Product evaluation method, device, equipment and medium

Abstract

The invention discloses a product evaluation method, device and equipment and a medium, and the method comprises the steps: obtaining a product statistical parameter, a parameter limit value, and a measurement statistical parameter of a measurement system, and the measurement system is used for carrying out the product qualification measurement; determining the production risk probability of the product and the measurement risk probability of the product measured by the measurement system based on the product statistical parameter, the parameter limit value and the measurement statistical parameter of the measurement system; and obtaining an index value corresponding to the product evaluation index based on the production risk probability and the measurement risk probability.

Description

Technical Field

[0001] This application relates to the technical fields of quality and statistics, and in particular to a product evaluation method, apparatus, equipment, and medium. Background Technology

[0002] With the development of intelligent manufacturing technology, users have increasingly higher requirements for product quality and reliability. The over-scraping rate and under-scraping rate are very important indicators in the production process. A high under-scraping rate means that more defective products may enter the market.

[0003] In related technologies, the overkill rate is assessed using the formula: For accurate assessment results, calculations typically need to reach the level of defective parts per million (DPPM) or even defective parts per billion (DPPB). However, achieving DPPM or DPPB levels requires an enormous sample size, which is practically impossible to calculate directly using formulas. This makes it difficult to meet the accuracy requirements of product assessment results, compromising product quality and hindering the analysis of manufacturing process capabilities. Summary of the Invention

[0004] In view of the above problems, this application provides a product evaluation method, apparatus, equipment and medium that can directly calculate the process over-miss rate, facilitate the analysis of process capability, improve the accuracy of product evaluation and improve product quality.

[0005] In a first aspect, this application provides a product evaluation method, which includes: obtaining product statistical parameters, parameter limits, and measurement statistical parameters of a measurement system, wherein the measurement system is used to perform product qualification measurement; determining the production risk probability of the product and the measurement risk probability of the measurement system measuring the product based on the product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system; and obtaining the index value corresponding to the product evaluation index based on the production risk probability and the measurement risk probability.

[0006] In the technical solution of this application embodiment, multiple data are comprehensively considered, such as product statistical parameters, parameter limits, and measurement system statistical parameters, to determine the production risk probability of the product and the measurement risk probability of the measurement system measuring the product. This can accurately assess the production process capability, making the calculation of over-missed and under-killed rates more convenient. Moreover, this assessment method does not require a huge number of samples, the assessment speed is fast, and the accuracy is high.

[0007] In some embodiments, the production risk probability of the product and the measurement risk probability of the measurement system measuring the product are determined based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system. This includes: determining the normal distribution data of the product and the normal distribution data of the measurement system based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system; determining the production risk probability based on the normal distribution data of the product; and determining the measurement risk probability based on the normal distribution data of the measurement system.

[0008] In the technical solution of this application embodiment, the production risk probability and measurement risk probability are calculated based on the normal distribution data of the product and the normal distribution data of the measurement system, respectively. The above-mentioned normal distribution-based method makes the calculation of the missed kill rate more convenient. The normal distribution method only requires a small amount of data to achieve high accuracy. The small amount of data may even only require a dozen or a few dozen samples.

[0009] In some embodiments, product statistical parameters include the product process mean and the product process standard deviation, and measurement statistical parameters of the measurement system include the measurement standard deviation of the measurement system. Determining the normal distribution data of the product and the normal distribution data of the measurement system based on the product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system includes: determining the normal distribution data of the product based on the product process mean and the product process standard deviation; determining the product process risk interval from the normal distribution data of the product based on the parameter limits and the measurement standard deviation of the measurement system; determining the measurement mean of the measurement system based on sub-intervals within the product process risk interval; and determining the normal distribution data of the measurement system based on the measurement mean and the measurement standard deviation of the measurement system.

[0010] In the technical solution of this application embodiment, the calculation of product process mean, process standard deviation, measurement mean and measurement standard deviation is relatively simple, and the measurement mean is calculated separately based on multiple sub-intervals in the product risk interval, which is more reasonable and improves the accuracy of the over-missed kill rate calculation.

[0011] In some embodiments, determining the measurement mean of the measurement system based on the product process risk range includes: determining the mean of the interval limits of the sub-intervals in the product process risk range as the measurement mean of the measurement system.

[0012] In the technical solution of this application embodiment, the measurement mean of the measurement system is determined based on the mean of the interval limits of the sub-intervals in the product process risk interval. When the sub-intervals are small enough, the mean of the interval limits is used as the measurement mean of the measurement system. This simplifies the calculation while ensuring accuracy, improves the accuracy of the over-miss rate calculation, and makes the process capability assessment more reliable.

[0013] In some embodiments, determining the production risk probability based on the product's normal distribution data includes: obtaining the interval probability of the product process risk interval based on the probability density function corresponding to the product's normal distribution data, and using it as the production risk probability.

