Identifying process anomalies using measurement violation analysis

Abstract

The subject matter herein may be embodied, inter alia, in a method, system, and / or apparatus that receives current metrology data of an operation for a current sample in a manufacturing process. The metrology data includes a current value of a parameter at each of one or more locations on the current sample. The method includes obtaining a baseline rate of change of a parameter value for the parameter for each of the one or more locations. The method further includes determining a current rate of change of the parameter value for each of the one or more locations. The current rate of change is associated with the current sample. The method further includes comparing the current rate of change of the parameter value to the baseline rate of change of the parameter value and identifying an instance of an anomaly in the manufacturing process based on the comparison.

Description

[Technical Field]

[0001] Some embodiments of the present invention generally relate to systems, methods, and apparatus for detecting anomalies in manufacturing systems using sample measurement violation analysis. [Background technology]

[0002] In manufacturing, for example, in the manufacture of semiconductor devices, product quality can be measured directly using metrology tools and indirectly by monitoring process equipment sensors. This information is collected at different points in the product manufacturing lifecycle. When a problem with a process tool or the resulting product needs to be identified, manufacturing engineers must go through the laborious and costly process of analyzing numerous data points (e.g., metrology data for many samples containing various measured parameters). For example, when notified of a potential product problem, engineers must review the corresponding metrology data to find warning characteristics of the product. A common technique for identifying metrology violations is the use of statistical process control (SPC).

[0003] Statistical process control (SPC) is a quality control method that uses statistical methods to monitor and control processes. SPC can help ensure that processes operate with controlled variation and produce products that meet specifications with less waste (e.g., rework or scrap). SPC can be applied to a variety of processes where the output of a met product (e.g., product that meets specifications) can be measured. SPC can include industry-standard methods for measuring and controlling quality during the manufacturing process. Quality data in the form of product and process measurements can be acquired in real time during production. The data can then be plotted on a graph with calculated control limits. Two limits often used to draw boundaries on data include, first, control limits, which may be determined by the capability of the process, and, second, specification limits, which may be determined by the desired outcome (e.g., the range of measurements that meet certain specification requirements). Summary of the Invention

[0004] A method and system for identifying an instance (e.g., a source) of an anomaly in a manufacturing process. The method includes receiving current metrology data of operation for a current sample in the manufacturing process. The metrology data includes current values ​​of a parameter at each of one or more locations on the sample from the current sample and a previous metrology process step. The method includes obtaining a baseline rate of change of the parameter value for the parameter for each of the one or more locations. The method further includes determining a current rate of change of the parameter value for each of the one or more locations. The current rate of change is associated with the current sample. The method further includes comparing the current rate of change of the parameter value to the baseline rate of change of the parameter value and identifying the instance of an anomaly in the manufacturing process based on the comparison.

[0005] In the figures of the accompanying drawings, the present invention is illustrated by way of example, and not by way of limitation, in which like reference numerals refer to like elements. It should be noted that different references to "an" or "one" embodiment of the present disclosure do not necessarily refer to the same embodiment, and such references do mean at least one. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a block diagram illustrating a manufacturing system according to aspects of the present disclosure. [Figure 2] FIG. 1 is a block diagram illustrating a manufacturing process of a manufacturing system according to aspects of the present disclosure. [Figure 3] FIG. 10 illustrates a distribution of the rate of change of parameter values ​​for various samples with respect to operations in a manufacturing process, according to aspects of the present disclosure. [Figure 4] FIG. 10 illustrates an exemplary graphical user interface for a sample pattern, according to aspects of the present disclosure. [Figure 5] FIG. 1 is a block diagram illustrating a process failure mode and effects analysis (FMEA) according to an aspect of the present disclosure. [Figure 6] 1 is a flow diagram of a method for identifying an instance of an anomaly in a manufacturing process, according to an aspect of the present disclosure. [Figure 7] FIG. 1 is a block diagram of an example computing device capable of identifying instances of anomalies in a manufacturing process. DETAILED DESCRIPTION OF THE INVENTION

[0007] In manufacturing (e.g., microfabrication, wafer fabrication, substrate generation, and / or the like), various processing tools and procedures are used to produce a desired result (e.g., a sample meeting desired specifications or having desired properties). The manufacturing process may include various manufacturing and metrology steps. Metrology steps may be used between manufacturing steps to measure metrology data indicative of the quality and success of previously performed manufacturing steps. Metrology data may consist of numerous parameter site measurements (e.g., thickness, roughness, depth, particle count, surface slope, etc.) taken at various locations on the wafer containing the sample. As the sample goes through the manufacturing process, many metrology steps may measure and store historical metrology data to show how the sample reached its current parameter value. Manufacturing systems may flag measurements that violate specifications. For example, in SPC, a measurement may be violating if it is outside a control limit, violates a predetermined rule, is outside a specification limit, or is otherwise deemed unacceptable. Violating measurements may be caused by, among other things, a faulty manufacturing machine or process. For example, a manufacturing machine may contain broken tools or worn equipment that is not performing as normal. Identifying the source of a violation measurement can be costly and illusory. For example, manufacturing downtime, production of an improper product, and / or escalating costs to identify and repair the source of a manufacturing anomaly can be costly and resource intensive.

[0008] Traditionally, SPC violation analysis is performed manually. An SPC chart with identified measurement violations can be presented to the user. The user is tasked with identifying anomalies in the manufacturing process, including potentially defective machines, equipment, procedures, etc., based on their knowledge. However, as manufacturing systems become more complex and increasingly automated, the ability to measure and collect more data increases, making the amount of data unmanageable for users to process based solely on their own knowledge. Furthermore, manufacturing systems can be designed to handle many different processes (e.g., different substrate recipes and diverse samples that use different machines, equipment, and / or procedures to reach the manufactured result), requiring knowledge and memory beyond what the human brain can achieve. Furthermore, determining anomalies based on SPC results is insufficient to determine upstream failures of machines and / or processes used or performed in connection with the operation of the manufacturing process prior to the current or final operation of the manufacturing process. For example, even if the first machine is the source of the anomaly, the process may use 20 machines, and after this use, the source of the error may be hidden or diluted, making source identification difficult.

