Intelligent calibration method and system for semiconductor testing equipment

Abstract

The present invention discloses an intelligent calibration method and system for semiconductor detection equipment, which specifically relates to the field of semiconductor detection equipment and is used to solve the problem of calibration error traceability. The method splits the measurement data into time series and constructs a correspondence between the measurement time grid and the measurement area, so that the source of the error can be accurately located in time and space. At the same time, combined with an in-depth analysis of the measurement error trend, it identifies whether the error is a short-term fluctuation or a long-term anomaly, thereby distinguishing between accidental errors and hardware failures. When the error is a short-term fluctuation, the last measurement data is traced back according to the measurement time grid, and the interval with stable environment is screened to determine the location where the error first occurred and its corresponding measurement area. Local calibration is performed for this area to avoid redundant operations that are repeatedly performed throughout the entire process in traditional methods, so that the semiconductor detection equipment can still maintain high measurement stability and data reliability under high precision requirements.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor testing equipment, and more specifically, to an intelligent calibration method and system for semiconductor testing equipment. Background Art

[0002] In semiconductor inspection, optical profilers are high-precision measurement devices, and their calibration process is directly related to the accuracy of measurement data and production efficiency. Traditional calibration methods typically use a full-process retry approach to address any out-of-tolerance situations. Once the calibration result exceeds the preset tolerance, the system reruns the entire process without carefully analyzing the collected measurement and environmental data. This approach fails to utilize the temporal and spatial distribution characteristics of data and ignores the impact of environmental conditions on errors, making it difficult to accurately locate the specific time period and area where the error occurred.

[0003] When the current system encounters calibration results that are out of tolerance, it directly adopts a full-process retry operation strategy. It fails to extract the error based on the collected pre-processed data and the degree of deviation from historical data, and fails to conduct a comprehensive assessment based on environmental impacts and time fluctuations. As a result, it is unable to distinguish between accidental errors and hardware failures, and it is unable to determine the error starting point and local abnormal area through backtracking, resulting in repeated operations, wasted detection time and difficulties in targeted maintenance.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent calibration method and system for semiconductor detection equipment. By time-series splitting the measurement data and constructing a correspondence between the measurement time grid and the measurement area, the source of the error can be accurately located in time and space. At the same time, combined with an in-depth analysis of the measurement error trend, it is possible to identify whether the error is a short-term fluctuation or a long-term anomaly, thereby distinguishing between accidental errors and hardware failures. In the case where the error is a short-term fluctuation, the last measurement data is traced back based on the measurement time grid, and the interval with stable environment is screened to determine the location where the error first occurred and its corresponding measurement area. Local calibration is performed on the area, avoiding redundant operations that are repeated throughout the entire process in traditional methods, improving measurement efficiency, reducing equipment downtime, and enhancing the accuracy of measurement error correction, so that semiconductor detection equipment can still maintain high measurement stability and data reliability under high precision requirements, thereby solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent calibration method for semiconductor testing equipment comprises the following steps:

[0008] S1: When calibration begins, pre-process the measurement data and environmental data within fixed sampling points and time intervals, and create samples by splitting them into measurement time grids;

[0009] S2: Extract the degree of deviation between the current measurement error and historical measurement data, and quantify its stability in combination with the influence of environmental conditions. At the same time, calculate the error fluctuation range within the measurement time grid, and adjust the calculation based on the time factor to obtain the deviation amplitude.

[0010] S3: Extract the overall error trend and compare it with the historical stable state to form a comprehensive deviation. Then match it with the set reference limit to determine whether it is a hardware failure.

[0011] S4: If the error is determined to be non-hardware fault, the previous measurement data is retraced, and the historical error data is aligned according to the measurement time grid. The degree of environmental change within each time grid is checked, and the stable interval is screened. The measurement time grid where the error first occurred and the corresponding measurement area are determined.

[0012] S5: Based on the determined measurement time grid and the corresponding measurement area, re-perform local calibration of the corresponding measurement area according to preset rules.

[0013] In a preferred embodiment, step S1 includes the following contents:

[0014] During calibration, all sensor data must be stored at set time intervals and correspond to specific measurement time grids to form a time series dataset. After data acquisition is completed, the collected data is denoised and normalized, and the processed data is split according to the time grid. Each measurement time grid contains the measurement data and environmental data within the corresponding time period, and a complete time series dataset is constructed according to the measurement order to form a standardized data structure.

