates that training sample is sampled at (n-1)th
The temperature at moment controls difference, and u (n) indicates that the dye liquor temperature of n-th of sampling instant controller controls output valve, KP,KI,KDTable
Show that the pid control parameter generated using improved RBF neural, e (m) indicate training sample in the temperature of m-th of sampling instant
Degree control difference, m=1,2 ... n, n indicate the number of sampling instant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910696867.8A CN110262582B (en) | 2019-07-30 | 2019-07-30 | High-temperature high-pressure jig dyeing machine temperature control method based on improved RBF neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910696867.8A CN110262582B (en) | 2019-07-30 | 2019-07-30 | High-temperature high-pressure jig dyeing machine temperature control method based on improved RBF neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110262582A true CN110262582A (en) | 2019-09-20 |
| CN110262582B CN110262582B (en) | 2020-09-11 |
Family
ID=67912394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910696867.8A Active CN110262582B (en) | 2019-07-30 | 2019-07-30 | High-temperature high-pressure jig dyeing machine temperature control method based on improved RBF neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110262582B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111719322A (en) * | 2020-07-16 | 2020-09-29 | 浙江流庆纺织有限公司 | One-bath dyeing method of polyester-nylon and cationic polyester-nylon composite fiber terry knitted fabric |
| CN111850892A (en) * | 2020-07-10 | 2020-10-30 | 绍兴数智科技有限公司 | Method and device for realizing abnormal alarm in dyeing process of overflow dyeing machine |
| CN112363556A (en) * | 2020-11-10 | 2021-02-12 | 贵州华亿绿色纺织产业科技有限公司 | Temperature and smoke humidity control system |
| CN112553817A (en) * | 2020-12-11 | 2021-03-26 | 河南省纺织产品质量监督检验院 | Method and system for real-time control and adjustment of textile dyeing process based on artificial intelligence |
| CN112680918A (en) * | 2020-12-30 | 2021-04-20 | 江苏华一机械有限公司 | Sanding treatment method and system based on combined carbon fiber sanding machine |
| CN114137823A (en) * | 2021-11-10 | 2022-03-04 | 中国科学院上海技术物理研究所 | PID parameter setting method for multi-stage temperature control of low-temperature region of mechanical refrigerator |
| CN114870761A (en) * | 2022-04-28 | 2022-08-09 | 中国计量大学 | Intelligent safety temperature control method applied to calorimetric reaction kettle |
| CN115328232A (en) * | 2022-09-01 | 2022-11-11 | 厦门宇昊软件有限公司 | Temperature control method and system |
| CN116219665A (en) * | 2023-02-09 | 2023-06-06 | 青岛富润达纺织有限公司 | Dye liquor process temperature following control method based on temperature speed adjustment |
| CN116643497A (en) * | 2023-05-29 | 2023-08-25 | 浙江荣鑫纤维股份有限公司 | Dyeing control system and method for cheese |
| CN117873221A (en) * | 2024-03-12 | 2024-04-12 | 广州中科医疗美容仪器有限公司 | Temperature monitoring control method and system for moxibustion therapy bin |
Citations (6)
| 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 |
| CN102914623A (en) * | 2012-10-19 | 2013-02-06 | 南京信息工程大学 | Fusing method of temperature compensation of humidity sensor |
| CN103611734A (en) * | 2013-11-25 | 2014-03-05 | 华中科技大学 | Laminar cooling temperature control method and system |
| CN108719516A (en) * | 2018-05-22 | 2018-11-02 | 湖南师范大学 | One kind being based on RBF neural tea machine processing control parameter intelligence setting method |
| CN108958020A (en) * | 2018-05-29 | 2018-12-07 | 南京理工大学 | A kind of temprature control method based on RBF neural dynamic prediction PID |
| CN109597449A (en) * | 2019-01-30 | 2019-04-09 | 杭州庆睿科技有限公司 | A kind of ultrasonic wave separating apparatus temprature control method neural network based |
-
2019
- 2019-07-30 CN CN201910696867.8A patent/CN110262582B/en active Active
Patent Citations (6)
| 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 |
| CN102914623A (en) * | 2012-10-19 | 2013-02-06 | 南京信息工程大学 | Fusing method of temperature compensation of humidity sensor |
| CN103611734A (en) * | 2013-11-25 | 2014-03-05 | 华中科技大学 | Laminar cooling temperature control method and system |
| CN108719516A (en) * | 2018-05-22 | 2018-11-02 | 湖南师范大学 | One kind being based on RBF neural tea machine processing control parameter intelligence setting method |
| CN108958020A (en) * | 2018-05-29 | 2018-12-07 | 南京理工大学 | A kind of temprature control method based on RBF neural dynamic prediction PID |
| CN109597449A (en) * | 2019-01-30 | 2019-04-09 | 杭州庆睿科技有限公司 | A kind of ultrasonic wave separating apparatus temprature control method neural network based |
Non-Patent Citations (2)
| Title |
|---|
| 魏苗苗，刘洲峰: ""基于BP神经网络的卷染机温度控制技术"", 《毛纺科技》 * |
| 魏苗苗，刘洲峰: ""基于神经网络的卷染机控制系统设计"", 《中原工学院学报》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111850892B (en) * | 2020-07-10 | 2023-08-11 | 绍兴数智科技有限公司 | Method and device for realizing abnormal alarm in dyeing process of overflow dyeing machine |
