CN110866670A - Method and system for identifying stub bar and tail in cigarette production and manufacturing process - Google Patents
Method and system for identifying stub bar and tail in cigarette production and manufacturing process Download PDFInfo
- Publication number
- CN110866670A CN110866670A CN201910356087.9A CN201910356087A CN110866670A CN 110866670 A CN110866670 A CN 110866670A CN 201910356087 A CN201910356087 A CN 201910356087A CN 110866670 A CN110866670 A CN 110866670A
- Authority
- CN
- China
- Prior art keywords
- data
- sample
- sample data
- cigarette production
- stub bar
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 130
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000007621 cluster analysis Methods 0.000 claims abstract description 29
- 238000001914 filtration Methods 0.000 claims abstract description 26
- 238000009499 grossing Methods 0.000 claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 41
- 238000005070 sampling Methods 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000003908 quality control method Methods 0.000 description 5
- 241000208125 Nicotiana Species 0.000 description 3
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Manufacturing & Machinery (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Manufacturing Of Cigar And Cigarette Tobacco (AREA)
Abstract
The invention provides a method and a system for identifying the stub bar and the tail in the cigarette production and manufacturing process, wherein the method comprises the following steps: collecting sample data of technological parameters in the cigarette production process in real time; filtering the sample data to realize the smoothing of the data; performing cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the process parameters; and identifying a stub bar and tailing procedure in the cigarette production process according to the steady-state data and the unsteady-state data. The method can improve the control of cigarette production quality, effectively extract steady-state data which accords with actual production, and facilitate the analysis and statistics of the cigarette production data in the later period.
Description
Technical Field
The invention relates to the technical field of tobacco processing informatization, in particular to a method and a system for identifying a stub bar and a tail in a cigarette production and manufacturing process.
Background
At present, the improvement of cigarette production and manufacturing capacity is characterized in that the comprehensive efficiency of cigarette equipment, the quality control level of the cigarette process and the real-time control of cigarette process loss are required, the improvement of cigarette production and manufacturing capacity is realized, the key point is that stable data in the cigarette production process are effectively analyzed, the stable data are obtained and are effectively identified and intercepted according to the stub and the tail in the cigarette production and manufacturing process, currently, a conventional method is adopted, when a certain quality index of a cigarette is higher than a certain value at the beginning of production, the intercept of N units is deleted forwards, when the production is close to the end, the intercept of M units is deleted backwards when the certain quality index is lower than the certain value, and the actual production data in the range are the stable data of cigarette production and manufacturing. Due to the fact that the weight of each batch of cigarettes is different, the difference between the moisture of supplied materials and the temperature is large, the problems that the data of the material head and the material tail are intercepted excessively or cannot be intercepted cleanly and the like often occur in the conventional method.
Disclosure of Invention
The invention provides a method and a system for identifying a stub bar and a tail in a cigarette production and manufacturing process, which solve the problems that production data of the stub bar and the tail in the existing cigarette production and manufacturing process is excessively intercepted or is not completely intercepted, and production actual steady-state data and non-steady-state data cannot be accurately distinguished easily, can improve cigarette production quality control, effectively extract steady-state data which accords with production actual, and are convenient for analyzing and counting the cigarette production data in the later period.
In order to achieve the above purpose, the invention provides the following technical scheme:
a method for identifying the stub bar and the tail in the cigarette production and manufacturing process comprises the following steps:
collecting sample data of technological parameters in the cigarette production process in real time;
filtering the sample data to realize the smoothing of the data;
performing cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the process parameters;
and identifying a stub bar and tailing procedure in the cigarette production process according to the steady-state data and the unsteady-state data.
Preferably, the filtering the sample data to implement data smoothing includes:
determining a sampling value and a sampling number according to the sample data;
and calculating the mean value according to the acquisition value and the sampling number, and performing mean value filtering analysis on the sample data according to the mean value.
