CN102591267A - Method for monitoring quality of production process by using target - Google Patents
Method for monitoring quality of production process by using target Download PDFInfo
- Publication number
- CN102591267A CN102591267A CN2011102865159A CN201110286515A CN102591267A CN 102591267 A CN102591267 A CN 102591267A CN 2011102865159 A CN2011102865159 A CN 2011102865159A CN 201110286515 A CN201110286515 A CN 201110286515A CN 102591267 A CN102591267 A CN 102591267A
- Authority
- CN
- China
- Prior art keywords
- line
- target
- quality
- characteristic value
- distribution curve
- 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
Images
Classifications
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for monitoring the quality of a production process by using a target. The method comprises the following steps of: firstly, determining a production quality target according to technical requirements of customers, i.e. an upper limit TU and a lower limit TL of a target quality characteristic value; secondly, selecting a process performance index (PPK); thirdly, establishing a target monitoring diagram, wherein the target monitoring diagram comprises an indication line part and a target distribution curve, the target distribution curve is positioned on the left side of a coordinate system and indication lines comprise six transverse lines, i.e. an upper specification line, a lower specification line, an upper warning line, a lower warning line, an upper high-quality product line and a lower high-quality product line; fourthly, dotting, producing point connecting lines, an average value vernier and a production quality characteristic value actual distribution curve in the target monitoring diagram according to the actually-determined production quality characteristic value; and fifthly, judging the target achieving effect. According to the method, the establishment process of the target monitoring diagram is simple; the production process is constrained by using the target monitoring diagram, so that the stability and the excellence of the production quality are ensured; and the method is especially suitable for enterprises for processing materials supplied by clients and small-batch production.
Description
Technical field
The present invention relates to a kind of quality control method, it is to come the monitoring industrial processes method for quality with target, to reach or near being dbjective state.Be specially adapted to guarantee the quality monitoring under stable production process or the less situation of batch, also can be used for the checking of quality analysis and improvement effect.
Background technology
(1) wave pattern
Wave pattern is applicable to be observed in the quality control and the up to standard and fluctuation situation of analysis quality characteristic value, so that control and improve quality.It has simple in structure, direct characteristics, but it is a kind of quality monitoring instrument of extensive property.
(2) shewhart control chart
The principle of control chart is the small probability event principle.It is wide, highly sensitive that it has usable range; But implementation process is complicated, workload is big; Prepare data, judge whether be in statistical Process Control state and technological stable state, and control line is wanted periodic maintenance; Therefore its quantity of information still is weak, and can't under non-statistical process control state and technological stable state or less in batches situation, use.
Summary of the invention
The objective of the invention is to guaranteeing stable production process or the in batches quality monitoring under the less situation, proposed a kind ofly to come the monitoring industrial processes method for quality with target.
Technical scheme of the present invention is: a kind ofly come the monitoring industrial processes method for quality with target, comprise the steps:
1. confirm quality of production target according to client's technical requirement, i.e. the upper limit T of aimed quality characteristic value
U, lower limit T
L,
2. select operation performance index P
PK
3. set up target monitoring figure, this figure is a rectangular coordinate system, and its transverse axis is a time shaft, and vertical pivot is the quality characteristic value axle;
This target monitoring figure comprises index line part and target distribution curve, and the target distribution curve is positioned at the left side of coordinate system;
Described index line has six horizontal lines, comprises upper and lower gauge wire (also claiming acceptance line), in outermost; Upper and lower warning line (also claiming the Grade A line, in the inferior outside), upper and lower high-class product line are in specification center line both sides; The specification center line; Above-mentioned index line passes through target width, i.e. the upper limit T of aimed quality characteristic value
U, lower limit T
LBetween six five equilibriums get;
Gauge wire, last gauge wire T
U, following gauge wire T
L,
Warning line, last warning line
is warning line
down
The high-class product line, last high-class product line
is high-class product line
down
The specification center line,
Said target distribution curve is according to aimed quality characteristic value bound (T
U, T
L) and the operation performance index P that selects
PKSet up;
Under the perfect condition (being dbjective state), quality characteristic value mean value overlaps with quality characteristic value bound center, by operation performance index formula:
P in the formula
PKBe the operation performance index, S is a sample standard deviation, and the operation performance index is confirmed, can calculate the sample standard deviation of requirement, estimates standard deviation in population σ with sample standard deviation S, because the distribution of perfect condition followed normal distribution, by normpdf:
