Method, device, and computer equipment for detecting abnormal working parameters of production machines

Abstract

The present application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for detecting abnormalities in the operating parameters of a production machine. The method comprises: obtaining multiple data points of target operating parameters of a target machine during the production of a target wafer; forming a first edge line and a second edge line based on the multiple data points in a preset coordinate system, wherein the preset coordinate system uses the entry point number of the data point as the first coordinate axis and the target operating parameter value as the second coordinate axis; calculating the area of ​​the region between the first edge line and the second edge line; and determining, based on the area of ​​the region, whether the target operating parameters of the target machine during the production of the target wafer are abnormal. The present method can effectively control and intercept the target wafers produced by the target machine when the target operating parameters of the target machine are abnormal.

Description

Technical Field

[0001] The present application relates to the field of semiconductor production technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for detecting abnormalities in operating parameters of a production machine. Background Art

[0002] During semiconductor production, the Moving Range (MR) method is often used to analyze and determine the failure rates of various performance parameters of wafer products, thereby controlling wafer product quality. However, this method is prone to control failure when the failure rate of wafer product performance parameters is low. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for detecting abnormal working parameters of a production machine that can effectively control and intercept wafers to address the above technical problems.

[0004] A method for detecting abnormal working parameters of a production machine, comprising:

[0005] Acquire multiple data points of target operating parameters of a target tool during the production of a target wafer;

[0006] In a preset coordinate system, a first edge line and a second edge line are formed based on the plurality of data points, wherein the preset coordinate system has the ordinal number of the data point as a first coordinate axis and the target working parameter value as a second coordinate axis;

[0007] Calculating the area of ​​the region between the first edge line and the second edge line;

[0008] Based on the area of ​​the region, an abnormality of a target operating parameter of the target tool during the production of the target wafer is determined.

[0009] In one embodiment, forming the first edge line and the second edge line based on the plurality of data points in a preset coordinate system includes:

[0010] Among the plurality of data points, a plurality of upper inflection points and a plurality of lower inflection points are determined; wherein the plurality of upper inflection points are used to form the first edge line, and the plurality of lower inflection points are used to form the second edge line.

[0011] In one embodiment, determining a plurality of upper inflection points and a plurality of lower inflection points from the plurality of data points comprises:

[0012] Calculating the target operating parameter value variation between adjacent data points and generating a variation array;

[0013] identifying an upper inflection point among the plurality of data points according to the variation array;

[0014] A lower inflection point among the plurality of data points is identified based on the variance array.

[0015] In one embodiment, the target operating parameter value change between the i+1th data point and the ith data point is Δ i , the target operating parameter value change between the i+2th data point and the i+1th data point is △ i+1 , the change in the target operating parameter value between the i+3th data point and the i+2th data point is △ i+2 , 1≤i≤n, n is the number of data points,

[0016] The step of identifying an upper inflection point among the plurality of data points according to the variation array includes:

[0017] When i >0 and △ i+1 When <0, identify the i+1th data point as the upper inflection point;

[0018] When i >0 and △ i+1 =0 and △ i+2 When <0, identify the i+1th or i+2th data point as the upper inflection point;

[0019] and / or,

[0020] The step of identifying a lower inflection point among the plurality of data points according to the variation array includes:

[0021] When i <0 and △ i+1 When >0, identify the i+1th data point as the lower inflection point;

[0022] When i <0 and △ i+1 =0 and △ i+2 When >0, identify the i+1th or i+2th data point as the lower inflection point.

[0023] In one embodiment, calculating the area of ​​the region between the first edge line and the second edge line includes:

[0024] Calculating a first area of ​​a region between a first edge line and the first coordinate axis;

[0025] calculating a second area of ​​a region between a second edge line and the first coordinate axis;

[0026] The area of ​​the region is calculated based on the difference between the first area and the second area.

[0027] In one embodiment,

[0028] Calculating a first area of ​​a region between the first edge line and the first coordinate axis includes:

[0029] Sequentially pairing adjacent upper inflection points to generate multiple first paired line segments;

[0030] calculating the area of ​​a first trapezoid between the first paired line segment and the first coordinate axis;

[0031] calculating the sum of the areas of the first trapezoids corresponding to the first paired line segments to obtain the first area;

[0032] and / or,

[0033] Calculating a second area of ​​a region between the second edge line and the first coordinate axis includes:

[0034] Sequentially pairing adjacent lower inflection points to generate multiple second paired line segments;

[0035] calculating the area of ​​a second trapezoid between the second paired line segment and the first coordinate axis;

[0036] The sum of the areas of the second trapezoids corresponding to the second paired line segments is calculated to obtain the second area.

[0037] In one embodiment, after determining the abnormality of the target operating parameter of the target machine based on the area of ​​the region, the method further includes:

[0038] When the target operating parameters of the target machine are abnormal, the target wafer abnormality is reported to a manufacturing execution system.

[0039] A device for detecting abnormal working parameters of a production machine, the device comprising:

[0040] An acquisition module, used to acquire multiple data points of target operating parameters of a target machine during the production of a target wafer;

[0041] an edge line forming module, configured to form a first edge line and a second edge line based on the plurality of data points in a preset coordinate system, wherein the preset coordinate system has an entry point number of the data point as a first coordinate axis and a target working parameter value as a second coordinate axis;

[0042] a calculation module, configured to calculate the area of ​​a region between the first edge line and the second edge line;

[0043] The abnormality determination module is used to determine the abnormality of the target operating parameters of the target machine during the production of the target wafer based on the area of ​​the region.

