CN111053288A - Novel tobacco flow control system based on BP neural network - Google Patents
Novel tobacco flow control system based on BP neural network Download PDFInfo
- Publication number
- CN111053288A CN111053288A CN201910532531.8A CN201910532531A CN111053288A CN 111053288 A CN111053288 A CN 111053288A CN 201910532531 A CN201910532531 A CN 201910532531A CN 111053288 A CN111053288 A CN 111053288A
- Authority
- CN
- China
- Prior art keywords
- flow
- neural network
- scale
- system based
- control system
- 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
- 241000208125 Nicotiana Species 0.000 title claims abstract description 28
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 27
- 238000013499 data model Methods 0.000 claims abstract description 10
- 238000004519 manufacturing process Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000002156 mixing Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 9
- 230000004069 differentiation Effects 0.000 abstract description 3
- 230000010354 integration Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 239000000109 continuous material Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000013072 incoming material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24C—MACHINES FOR MAKING CIGARS OR CIGARETTES
- A24C5/00—Making cigarettes; Making tipping materials for, or attaching filters or mouthpieces to, cigars or cigarettes
Landscapes
- Manufacturing Of Cigar And Cigarette Tobacco (AREA)
Abstract
The invention discloses a novel tobacco flow control system based on a BP (back propagation) neural network, which belongs to the field of tobacco production, and is characterized in that a BP neural network algorithm is introduced into the novel tobacco flow control system based on the BP neural network, a flavoring flow data model is simulated by utilizing big data, the optimal set flow is found out, a PLC control program is re-optimized through matching of a metering tube and a frequency converter with PID (proportion integration differentiation) control, the gradient dynamic adjustment of the set flow can be realized according to supplied materials, and the novel tobacco flow control system based on the BP neural network and the PLC program is developed, so that the aim of stably controlling the material flow is fulfilled.
Description
Technical Field
The invention belongs to the field of tobacco production, and particularly relates to a novel tobacco flow control system based on a BP neural network.
Background
At present, the material flow of the tobacco industry is mainly measured and controlled by an electronic belt scale. The electronic scale is divided into two types, one type is metering type, and the other type is control type, and the metering type can realize continuous and automatic metering and display the instantaneous flow and the accumulated mass of continuous materials on a conveyor of the belt scale. The controllable electronic scale can not only realize continuous measurement of material flow, but also control material flow to realize the mixture ratio of more than two different materials, and the BWE series electronic belt scale manufactured by German HAUNI is mainly used in our factory at present.
The BWE series electronic belt weighers are divided into two types: a control type electronic belt scale (BWE-D) and a metering type electronic belt scale (BWE-R). The electronic belt weighers of the two models are both designed by the same machine. Whether the weighing electronic system uses proportion control or not will determine whether the electronic belt scale is used as a control type electronic belt scale or a metering type electronic belt scale.
The metering type electronic belt scale can only realize the metering of flow and accumulated mass, and the control type electronic scale has the double functions of control and metering, but the control type electronic belt scale has higher general cost than the metering type electronic belt scale, and is difficult to be generally used by general enterprises; and once a metering type Tina sub-belt scale is adopted, if a control function needs to be added in the later period, only a control type metering scale can be purchased newly, so that the waste of original equipment and the great increase of the equipment cost are caused. At present, a high-grade tobacco line perfuming process in a silk making workshop of our factory uses a BWE-R type metering electronic belt scale of Germany HAUNI company, and because the electronic scale cannot carry out flow control and does not have a buffer device before the perfuming process, the flow fluctuation of the perfuming process is large, the perfuming uniformity is influenced, and the hidden trouble of product quality is brought.
Disclosure of Invention
On the basis of the original electronic metering scale equipment structure and metering principle, hardware cost is not increased, a BP neural network algorithm is introduced, a flavoring flow data model is simulated by utilizing big data, the optimal set flow is found, a PLC control program is re-optimized by matching a metering tube and a frequency converter with PID (proportion integration differentiation) control, the gradient dynamic adjustment of the set flow can be realized according to incoming materials, and a novel tobacco flow control system based on the BP neural network and the PLC program is developed, so that the aim of stably controlling the material flow is fulfilled.