[0014] In the technical solution of this application embodiment, the probability density function corresponding to the normal distribution data of the product is integrated in the corresponding interval to obtain the production risk probability. The calculation is simple and the complexity of the algorithm is reduced.

[0015] In some embodiments, determining the measurement risk probability based on the normal distribution data of the measurement system includes: determining the measurement risk interval from the normal distribution data of the measurement system based on parameter limits; and obtaining the interval probability of the measurement risk interval based on the probability density function corresponding to the normal distribution data of the measurement system, as the measurement risk probability.

[0016] In the technical solution of this application embodiment, the measurement risk interval of the normal distribution data of the measurement system is determined according to the parameter limit. The measurement risk probability can be obtained by performing integral operation on the probability density function corresponding to the normal distribution data of the measurement system in the corresponding interval. The calculation is simple.

[0017] In some embodiments, the index value corresponding to the product evaluation index is obtained based on the production risk probability and the measurement risk probability, including: obtaining the index value corresponding to the product evaluation index based on the product of the production risk probability and the measurement risk probability.

[0018] In the technical solution of this application embodiment, the process over-miss rate is directly obtained based on the product of the production risk probability and the measurement risk probability. The calculation is simple and the algorithm complexity is reduced, which facilitates the analysis of process capability and improves product quality.

[0019] In some embodiments, the product process risk interval is divided into multiple sub-intervals, the production risk probability includes multiple first sub-probabilities corresponding to multiple sub-intervals, and the measurement risk probability includes multiple second sub-probabilities corresponding to multiple sub-intervals; the index value corresponding to the product evaluation index is obtained based on the product of the production risk probability and the measurement risk probability, including: multiplying the first sub-probability and the second sub-probability corresponding to each sub-interval to obtain the index value corresponding to the product evaluation index of each sub-interval, and adding the index values ​​corresponding to the product evaluation index of multiple sub-intervals.

[0020] In the technical solution of this application embodiment, the product risk range is divided into multiple sub-ranges, and each sub-range corresponds to multiple production risk probabilities and multiple measurement risk probabilities. The product of the production risk probability and the measurement risk probability is calculated for each sub-range, and the sum of the products of the multiple sub-ranges is used as the final over / undershoot / missed detection rate. In the above method, dividing the product risk range into multiple sub-ranges for calculation reduces computational complexity, and calculating each sub-range separately makes the over / undershoot / missed detection rate calculation more accurate and reliable.

[0021] In some embodiments, the product evaluation index includes at least one of the following: a missed detection index, wherein the missed detection rate corresponding to the missed detection index represents the probability that the production parameters of the product exceed the parameter limits, but the measurement system measures the product as qualified; and an over-detection index, wherein the over-detection rate corresponding to the over-detection index represents the probability that the production parameters of the product do not exceed the parameter limits, but the measurement system measures the product as unqualified.

[0022] In some embodiments, the parameter limits include at least one of the lower limit of product tolerance and the upper limit of product tolerance; the product process risk range includes at least one of the following: a first missed detection risk range, which is determined based on the lower limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product exceed the lower limit of product tolerance; a second missed detection risk range, which is determined based on the upper limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product exceed the upper limit of product tolerance; a first over-detection risk range, which is determined based on the lower limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product do not exceed the lower limit of product tolerance; and a second over-detection risk range, which is determined based on the upper limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product do not exceed the upper limit of product tolerance.

[0023] In the technical solution of this application embodiment, the upper and lower limits of the product tolerance can be flexibly set as needed, which is more convenient. Moreover, there is a missed detection range and an over-detection range on both sides of the upper and lower limits of the product tolerance, which can more accurately evaluate the process capability.

[0024] On the other hand, this application provides a product evaluation device, which includes: an acquisition module for acquiring product statistical parameters, parameter limits, and measurement statistical parameters of a measurement system, wherein the measurement system is used to perform product qualification measurement; a determination module for determining the production risk probability of the product and the measurement risk probability of the measurement system measuring the product based on the product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system; and an acquisition module for obtaining the index value corresponding to the product evaluation index based on the production risk probability and the measurement risk probability.

[0025] On the other hand, this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method of any of the above embodiments.

[0026] On the other hand, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of any of the above embodiments.

[0027] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0028] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0029] Figure 1 A schematic diagram of the product evaluation method provided for the implementation of this application;

[0030] Figure 2 This application illustrates a schematic diagram defining the upper and lower limits of missed and overkill detections in an embodiment of the present application.

[0031] Figure 3 The normal distribution diagram of the missed detection and over-detection intervals in an embodiment of this application is shown;

[0032] Figure 4 This illustration shows a schematic diagram of the risk analysis of missed detections at the lower limit side in an embodiment of this application;

[0033] Figure 5 This diagram illustrates the product risk probability in the first missed detection risk range according to an embodiment of this application.