[0044] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0045] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0046] A computer program product comprises a computer program, wherein the computer program implements the steps of the above method when executed by a processor.

[0047] The above-mentioned method, device, computer equipment, computer-readable storage medium, and computer program product for detecting abnormal working parameters of production machines have the following unexpected technical effects:

[0048] First, multiple data points of the target operating parameters of the target machine during the production of the target wafer are obtained, and a first edge line and a second edge line are formed based on the multiple data points. Then, the area of ​​the region between the first edge line and the second edge line is calculated, so that the degree of fluctuation of the target operating parameter value of the target machine during the production of the target wafer can be quantified, and then the abnormality of the target operating parameter of the target machine during the production of the target wafer can be effectively judged. When the target operating parameters of the target machine are abnormal, the performance parameters of the target wafer are likely to be abnormal. Based on this, the corresponding target wafer can be effectively controlled and intercepted through the abnormality of the target operating parameters of the target machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 A schematic diagram of a curve showing the failure rate of bin 38 of a wafer product analyzed using MR values ​​using conventional technology;

[0051] Figure 2 1 is a flow chart of a method for detecting abnormality in operating parameters of a production machine in one embodiment;

[0052] Figure 3is a schematic diagram of a first edge line and a second edge line in one embodiment;

[0053] Figure 4 is the area of ​​the region between the first edge line and the second edge line in one embodiment, Figure 1 Schematic diagram of a curve analyzing the failure rate of bin 38 of the same batch of wafers;

[0054] Figure 5 Schematic diagram of an upper inflection point and a lower inflection point in one embodiment;

[0055] Figure 6 1 is a flow chart of steps for determining a plurality of upper inflection points and a plurality of lower inflection points from a plurality of data points in one embodiment;

[0056] Figure 7 A schematic diagram of identifying an upper inflection point in one embodiment;

[0057] Figure 8 A schematic diagram of identifying a lower inflection point in one embodiment;

[0058] Figure 9 A schematic flow chart of a step of calculating the area of ​​a region between a first edge line and a second edge line in one embodiment;

[0059] Figure 10 A schematic flow chart of a step of calculating a first area of ​​a region between a first edge line and a first coordinate axis in one embodiment;

[0060] Figure 11 is a schematic diagram of a first paired line segment and a second paired line segment in one embodiment;

[0061] Figure 12 is a schematic diagram of the area of ​​a first trapezoid between a first paired line segment and a first coordinate axis in one embodiment;

[0062] Figure 13 FIG. 4 is a structural block diagram of a device for detecting abnormal working parameters of a production machine in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0064] As mentioned in the background art, in traditional technologies, it is easy to encounter the problem of wafer product card control failure.

[0065] Specifically, see, for example, Figure 1The failure rate (failure percentage) of wafer products from different batches (Batch A, Batch B, and Batch C) regarding the 38th performance parameter (bin 38) is different. Figure 1 The numerical value of the horizontal axis in represents the sequence number of wafers in each batch. For example, 1 in batch A represents the first wafer in batch A.

[0066] For some wafers with lower failure rates (such as some wafers from Batch B and wafers from Batch C), while the failure rate is relatively low, it's still difficult to achieve the ideal value, necessitating card control and interception. In this case, if the traditional method uses a MR value threshold of 0.02 to intercept wafer products, card control will fail for these wafers because the MR value is less than 0.02.

[0067] At the same time, the inventors have discovered through research that the failure of performance parameters of some wafer products is related to the fluctuation of operating parameters (such as voltage) of the production machines of the wafer products.

[0068] Based on this, embodiments of the present application provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for detecting abnormalities in operating parameters of a production machine, so as to effectively control products that may have problems.

[0069] At the same time, it can be understood that the working parameter anomaly detection method, device, computer equipment, computer-readable storage medium and computer program product of the production machine provided in the embodiments of the present application can be applied to, but not limited to, error detection and classification systems for semiconductor production, and can be applied to, but not limited to, card control and interception of wafers with a low performance parameter failure rate.

[0070] In one embodiment, see Figure 2 , provides a method for detecting abnormal working parameters of a production machine, comprising:

[0071] Step S10, obtaining multiple data points of target operating parameters of a target machine during the production of a target wafer;

[0072] Step S20, see Figure 3 , forming a first edge line and a second edge line based on a plurality of data points in a preset coordinate system, wherein the preset coordinate system has the sequence number of the data point as the first coordinate axis and the target working parameter value as the second coordinate axis;

[0073] Step S30, calculating the area of ​​the region between the first edge line and the second edge line;

[0074] Step S40 , determining abnormalities of target operating parameters of the target tool during the production of the target wafer based on the area of ​​the region.

[0075] In step S10 , the target operating parameter is an operating parameter of the target tool that may affect the performance parameter of the target wafer. As an example, the target operating parameter may include the voltage of the target tool.

[0076] During the production of target wafers on the target machine, a voltage detection device (e.g., a sensor) within the machine can detect and upload the actual values ​​of the target operating parameters of the production machine at a preset frequency, generating multiple data points. The preset frequency can be set based on actual needs.

[0077] In step S20, refer to Figure 3 The preset coordinate system uses the data point sequence number as the first coordinate axis and the target operating parameter value (such as voltage value) as the second coordinate axis.