Preferably, the filtering the sample data to implement data smoothing further includes:
and if the sample data can not be smoothed, removing abnormal data, and performing smoothing pretreatment by adopting a ButterWorth mode.
Preferably, the performing cluster analysis on the smoothed sample data includes:
performing time-line clustering analysis on the sample data by adopting a K-MEANS algorithm;
and judging according to the result of the clustering analysis, and entering a manual judgment program if the classification result cannot be obtained.
Preferably, the time-line cluster analysis of the sample data by using the K-MEANS algorithm includes:
setting a K-MEANS algorithm termination condition, wherein the termination condition comprises the following steps:
1) the change of the criterion function value is less than a set threshold value;
2) the cluster center does not change within a certain range;
3) a specified number of iterations is reached.
Preferably, the time-line cluster analysis of the sample data by using the K-MEANS algorithm further includes:
(a) randomly initializing sample points;
(b) randomly setting a cluster center;
(c) assigning the cluster center closest to the sample point;
(d) updating the cluster center to be the mean value of all samples in the cluster;
(e) and (d) judging whether each sample is divided into the cluster center closest to the sample, taking the sample mean value belonging to the same cluster as the new cluster center, and if not, repeating the steps (c) and (d) until convergence.
The invention also provides a system for identifying the stub bar and the tail in the cigarette production and manufacturing process, which comprises the following steps:
the acquisition unit is used for acquiring sample data of process parameters in the cigarette production process in real time;
the filtering processing unit is used for filtering the sample data to realize the smoothing of the data;
the cluster analysis unit is used for carrying out cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the process parameters;
and the identification unit is used for identifying a stub bar and tailing procedure in the cigarette production process according to the steady-state data and the unsteady-state data.
Preferably, the filtering processing unit includes:
the mean value processing unit is used for determining a sampling value and a sampling number according to the sample data, carrying out mean value calculation according to the sampling value and the sampling number, and further carrying out mean value filtering analysis on the sample data according to the mean value;
and the smoothing preprocessing unit is used for eliminating abnormal data when the sample data cannot be smoothed, and performing smoothing preprocessing in a ButterWorth mode.
Preferably, the cluster analysis unit includes:
the K-MEANS algorithm analysis unit is used for performing time-line clustering analysis on the sample data by adopting a K-MEANS algorithm;
and the manual judgment control unit is used for judging according to the result of the clustering analysis, and entering a manual judgment program if the classification result cannot be obtained.
Preferably, the K-MEANS algorithm analysis unit includes:
the termination condition setting unit is used for setting a termination condition of the K-MEANS algorithm;
an algorithm processing unit, configured to perform the following steps on the sample data: (a) randomly initializing sample points; (b) randomly setting a cluster center; (c) assigning the cluster center closest to the sample point; (d) updating the cluster center to be the mean value of all samples in the cluster;
and the convergence judging unit is used for judging whether each sample is divided into the cluster center closest to the sample, taking the sample mean value belonging to the same cluster as a new cluster center, and if not, performing clustering processing on the sample data through the algorithm processing unit.
The invention provides a method and a system for identifying a stub bar and a tail in a cigarette production and manufacturing process, which are used for performing cluster analysis on real-time data of cigarette production through a big data K-MEANS algorithm, can divide the real-time data of the cigarette production into two types of steady-state data and non-steady-state data, solve the problems that production data extraction is inaccurate and actual steady-state data and non-steady-state data cannot be accurately distinguished due to the influence of the stub bar and the tail in the existing cigarette production and manufacturing, improve the quality control of the cigarette production, effectively extract steady-state data which accords with the actual production, and facilitate the analysis and statistics of the cigarette production data in the later period.
Drawings
In order to more clearly describe the specific embodiments of the present invention, the drawings to be used in the embodiments will be briefly described below.
