Method, device and system for monitoring semiconductor process

Abstract

The present disclosure discloses a kind of monitoring method, device and system of semiconductor process, to detect the abnormal situation of the sharp change of preventive maintenance related parameter in short term in advance and then early warning, avoid to cause more wafer scrap, reduce loss.A kind of monitoring method of semiconductor process provided by the present disclosure, comprising: obtaining the preventive maintenance related parameter generated in current semiconductor process;Wherein the preventive maintenance related parameter includes the parameter of semiconductor processing equipment involved in the current semiconductor process, and / or the parameter of semiconductor product involved in the current semiconductor process;According to the preventive maintenance related parameter generated in the current semiconductor process, the estimation of preventive maintenance related parameter to be generated is carried out, and the estimated preventive maintenance related parameter is obtained;When the estimated preventive maintenance related parameter meets the preset parameter abnormal early warning condition, early warning signal is sent.

Description

Technical Field

[0001] This disclosure relates to the field of semiconductor technology, and in particular to a method, apparatus, and system for monitoring semiconductor manufacturing processes. Background Technology

[0002] Conventional univariate analysis (UVA) statistical models control anomalies by setting upper and lower control limits (Specs). However, they cannot detect abnormal situations where preventive maintenance (PM) parameters of semiconductor manufacturing equipment change drastically in a short period of time. They cannot detect these anomalies quickly and will only trigger an alarm when the difference is very large. By then, a large loss may have already occurred, and more than a hundred wafers may have been scrapped. Summary of the Invention

[0003] This disclosure provides a method, apparatus, and system for monitoring semiconductor manufacturing processes, which can detect abnormal situations where preventive maintenance-related parameters change drastically in a short period of time and provide early warnings to avoid more wafer scrap and reduce losses.

[0004] This disclosure provides a method for monitoring a semiconductor manufacturing process, comprising:

[0005] Obtain preventive maintenance related parameters generated in the current semiconductor manufacturing process; wherein the preventive maintenance related parameters include parameters of the semiconductor processing equipment involved in the current semiconductor manufacturing process, and / or parameters of the semiconductor products involved in the current semiconductor manufacturing process;

[0006] Based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the preventive maintenance-related parameters to be generated in the future are estimated to obtain the estimated preventive maintenance-related parameters.

[0007] When the estimated preventive maintenance-related parameters meet the preset abnormal parameter warning conditions, a warning signal is issued.

[0008] In this embodiment of the disclosure, the method obtains the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process; wherein the preventive maintenance-related parameters include the parameters of the semiconductor processing equipment involved in the current semiconductor manufacturing process, and / or the parameters of the semiconductor products involved in the current semiconductor manufacturing process; based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the preventive maintenance-related parameters to be generated are estimated to obtain the estimated preventive maintenance-related parameters; when the estimated preventive maintenance-related parameters meet the preset parameter abnormality warning conditions, a warning signal is issued, thereby detecting abnormal situations in which the preventive maintenance-related parameters change drastically in a short period of time in advance and thus providing early warning, avoiding more wafer scrap and reducing losses.

[0009] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0010] Identify the N most recently acquired data points from the preventive maintenance-related parameters generated in the current semiconductor manufacturing process; wherein, N is a preset integer greater than 1;

[0011] Determine the trend information of the N data points;

[0012] Based on the changing trend information of the N data points, the changing trend information of the M data points of the preventive maintenance related parameters to be generated is determined; wherein, M is a preset integer greater than 1;

[0013] Based on the trend information of the M data points, at least one data value among the M data points is determined as an estimated preventive maintenance related parameter.

[0014] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0015] From the N most recently collected data points in the preventive maintenance-related parameters generated in the current semiconductor manufacturing process, select the i-th data point and the (i+d)-th data point, where the data value of the i-th data point is a and the data value of the (i+d)-th data point is b; where 1 ≤ i < N;

[0016] The estimated value of the data point at the (i+2d)th data point is 2b-a, and 2b-a is used as the estimated parameter related to preventive maintenance.

[0017] In some implementations, when the estimated preventive maintenance-related parameters meet preset abnormality warning conditions, a warning signal is issued, including:

[0018] When the estimated 2b-a is greater than the preset threshold, an early warning signal is issued.

[0019] In some embodiments, the method further includes: determining a preventive maintenance cycle based on preventive maintenance-related parameters generated in the current semiconductor process;

[0020] The estimation of upcoming preventive maintenance parameters based on the preventive maintenance parameters already generated in the current semiconductor manufacturing process includes:

[0021] During the preventive maintenance cycle, based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the preventive maintenance-related parameters to be generated are estimated.

[0022] In some implementations, determining the preventive maintenance cycle based on preventive maintenance-related parameters generated in the current semiconductor manufacturing process includes:

[0023] Based on the preventive maintenance parameters generated in the current semiconductor manufacturing process, identify the time point of the most recent data mutation.

[0024] The preventive maintenance cycle is determined based on the aforementioned time points.

[0025] In some implementations, a preset sliding period test method is used to identify the time point of the most recent data mutation.

[0026] In some implementations, the time point of the most recent data mutation is identified using a preset sliding period check method, including:

[0027] Multiple sets of data point sequences are obtained sequentially according to the order in which the data points are generated, and the statistics of each set of data point sequences are calculated respectively.

[0028] Based on the statistics, identify the time point of the most recent data mutation.