[0078] The data point entry number may be an ordinal number indicating the order in which the data points are obtained. The entry number of the i-th obtained data point may be i, where i is a positive integer. For example, the entry number of the first obtained data point may be 1.

[0079] In a preset coordinate system, a first edge line and a second edge line are formed based on a plurality of data points. A target operating parameter value of the first edge line is greater than a target operating parameter value of the second edge line.

[0080] In step S30 , the first coordinate axis and the second coordinate axis may be used as size measurement benchmarks in different directions to calculate the area of ​​the region between the first edge line and the second edge line.

[0081] In step S40, if the area between the first edge line and the second edge line is less than (or less than or equal to) the area threshold, it indicates that the fluctuation of the target operating parameter value of the target tool is small. In this case, it can be determined that the target operating parameter of the target tool is normal during the production process of the target wafer.

[0082] When the area between the first edge line and the second edge line is equal to or greater than the area threshold, it indicates that the target operating parameter value of the target tool has fluctuated significantly. In this case, it can be determined that the target operating parameter of the target tool is abnormal during the production process of the target wafer.

[0083] The area threshold can be set according to actual needs. For example, the area threshold can be set to 300 to 500 (such as 400).

[0084] In this embodiment, a plurality of data points of the target operating parameters of the target machine during the production of the target wafer are first obtained, and a first edge line and a second edge line are formed based on the plurality of data points. Then, the area of ​​the region between the first edge line and the second edge line is calculated, so that the degree of fluctuation of the target operating parameter value of the target machine during the production of the target wafer can be quantified, and then the abnormality of the target operating parameter of the target machine during the production of the target wafer can be effectively judged. When the target operating parameter of the target machine is abnormal, the performance parameters of the target wafer are likely to be abnormal. Based on this, the corresponding target wafer can be effectively controlled and intercepted by the abnormality of the target operating parameter of the target machine.

[0085] As a verification, see Figure 4 , Figure 4 is the area of ​​the region between the first edge line and the second edge line in one embodiment, Figure 1 Schematic diagram of the curve analyzing the failure rate of bin 38 of the same batch of wafers.

[0086] Will Figure 4 and Figure 1 By comparison, it can be seen that, through the method of this embodiment, by comparing and analyzing the area of ​​the region between the first edge line and the second edge line with the area threshold, the Figure 1 Effective card control and interception can be performed on wafers with a low failure rate that are difficult to control and intercept by MR value.

[0087] In one embodiment, after step S40, the method further includes:

[0088] In step S50 , when the target operating parameters of the target tool are abnormal, the target wafer abnormality is reported to the manufacturing execution system.

[0089] After receiving the reported information, the Manufacturing Execution System (MES) can generate an abnormal problem record sheet, thereby reminding the relevant person in charge to handle the abnormal problem.

[0090] For example, after receiving the abnormal problem record, the relevant person in charge can adjust the target operating parameters of the target machine to restore it to normal. And / or, the relevant person in charge can further process the target wafer (such as rework or scrapping).

[0091] In one embodiment, see Figure 5 , step S20 includes:

[0092] Step S21 : determining a plurality of upper inflection points and a plurality of lower inflection points from a plurality of data points; wherein the plurality of upper inflection points are used to form a first edge line, and the plurality of lower inflection points are used to form a second edge line.

[0093] The upper inflection point and the lower inflection point are both inflection point values ​​of the target operating parameter values.

[0094] The target operating parameter value of the upper inflection point is not less than the target operating parameter values ​​of the two data points located on both sides of the upper inflection point.

[0095] The target operating parameter value of the lower inflection point is not greater than the target operating parameter values ​​of the two data points located on both sides of the adjacent inflection point.

[0096] As an example, after determining multiple upper inflection points and multiple lower inflection points, the multiple upper inflection points can be connected sequentially according to their entry point sequence numbers to form a first edge line; at the same time, the multiple lower inflection points can be connected sequentially according to their entry point sequence numbers to form a second edge line. In this case, the first edge line and the second edge line can be continuous solid line segments.

[0097] Of course, the forms of the first edge line and the second edge line are not limited thereto. For example, the first edge line may be a discontinuous dashed line segment formed by multiple upper inflection points. And / or, the second edge line may be a discontinuous dashed line segment formed by multiple lower inflection points.

[0098] In this embodiment, by determining the upper inflection point and the lower inflection point, the first edge line and the second edge line can be formed conveniently and effectively.

[0099] Of course, in other embodiments, the first edge line and the second edge line may also be obtained according to other algorithms, which is not limited here.

[0100] In one embodiment, see Figure 6 , step S21 includes:

[0101] Step S211, calculating the target operating parameter value variation between adjacent data points and generating a variation array;

[0102] Step S212, identifying an upper inflection point among the plurality of data points according to the variation array;

[0103] Step S213: identifying the lower inflection point among the multiple data points according to the variation array.

[0104] In step S211, the number of data points obtained in step S10 is set to n. The target working parameter value of the data point with the sequence number k can be y k . 1≤k≤n.

[0105] A target operating parameter value variation is formed between every two adjacent data points, and n-1 target operating parameter value variations can be obtained from n data points, so the variation array includes n-1 target operating parameter value variations.

[0106] Among them, the change in the target operating parameter value between the i+1th data point and the i-th data point can be △ i =y i+1 -y i Where i is a positive integer. Then the variable array can be (△1, △2, ..., △ j ,…,△ n-1 ).