[0009] Aspects and embodiments of the present disclosure address these and other shortcomings of existing techniques by identifying instances of manufacturing process anomalies (e.g., broken machinery, defective operations, worn tools, etc.) using measurement data of a sample associated with the manufacturing process. Initially, a processing device may receive current metrology data of operations for a current sample in the manufacturing process. The metrology data may include current values ​​of parameters at each of one or more locations on the current sample. The processing device may obtain a baseline rate of change of the parameter value for the parameter for each of the one or more locations. The current rate of change of the parameter value may be associated with the current sample. The processing device may further include comparing the current rate of change of the parameter value to the baseline rate of change of the parameter value and, based on the comparison, identifying instances of manufacturing process anomalies.

[0010] Aspects of the present disclosure result in significant reductions in energy consumption (e.g., battery or power consumption), bandwidth, latency, etc. For example, processing and analyzing metrology data in the disclosed manner can process data faster than conventional systems and can allow for more efficient data storage and retrieval than conventional systems. Furthermore, recommended corrective actions to take to repair anomalies can be identified and applied sooner than conventional systems, resulting in reduced costs from producing defective or malfunctioning samples before they are corrected, preventing further damage from worn, broken, or otherwise defective equipment, and predicting impending anomalies, defects, failures, and / or errors so that corrective actions can be taken proactively.

[0011] 1 is a block diagram illustrating a manufacturing system 100 according to an aspect of the present disclosure. As shown in FIG. 1, the manufacturing system 100 includes a manufacturing execution system 102, a metrology system 110, a statistical process control (SPC) system 116, a data store 122, a client device 128, and an equipment engineering system 130. The manufacturing execution system 102, the metrology system 110, the SPC system 116, the data store 122, and / or the equipment engineering system 130 may each be hosted on one or more computing devices, including a server computer, a desktop computer, a laptop computer, a tablet computer, a notebook computer, a personal digital assistant (PDA), a mobile communication device, a cellular phone, a smartphone, a handheld computer, or the like.

[0012] The manufacturing execution system 102, the metrology system 110, the SPC system 116, the data store 122, the equipment engineering system 130, and the client devices 128 may be coupled to one another via a network 140 to identify instances of anomalies in the manufacturing execution system 102. In some embodiments, the network 140 is a public network that provides each element of the manufacturing system 100 with access to each other and to other publicly available computing devices. In some embodiments, the network 140 is a private network that provides each element of the manufacturing system 100 with access to each other and to other privately available computing devices. The network 140 may include one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), routers, hubs, switches, server computers, and / or combinations thereof. Alternatively or additionally, any of the elements of manufacturing system 100 may be integrated together or otherwise coupled without the use of network 140 .

[0013] The client device 128 may be or may include a personal computer (PC), laptop, mobile phone, tablet computer, netbook computer, network-connected television (“smart TV”), network-connected media player (e.g., Blu-ray player), set-top box, over-the-top (OOT) streaming device, operator box, etc. The client device 128 may include a browser, an application, and / or a measurement violation tool. In some embodiments, the client device 128 may be capable of accessing the manufacturing execution system 102, the metrology system 110, the SPC system 116, the data store 122, and / or the equipment engineering system 130 (e.g., via the network 140 using a browser or an application) as described herein, and may communicate (e.g., send and / or receive) indications of violation measurements, identified anomalies, and metrology data during various stages of violation analysis.

[0014] The manufacturing execution system 102 may include machine operations 104, process implementations 106, and process dependencies 108 for various manufacturing processes. The manufacturing process may include various steps or operations that utilize one or more machines to perform one or more machine operations 104 using one or more different process implementations 106. For example, the various machines may include specialized chambers such as etch chambers, deposition chambers (including chambers for atomic layer deposition, chemical vapor deposition, or plasma-enhanced chemical vapor deposition), anneal chambers, and / or other similar chambers. In another example, the machines may include a sample transport system (e.g., a selective compliance assembly robot arm (SCARA) robot, a transfer chamber, a front-opening pod (FOUP), a side storage pod (SSP), and / or other similar) for transporting samples between machines and process steps.

[0015] The process implementation 106 can include various specifications for performing the machine operation 104 in a manufacturing process. For example, the process implementation 106 can include process specifications such as the duration of the machine operation 104, the machine tool used for the operation, the temperature, flow rate, pressure, etc. of the machine (e.g., chamber), deposition sequence, and the like. In another example, the process implementation can include transport instructions for transporting the sample to a further process step or for measurement by the metrology system 110.

[0016] The process dependencies 108, also referred to as manufacturing recipes or manufacturing process instructions, comprise a sequencing of machine operations 104 using process implementations 106 that, when applied in a specified order, produce a manufactured sample (e.g., a substrate or wafer having predetermined properties or meeting predetermined specifications). In some embodiments, the process dependencies 108 of a manufacturing process are stored in a data store or, alternatively or additionally, in a manner that produces a table of data representing steps or operations in the manufacturing process. For example, one or more of the metrology system 110, SPC system 116, and / or equipment engineering system 130 may request process dependencies for a sample currently being measured or for which associated metrology data is being processed. In a further example, process dependencies for a specified number of steps prior to the operation on the current sample in the manufacturing process (e.g., the last 5, 10, 15, or n process steps of the manufacturing process) may be requested.