In order to achieve the purpose, the invention is realized by the following technical scheme: the novel tobacco flow control system based on the BP neural network is used for controlling the flow of tobacco by the following steps:
simulating a flavoring flow data model by using big data, and predicting the flow of the flavoring control scale;
step 3, selecting a historical production data training data model of the high-grade tobacco line;
and 4, calculating a set value of the perfuming control scale, and dynamically changing the set flow of the electronic scale.
Preferably, the specific implementation manner of step 1 is to perform PID adjustment on the process flow under the condition that the belt is not shut down by modifying a PLC program, so as to realize the flow control function of the metering scale, and dynamically adjust the set flow in a gradient manner.
Preferably, the specific implementation manner of the step 2 is to simulate a perfuming flow data model by using big data and predict the perfuming control scale flow by using a BP neural network algorithm; the flow data of the main and auxiliary blending scales (cut stems and air flow shreds) are used as input vectors, and the flow of the flavoring control scale is used as an output vector.
Preferably, the specific implementation manner of the step 3 is to select historical production data of high-grade tobacco lines to train a BP neural network.
Preferably, the specific implementation manner of step 4 is to calculate the set value of the perfuming control scale according to the real-time flow rates of the master scale and the slave blending scale, and dynamically change the set flow rate of the electronic scale.
The invention has the beneficial effects that:
on the basis of the original electronic metering scale equipment structure and metering principle, hardware cost is not increased, a BP neural network algorithm is introduced, a flavoring flow data model is simulated by utilizing big data, the best set flow is found out, the metering pipe and a frequency converter are matched with PID (proportion integration differentiation) for control, a PLC (programmable logic controller) control program is re-opened and optimized, the gradient dynamic adjustment of the set flow can be realized according to supplied materials, a novel tobacco flow control system based on the BP neural network and the PLC program is developed, the purpose of stable control of material flow is achieved, and meanwhile, the cost for newly purchasing corresponding equipment is saved.
Drawings
FIG. 1 is a BP neural network structure;
FIG. 2 is a schematic diagram of model fitting under a neural network;
fig. 3 is a graph of improved front and rear comparative effects.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the accompanying drawings and examples, which are not intended to limit the present invention.
The novel tobacco flow control system based on the BP neural network is used for controlling the flow of tobacco by the following steps:
the specific implementation mode of the step 1 is to carry out PID adjustment on the process flow under the condition of ensuring that the belt does not stop by modifying a PLC program, realize the flow control function of the metering scale and dynamically adjust the set flow in a gradient manner. The specific implementation mode of the step 2 is that a BP neural network algorithm is adopted, a flavoring flow data model is simulated by utilizing big data, and the flow of the flavoring control scale is predicted; the flow data of the main and auxiliary blending scales (cut stems and air flow shreds) are used as input vectors, and the flow of the flavoring control scale is used as an output vector. And 3, selecting historical production data of the high-grade tobacco line to train the BP neural network. After 56 training sessions, the training was stopped. At this point the training target reached 0.00014854, with a fitness R of 0.96615. (
And 4, calculating a set value of the perfuming control scale according to the real-time flow of the main scale and the auxiliary blending scale, and dynamically changing the set flow of the electronic scale.
The technical content of the present invention is further explained by the examples only, so as to facilitate the understanding of the reader. The general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not limited to the embodiments shown herein, and any technical extension or re-creation performed according to the present invention is protected by the present invention.
Claims (5)
1. A novel tobacco flow control system based on a BP neural network is characterized in that: the novel tobacco flow control system based on the BP neural network is used for controlling the flow of tobacco by the following steps:
step 1, carrying out PID adjustment on process flow to realize the flow control function of a metering scale;
simulating a flavoring flow data model by using big data, and predicting the flow of the flavoring control scale;
step 3, selecting a historical production data training data model of the high-grade tobacco line;
and 4, calculating a set value of the perfuming control scale, and dynamically changing the set flow of the electronic scale.