[0107] In step S212, the upper inflection point may be determined based on the magnitude relationship between adjacent target operating parameter value changes.

[0108] As an example, see Figure 7 , the change in the target operating parameter value between the i+1th data point and the ith data point is △ i , the target operating parameter value change between the i+2th data point and the i+1th data point is △ i+1 , the change in the target operating parameter value between the i+3th data point and the i+2th data point is △ i+2 , 1≤i≤n, n is the number of data points.

[0109] Based on this, step S212 may include:

[0110] Step S2121, when △ i >0 and △ i+1 When <0, identify the i+1th data point as the upper inflection point;

[0111] Step S2122, when △ i >0 and △ i+1 =0 and △ i+2 When <0, identify the i+1th or i+2th data point as the upper inflection point.

[0112] In step S2121, refer to Figure 7 In Figure (a), △ i >0 and △ i+1 <0, the target operating parameter values ​​corresponding to the i-th data point, the i+1-th data point, and the i+2-th data point show a trend of first increasing and then decreasing. Based on this, the i+1-th data point can be determined as the upper inflection point.

[0113] In step S2122, refer to Figure 7 In Figure (b), △ i >0, indicating that the target operating parameter value of the i+1th data point is greater than the target operating parameter value of the i-th data point.

[0114] △ i+1 =0, indicating that the target operating parameter value of the i+2th data point is equal to the target operating parameter value of the i+1th data point.

[0115] △ i+2 <0, indicating that the target operating parameter value of the i+2th data point is greater than the target operating parameter value of the i+3th data point.

[0116] The target operating parameter values ​​corresponding to the four data points (i, i+1, i+2, and i+3) show a trend that first increases, then levels off, and then decreases. Based on this, the i+1 data point can be determined to be the upper inflection point. Alternatively, the i+2 data point can also be determined to be the upper inflection point.

[0117] In this case, a single data point or one of two equal data points with a target operating parameter value greater than the two data points on both sides is used as the upper inflection point, thereby determining a sufficient number of upper inflection points while ensuring accurate definition of the inflection points. It will be understood that equal data points here refer to data points with the same target operating parameter value.

[0118] Of course, in other examples, the method for identifying the upper inflection point is not limited to this. For example, a single data point whose target operating parameter value is greater than the data points on either side may be determined as the upper inflection point. Alternatively, one of m (e.g., three) equal data points whose target operating parameter value is greater than the data points on either side may be determined as the upper inflection point.

[0119] In step S213 , the lower inflection point may be determined based on the magnitude relationship between adjacent target operating parameter value changes.

[0120] As an example, see Figure 8 , the change in the target operating parameter value between the i+1th data point and the ith data point is △ i , the target operating parameter value change between the i+2th data point and the i+1th data point is △ i+1 , the change in the target operating parameter value between the i+3th data point and the i+2th data point is △ i+2 , 1≤i≤n, n is the number of data points.

[0121] Based on this, step S213 may include:

[0122] Step S2131, when △ i <0 and △ i+1 When >0, identify the i+1th data point as the lower inflection point;

[0123] Step S2132, when △ i <0 and △ i+1 =0 and △ i+2 When >0, identify the i+1th or i+2th data point as the lower inflection point.

[0124] In step S2131, refer to Figure 8 In Figure (a), △ i <0 and △ i+1 >0, then the target operating parameter values ​​corresponding to the i-th data point, the i+1-th data point, and the i+2-th data point show a trend of first decreasing and then increasing. Based on this, the i+1-th data point can be determined as the lower inflection point.

[0125] In step S2122, refer to Figure 8 In Figure (b), △ i <0, indicating that the target operating parameter value of the i+1th data point is less than the target operating parameter value of the i-th data point.

[0126] △ i+1 =0, indicating that the target operating parameter value of the i+2th data point is equal to the target operating parameter value of the i+1th data point.

[0127] △ i+2 >0, indicating that the target operating parameter value of the i+2th data point is less than the target operating parameter value of the i+3th data point.

[0128] The target operating parameter values ​​corresponding to the four data points (i, i+1, i+2, and i+3) show a trend that first decreases, then levels off, and then increases. Based on this, the i+1 data point can be determined to be the lower inflection point. Alternatively, the i+2 data point can also be determined to be the lower inflection point.

[0129] In this case, a single data point or one of two equal data points with a target operating parameter value smaller than the two data points on both sides is used as the lower inflection point, thereby determining a sufficient number of lower inflection points while ensuring an accurate definition of the inflection point. It is understood that equal data points here refer to data points with the same target operating parameter value.

[0130] Of course, in other examples, the method for identifying the lower inflection point is not limited to this. For example, a single data point whose target operating parameter value is smaller than the data points on either side may be determined as the lower inflection point. Alternatively, one of m (e.g., three) equal data points whose target operating parameter value is larger than the data points on either side may be determined as the lower inflection point.

[0131] In this embodiment, the upper inflection point and the lower inflection point are effectively determined based on the change in the target operating parameter value between adjacent data points.

[0132] Of course, in other embodiments, the upper inflection point and / or the lower inflection point may be determined in other ways, such as by directly comparing the target operating parameter values ​​of adjacent data points.

[0133] In one embodiment, see Figure 9 , step S30 includes:

[0134] Step S31, calculating a first area of ​​a region between a first edge line and a first coordinate axis;

[0135] Step S32, calculating a second area of ​​a region between the second edge line and the first coordinate axis;

[0136] Step S33: Calculate the area of ​​the region based on the difference between the first area and the second area.