(average μ equals aimed quality characteristic value bound center to-∞＜x＜∞ in the formula, promptly
), mark the target distribution curve;
4. in above-mentioned target monitoring figure, get, make a connecting line, mean value vernier and quality of production characteristic value actual distribution curve ready according to the quality of production characteristic value of practical measurement in a period of time,
The data of a. regularly sampling and measuring according to time sequencing for the laboratory are directly got quality of production characteristic value ready in rectangular coordinate system; For the continuous data that on-line instrument is measured, calculate quartile, draw the case line chart and come out the information representation of a period of time data;
B. with broken line the median of the point of coordinate system or case line is coupled together and form a some connecting line;
C. calculate moving average, showing in coordinate system with short-term simultaneously forms the mean value vernier;
D. the quality of production characteristic value actual distribution curve of adding up and draw;
The upper limit, the lower limit of quality of production characteristic value are divided between several region;
The quality characteristic value that calculating records is at each interval frequency N that occurs;
Calculate each frequency sum M;
Calculate the percentage amount of the influence W of each interval frequency N that occurs,
With each interval central point characteristic value is ordinate, and W is a horizontal ordinate, in coordinate system, marks the actual distribution curve;
5. judge the effect of realization of goal
A. qualitative objective effect:
Through the accordance of eyesight identification quality of production characteristic value actual distribution curve and target distribution curve, confirm the realization of goal effect;
B. quantitative objective effect:
Confirm the realization of goal effect through calculating the target degree of conformity;
Operation performance index P under the frequency percentage amount of influence sum+normal distribution situation that the frequency percentage amount of influence W of each interval correspondence is corresponding with outer each interval of coefficient of correspondence multiplied result sum-aimed quality characteristic value bound in target degree of conformity=aimed quality characteristic value bound
PKPairing disqualification rate;
Following table is each interval institute coefficient of correspondence in the aimed quality characteristic value bound after normalization is handled;
Coefficient * p (x) row sum equals 100
Described productive target is done normalization and is handled, and below is limited to 0, on be limited to 1, six five equilibriums then;
The normalization processing formula:
wherein X needs normalized variable;
Corresponding index line of setting up after the normalization and target distribution curve:
Gauge wire, last gauge wire 1, gauge wire 0 down;
Warning line, last warning line 0.5+1/3, following warning line 0.5-1/3;
The high-class product line, last high-class product line 0.5+1/6, following high-class product line 0.5-1/6;
The specification center line is 0.5;
Corresponding quality of production characteristic value is also done normalization and is handled, and the corresponding quality of production characteristic value actual distribution curve that draws.
This method also comprises declares different rule.
According to the small probability event principle: small probability event possibly take place in single test hardly, if take place promptly to judge unusual, according to 6 times of standard deviations controls such as mass property index width, like Fig. 2, produces the following different rule of declaring:
Criterion 1: any drops on beyond the gauge wire, makes a false report alarm probability 0.27%,
Prompting: any drops on beyond the gauge wire, shows to have the phenomenon that exceeds standard, and should in time adjust;
Criterion 2: have in continuous 3 beyond 2 warning lines that drop on the same side, make a false report alarm probability 0.046%,
Prompting: have in continuous 3 beyond 2 warning lines that drop on the same side, it is unusual to show that control exists, and has the one-sided possibility of deflection, should in time adjust;
Criterion 3: beyond continuous 2 warning lines that drop on homonymy not, make a false report alarm probability 0.18%,
Prompting: beyond continuous 2 warning lines that drop on homonymy not, show that quality fluctuation is bigger, should ascertain the reason, in time adjustment;
Criterion 4: continuous 9 are dropped on specification center line the same side, make a false report alarm probability 0.3906%,
Prompting: continuous 9 are dropped on specification center line the same side, show control center's central value that departs from objectives, and should in time adjust;
Criterion 5: continuous 6 increasing or decreasings, make a false report alarm probability 0.2733%,
Prompting: continuous 6 increasing or decreasings, it is unusual to show that equipment or control exist, and should ascertain the reason, and in time gets rid of or adjustment;
Criterion 6: have in continuous 5 beyond 4 high-class product lines that drop on the same side, make a false report alarm probability 0.5331%,
Prompting: have in continuous 5 beyond 4 high-class product lines that drop on the same side, show that control center and target's center's value deviation are bigger, one-sided in short-term departing from occur, should in time adjust control center;
Above-mentioned various false declaration police adopts alarm point to represent in target monitoring figure, and alarm point is positioned at the top of index line part.