[0017] In some embodiments, the manufacturing execution system 102 contains all the instructions, machines, and processes for manufacturing a sample (e.g., a substrate or wafer), while in other embodiments, the manufacturing execution system 102 controls and coordinates the various machines, tools, and processes in manufacturing the sample. In other embodiments, the manufacturing execution system 102 in combination with the metrology system 110 may form one system designed to alternate between manufacturing and metrology processes throughout the manufacturing process.

[0018] The metrology system 110 includes metrology tools 114 for measuring parameters at various locations on samples being manufactured by the manufacturing execution system 102. These parameters may include various measurements indicative of the quality of operations performed by the manufacturing process by the manufacturing execution system 102. For example, the parameters may include sample thickness, etch rate, resistivity, particle count, etc. In some embodiments, the metrology tools coordinate measurements taken at specific, predetermined locations on each sample. For example, after a particular manufacturing operation (e.g., a deposition or etch operation), each sample is sent to the metrology system 110. The metrology tools 114 measure one or more parameters at the same location for each sample. The metrology system 110 can transfer this data to the SPC system 116 to create a historical record of measurements associated with a particular operation of the manufacturing process. The metrology system 110 and / or the SPC system 116 can use the historical sample data 124 to create a record of parameter measurements across a range of samples that are in process after the same operation of the manufacturing process.

[0019] In some embodiments, samples produced by the manufacturing execution system 102 are measured for each step of the manufacturing recipe by the metrology system 110. In some embodiments, the process dependencies 108 or manufacturing recipe may include measurement steps such that every sample is manufactured using the same process dependencies 108 and every sample is measured after the same operations and under the same conditions.

[0020] As shown in FIG. 1 , statistical process control (SPC) system 116 can include statistical process tools 118 and an SPC data store, such as SPC database 120. SPC system 116 receives metrology data from metrology system 110 and / or equipment engineering system 130. The SPC system can receive context data (e.g., channel ID, equipment ID, product, process name, process step number, lot ID, etc.) from manufacturing execution system 102, metrology system 110, data store 122, and / or equipment engineering system 130. SPC system 116 applies the metrology data to appropriate charts (e.g., thickness, etch rate, resistivity, particle count, etc.), analyzes the metrology data to detect violations (e.g., product characteristics greater than or less than predetermined thresholds), generates information about products with detected violations (e.g., lot ID, wafer ID, recipe name), and provides this information to equipment engineering system 130. Additionally, SPC system 116 presents SPC charts to SPC clients, such as client device 128. For example, the SPC charts may be presented in a client application and / or web-based browser application hosted on a client device 128 such as a personal computer, laptop, mobile phone, or the like.

[0021] The SPC database 120 includes historical metrology data. For example, the historical metrology data can include past SPC charts (e.g., thickness, etch rate, resistivity, particle count, etc.) and measurement violation data. The SPC database 120 can calculate baseline parameter rates of change 121 for the historical sample data 124. For example, an analysis of variance (ANOVA) can be calculated for one or more historical rates of change for samples produced by the manufacturing execution system 102 and subsequently measured by the metrology system 110. In some embodiments, the SPC system 116 stores the baseline rates of change 121 of parameter values ​​and the historical sample data; in other embodiments, the SPC system 116 stores the rates of change of parameter values ​​and the historical sample data in the data store 122.

[0022] The data store 122 may be a memory (e.g., random access memory), a drive (e.g., a hard drive, a flash drive), a database system, or another type of component or device capable of storing data. The data store 122 may store one or more of historical sample data 124 and failure mode and effects analysis (FMEA) data 126. The historical sample data 124 may include parameter values ​​for various parameters measured from samples produced during various manufacturing processes (e.g., manufacturing process 200 in FIG. 2 ). The historical sample data 124 may include baseline rates of change in parameter values ​​for each parameter at respective locations on one or more previous samples previously produced during the manufacturing process. The FMEA data 126 may store data associated with a failure mode and effects analysis tool 138, which may process failure mode and effects analysis more generally (see, e.g., process failure mode and effects analysis 500 in FIG. 5 ).

[0023] The equipment engineering system 130 may include a measurement violation tool 132. The measurement violation tools include a process dependency tool 134, a rate of change tool 135, a pattern mapping tool 137, and a failure mode and effects analysis (FMEA) tool 138. The equipment engineering system 130 receives metrology data from the metrology system 110 and / or the manufacturing execution system 102 and sends the metrology data to the SPC system 116. The equipment engineering system 130 receives SPC data related to the machines, tools, and / or process operations of the manufacturing process associated with the metrology data.

[0024] The process dependency tool 134 requests process dependency 108 data from the manufacturing execution system 102 and / or data store 122 that is associated with the metrology data measured by the metrology tool 114. The process dependency tool 134 matches previous machine operations 104 and process implementations 106 with the measurements of the current sample.

[0025] The rate of change tool 135 calculates the current rate of change of the current sample being measured by the metrology system 110. The current rate of change can include determining the rate of change of the current parameter value. For example, the metrology system 110 measures a parameter to obtain a set of parameter values ​​at various locations throughout the sample. These parameter values ​​are compared to historical parameter values ​​to determine how much the current parameter value has changed. In some embodiments, the rate of change of the parameter value is calculated by comparing the current parameter value to a sample manufactured immediately before the current sample. The difference between the current parameter value and the parameter value measured from the sample manufactured immediately before the current sample can provide the rate of change of the parameter value. In other embodiments, multiple historical measurements are used along with various techniques for calculating the rate of change of the parameter value. For example, the rate of change can be calculated using a moving average, a mean statistic, a long-term statistic, a short-term statistic, a derivative, an integral, and / or one of the known rate of change calculation methods.