[0034] Figure 6 This diagram illustrates the measurement risk probability of the first missed detection risk interval according to an embodiment of this application.

[0035] Figure 7 A flowchart of the product evaluation algorithm steps according to another embodiment of this application is shown;

[0036] Figure 8 A block diagram of a product evaluation apparatus provided for one embodiment of this application. Detailed Implementation

[0037] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0039] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0040] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0041] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0042] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0043] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0044] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0045] With the development of intelligent manufacturing technology, users have increasingly higher requirements for product quality and reliability. The over-scraping rate and under-scraping rate are very important indicators in the production process. A high under-scraping rate means that more defective products may enter the market.

[0046] In related technologies, the overkill rate is assessed using the formula: For accurate assessment results, calculations typically need to reach the level of defective parts per million (DPPM) or even defective parts per billion (DPPB). However, achieving DPPM or DPPB levels requires an enormous sample size, which is practically impossible to calculate directly using formulas. This makes it difficult to meet the accuracy requirements of product assessment results, compromising product quality and hindering the analysis of manufacturing process capabilities.

[0047] In view of the above problems, this application provides a product evaluation method that can directly calculate the process over-miss rate, facilitate the analysis of process capability, improve the accuracy of product evaluation, and enhance product quality.

[0048] Figure 1 A schematic diagram of the product evaluation method provided for the implementation of this application.

[0049] like Figure 1As shown, the product evaluation method 100 provided in this application embodiment includes, for example, steps S110-S130.

[0050] Step S110: Obtain product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, wherein the measurement system is used to perform product qualification measurement.

[0051] For example, statistical parameters of the process product and the measurement system are obtained. Parameter limits can be set in advance, and the parameter limits represent the degree of fault tolerance of the product.

[0052] The product can be a battery or a battery component, and batteries can include vehicle power batteries. Battery components include, for example, positive electrode plates, negative electrode plates, separators, and battery casings. Product statistical parameters can be the size and weight data of the components. For example, product statistical parameters can be the overall weight and size of the battery, or they can be the length, width, and thickness of the positive or negative electrode plates. Separators are generally made of polyolefin materials, such as polyethylene and polypropylene, and product statistical parameters can be the thickness and pore size of the separator. Battery casings are generally made of metal or plastic materials, such as steel casings, aluminum casings, and plastic casings, and product statistical parameters can be the length, width, and height of the casing.

[0053] Step S120: Based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, determine the production risk probability of the product and the measurement risk probability of the measurement system measuring the product.

[0054] For example, production risk probability and measurement risk probability are calculated based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system within a specific interval.

[0055] Step S130: Based on the production risk probability and the measurement risk probability, obtain the index values ​​corresponding to the product evaluation index.

[0056] For example, the calculated probability and the measured risk probability are used to calculate the final product evaluation index value according to the relevant mathematical formulas corresponding to the principle.

[0057] It is understandable that product statistical parameters represent the parameters after the product is produced. Whether the product statistical parameters meet the production requirements is mainly determined by the production equipment or production process. Whether the product is qualified can be represented by the production risk probability, for example.

[0058] After product manufacturing, when a measurement system is used to inspect the product for conformity, inaccurate measurement results can occur due to fluctuations or inherent measurement errors in the system itself. For example, a qualified product might be measured as unqualified, or an unqualified product as qualified. These fluctuations or measurement errors can be represented by measurement statistical parameters. Measurement errors are particularly prone to occur around parameter limits, as products near these limits are on the borderline between qualified and unqualified. Therefore, if the measurement system has fluctuations or inherent measurement errors, it is more likely to produce errors. Whether a measurement system is prone to error can be represented, for example, by the probability of measurement risk.

[0059] Therefore, this application determines the index values ​​corresponding to the product evaluation indicators based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, comprehensively considering the risks of the product manufacturing process and the measurement risks of the measurement system, thereby improving the accuracy of product evaluation.

[0060] In the technical solution of this application embodiment, multiple data are comprehensively considered, such as product statistical parameters, parameter limits, and measurement system statistical parameters, to determine the production risk probability of the product and the measurement risk probability of the measurement system measuring the product. This can accurately assess the production process capability, making the calculation of over-missed and under-killed rates more convenient. Moreover, this assessment method does not require a huge number of samples, the assessment speed is fast, and the accuracy is high.

[0061] Figure 2 A schematic diagram illustrating the definition of the upper and lower limits of missed detections and over-detections in an embodiment of this application is shown.

[0062] The parameter limits include at least one of the lower limit of product tolerance and the upper limit of product tolerance.

[0063] For example, parameter limits include the upper specification limit (USL) and the lower specification limit (LSL). In machine design and manufacturing, the upper and lower tolerance limits refer to the allowable variation in the actual parameter values ​​of machinery or machine parts.

