CN109946265A - Pipe tobacco pollutes On-line near infrared analyzer alarm system - Google Patents
Pipe tobacco pollutes On-line near infrared analyzer alarm system Download PDFInfo
- Publication number
- CN109946265A CN109946265A CN201711389520.6A CN201711389520A CN109946265A CN 109946265 A CN109946265 A CN 109946265A CN 201711389520 A CN201711389520 A CN 201711389520A CN 109946265 A CN109946265 A CN 109946265A
- Authority
- CN
- China
- Prior art keywords
- pipe tobacco
- near infrared
- alarm system
- infrared analyzer
- line near
- 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
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of pipe tobaccos to pollute On-line near infrared analyzer alarm system, is used for pipe tobacco On-line NIR acquisition system, data processing and alarm;Online alarm identification step includes (1) spectrum data gathering, and the transmission of (2) spectroscopic data, (3) spectroscopic data calculates and identifying processing, the transmission of (4) identification signal and alarm.
Description
Technical field
The invention belongs to pipe tobaccos to pollute On-line near infrared analyzer alarm system, in particular to a kind of multichannel pipe tobacco pollution is online close
IR alarm system.
Background technique
Since equipment lubrication component leaks in cigarette process, causes pipe tobacco to pollute, directly affect cigarette quality.Due to
Source of leaks is numerous, it is difficult to find.This on-line checking that pipe tobacco is polluted becomes in cigarette field with alarm not can solve for a long time
Important technology project.Since lubricating oil or lubricating grease are different from pipe tobacco composition, near infrared spectrum is different.When pipe tobacco moistens
When lubrication prescription pollutes, near infrared spectrum also changes.By the near infrared spectrum of on-line measurement pipe tobacco, and according to on-line checking
Pipe tobacco spectrum change, judge pipe tobacco whether by lubricant contamination.
Summary of the invention
The present invention is directed to research and develop a set of pipe tobacco pollution On-line near infrared analyzer detection alarm system, cigarette in cigarette process is realized
The on-line checking and Realtime Alerts of silk pollution condition.
System Working Principle is since lubricating oil or lubricating grease are different from pipe tobacco composition, and near infrared spectrum is different.Work as cigarette
When lubricant pollution occurs for silk, near infrared spectrum also changes.By the near infrared spectrum of on-line measurement pipe tobacco, according to
Whether the near infrared spectrum variation of the pipe tobacco of line detection, judge pipe tobacco by lubricant contamination.
Pipe tobacco pollute On-line near infrared analyzer alarm system, including online near infrared spectra collection system, data processing system and
Alarm system.Online alarm identification step includes (1) spectrum data gathering;(2) spectroscopic data transmits;(3) spectroscopic data calculates
And identifying processing;(4) identification signal transmission and alarm.
On-line NIR acquisition system is multichannel pipe tobacco On-line NIR acquisition system, mainly includes light source
Module, multi-path fiber coupling module and near infrared spectrometer module.The light that light source issues is more by being coupled into optical fiber feeding
Road fiber coupler couples light into wherein optical fiber all the way according to timing, and by the probe of fiber-optic output, light is irradiated
The pipe tobacco material of moving condition on to conveyer belt, part of light is had an effect with pipe tobacco, and is propagated with diffusing reflection form, optical fiber
Probe collection part diffuses, and is sent to multi-channel optical fibre coupler, subsequently into output optical fibre, is sent into spectrometer module,
It is detected by dispersion and detector, obtains the diffusing reflection near infrared spectrum of pipe tobacco.Multi-channel optical fibre coupler is cut according to setting timing
It changes, realizes the pipe tobacco spectra collection of multichannel (different measurement points).
Data processing system mainly includes database and messaging software.
Database includes pollution sources spectroscopic data, pipe tobacco type spectroscopic data and pipe tobacco pollution identification model.Pipe tobacco pollution
Identification model includes two identification models of pollution pipe tobacco and pure pipe tobacco established respectively using SIMCA clustering method.
