CN113743744B - Automatic identification and early warning method for quality micro-variation in cigarette manufacturing process - Google Patents
Automatic identification and early warning method for quality micro-variation in cigarette manufacturing process Download PDFInfo
- Publication number
- CN113743744B CN113743744B CN202110931006.0A CN202110931006A CN113743744B CN 113743744 B CN113743744 B CN 113743744B CN 202110931006 A CN202110931006 A CN 202110931006A CN 113743744 B CN113743744 B CN 113743744B
- Authority
- CN
- China
- Prior art keywords
- factor
- quality
- early warning
- term
- judgment
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 22
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 11
- 230000007774 longterm Effects 0.000 claims abstract description 22
- 238000012163 sequencing technique Methods 0.000 claims abstract description 5
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 102000003712 Complement factor B Human genes 0.000 claims description 24
- 108090000056 Complement factor B Proteins 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 24
- 230000003993 interaction Effects 0.000 claims description 5
- 101100518501 Mus musculus Spp1 gene Proteins 0.000 claims description 2
- 241000208125 Nicotiana Species 0.000 abstract description 3
- 235000002637 Nicotiana tabacum Nutrition 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000010998 test method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000000265 homogenisation Methods 0.000 description 3
- 241000748095 Hymenopappus filifolius Species 0.000 description 2
- 238000000546 chi-square test Methods 0.000 description 2
- 230000003750 conditioning effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000007605 air drying Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- 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—Systems or methods specially adapted for 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
Abstract
The invention discloses a method for automatically identifying and early warning quality micro-variation in a cigarette manufacturing process, which belongs to the field of tobacco production, and comprises short-term quality early warning and long-term quality judgment, wherein the short-term quality early warning is realized by the following steps: step 1, searching out batches meeting the conditions through system searching; step 2, subtracting the ordered data from standard values respectively, and carrying out absolute value conversion on the difference values; step 3, sequencing the absolute value of the converted difference value from small to large, and then solving the rank; the invention can establish a quality micro-change automatic early warning and judging system combining short-term early warning and long-term judgment, and can provide important guarantee for long-term controllability, stability and homogeneity of product quality.
Description
Technical Field
The invention belongs to the field of tobacco quality management, and particularly relates to an automatic quality micro-change identification and early warning method in a cigarette manufacturing process.
Background
With the continuous development of cigarette industry informatization, a digital production framework is built based on data interaction of Ethernet, a database, MES and the like and a processing system. The platforms create conditions for acquisition, calculation, storage and analysis of production data, and open up digital channels for intelligent manufacture, accurate manufacture and individual processing of cigarettes. However, in the aspect of digital function exertion, a few defects still exist, particularly, analysis of quality aging results, namely short-term target judgment, is highlighted, long-term quality target analysis and judgment are ignored, however, the quality final target is required to realize short-term quality targets, long-term quality early warning and determinability are required, and the quality final target is not only the long-term stability and homogenization of products, but also the value direction of digital intelligent manufacturing.
In terms of the application effect of the digital intelligent platform in the cigarette processing process at present, important roles are played in realizing short-term quality targets, for example, in analysis of whether each index meets the standards or not, point-to-point judgment can be accurately and quickly carried out according to conditions, for example, continuous multi-batch CPK of one index in the product processing process can reach more than 1.0, the process capability of the index is sufficient in short-term judgment, but if the actual result of the index is mostly located at one side of the standard value, whether the index deviates from the quality expected characteristic? A reliable and accurate decision system is clearly needed. Particularly, for characteristic changes of multiple brands and multiple indexes during long-term production, a perfect intelligent tracking and monitoring analysis platform is more required to be established. It is well known that cigarette products are often affected by factors such as: the effects of the factors on the product quality can be difficult to distinguish in a short period, and if a quality micro-change automatic early warning and judging system combining short-term early warning and long-term judgment can be established, important guarantee is provided for long-term controllability, stability and homogeneity of the product quality.
Disclosure of Invention
The invention can establish a quality micro-change automatic early warning and judging system combining short-term early warning and long-term judgment, and can provide important guarantee for long-term controllability, stability and homogeneity of product quality.