[0015] In a preferred embodiment, step S2 includes the following:

[0016] The degree of deviation between the current measurement error and the historical measurement data is extracted, and its stability is quantified in combination with the influence of environmental conditions. The time-varying entropy diffusion index is obtained through measurement. The processing steps are as follows:

[0017] Set the current measurement error within the measurement time grid to , the historical measurement error is ,in represents the time grid index, Represents the sampling point index within the time grid, Represents the normalized measurement error; the error deviation is calculated using the following formula: ;in, Time grid Internally normalized environmental impact factor; time-varying entropy diffusion index The definition is as follows: ;in, Time grid The number of data points within Time grid The central moment, To measure the reference time, is the time normalization parameter.

[0018] In a preferred embodiment, step S2 further includes the following:

[0019] Calculate the error fluctuation range within the measurement time grid, adjust the calculation based on the time factor to obtain the deviation amplitude, and finally obtain the time domain ripple jump index. The processing steps are as follows:

[0020] At each measurement time Within, the error change between adjacent sampling points is transformed into an exponential scale, and the normalized measurement error is set to , then the error jump value is defined as: ;in, For sensitivity adjustment parameters, the time domain ripple jump index is calculated as follows: ;in, Time grid duration, is the time equilibrium constant.

[0021] In a preferred embodiment, step S3 includes the following contents:

[0022] Set the measurement time grid index to ,exist Double difference transformation is performed on the time-varying entropy diffusion index and the time-domain ripple jump index within the time grid; then, the transformation results of the time-varying entropy diffusion index and the time-domain ripple jump index are time-series integrated to obtain the overall error trend; obtain the overall error trend After that, it is compared with the historical stable state to determine the overall deviation of the measurement error; the historical stable state is fitted by the time-varying entropy diffusion index and the mean of the time-domain ripple jump index of the measuring equipment under stable working conditions, and the historical stable error characteristics are defined as: ;in, is the total number of measurement time grids of historical stable data, Indicates the measurement time grid index used to calculate the historical stability error characteristics, ranging from 1 to ; Then calculate the comprehensive deviation of the current overall error trend compared to the historical stable error: ;in, Parameters for adjusting the deviation mapping.

[0023] In a preferred embodiment, step S3 further includes the following:

[0024] In calculating the comprehensive deviation After that, it is matched with the set reference limit to determine whether the current error is a short-term fluctuation or a long-term abnormality, and whether it is a hardware failure. The reference limit is set to include the upper limit of short-term fluctuation. and long-term abnormal threshold , judge according to the following rules:

[0025] like , then the error is determined to be within the normal range and no additional adjustment is required;

[0026] like , then the error is judged to be a short-term fluctuation, not a hardware failure;

[0027] like , it is determined that the measurement error has deviated from the historical stable state and exceeded the normal measurement operating range, indicating that there is a hardware failure.

[0028] In a preferred embodiment, step S4 includes the following contents:

[0029] If it is determined to be a non-hardware fault, first call the data records stored in the last complete measurement process, including the normalized measurement error data and environmental data, and align them one-to-one according to the current measurement time grid structure; set the current measurement time grid index to , the historical measurement time grid index is , then the time grid is matched on the time axis. After the time grid data alignment is completed, the degree of change of the environmental data in the measurement time grid is analyzed; the weighted calculation of the current measurement time grid is used The corresponding historical measurement time grid Normalized offset on environmental parameters; if the normalized offset value is less than the environmental change threshold, the corresponding time grid is determined to be in the environmental stability range, otherwise the corresponding time grid is eliminated.

[0030] In a preferred embodiment, step S4 further includes the following:

[0031] After selecting the environmental stability interval, the time grid where the error first appeared and the corresponding measurement area are determined based on the difference between the current measurement error and the historical error data;

[0032] Then, all time grids that meet the environmental stability conditions are searched in chronological order, and the first time grid that meets the measurement error change rate exceeding the error mutation threshold is found. , this time grid As the error starting time grid, determine the corresponding measurement area;

[0033] In order to locate the error starting time grid The corresponding measurement area determines the physical area covered by the measurement device in the corresponding time grid according to the correspondence between the time grid and the spatial scanning path; the measurement area index is set to , then the measurement area corresponding to the error starting time grid is: ;in, It refers to the mapping relationship between the measurement time grid and the measurement area;

[0034] Finally, the measurement time grid where the error first appeared is located. and its corresponding measurement area .