FIG. 1 is a schematic view of a method for identifying the stub bar and the tail in the cigarette manufacturing process according to the present invention;
fig. 2 is a flow chart of identifying a stub bar and a tail in a silk making process according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the steps of executing the K-means algorithm according to an embodiment of the present invention
FIG. 4 is a schematic diagram of a clustering analysis result of a big data K-MEANS algorithm based on an index of discharged water content in a first-stage feeding procedure of cigarette production in the embodiment of the invention;
FIG. 5 is a schematic diagram of a clustering analysis result of a big data K-MEANS algorithm based on an index of moisture content of discharged materials in a loosening and conditioning process in cigarette production.
Detailed Description
In order to make the technical field of the invention better understand the scheme of the embodiment of the invention, the embodiment of the invention is further described in detail with reference to the drawings and the implementation mode.
Aiming at the problems that in the current cigarette production process, the identification of unstable data in the production process of the stub bar and the stub bar is inaccurate, and the analysis and the statistical result of cigarette production data are influenced. The invention provides a method and a system for identifying a stub bar and a tail in the cigarette production and manufacturing process, which are used for performing cluster analysis on real-time data of cigarette production through a big data K-MEANS algorithm, can divide the real-time data of the cigarette production into two types of steady-state data and non-steady-state data, solve the problems that the production data of the stub bar and the tail in the existing cigarette production and manufacturing process are excessively intercepted or incompletely intercepted, and the steady-state data and the non-steady-state data of actual production cannot be accurately distinguished, can improve the control of the cigarette production quality, effectively extract the steady-state data which accords with the actual production, and are convenient for analyzing and counting the cigarette production data in the later period.
As shown in fig. 1, a method for identifying a stub bar and a tail in a cigarette production and manufacturing process comprises the following steps:
s1: collecting sample data of technological parameters in the cigarette production process in real time;
s2: filtering the sample data to realize the smoothing of the data;
s3: performing cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the process parameters;
s4: and identifying a stub bar and tailing procedure in the cigarette production process according to the steady-state data and the unsteady-state data.
In practical application, in the cigarette production and manufacturing process, technical indexes of all working procedures in the production process are determined by detecting process parameters, and whether the production process is in a stable hidden stage or not is further judged. In an embodiment, the filament manufacturing process is taken as an example, wherein the process parameter may be any one of an outlet moisture content, an outlet temperature, a cylinder wall pressure, an auxiliary air temperature, a discharge cover negative pressure, a flow rate of an electric scale, an inlet moisture content, and a hot air temperature, but is not limited to the above examples of the process parameter. Taking the moisture content of the outlet of the cut tobacco drying procedure as an example, firstly, sample data of the moisture content of the outlet in the cut tobacco drying procedure is acquired in real time, wherein the sample data comprises: sample values and sample numbers. And secondly, processing the sample data, including adopting filtering analysis to realize the smoothing of the data. And finally, performing cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the water content of the outlet, and determining the time and the interval of the process of the stub bar and the tail according to the data of the water content of the outlet. The method can improve the accuracy of distinguishing the steady-state data from the non-steady-state data by the production data.
Further, the filtering the sample data to realize data smoothing includes:
s21: and determining a sampling value and a sampling number through the sample data.
S22: and calculating the mean value according to the acquisition value and the sampling number, and performing mean value filtering analysis on the sample data according to the mean value.
In practical application, x is set as a sampling value of the process parameter, n is set as a sampling number, and a corresponding average value is calculated according to the sampling value x and the sampling number n. Secondly, two points in the space are calculated according to the Euclidean distance, for example, the space coordinates of the two points are respectively as follows: p (p1, p2, p 3.. pn), q (q1, q2, q 3.. qn), the distance between two points can be expressed as:
and then, mean value filtering analysis is carried out according to the distance between each sampling point and the mean value, so that abnormal data are removed from the sample data to realize smooth processing.
Further, the filtering the sample data to realize data smoothing further includes:
s23: and if the sample data can not be smoothed, removing abnormal data, and performing smoothing pretreatment by adopting a ButterWorth mode.