In order to achieve the above purpose, the present invention is realized by adopting the following technical scheme: the automatic identification and early warning method for the micro-variation of the quality in the cigarette manufacturing process comprises a short-term quality early warning method and a long-term quality judgment method, wherein the short-term quality early warning method is realized by the following steps:
step 1, searching out batches meeting the conditions through system searching;
step 2, subtracting the ordered data from standard values respectively, and carrying out absolute value conversion on the difference values;
and step 3, sequencing the absolute value of the converted difference value from small to large, and then solving the rank.
Preferably, the long-term quality judging method is realized by the following steps:
step 1, searching production batches meeting the conditions;
step 2, designing a list man-machine interaction interface, wherein category attributes (factors A and B) can be designed into factor options according to requirements;
step 3, according to the judgment and selection of each index, combining with the preset index standard value to rapidly calculate the test statistic of the affected factor A and each affecting condition B C Variation results of (2);
and 4, performing independence test by using the list.
Preferably, in the step 1, the short-term quality early warning method is adopted, the batches meeting the conditions are searched through system searching, the batches without process shutdown and material breaking are searched through process flow standard deviation or variation coefficient and the like, and the average value calculated under the steady state condition of the searched batch index data is sorted from small to large.
Preferably, step 3, rank is calculated after sequencing the absolute value of the converted difference value from small to large; the specific method comprises the following steps: the corresponding rank sums with negative differences and the corresponding rank sums with positive differences are obtained respectively, meanwhile, the negative number (n 1) of differences and the positive number (n 2) of differences are counted, since the rank sum check table already prescribes the judgment boundary values (T1, T2) under the condition of (n 1, n 2), the smaller numbers of the rank sums and the larger numbers fall into the interval, the index is judged not to deviate (eta 1=eta 2), otherwise, the quality is proved to deviate when one rank sum falls outside the judgment boundary, the rank sum check table can distinguish the probability under the condition of given judgment boundary values (T1, T2), namely P (T1 < T2) =1-2 a, when the significance level a takes 0.05, P=0.9, T is the positive rank sum or the negative rank sum, and the judgment boundary values (T1, T2) under the condition of (n 1, n 2) can be written together.
Preferably, in the long-term quality judging method, in the step 2, designing a list man-machine interaction interface, for category attributes (factors a and B), factor B may be designed as required, and factor B may include year, month, quarter, group, shift and other choices, and each choice may be subdivided; factor a may include moisture, temperature, weight, circumference, etc., as well as each option may be subdivided into factors such as average, median.
Preferably, the step 4 of performing the independence test by using the list includes the following steps:
s1: establishing a hypothesis;
s2: determining a test statistic (n);
s3: the reject domain at significance level a=0.05 is W.
Preferably, said S1: establishing a hypothesis; h 0 The assumption is that factor A and factor B are independent of each other; h1 (alternative hypothesis): factor a and factor B are not independent of each other.
Preferably, said S2 determines a test statistic (n): the following method is adopted;
in the list belonging to A i Row and B j The expected data values for the column cross trellis are: e (E) ij ＝Q i. Q .j /n；
When the actual observation value Q ij And the expected value E ij When the difference is not large, the factor A and the factor B can be considered to be irrelevant or independent; if the difference is too large, the two factors cannot be considered to be irrelevant, so the chi-square statistic formula is selected as follows:
preferably, the reject domain at the S3 significance level a=0.05 is W; x-shaped articles 2 ＞χ 2 1-a ((r-1)(c-1))
After the chi-square result is obtained, if the test statistic does not fall in the reject domain, it is indicated that the factor A and the factor B have independence, whereas if the test statistic falls in the reject domain, it is indicated that the two factors have no independence, and the factor B affects the factor A.
The invention has the beneficial effects that:
and meanwhile, a plurality of indexes are selected and intensively judged by adopting the same method, so that index variation sources can be rapidly mastered, and accurate control on short-term or long-term quality is facilitated. The method has the advantages of high sensitivity and accuracy, simplicity and convenience in operation and the like, has certain use and popularization values, fills the gap of insufficient quality micro-change early warning and judging methods in the production process, provides a novel early warning method for process quality management work, and provides relevant basis for long-term stability and homogenization control of product quality.