Also have the numerical value display part among the described target monitoring figure, tabulation shows quality of production characteristic value.
This method also comprises the steps, adopts the mode that shows in real time to offer by the operation teams and groups or the workman of sampling Detection in the figure of above-mentioned foundation.
Beneficial effect of the present invention
The present invention realizes the quality control of production run through setting up target monitoring figure; This target monitoring figure is exactly the defective to wave pattern and shewhart control chart existence; Absorb its advantage, abandon its deficiency; On the basis of " target control theory " and actual tests for many years and experience deposition, introduce rate of classification of product line, create according to normal distribution and small probability event principle.
It has directly, quick, the characteristics that contain much information; Be suitable for the mass property monitoring with " upper and lower limit " of Normal Distribution; Be specially adapted to guarantee the quality monitoring under stable production process or the less situation of batch, mainly take process fine setting measure to realize target distribution.
The foundation of target monitoring figure is before production is carried out in this method; Need from production run, produce unlike other control chart, this target monitoring figure is particularly suitable for processing with foreign materials enterprise, and production run changes with different customer requirements at any time; Process is difficult to stablize; Utilize other control chart to come monitoring industrial processes, possible production run is through with, and control chart does not also have enough time to set up.
Accompanying drawing 2-6 has reflected the effect directly perceived of utilizing this control chart to carry out the production run quality control through the contrast of statistics.
The target monitoring figure of employing method carries out the control of production run; Simplified the process that control chart is set up; Can be that target is set up control chart directly according to customer demand; Utilize this control chart to go to retrain production run then, can guarantee the stability and the superiority of the quality of production, especially suitable for processing with foreign materials enterprise and small serial production.
This target monitoring figure not only comprises index line part and distribution curve, also comprises mean value vernier, alarm point in addition, can give expression to various information, and intuitive is strong, is convenient to understand.
Set up in the process of target monitoring figure quality characteristic value carried out normalization and handles after; Can the production run of different batches be unified; Be more conducive to the enforcement of this target monitoring figure; For workman and managerial personnel, more directly perceived to the understanding of production run quality (quality is the optimum value that departing from of desired value is obtained through reducing to greatest extent---Japanese quality management scholar field mouth profound).
Description of drawings
Fig. 1 is the structural representation of this target monitoring figure;
Fig. 2 is the different synoptic diagram of declaring of this target monitoring figure;
The qualitative evaluation of the production run quality situation when Fig. 3 comes the monitoring industrial processes method for quality for first teams and groups do not use with target;
The qualitative evaluation of the production run quality situation when Fig. 4 comes the monitoring industrial processes method for quality for the use of first teams and groups with target;
The qualitative evaluation of the production run quality situation when Fig. 5 comes the monitoring industrial processes method for quality for second teams and groups do not use with target;
The qualitative evaluation of the production run quality situation when Fig. 6 comes the monitoring industrial processes method for quality for the use of second teams and groups with target.
Transverse axis is a time shaft among Fig. 1; Vertical pivot is the quality characteristic value axle; The dotted line of centre wherein is the mean value line of target property value; Solid line near mean value line both sides is respectively upper and lower high-class product line, and the solid line line in the high-class product line outside is upper and lower warning line, and outermost solid line is upper and lower gauge wire.
Asterisk is an alarm point among Fig. 1, and the curve that the solid line on right side forms is the target distribution curve, and the curve that dotted line forms is a quality of production characteristic value actual distribution curve, and the rectangle stick is the mean value vernier.