[0064] In one example, the product evaluation metrics include at least one of the following: a missed detection metric, wherein the missed detection rate corresponding to the missed detection metric represents the probability that the product's production parameters exceed the parameter limits, but the measurement system measures the product as qualified; and an over-detection metric, wherein the over-detection rate corresponding to the over-detection metric represents the probability that the product's production parameters do not exceed the parameter limits, but the measurement system measures the product as unqualified.

[0065] For example, over-detection means misjudging qualified products as unqualified products, and the over-detection rate (α risk) = number of over-detected products / total number of inspections; under-detection means misjudging unqualified products as qualified products, and the under-detection rate (β risk) = number of under-detected products / total number of inspections.

[0066] For example, such as Figure 2 As shown, Figure 2 The upper and lower limits refer to the upper specification limit (USL) and lower specification limit (LSL) of the process product tolerance, respectively. These limits divide the target range into three sections, each corresponding to a different category. In Category I, defective parts (products) are always referred to as defective parts (products); in Category II, potentially erroneous decisions may be made, such as referring to good parts (products) as defective parts (products) and vice versa; in Category III, good parts (products) are always referred to as good parts (products).

[0067] The product evaluation method of this application is subject to the following preconditions: the measurement system is corrected by standard parts measurement or calibration report results to ensure that the measurement system is unbiased; the risk of over-kill and under-kill is mainly determined by fluctuations; and the production process and measurement process follow a normal distribution.

[0068] Based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, determine the production risk probability of the product and the measurement risk probability of the measurement system measuring the product. This includes: determining the normal distribution data of the product and the normal distribution data of the measurement system based on the product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system; determining the production risk probability based on the normal distribution data of the product; and determining the measurement risk probability based on the normal distribution data of the measurement system.

[0069] For example, based on the product statistical parameters, parameter limits, and measurement statistical parameters, since both the production process and the measurement process follow a normal distribution, the normal distribution diagram of the product and the normal distribution diagram of the measurement system can be obtained. Based on the normal distribution relationship, the probability of the interval can be calculated by integrating the corresponding interval, thereby determining the production risk probability and measurement risk probability of the product.

[0070] In the technical solution of this application embodiment, the production risk probability and measurement risk probability are calculated based on the normal distribution data of the product and the normal distribution data of the measurement system, respectively. The above-mentioned normal distribution-based method makes the calculation of the missed kill rate more convenient. The normal distribution method only requires a small amount of data to achieve high accuracy. The small amount of data may even only require a dozen or a few dozen samples.

[0071] Figure 3The diagram shows the normal distribution of missed and overkill intervals in an embodiment of this application.

[0072] Product statistical parameters include the product process mean and the product process standard deviation, while measurement statistical parameters of the measurement system include the measurement standard deviation of the measurement system.

[0073] Determining the normal distribution data of the product and the normal distribution data of the measurement system based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system may include the following process:

[0074] Based on the product process mean and product process standard deviation, determine the normal distribution data of the product.

[0075] Based on parameter limits and the measurement standard deviation of the measurement system, the product process risk range is determined from the product's normal distribution data.

[0076] The measurement mean of the measurement system is determined based on the sub-intervals within the product process risk interval.

[0077] Based on the measurement mean and measurement standard deviation of the measurement system, the normal distribution data of the measurement system is determined.

[0078] For example, since the production process follows a normal distribution, a normal distribution map of the product can be obtained based on the product process mean and standard deviation. Risk zones exist near the upper and lower tolerance limits, and the corresponding missed detection and over-detection risk intervals can be identified based on the measurement standard deviation of the measurement system. Then, each interval within the missed detection and over-detection risk intervals is divided into multiple sub-intervals for calculation. The mean of these sub-intervals is used as the measurement mean of the measurement system. Since the measurement process follows a normal distribution, a normal distribution map of the measurement system can be obtained based on the measurement standard deviation and measurement mean.

[0079] For example, the product process risk range includes at least one of the following: a first missed detection risk range, a second missed detection risk range, a first over-detection risk range, and a second over-detection risk range.

[0080] The first missed detection risk range is determined based on the lower limit of product tolerance and the standard deviation of the measurement system. The first missed detection risk range indicates that the product's production parameters exceed the lower limit of product tolerance.

[0081] The second omission risk range is determined based on the upper limit of product tolerance and the standard deviation of the measurement system. The second omission risk range indicates that the product's production parameters exceed the upper limit of product tolerance.

[0082] The first over-cut risk range is determined based on the lower limit of product tolerance and the standard deviation of the measurement system. The first over-cut risk range indicates that the production parameters of the product have not exceeded the lower limit of product tolerance.

[0083] The second over-cutting risk range is determined based on the upper limit of product tolerance and the standard deviation of the measurement system. The second over-cutting risk range indicates that the production parameters of the product have not exceeded the upper limit of product tolerance.

