CN-121768552-B - Screening method and device for material proportion of semiconductor diaphragm

CN121768552BCN 121768552 BCN121768552 BCN 121768552BCN-121768552-B

Abstract

The application provides a screening method and a screening device for a semiconductor diaphragm material ratio, wherein in the method, the performance value of each stability item of each candidate component formula is predicted according to an obtained prediction model of each stability item, then the predicted value of each stability item and a target performance value are respectively compared to determine the performance achievement degree of each stability item, then the minimum performance which can be achieved under the constraint of each variable of each stability item is determined, so that the inverse performance achievement degree of each stability item is determined by using the minimum performance, finally the expected difference value of the current component ratio and the expected component ratio corresponding to the target performance value is determined according to the weight of each stability item, and then a plurality of component ratios with the minimum expected difference value are selected as the basis of the subsequent performance test.

Inventors

SONG HAIXIAO
XUE HUI
REN QINGMING
TAO ZHICHENG

Assignees

上海聚克流体控制有限公司

Dates

Publication Date: 20260508
Application Date: 20260228

Claims (10)

1. The screening method for the material proportion of the semiconductor diaphragm is characterized by comprising the following steps of: After obtaining the prediction model of each stability item, obtaining a target performance value set for each stability item, wherein independent variables of the prediction model of each stability item are the same, and each prediction model is a performance expected model, and the types of the performance expected model comprise a small-sized model and a large-sized model; Inputting the candidate component ratios as independent variables into the prediction models of the stability items aiming at the candidate component ratios to obtain predicted values output by the prediction models of the stability items; For each stability item, calculating a first ratio between a predicted value corresponding to the stability item and a target performance value corresponding to the stability item; Determining a section configured for the type of the predictive model of the stability item in which the first ratio is located, so as to determine the performance achievement level of the stability item according to the section; taking the value ranges of the respective variables of the stability item as constraints, and calculating the worst value corresponding to the stability item in the lowest performance according to the type of the performance expected model of the stability item; calculating a second ratio of the target performance value and the worst value corresponding to the stability item, and taking the second ratio as the degree of achievement of the anti-performance of the stability item; Determining an expected difference value of the candidate component ratio and an expected component ratio corresponding to the target performance value according to the performance achievement degree and the inverse performance achievement degree of each stability item; after the expected differences corresponding to all the candidate component proportions are obtained, determining target expected differences of preset quantity according to the sequence from small expected differences to large expected differences; outputting the target component ratio corresponding to the target expected difference value to perform performance test on the material corresponding to the target component ratio.
2. The screening method of claim 1, wherein the stability term comprises: leakage rate, pressure decay rate, and temperature resistance; the prediction model corresponding to the leakage rate and the attenuation property is a small-sized model, and the prediction model corresponding to the temperature resistance is a large-sized model.
3. The screening method of claim 2, wherein determining the interval in which the first ratio is located that is configured for the type of the predictive model of the stability term, to determine the performance achievement level of the stability term based on the interval, comprises: for a small-sized model, calculating the performance achievement degree of the stability term by using the following formula: formula one; Wherein, the The predicted value of the predictive model for the j-th stability term, A target performance value for the j-th stability term; calculating the performance achievement level of the stability term using the following equation II: A second formula; Wherein, the Is the predicted value of the predicted model corresponding to the temperature resistance, Is a target performance value corresponding to the temperature resistance.
4. The screening method according to claim 2, wherein a worst value of the leak rate and the pressure decay rate is a minimum value, and a worst value of the temperature resistance is a maximum value.
5. The screening method of claim 1, wherein determining the expected difference in the candidate component ratio to the expected component ratio corresponding to the target performance value based on the performance achievement level and the inverse performance achievement level for each stability term comprises: determining a desired difference in the candidate ingredient ratio to a desired ingredient ratio corresponding to the target property value using equation three: D( )=√[∑W i ×((1-d i ( ) (1-d i - )) 2]; equation three Wherein, V is root number, W i is weight corresponding to the ith stability item, d i # ) For the performance achievement degree corresponding to the ith stability item, d i - is the reaction achievement degree corresponding to the ith stability item, and the value of i is the number of the stability items.
6. A screening apparatus for semiconductor separator material proportioning, the apparatus comprising: the system comprises an acquisition unit, a prediction unit and a calculation unit, wherein the acquisition unit is used for acquiring target performance values set for each stability item after obtaining a prediction model of each stability item, wherein independent variables of the prediction models of the stability items are the same, and each prediction model is a performance expected model, and the types of the performance expected models comprise a small-sized model and a large-sized model; The first determining unit is used for inputting the candidate component proportion as an independent variable into the prediction model of each stability item to obtain a predicted value output by the prediction model of each stability item; A first calculating unit, configured to calculate, for each stability item, a first ratio between a predicted value corresponding to the stability item and a target performance value corresponding to the stability item; a second determining unit, configured to determine a section configured for a type of the prediction model of the stability term where the first ratio is located, so as to determine a performance achievement level of the stability term according to the section; the second calculation unit is used for calculating the worst value corresponding to the stability item in the lowest performance according to the type of the performance expected model of the stability item by taking the value range of each variable of the stability item as a constraint; The third calculating unit is used for calculating a second ratio of the target performance value and the worst value corresponding to the stability item, so that the second ratio is used as the degree of achievement of the anti-performance of the stability item; a third determining unit, configured to determine, according to the performance achievement degree and the inverse performance achievement degree of each stability item, an expected difference value of the candidate component ratio and an expected component ratio corresponding to the target performance value; A fourth determining unit, configured to determine a preset number of target expected differences according to the order from the smaller expected differences to the larger expected differences after obtaining the expected differences corresponding to the proportions of all the candidate components; and the output unit is used for outputting the target component ratio corresponding to the target expected difference value so as to perform performance test on the material corresponding to the target component ratio.
7. The screening apparatus of claim 6, wherein the stability term comprises: leakage rate, pressure decay rate, and temperature resistance; the prediction model corresponding to the leakage rate and the attenuation property is a small-sized model, and the prediction model corresponding to the temperature resistance is a large-sized model.
8. The screening apparatus of claim 7, wherein the second determining unit is configured to determine a section configured for a type of the predictive model of the stability item in which the first ratio is located, to determine the performance achievement level of the stability item according to the section, includes: for a small-sized model, calculating the performance achievement degree of the stability term by using the following formula: formula one; Wherein, the The predicted value of the predictive model for the j-th stability term, A target performance value for the j-th stability term; calculating the performance achievement level of the stability term using the following equation II: A second formula; Wherein, the Is the predicted value of the predicted model corresponding to the temperature resistance, Is a target performance value corresponding to the temperature resistance.
9. The screening apparatus of claim 7, wherein a worst value of the leak rate and the pressure decay rate is a minimum value, and a worst value of the temperature resistance is a maximum value.
10. The screening apparatus according to claim 6, wherein the third determining unit is configured to determine, based on the performance achievement level and the inverse performance achievement level of each stability term, a desired difference in the candidate component ratio from a desired component ratio corresponding to a target performance value, including: determining a desired difference in the candidate ingredient ratio to a desired ingredient ratio corresponding to the target property value using equation three: D( )=√[∑W i ×((1-d i ( ) (1-d i - )) 2]; equation three Wherein, V is root number, W i is weight corresponding to the ith stability item, d i # ) For the performance achievement degree corresponding to the ith stability item, d i - is the reaction achievement degree corresponding to the ith stability item, and the value of i is the number of the stability items.