[0035] An intelligent calibration system for semiconductor testing equipment includes: a data sorting module, a deviation analysis module, a trend induction module, an error tracing module and a local calibration module;

[0036] Data sorting module: When calibration starts, it preprocesses the measurement data and environmental data within fixed sampling points and time intervals, creates samples based on the measurement time grid, and passes the preprocessed data to the deviation analysis module.

[0037] Deviation analysis module: extracts the degree of deviation between the current measurement error and historical measurement data, and quantifies its stability in combination with the influence of environmental conditions. At the same time, it calculates the error fluctuation range within the measurement time grid, adjusts the calculation based on the time factor to obtain the deviation amplitude, and passes the calculation result to the trend induction module;

[0038] Trend Summarization Module: Extracts the overall error trend and compares it with the historical stable state to form a comprehensive deviation. This is then matched with the set reference limit to determine whether it is a hardware failure and pass the judgment result to the error tracing module.

[0039] Error tracing module: If the error is determined to be non-hardware fault, the module traces back the last measurement data, aligns the historical error data by measurement time grid, checks the degree of environmental change within each time grid, selects the stable interval, determines the measurement time grid where the error first occurred and the corresponding measurement area, and passes the results to the local calibration module.

[0040] Local calibration module: Based on the determined measurement time grid and the corresponding measurement area, re-execute the local calibration of the corresponding measurement area according to the preset rules.

[0041] The technical effects and advantages of the intelligent calibration method and system for semiconductor testing equipment of the present invention are as follows:

[0042] The present invention splits the measurement data into time series and constructs a correspondence between the measurement time grid and the measurement area, so that the source of the error can be accurately located in time and space. At the same time, combined with an in-depth analysis of the measurement error trend, it identifies whether the error is a short-term fluctuation or a long-term anomaly, thereby distinguishing between accidental errors and hardware failures. In the case of short-term fluctuations, the last measurement data is traced back based on the measurement time grid, and the interval with stable environment is screened to determine the location where the error first occurred and its corresponding measurement area. Local calibration is performed on this area, avoiding redundant operations that are repeatedly performed throughout the entire process in traditional methods, improving measurement efficiency, reducing equipment downtime, and enhancing the accuracy of measurement error correction, so that semiconductor detection equipment can still maintain high measurement stability and data reliability under high precision requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic flow chart of an intelligent calibration method for semiconductor testing equipment according to the present invention;

[0044] Figure 2 This is a structural diagram of an intelligent calibration system for semiconductor testing equipment according to the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] Example 1: Figure 1 The present invention provides an intelligent calibration method for semiconductor testing equipment, comprising:

[0047] S1: When calibration starts, the measurement data and environmental data within fixed sampling points and time intervals are preprocessed, and samples are created by splitting them according to the measurement time grid.

[0048] S2: Extract the degree of deviation between the current measurement error and historical measurement data, and quantify its stability in combination with the influence of environmental conditions. At the same time, calculate the error fluctuation range within the measurement time grid, and adjust the calculation based on the time factor to obtain the deviation amplitude.

[0049] S3: Extract the overall error trend and compare it with the historical stable state to form a comprehensive deviation. Then match it with the set reference limit to determine whether it is a hardware failure.

[0050] S4: If the error is determined to be non-hardware failure, trace back the last measurement data, align the historical error data according to the measurement time grid, check the degree of environmental change within each time grid, screen out the stable interval, and determine the measurement time grid where the error first occurred and the corresponding measurement area.

[0051] S5: Based on the determined measurement time grid and the corresponding measurement area, re-perform local calibration of the corresponding measurement area according to preset rules.

[0052] Step S1 includes the following contents:

[0053] At the beginning of calibration, fixed measurement sampling points and their corresponding time intervals are determined, and a data collection mechanism is established to ensure that data within each measurement time grid is fully recorded. Measurement data includes core measurement information such as height data, reflectivity, and interferometric image signals acquired by the optical profiler. Environmental data, including external factors that affect measurement stability, such as temperature, humidity, vibration, and light source power, is also collected simultaneously. The data collection process must ensure time synchronization, meaning that data from all sensors must be stored at set intervals and mapped to specific measurement time grids to form a time series dataset.

[0054] After data acquisition is complete, the collected data is denoised. First, neighborhood differencing is used to screen outliers in the measured data, and abnormal signals that significantly deviate from their adjacent measurements are removed to reduce the impact of transient fluctuations in the measuring equipment. Second, the environmental data is smoothed using sliding window averaging or median filtering to remove single sampling errors, making it more reflective of overall trends rather than being affected by short-term interference. For signals with random noise, such as interferometric image signals or reflectivity data, high-frequency noise components are filtered out through signal frequency domain analysis to retain key features.