Drawings
FIG. 1 is a flow chart of the automatic identification and early warning system of the quality micro-variation.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the production process data is transmitted to a database through an OPC protocol, the database performs quality analysis and determination according to an instructive program, and an administrator can grasp the quality deviation degree at the first time, so that emergency measures can be accurately made, for example: revising the judgment standard or deeply searching for the symptom and knot of the problem, etc.
In the quality judgment method, considering the short-term rapid quality judgment requirement of a production unit, a single-sample sign rank test method is selected under the condition that the sample size of batches is relatively small (less than or equal to 20 batches), the purpose of the single-sample sign rank test method is to establish whether short-term quality results are mutated, and long-term quality judgment is necessarily large-batch result mutation analysis under different conditions, so that quality management is guided, and therefore a list chi-square test method is selected.
2. Short-term quality early warning and long-term quality judgment implementation process
On the aspect of short-term quality early warning, a single-sample coincidence rank test method is adopted to automatically distinguish whether the actual result deviates from the standard value in a short period. When the quality standard values of various brands are known, it is expected that the results of all batches can be completely matched with the quality standard values, namely: if η1=η2, if η1++η2, it can be intuitively determined by the data appearance that the actual result deviates from the standard value? Obviously, it cannot be proved, but how to quickly distinguish the quality deviation, and the specific steps are as follows: firstly, searching out a batch meeting the conditions through a system search, for example: searching the batch without process shutdown according to the standard deviation of the process flow or the variation coefficient, and sorting the average value calculated under the steady state condition of the index data of the searched batch from small to large; secondly, subtracting the ordered data from standard values respectively, and carrying out absolute value conversion on the difference; then, the converted absolute values of the differences are ranked from small to large (the ranks are the positions with the sequence numbers 1, 2 and 3 of a group of data from small to large, when two or more than two identical data exist, the ranks are the average value of the digits of the identical data), and the corresponding rank sum with the negative difference and the corresponding rank sum with the positive difference are respectively obtained. Meanwhile, the number (n 1) with negative difference and the number (n 2) with positive difference are counted. Since the rank and test table has already specified the determination boundary value (T1, T2) under the condition of (n 1, n 2), the rank and the smaller number and the larger number can be determined that the index is not deviated (η1=η2) as long as they fall within the section, whereas a rank and a larger number fall outside the determination boundary to prove that the quality is deviated. The rank-sum test table can distinguish the probability given a decision boundary value (T1, T2), i.e. P (T1 < T2) =1-2 a, p=0.9 when the significance level a takes 0.05, T being the positive or negative rank sum. The determination boundary values (T1, T2) under the conditions (n 1, n 2) may be written together.
On the aspect of long-term quality early warning and judgment, the method for checking the list chi-square can realize the check whether the two factors are mutually independent. In the calculation of test statistics, data materials are classified by two criteria or attributes, and then all data materials can be assigned to a list. For example: the factor A represents different shifts (divided into white, medium and late), the factor B represents quality results (divided into two types: upward deviation and downward deviation), the calculated results can obtain corresponding frequency (for example, the batch index results of white shift production show that the actual results are higher than the Nh batch with a certain index standard value, the actual results are lower than the Nl batch with a certain index standard value, and the like), the collected data can be used for forming a column-linked list (as shown in a table 1-1), and in the implementation of a judging function, firstly, the production batch meeting the condition is searched, and the method is consistent with a single sample symbol rank searching method. Secondly, designing a list man-machine interaction interface (similar to the table 1-1), and designing factor options for category attributes (factors A and B) according to requirements, for example: factor B may include year, month, quarter, group, shift, etc., each of which may be subdivided, etc.; factor a may comprise moisture, temperature, weight, circumference, etc., as well as each option may be subdivided into factors such as average, median, etc. And then, carrying out background program calculation on index results of factors in the list, wherein the system can quickly calculate test statistics of the affected factor A and variation results of each influence condition BC according to judgment and selection of each index and combining with a preset index standard value.