[0137] In step S31, a first area of ​​a region between the first edge line and the first coordinate axis can be obtained using a first preset software algorithm. The first preset software algorithm can be specifically configured according to actual needs.

[0138] In step S32, the second area of ​​the region between the second edge line and the first coordinate axis can be obtained using a second preset software algorithm. The second preset software algorithm can be specifically configured according to actual needs.

[0139] Step S33 may be used to subtract the second area from the first area to obtain the region area.

[0140] In this embodiment, the area of ​​the region between the first edge line and the second edge line is obtained simply and effectively by using the difference between the areas of the regions between the first coordinate axis and the first edge line.

[0141] In one embodiment, see Figure 10 , step S31 may include:

[0142] Step S311: sequentially pair adjacent upper inflection points to generate a plurality of first pairing line segments;

[0143] Step S312, calculating the area of ​​the first trapezoid between the first paired line segment and the first coordinate axis;

[0144] Step S313 : calculating the sum of the areas of the first trapezoids corresponding to the first paired line segments to obtain a first area.

[0145] In step S311, refer to Figure 11 , sequentially pair the adjacent upper inflection points, that is, sequentially pair the data points used as upper inflection points according to the sequence number of the entry points to obtain multiple first paired line segments.

[0146] For example, see Figure 12 , the upper inflection points in the figure are data points A3, A6, A 10 、A 14 、A 16 、A 18. Among them, 3, 6, 10, 14, 16, and 18 are the entry point numbers of the data points, that is, the first coordinate axis coordinates of the data points.

[0147] Among these 6 upper inflection points, 5 first paired line segments can be generated by sequentially pairing the adjacent upper inflection points. The 5 first paired line segments are L 3-6 , L 6-10 , L 10-14 , L 14-16 , L 16-18 .

[0148] In step S312 , the area of ​​each first trapezoid between each first paired line segment and the first coordinate axis may be calculated.

[0149] For example, Figure 12 , the 5 first paired line segments L 3-6 , L 6-10 , L 10-14 , L 14-16 , L 16-18 The area of ​​the first trapezoid between the first coordinate axis and the first coordinate axis can be S 3-6 、S 6-10 、S 10-14 、S 14-16 、S 16-18 .

[0150] Among them, S i-j =1 / 2(U j +U i )*(ji), S i-j Indicates the adjacent upper inflection point A i With A j The first pairing line segment L between i-j The area of ​​the first trapezoid between the first coordinate axis and the first coordinate axis. i represents the upper inflection point A i The entry point number (that is, the data point A as the upper inflection point i j represents the upper inflection point A. j The entry point number (that is, the data point A as the upper inflection point j The sequence number of the entry point). U i Indicates the upper inflection point A i The target operating parameter value. j Indicates the upper inflection point A j The target operating parameter value. For example, S 3-6 =1 / 2(U j +U i )*(6-3).

[0151] In step S313 , the areas of the first trapezoids corresponding to all the first paired line segments are summed up to obtain the total area of ​​the region between the first edge line and the first coordinate axis, that is, the first area.

[0152] In this embodiment, first paired line segments are formed between adjacent upper inflection points, and the areas of the first trapezoids between each first paired line segment and the first coordinate axis are integrated and summed, thereby effectively obtaining the first area.

[0153] In one embodiment, step S32 may include:

[0154] Step S321, sequentially pairing adjacent lower inflection points to generate a plurality of second paired line segments;

[0155] Step S322, calculating the area of ​​the second trapezoid between the second paired line segment and the first coordinate axis;

[0156] Step S323 , calculating the sum of the areas of the second trapezoids corresponding to the second paired line segments to obtain a second area.

[0157] In step S321 , adjacent lower inflection points are sequentially paired, that is, the data points serving as lower inflection points are sequentially paired according to the sequence numbers of the entry points to obtain a plurality of second paired line segments.

[0158] In step S322 , the area of ​​each second trapezoid between each second paired line segment and the first coordinate axis may be calculated.

[0159] The second paired line segment L p-q The area of ​​the second trapezoid between the first coordinate axis can be expressed as S p-q =1 / 2(U q +U p )*(qp). Where p represents the lower inflection point A p The entry point number (that is, the data point A as the lower inflection point p q represents the lower inflection point A q The entry point number (that is, the data point A as the lower inflection point q The sequence number of the entry point). U p Indicates the lower inflection point A p The target operating parameter value. q Indicates the lower inflection point A q target operating parameter values.

[0160] In step S313 , the areas of the second trapezoids corresponding to all the second paired line segments are summed up to obtain the total area of ​​the region between the second edge line and the first coordinate axis, that is, the second area.

[0161] It can be understood that the specific execution process of steps S321, S322 and S323 can be similar to that of steps S311, S312 and S313, and will not be described in detail here.

[0162] In this embodiment, second paired line segments are formed between adjacent lower inflection points, and the areas of the second trapezoids between each second paired line segment and the first coordinate axis are integrated and summed, thereby effectively obtaining the second area.

[0163] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0164] Based on the same inventive concept, the present application also provides an apparatus for detecting anomalies in operating parameters of production machines, which is used to implement the aforementioned method for detecting anomalies in operating parameters of production machines. The solution provided by this apparatus is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the apparatus for detecting anomalies in operating parameters of production machines provided below can be found in the aforementioned method for detecting anomalies in operating parameters of production machines, and will not be further elaborated here.