[0055] After denoising, the measurement and environmental data are normalized so that values ​​of different dimensions fall within the same scale range, facilitating subsequent analysis. Normalization uses interval mapping, mapping the measurement and environmental data to a preset standard range while preserving the relative trends of the original data, ensuring that the normalization process does not affect the essential information of the data. The normalized data is then split into time grids, with each measurement grid containing the measurement and environmental data for the corresponding time period. A complete time series dataset is constructed according to the measurement sequence, forming a standardized data structure that can be used for subsequent error analysis.

[0056] A measurement time grid refers to a unit of measurement data divided at fixed time intervals during the calibration or measurement process. Since the measurement process of an optical profiler is continuous, in order to facilitate the analysis of the stability and changing trends of the measurement data, the measurement data needs to be divided into time dimensions. The length of the measurement time grid is determined by the sampling frequency, data processing capabilities, and measurement requirements, and is usually set to range from a few milliseconds to a few seconds. Each measurement time grid contains all measurement data and environmental data within that time period, including information such as height, reflectivity, interference patterns, temperature and humidity, and vibration. The role of the measurement time grid is to provide a data structure in the time dimension, so that data analysis not only focuses on the status of the measurement point itself, but also can observe the changing trend of errors in combination with historical data.

[0057] The measurement area refers to the physical space covered by the optical profiler as it scans the workpiece surface during measurement. The size and shape of the measurement area depend on the measuring device's optical system, scanning pattern, and the geometric characteristics of the object being measured. During actual measurement, the device collects data at different physical locations along a preset scanning path to obtain complete profile information of the workpiece surface. The measurement area can be further divided into multiple local measurement units, each corresponding to a specific spatial coordinate range and recording the measurement data within that range. The purpose of the measurement area is to provide a data structure in the spatial dimension, enabling the system to track the distribution of errors at physical locations.

[0058] The measurement time grid and the measurement area are two interrelated dimensions. The former describes the temporal distribution characteristics of the data, while the latter describes the spatial distribution characteristics of the data. Since the measuring head of the optical profiler collects data from different areas in sequence along a predetermined path during the scanning process, the measurement data corresponding to each measurement time grid is not limited to a single measurement area, but is related to the scanning speed and path of the device. During the data analysis process, the relationship between the measurement time grid and the measurement area can be established through time-space mapping. That is, within a certain measurement time grid, the system can determine the physical area where the device's measuring head is located and perform error analysis based on the measurement data within that area. This time-space association method allows errors to be traced not only in the time dimension, but also to be precisely located in specific areas in physical space. This allows errors to be traced back to the corresponding measurement area when they exceed the tolerance, and local calibration can be performed on that area without the need for performing a full-process calibration.

[0059] Through the above processing flow, we finally obtain a time series sample containing complete measurement data and environmental data, and ensure data quality. This allows subsequent error analysis to be carried out on the basis of noise-free, normalized data, and the error sources and changing trends can be traced according to the measurement time grid structure.

[0060] Step S2 includes the following contents:

[0061] The degree of deviation between the current measurement error and historical measurement data is extracted, and its stability is quantified in combination with the influence of environmental conditions. The time-varying entropy diffusion index is measured to quantify the degree of deviation of the current measurement error compared to historical measurement data, and the error stability is corrected in combination with environmental conditions. The calculation is based on the normalized data split according to the measurement time grid. Each time grid contains measurement data and environmental data, and a complete time series data set is constructed. The processing steps are as follows:

[0062] Since the error trend may be affected by environmental parameters, it is necessary to normalize the current measurement error and the historical error before calculating the error deviation. Set the current measurement error within the measurement time grid to , the historical measurement error is ,in represents the time grid index, Represents the sampling point index within the time grid, Represents the normalized measurement error. The error deviation is calculated using the following formula: ;in, Time grid The internally normalized environmental impact factor is calculated by normalizing environmental parameters such as temperature, humidity, and vibration. Its purpose is to compensate for the impact of the environment on the measurement error in the error calculation.

[0063] Calculation error deviation Finally, it is necessary to introduce the time impact factor to reflect the diffusion characteristics of the error in the time dimension. The definition is as follows: ;in, Time grid The number of data points within Time grid The central moment, To measure the reference time, is the time normalization parameter. This index introduces the time factor into the error deviation calculation through nonlinear logarithmic modulation to capture the long-term trend of error changes.