Performing cluster analysis on the smoothed sample data, including:
s31: and performing time-line clustering analysis on the sample data by adopting a K-MEANS algorithm.
S32: and judging according to the result of the clustering analysis, and entering a manual judgment program if the classification result cannot be obtained.
Specifically, as shown in fig. 2, in the cigarette production process, sample data of the moisture content at the outlet is collected, filtering analysis is performed to smooth the data, abnormal data is eliminated, if the data cannot be smoothed, smoothing preprocessing is performed in a ButterWorth mode, clustering analysis is performed on the smoothed data, as shown in fig. 3, a K-MEANS algorithm is used to classify the data, steady-state data and unsteady-state data are obtained to be used for analysis in the production process, and if a classification result cannot be obtained, manual judgment is performed on abnormal classification conditions, the reason of the abnormality is found, and subsequent improvement is facilitated.
Further, the time-line cluster analysis of the sample data by adopting the K-MEANS algorithm includes:
setting a K-MEANS algorithm termination condition, wherein the termination condition comprises the following steps:
1) the change of the criterion function value is less than a set threshold value;
2) the cluster center does not change within a certain range;
3) a specified number of iterations is reached.
Further, the time-line cluster analysis of the sample data by using the K-MEANS algorithm further includes:
(a) randomly initializing sample points;
(b) randomly setting a cluster center;
(c) assigning the cluster center closest to the sample point;
(d) updating the cluster center to be the mean value of all samples in the cluster;
(e) and (d) judging whether each sample is divided into the cluster center closest to the sample, taking the sample mean value belonging to the same cluster as the new cluster center, and if not, repeating the steps (c) and (d) until convergence.
Specifically, the inner loop of the algorithm accomplishes two tasks: firstly, dividing each sample into a cluster center closest to the sample; and secondly, taking the sample mean value belonging to the same cluster as a new cluster center. In one embodiment, as shown in fig. 4, a schematic diagram of a cluster analysis result of a big data K-MEANS algorithm based on an index of moisture content of discharged material in a first-stage feeding procedure of cigarette production is shown; wherein the horizontal thin solid lines represent steady state data; the vertical dashed line represents unsteady data. In another embodiment, as shown in fig. 5, a schematic diagram of a cluster analysis result of a big data K-MEANS algorithm based on an index of moisture content of discharged material in a loose moisture regain process in cigarette production is shown in the embodiment of the present invention; wherein the horizontal thin solid lines represent steady state data; the vertical dashed line represents unsteady data.
The method for identifying the stub bar and the tail in the cigarette production and manufacturing process can be used for performing cluster analysis on the real-time data of the cigarette production through a big data K-MEANS algorithm, dividing the real-time data of the cigarette production into two types of steady-state data and non-steady-state data, solving the problems that the extraction of the production data is inaccurate and the actual steady-state data and the actual non-steady-state data cannot be accurately distinguished due to the influence of the stub bar and the tail in the existing cigarette production and manufacturing process, improving the quality control of the cigarette production, effectively extracting the steady-state data which accords with the actual production, and facilitating the analysis and statistics of the cigarette production data in the later period.
Correspondingly, the invention also provides a system for identifying the stub bar and the tail in the cigarette production and manufacturing process, which comprises the following steps: and the acquisition unit is used for acquiring sample data of the process parameters in the cigarette production process in real time. And the filtering processing unit is used for filtering the sample data so as to realize the smoothing of the data. And the cluster analysis unit is used for carrying out cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the process parameters. And the identification unit is used for identifying a stub bar and tailing procedure in the cigarette production process according to the steady-state data and the unsteady-state data.
Further, the filter processing unit includes: and the mean value processing unit is used for determining a sampling value and a sampling number according to the sample data, carrying out mean value calculation according to the sampling value and the sampling number, and further carrying out mean value filtering analysis on the sample data according to the mean value. And the smoothing preprocessing unit is used for eliminating abnormal data when the sample data cannot be smoothed, and performing smoothing preprocessing in a ButterWorth mode.