[0084] For example, such as Figure 3 As shown, the mean of the normal distribution is μ, and the standard deviation is σ. Figure 3 In the process, the product mean is μ, σ ms The measurement standard deviation of the measurement system is defined as Interval II, and the range of Interval II is as follows: LSL - 3 * σ ms ~LSL+3*σ ms USL-3*σ ms ~USL+3*σ ms The risk interval for missed detections is represented as: First risk interval for missed detections LSL - 3 * σ ms ~LSL, the second risk range for missed kills is USL~USL+3*σ ms The overshoot risk range is represented as: the first overshoot risk range LSL ~ LSL + 3*σ ms The second overkill risk range is USL-3*σ ms ~USL.

[0085] In the technical solution of this application embodiment, the calculation of the product process mean, product process standard deviation, measurement mean of the measurement system, and measurement standard deviation is relatively simple. The measurement mean is calculated separately based on multiple sub-intervals in the product risk interval, making the settings more reasonable and improving the accuracy of the over / under-kill rate calculation. Furthermore, the upper and lower limits of the product tolerance can be flexibly set as needed, making it more convenient. There is an over-kill interval and an under-kill interval on both sides of the upper and lower tolerance limits, allowing for a more accurate assessment of process capability.

[0086] Figure 4 This illustration shows a schematic diagram of the risk analysis of missed detections at the lower limit side in an embodiment of this application.

[0087] like Figure 4 As shown, for Figure 3 Taking the first missed detection risk interval on the lower limit side as an example for analysis (the analysis of the second missed detection risk interval, the first over-detection risk interval, and the second over-detection risk interval is similar), the input conditions of the product evaluation algorithm include, for example, the upper limit of product tolerance (USL), the lower limit of tolerance (LSL), and the standard deviation σ of the measurement system. ms Product process mean μ, product process standard deviation σ p In general, the population standard deviation σ of the process is directly observed. total ,

[0088] The first missed detection risk interval spans 3σ ms Within the first missed detection area, the entire interval is divided into n (n→∞) sub-intervals. For any sub-interval s, its span is l (l→0), where l approaches 0. The starting point of sub-interval s is l0, and the ending point is l1, as shown below. Figure 4 The vertical bar in the middle represents the subinterval s. The probability density function of the normal distribution is... In the process distribution, the probability that a product appears in the over-missed area (i.e., the production risk probability) is P1. Based on the standard deviation σ of the measurement system... ms The probability that a product appearing in the over- or under-killed area will be over-killed or under-killed (i.e., the probability of measuring risk) can be calculated as P2.

[0089] Among them, determining the measurement mean of the measurement system based on the product process risk range includes: determining the mean of the interval limits of the sub-intervals in the product process risk range as the measurement mean of the measurement system.

[0090] For example, such as Figure 4 As shown, for any subinterval s with a span l (l→0), the interval limits of subinterval s are the starting point l0 and the ending point l1. When the subinterval s is very small, the interval mean can be used. Instead of this interval, the mean μ s As the measurement mean of the measurement system corresponding to sub-interval s, based on the measurement mean μ of the measurement system s and the standard deviation σ of the measurement system ms The normal distribution of the measurement system corresponding to the subinterval s can be obtained (as follows). Figure 6 ).

[0091] In the technical solution of this application embodiment, the measurement mean of the measurement system is determined based on the mean of the interval limits of the sub-intervals in the product process risk interval. When the sub-intervals are small enough, the mean of the interval limits is used as the measurement mean of the measurement system. This simplifies the calculation while ensuring accuracy, improves the accuracy of the over-miss rate calculation, and makes the process capability assessment more reliable.

[0092] Figure 5 This diagram illustrates the product risk probability of the first missed detection risk range according to an embodiment of this application.

[0093] Based on the normal distribution data of the product, the production risk probability is determined, including: based on the probability density function corresponding to the normal distribution data of the product, the interval probability of the product process risk interval is obtained, which is used as the production risk probability.

[0094] For example, such as Figure 5 As shown, the probability density function of the normal distribution is In the process distribution, if the probability of subinterval s is P1, then... This represents the production risk probability within that interval, where μ is the product process mean, and σ... p This represents the standard deviation of the product process.

[0095] In the technical solution of this application embodiment, the probability density function corresponding to the normal distribution data of the product is integrated in the corresponding interval to obtain the production risk probability. The calculation is simple and the complexity of the algorithm is reduced.

[0096] Figure 6 This diagram illustrates the measurement risk probability of the first missed detection risk interval in an embodiment of this application.

[0097] Based on the normal distribution data of the measurement system, the measurement risk probability is determined, including: determining the measurement risk interval from the normal distribution data of the measurement system based on parameter limits; and obtaining the interval probability of the measurement risk interval based on the probability density function corresponding to the normal distribution data of the measurement system, which is used as the measurement risk probability.