Fig. 1 raising middle flask line chart " zero " is represented gentle exceptional value.The case line chart, following horizontal line is the minimum mass characteristic value, i.e. zero-bit or lower limb; Last horizontal line is a biggest quality characteristic value, i.e. 100% figure place or coboundary, and the nowel line is 25% quality characteristic value or lower quartile; The top box line is 75% quality characteristic value or upper quartile, and horizontal line is that 50% figure place is meta quality characteristic value, i.e. median in the case; Upper quartile subtracts lower quartile and is called interquartile-range IQR, exceeds median ± 1.5 times interquartile-range IQR, and is called gentle exceptional value less than median ± 3 a times interquartile-range IQR; Represent with zero, exceed median ± 3 a times interquartile-range IQR and claim extreme exceptional value, represent with *
Embodiment
Embodiment: a kind ofly come the monitoring industrial processes method for quality, comprise the steps: with target
1. confirm quality of production target according to customer requirement, i.e. the upper limit T of aimed quality characteristic value
U, lower limit T
LSome client can directly propose two borders of the upper limit, lower limit of aimed quality characteristic value in actual production; But also exist the part client only to propose one of them border,, can draft out the rational border of another one according to this operation and the concrete condition of self for this situation.
2. select operation performance index P
PK
3. set up target monitoring figure, this figure is a rectangular coordinate system, and its transverse axis is a time shaft, and vertical pivot is the quality characteristic value axle;
This target monitoring figure comprises index line part and target distribution curve, and the target distribution curve is positioned at the left side of coordinate system;
Described index line has six horizontal lines, comprises upper and lower gauge wire (also claiming acceptance line), in outermost; Upper and lower warning line (also claiming the Grade A line, in the inferior outside), upper and lower high-class product line are in specification center line both sides; The specification center line; Above-mentioned index line passes through target width, i.e. the upper limit T of aimed quality characteristic value
U, lower limit T
LBetween six five equilibriums get;
Gauge wire, last gauge wire T
U, following gauge wire T
L,
Warning line, last warning line
is warning line
down
The high-class product line, last high-class product line
is high-class product line
down
The specification center line,
Said target distribution curve is according to aimed quality characteristic value bound (T
U, T
L) and the operation performance index P that selects
PKSet up;
Under the perfect condition (being dbjective state), quality characteristic value mean value overlaps with quality characteristic value bound center, by operation performance index formula:
P in the formula
PKBe the operation performance index, S is a sample standard deviation, and the operation performance index is confirmed, can calculate the sample standard deviation of requirement, estimates standard deviation in population σ with sample standard deviation S, because the distribution of perfect condition followed normal distribution, by normpdf:
(average μ equals aimed quality characteristic value bound center to-∞＜x＜∞ in the formula, promptly
), mark the target distribution curve;
4. in above-mentioned target monitoring figure, get, make a connecting line, mean value vernier and quality of production characteristic value actual distribution curve ready according to the quality of production characteristic value of practical measurement in a period of time,
The data of a. regularly sampling and measuring according to time sequencing for the laboratory are directly got quality of production characteristic value ready in rectangular coordinate system; For the continuous data that on-line instrument is measured, calculate quartile, draw the case line chart and come out the information representation of a period of time data;
B. with broken line the median of the point of coordinate system or case line is coupled together and form a some connecting line;
C. calculate moving average, showing in coordinate system with short-term simultaneously forms the mean value vernier;
D. the quality of production characteristic value actual distribution curve of adding up and draw;
The upper limit, the lower limit of quality of production characteristic value are divided between several region;
The quality characteristic value that calculating records is at each interval frequency N that occurs;
Calculate each frequency sum M;
Calculate the percentage amount of the influence W of each interval frequency N that occurs,
With each interval mid point characteristic value is ordinate, and W is a horizontal ordinate, in coordinate system, marks the actual distribution curve;
5. judge the effect of realization of goal
A. qualitative objective effect:
Through the accordance of eyesight identification quality of production characteristic value actual distribution curve and target distribution curve, confirm the realization of goal effect;
B. quantitative objective effect:
Confirm the realization of goal effect through calculating the target degree of conformity;
Operation performance index P under the frequency percentage amount of influence sum+normal distribution situation that the frequency percentage amount of influence W of each interval correspondence is corresponding with outer each interval of coefficient of correspondence multiplied result sum-aimed quality characteristic value bound in target degree of conformity=aimed quality characteristic value bound
PKPairing disqualification rate;
Following table is each interval institute coefficient of correspondence in the aimed quality characteristic value bound after normalization is handled;
Coefficient * p (x) row sum equals 100
Concrete can do normalization with productive target recited above and handle referring to accompanying drawing 1, below is limited to 0, on be limited to 1, six five equilibriums then;
The normalization processing formula:
wherein X needs normalized variable;
Corresponding index line of setting up after the normalization and target distribution curve:
Gauge wire, last gauge wire 1, gauge wire 0 down; Represent with solid line among the figure.