[0029] In some implementations, the step of sequentially acquiring multiple sets of data point sequences according to the order in which the data points were generated, and calculating the statistics for each set of data point sequences, includes:

[0030] Get the first set of two data point sequences generated sequentially with the j-th data point as the last point, calculate the average of the first data point sequence and the average of the second data point sequence, and calculate the statistic T1 based on the average of the two data point sequences;

[0031] Obtain the second set of two data point sequences generated sequentially with the (j+1)th data point as the last point, calculate the average of the first data point sequence and the average of the second data point sequence, and calculate the statistic T2 based on the average of the two data point sequences;

[0032] Obtain the three sets of two data point sequences generated sequentially with the (j+2)th data point as the last point. Calculate the average of the first and second data point sequences and the average of the last data point sequence. Calculate the statistic T3 based on the average of the two data point sequences.

[0033] Where j is an integer greater than 1.

[0034] In some implementations, identifying the time point of the most recent data mutation based on the statistics includes:

[0035] When T1<T2<T3 and T2 is less than a preset threshold, determine the (j+1)th data point as the time point at which the data mutation occurred most recently; or

[0036] When T1<T2<T3 and T2 is greater than a preset threshold, determine the (j+1)th data point as the time point at which the data mutation occurred most recently.

[0037] In some embodiments, a two-sample equal variance assumption algorithm is used to calculate said statistics T1, T2 and T3;

[0038] Said identifying the time point at which the data mutation occurred most recently according to said statistics comprises:

[0039] When T1<T2 and T2>T3, determine the j-th data point or the (j+1)th data point as the time point at which the data mutation occurred most recently; or

[0040] When T1>T2 and T2<T3, determine the j-th data point or the (j+1)th data point as the time point at which the data mutation occurred most recently.

[0041] In some embodiments, before said issuing an early warning signal, the method comprises:

[0042] determining whether the estimated preventive maintenance-related parameter is greater than a preset threshold;

[0043] when the estimated preventive maintenance-related parameter is greater than a preset threshold, determining that the estimated preventive maintenance-related parameter satisfies a preset parameter abnormality early warning condition.

[0044] A monitoring apparatus for a semiconductor manufacturing process provided by an embodiment of the present disclosure comprises:

[0045] an existing parameter acquisition module, configured to acquire preventive maintenance-related parameters that have been generated in a current semiconductor manufacturing process; wherein said preventive maintenance-related parameters comprise parameters of semiconductor processing equipment involved in said current semiconductor manufacturing process, and / or parameters of semiconductor products involved in said current semiconductor manufacturing process;

[0046] a parameter estimation module, configured to estimate preventive maintenance-related parameters that are about to be generated according to the preventive maintenance-related parameters that have been generated in said current semiconductor manufacturing process, to obtain estimated preventive maintenance-related parameters;

[0047] an early warning module, configured to issue an early warning signal when said estimated preventive maintenance-related parameter satisfies a preset parameter abnormality early warning condition.

[0048] A monitoring apparatus for a semiconductor manufacturing process provided by an embodiment of the present disclosure comprises:

[0049] Memory, used to store program instructions;

[0050] The processor is configured to invoke program instructions stored in the memory and execute any of the methods described above according to the obtained program.

[0051] This disclosure provides a semiconductor processing system, including semiconductor processing equipment and a monitoring device connected to the semiconductor processing equipment.

[0052] Furthermore, according to embodiments, for example, a computer program product for a computer is provided, which includes software code portions that, when the product is run on the computer, perform the steps of the methods defined above. The computer program product may include a computer-readable medium on which the software code portions are stored. Furthermore, the computer program product may be directly loaded into the computer's internal memory and / or sent via a network through at least one of an upload process, a download process, and a push process.

[0053] Another embodiment of this disclosure provides a computer-readable storage medium storing computer-executable instructions for causing the computer to perform any of the methods described above. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 A schematic diagram of the PM cycle provided in the embodiments of this disclosure;

[0056] Figure 2 A schematic diagram illustrating abnormal monitoring data provided in this embodiment of the disclosure;

[0057] Figure 3 A schematic flowchart illustrating a semiconductor process monitoring method provided in this embodiment of the disclosure;

[0058] Figure 4 A schematic diagram illustrating data trend prediction provided in this embodiment of the disclosure;

[0059] Figures 5-7 A schematic diagram illustrating the determination of preventive maintenance cycles provided in embodiments of this disclosure;

[0060] Figure 8 This is a schematic diagram illustrating the early warning time points of existing technologies;

[0061] Figure 9 This is a schematic diagram of the early warning time points provided in the embodiments of this disclosure;

[0062] Figure 10 A schematic diagram of the structure of a semiconductor process monitoring device provided in an embodiment of this disclosure;

[0063] Figure 11 A schematic diagram of the structure of another semiconductor process monitoring device provided in an embodiment of this disclosure;

[0064] Figure 12 A schematic diagram of the structure of a semiconductor process monitoring system provided in an embodiment of this disclosure;

[0065] Figure 13 This is a schematic diagram of the structure of a semiconductor processing system provided in an embodiment of the present disclosure. Detailed Implementation

[0066] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this disclosure.

[0067] This disclosure provides a method, apparatus, and system for monitoring semiconductor manufacturing processes, which can detect abnormal situations where preventive maintenance-related parameters change drastically in a short period of time and provide early warnings to avoid more wafer scrap and reduce losses.

[0068] The method and apparatus are based on the same concept of the application. Since the methods and apparatus solve problems in similar ways, the implementation of the apparatus and methods can refer to each other, and the repeated parts will not be described again.