TABLE 1-1 list of random samples
And (3) performing an independence test step by using a list table:
(1) Creating assumptions
H0 It is assumed that factor A and factor B are independent of each other
H1 (alternative hypothesis): factor A and factor B are not independent of each other
(2) Determination of test statistic (n)
The expected data values belonging to the Ai rows and Bj columns in the column-linked list are as follows: eij=qi.q.j/n
When the actual observed value Qij does not differ much from the expected value Eij, the factor a and the factor B may be considered to be uncorrelated or independent of each other; if the difference is too large, the two factors cannot be considered to be irrelevant, so we choose chi-square statistics:
(3) Reject domain at significance level a=0.05 is W:
χ 2 ＞χ 2 1-a ((r-1) (c-1))
after the chi-square result is obtained, if the test statistic does not fall in the reject domain, it is indicated that the factor A and the factor B have independence, whereas if the test statistic falls in the reject domain, it is indicated that the two factors have no independence, and the factor B affects the factor A.
When the program is designed, firstly, the reject domain with the significance level of a=0.05 or a=0.1 is recorded into a system as a W standard value, and when the quality is determined, the quality is only required to be called and compared according to the actual result.
When the test statistic falls in the reject domain, the chi-square result of several sub-items Bc of the factor B can be intuitively compared through the chi-square calculation result, the magnitude of the sub-item chi-square value and the deviation degree of the expected value and the actual value of each sub-item are judged to be the main variation source, so that the key variation is guided to be early-warned and treated.
4. Application instance
1. The first class wants to know the temperature control condition of the loose and moisture regained hot air of a certain brand in the week of the first class, and operates in a system: time selection, blade procedure, loosening and conditioning, hot air temperature average value, and after clicking and submitting, a list of average values of the number of first class loosening and conditioning hot air temperatures for one week (shown in table 4-1) is shown, and the index standard is known to be 65 ℃.
TABLE 4-1 Loose moisture regain Hot air temperature Single sample symbol rank test decision
2. And B, wanting to know the moisture control condition of cut tobacco shreds of a certain brand in the current middle class of the team, and operating in a system: time selection, cutting and baking process, shredder, average shredding moisture value, and after clicking and submitting, the average value list of the cut leaf moisture value of the current month of the brand of the second class appears (as shown in table 4-2), wherein the index standard is 20.5%.
TABLE 4-2 cut leaf shred moisture single sample symbol rank test decision results
3. The workshops want to know whether the drying temperature of the pneumatic dryer of a certain brand deviates in the last half year, and the workshops are verified by adopting a method of testing a list card square (shown in tables 4-3), wherein the index standard is 178 ℃. After searching, the batch number of non-shutdown broken materials is as follows: 1 month 19, 2 month 8, 3 month 24, 4 month 16, 5 month 14, 6 month 23.
TABLE 4-3 air drying temperature column-Table chi-square test determination results
The method has the advantages of high sensitivity and accuracy, simplicity and convenience in operation and the like, has certain use and popularization values, fills the gap of insufficient quality micro-change early warning and judging methods in the production process, provides a novel early warning method for process quality management work, and provides relevant basis for long-term stability and homogenization control of product quality.
Finally, it is noted that the above-mentioned preferred embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the invention, which has been described in detail by means of the above-mentioned preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the invention.