Still further, the cluster analysis unit includes: and the K-MEANS algorithm analysis unit is used for performing time-line clustering analysis on the sample data by adopting a K-MEANS algorithm. And the manual judgment control unit is used for judging according to the result of the clustering analysis, and entering a manual judgment program if the classification result cannot be obtained.
The K-MEANS algorithm analysis unit comprises: the termination condition setting unit is used for setting a termination condition of the K-MEANS algorithm; an algorithm processing unit, configured to perform the following steps on the sample data: (a) randomly initializing sample points; (b) randomly setting a cluster center; (c) assigning the cluster center closest to the sample point; (d) updating the cluster center to be the mean value of all samples in the cluster; and the convergence judging unit is used for judging whether each sample is divided into the cluster center closest to the sample, taking the sample mean value belonging to the same cluster as a new cluster center, and if not, performing clustering processing on the sample data through the algorithm processing unit.
Therefore, the invention provides a system for identifying the stub bar and the tail in the cigarette production and manufacturing process, which performs cluster analysis on the real-time data of the cigarette production through a big data K-MEANS algorithm, can divide the real-time data of the cigarette production into two types of steady-state data and non-steady-state data, solves the problems that the extraction of the production data is inaccurate and the actual steady-state data and the actual non-steady-state data cannot be accurately distinguished due to the influence of the stub bar and the tail in the existing cigarette production and manufacturing, can improve the quality control of the cigarette production, effectively extracts the steady-state data which accords with the actual production, and is convenient for analyzing and counting the cigarette production data in the later period.
The construction, features and functions of the present invention have been described in detail with reference to the embodiments shown in the drawings, but the present invention is not limited to the embodiments shown in the drawings, and all equivalent embodiments modified or modified by the spirit and scope of the present invention should be protected without departing from the spirit of the present invention.
Claims (10)
1. A method for identifying the stub bar and the tail in the cigarette production and manufacturing process is characterized by comprising the following steps:
collecting sample data of technological parameters in the cigarette production process in real time;
filtering the sample data to realize the smoothing of the data;
performing cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the process parameters;
and identifying a stub bar and tailing procedure in the cigarette production process according to the steady-state data and the unsteady-state data.
2. The method for identifying the stub bar and the tail in the cigarette production and manufacturing process according to claim 1, wherein the step of filtering the sample data to smooth the data comprises the following steps:
determining a sampling value and a sampling number according to the sample data;
and calculating the mean value according to the acquisition value and the sampling number, and performing mean value filtering analysis on the sample data according to the mean value.
3. The method for identifying the stub bar and the tail in the cigarette production and manufacturing process according to claim 2, wherein the step of filtering the sample data to smooth the data further comprises the following steps:
and if the sample data can not be smoothed, removing abnormal data, and performing smoothing pretreatment by adopting a ButterWorth mode.
4. The method for identifying the stub bar and the tail in the cigarette production and manufacturing process according to claim 1, wherein the performing cluster analysis on the smoothed sample data comprises:
performing time-line clustering analysis on the sample data by adopting a K-MEANS algorithm;
and judging according to the result of the clustering analysis, and entering a manual judgment program if the classification result cannot be obtained.
5. The method for identifying the stub bar and the tail in the cigarette production and manufacturing process according to claim 4, wherein the time-line cluster analysis of the sample data by adopting the K-MEANS algorithm comprises the following steps:
setting a K-MEANS algorithm termination condition, wherein the termination condition comprises the following steps: 1) the change of the criterion function value is less than a set threshold value; 2) the cluster center does not change within a certain range; 3) a specified number of iterations is reached.