[0069] The terms "first," "second," etc. (if present) in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0070] The following examples and embodiments are to be understood as illustrative only. While this specification may refer to "a," "an," or "some" examples or embodiments in several places, this does not mean that every such reference relates to the same example or embodiment, nor does it mean that the feature applies only to a single example or embodiment. Individual features of different embodiments may also be combined to provide other embodiments. Furthermore, terms such as "comprising" and "including" should be understood not to limit the described embodiments to consisting only of those features mentioned; such examples and embodiments may also include features, structures, units, modules, etc., not specifically mentioned.

[0071] The various embodiments of this disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the order in which the embodiments are presented represents only a chronological order and does not indicate the superiority or inferiority of the technical solutions provided by the embodiments.

[0072] The Fault Detection and Classification (FDC) system builds a UVA model to analyze trace data (run-in trace data) from sensor parameters or virtual parameters of semiconductor process equipment. It applies specific statistical measures for calculation and combines this with upper and lower control limits (Specs) provided by engineers to achieve real-time monitoring and immediate alarms during the semiconductor product manufacturing process. For example... Figure 1 As shown, PM-related parameters ( Figure 1 The upper and lower control limits of the UVA model are determined by simulating long-term data (such as multiple months or multiple PM cycles) to control the upper and lower limits of the spec.

[0073] However, the following problems exist in the semiconductor equipment manufacturing process:

[0074] Some sensor parameters of the machine are related to the machine's PM cycle. For example, after each PM cycle, the polishing pad hardware of a chemical mechanical polishing machine is replaced. Under normal circumstances, the polishing time parameter will fluctuate greatly over long PM cycles. The upper and lower control limits set by the conventional UVA model are relatively wide. Figure 1 As shown, the gap between the upper and lower spec limits is significant. Data fluctuates within the PM cycle. When equipment parts malfunction, PM-related parameters will also show abnormalities. However, see... Figure 2According to the UVA model results, due to the insensitivity of the upper and lower spec limits, the significant change (abnormal jump) in data cannot be detected in the short term. PM-related parameters change drastically within a short period, making timely detection impossible. The upper and lower spec limits provided by engineers failed to detect such out-of-spec (OOS) anomalies in a timely manner, resulting in a large number of products being scrapped by the time the system detected the anomaly.

[0075] For example, if the pad is not replaced when a PM occurs, the grinding time becomes abnormal, and the value rises sharply in a short period of time. However, the conventional UVA model does not detect this anomaly in time, resulting in the wafer being scrapped by the time the warning is issued.

[0076] In summary, semiconductor manufacturing processes exhibit a cyclical decay process, meaning that process capability declines and processing time needs to be compensated. This is reflected in the extension of processing time parameters. Specifications take multiple cycles into account. However, the current upper and lower limits of specifications cannot identify abnormal situations where PM-related parameters rise rapidly in a short period of time but do not exceed the specifications. At this point, the equipment has already malfunctioned and requires maintenance.

[0077] See Figure 3 This disclosure provides a method for monitoring a semiconductor manufacturing process, comprising:

[0078] S101. Obtain the preventive maintenance related parameters generated in the current semiconductor manufacturing process; wherein the preventive maintenance related parameters include the parameters of the semiconductor processing equipment involved in the current semiconductor manufacturing process, and / or the parameters of the semiconductor products involved in the current semiconductor manufacturing process.

[0079] The preventive maintenance related parameters, i.e. PM related parameters, which are the monitoring data in this embodiment of the disclosure, can be various data in the semiconductor manufacturing process; the parameters of the semiconductor processing equipment, such as the Pad hardware parameters of a chemical mechanical polishing machine (e.g., the time required to polish each nanometer); and the parameters of the semiconductor product, such as the wafer thickness change rate.

[0080] S102. Based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, estimate the preventive maintenance-related parameters to be generated in the future, and obtain the estimated preventive maintenance-related parameters.

[0081] S103. When the estimated preventive maintenance-related parameters meet the preset abnormal parameter warning conditions, a warning signal is issued.

[0082] In other words, compared with the prior art, the semiconductor process monitoring method provided in this disclosure can predict current trends and issue warnings when the monitoring data is less than the Spec.

[0083] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0084] Identify the N most recently acquired data points from the preventive maintenance-related parameters generated in the current semiconductor manufacturing process; wherein, N is a preset integer greater than 1;

[0085] Determine the trend information of the N data points;

[0086] Based on the changing trend information of the N data points, the changing trend information of the M data points of the preventive maintenance related parameters to be generated is determined; wherein, M is a preset integer greater than 1;

[0087] Based on the trend information of the M data points, at least one data value among the M data points is determined as an estimated preventive maintenance related parameter.

[0088] M can be the same as or different from N. For example, N equals 5, and M also equals 5, or M equals 10, i.e., M = 2N.

[0089] The trend information of the N data points, for example Figure 4 The curve showing the trend of existing data is shown in the figure.

[0090] The trend information of the M data points, for example Figure 4 The curve shown represents the trend of the predicted data.

[0091] As can be seen, the trend curve of the predicted data has exceeded the upper limit of Spec, therefore, an early warning can be issued.

[0092] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0093] From the N most recently collected data points in the preventive maintenance-related parameters generated in the current semiconductor manufacturing process, select the i-th data point and the (i+d)-th data point, where the data value of the i-th data point is a and the data value of the (i+d)-th data point is b; where 1 ≤ i < N;

[0094] The estimated value of the data point at the (i+2d)th data point is 2b-a, and 2b-a is used as the estimated parameter related to preventive maintenance.

[0095] In some implementations, when the estimated preventive maintenance-related parameters meet preset abnormality warning conditions, a warning signal is issued, including:

[0096] When the estimated 2b-a is greater than the preset threshold, an early warning signal is issued.