[0026] The rate of change tool 135 compares a reference rate of change of the parameter value (e.g., a historical rate of change of the parameter value) received from the SPC system 116 or calculated locally by the equipment engineering system 130 to the current rate of change of the parameter value for the current sample. In some embodiments, the reference rate of change of the parameter value is determined using one or more historical rates of change of the parameter value from historical metrology data of operation for one or more previous samples in the manufacturing process.

[0027] In some embodiments, based on a comparison of the current rate of change of the parameter value to the reference rate of change of the parameter value, the rate of change tool 135 identifies one or more violation locations each having an associated current rate of change of the parameter value that is greater than the associated reference rate of change of the parameter value.

[0028] An analysis of variance (ANOVA) tool 136 works in conjunction with the rate of change tool 135 to identify one or more violating locations. The ANOVA tool 136 performs an ANOVA using one or more of the historical rates of change in parameter values ​​to determine a baseline rate of change in the parameter values. In further embodiments, the results of this ANOVA can be used to determine a threshold range of acceptable or non-violating rate of change in parameter values ​​for the parameters at each of one or more locations for operation on a current sample in the manufacturing process. In some embodiments, the baseline rate of change in parameter values ​​can be a range of non-violating values ​​statistically calculated by the ANOVA tool 136 from one or more historical rates of change in parameter values.

[0029] The pattern mapping tool 137 receives one or more violation locations from one of the rate of change tool 135 and / or the ANOVA tool 136 and generates a sample pattern associated with the one or more violation locations on the current sample. In some embodiments, the pattern mapping tool 137 applies scaling (e.g., normalization of data points) to different violation locations based on trends or common patterns recorded on previous samples.

[0030] The failure mode and effects analysis (FMEA) tool 138 identifies instances of anomalies in the manufacturing process based on a comparison of the current rate of change of parameter values ​​to a reference rate of change of parameter values. In some embodiments, the FMEA tool 138 receives sample patterns from the pattern mapping tool 137 and identifies instances of anomalies based on the sample patterns.

[0031] The FMEA tool 138 can retrieve FMEA data 126 from the data store 122. The FMEA data 126 can include a list of known problems and root causes for a given piece of equipment, each with associated known symptoms. The pattern sample data received by the FMEA tool 138 is applied to the list of known problems, and a report is generated that identifies common causes of violation locations. For example, the FMEA tool 138 can receive the sample pattern and identify defective tools, machines, or operations in a manufacturing process.

[0032] In some embodiments, the FMEA tool 138 can be used in conjunction with the process dependency tool 134 to identify tools, machines, or processes that operated upstream from the current machine operation being performed on the current sample (e.g., an operational step performed before the current manufacturing step in the same manufacturing process). For example, the current sample may have recently undergone a first operation by a first machine. In some embodiments, the combination of the process dependency tool 134 and the FMEA tool 138 can explore past operations on the sample, such as a second operation by a second machine or tool. The FMEA tool 138 can use the sample pattern to identify the second machine or second tool as the source of the anomaly.

[0033] After an anomaly instance is identified, the FMEA tool 138 may proceed to one of modifying at least one of a machine operation or process implementation associated with the anomaly instance and / or providing a graphical user interface (GUI) that presents a visual indicator of the machine or process associated with the anomaly instance. The GUI may be transmitted over the network 140 and presented on the client device 128. In some embodiments, modifying the machine operation or process implementation may include transmitting instructions to the manufacturing execution system 102 to modify the machine operations 104 and / or process implementations 106 associated with the process recipe or process dependency 108.

[0034] While manufacturing system 100 is shown and described as several different systems and / or devices, it should be noted that various devices can be combined together to perform the functions of the entities shown as separate in FIG. 1 . For example, manufacturing execution system 102 can be combined with metrology system 110 to execute a manufacturing process through manufacturing and metrology operations. In another example, equipment engineering system 130 can be combined with SPC system 116 to analyze data from both SPC analysis and rate of change analysis using statistical process tools 118 and rate of change tools 135. In another example, data store 122 can be stored on one or more of manufacturing execution system 102, metrology system 110, SPC system 116, equipment engineering system 130, and / or client device 128. Additionally, although shown in FIG. 1 as communicating with each other using network 140, any of manufacturing execution system 102, metrology system 110, SPC system 116, data store 122, client device 128, and / or equipment engineering system 130 can be directly coupled and can communicate with each other without the need for network 140.

[0035] 2 is a block diagram illustrating a manufacturing process 200 of a manufacturing system (e.g., manufacturing system 100 of FIG. 1 ) according to an embodiment of the present disclosure. Manufacturing process 200 may include one or more manufacturing operations 202A-B and one or more metrology operations 204A-B. Manufacturing operations 202A-B may be performed by a manufacturing execution system (e.g., manufacturing execution system 102 of FIG. 1 ). Metrology operations 204A-B may be performed by a metrology system (e.g., metrology system 110 of FIG. 1 ).

[0036] In some embodiments, manufacturing process 200 can include a series of manufacturing operations 202A-B and metrology operations 204A-B that, when completed, form a manufactured sample having predetermined characteristics and / or specifications. For example, a manufacturing process for manufacturing a multi-layer substrate can include various layer deposition operations, each of which deposits a layer on a substrate. The manufacturing operations 202A-B can be designed to be completed in a predetermined order to form a multi-layer substrate having a precise layer sequence.

[0037] Fabrication operations 202A-B can include various methods of fabricating the sample. For example, fabrication operations can include etching (e.g., dry etching, plasma etching, wet etching, chemical etching, etc.), deposition (e.g., atomic layer deposition (ALD), chemical vapor deposition (CVD), or plasma-enhanced CVD), patterning (e.g., photolithography, masking, etc.), microforming, and / or the like.

