CN103219209A - Method for determining and optimizing manufacturing process parameter values of plasma display panel - Google Patents

Abstract

The invention discloses a method for determining and optimizing manufacturing process parameter values of a plasma display panel. The method disclosed by the invention comprises the following steps of: associating the number of occurrence times of observed values of the parameters with grades of a screen under corresponding observed values; and determining a screen grade which is most relevant to the parameter values to take a parameter value which is most relevant to a confidence level zone of the screen grade as an optimized parameter value. The method disclosed by the invention has the positive effects of saving time and resource costs consumed in the manner of repeatedly testing design and verifying, improving the accuracy for determining the manufacturing process parameter values related to the quality of the plasma display panel, spirally reusing a model analyzing method via an adjusted new history data accumulation to find the manufacturing process parameter values of the quality of the plasma display panel, and simultaneously not relating to the interruption of production of a production line in the process of using the method model and avoiding unnecessary line-stopping loss.

Description

Determining and optimization method of plasma panel process parameters value

Technical field

The present invention relates to a kind of data mining technology of plasma panel manufacture process characteristic, especially relate to determining and optimization method of a kind of plasma panel process parameters value.

Background technology

Plasma panel process parameters value is extremely important.Specifically, plasma panel process parameters value difference can directly cause making result's difference.Plasma panel process parameters value was by the EXPERIMENTAL DESIGN of construction period in the past and checking is next repeatedly determines.Along with production programming extension and 7*24 hour uninterrupted volume production,, also need production line to stop the debugging design that line carries out the test parameters value simultaneously if continue to adopt traditional test design method will waste great amount of manpower and kinetic energy consuming cost.This method has reduced the production efficiency of volume production on the one hand, will expend great amount of manpower and kinetic energy consuming cost simultaneously.Therefore need a kind of new method dynamically to carry out determining and optimization of process parameters value.

Along with the large quantities of volume productions of plasma panel, face data magnanimity situation again.In the plasma panel manufacture process volume production process, separate unit plasma panel process of producing product device parameter is included the storage of MES system in and is reached 1.2 ten thousand, more than the every day data volume 10G, the parameter that relates to is above 9000, in quantity, have the big data characteristics of magnanimity on dimension and the data generation speed, press for a kind of new method of invention more and dynamically carry out determining and optimization of process parameters value.

The present invention launches under should this background.

Summary of the invention

In order to overcome the above-mentioned shortcoming of prior art, the invention provides determining and optimization method of a kind of plasma panel process parameters value, carry out association by the grade of shielding under number of times that the parameter estimator value is occurred and the corresponding measured value, determine the screen grade with each parameter value relevance maximum, thus will with the screen grade from the parameter value of the interval relevance maximum of reliability as the optimum parameters value.

The technical solution adopted for the present invention to solve the technical problems is: determining and optimization method of a kind of plasma panel process parameters value comprises the steps:

Step 1, on pending data, different parameter values is carried out the association of screen products grade, and calculate the number of times that the different brackets of corresponding screen products under each parameter value occurs;

Step 2, determine and the screen grade of each parameter value relevance maximum;

Step 3, will with the screen grade from the parameter value of the interval relevance maximum of reliability as the optimum parameters value.

Compared with prior art, good effect of the present invention is: save by mode spent time and the resources costs of repetition test design with checking, promoted the accuracy of determining concerning the process parameters value of plasma panel quality, and by adjusted new historical data accumulation, carry out the screw type process parameters value of utilizing this analytical model method to seek out the plasma panel quality again, manufacturing technology personnel are according to the parameter value recommended value, carry out the parameter value management and control, not only reach the purpose that continues spiral lifting plasma panel yields, but also reduce the percent defective of manufacture process indirectly.Simultaneously, in the use of method model, can not relate to the breaks in production of production line, avoid the unnecessary line loss of stopping to lose.