Warning line, last warning line 0.5+1/3, following warning line 0.5-1/3; Represent with double dot dash line among the figure.
The high-class product line, last high-class product line 0.5+1/6, following high-class product line 0.5-1/6; Represent with dot-and-dash line among the figure.
The specification center line is 0.5; The with dashed lines line is represented among the figure.
Represent with block curve in the target distribution curve map.
Corresponding quality of production characteristic value is also done normalization and is handled, and the with dashed lines corresponding quality of production characteristic value actual distribution curve that draws.
This method also comprises declares different rule,
According to the small probability event principle: small probability event possibly take place in single test hardly, if take place promptly to judge unusual, according to 6 times of standard deviations controls such as mass property index width, like Fig. 2, produces the following different rule of declaring:
Criterion 1: any drops on beyond the gauge wire, makes a false report alarm probability 0.27%,
Prompting: any drops on beyond the gauge wire, shows to have the phenomenon that exceeds standard, and should in time adjust;
Criterion 2: have in continuous 3 beyond 2 warning lines that drop on the same side, make a false report alarm probability 0.046%,
Prompting: have in continuous 3 beyond 2 warning lines that drop on the same side, it is unusual to show that control exists, and has the one-sided possibility of deflection, should in time adjust;
Criterion 3: beyond continuous 2 warning lines that drop on homonymy not, make a false report alarm probability 0.18%,
Prompting: beyond continuous 2 warning lines that drop on homonymy not, show that quality fluctuation is bigger, should ascertain the reason, in time adjustment;
Criterion 4: continuous 9 are dropped on specification center line the same side, make a false report alarm probability 0.3906%,
Prompting: continuous 9 are dropped on specification center line the same side, show control center's central value that departs from objectives, and should in time adjust;
Criterion 5: continuous 6 increasing or decreasings, make a false report alarm probability 0.2733%,
Prompting: continuous 6 increasing or decreasings, it is unusual to show that equipment or control exist, and should ascertain the reason, and in time gets rid of or adjustment;
Criterion 6: have in continuous 5 beyond 4 high-class product lines that drop on the same side, make a false report alarm probability 0.5331%,
Prompting: have in continuous 5 beyond 4 high-class product lines that drop on the same side, show that control center and target's center's value deviation are bigger, one-sided in short-term departing from occur, should in time adjust control center;
Above-mentioned various false declaration police adopts alarm point to represent in target monitoring figure, and alarm point is positioned at the top of index line part, and the asterisk among Fig. 1 is the warning point.
Also have the numerical value display part among the described target monitoring figure, tabulation shows quality of production characteristic value.This tabulation display part shows the setting area separately.
This method also comprises the steps, adopts the mode that shows in real time to offer by the operation teams and groups or the workman of sampling Detection in the figure of above-mentioned foundation.