Claims (1)
1. A method for automatically identifying and early warning quality micro-variation in a cigarette manufacturing process is characterized in that: the automatic identification and early warning method for the quality micro-variation in the cigarette manufacturing process comprises a short-term quality early warning method and a long-term quality judgment method, wherein the short-term quality early warning method is realized by the following steps:
step 1, searching out batches meeting the conditions through a system, searching out batches without process shutdown according to standard deviation, variation coefficient and the like of process flow, and sequencing the average value calculated under the steady state condition of the index data of the searched batches from small to large;
step 2, subtracting the ordered data from standard values respectively, and carrying out absolute value conversion on the difference values;
step 3, sequencing the absolute value of the converted difference value from small to large, and then solving the rank; rank is a group of data from small to large ordered position numbers 1, 2, 3..n, when there are two or more identical data, their rank is the average value of the number of bits of the identical data; respectively solving a corresponding rank sum with a negative difference value and a corresponding rank sum with a positive difference value, and simultaneously counting a negative number n1 of difference values and a positive number n2 of difference values, wherein the rank sum check table already prescribes the judgment boundary values (T1, T2) under the conditions of the number n1 and the number n2, the smaller number of the rank sum and the larger number only fall into the interval, so that the index is judged not to deviate from eta 1=eta 2, otherwise, the quality is proved to deviate when one rank sum falls outside the judgment boundary, the rank sum check table can distinguish the probability under the condition of the given judgment boundary values (T1, T2), namely P (T1 < T2) =1-2 a, when the significance level a is 0.05, P=0.9, the smaller number of the rank sum and the larger number of the judgment boundary values (T1, T2), and the smaller number of the rank sum and the larger number only need to write the program together with the judgment boundary values (T1, T2) under the condition of the significance level a;
the long-term quality judging method is realized by the following steps:
step 1, searching production batches meeting the conditions;
step 2, designing a list man-machine interaction interface, and designing a factor selection item according to the requirement on the category attribute; the category attributes include a factor a and a factor B; factor B includes year, month, quarter, team, shift; factor a comprises moisture, temperature, weight, circumference;
step 3, according to the judgment and selection of each index, combining with the preset index standard value to rapidly calculate the test statistic of the affected factor A and each affecting condition B c Variation results of (2);
step 4, performing independence test by using the list;
the step 4 of performing the independence test by using the list comprises the following steps:
s1: creating assumptions
Original assumption H 0 : factor a and factor B are independent of each other;
alternative hypothesis H 1 : factor a and factor B are not independent of each other;
s2: determining test statistic n
In the list belonging to A i Row and B j The expected data values for the column cross trellis are: eij=qi.q.j/n; when the actual observed value Qiaj is different from the expected value EijWhen large, the factor A is not related to the factor B, or is independent of the factor B; if the phase difference is too large, a chi-square statistic formula is selected:
s3: reject domain at significance level a=0.05 is W; x-shaped articles 2 >χ 2 1-a ((r-1)(c-1))；
After the chi-square result is obtained, if the test statistic does not fall in the reject domain, the factor A and the factor B have independence, whereas if the test statistic falls in the reject domain, the factor A and the factor B have no independence, and the factor B affects the factor A.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110931006.0A CN113743744B (en) | 2021-08-13 | 2021-08-13 | Automatic identification and early warning method for quality micro-variation in cigarette manufacturing process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110931006.0A CN113743744B (en) | 2021-08-13 | 2021-08-13 | Automatic identification and early warning method for quality micro-variation in cigarette manufacturing process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113743744A CN113743744A (en) | 2021-12-03 |
| CN113743744B true CN113743744B (en) | 2024-02-23 |
Family