Embodiment

Determining and optimization method of a kind of plasma panel process parameters value may further comprise the steps:

Step 1, on pending data, different parameter values is carried out the association of screen products grade, and calculate the number of times that the different brackets of corresponding screen products under each parameter value occurs;

Step 2, determine and the screen grade of each parameter value relevance maximum:

(1) be calculated as follows from reliability:

$P(Z_{\mathrm{\&alpha;}/2}<\frac{\mathrm{acc}-p}{\sqrt{p(1-p)/N}}<Z_{1-\mathrm{\&alpha;}/2})=1-\mathrm{\&alpha;},$

P is an average in the formula, and α is the yield of expectation, and N represents sample size altogether, and acc is illustrated in the yield on the sample that observes, Z _α/2Be illustrated under the condition of current yield acc, be distributed as the probability lower limit of benchmark, Z with current yield _1-α/2Be illustrated under the condition of current yield acc, be distributed as the probability upper limit of benchmark with current yield.

(2) be calculated as follows from the reliability interval:

$p=\frac{2\&times;N\&times;\mathrm{acc}+Z_{\mathrm{\&alpha;}/2}^2\&PlusMinus;\sqrt{Z_{\mathrm{\&alpha;}/2}^2+4\&times;N\&times;\mathrm{acc}-4\&times;N\&times;{\mathrm{acc}}^2}}{2(N+Z_{\mathrm{\&alpha;}/2}^2)}$

(3) determine screen grade with each parameter value relevance maximum:

Judgement from the lower limit in reliability interval whether more than or equal to prior preset threshold, if determine that then this screen grade from the interval corresponding equipment of reliability is the screen grade with each parameter value relevance maximum.

Step 3, will with the screen grade from the parameter value of the interval relevance maximum of reliability as the optimum parameters value.

The inventive method illustrates as follows:

Setting parameter M is associated with G level screen quantity on measured value k be 800, and being associated with S level screen quantity is 200, i.e. N=1000, possess 95% from reliability, promptly 1-α=0.95 obtains by the inquiry following table: Z _α/2=1.96

1-α	0.99	0.98	0.95	0.90
					Z	2.58	2.33	1.96	1.65

This table is by supposing that yield is the ready-made form under the normal distribution.

The value of each computational element has in this example:

N	50	100	500	1000	5000
						P (lower limit)	0.670	0.711	0.763	0.774	0.789
P (upper limit)	0.888	0.866	0.833	0.824	0.811

Can see in the superincumbent result of calculation parameter M on value k, to guarantee G level screen ratio reach 80% and from reliability at 95% o'clock, this is 0.774～0.824 from the reliability interval.

The present invention can carry out calculating from reliability to the measured value of each parameter by above calculation procedure, select with shield grade from the optimization foundation of the interval higher parameter value of reliability as parameter value.

Claims (2)

1. determining and optimization method of a plasma panel process parameters value is characterized in that: comprise the steps:

Step 1, on pending data, different parameter values is carried out the association of screen products grade, and calculate the number of times that the different brackets of corresponding screen products under each parameter value occurs;

Step 2, determine and the screen grade of each parameter value relevance maximum;

Step 3, will with the screen grade from the parameter value of the interval relevance maximum of reliability as the optimum parameters value.

2. determining and optimization method of plasma panel process parameters value according to claim 1 is characterized in that: step 2 is described determine with the method for the screen grade of each parameter value relevance maximum be:

(1) be calculated as follows from reliability:

P is an average in the formula, and α is the yield of expectation, and N represents sample size altogether, and acc is illustrated in the yield on the sample that observes, Z _α/2Be illustrated under the condition of current yield acc, be distributed as the probability lower limit of benchmark, Z with current yield _1-α/2Be illustrated under the condition of current yield acc, be distributed as the probability upper limit of benchmark with current yield;

(2) be calculated as follows from the reliability interval:

(3) determine screen grade with each parameter value relevance maximum:

Judgement from the lower limit in reliability interval whether more than or equal to prior preset threshold, if determine that then this screen grade from the interval corresponding equipment of reliability is the screen grade with each parameter value relevance maximum.