[0097] In some embodiments, the method further includes: determining a preventive maintenance cycle based on preventive maintenance-related parameters generated in the current semiconductor process;

[0098] The estimation of upcoming preventive maintenance parameters based on the preventive maintenance parameters already generated in the current semiconductor manufacturing process includes:

[0099] During the preventive maintenance cycle, based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the preventive maintenance-related parameters to be generated are estimated.

[0100] In other words, the embodiments of this disclosure can estimate the data to be generated within the PM cycle based on the monitoring data, thereby obtaining a more accurate estimation result and avoiding excessive estimation errors across PM cycles.

[0101] In some implementations, determining the preventive maintenance cycle based on preventive maintenance-related parameters generated in the current semiconductor manufacturing process includes:

[0102] Based on the preventive maintenance parameters generated in the current semiconductor manufacturing process, identify the time point of the most recent data mutation.

[0103] The preventive maintenance cycle is determined based on the aforementioned time points.

[0104] The occurrence of a data mutation refers to the difference between two consecutive data collections of preventive maintenance-related parameters exceeding a preset threshold, for example... Figure 1 , Figure 2 The PM cycle shown in the diagram signifies the start of a new PM cycle (and the end of the previous PM cycle) when a data mutation occurs.

[0105] Regarding how to determine the occurrence of data mutations, i.e. how to determine the PM cycle, it can be determined according to actual needs. For example, in some implementations, a preset sliding cycle test method is used to identify the time period of the most recent data mutation.

[0106] In some implementations, a preset sliding period test method is used to identify the time point of the most recent data mutation.

[0107] The sliding period test method, also known as the double-slider T-test method, is as follows: Figure 5 , Figure 6 , Figure 7 as shown in the figure.

[0108] In some embodiments, identifying the time point when the most recent data mutation occurs by a preset sliding period test method comprises:

[0109] Acquiring a plurality of groups of data point sequences sequentially according to the generation order of data points, and calculating the statistics of each group of data point sequences respectively;

[0110] Identifying the time point of the most recent data mutation according to the statistics.

[0111] In some embodiments, said acquiring a plurality of groups of data point sequences sequentially according to the generation order of data points, and calculating the statistics of each group of data point sequences respectively comprises:

[0112] Acquiring a first group of two sequentially generated data point sequences with the j-th data point as the last point (e.g., Figure 7 Sequence 1 and Sequence 2 shown in ), calculating the average value of the previous data point sequence and the average value of the subsequent data point sequence, and calculating the statistic T1 according to the average values of the two data point sequences;

[0113] Acquiring a second group of two sequentially generated data point sequences with the (j+1)-th data point as the last point (e.g., Figure 7 Sequence 3 and Sequence 4 shown in ), calculating the average value of the previous data point sequence and the average value of the subsequent data point sequence, and calculating the statistic T2 according to the average values of the two data point sequences;

[0114] Acquiring a third group of two sequentially generated data point sequences with the (j+2)-th data point as the last point (e.g., Figure 7 Sequence 5 and Sequence 6 shown in ), calculating the average value of the previous data point sequence and the average value of the subsequent data point sequence, and calculating the statistic T3 according to the average values of the two data point sequences;

[0115] wherein j is an integer greater than 1.

[0116] In some embodiments, said identifying the time point of the most recent data mutation according to the statistics comprises:

[0117] when T1<T2<T3 and T2 is less than a preset threshold, determining the (j+1)-th data point as the time point when the most recent data mutation occurs; or

[0118] when T1<T2<T3 and T2 is greater than a preset threshold, determining the (j+1)-th data point as the time point when the most recent data mutation occurs.

[0119] In some embodiments, the two-sample equal variance hypothesis algorithm is used to calculate the statistics T1, T2 and T3;

[0120] The step of identifying the time point at which the latest data mutation occurs according to the statistics comprises:

[0121] when T1<T2 and T2>T3, determining the j-th data point or the j+1-th data point as the time point of the latest data mutation; or

[0122] when T1>T2 and T2<T3, determining the j-th data point or the j+1-th data point as the time point of the latest data mutation.

[0123] In some embodiments, before issuing the early warning signal, the method comprises:

[0124] determining whether the estimated preventive maintenance related parameter is greater than a preset threshold;

[0125] when the estimated preventive maintenance related parameter is greater than the preset threshold, determining that the estimated preventive maintenance related parameter satisfies a preset parameter abnormality early warning condition.

[0126] Herein, for different actual application scenarios, an alarm is triggered when the estimated preventive maintenance related parameter is greater than the preset threshold, or when the estimated preventive maintenance related parameter is smaller than the preset threshold.

[0127] In conclusion, referring to Figure 8 , the prior art requires an early warning when monitoring data exceeds a limit value, for example, the early warning time is 8:45 AM on February 12th; and referring to Figure 9 , by adopting the method provided by the embodiments of the present disclosure, an early warning can be issued when the monitoring data does not exceed the limit value, for example, the early warning time is 4:37 AM on February 12th, which is about 4 hours earlier, thereby reducing wafer scrap.

[0128] The device or apparatus provided by the embodiments of the present disclosure will be introduced below. Explanations or illustrative descriptions of technical features that are the same as or corresponding to those described in the above method will not be repeated hereinafter.

[0129] Referring to Figure 10 , a monitoring apparatus for a semiconductor manufacturing process provided by an embodiment of the present disclosure comprises:

[0130] an existing parameter acquisition module 11, configured to acquire preventive maintenance related parameters that have been generated in the current semiconductor manufacturing process; wherein the preventive maintenance related parameters comprise parameters of semiconductor processing equipment involved in the current semiconductor manufacturing process, and / or parameters of semiconductor products involved in the current semiconductor manufacturing process;

[0131] The parameter estimation module 12 is used to estimate the preventive maintenance related parameters to be generated based on the preventive maintenance related parameters already generated in the current semiconductor process, and to obtain the estimated preventive maintenance related parameters.