2. The novel tobacco flow control system based on the BP neural network as claimed in claim 1, wherein: the specific implementation mode of the step 1 is to perform PID adjustment on the process flow under the condition of ensuring that the belt does not stop by modifying a PLC program, realize the flow control function of the metering scale and dynamically adjust the set flow in a gradient manner.
3. The novel tobacco flow control system based on the BP neural network as claimed in claim 1, wherein: the specific implementation mode of the step 2 is to simulate a flavoring flow data model by using big data and predict the flow of the flavoring control scale by adopting a BP neural network algorithm; the flow data of the main and auxiliary blending scales (cut stems and air flow shreds) are used as input vectors, and the flow of the flavoring control scale is used as an output vector.
4. The novel tobacco flow control system based on the BP neural network as claimed in claim 1, wherein: the specific implementation manner of the step 3 is to select historical production data of the high-grade tobacco line to train a BP neural network.
5. The novel tobacco flow control system based on the BP neural network as claimed in claim 1, wherein: the specific implementation mode of the step 4 is to calculate the set value of the perfuming control scale according to the real-time flow of the main scale and the auxiliary blending scale, and dynamically change the set flow of the electronic scale.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910532531.8A CN111053288A (en) | 2019-06-19 | 2019-06-19 | Novel tobacco flow control system based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910532531.8A CN111053288A (en) | 2019-06-19 | 2019-06-19 | Novel tobacco flow control system based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111053288A true CN111053288A (en) | 2020-04-24 |
Family
ID=70297414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910532531.8A Pending CN111053288A (en) | 2019-06-19 | 2019-06-19 | Novel tobacco flow control system based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111053288A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114947163A (en) * | 2022-05-05 | 2022-08-30 | 河北白沙烟草有限责任公司保定卷烟厂 | Tobacco shred constant flow control method and device based on tobacco shred production line |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030097192A1 (en) * | 2001-11-20 | 2003-05-22 | Automation Control Technology, Inc. | System and method for tuning the weight control of a flow of material |
| CN103011356A (en) * | 2012-08-15 | 2013-04-03 | 重庆水务集团股份有限公司 | Method for controlling automatic chemical dosing of high-turbidity water system |
| CN103610227A (en) * | 2013-12-09 | 2014-03-05 | 中南大学 | Cut tobacco dryer head and tail section process variable optimizing control method |
| CN103876277A (en) * | 2014-04-11 | 2014-06-25 | 龙岩烟草工业有限责任公司 | Device and method for controlling material flow |
| WO2016068863A1 (en) * | 2014-10-28 | 2016-05-06 | Halliburton Energy Services, Inc. | Pneumatic conveying system and method using optical flow characterization data |
| CN105947600A (en) * | 2016-06-27 | 2016-09-21 | 云南昆船电子设备有限公司 | Constant flow system without cache device and control method |
| CN106579535A (en) * | 2017-01-23 | 2017-04-26 | 龙岩烟草工业有限责任公司 | Tobacco flavoring and feeding system, control method and tobacco shred production system |
| CN108523204A (en) * | 2017-03-03 | 2018-09-14 | 红塔烟草(集团)有限责任公司 | Improve the method and device of stem flavoring control accuracy |
| CN109315823A (en) * | 2018-08-30 | 2019-02-12 | 广东中烟工业有限责任公司 | A kind of automatic flow control method of leaf silk scale |
-
2019
- 2019-06-19 CN CN201910532531.8A patent/CN111053288A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030097192A1 (en) * | 2001-11-20 | 2003-05-22 | Automation Control Technology, Inc. | System and method for tuning the weight control of a flow of material |
| CN103011356A (en) * | 2012-08-15 | 2013-04-03 | 重庆水务集团股份有限公司 | Method for controlling automatic chemical dosing of high-turbidity water system |