[0165] In one embodiment, see Figure 13 , provides a device for detecting abnormality in working parameters of a production machine, comprising: an acquisition module 100, an edge line forming module 200, a calculation module 300 and an abnormality determination module 400, wherein:

[0166] The acquisition module 100 is used to acquire multiple data points of target operating parameters of a target tool during the process of producing a target wafer.

[0167] The edge line forming module 200 is used to form a first edge line and a second edge line based on multiple data points in a preset coordinate system. The preset coordinate system uses the data point sequence number as the first coordinate axis and the target working parameter value as the second coordinate axis.

[0168] The calculation module 300 is used to calculate the area of ​​the region between the first edge line and the second edge line.

[0169] The abnormality determination module 400 is used to determine abnormalities of target operating parameters of a target tool during the production of a target wafer based on the area of ​​the region.

[0170] In one embodiment, the edge line forming module 200 includes an inflection point confirmation unit for determining a plurality of upper inflection points and a plurality of lower inflection points from a plurality of data points, wherein the plurality of upper inflection points are used to form a first edge line, and the plurality of lower inflection points are used to form a second edge line.

[0171] In one embodiment, the inflection point confirmation unit includes a variation array generation subunit, an upper inflection point confirmation subunit, and a lower inflection point confirmation subunit.

[0172] The variation array generation subunit is used to calculate the variation of the target working parameter value between adjacent data points and generate a variation array.

[0173] The upper inflection point confirmation subunit is used to identify the upper inflection point among multiple data points based on the variation array.

[0174] The lower inflection point confirmation subunit is used to identify the lower inflection point among multiple data points based on the variation array.

[0175] In one embodiment, the target operating parameter value change between the i+1th data point and the ith data point is Δ i , the target operating parameter value change between the i+2th data point and the i+1th data point is △ i+1 , the change in the target operating parameter value between the i+3th data point and the i+2th data point is △ i+2 , 1≤i≤n, n is the number of data points.

[0176] The upper inflection point confirmation subunit is used to i >0 and △ i+1 <0, identify the i+1th data point as the upper inflection point, and in △ i >0 and △ i+1 =0 and △ i+2 When <0, identify the i+1th or i+2th data point as the upper inflection point.

[0177] In one embodiment, the lower inflection point confirmation subunit is used to i <0 and △ i+1 >0, identify the i+1th data point as the lower inflection point, and in △ i <0 and △ i+1 =0 and △ i+2 When >0, identify the i+1th or i+2th data point as the lower inflection point.

[0178] In one embodiment, the calculation module 300 includes a first calculation unit, a second calculation unit, and a third calculation unit. The first calculation unit is configured to calculate a first area of ​​a region between a first edge line and a first coordinate axis. The second calculation unit is configured to calculate a second area of ​​a region between a second edge line and the first coordinate axis. The third calculation unit is configured to calculate an area of ​​a region based on the difference between the first area and the second area.

[0179] In one embodiment, the first calculation unit is configured to sequentially pair adjacent upper inflection points to generate a plurality of first paired line segments; calculate the area of ​​a first trapezoid between the first paired line segments and the first coordinate axis; and calculate the sum of the areas of the first trapezoids corresponding to the first paired line segments to obtain a first area.

[0180] In one embodiment, the second calculation unit is configured to sequentially pair adjacent lower inflection points to generate a plurality of second paired line segments; calculate the area of ​​a second trapezoid between the second paired line segments and the first coordinate axis; and calculate the sum of the areas of the second trapezoids corresponding to the second paired line segments to obtain a second area.

[0181] In one embodiment, the apparatus for detecting abnormal working parameters of a production tool further includes a reporting module configured to report abnormality of a target wafer to a manufacturing execution system when a target working parameter of the target tool is abnormal.

[0182] Each module in the aforementioned production machine operating parameter anomaly detection device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device in hardware form, or can be stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0183] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0184] Step S10, obtaining multiple data points of target operating parameters of a target machine during the production of a target wafer;

[0185] Step S20, forming a first edge line and a second edge line based on the plurality of data points in a preset coordinate system, wherein the preset coordinate system has the data point sequence number as the first coordinate axis and the target working parameter value as the second coordinate axis;

[0186] Step S30, calculating the area of ​​the region between the first edge line and the second edge line;

[0187] Step S40 , determining abnormalities of target operating parameters of the target tool during the production of the target wafer based on the area of ​​the region.

[0188] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Step S50 , when the target operating parameters of the target tool are abnormal, reporting the target wafer abnormality to the manufacturing execution system.

[0189] In one embodiment, when the processor executes the computer program, the following steps are also implemented: Step S21, determining multiple upper inflection points and multiple lower inflection points among multiple data points; wherein the multiple upper inflection points are used to form a first edge line, and the multiple lower inflection points are used to form a second edge line.

[0190] In one embodiment, when the processor executes the computer program, the following steps are also implemented: step S211, calculating the change in the target working parameter value between adjacent data points and generating a change array; step S212, identifying the upper inflection point among multiple data points based on the change array; step S213, identifying the lower inflection point among multiple data points based on the change array.

[0191] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Step S2121, when △ i >0 and △ i+1 <0, identify the i+1th data point as the upper inflection point; step S2122, when △ i >0 and △ i+1 =0 and △ i+2 When <0, identify the i+1th or i+2th data point as the upper inflection point.