[0132] The early warning module 13 is used to issue an early warning signal when the estimated preventive maintenance-related parameters meet the preset abnormal parameter early warning conditions.

[0133] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0134] Identify the N most recently acquired data points from the preventive maintenance-related parameters generated in the current semiconductor manufacturing process; wherein, N is a preset integer greater than 1;

[0135] Determine the trend information of the N data points;

[0136] Based on the changing trend information of the N data points, the changing trend information of the M data points of the preventive maintenance related parameters to be generated is determined; wherein, M is a preset integer greater than 1;

[0137] Based on the trend information of the M data points, at least one data value among the M data points is determined as an estimated preventive maintenance related parameter.

[0138] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0139] From the N most recently collected data points in the preventive maintenance-related parameters generated in the current semiconductor manufacturing process, select the i-th data point and the (i+d)-th data point, where the data value of the i-th data point is a and the data value of the (i+d)-th data point is b; where 1 ≤ i < N;

[0140] The estimated value of the data point at the (i+2d)th data point is 2b-a, and 2b-a is used as the estimated parameter related to preventive maintenance.

[0141] In some implementations, when the estimated preventive maintenance-related parameters meet preset abnormality warning conditions, a warning signal is issued, including:

[0142] When the estimated 2b-a is greater than the preset threshold, an early warning signal is issued.

[0143] In some implementations, the parameter estimation module 12 is further configured to: determine the preventive maintenance cycle based on the preventive maintenance-related parameters generated in the current semiconductor process;

[0144] The estimation of upcoming preventive maintenance parameters based on the preventive maintenance parameters already generated in the current semiconductor manufacturing process includes:

[0145] During the preventive maintenance cycle, based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the preventive maintenance-related parameters to be generated are estimated.

[0146] In some implementations, determining the preventive maintenance cycle based on preventive maintenance-related parameters generated in the current semiconductor manufacturing process includes:

[0147] Based on the preventive maintenance parameters generated in the current semiconductor manufacturing process, identify the time point of the most recent data mutation.

[0148] The preventive maintenance cycle is determined based on the aforementioned time points.

[0149] In some implementations, a preset sliding period test method is used to identify the time point of the most recent data mutation.

[0150] In some implementations, the time point of the most recent data mutation is identified using a preset sliding period check method, including:

[0151] Multiple sets of data point sequences are obtained sequentially according to the order in which the data points are generated, and the statistics of each set of data point sequences are calculated respectively.

[0152] Based on the statistics, identify the time point of the most recent data mutation.

[0153] In some implementations, the step of sequentially acquiring multiple sets of data point sequences according to the order in which the data points were generated, and calculating the statistics for each set of data point sequences, includes:

[0154] Get the first set of two data point sequences generated sequentially with the j-th data point as the last point, calculate the average of the first data point sequence and the average of the second data point sequence, and calculate the statistic T1 based on the average of the two data point sequences;

[0155] Obtain the second set of two data point sequences generated sequentially with the (j+1)th data point as the last point, calculate the average of the first data point sequence and the average of the second data point sequence, and calculate the statistic T2 based on the average of the two data point sequences;

[0156] Acquiring a third group of two sequentially generated data point sequences with the (j+2)-th data point as the last data point, calculating the average value of the previous data point sequence and the average value of the subsequent data point sequence, and calculating the statistic T3 based on the average values of the two data point sequences;

[0157] wherein j is an integer greater than 1.

[0158] In some embodiments, said identifying the time point at which the most recent data mutation occurred based on said statistic comprises:

[0159] when T1 < T2 < T3 and T2 is less than a preset threshold, determining the (j+1)-th data point as the time point at which the most recent data mutation occurred; or

[0160] when T1 < T2 < T3 and T2 is greater than a preset threshold, determining the (j+1)-th data point as the time point at which the most recent data mutation occurred.

[0161] In some embodiments, the two-sample equal variance assumption algorithm is used to calculate the statistics T1, T2 and T3;

[0162] said identifying the time point at which the most recent data mutation occurred based on said statistic comprises:

[0163] when T1 < T2 and T2 > T3, determining the j-th data point or the (j+1)-th data point as the time point at which the most recent data mutation occurred; or

[0164] when T1 > T2 and T2 < T3, determining the j-th data point or the (j+1)-th data point as the time point at which the most recent data mutation occurred.

[0165] In some embodiments, before said issuing an early warning signal, the early warning module 13 is further configured to:

[0166] determine whether the estimated preventive maintenance-related parameter is greater than a preset threshold;

[0167] when the estimated preventive maintenance-related parameter is greater than the preset threshold, determining that the estimated preventive maintenance-related parameter satisfies a preset parameter abnormality early warning condition.

[0168] It should be noted that the division of functional units and modules in the embodiments of the present disclosure is schematic, and is merely a logical function division. Another division mode may be adopted in actual implementation. In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, may exist separately and physically individually, or two or more units may be integrated into one unit. The integrated unit above may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

[0169] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0170] See Figure 11 Another semiconductor process monitoring device provided in this disclosure includes:

[0171] Processor 600 is used to read the program from memory 620 and execute the following procedures:

[0172] Obtain preventive maintenance related parameters generated in the current semiconductor manufacturing process; wherein the preventive maintenance related parameters include parameters of the semiconductor processing equipment involved in the current semiconductor manufacturing process, and / or parameters of the semiconductor products involved in the current semiconductor manufacturing process;

[0173] Based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the preventive maintenance-related parameters to be generated in the future are estimated to obtain the estimated preventive maintenance-related parameters.