[0064] Calculate the error fluctuation range within the measurement time grid, adjust the calculation based on the time factor to obtain the deviation amplitude, and finally obtain the time domain ripple jump index, which is used to characterize the fluctuation amplitude of the error within the measurement time grid and adjust the cumulative effect of the fluctuation based on the time scale. The calculation is based on the processing results of the first step, that is, the measurement data and environmental data after the time grid is divided, and secondary processing is performed based on the calculation results of the time-varying entropy diffusion index. The processing steps are as follows:

[0065] At each measurement time Within , the error changes between adjacent sampling points are transformed into exponential scales to amplify the influence of small fluctuations. The normalized measurement error is set to , then the error jump value is defined as: ;in, This sensitivity adjustment parameter controls the response of the error jump calculation to small fluctuations. This calculation method ensures that the response is low when the error fluctuates within a small range, while exponentially amplifying the impact of sudden error changes.

[0066] After calculating the error jump, it is necessary to adjust the time scale of the overall fluctuation of the measurement time grid to consider the impact of different time grid lengths on error accumulation. The time domain ripple jump index is calculated as follows: ;in, Time grid duration, is the time equilibrium constant. Through the square root time modulation function, this exponent automatically adjusts the error accumulation effect of different time grids, ensuring that the error in long time grids is not excessively amplified by the increase in the number of samples, while ensuring the stability of error fluctuations in short time grids.

[0067] Step S3 includes the following contents:

[0068] In the measurement time grid, we first obtain the time series variation characteristics of the error based on the time-varying entropy diffusion index and the time domain ripple jump index, and then use the time series transformation method to extract the overall error trend of the measurement time grid. Set the measurement time grid index to ,exist The values ​​calculated for the time-varying entropy diffusion index and the time-domain ripple jump index within the time grid are and , then in the continuous Within each measurement time grid, the error trend function is constructed according to the nonlinear transformation method, and the overall error trend is extracted based on it.

[0069] First, double difference calculations are performed on the time-varying entropy diffusion index and the time-domain ripple jump index in the time series to eliminate the linear growth term of the measurement error and highlight the nonlinear change trend in a short period of time:

[0070] ;

[0071] ;

[0072] The purpose of this double difference calculation is to extract the acceleration characteristics of the error change in the time grid series, ensuring that the trend amplitude is low when the error changes slowly, and amplifying the change signal when the error changes suddenly. Afterwards, the transformation results of the time-varying entropy diffusion index and the time-domain ripple jump index are time-series integrated to obtain the overall error trend: ;in, represents the base of natural logarithms, is a time decay factor, which gradually reduces the impact of errors in more distant timeframes while making the impact of recent error fluctuations stronger. This calculation method ensures that the system prioritizes error changes in the most recent timeframe while also taking into account error trends over longer timeframes.

[0073] In obtaining the overall error trend Finally, it is necessary to compare it with the historical stable state to determine the overall deviation of the measurement error. The historical stable state is fitted by the time-varying entropy diffusion index and the mean of the time-domain ripple jump index of the measuring equipment under stable working conditions, and the historical stable error characteristics are defined as: ;in, is the total number of measurement time grids of historical stable data, Indicates the measurement time grid index used to calculate the historical stability error characteristics, ranging from 1 to Then calculate the comprehensive deviation of the current overall error trend compared to the historical stable error: ;in, Adjusting the deviation mapping parameters is used to control the nonlinear amplification effect of error deviation. This calculation method ensures that when the overall error trend is close to the historical stable state, the overall deviation is small. When the error trend moves away from the historical stable state, the deviation increases rapidly along with the nonlinear mapping function, enhancing sensitivity to abnormal changes.

[0074] In calculating the comprehensive deviation After that, it is necessary to match it with the set reference limit to determine whether the current error is a short-term fluctuation or a long-term abnormality, and further determine whether it is a hardware failure. The reference limit setting includes the upper limit of short-term fluctuation and long-term abnormal threshold , judge according to the following rules:

[0075] like , the error is judged to be within the normal range and no additional adjustment is required.

[0076] like , the error is determined to be a short-term fluctuation, not a hardware fault. The measurement error is within the fluctuation range, and the error change has not formed a sustained trend. This is usually caused by environmental fluctuations, transient interference, or single measurement deviation. The system will review the previous measurement data and screen the stable range based on the environmental data within the measurement time grid. It will further analyze the measurement time grid where the error first occurred and the corresponding measurement area to provide a precise adjustment range for subsequent local calibration.