Two class pipe tobaccos are sampled first, scan the near infrared spectrum of the multiple samples of target pipe tobacco, then to target pipe tobacco
Near infrared spectrum carries out the data model that principal component analysis operation generates every kind of target pipe tobacco, then scans the close red of unknown tobacco leaf
External spectrum carries out principal component decomposition calculating to unknown pipe tobacco near infrared spectrum with target pipe tobacco data model, calculates unknown pipe tobacco
At a distance from target pipe tobacco, the similarity degree of unknown pipe tobacco and target pipe tobacco is measured by distance.The experimental results showed that using
SIMCA method establishes pipe tobacco pollution identification model and reaches 100% to the correct recognition rata of unknown pipe tobacco.
Whether messaging software will be sentenced according to pipe tobacco spectrum, online differentiation pipe tobacco by lubricating oil or grease contaminated
Other result is sent to alarm system.
Detailed description of the invention
Fig. 1 pipe tobacco pollutes On-line near infrared analyzer alarm system structural schematic diagram;
The original spectrum of Fig. 2 pollution pipe tobacco and pure pipe tobacco;
Fig. 3 classifying quality figure.
Specific embodiment
The present invention provides a kind of pipe tobacco pollution On-line near infrared analyzer alarm system, is explained with reference to the accompanying drawing.
1. on-line checking process
Fig. 1 show pipe tobacco pollution On-line near infrared analyzer alarm system structural schematic diagram.The light issued by light source, by being coupled into
Optical fiber is sent into multi-channel optical fibre coupler according to timing and couples light into wherein optical fiber all the way, passes through the spy of fiber-optic output
Head light shines on the pipe tobacco material of moving condition on conveyer belt, and part of light is had an effect with pipe tobacco, and with diffusing reflection
Form is propagated, and fibre-optical probe collection part diffuses, is sent to multi-channel optical fibre coupler, subsequently into output optical fibre, send
Enter spectrometer module, is detected by dispersion and detector, obtain the diffusing reflection near infrared spectrum of pipe tobacco.The pipe tobacco that will be acquired in real time
On-line NIR is sent into data processing system, according to identification model, realizes the pollution of online recognition pipe tobacco, and Realtime Alerts.
Multi-channel optical fibre coupler realizes the pipe tobacco spectrum of multichannel (i.e. different measurement points) according to setting timing switching.According to pollutant with
The near infrared spectrum difference of pipe tobacco establishes online spectral matching factor pollutant model.
2. the foundation of prediction model
Establish pollution pipe tobacco and pure pipe tobacco identification model respectively using SIMCA clustering method.
Two class pipe tobaccos are sampled first, scan the near infrared spectrum of the multiple samples of target pipe tobacco, then to target pipe tobacco
Near infrared spectrum carries out the data model that principal component analysis operation generates every kind of target pipe tobacco, then scans the close red of unknown tobacco leaf
External spectrum carries out principal component decomposition calculating to unknown pipe tobacco near infrared spectrum with target pipe tobacco data model, calculates unknown pipe tobacco
At a distance from target pipe tobacco, the similarity degree of unknown pipe tobacco and target pipe tobacco is measured by distance, this method correct recognition rata reaches
To 100%.
Embodiment
1) sample collection
Lubricating oil (22, sample of lubrication oil content > 10% are adulterated by 80;24, sample between content 1%-10%, content <
1% sample) pollution pipe tobacco be one group, the pure pipe tobacco that lubrication oil content is zero is one group (45).
2) spectra collection and pretreatment
Spectroscopic data is acquired by above-mentioned spectra collection system real-time online, gained spectroscopic data is as shown in Figure 2.It lubricates as seen from the figure
There are larger differences for the original spectrum of the doping pipe tobacco of oil content > 10% and pure pipe tobacco, can be separated the two with original spectrum;
And as the original spectrum difference of reduction the doping pipe tobacco and pure pipe tobacco of lubrication oil content is smaller and smaller, it is difficult to directly separate.Separately
On the one hand since near infrared spectrum is vulnerable to environment, the influence of the factors such as detecting distance, in collected spectrum, inevitably
Various noises, shift phenomenon can be contained, these would necessarily affect the analysis of spectroscopic data and the analysis precision of calibration model and
Stability, therefore pipe tobacco thickness fluctuation, moisture wave are eliminated it is necessary to carry out mathematics pretreatment to original spectrum before establishing model
The influence of the factors such as dynamic, pipe tobacco type improves signal-to-noise ratio to minimize noise.It is micro- that multiplicative scatter correction, second order is respectively adopted
Point and S-G smooth mode, spectrum is pre-processed, comparative analysis is as a result, obtain optimal spectrum data.