[0174] When the estimated preventive maintenance-related parameters meet the preset abnormal parameter warning conditions, a warning signal is issued.

[0175] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0176] Identify the N most recently acquired data points from the preventive maintenance-related parameters generated in the current semiconductor manufacturing process; wherein, N is a preset integer greater than 1;

[0177] Determine the trend information of the N data points;

[0178] Based on the changing trend information of the N data points, the changing trend information of the M data points of the preventive maintenance related parameters to be generated is determined; wherein, M is a preset integer greater than 1;

[0179] Based on the trend information of the M data points, at least one data value among the M data points is determined as an estimated preventive maintenance related parameter.

[0180] In some implementations, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the estimated preventive maintenance-related parameters to be generated are estimated, including:

[0181] From the N most recently collected data points in the preventive maintenance-related parameters generated in the current semiconductor manufacturing process, select the i-th data point and the (i+d)-th data point, where the data value of the i-th data point is a and the data value of the (i+d)-th data point is b; where 1 ≤ i < N;

[0182] The estimated value of the data point at the (i+2d)th data point is 2b-a, and 2b-a is used as the estimated parameter related to preventive maintenance.

[0183] In some implementations, when the estimated preventive maintenance-related parameters meet preset abnormality warning conditions, a warning signal is issued, including:

[0184] When the estimated 2b-a is greater than the preset threshold, an early warning signal is issued.

[0185] In some embodiments, the processor 600 is further configured to read a program from the memory 620 and execute the following process: determining the preventive maintenance cycle based on preventive maintenance-related parameters generated in the current semiconductor process;

[0186] The estimation of upcoming preventive maintenance parameters based on the preventive maintenance parameters already generated in the current semiconductor manufacturing process includes:

[0187] During the preventive maintenance cycle, based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the preventive maintenance-related parameters to be generated are estimated.

[0188] In some implementations, determining the preventive maintenance cycle based on preventive maintenance-related parameters generated in the current semiconductor manufacturing process includes:

[0189] Based on the preventive maintenance parameters generated in the current semiconductor manufacturing process, identify the time point of the most recent data mutation.

[0190] The preventive maintenance cycle is determined based on the aforementioned time points.

[0191] In some embodiments, the time point at which the latest data mutation occurs is identified through a preset moving period test method.

[0192] In some embodiments, identifying the time point at which the latest data mutation occurs through a preset moving period test method comprises:

[0193] Sequentially obtaining multiple groups of data point sequences according to the generation order of data points, and calculating the statistics of each group of data point sequences respectively;

[0194] Identifying the time point at which the latest data mutation occurs according to the statistics.

[0195] In some embodiments, sequentially obtaining multiple groups of data point sequences according to the generation order of data points, and calculating the statistics of each group of data point sequences respectively comprises:

[0196] Obtaining a first group of two sequentially generated data point sequences with the j-th data point as the last point, calculating the average value of the former data point sequence and the average value of the latter data point sequence, and calculating a statistic T1 based on the average values of the two data point sequences;

[0197] Obtaining a second group of two sequentially generated data point sequences with the (j+1)-th data point as the last point, calculating the average value of the former data point sequence and the average value of the latter data point sequence, and calculating a statistic T2 based on the average values of the two data point sequences;

[0198] Obtaining a third group of two sequentially generated data point sequences with the (j+2)-th data point as the last point, calculating the average value of the former data point sequence and the average value of the latter data point sequence, and calculating a statistic T3 based on the average values of the two data point sequences;

[0199] wherein j is an integer greater than 1.

[0200] In some embodiments, identifying the time point at which the latest data mutation occurs according to the statistics comprises:

[0201] when T1 < T2 < T3 and T2 is less than a preset threshold, determining the (j+1)-th data point is the time point at which the latest data mutation occurs; or

[0202] when T1 < T2 < T3 and T2 is greater than a preset threshold, determining the (j+1)-th data point is the time point at which the latest data mutation occurs.

[0203] In some embodiments, a two-sample equal variance assumption algorithm is used to calculate the statistics T1, T2 and T3;

[0204] Identifying the time point at which the last data mutation occurred according to the statistic comprises:

[0205] when T1 < T2 and T2 > T3, determining the j-th data point or the (j+1)-th data point as the time point at which the last data mutation occurred; or

[0206] when T1 > T2 and T2 < T3, determining the j-th data point or the (j+1)-th data point as the time point at which the last data mutation occurred.

[0207] In some implementations, before issuing the early warning signal, the processor 600 is further configured to read a program in the memory 620 and execute the following process:

[0208] determining whether the estimated preventive maintenance-related parameter is greater than a preset threshold;

[0209] when the estimated preventive maintenance-related parameter is greater than the preset threshold, determining that the estimated preventive maintenance-related parameter satisfies a preset parameter abnormality early warning condition.

[0210] In some embodiments, the monitoring apparatus for semiconductor manufacturing further comprises a transceiver 610 configured to receive and transmit data under the control of the processor 600.

[0211] wherein, in Figure 11 , the bus architecture may comprise any number of interconnected buses and bridges, which specifically links various circuits of one or more processors represented by the processor 600 and the memory represented by the memory 620. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, power management circuits and the like, which are all well known in the art, and therefore, no further description will be given herein. The bus interface provides an interface. The transceiver 610 may be a plurality of elements, that is, comprising a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium.

[0212] In some embodiments, the apparatus further comprises a user interface 630, and the user interface 630 may be an interface capable of externally or internally connecting required devices, and the connected devices include, but are not limited to, a keypad, a display, a speaker, a microphone, a joystick and the like.