[0077] like , it is determined that the measurement error has deviated from the historical stable state and exceeded the normal measurement operating range, indicating that there is a hardware failure. The system triggers a fault warning and performs a complete calibration process.

[0078] Step S4 includes the following contents:

[0079] If it is determined to be a non-hardware fault, first call the data records stored in the last complete measurement process, including the normalized measurement error data and environmental data, and align them one-to-one according to the current measurement time grid structure. Set the current measurement time grid index to , the historical measurement time grid index is , then time grid matching is performed on the time axis so that for any The measurement data can be found in the time grid corresponding to the last measurement data. During the data alignment process, ensure that the measurement error data and environmental data are synchronized at the same time interval so that the measurement error trend and environmental changes can accurately correspond on the time axis to avoid data deviation caused by time drift.

[0080] After the time grid data alignment is completed, analyze the degree of change of the environmental data within the measurement time grid to screen out the stable range where the error can be traced. Set the environmental data including temperature ,humidity ,vibration The current measurement time grid is calculated by weighted factors such as The corresponding historical measurement time grid Normalized offset on the environmental parameter: ;in, , , is the standard normalization factor of each environmental parameter, so that different physical quantities can be compared on the same scale. , , are the preset scaling coefficients for their respective environmental parameters. If the normalized offset value is less than the environmental change threshold, the corresponding time grid is determined to be in the environmental stability range. Otherwise, the corresponding time grid is discarded and does not participate in the error backtracking analysis, ensuring that subsequent analysis is calculated based on environmentally stable time grids.

[0081] After filtering out the environmental stability interval, based on the difference between the current measurement error and the historical error data, determine the time grid where the error first appeared and the corresponding measurement area. Set the measurement error data to And the historical error data is , calculate the rate of change of measurement error: Then, search all time grids that meet the environmental stability conditions in chronological order and find the first time grid that meets the measurement error change rate exceeding the error mutation threshold. This time grid As the error starting time grid, the corresponding measurement area is further determined.

[0082] In order to locate the error starting time grid The corresponding measurement area determines the physical area covered by the measurement device within the time grid based on the correspondence between the time grid and the spatial scanning path. Set the measurement area index to , then the measurement area corresponding to the error starting time grid is: ;in, It refers to the mapping relationship between the measurement time grid and the measurement area, that is, the physical area covered by the scanning path of the measurement device within a certain time grid. Since the optical profiler moves along a predetermined trajectory during scanning, the scanning position corresponding to each measurement time grid can be derived from the motion trajectory of the device, the scanning speed, and the time grid length. For example, if the optical profiler scans the surface of a wafer at a fixed rate and each measurement time grid lasts for 50 milliseconds, then the scanning position in the time grid is 50 milliseconds. During this period, the measuring head moves from position Move to location , then the measurement area of ​​the time grid is from arrive If the error first occurs in the time grid ,So This indicates the specific physical location where the error occurs, such as a local area on the wafer or the edge of the chip package. Through this mapping, the measurement system can accurately trace the source of the error and perform local calibration in that area without affecting the overall measurement process.

[0083] Finally, through the above data alignment, environmental stability screening and error starting point identification, the measurement time grid where the error first appeared is accurately located. and its corresponding measurement area , providing a basis for subsequent local calibration and avoiding unnecessary recalibration of the entire process.

[0084] Step S5 includes the following contents:

[0085] After determining the measurement time grid where the error starts and the corresponding measurement area, first enter the local calibration mode. At this time, all data that completely corresponds to the measurement time grid will be extracted from the complete measurement data set, and then the local calibration mode will be used to calculate the error. Determine the physical area scanned by the device during the time period. Ensure that the time grid and measurement area information are consistent during data extraction to avoid subsequent processing errors caused by data confusion.

[0086] Subsequently, local calibration is performed on the extracted measurement area according to pre-set local calibration rules. The specific steps include: first, analyzing the differences between the historical measurement data and the current data within the area to determine the calibration parameters that need to be adjusted; then, invoking a pre-configured calibration routine to fine-tune and correct the optical components, scanning speed, exposure parameters, and other parameters within the area; during the adjustment process, the measurement data and environmental data are continuously monitored to ensure that the changes in various parameters during the local calibration process are within the expected range.

[0087] After completing a local calibration, the recalibrated measurement area is verified. This involves comparing the new calibrated data with a preset reference standard to confirm whether the error has returned to a normal fluctuation range. If the verification result meets the preset standard, the calibration parameters for that area are updated; otherwise, the system re-calibrates the local calibration according to preset rules until it reaches a qualified state. This complete process ensures precise and targeted local calibration without affecting the overall inspection work.