[0098] For example, such as Figure 6 As shown, in the measurement distribution, the mean interval corresponding to the sub-interval s is μ. s The measurement system will measure the product process mean within the interval μ. s The probability of measuring within the acceptable range is: Right now Figure 6 The right-tail probability in the distribution of the measurement system.

[0099] In the technical solution of this application embodiment, the measurement risk interval of the normal distribution data of the measurement system is determined according to the parameter limit. The measurement risk probability can be obtained by performing integral operation on the probability density function corresponding to the normal distribution data of the measurement system in the corresponding interval. The calculation is simple.

[0100] Based on the production risk probability and the measurement risk probability, the corresponding index values ​​for the product evaluation indicators are obtained, including: based on the product of the production risk probability and the measurement risk probability, the corresponding index values ​​for the product evaluation indicators are obtained.

[0101] For example, within the missed detection region (first missed detection risk interval) on the lower limit LSL side, the missed detection probability for any sub-interval s is P. s =P1*P2, the result of which is P s This refers to the indicator value corresponding to the product evaluation indicator for that sub-interval.

[0102] In the technical solution of this application embodiment, the process over-miss rate is directly obtained based on the product of the production risk probability and the measurement risk probability. The calculation is simple and the algorithm complexity is reduced, which facilitates the analysis of process capability and improves product quality.

[0103] The aforementioned product process risk range is divided into multiple sub-ranges. The production risk probability includes multiple first sub-probabilities corresponding to multiple sub-ranges, and the measurement risk probability includes multiple second sub-probabilities corresponding to multiple sub-ranges. Based on the product of the production risk probability and the measurement risk probability, the index value corresponding to the product evaluation index is obtained, including: multiplying the first sub-probability and the second sub-probability corresponding to each sub-range to obtain the index value corresponding to the product evaluation index for each sub-range, and adding the index values ​​corresponding to the product evaluation index for multiple sub-ranges.

[0104] For example, taking product process risk as the first missed detection risk interval, the missed detection probabilities of the n sub-intervals of the first missed detection risk interval can be added together to obtain the missed detection rate of the lower limit LSL side (first missed detection risk interval). Similarly, the false negative rate P on the USL side (the second false negative risk interval) can be calculated. UsL-β The overkill rate P on the lower limit LSL side (first overkill risk interval) LSL-α Overkill rate P on the USL side (second overkill risk zone) USL-α .

[0105] Specifically, the overall missed detection rate can be calculated, and the overall missed detection probability (β risk) is shown in formula (1):

[0106]

[0107] The overall overkill probability (α risk) is shown in formula (2):

[0108]

[0109] The integral of the probability density function of the normal distribution, i.e., the cumulative distribution formula. It cannot be calculated directly by integration; it is obtained by Taylor series expansion. By performing an infinite approximation, an approximate value is obtained. Excel and Minitab use similar algorithms and have already implemented the calculation of the cumulative distribution formula, which can be directly called.

[0110] In the technical solution of this application embodiment, the product risk range is divided into multiple sub-ranges, and each sub-range corresponds to multiple production risk probabilities and multiple measurement risk probabilities. The product of the production risk probability and the measurement risk probability is calculated for each sub-range, and the sum of the products of the multiple sub-ranges is used as the final over / undershoot / missed detection rate. In the above method, dividing the product risk range into multiple sub-ranges for calculation reduces computational complexity, and calculating each sub-range separately makes the over / undershoot / missed detection rate calculation more accurate and reliable.

[0111] Figure 7A flowchart of the product evaluation algorithm steps according to another embodiment of this application is shown.

[0112] like Figure 7 As shown, another embodiment of the product evaluation algorithm 700 provided in this application includes, for example, steps S710-S750.

[0113] Step S710: Divide II into overkill area and missed kill area. The range of the missed kill area is represented as LSL-3σ. ms ~LSL and USL~USL+3σ ms The overkill zone is represented as LSL~LSL+3σ. ms and USL-3σ ms ~USL.

[0114] Step S720: For each region, divide it evenly into n smaller intervals s. n is a hyperparameter of the algorithm, which can be adjusted as needed.

[0115] Step S730: Calculate the starting point X coordinate l0 and ending point X coordinate l1 between each cell, and the mean value between each cell.

[0116] Step S740: Calculate P1 and P2 for each small interval, and perform integral calculation on P1 and P2 corresponding to multiple small intervals to obtain the probability of each missed kill interval and overkill interval.

[0117] LSL side-miss kill probability P LSL-β :

[0118] USL side-by-side kill probability P USL-β :

[0119] LSL side-cross kill probability P LSL-α :

[0120] USL side-pass kill probability P USL-α :

[0121] Step S750, missed detection rate P β =P LSL-β +P USL-β Overkill rate P α =P LSL-α +P USL-α False negative rate P β and overkill rate P α The value of the indicator can be used as the product evaluation indicator, which is the final product evaluation result.