Claims (5)
1. one kind is come the monitoring industrial processes method for quality with target, comprises the steps:
1. confirm quality of production target according to client's technical requirement, i.e. the upper limit T of aimed quality characteristic value
U, lower limit T
L,
2. select operation performance index P
PK
3. set up target monitoring figure, this figure is a rectangular coordinate system, and its transverse axis is a time shaft, and vertical pivot is the quality characteristic value axle;
This target monitoring figure comprises index line part and target distribution curve, and the target distribution curve is positioned at the left side of coordinate system;
Described index line has six horizontal lines, comprises upper and lower gauge wire (also claiming acceptance line), in outermost; Upper and lower warning line (also claiming the Grade A line, in the inferior outside), upper and lower high-class product line are in specification center line both sides; The specification center line; Above-mentioned index line passes through target width, i.e. the upper limit T of aimed quality characteristic value
U, lower limit T
LBetween six five equilibriums get;
Gauge wire, last gauge wire T
U, following gauge wire T
L,
Warning line, last warning line
is warning line
down
The high-class product line, last high-class product line
is high-class product line
down
The specification center line,
Said target distribution curve is according to aimed quality characteristic value bound (T
U, T
L) and the operation performance index P that selects
PKSet up;
Under the perfect condition (being dbjective state), quality characteristic value mean value overlaps with quality characteristic value bound center, by operation performance index formula:
P in the formula
PKBe the operation performance index, S is a sample standard deviation, and the operation performance index is confirmed, can calculate the sample standard deviation of requirement, estimates standard deviation in population σ with sample standard deviation S, because the distribution of perfect condition followed normal distribution, by normpdf:
(average μ equals aimed quality characteristic value bound center to-∞＜x＜∞ in the formula, promptly
), mark the target distribution curve;
4. in above-mentioned target monitoring figure, get, make a connecting line, mean value vernier and quality of production characteristic value actual distribution curve ready according to the quality of production characteristic value of practical measurement in a period of time,
The data of a. regularly sampling and measuring according to time sequencing for the laboratory are directly got quality of production characteristic value ready in rectangular coordinate system; For the continuous data that on-line instrument is measured, calculate quartile, draw the case line chart and come out the information representation of a period of time data;
B. with broken line the median of the point of coordinate system or case line is coupled together and form a some connecting line;
C. calculate moving average, showing in coordinate system with short-term simultaneously forms the mean value vernier;
D. the quality of production characteristic value actual distribution curve of adding up and draw;
The upper limit, the lower limit of quality of production characteristic value are divided between several region;
The quality characteristic value that calculating records is at each interval frequency N that occurs;
Calculate each frequency sum M;
Calculate the percentage amount of the influence W of each interval frequency N that occurs,
With each interval central point characteristic value is ordinate, and W is a horizontal ordinate, in coordinate system, marks the actual distribution curve;
5. judge the effect of realization of goal
A. qualitative objective effect:
Through the accordance of eyesight identification quality of production characteristic value actual distribution curve and target distribution curve, confirm the realization of goal effect;
B. quantitative objective effect:
Confirm the realization of goal effect through calculating the target degree of conformity;
Operation performance index P under the frequency percentage amount of influence sum+normal distribution situation that the frequency percentage amount of influence W of each interval correspondence is corresponding with outer each interval of coefficient of correspondence multiplied result sum-aimed quality characteristic value bound in target degree of conformity=aimed quality characteristic value bound
PKPairing disqualification rate;
Following table is each interval institute coefficient of correspondence in the aimed quality characteristic value bound after normalization is handled;
Coefficient * p (x) row sum equals 100.
2. according to claim 1ly come the monitoring industrial processes method for quality with target, it is characterized in that: described productive target is done normalization and is handled, and below is limited to 0, on be limited to 1, six five equilibriums then;
The normalization processing formula:
wherein X needs normalized variable;
Corresponding index line of setting up after the normalization and target distribution curve:
Gauge wire, last gauge wire 1, gauge wire 0 down;
Warning line, last warning line 0.5+1/3, following warning line 0.5-1/3;
The high-class product line, last high-class product line 0.5+1/6, following high-class product line 0.5-1/6;
The specification center line is 0.5;
Corresponding quality of production characteristic value is also done normalization and is handled, and the corresponding quality of production characteristic value actual distribution curve that draws.
3. according to claim 1 and 2ly come the monitoring industrial processes method for quality with target, it is characterized in that: this method also comprises declares different rule.
According to the small probability event principle: small probability event possibly take place in single test hardly, if take place promptly to judge unusual, according to 6 times of standard deviations controls such as mass property index width, like Fig. 2, produces the following different rule of declaring:
Criterion 1: any drops on beyond the gauge wire, makes a false report alarm probability 0.27%,
Prompting: any drops on beyond the gauge wire, shows to have the phenomenon that exceeds standard, and should in time adjust;
Criterion 2: have in continuous 3 beyond 2 warning lines that drop on the same side, make a false report alarm probability 0.046%,
Prompting: have in continuous 3 beyond 2 warning lines that drop on the same side, it is unusual to show that control exists, and has the one-sided possibility of deflection, should in time adjust;
Criterion 3: beyond continuous 2 warning lines that drop on homonymy not, make a false report alarm probability 0.18%,
Prompting: beyond continuous 2 warning lines that drop on homonymy not, show that quality fluctuation is bigger, should ascertain the reason, in time adjustment;
Criterion 4: continuous 9 are dropped on specification center line the same side, make a false report alarm probability 0.3906%,
Prompting: continuous 9 are dropped on specification center line the same side, show control center's central value that departs from objectives, and should in time adjust;
Criterion 5: continuous 6 increasing or decreasings, make a false report alarm probability 0.2733%,
Prompting: continuous 6 increasing or decreasings, it is unusual to show that equipment or control exist, and should ascertain the reason, and in time gets rid of or adjustment;
Criterion 6: have in continuous 5 beyond 4 high-class product lines that drop on the same side, make a false report alarm probability 0.5331%,
Prompting: have in continuous 5 beyond 4 high-class product lines that drop on the same side, show that control center and target's center's value deviation are bigger, one-sided in short-term departing from occur, should in time adjust control center;
Above-mentioned various false declaration police adopts alarm point to represent in target monitoring figure, and alarm point is positioned at the top of index line part.