Description

Screening method and device for material proportion of semiconductor diaphragm Technical Field The application relates to the technical field of computers, in particular to a screening method and a screening device aiming at the material proportion of a semiconductor diaphragm. Background Diaphragm valves in semiconductor manufacturing processes are critical components for controlling the delivery of ultra-pure gases and chemical liquids, and the reliability and lifetime of the valve are directly determined by the properties of the valve seat or diaphragm material. These materials are typically compounded from a variety of known polymeric matrices (e.g., polytetrafluoroethylene or soluble polytetrafluoroethylene) and functional fillers (e.g., carbon fibers, glass beads, lubricants, etc.). The material needs to meet both extremely low leakage rate (air tightness), long-term stable pressure holding capability (positive pressure holding) and dimensional and performance stability (temperature resistance) over a wide temperature range (e.g. -20 ℃ to 150 ℃). With the development of technology, one can determine a certain property of a certain material in a simulated manner, but how to integrate a plurality of conflicting property targets (such as air tightness, positive pressure maintaining and temperature resistance) and find out a relatively suitable component proportion is still a technical problem. Disclosure of Invention In view of the above, the embodiment of the application provides a screening method and a screening device for the material proportion of a semiconductor diaphragm, so as to accurately screen the component proportion with relatively good comprehensive performance. In a first aspect, an embodiment of the present application provides a screening method for a material ratio of a semiconductor separator, where the method includes: After obtaining the prediction model of each stability item, obtaining a target performance value set for each stability item, wherein independent variables of the prediction model of each stability item are the same, and each prediction model is a performance expected model, and the types of the performance expected model comprise a small-sized model and a large-sized model; Inputting the candidate component ratios as independent variables into the prediction models of the stability items aiming at the candidate component ratios to obtain predicted values output by the prediction models of the stability items; For each stability item, calculating a first ratio between a predicted value corresponding to the stability item and a target performance value corresponding to the stability item; Determining a section configured for the type of the predictive model of the stability item in which the first ratio is located, so as to determine the performance achievement level of the stability item according to the section; taking the value ranges of the respective variables of the stability item as constraints, and calculating the worst value corresponding to the stability item in the lowest performance according to the type of the performance expected model of the stability item; calculating a second ratio of the target performance value and the worst value corresponding to the stability item, and taking the second ratio as the degree of achievement of the anti-performance of the stability item; Determining an expected difference value of the candidate component ratio and an expected component ratio corresponding to the target performance value according to the performance achievement degree and the inverse performance achievement degree of each stability item; after the expected differences corresponding to all the candidate component proportions are obtained, determining target expected differences of preset quantity according to the sequence from small expected differences to large expected differences; outputting the target component ratio corresponding to the target expected difference value to perform performance test on the material corresponding to the target component ratio. In a second aspect, an embodiment of the present application provides a screening apparatus for a material ratio of a semiconductor separator, the apparatus including: the system comprises an acquisition unit, a prediction unit and a calculation unit, wherein the acquisition unit is used for acquiring target performance values set for each stability item after obtaining a prediction model of each stability item, wherein independent variables of the prediction models of the stability items are the same, and each prediction model is a performance expected model, and the types of the performance expected models comprise a small-sized model and a large-sized model; The first determining unit is used for inputting the candidate component proportion as an independent variable into the prediction model of each stability item to obtain a predicted value output by the prediction model of each stability ite