[0122] In the technical solution of this application embodiment, the probability density function corresponding to the normal distribution data of the product and the probability density function corresponding to the normal distribution data of the measurement system are integrated in the corresponding intervals to obtain the production risk probability and the measurement risk probability. Finally, their products are summed to obtain the final product evaluation index value. The calculation is simple and more accurate.

[0123] This application provides a product evaluation device 800. Please refer to [link to relevant documentation]. Figure 8 The product evaluation device 800 includes:

[0124] The acquisition module 810 acquires product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, wherein the measurement system is used to perform product qualification measurements.

[0125] The determination module 820, based on product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, determines the production risk probability of the product and the measurement risk probability of the measurement system measuring the product.

[0126] Module 830 obtains the index values ​​corresponding to the product evaluation indicators based on the production risk probability and the measurement risk probability.

[0127] It is understood that for a detailed description of the product evaluation device 800, please refer to the description of the product evaluation method above.

[0128] For example, the determining module 820 is further configured to: determine the normal distribution data of the product and the normal distribution data of the measurement system based on the product statistical parameters, parameter limits and measurement statistical parameters of the measurement system; determine the production risk probability based on the normal distribution data of the product; and determine the measurement risk probability based on the normal distribution data of the measurement system.

[0129] For example, the determining module 820 is further configured to: determine the normal distribution data of the product based on the product process mean and product process standard deviation, including product statistical parameters; determine the product process risk interval from the normal distribution data of the product based on the parameter limits and the measurement standard deviation of the measurement system; determine the measurement mean of the measurement system based on the sub-intervals in the product process risk interval; and determine the normal distribution data of the measurement system based on the measurement mean and the measurement standard deviation of the measurement system.

[0130] For example, the determining module 820 is further configured to: determine the mean of the interval limits of the sub-intervals in the product process risk interval as the measurement mean of the measurement system.

[0131] For example, the determining module 820 is further configured to: obtain the interval probability of the product process risk interval based on the probability density function corresponding to the normal distribution data of the product, and use it as the production risk probability.

[0132] For example, the determining module 820 is further configured to: determine the measurement risk interval from the normal distribution data of the measurement system based on the parameter limit; and obtain the interval probability of the measurement risk interval based on the probability density function corresponding to the normal distribution data of the measurement system, as the measurement risk probability.

[0133] For example, the obtaining module 830 is also used to: obtain the index value corresponding to the product evaluation index based on the product of the production risk probability and the measurement risk probability.

[0134] For example, the product process risk interval is divided into multiple sub-intervals. The production risk probability includes multiple first sub-probabilities corresponding to multiple sub-intervals, and the measurement risk probability includes multiple second sub-probabilities corresponding to multiple sub-intervals. Based on the product of the production risk probability and the measurement risk probability, the index value corresponding to the product evaluation index is obtained, including: multiplying the first sub-probability and the second sub-probability corresponding to each sub-interval to obtain the index value corresponding to the product evaluation index of each sub-interval, and adding the index values ​​corresponding to the product evaluation index of multiple sub-intervals.

[0135] For example, the product evaluation indicators include at least one of the following: a missed detection indicator, wherein the missed detection rate corresponding to the missed detection indicator represents the probability that the production parameters of the product exceed the parameter limits, but the measurement system measures the product as qualified; and an over-detection indicator, wherein the over-detection rate corresponding to the over-detection indicator represents the probability that the production parameters of the product do not exceed the parameter limits, but the measurement system measures the product as unqualified.

[0136] For example, the parameter limit includes at least one of the lower limit of product tolerance and the upper limit of product tolerance; the product process risk range includes at least one of the following: a first missed detection risk range, which is determined based on the lower limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product exceed the lower limit of product tolerance; a second missed detection risk range, which is determined based on the upper limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product exceed the upper limit of product tolerance; a first over-detection risk range, which is determined based on the lower limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product do not exceed the lower limit of product tolerance; and a second over-detection risk range, which is determined based on the upper limit of product tolerance and the standard deviation of the measurement system, indicating that the production parameters of the product do not exceed the upper limit of product tolerance.

[0137] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the above embodiments.

[0138] On the other hand, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of any of the above embodiments.

[0139] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this application, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0140] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A product evaluation method, characterized in that, The method includes: Obtain product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, wherein the measurement system is used to perform product qualification measurements; Based on the product statistical parameters, the parameter limits, and the measurement statistical parameters of the measurement system, the production risk probability of the product and the measurement risk probability of the measurement system measuring the product are determined. Based on the production risk probability and the measurement risk probability, the corresponding index values ​​for the product evaluation indicators are obtained.