[0192] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Step S2131, when △ i <0 and △ i+1 >0, identify the i+1th data point as the lower inflection point; step S2132, when △ i <0 and △ i+1 =0 and △ i+2 When >0, identify the i+1th or i+2th data point as the lower inflection point.

[0193] In one embodiment, when the processor executes the computer program, the following steps are further implemented: step S31, calculating the first area of ​​the area between the first edge line and the first coordinate axis; step S32, calculating the second area of ​​the area between the second edge line and the first coordinate axis; step S33, calculating the area of ​​the area based on the difference between the first area and the second area.

[0194] In one embodiment, when executing the computer program, the processor further implements the following steps: step S311, sequentially pairing adjacent upper inflection points to generate multiple first paired line segments; step S312, calculating the area of ​​the first trapezoid between the first paired line segments and the first coordinate axis; step S313, calculating the sum of the areas of the first trapezoids corresponding to the first paired line segments to obtain a first area.

[0195] In one embodiment, when executing the computer program, the processor further implements the following steps: step S321, sequentially pairing adjacent lower inflection points to generate multiple second paired line segments; step S322, calculating the area of ​​the second trapezoid between the second paired line segments and the first coordinate axis; step S323, calculating the sum of the areas of the second trapezoids corresponding to the second paired line segments to obtain a second area.

[0196] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0197] Step S10, obtaining multiple data points of target operating parameters of a target machine during the production of a target wafer;

[0198] Step S20, forming a first edge line and a second edge line based on the plurality of data points in a preset coordinate system, wherein the preset coordinate system has the data point sequence number as the first coordinate axis and the target working parameter value as the second coordinate axis;

[0199] Step S30, calculating the area of ​​the region between the first edge line and the second edge line;

[0200] Step S40 , determining abnormalities of target operating parameters of the target tool during the production of the target wafer based on the area of ​​the region.

[0201] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: Step S50 , when the target operating parameters of the target tool are abnormal, reporting the target wafer abnormality to the manufacturing execution system.

[0202] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: Step S21, among multiple data points, multiple upper inflection points and multiple lower inflection points are determined; wherein, the multiple upper inflection points are used to form a first edge line, and the multiple lower inflection points are used to form a second edge line.

[0203] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: Step S211, calculating the change in the target working parameter value between adjacent data points and generating a change array; Step S212, identifying the upper inflection point among multiple data points based on the change array; Step S213, identifying the lower inflection point among multiple data points based on the change array.

[0204] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: Step S2121, when △ i >0 and △ i+1 <0, identify the i+1th data point as the upper inflection point; step S2122, when △ i >0 and △ i+1 =0 and △ i+2 When <0, identify the i+1th or i+2th data point as the upper inflection point.

[0205] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: Step S2131, when △ i <0 and △ i+1 >0, identify the i+1th data point as the lower inflection point; step S2132, when △ i <0 and △ i+1 =0 and △ i+2 When >0, identify the i+1th or i+2th data point as the lower inflection point.

[0206] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: step S31, calculating the first area of ​​the area between the first edge line and the first coordinate axis; step S32, calculating the second area of ​​the area between the second edge line and the first coordinate axis; step S33, calculating the area of ​​the area based on the difference between the first area and the second area.

[0207] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: step S311, sequentially pairing adjacent upper inflection points to generate multiple first paired line segments; step S312, calculating the area of ​​the first trapezoid between the first paired line segments and the first coordinate axis; step S313, calculating the sum of the areas of the first trapezoids corresponding to the first paired line segments to obtain a first area.

[0208] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: step S321, sequentially pairing adjacent lower inflection points to generate multiple second paired line segments; step S322, calculating the area of ​​the second trapezoid between the second paired line segments and the first coordinate axis; step S323, calculating the sum of the areas of the second trapezoids corresponding to the second paired line segments to obtain a second area.

[0209] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0210] Step S10, obtaining multiple data points of target operating parameters of a target machine during the production of a target wafer;

[0211] Step S20, forming a first edge line and a second edge line based on the plurality of data points in a preset coordinate system, wherein the preset coordinate system has the data point sequence number as the first coordinate axis and the target working parameter value as the second coordinate axis;

[0212] Step S30, calculating the area of ​​the region between the first edge line and the second edge line;

[0213] Step S40 , determining abnormalities of target operating parameters of the target tool during the production of the target wafer based on the area of ​​the region.

[0214] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: Step S50 , when the target operating parameters of the target tool are abnormal, reporting the target wafer abnormality to the manufacturing execution system.

[0215] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: Step S21, among multiple data points, multiple upper inflection points and multiple lower inflection points are determined; wherein, the multiple upper inflection points are used to form a first edge line, and the multiple lower inflection points are used to form a second edge line.

[0216] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: Step S211, calculating the change in the target working parameter value between adjacent data points and generating a change array; Step S212, identifying the upper inflection point among multiple data points based on the change array; Step S213, identifying the lower inflection point among multiple data points based on the change array.

[0217] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: Step S2121, when △ i >0 and △ i+1 <0, identify the i+1th data point as the upper inflection point; step S2122, when △ i >0 and △ i+1 =0 and △ i+2 When <0, identify the i+1th or i+2th data point as the upper inflection point.

[0218] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: Step S2131, when △ i <0 and △ i+1 >0, identify the i+1th data point as the lower inflection point; step S2132, when △ i <0 and △ i+1 =0 and △ i+2 When >0, identify the i+1th or i+2th data point as the lower inflection point.