[0038] Metrology operations 204A-B may include various methods and techniques for measuring a set of parameters 206A-D, 208A-D across one or more locations on a fabricated sample at various stages of manufacturing process 200. The set of parameters 206A-D, 208A-D may include various measurements associated with manufacturing operations 202A-B. For example, the set of parameters 206A-D, 208A-D may include measuring a channel thickness, layer or region thickness, etch rate, resistivity, particle count, etc. of a sample. The parameter measurements may indicate the quality level of a fabrication operation performed. In some embodiments, manufacturing process 200 measures 25-50 parameters across 12-20 locations across each sample.

[0039] In some embodiments, the parameters measured during metrology operations 204A-B indicate the quality of a previous manufacturing operation. Alternatively, the parameters measured during metrology operations 204A-B may be indicative of the quality of one or more of the previous manufacturing operations. For example, manufacturing operations 202A and 202B may both be layer deposition operations, and a parameter (e.g., 208A) may indicate the thickness of the substrate. The thickness of the substrate during metrology operation 204B may be affected by manufacturing operations 202A and 202B. This relationship between the parameter and the operation may be stored as part of a manufacturing process recipe or process dependency (e.g., process dependency 108 in FIG. 1 ). The process dependency may track and manage the impact of manufacturing operations 202A-B and downstream processes (e.g., machine operations and process implementations performed in the future as the current machine operation or process implementation of the same manufacturing process), or the impact of processes performed after the specified manufacturing operation. Furthermore, when parameter values ​​are processed or analyzed, the process dependency data may provide a link between previous operations and the current manufacturing quality of a manufacturing sample at a specified stage in manufacturing process 200.

[0040] In some embodiments, manufacturing operations 202A-B and metrology operations 204A-B are alternated throughout the manufacturing process. It should be noted that in some embodiments, multiple manufacturing operations 202A-B can be performed between metrology operations 204A-B. Similarly, various metrology operations can also be performed between manufacturing operations 202A-B. The sequence and flow of manufacturing operations 202A-B and metrology operations 204A-B can depend on the particular manufacturing process 200.

[0041] FIG. 3 illustrates a distribution 300 of parameter rates of change for various samples with respect to operations in a manufacturing process, according to an embodiment of the present disclosure. As discussed with respect to FIG. 2, a manufacturing process (e.g., manufacturing process 200 of FIG. 2) can include various manufacturing operations (e.g., manufacturing operations 202A-B of FIG. 2) and various metrology operations (e.g., metrology operations 204A-B of FIG. 2) associated with the various manufacturing operations. The manufacturing process can be used to generate a large number of samples. As a result, values ​​of a given parameter (e.g., parameters 206A-D, 208A-D of FIG. 2) at each of one or more locations on a set of samples are measured.

[0042] 3, parameters related to operation in a manufacturing process are measured at specified locations on a set of samples (e.g., Sample 1, Sample 2, Sample 3, and Sample 4). A rate of change tool (e.g., rate of change tool 135 in FIG. 1) can be used to process the raw metrology data to determine a current rate of change of the parameter value and a baseline or historical rate of change of the parameter value.

[0043] A current rate of change of a parameter value can be calculated using a current measurement of the current sample and a previous measurement of a sample produced immediately before the current sample. In some embodiments, sample 1 can be produced before sample 2, sample 2 can be produced before sample 3, sample 3 can be produced before sample 4, and sample 4 can be the current sample. The current sample rate of change can include calculating the difference between the current sample and the immediately previous sample (e.g., sample 4 and sample 3, respectively). This current rate of change of the parameter value can be calculated for each subsequent position on the sample. Additionally, the current rate of change of the parameter value can be calculated for all parameters.

[0044] A baseline rate of change of a parameter value can be calculated using historical metrology data (e.g., historical sample data 124). For example, a historical rate of change of a parameter value for a parameter at a particular location on the sample can be calculated using a previous sample (e.g., sample 1, sample 2, and / or sample 3). For example, the rate of change of a parameter value can be calculated using a moving average, a mean statistic, a long-term statistic, a short-term statistic, a derivative, an integral, and / or one of the known rate of change calculation methods.

[0045] The current rate of change of the parameter value is compared to a baseline rate of change of the parameter value. In one embodiment, this comparison is performed by applying a statistical distribution to the baseline rate of change of the parameter value to identify the variance between the current rate of change of the parameter value and the baseline rate of change of the parameter value. For example, a mean and standard deviation are calculated from the historical rates of change of the parameter value and compared to the current rate of change of the parameter value to identify how many standard deviations the current rate of change of the parameter value is from the mean of one or more historical rates of change of the parameter value.

[0046] In some embodiments, predetermined control or threshold limits (e.g., one standard deviation, two standard deviations, three standard deviations, etc.) are used to identify locations with abnormal current rates of change in parameter values. It should be noted that the control limits identified herein may differ from traditional SPC control limits. SPC controls identify threshold ranges for measurements, while the control limits identified herein identify threshold ranges for rates of change in parameter values ​​instead of evaluating static measurements of samples. This difference may identify violation locations that may not be flagged by traditional SPC analysis.

[0047] In some embodiments, a defined sampling window can be used to calculate the baseline rate of change in parameter values. For example, the baseline rate of change in parameter values ​​can be generated by n samples generated before the current sample. For example, the baseline rate of change in parameter values ​​can be limited to samples produced within a time period (e.g., the last 24 hours, a week, a month, etc.) or to a quantity of samples (e.g., the last 10, 100, 1000, etc. samples produced). It should also be noted that the baseline rate of change in parameter values ​​is calculated at each position or site on the sample. The current rate of change in parameter values ​​is compared in a position-by-position comparison across the surface of the sample.