ID=78731087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110931006.0A Active CN113743744B (en) | 2021-08-13 | 2021-08-13 | Automatic identification and early warning method for quality micro-variation in cigarette manufacturing process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743744B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7047208B1 (en) * | 2001-08-16 | 2006-05-16 | Honda Motor Co., Ltd. | System and method for detecting supplier instability |
| CN103616878A (en) * | 2013-12-03 | 2014-03-05 | 山东中烟工业有限责任公司 | System and method for detecting on-line state of feeding loop in tobacco processing process |
| CN107220907A (en) * | 2017-06-10 | 2017-09-29 | 福州大学 | A kind of harmonic pollution user stage division of use sum of ranks than overall merit |
| CN110544049A (en) * | 2019-09-11 | 2019-12-06 | 贵州省烟草公司六盘水市公司 | monitoring and early warning method, system and device based on real-time data of cigarette operation inner tube |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020039990A1 (en) * | 1998-07-20 | 2002-04-04 | Stanton Vincent P. | Gene sequence variances in genes related to folate metabolism having utility in determining the treatment of disease |
| US9342297B2 (en) * | 2013-06-07 | 2016-05-17 | Capital One Financial Corporation | Systems and methods for providing predictive quality analysis |
-
2021
- 2021-08-13 CN CN202110931006.0A patent/CN113743744B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7047208B1 (en) * | 2001-08-16 | 2006-05-16 | Honda Motor Co., Ltd. | System and method for detecting supplier instability |
| CN103616878A (en) * | 2013-12-03 | 2014-03-05 | 山东中烟工业有限责任公司 | System and method for detecting on-line state of feeding loop in tobacco processing process |
| CN107220907A (en) * | 2017-06-10 | 2017-09-29 | 福州大学 | A kind of harmonic pollution user stage division of use sum of ranks than overall merit |
| CN110544049A (en) * | 2019-09-11 | 2019-12-06 | 贵州省烟草公司六盘水市公司 | monitoring and early warning method, system and device based on real-time data of cigarette operation inner tube |
Non-Patent Citations (6)
| Title |
|---|
| 卷烟生产质量风险预警体系研究;陈恩;谷德良;李学;刘馨;;当代经济(第06期);全文 * |
| 基于秩和比综合评价法的用户谐波危害分级评估;周琪琪;邵振国;林韩;;电力电容器与无功补偿(第05期);全文 * |
| 妊娠期体质量变化的相关研究;叶立;;检验医学与临床(第19期);全文 * |
| 环境空气质量预警方法的探讨;耿建生;;三峡环境与生态(第03期);全文 * |
| 秩和比法在春运期间车站候车室空气质量综合评价中的应用;谷玉祥;孙齐蕊;孙爱峰;;中国卫生产业(第03期);全文 * |
| 统计技术在环锭纺纱捻度设计及品质控制上的应用;朱松;;聚酯工业(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113743744A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108764597A (en) | A kind of product quality control method based on integrated study | |
| CN115630839B (en) | Intelligent feedback production regulation and control system based on data mining | |
| CN109406984B (en) | Intelligent test analysis method for integrated circuit full ecological chain | |
| CN111103854A (en) | System and method for improving production stability of tobacco cut-tobacco drier | |
| CN112749763B (en) | Time series classification analysis method and system for glass quality influence factors | |
| CN106529580A (en) | EDSVM-based software defect data association classification method | |
| CN115083549B (en) | Product raw material ratio reverse derivation method based on data mining | |
| Ou et al. | First time quality diagnostics and improvement through data analysis: A study of a crankshaft line | |
| CN111882188A (en) | Process quality homogeneity level evaluation method and system based on Birch clustering algorithm | |
| CN107944487B (en) | Crop breeding variety recommendation method based on mixed collaborative filtering algorithm | |
| CN113743744B (en) | Automatic identification and early warning method for quality micro-variation in cigarette manufacturing process | |
| Ginting et al. | Proposed Improvement of Flour Quality by using New Seven Tools Method (Case Study: XYZ Company) | |
| CN106681204A (en) | On-line production quality inspection system and method | |
| CN108537249B (en) | Industrial process data clustering method for density peak clustering | |
| CN110320872B (en) | Method for improving standard production of cigarette mainstream smoke indexes | |
| CN112183876A (en) | Yield loss root cause analysis method based on information fusion | |
| CN112837754B (en) | Method and device for automatically classifying single cells based on characteristic genes | |
| Buschmann et al. | Data-driven decision support for process quality improvements | |
| CN110348480A (en) | A kind of non-supervisory anomaly data detection algorithm | |
| CN110659691A (en) | Method and device for monitoring quality and style of tobacco leaf raw material and computer readable storage medium | |
| CN114912898A (en) | System for rapidly analyzing equipment difference root cause in semiconductor manufacturing | |
| US20240004375A1 (en) | Data processing method, and electronic device and storage medium | |
| TWI822262B (en) | Data processing method, data processing apparatus, data processing system, and computer program products | |
| CN113537356A (en) | Map-based bad root cause analysis method | |
| Anaya et al. | Yield improvement using advanced data analytics |
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 |