[0219] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: step S31, calculating the first area of ​​the area between the first edge line and the first coordinate axis; step S32, calculating the second area of ​​the area between the second edge line and the first coordinate axis; step S33, calculating the area of ​​the area based on the difference between the first area and the second area.

[0220] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: step S311, sequentially pairing adjacent upper inflection points to generate multiple first paired line segments; step S312, calculating the area of ​​the first trapezoid between the first paired line segments and the first coordinate axis; step S313, calculating the sum of the areas of the first trapezoids corresponding to the first paired line segments to obtain a first area.

[0221] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: step S321, sequentially pairing adjacent lower inflection points to generate multiple second paired line segments; step S322, calculating the area of ​​the second trapezoid between the second paired line segments and the first coordinate axis; step S323, calculating the sum of the areas of the second trapezoids corresponding to the second paired line segments to obtain a second area.

[0222] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0223] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0224] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for detecting abnormal working parameters of a production machine, characterized in that: include: Acquire multiple data points of target operating parameters of a target tool during the production of a target wafer; In a preset coordinate system, a first edge line and a second edge line are formed based on the plurality of data points, wherein the preset coordinate system has the ordinal number of the data point as a first coordinate axis and the target working parameter value as a second coordinate axis; Calculating the area of ​​the region between the first edge line and the second edge line; Based on the area of ​​the region, determining abnormality of target operating parameters of the target tool during the production of the target wafer; The forming of the first edge line and the second edge line based on the plurality of data points in a preset coordinate system includes: Among the plurality of data points, a plurality of upper inflection points and a plurality of lower inflection points are determined; wherein the plurality of upper inflection points are used to form the first edge line, and the plurality of lower inflection points are used to form the second edge line.

2. The method for detecting abnormal working parameters of a production machine according to claim 1, wherein: Determining a plurality of upper inflection points and a plurality of lower inflection points from the plurality of data points comprises: Calculating the target operating parameter value variation between adjacent data points and generating a variation array; identifying an upper inflection point among the plurality of data points according to the variation array; A lower inflection point among the plurality of data points is identified based on the variance array.

3. The method for detecting abnormality in operating parameters of a production machine according to claim 2, wherein: The change in the target operating parameter value between the i+1th data point and the i-th data point is △ i , the target operating parameter value change between the i+2th data point and the i+1th data point is △ i+1 , the change in the target operating parameter value between the i+3th data point and the i+2th data point is △ i+2 , 1≤i≤n, n is the number of data points, The step of identifying an upper inflection point among the plurality of data points according to the variation array includes: When i >0 and △ i+1 When <0, identify the i+1th data point as the upper inflection point; When i >0 and △ i+1 =0 and △ i+2 When <0, identify the i+1th or i+2th data point as the upper inflection point; and / or, The step of identifying a lower inflection point among the plurality of data points according to the variation array includes: When i <0 and △ i+1 When >0, identify the i+1th data point as the lower inflection point; When i <0 and △ i+1 =0 and △ i+2 When >0, identify the i+1th or i+2th data point as the lower inflection point.

4. The method for detecting abnormality in operating parameters of a production machine according to claim 1, wherein: The calculating the area of ​​the region between the first edge line and the second edge line includes: Calculating a first area of ​​a region between a first edge line and the first coordinate axis; calculating a second area of ​​a region between a second edge line and the first coordinate axis; The area of ​​the region is calculated based on the difference between the first area and the second area.

5. The method for detecting abnormality in working parameters of a production machine according to claim 4, wherein: Calculating a first area of ​​a region between the first edge line and the first coordinate axis includes: Sequentially pairing adjacent upper inflection points to generate multiple first paired line segments; calculating the area of ​​a first trapezoid between the first paired line segment and the first coordinate axis; calculating the sum of the areas of the first trapezoids corresponding to the first paired line segments to obtain the first area; and / or, Calculating a second area of ​​a region between the second edge line and the first coordinate axis includes: Sequentially pairing adjacent lower inflection points to generate multiple second paired line segments; calculating the area of ​​a second trapezoid between the second paired line segment and the first coordinate axis; The sum of the areas of the second trapezoids corresponding to the second paired line segments is calculated to obtain the second area.

6. The method for detecting abnormality in operating parameters of a production machine according to claim 1, wherein: After determining the abnormality of the target operating parameter of the target machine based on the area of ​​the region, the method further includes: When the target operating parameters of the target machine are abnormal, the target wafer abnormality is reported to a manufacturing execution system.

7. A device for detecting abnormal working parameters of a production machine, characterized in that: The device comprises: An acquisition module, used to acquire multiple data points of target operating parameters of a target machine during the production of a target wafer; an edge line forming module, configured to form a first edge line and a second edge line based on the plurality of data points in a preset coordinate system, wherein the preset coordinate system has an entry point number of the data point as a first coordinate axis and a target working parameter value as a second coordinate axis; a calculation module, configured to calculate the area of ​​a region between the first edge line and the second edge line; an abnormality determination module, configured to determine, based on the area of ​​the region, an abnormality of a target operating parameter of the target machine during the production of a target wafer; The forming of the first edge line and the second edge line based on the plurality of data points in a preset coordinate system includes: Among the plurality of data points, a plurality of upper inflection points and a plurality of lower inflection points are determined; wherein the plurality of upper inflection points are used to form the first edge line, and the plurality of lower inflection points are used to form the second edge line.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images