2. The method according to claim 1, characterized in that, The determination of the production risk probability of the product and the measurement risk probability of the measurement system measuring the product based on the product statistical parameters, the parameter limits, and the measurement statistical parameters of the measurement system includes: Based on the product statistical parameters, the parameter limits, and the measurement statistical parameters of the measurement system, determine the normal distribution data of the product and the normal distribution data of the measurement system; The production risk probability is determined based on the product's normal distribution data; The measurement risk probability is determined based on the normal distribution data of the measurement system.

3. The method according to claim 2, characterized in that, The product statistical parameters include the product process mean and the product process standard deviation, and the measurement statistical parameters of the measurement system include the measurement standard deviation of the measurement system; determining the normal distribution data of the product and the normal distribution data of the measurement system based on the product statistical parameters, the parameter limits, and the measurement statistical parameters of the measurement system includes: Based on the product process mean and the product process standard deviation, determine the normal distribution data of the product; Based on the parameter limits and the measurement standard deviation of the measurement system, the product process risk range is determined from the product's normal distribution data; The measurement mean of the measurement system is determined based on the sub-intervals within the product process risk interval. Based on the measurement mean and measurement standard deviation of the measurement system, the normal distribution data of the measurement system is determined.

4. The method according to claim 3, characterized in that, The determination of the measurement mean of the measurement system based on the product process risk range includes: The mean value of the interval limits of the sub-intervals in the product process risk interval is determined as the measurement mean value of the measurement system.

5. The method according to claim 3 or 4, characterized in that, The determination of the production risk probability based on the product's normal distribution data includes: Based on the probability density function corresponding to the normal distribution data of the product, the interval probability of the process risk interval of the product is obtained, which is used as the production risk probability.

6. The method according to any one of claims 2-5, characterized in that, The determination of the measurement risk probability based on the normal distribution data of the measurement system includes: Based on the parameter limits, the measurement risk interval is determined from the normal distribution data of the measurement system; Based on the probability density function corresponding to the normal distribution data of the measurement system, the interval probability of the measurement risk interval is obtained, which is used as the measurement risk probability.

7. The method according to any one of claims 3-5, characterized in that, The process of obtaining the index values ​​corresponding to the product evaluation indicators based on the production risk probability and the measurement risk probability includes: The index value corresponding to the product evaluation index is obtained by multiplying the production risk probability and the measurement risk probability.

8. The method according to claim 7, characterized in that, The product process risk interval is divided into multiple sub-intervals, the production risk probability includes multiple first sub-probabilities corresponding to the multiple sub-intervals, and the measurement risk probability includes multiple second sub-probabilities corresponding to the multiple sub-intervals; the index value corresponding to the product evaluation index is obtained based on the product of the production risk probability and the measurement risk probability, including: Multiply the first and second sub-probabilities corresponding to each sub-interval to obtain the index value corresponding to the product evaluation index for each sub-interval, and then add the index values ​​corresponding to the product evaluation index for multiple sub-intervals.

9. The method according to any one of claims 1-8, characterized in that, The product evaluation indicators include at least one of the following: The missed detection index, wherein the missed detection rate corresponding to the missed detection index represents the probability that the production parameters of a product exceed the parameter limits, but the measurement system measures the product and the result is qualified; The overkill index, wherein the overkill rate corresponding to the overkill index represents the probability that the production parameters of the product do not exceed the parameter limits, but the measurement system determines that the product is unqualified.

10. The method according to any one of claims 3-5, characterized in that, The parameter limits include at least one of the lower limit of product tolerance and the upper limit of product tolerance; the product process risk range includes at least one of the following: The first missed detection risk range is determined based on the lower limit of the product tolerance and the standard deviation of the measurement system. The first missed detection risk range indicates that the production parameters of the product exceed the lower limit of the product tolerance. The second omission risk range is determined based on the product tolerance upper limit and the measurement system standard deviation. The second omission risk range indicates that the product's production parameters exceed the product tolerance upper limit. The first overkill risk range is determined based on the lower limit of the product tolerance and the standard deviation of the measurement system. The first overkill risk range indicates that the production parameters of the product have not exceeded the lower limit of the product tolerance. The second over-exploitation risk range is determined based on the upper limit of the product tolerance and the standard deviation of the measurement system. The second over-exploitation risk range indicates that the production parameters of the product have not exceeded the upper limit of the product tolerance.

11. A product evaluation device, characterized in that, The device includes: The acquisition module is used to acquire product statistical parameters, parameter limits, and measurement statistical parameters of the measurement system, wherein the measurement system is used to perform product qualification measurements. The determination module is used to determine the production risk probability of the product and the measurement risk probability of the measurement system measuring the product based on the product statistical parameters, the parameter limits, and the measurement statistical parameters of the measurement system. The acquisition module is used to obtain the index value corresponding to the product evaluation index based on the production risk probability and the measurement risk probability.

12. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-10.

Images