| CN103610227A (en) * | 2013-12-09 | 2014-03-05 | 中南大学 | Cut tobacco dryer head and tail section process variable optimizing control method |
| CN103876277A (en) * | 2014-04-11 | 2014-06-25 | 龙岩烟草工业有限责任公司 | Device and method for controlling material flow |
| WO2016068863A1 (en) * | 2014-10-28 | 2016-05-06 | Halliburton Energy Services, Inc. | Pneumatic conveying system and method using optical flow characterization data |
| CN105947600A (en) * | 2016-06-27 | 2016-09-21 | 云南昆船电子设备有限公司 | Constant flow system without cache device and control method |
| CN106579535A (en) * | 2017-01-23 | 2017-04-26 | 龙岩烟草工业有限责任公司 | Tobacco flavoring and feeding system, control method and tobacco shred production system |
| CN108523204A (en) * | 2017-03-03 | 2018-09-14 | 红塔烟草(集团)有限责任公司 | Improve the method and device of stem flavoring control accuracy |
| CN109315823A (en) * | 2018-08-30 | 2019-02-12 | 广东中烟工业有限责任公司 | A kind of automatic flow control method of leaf silk scale |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114947163A (en) * | 2022-05-05 | 2022-08-30 | 河北白沙烟草有限责任公司保定卷烟厂 | Tobacco shred constant flow control method and device based on tobacco shred production line |
| CN114947163B (en) * | 2022-05-05 | 2022-12-27 | 河北白沙烟草有限责任公司保定卷烟厂 | Tobacco shred constant flow control method and device based on tobacco shred production line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105520183B (en) | A kind of method for improving loosening steam conditioner moisture content of outlet stability | |
| CN102754903B (en) | Method for flexibly and uniformly blending materials in storage cabinet | |
| CN103426035A (en) | Self-balanced byproduct blast furnace gas dispatching system in iron and steel industry and method for predicting yield and consumption | |
| CN109827073B (en) | Automatic distribution and transmission implementation method for natural gas pipeline | |
| CN111053288A (en) | Novel tobacco flow control system based on BP neural network | |
| CN208634792U (en) | A kind of steam pipe line stable-pressure device | |
| CN105214584B (en) | Keep the multiple target inter-linked controlling method and device of reactor level stability | |
| CN102221824A (en) | Bowl mill ore-feeding amount intelligent control apparatus | |
| CN105539932B (en) | A kind of method of adaptive correction weighing system error | |
| CN109090679A (en) | Novel tobacco charging automatic deviation rectification control system | |
| CN106094714B (en) | A kind of yarn group's number automatic regulating system and its method | |
| CN115218603B (en) | Cooling flow control method and device | |
| CN102371278A (en) | Method for automatically controlling plate shape of continuous annealing leveling mill based on stability index | |
| CN111002564A (en) | Blow molding process parameter online regulation and control method | |
| CN105785760B (en) | A kind of annealing furnace clean circulating water hardness automatic control system and its method | |
| CN202898447U (en) | Intelligent gas control valve station based on continuous gas control | |
| CN108887730A (en) | A kind of tobacco cutting secondary charging make-up water supply control system and its control method | |
| CN106893792A (en) | Pulverized coal injection autocontrol method | |
| CN110218862B (en) | Sintering flux addition adjusting method | |
| CN113655816B (en) | Ladle bottom argon blowing system flow control method and computer readable storage medium | |
| CN201716087U (en) | Automatic test system of perfuming, feeding precision and flowmeter precision | |
| CN106893793A (en) | The monitoring method of real-time coal powder injection rate | |
| CN108066871A (en) | A kind of anesthesia respirator proportioning valve flow control methods | |
| CN201867603U (en) | RSLogi*5000 based PID (proportional-integral-derivative) control device for moisture of sintering mixture | |
| CN108660360A (en) | Casting economy and quick feed proportioning system application technology |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200424 |
|
| RJ01 | Rejection of invention patent application after publication |