| CN111850892A (en) * | 2020-07-10 | 2020-10-30 | 绍兴数智科技有限公司 | Method and device for realizing abnormal alarm in dyeing process of overflow dyeing machine |
| CN111719322A (en) * | 2020-07-16 | 2020-09-29 | 浙江流庆纺织有限公司 | One-bath dyeing method of polyester-nylon and cationic polyester-nylon composite fiber terry knitted fabric |
| CN112363556A (en) * | 2020-11-10 | 2021-02-12 | 贵州华亿绿色纺织产业科技有限公司 | Temperature and smoke humidity control system |
| CN112553817A (en) * | 2020-12-11 | 2021-03-26 | 河南省纺织产品质量监督检验院 | Method and system for real-time control and adjustment of textile dyeing process based on artificial intelligence |
| CN112553817B (en) * | 2020-12-11 | 2022-11-15 | 河南省纺织产品质量监督检验院 | Method and system for real-time control and adjustment of textile dyeing process based on artificial intelligence |
| CN112680918A (en) * | 2020-12-30 | 2021-04-20 | 江苏华一机械有限公司 | Sanding treatment method and system based on combined carbon fiber sanding machine |
| CN114137823A (en) * | 2021-11-10 | 2022-03-04 | 中国科学院上海技术物理研究所 | PID parameter setting method for multi-stage temperature control of low-temperature region of mechanical refrigerator |
| CN114137823B (en) * | 2021-11-10 | 2023-12-26 | 中国科学院上海技术物理研究所 | PID parameter setting method for multi-stage temperature control in low-temperature area of mechanical refrigerator |
| CN114870761A (en) * | 2022-04-28 | 2022-08-09 | 中国计量大学 | Intelligent safety temperature control method applied to calorimetric reaction kettle |
| CN115328232A (en) * | 2022-09-01 | 2022-11-11 | 厦门宇昊软件有限公司 | Temperature control method and system |
| CN115328232B (en) * | 2022-09-01 | 2023-12-19 | 厦门宇昊软件有限公司 | Temperature control method and system |
| CN116219665A (en) * | 2023-02-09 | 2023-06-06 | 青岛富润达纺织有限公司 | Dye liquor process temperature following control method based on temperature speed adjustment |
| CN116643497A (en) * | 2023-05-29 | 2023-08-25 | 浙江荣鑫纤维股份有限公司 | Dyeing control system and method for cheese |
| CN116643497B (en) * | 2023-05-29 | 2024-05-10 | 汕头市鼎泰丰实业有限公司 | Dyeing control system and method for cheese |
| CN117873221A (en) * | 2024-03-12 | 2024-04-12 | 广州中科医疗美容仪器有限公司 | Temperature monitoring control method and system for moxibustion therapy bin |
| CN117873221B (en) * | 2024-03-12 | 2024-05-28 | 广州中科医疗美容仪器有限公司 | Temperature monitoring control method and system for moxibustion therapy bin |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110262582B (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262582A (en) | A kind of barotor temprature control method based on improvement RBF neural | |
| US5159660A (en) | Universal process control using artificial neural networks | |
| CN110187727A (en) | A kind of Glass Furnace Temperature control method based on deep learning and intensified learning | |
| CN107608209A (en) | The feedforward of piezoelectric ceramic actuator and closed loop composite control method, system | |
| Selamat et al. | Comparison of LQR and PID controller tuning using PSO for Coupled Tank System | |
| CN100349076C (en) | Control method of evaporation rate in Chinese medicine production concentration process | |
| CN105955026A (en) | Fuzzy PID control method, device and system | |
| CN110703718A (en) | Industrial process control method based on signal compensation | |
| CN113253779A (en) | Heat pump temperature control system based on particle swarm fuzzy PID algorithm | |
| Prusty et al. | A novel fuzzy based adaptive control of the four tank system | |
| CN105652666B (en) | Large-scale drop press upper beam prediction of speed control method based on BP neural network | |
| Xu et al. | Design of the PID controller for industrial processes based on the stability margin | |
| Pillay | A particle swarm optimization approach for tuning of SISO PID control loops | |
| Manikandan et al. | Real-time implementation and performance analysis of an intelligent fuzzy logic controller for level process | |
| Sowmya et al. | A fuzzy control scheme for nonlinear process | |
| CN109597300B (en) | Electromagnetic switch full-life-cycle self-adaptive control method based on closed-loop RBR technology | |
| Zhuang et al. | The internal mode fractional-order PID control based on neural network for the temperature of air-conditioned rooms | |
| CN112255912A (en) | Polymerization kettle product concentration control method of model-free adaptive PID control strategy | |
| Üstüner et al. | INVERTED DECOUPLING PID CONTROLLER DESIGN FOR A MIMO SYSTEM | |
| CN102495651A (en) | Nonovershooting industry resistance furnace temperature control method | |
| CN106610588B (en) | A kind of tandem Predictive Control System and method | |
| Ekren et al. | Operation of compressor and electronic expansion valve via different controllers | |
| CN118192204A (en) | Temperature and humidity self-adaptive PID control system and method for textile printing and dyeing equipment | |
| Silva et al. | Implementation and tuning of a FUZZY-PID control system via fieldbus communication | |
| El Aoud et al. | Self-tuning method of fuzzy system: An application on greenhouse process |
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 |