[0213] The processor 600 is responsible for managing the bus architecture and general processing, and the memory 620 can store data used by the processor 600 when performing operations.

[0214] In some embodiments, the processor 600 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a CPLD (Complex Programmable Logic Device).

[0215] This disclosure provides a control system for semiconductor processing equipment, including a monitoring device for any of the aforementioned semiconductor processes. In addition, it may include devices such as a database for storing preventative maintenance parameters (i.e., monitoring data) related to the semiconductor process. Figure 12 As shown in the diagram. Different databases can be used to maintain monitoring data for different types of semiconductor processing equipment, or they can be maintained by a single database.

[0216] See Figure 13 The present disclosure provides a semiconductor processing system, including a semiconductor processing device and a monitoring device connected to the semiconductor processing device.

[0217] The semiconductor processing equipment mentioned above includes, for example, machines and other equipment used in various stages of the process. Furthermore, it should be noted that other devices can be installed between the semiconductor processing equipment and its control system to acquire monitoring data from the semiconductor processing equipment and store it in a corresponding database. Figure 13 Not shown in the diagram. Of course, semiconductor processing equipment can also directly send data to the corresponding database.

[0218] This disclosure provides a computing device, which may specifically be a desktop computer, portable computer, smartphone, tablet computer, personal digital assistant (PDA), etc. The computing device may include a central processing unit (CPU), memory, input / output devices, etc. Input devices may include a keyboard, mouse, touchscreen, etc., and output devices may include display devices such as liquid crystal displays (LCDs) and cathode ray tubes (CRTs).

[0219] The memory may include read-only memory (ROM) and random access memory (RAM), and provides the processor with program instructions and data stored in the memory. In embodiments of this disclosure, the memory may be used to store the program for any of the methods provided in embodiments of this disclosure.

[0220] The processor executes any of the methods described in the embodiments of this disclosure according to the program instructions stored in memory.

[0221] This disclosure also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the methods described in the above embodiments. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0222] This disclosure provides a computer-readable storage medium for storing computer program instructions used in the apparatus provided in the embodiments of this disclosure, including a program for performing any of the methods provided in the embodiments of this disclosure. The computer-readable storage medium may be a non-transitory computer-readable medium.

[0223] The computer-readable storage medium can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0224] It should be understood that:

[0225] The access technology used by entities in a communication network to transmit traffic can be any suitable current or future technology, such as WLAN (Wireless Local Access Network), WiMAX (Microwave Access Global Interoperability), LTE, LTE-A, 5G, Bluetooth, infrared, etc.; in addition, embodiments may also apply wired technologies, such as IP-based access technologies, such as wired networks or fixed lines.

[0226] An embodiment suitable for implementation as software code or as part thereof and for operation using a processor or processing function is independent of the software code and can be specified using any known or future-developed programming language, such as high-level programming languages ​​such as Objective-C, C, C++, C#, Java, Python, Javascript, other scripting languages, etc., or low-level programming languages ​​such as machine language or assembler.

[0227] The implementation of the embodiments is hardware-independent and can be implemented using any known or future-developed hardware technology or any combination thereof, such as microprocessors or CPUs (central processing units), MOS (metal-oxide-semiconductor), CMOS (complementary MOS), BiMOS (bipolar MOS), BiCMOS (bipolar CMOS), ECL (emitter-coupled logic), and / or TTL (transistor-transistor logic).

[0228] The embodiments may be implemented as individual devices, apparatuses, units, components or functions, or in a distributed manner. For example, one or more processors or processing functions may be used or shared in the process, or one or more processing segments or processing portions may be used and shared in the process, wherein one or more physical processors may be used to implement one or more processing portions dedicated to a particular process as described.

[0229] The device can be implemented by a semiconductor chip, a chipset, or a (hardware) module that includes such a chip or chipset.

[0230] The implementation can also be implemented as any combination of hardware and software, such as ASIC (Application-Specific IC (Integrated Circuit)) components, FPGA (Field Programmable Gate Array) or CPLD (Complex Programmable Logic Device) components or DSP (Digital Signal Processor) components.

[0231] The embodiments can also be implemented as computer program products, including a computer-usable medium in which computer-readable program code is embodied, the computer-usable program code being adapted to perform the processes described in the embodiments, wherein the computer-usable medium may be a non-transitory medium.

[0232] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0233] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0234] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0235] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0236] Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

1. A method for monitoring a semiconductor manufacturing process, characterized in that, The method includes: Obtain preventive maintenance related parameters generated in the current semiconductor manufacturing process; wherein the preventive maintenance related parameters include parameters of the semiconductor processing equipment involved in the current semiconductor manufacturing process, and / or parameters of the semiconductor products involved in the current semiconductor manufacturing process; The preventive maintenance cycle is determined based on the preventive maintenance parameters generated in the current semiconductor manufacturing process. During the preventive maintenance cycle, based on the preventive maintenance-related parameters already generated in the current semiconductor process, the preventive maintenance-related parameters to be generated are estimated to obtain the estimated preventive maintenance-related parameters. When the estimated preventive maintenance-related parameters meet the preset abnormal parameter warning conditions, a warning signal is issued; Specifically, based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the estimated preventive maintenance-related parameters to be generated are calculated, resulting in the estimated preventive maintenance-related parameters, including: Identify the N most recently acquired data points from the preventive maintenance-related parameters generated in the current semiconductor manufacturing process; wherein, N is a preset integer greater than 1; Determine the trend information of the N data points; Based on the changing trend information of the N data points, the changing trend information of the M data points of the preventive maintenance related parameters to be generated is determined; wherein, M is a preset integer greater than 1; Based on the trend information of the M data points, at least one data value among the M data points is determined as an estimated preventive maintenance related parameter.