6. The method for identifying the stub bar and the tail in the cigarette manufacturing process according to claim 5, wherein the time-line cluster analysis of the sample data by using the K-MEANS algorithm further comprises:
(a) randomly initializing sample points;
(b) randomly setting a cluster center;
(c) assigning the cluster center closest to the sample point;
(d) updating the cluster center to be the mean value of all samples in the cluster;
(e) and (d) judging whether each sample is divided into the cluster center closest to the sample, taking the sample mean value belonging to the same cluster as the new cluster center, and if not, repeating the steps (c) and (d) until convergence.
7. A cigarette manufacture manufacturing process stub bar material tail's identification system which characterized in that includes:
the acquisition unit is used for acquiring sample data of process parameters in the cigarette production process in real time;
the filtering processing unit is used for filtering the sample data to realize the smoothing of the data;
the cluster analysis unit is used for carrying out cluster analysis on the smoothed sample data to obtain steady-state data and unsteady-state data of the process parameters;
and the identification unit is used for identifying a stub bar and tailing procedure in the cigarette production process according to the steady-state data and the unsteady-state data.
8. The system for identifying a cigarette production manufacturing process stub bar and stub bar according to claim 7, wherein the filter processing unit comprises:
the mean value processing unit is used for determining a sampling value and a sampling number according to the sample data, carrying out mean value calculation according to the sampling value and the sampling number, and further carrying out mean value filtering analysis on the sample data according to the mean value;
and the smoothing preprocessing unit is used for eliminating abnormal data when the sample data cannot be smoothed, and performing smoothing preprocessing in a ButterWorth mode.
9. The system for identifying a cigarette production manufacturing process stub bar and tail according to claim 8, wherein the cluster analysis unit comprises:
the K-MEANS algorithm analysis unit is used for performing time-line clustering analysis on the sample data by adopting a K-MEANS algorithm;
and the manual judgment control unit is used for judging according to the result of the clustering analysis, and entering a manual judgment program if the classification result cannot be obtained.
10. The system for identifying a cigarette production manufacturing process stub bar and tail according to claim 9, wherein the K-MEANS algorithm analysis unit comprises:
the termination condition setting unit is used for setting a termination condition of the K-MEANS algorithm;
an algorithm processing unit, configured to perform the following steps on the sample data: (a) randomly initializing sample points; (b) randomly setting a cluster center; (c) assigning the cluster center closest to the sample point; (d) updating the cluster center to be the mean value of all samples in the cluster;
and the convergence judging unit is used for judging whether each sample is divided into the cluster center closest to the sample, taking the sample mean value belonging to the same cluster as a new cluster center, and if not, performing clustering processing on the sample data through the algorithm processing unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356087.9A CN110866670A (en) | 2019-04-29 | 2019-04-29 | Method and system for identifying stub bar and tail in cigarette production and manufacturing process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356087.9A CN110866670A (en) | 2019-04-29 | 2019-04-29 | Method and system for identifying stub bar and tail in cigarette production and manufacturing process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110866670A true CN110866670A (en) | 2020-03-06 |
Family
ID=69651926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910356087.9A Pending CN110866670A (en) | 2019-04-29 | 2019-04-29 | Method and system for identifying stub bar and tail in cigarette production and manufacturing process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866670A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882188A (en) * | 2020-07-15 | 2020-11-03 | 山东中烟工业有限责任公司 | Process quality homogeneity level evaluation method and system based on Birch clustering algorithm |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324089A (en) * | 2012-03-24 | 2013-09-25 | 厦门烟草工业有限责任公司 | Thread making technological parameter dynamic quality stability characterization method |