[0048] In some embodiments, the location of violations on a sample can be indicated by a scoring system or by placing each location into a hierarchy or degree of violation rather than a binary indication of the violation measurement. For example, locations can be categorized into hierarchies such as "pass," "Level 1 violation," "Level 2 violation," and "Level 3 violation." These violation hierarchies can correspond to the variance of the current rate of change of the parameter value from the baseline rate of change of the parameter value at each location. For example, locations less than one standard deviation away can be classified as "pass," locations between one and two standard deviations away can be classified as "Level 1 violation," locations between two and three standard deviations away can be classified as "Level 2 violation," and so on. As described with respect to FIG. 4 , each violation can be assigned a weight or score that can be used to further establish the sample pattern.

[0049] In some embodiments, the rate of change of the parameter value is calculated for each sample transition. For example, with reference to Figure 3, the rates of change from sample 1 to sample 2, from sample 2 to sample 3, and from sample 3 to sample 4 can be calculated to form a historical rate of change of the parameter value data set.

[0050] In some embodiments, a first analysis of variance (ANOVA) is calculated for each process step, parameter, and location to identify variation within and across samples for specific process steps and parameters for comparing data between wafers. In some embodiments, a second ANOVA is calculated within and across locations for specific process steps and parameters for comparing locations within a wafer. In some embodiments, a third ANOVA is calculated within and across the entire dataset of historical rate of change in parameter values ​​(e.g., a combination of the first and second ANOVAs). The first, second, and / or third ANOVAs can then be used to generate a sample pattern for a given parameter and process step of the manufacturing process for the current sample and previous historical samples.

[0051] 4 illustrates an exemplary graphical user interface (GUI) 400 for a sample pattern 404, according to an aspect of the present disclosure. The GUI 400 identifies one or more locations 402 on the sample, one or more sample patterns 404, a score 406 associated with each pattern, a conclusion 408, a site conclusion 410, and an overall conclusion 412.

[0052] The one or more locations 402 can include a first subset of locations identified as violating and a second subset of locations identified as passing or matching. In some embodiments, the one or more locations 402 can include a score quantifying the degree to which each location is violating (e.g., passing, tier 1 violation, tier 2 violation, etc.).

[0053] The sample patterns 404 can include various combinations of violations that a sample may experience during a manufacturing process. These sample patterns 404 can be based on common violation groupings on the sample. For example, a malfunctioning tool may incorrectly process multiple locations on the sample that are close to each other. In some embodiments, the sample patterns 404 are associated with violation patterns of process functions 502, parameters 504, potential failure modes 506, and potential failure effects 508 of a failure mode and effects analysis (FMEA), as described in connection with FIG. 5 . For example, identifying the sample patterns 404 can include identifying wafer center or quadrature edge sites or dishing issues. In another example, the sample patterns 404 can identify behavior specific to a particular location, zone, or process tool, machine, or operation.

[0054] As previously described (e.g., in connection with ANOVA tool 136 of FIG. 1 ), in some embodiments, a first analysis of variance (ANOVA) is calculated for each process step, parameter, and location to identify variation within and across samples for specific process steps and parameters for comparing data between wafers. In some embodiments, a second ANOVA is calculated within and across locations for specific process steps and parameters for comparing locations within a wafer. In some embodiments, a third ANOVA is calculated (e.g., a combination of the first and second ANOVAs) within and across the entire dataset of historical rate of change of parameter values. The first, second, and third ANOVAs can then be used to generate a sample pattern for a given parameter and process step of the manufacturing process for the current sample and previous historical samples.

[0055] The conclusion 408 focuses on wafer-to-wafer variation in the current process. The conclusion 408 can include processing data associated with a first ANOVA. For example, the first ANOVA can identify variation within and across samples of a particular process step with specified parameters. The conclusion 408 can be provided based on processing logic that compares the current wafer with previous wafers and analyzes a single parameter to determine whether a pattern exists with a common parameter that is failing across different wafers.

[0056] The site conclusions 410 focus on the variation that exists within the sample set for the current process. The site conclusions 410 can be provided by processing data associated with a second ANOVA. For example, the second ANOVA can identify a particular site and determine how various parameters and samples perform at the particular site. The site conclusions 410 can be provided based on processing logic that compares data associated with the particular site from current and historical samples to determine whether there are patterns in the values ​​of various parameters and various samples at specific locations on each sample.

[0057] The overall conclusion is focused on identifying inherited variations from upstream processes that may affect the results of the current process. The overall conclusion 412 can be provided by the processed data associated with the third ANOVA. For example, the third ANOVA can identify patterns across the entire data set, including process dependence on multiple locations across various samples. For example, the overall conclusion 412 can be based on processing logic that compares historical metrology data (e.g., baseline rate of change of a parameter) with metrology data at various locations (e.g., current rate of change of a parameter) and various parameters to determine whether a pattern exists between historical or inherited violation measurements from upstream measurements or in the historical metrology data and current violation measurements in the current metrology data from the data associated with the third ANOVA.

[0058] FIG. 5 is a block diagram illustrating a process failure mode and effects analysis (FMEA) 500 according to an embodiment of the present disclosure. The process FMEA includes process functions 502, parameters 504, potential failure modes 506, and potential failure effects 508. The process FMEA can be performed using a process FMEA tool (e.g., failure mode and effects analysis tool 138 of FIG. 1). The process FMEA receives process functions 502 from one of a manufacturing system, a metrology system, and / or an SPC system. The process functions 502 can be organized into process dependencies. For example, the process functions 502 can be stored in a dependency table, where the dependencies identify the parameters and locations on a sample that a particular process function 502 affects. For example, the process functions 502 can define machine operations (e.g., lithography, etch, deposition, etc.).