4. according to claim 3ly come the monitoring industrial processes method for quality with target, it is characterized in that: also have the numerical value display part among the described target monitoring figure, tabulation shows quality of production characteristic value.
5. according to claim 4ly come the monitoring industrial processes method for quality with target, it is characterized in that: this method also comprises the steps, adopts the mode that shows in real time to offer by the operation teams and groups or the workman of sampling Detection in the figure of above-mentioned foundation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102865159A CN102591267A (en) | 2011-09-23 | 2011-09-23 | Method for monitoring quality of production process by using target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102865159A CN102591267A (en) | 2011-09-23 | 2011-09-23 | Method for monitoring quality of production process by using target |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102591267A true CN102591267A (en) | 2012-07-18 |
Family
ID=46480098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102865159A Pending CN102591267A (en) | 2011-09-23 | 2011-09-23 | Method for monitoring quality of production process by using target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102591267A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503416A (en) * | 2015-01-01 | 2015-04-08 | 韩杰 | Method and equipment for performing subsection quality control on objects on production line |
| CN107256001A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | The improved algorithm for weighing manufacturing process multivariate quality ability |
| CN107256000A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | Algorithm of the improved Domain Volume than weighing manufacturing process multivariate quality ability |
| CN107272611A (en) * | 2017-05-27 | 2017-10-20 | 四川用联信息技术有限公司 | A kind of algorithm for weighing manufacture procedure quality ability |
| CN107291065A (en) * | 2017-05-27 | 2017-10-24 | 四川用联信息技术有限公司 | The improved manufacturing process multivariate quality diagnostic classification device based on decision tree |
| CN107390667A (en) * | 2017-05-27 | 2017-11-24 | 四川用联信息技术有限公司 | Manufacturing process multivariate quality diagnostic classification device based on decision tree |
| CN109753027A (en) * | 2017-11-08 | 2019-05-14 | 阿里巴巴集团控股有限公司 | It is a kind of industry manufacture in parameter monitoring method and device |
| CN110084449A (en) * | 2018-01-25 | 2019-08-02 | 红塔烟草(集团)有限责任公司 | Standardization and evaluation system and its method based on cigarette batch data |
| CN112116014A (en) * | 2020-09-24 | 2020-12-22 | 贵州电网有限责任公司 | Test data outlier detection method for distribution automation equipment |
| CN114384872A (en) * | 2021-12-02 | 2022-04-22 | 北京能科瑞元数字技术有限公司 | Product development process quality comprehensive management and control system |
| CN115238421A (en) * | 2022-09-23 | 2022-10-25 | 中国人民解放军国防科技大学 | Method and device for designing charging configuration of multi-pulse gas generator and computer equipment |
| CN115619262A (en) * | 2022-10-11 | 2023-01-17 | 联宝(合肥)电子科技有限公司 | Quality monitoring method and device and electronic equipment |
-
2011
- 2011-09-23 CN CN2011102865159A patent/CN102591267A/en active Pending
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503416B (en) * | 2015-01-01 | 2017-10-24 | 韩杰 | One kind production on-line goods segmentation method of quality control and equipment |
| CN104503416A (en) * | 2015-01-01 | 2015-04-08 | 韩杰 | Method and equipment for performing subsection quality control on objects on production line |
| CN107390667A (en) * | 2017-05-27 | 2017-11-24 | 四川用联信息技术有限公司 | Manufacturing process multivariate quality diagnostic classification device based on decision tree |
| CN107272611A (en) * | 2017-05-27 | 2017-10-20 | 四川用联信息技术有限公司 | A kind of algorithm for weighing manufacture procedure quality ability |
| CN107256000A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | Algorithm of the improved Domain Volume than weighing manufacturing process multivariate quality ability |