[0088] Example 2: Figure 2 The present invention provides an intelligent calibration system for semiconductor testing equipment, comprising:

[0089] Data sorting module, deviation analysis module, trend induction module, error tracing module and local calibration module;

[0090] Data sorting module: When calibration starts, it preprocesses the measurement data and environmental data within fixed sampling points and time intervals, creates samples based on the measurement time grid, and passes the preprocessed data to the deviation analysis module.

[0091] Deviation analysis module: extracts the degree of deviation between the current measurement error and historical measurement data, and quantifies its stability in combination with the influence of environmental conditions. At the same time, it calculates the error fluctuation range within the measurement time grid, adjusts the calculation based on the time factor to obtain the deviation amplitude, and passes the calculation result to the trend induction module;

[0092] Trend Summarization Module: Extracts the overall error trend and compares it with the historical stable state to form a comprehensive deviation. This is then matched with the set reference limit to determine whether it is a hardware failure and pass the judgment result to the error tracing module.

[0093] Error tracing module: If the error is determined to be non-hardware fault, the module traces back the last measurement data, aligns the historical error data by measurement time grid, checks the degree of environmental change within each time grid, selects the stable interval, determines the measurement time grid where the error first occurred and the corresponding measurement area, and passes the results to the local calibration module.

[0094] Local calibration module: Based on the determined measurement time grid and the corresponding measurement area, re-execute the local calibration of the corresponding measurement area according to the preset rules.

[0095] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0096] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

[0097] It should be noted that, in this document, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article or device. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0098] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An intelligent calibration method for semiconductor testing equipment, characterized in that: Including steps: S1: When calibration begins, pre-process the measurement data and environmental data within fixed sampling points and time intervals, and create samples by splitting them into measurement time grids; S2: Extract the degree of deviation between the current measurement error and historical measurement data, and quantify its stability in combination with the influence of environmental conditions. At the same time, calculate the error fluctuation range within the measurement time grid, and adjust the calculation based on the time factor to obtain the deviation amplitude. Step S2 includes the following contents: The degree of deviation between the current measurement error and the historical measurement data is extracted, and its stability is quantified in combination with the influence of environmental conditions. The time-varying entropy diffusion index is obtained through measurement. The processing steps are as follows: Set the current measurement error within the measurement time grid to , the historical measurement error is ,in represents the time grid index, Represents the sampling point index within the time grid, Represents the normalized measurement error; the error deviation is calculated using the following formula: ;in, Time grid Internally normalized environmental impact factor; time-varying entropy diffusion index The definition is as follows: ;in, Time grid The number of data points within Time grid The central moment, To measure the reference time, is the time normalization parameter; Calculate the error fluctuation range within the measurement time grid, adjust the calculation based on the time factor to obtain the deviation amplitude, and finally obtain the time domain ripple jump index. The processing steps are as follows: At each measurement time Within, the error change between adjacent sampling points is transformed into an exponential scale, and the normalized measurement error is set to , then the error jump value is defined as: ;in, For sensitivity adjustment parameters, the time domain ripple jump index is calculated as follows: ;in, Time grid duration, is the time equilibrium constant; S3: Extract the overall error trend and compare it with the historical stable state to form a comprehensive deviation. Then match it with the set reference limit to determine whether it is a hardware failure. Set the measurement time grid index to ,exist Double difference transformation is performed on the time-varying entropy diffusion index and the time-domain ripple jump index within the time grid; then, the transformation results of the time-varying entropy diffusion index and the time-domain ripple jump index are time-series integrated to obtain the overall error trend; S4: If the error is determined to be non-hardware fault, the previous measurement data is retraced, and the historical error data is aligned according to the measurement time grid. The degree of environmental change within each time grid is checked, and the stable interval is screened. The measurement time grid where the error first occurred and the corresponding measurement area are determined. S5: Based on the determined measurement time grid and the corresponding measurement area, re-perform local calibration of the corresponding measurement area according to preset rules.

2. The intelligent calibration method for semiconductor testing equipment according to claim 1, characterized in that: Step S1 includes the following contents: During calibration, all sensor data must be stored at set time intervals and correspond to specific measurement time grids to form a time series dataset. After data acquisition is completed, the collected data is denoised and normalized, and the processed data is split according to the time grid. Each measurement time grid contains the measurement data and environmental data within the corresponding time period, and a complete time series dataset is constructed according to the measurement order to form a standardized data structure.