[0059] The process FMEA receives data related to parameters 504. In some embodiments, the parameter data can be received as a sample pattern, as described with respect to FIG. 4. Alternatively, the parameter data can be received as a list of violation locations and the violating parameters over a predetermined threshold range. The parameter data can identify locations with violating measurements. Violating measurements can include data that does not meet a predetermined threshold, such as a rate of change in a parameter value of a measurement that exceeds an acceptable baseline rate of change in the parameter value for a given parameter at a particular location (as described with respect to FIG. 2).

[0060] The process FMEA 500 includes potential failure modes 506 and potential failure effects 508 for a manufacturing system (e.g., manufacturing system 100 of FIG. 1 ). For example, an FMEA table includes a list of known problems and root causes for a given machine, tool, and / or equipment and symptoms associated with each problem and root cause. The process FMEA 500 may include logic that links process functions 502 and / or parameters 504 to the potential failure modes 506 and / or potential failure effects 508. The process FMEA 500 may receive the processed metrology data and identify instances of anomalies in the manufacturing system. For example, the metrology data may be processed using other embodiments described herein and may be received by a process FMEA tool. The process FMEA tool may analyze the data and identify one or more defective machines, tools, and / or equipment, and further identify the impact of the defective tools on manufactured samples. For example, a process FMEA can identify deposition tools that are broken, malfunctioning, or otherwise in need of repair or replacement, and can further describe the effect of the deposition tool's current state (uneven layers, very thin or very thick layers, etc.) on the performance of its function across different locations on the sample.

[0061] In some embodiments, the process FMEA 500 can generate instructions for an equipment engineering system (e.g., the equipment engineering system 130 of FIG. 1 ) to modify either the operation of a machine or the implementation of a process associated with an instance of a manufacturing process anomaly identified by the process FMEA 500.

[0062] In some embodiments, the process FMEA 500 can generate instructions for an equipment engineering system (e.g., equipment engineering system 130 of FIG. 1 ) to provide a graphical user interface (GUI) that presents a visual indicator of the machine or process associated with the anomaly instance. For example, the visual indicator can be sent to a client device (e.g., client device 128 of FIG. 1 ) for a manufacturing process engineer or operator to manually modify a manufacturing execution system that executes the manufacturing process.

[0063] In some embodiments, machine learning (ML) algorithms that generate one or more trained machine learning models, deep ML algorithms, and / or other signal processing algorithms for analyzing parametric data can be used to determine potential failure modes 506 and potential failure effects 508 of a manufacturing system. These models, analyses, and / or algorithms can be used to calculate, predict, and evaluate combinations of process features 502 and parameters 504 to predict and identify potential failure modes 506 and potential failure effects 508. In some embodiments, training data for training the ML models can be obtained by a metrology system (e.g., metrology system 110 in FIG. 1 ) or historical sample data (e.g., historical sample data 124 in FIG. 1 ).

[0064] One type of machine learning model that can be used is an artificial neural network, such as a deep neural network. Artificial neural networks generally include a feature representation component with a classifier or recurrent layer that maps features to a desired output space. For example, a convolutional neural network (CNN) hosts multiple convolutional filter layers. Pooling is performed and nonlinearities can be addressed in lower layers, typically with a multilayer perceptron attached on top, which maps the top-layer features extracted by the convolutional layers to a decision (e.g., classification output). Deep learning is a type of machine learning algorithm that uses a cascade of multiple layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. Deep neural networks can be trained in a supervised (e.g., classification) and / or unsupervised (e.g., pattern analysis) manner. Deep neural networks include a hierarchy of layers, with different layers learning different levels of representations corresponding to different levels of abstraction. In deep learning, each level learns to transform its input data into slightly more abstract and complex representations. For example, in a process anomaly application, the raw inputs can be current and historical metrology data, a first representation layer can extract locations and parameter values, a second layer can construct and encode basic violation locations, a third layer can encode sample patterns, and a fourth layer can recognize and match the data against potential failure modes and effects in the manufacturing process. In particular, a deep learning process can independently learn which features are optimally placed at which levels. The "deep" in "deep learning" refers to the number of layers through which data is transformed. More precisely, a deep learning system has significant Credit Assignment Path (CAP) depth. A CAP is a chain of transformations from input to output. A CAP describes the potentially causal connections between inputs and outputs.For feedforward neural networks, the depth of the CAP can be the depth of the network, which can be the number of hidden layers plus 1. For recurrent neural networks, where a signal may propagate through a layer more than once, the depth of the CAP is potentially infinite.

[0065] In one embodiment, a neural network is trained using a training data set including a number of data points, each data point including a parameter 504, a location on the sample, and a process function 502. Each training data point may further include or be associated with a potential failure mode 506 and / or a potential failure effect 508. Using the training data set, the neural network can be trained to receive inputs of the process function, the location on the sample, and the parameter, and to output an identification of an instance of an anomaly in the manufacturing system. Alternatively or additionally, the neural network may include using sample patterns as inputs or outputs of the training data set, as described with respect to FIG.

[0066] 6 is a flow diagram of a method 600 for identifying instances of anomalies in a manufacturing process according to an embodiment of the present disclosure. For simplicity of explanation, method 600 is shown and described as a series of operations. However, operations according to this disclosure may be performed in various orders and / or concurrently with other operations not presented and described herein. Moreover, not all illustrated operations may be performed to implement method 600 according to the disclosed subject matter. Furthermore, those skilled in the art will understand and appreciate that method 600 may instead be represented as a series of interrelated states via a state diagram or as a series of events.

[0067] 6 , at block 601, processing logic receives current metrology data for operations on a current sample in a manufacturing process. This metrology data may include parameter values ​​at each of one or more locations on the current sample. This current metrology data may be received from a metrology system (e.g., metrology system 110 in FIG. 1 ), a manufacturing execution system (manufacturing system 102 in FIG. 1 ), or an SPC system (e.g., SPC system 116 in FIG. 1 ). This metrology data may be associated with a machine operation (e.g., machine operation 104 in FIG. 1 ) and / or a process implementation (e.g., process implementation 106 in FIG. 1 ) of the manufacturing process (e.g., manufacturing process 200 in FIG. 2 ).