| CN107291065A (en) * | 2017-05-27 | 2017-10-24 | 四川用联信息技术有限公司 | The improved manufacturing process multivariate quality diagnostic classification device based on decision tree |
| CN107256001A (en) * | 2017-05-27 | 2017-10-17 | 四川用联信息技术有限公司 | The improved algorithm for weighing manufacturing process multivariate quality ability |
| CN109753027A (en) * | 2017-11-08 | 2019-05-14 | 阿里巴巴集团控股有限公司 | It is a kind of industry manufacture in parameter monitoring method and device |
| CN110084449A (en) * | 2018-01-25 | 2019-08-02 | 红塔烟草(集团)有限责任公司 | Standardization and evaluation system and its method based on cigarette batch data |
| CN112116014A (en) * | 2020-09-24 | 2020-12-22 | 贵州电网有限责任公司 | Test data outlier detection method for distribution automation equipment |
| CN114384872A (en) * | 2021-12-02 | 2022-04-22 | 北京能科瑞元数字技术有限公司 | Product development process quality comprehensive management and control system |
| CN115238421A (en) * | 2022-09-23 | 2022-10-25 | 中国人民解放军国防科技大学 | Method and device for designing charging configuration of multi-pulse gas generator and computer equipment |
| CN115238421B (en) * | 2022-09-23 | 2022-12-09 | 中国人民解放军国防科技大学 | Method and device for designing charging configuration of multi-pulse gas generator and computer equipment |
| CN115619262A (en) * | 2022-10-11 | 2023-01-17 | 联宝(合肥)电子科技有限公司 | Quality monitoring method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102591267A (en) | Method for monitoring quality of production process by using target | |
| CN110458474B (en) | Comprehensive evaluation method for physical quality of rolled cigarettes | |
| CN102885392B (en) | A kind of technology for making tobacco threds Quality Monitoring Control System and method | |
| CN107657288A (en) | A kind of power scheduling flow data method for detecting abnormality based on isolated forest algorithm | |
| CN109002974A (en) | Steel coil surface quality grading judgment method and device | |
| CN109741927B (en) | Intelligent prediction system for equipment faults and potential defective products of miniature transformer production line | |
| CN101127031A (en) | Point cloud data mean value filtering system and method | |
| CN103750552B (en) | A kind of intelligent sampling method and the application controlled at quality cigarette thereof | |
| CN109615185A (en) | A kind of unit mass guarantee ability evaluation method based on Fuzzy AHP | |
| CN111832955A (en) | Contact network state evaluation method based on reliability and multivariate statistics | |
| CN103786933A (en) | Online SPC analysis system and method for metering process capability of gravimetric filling equipment | |
| CN114648235A (en) | Industrial data quality quantitative analysis report generation method based on data image | |
| CN110320337A (en) | A kind of automatic evaluating system of strip surface quality and method | |
| CN107392979B (en) | The two dimensional visible state composition and quantitative analysis index method of time series | |
| CN108830444A (en) | A kind of assessment of raob data and modification method and device | |
| CN206470794U (en) | Fabric inspection and defect data statistical system | |
| CN104730217B (en) | The defect distribution display methods of a kind of glass substrate and display device | |
| CN110852617B (en) | SMT production line analysis method and system based on real-time data acquisition | |
| CN115951641A (en) | Production data monitoring method, system and storage medium | |
| CN109062998A (en) | Calculation method, the device of a kind of coal yard dump density and coal load quantity | |
| RU2470352C1 (en) | Statistical process control method (versions) | |
| CN115187026A (en) | Industrial risk monitoring method and system and readable storage medium | |
| CN108108834A (en) | A kind of helicopter important Parts wear rate Forecasting Methodology | |
| CN106066169B (en) | A kind of detection method of the copper negative plate for electrolysis verticality, apparatus and system | |
| CN114384872A (en) | Product development process quality comprehensive management and control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120718 |