| CN103941163A (en) * | 2014-05-12 | 2014-07-23 | 福州大学 | Resonant earthed system fault line selection method utilizing fuzzy K-means clustering |
| CN106226572A (en) * | 2016-07-13 | 2016-12-14 | 国家电网公司 | Household loads recognition methods based on transient characteristic cluster |
| CN108519760A (en) * | 2017-11-06 | 2018-09-11 | 红云红河烟草(集团)有限责任公司 | Filament making process steady-state identification method based on variable point detection theory |
| CN109407506A (en) * | 2018-11-28 | 2019-03-01 | 深圳圣缘节能科技有限公司 | A kind of acquisition methods of the power plant units dynamic optimal value based on data mining |
-
2019
- 2019-04-29 CN CN201910356087.9A patent/CN110866670A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324089A (en) * | 2012-03-24 | 2013-09-25 | 厦门烟草工业有限责任公司 | Thread making technological parameter dynamic quality stability characterization method |
| CN103941163A (en) * | 2014-05-12 | 2014-07-23 | 福州大学 | Resonant earthed system fault line selection method utilizing fuzzy K-means clustering |
| CN106226572A (en) * | 2016-07-13 | 2016-12-14 | 国家电网公司 | Household loads recognition methods based on transient characteristic cluster |
| CN108519760A (en) * | 2017-11-06 | 2018-09-11 | 红云红河烟草(集团)有限责任公司 | Filament making process steady-state identification method based on variable point detection theory |
| CN109407506A (en) * | 2018-11-28 | 2019-03-01 | 深圳圣缘节能科技有限公司 | A kind of acquisition methods of the power plant units dynamic optimal value based on data mining |
Non-Patent Citations (2)
| Title |
|---|
| 袁湘云 等: ""烟草制造过程中工艺管控大数据的运用前景初探"", 《中 国 管 理 信 息 化》 * |
| 隋先辉 等: "《舰载导弹作战使用技术及应用》", 31 August 2018, 北京：国防工业出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882188A (en) * | 2020-07-15 | 2020-11-03 | 山东中烟工业有限责任公司 | Process quality homogeneity level evaluation method and system based on Birch clustering algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114445387A (en) | Fiberboard quality classification method based on machine vision | |
| CN109343344A (en) | Cigarette machine operating parameter optimization method | |
| CN112036701A (en) | Technological parameter optimization method for multi-process industrial production process | |
| CN110399935A (en) | The real-time method for monitoring abnormality of robot and system based on isolated forest machine learning | |
| CN112330663A (en) | Computer vision tobacco shred width detection method based on variable diameter circle | |
| CN112395608A (en) | Network security threat monitoring method, device and readable storage medium | |
| CN110866670A (en) | Method and system for identifying stub bar and tail in cigarette production and manufacturing process | |
| CN117992808B (en) | Big data-based computer network management method and system | |
| CN108763584B (en) | Method and system for filtering scattered points of wind power curve | |
| CN112837754A (en) | Single cell automatic classification method and device based on characteristic genes | |
| CN105049286A (en) | Cloud platform speed measurement data judging method based on hierarchical clustering | |
| CN108519760A (en) | Filament making process steady-state identification method based on variable point detection theory | |
| CN114178176A (en) | Air quantity control method and device of tobacco shred winnowing machine and storage medium | |
| CN108596227A (en) | A kind of leading influence factor method for digging of user power utilization behavior | |
| CN114985283A (en) | Tea leaf identification method based on multi-feature image identification technology | |
| CN112036482B (en) | Traditional Chinese medicine classification method based on electronic nose sensor data | |
| CN115170820B (en) | Feature extraction and boundary identification method applied to data curve transition stage | |
| CN108550053B (en) | User consumption data acquisition and analysis system and method based on platform technology | |
| CN111076772B (en) | Processing method of cigarette shredding process data | |
| CN110675919A (en) | Method and system for predicting moisture at inlet of cut tobacco drying process based on K-nearest neighbor method | |
| CN113876008B (en) | Method for controlling stability of moisture content of loose and moisture regained tobacco flakes | |
| CN113269757B (en) | Groove characteristic parameter processing method based on hierarchical clustering analysis | |
| CN113210264B (en) | Tobacco sundry removing method and device | |
| CN108197271A (en) | A kind of films and television programs market analysis method based on big data | |
| CN111061257B (en) | Industrial process monitoring method based on dynamic global LPP |
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 |