3. The intelligent calibration method for semiconductor testing equipment according to claim 2, characterized in that: Step S3 includes the following contents: Obtaining the overall error trend After that, it is compared with the historical stable state to determine the overall deviation of the measurement error; the historical stable state is fitted by the time-varying entropy diffusion index and the mean of the time-domain ripple jump index of the measuring equipment under stable working conditions, and the historical stable error characteristics are defined as: ;in, is the total number of measurement time grids of historical stable data, Indicates the measurement time grid index used to calculate the historical stability error characteristics, ranging from 1 to ; Then calculate the comprehensive deviation of the current overall error trend compared to the historical stable error: ;in, Parameters for adjusting the deviation mapping.

4. The intelligent calibration method for semiconductor testing equipment according to claim 3, characterized in that: Step S3 also includes the following: In calculating the comprehensive deviation After that, it is matched with the set reference limit to determine whether the current error is a short-term fluctuation or a long-term abnormality, and whether it is a hardware failure. The reference limit is set to include the upper limit of short-term fluctuation. and long-term abnormal threshold , judge according to the following rules: like , then the error is determined to be within the normal range and no additional adjustment is required; like , then the error is judged to be a short-term fluctuation, not a hardware failure; like , it is determined that the measurement error has deviated from the historical stable state and exceeded the normal measurement operating range, indicating that there is a hardware failure.

5. The intelligent calibration method for semiconductor testing equipment according to claim 4, characterized in that: Step S4 includes the following contents: If it is determined to be a non-hardware fault, first call the data records stored in the last complete measurement process, including the normalized measurement error data and environmental data, and align them one-to-one according to the current measurement time grid structure; set the current measurement time grid index to , the historical measurement time grid index is , then the time grid is matched on the time axis. After the time grid data alignment is completed, the degree of change of the environmental data in the measurement time grid is analyzed; the weighted calculation of the current measurement time grid is used The corresponding historical measurement time grid Normalized offset on environmental parameters; if the normalized offset value is less than the environmental change threshold, the corresponding time grid is determined to be in the environmental stability range, otherwise the corresponding time grid is eliminated.

6. The intelligent calibration method for semiconductor testing equipment according to claim 5, characterized in that: Step S4 also includes the following: After selecting the environmental stability interval, the time grid where the error first appeared and the corresponding measurement area are determined based on the difference between the current measurement error and the historical error data; Then, all time grids that meet the environmental stability conditions are searched in chronological order, and the first time grid that meets the measurement error change rate exceeding the error mutation threshold is found. , this time grid As the error starting time grid, determine the corresponding measurement area; In order to locate the error starting time grid The corresponding measurement area determines the physical area covered by the measurement device in the corresponding time grid according to the correspondence between the time grid and the spatial scanning path; the measurement area index is set to , then the measurement area corresponding to the error starting time grid is: ;in, It refers to the mapping relationship between the measurement time grid and the measurement area; Finally, the measurement time grid where the error first appeared is located. and its corresponding measurement area .

7. An intelligent calibration system for semiconductor testing equipment, used to implement the intelligent calibration method for semiconductor testing equipment according to any one of claims 1 to 6, characterized in that: include: Data sorting module, deviation analysis module, trend induction module, error tracing module and local calibration module; Data sorting module: When calibration starts, it preprocesses the measurement data and environmental data within fixed sampling points and time intervals, creates samples based on the measurement time grid, and passes the preprocessed data to the deviation analysis module. Deviation analysis module: extracts the degree of deviation between the current measurement error and historical measurement data, and quantifies its stability in combination with the influence of environmental conditions. At the same time, it calculates the error fluctuation range within the measurement time grid, adjusts the calculation based on the time factor to obtain the deviation amplitude, and passes the calculation result to the trend induction module; Trend Summarization Module: Extracts the overall error trend and compares it with the historical stable state to form a comprehensive deviation. This is then matched with the set reference limit to determine whether it is a hardware failure and pass the judgment result to the error tracing module. Error tracing module: If the error is determined to be non-hardware fault, the module traces back the last measurement data, aligns the historical error data by measurement time grid, checks the degree of environmental change within each time grid, selects the stable interval, determines the measurement time grid where the error first occurred and the corresponding measurement area, and passes the results to the local calibration module. Local calibration module: Based on the determined measurement time grid and the corresponding measurement area, re-execute the local calibration of the corresponding measurement area according to the preset rules.

Images