3) model is established
To pretreated spectrum, the data model that principal component analysis operation generates pollution pipe tobacco and pure pipe tobacco is carried out.Two class moulds
The differentiation effect of type is as shown in figure 3, prediction accuracy can reach 100% according to the experimental results.Thus illustrate established model
Online pipe tobacco pollution identification, and Realtime Alerts may be implemented.
Claims (7)
1. pipe tobacco pollutes On-line near infrared analyzer alarm system, including online near infrared spectra collection system, data processing system and report
Alert system;Online alarm identification step includes (1) spectrum data gathering, the transmission of (2) spectroscopic data, (3) spectroscopic data calculate and
Identifying processing, the transmission of (4) identification signal and alarm.
2. pipe tobacco pollutes On-line near infrared analyzer alarm system according to claim 1, it is characterised in that: On-line NIR acquisition system
System is multichannel pipe tobacco On-line NIR acquisition system, mainly includes light source module, multi-path fiber coupling module and close
Infrared spectrometer module.
3. polluting On-line near infrared analyzer alarm system according to claim 2 pipe tobacco, it is characterised in that: multi-path fiber coupling module is set
The switching of timing sequence, realizes multichannel difference measurement point pipe tobacco spectra collection.
4. pipe tobacco pollutes On-line near infrared analyzer alarm system according to claim 1, it is characterised in that: data processing system mainly includes
Database and messaging software.
5. polluting On-line near infrared analyzer alarm system according to claim 4 pipe tobacco, it is characterised in that: database includes pollution sources spectrum
Data, pipe tobacco type spectroscopic data and pipe tobacco pollute identification model.
6. polluting On-line near infrared analyzer alarm system according to claim 5 pipe tobacco, it is characterised in that: pipe tobacco pollutes identification model and includes
Two identification models of pollution pipe tobacco and pure pipe tobacco established respectively using SIMCA clustering method.
7. polluting On-line near infrared analyzer alarm system according to claim 4 pipe tobacco, it is characterised in that: messaging software is according to pipe tobacco
Whether spectrum, online differentiation pipe tobacco will differentiate result be sent to alarm system by lubricating oil or grease contaminated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711389520.6A CN109946265A (en) | 2017-12-21 | 2017-12-21 | Pipe tobacco pollutes On-line near infrared analyzer alarm system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711389520.6A CN109946265A (en) | 2017-12-21 | 2017-12-21 | Pipe tobacco pollutes On-line near infrared analyzer alarm system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109946265A true CN109946265A (en) | 2019-06-28 |
Family
ID=67005317
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711389520.6A Pending CN109946265A (en) | 2017-12-21 | 2017-12-21 | Pipe tobacco pollutes On-line near infrared analyzer alarm system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109946265A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201066339Y (en) * | 2007-07-27 | 2008-05-28 | 浙江大学 | A portable near infrared spectrum instrument for identifying tobacco identity |
CN101261221A (en) * | 2008-04-21 | 2008-09-10 | 中国烟草总公司郑州烟草研究院 | Near-infrared tobacco feeding homogeneity test device |
US20130082173A1 (en) * | 2011-05-26 | 2013-04-04 | Altria Client Services, Inc. | Oil detection process and apparatus |
CN104330385A (en) * | 2014-11-14 | 2015-02-04 | 山东中烟工业有限责任公司 | Device and method for detecting cut tobacco blending uniformity online |
CN105628646A (en) * | 2015-12-30 | 2016-06-01 | 山东中烟工业有限责任公司 | Online cigarette tar predicting and warning method |
CN105928899A (en) * | 2016-04-15 | 2016-09-07 | 福建中烟工业有限责任公司 | Method and system for detecting color spot contamination of cigarettes |