2. The method according to claim 1, characterized in that, Based on the preventive maintenance-related parameters already generated in the current semiconductor manufacturing process, the estimated preventive maintenance-related parameters to be generated are obtained, including: From the N most recently collected data points in the preventive maintenance-related parameters generated in the current semiconductor manufacturing process, select the i-th data point and the (i+d)-th data point, where the data value of the i-th data point is a and the data value of the (i+d)-th data point is b; where 1 ≤ i < N; The estimated value of the data point at the (i+2d)th data point is 2b-a, and 2b-a is used as the estimated parameter related to preventive maintenance.

3. The method according to claim 2, characterized in that, When the estimated preventive maintenance-related parameters meet preset abnormal parameter warning conditions, a warning signal is issued, including: When the estimated 2b-a is greater than the preset threshold, an early warning signal is issued.

4. The method according to claim 3, characterized in that, The step of determining the preventive maintenance cycle based on the preventive maintenance-related parameters generated in the current semiconductor manufacturing process includes: Based on the preventive maintenance parameters generated in the current semiconductor manufacturing process, identify the time point of the most recent data mutation. The preventive maintenance cycle is determined based on the aforementioned time points.

5. The method according to claim 4, characterized in that, The time point of the most recent data mutation is identified by a preset sliding period test method.

6. The method according to claim 5, characterized in that, The time point of the most recent data mutation is identified using a preset sliding period check method, including: Multiple sets of data point sequences are obtained sequentially according to the order in which the data points are generated, and the statistics of each set of data point sequences are calculated respectively. Based on the statistics, identify the time point of the most recent data mutation.

7. The method according to claim 6, characterized in that, Said obtaining a plurality of groups of data point sequences sequentially according to the generation order of data points, and calculating the statistics of each group of data point sequences respectively comprises: obtaining a first group of two sequentially generated data point sequences with the j-th data point as the last point, calculating the average value of the former data point sequence and the average value of the latter data point sequence, and calculating the statistic T1 according to the average values of the two data point sequences; obtaining a second group of two sequentially generated data point sequences with the (j+1)-th data point as the last point, calculating the average value of the former data point sequence and the average value of the latter data point sequence, and calculating the statistic T2 according to the average values of the two data point sequences; obtaining a third group of two sequentially generated data point sequences with the (j+2)-th data point as the last point, calculating the average value of the former data point sequence and the average value of the latter data point sequence, and calculating the statistic T3 according to the average values of the two data point sequences; wherein j is an integer greater than 1.

8. The method according to claim 7, characterized in that, Said identifying the time point at which the data mutation occurred most recently according to the statistics comprises: when T1<T2 <T3 and T2 is less than a preset threshold, determining the (j+1)-th data point as the time point at which the most recent data mutation occurred; or when T1<T2 <T3 and T2 is greater than a preset threshold, determining the (j+1)-th data point as the time point at which the most recent data mutation occurred.

9. The method according to claim 7, characterized in that, calculating the statistics T1, T2 and T3 by adopting a two-sample equal variance hypothesis algorithm; Said identifying the time point at which the data mutation occurred most recently according to the statistics comprises: when T1<T2 and T2>T3, determining the j-th data point or the (j+1)-th data point as the time point at which the most recent data mutation occurred; or when T1>T2 and T2<T3, determining the j-th data point or the (j+1)-th data point as the time point at which the most recent data mutation occurred.

10. The method according to claim 1, characterized in that, before said issuing an early warning signal, the method comprises: judging whether the estimated preventive maintenance related parameter is greater than a preset threshold; when the estimated preventive maintenance related parameter is greater than a preset threshold, determining that the estimated preventive maintenance related parameter meets a preset parameter abnormality early warning condition.

11. A monitoring device for semiconductor manufacturing processes, characterized in that, Said device comprises: an existing parameter obtaining module, configured to obtain generated preventive maintenance related parameters in a current semiconductor manufacturing process; wherein the preventive maintenance related parameters comprise parameters of semiconductor processing equipment involved in the current semiconductor manufacturing process, and / or parameters of semiconductor products involved in the current semiconductor manufacturing process; The parameter estimation module is used to determine the preventive maintenance cycle based on the preventive maintenance-related parameters already generated in the current semiconductor process, and within the preventive maintenance cycle, to estimate the preventive maintenance-related parameters to be generated, based on the preventive maintenance-related parameters already generated in the current semiconductor process, to obtain the estimated preventive maintenance-related parameters. This includes: determining N most recently collected data points from the preventive maintenance-related parameters already generated in the current semiconductor process; where N is a preset integer greater than 1; determining the trend information of the changes in the N data points; determining the trend information of the changes in the M data points of the preventive maintenance-related parameters to be generated, based on the trend information of the changes in the N data points; where M is a preset integer greater than 1; and determining at least one data value from the M data points as the estimated preventive maintenance-related parameter based on the trend information of the changes in the M data points. The early warning module is used to issue an early warning signal when the estimated preventive maintenance-related parameters meet the preset abnormal parameter early warning conditions.

12. A monitoring device for semiconductor manufacturing processes, characterized in that, The device includes: Memory, used to store program instructions; A processor is configured to invoke program instructions stored in the memory and execute the method according to any one of claims 1 to 10.

13. A semiconductor processing system, characterized in that, The system includes semiconductor processing equipment and a monitoring device as described in claim 12 connected to the semiconductor processing equipment.

Images