-
2017
- 2017-12-21 CN CN201711389520.6A patent/CN109946265A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201066339Y (en) * | 2007-07-27 | 2008-05-28 | 浙江大学 | A portable near infrared spectrum instrument for identifying tobacco identity |
CN101261221A (en) * | 2008-04-21 | 2008-09-10 | 中国烟草总公司郑州烟草研究院 | Near-infrared tobacco feeding homogeneity test device |
US20130082173A1 (en) * | 2011-05-26 | 2013-04-04 | Altria Client Services, Inc. | Oil detection process and apparatus |
CN104330385A (en) * | 2014-11-14 | 2015-02-04 | 山东中烟工业有限责任公司 | Device and method for detecting cut tobacco blending uniformity online |
CN105628646A (en) * | 2015-12-30 | 2016-06-01 | 山东中烟工业有限责任公司 | Online cigarette tar predicting and warning method |
CN105928899A (en) * | 2016-04-15 | 2016-09-07 | 福建中烟工业有限责任公司 | Method and system for detecting color spot contamination of cigarettes |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101706307B (en) | Transmission spectra based method and device for detecting oil product interfaces in oil pipelines | |
CN104568836B (en) | Low-concentration and multi-component gas detection method based on integration of multiple spectrum technologies | |
CN102353634B (en) | Online calibration method of laser online detection system for direction of gas contents in smoke | |
CN108375546A (en) | The online multipoint detection device of chemical fertilizer based on Vis/NIR technology and its detection method | |
CN102353633B (en) | Flue gas content laser on-line detection method and system | |
CN1831516A (en) | Method for nondistructive discriminating variety and true and false of cigarette using visible light and near-infrared spectrum technology | |
CN102636450A (en) | Method for detecting wolfberry polyose content in Chinese wolfberry in a nondestructive way based on near infrared spectrum technology | |
CN106932378A (en) | The on-line detecting system and method for a kind of sour gas composition based on Raman spectrum | |
CN103792215A (en) | Method for rapidly measuring content of carbon element in steel | |
CN110967313A (en) | Near infrared spectrum prediction modeling method for nicotine content in tobacco tar of electronic cigarette and application | |
CN204462027U (en) | A kind of water environment field quick detection instrument based on color sensing | |
CN108318442B (en) | Detection method suitable for traditional Chinese medicine suspension system | |
CN114252430B (en) | Online pulp grade detection method based on laser-induced breakdown spectroscopy technology | |
CN107389603A (en) | Gas sensor based on the adaptive a variety of environment of light signal strength | |
CN202119397U (en) | Non-contact vision detection system for sampling inspection | |
CN102288574A (en) | Device and method for quantitatively analyzing concentration of multi-component oil fume | |
CN102830080A (en) | Near infrared spectrum method for judging inner quality stability of tipping paper for tobacco | |
CN109001182B (en) | Raman spectrum nondestructive testing method for alcohol content in closed container | |
Dai et al. | On-line UV-NIR spectroscopy as a process analytical technology (PAT) tool for on-line and real-time monitoring of the extraction process of Coptis Rhizome | |
CN114636687A (en) | Small sample coal quality characteristic analysis system and method based on deep migration learning | |
CN215115874U (en) | Near-infrared quality detection system of different size fruits of self-adaptation | |
Huang et al. | In‐line monitoring of component content of polypropylene/polystyrene blends during melt extrusion using Raman spectroscopy | |
CN104596976A (en) | Method for determining protein of paper-making reconstituted tobacco through ear infrared reflectance spectroscopy technique | |
CN110987899B (en) | Method for measuring content of total acid total esters in white spirit and identifying quality grade of white spirit | |
CN113984670A (en) | Double-sensor cavity adjusting method for cavity ring-down high-reflectivity measurement |
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: 20190628 |