[0068] At block 602, processing logic obtains a baseline rate of change of the parameter value for the parameter for each of the one or more locations. In some embodiments, the baseline rate of change of the parameter value is determined using one or more historical rates of change of the parameter value from historical metrology data of operation for one or more previous samples in the manufacturing process. Alternatively or additionally, the baseline rate of change may be obtained by any of the disclosed embodiments disclosed herein (e.g., by calculating the baseline rate of change of the parameter value as described with respect to FIGS. 1 and 3). In some embodiments, the baseline rate of change is calculated by an SPC system (e.g., SPC system 116 of FIG. 1) or a rate of change tool (e.g., rate of change tool 135 of FIG. 1).

[0069] At block 603, processing logic determines a current rate of change of the parameter value for each of the one or more locations. This current rate of change of the parameter value may be associated with the current sample. Determining the current rate of change of the parameter value associated with the current sample may include any or all of the disclosed statistical and data processing techniques disclosed herein (e.g., the statistical and data processing techniques disclosed in association with FIG. 3).

[0070] At block 604, processing logic compares the current rate of change of the parameter value for each of the one or more locations. In some embodiments, processing logic may further include identifying one or more violation locations, each having an associated current rate of change of the parameter value that is greater than an associated reference rate of change of the parameter value. Identifying the violation measurements may include any or all of the disclosed statistical and data processing techniques disclosed herein (e.g., the statistical and data processing techniques disclosed in connection with FIG. 3).

[0071] At block 605, processing logic identifies an instance of an anomaly in the manufacturing process based on a comparison of the current rate of change of the parameter value to a reference rate of change of the parameter value. In some embodiments, the process may further include retrieving one or more process dependencies of the manufacturing process and identifying an instance of an anomaly in the manufacturing process based on one or more of the process dependencies. An instance of an anomaly may include a defective machine, tool, or equipment, or an improperly performed process operation. Identifying an instance of an anomaly may include identifying a source of the anomaly (e.g., a machine, tool, equipment, process, etc.) or an effect of the anomaly (e.g., a damaged sample, potential damage to other machines, a parameter that is unlikely to meet specification requirements).

[0072] At block 606, processing logic optionally alters at least one of the machine operation or process implementation associated with the anomaly instance. Altering the machine operation or process implementation may include stopping the machine, stopping the process, or signaling the error and waiting for user input to stop or adjust the operating mode before resuming operation.

[0073] In some embodiments, the processing logic may provide a graphical user interface (GUI) that presents a visual indicator of a machine or process associated with an anomaly instance. For example, a measurement violation tool (e.g., measurement violation tool 132 in FIG. 1 ) may identify an anomaly instance (e.g., a faulty machine, tool, or process implementation) and arrange for a visual indicator of the anomaly instance to be presented on a client device (e.g., client device 128 in FIG. 1 ). A user (e.g., an engineer or manufacturing system operator) may use the indicator to prescribe remedial action to correct the anomaly.

[0074] In some embodiments, the processing logic may further identify one or more violation locations, each having an associated current rate of change of the parameter value that is greater than an associated reference rate of change of the parameter value. In a further embodiment, the processing logic may further include determining a sample pattern associated with the one or more violation locations and identifying an instance of the anomaly based on the sample pattern.

[0075] 7 shows a block diagram of an example computing device 700 capable of identifying instances of anomalies in a manufacturing process. In various illustrative examples, various components of computing device 700 may represent various components of manufacturing execution system 102, metrology system 110, SPC system 116, data store 122, client device 128, equipment engineering system 130, and network 140 shown in FIG.

[0076] The exemplary computing device 700 may be connected to other computer devices over a LAN, an intranet, an extranet, and / or the Internet. The computing device 700 may operate in the capacity of a server in a client-server network environment. The computing device 700 may be a personal computer (PC), a set-top box (STB), a server, a network router, switch, or bridge, or any device capable of executing (sequentially or otherwise) a set of instructions that specify operations to be performed by the device. Furthermore, while only a single exemplary computing device is shown, the term "computer" should also be taken to include a collection of computers that, separately or together, execute a set (or sets) of instructions to perform one or more of the methodologies discussed herein.

[0077] The exemplary computing device 700 may include a processing unit 702 (also referred to as a processor or CPU), a main memory 704 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM), e.g., synchronous DRAM (SDRAM)), etc.), a static memory 706 (e.g., flash memory, static random access memory (SRAM), etc.), and a secondary memory (e.g., a data storage device 718), which may communicate with each other via a bus 730.

[0078] Processing unit 702 represents one or more general-purpose processing devices, such as a microprocessor, a central processing unit, or the like. More specifically, processing unit 702 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing other instruction sets, or a processor implementing a combination of instruction sets. Processing unit 702 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, or the like. According to one or more aspects of the present disclosure, processing unit 702 may be configured to execute instructions to implement method 600 shown in FIG. 6.

[0079] The exemplary computing device 700 may further include a network interface device 708, which may be communicatively coupled to a network 720. The exemplary computing device 700 may further include a video display 710 (e.g., a liquid crystal display (LCD), touch screen, or cathode ray tube (CRT)), an alphanumeric input device 712 (e.g., a keyboard), a cursor control device 714 (e.g., a mouse), and an audio signal generating device 716 (e.g., a speaker).

[0080] The data storage device 718 may include a machine-readable storage medium (or more specifically, a non-transitory machine-readable storage medium) 728 having stored thereon one or more sets of executable instructions 722. According to one or more aspects of the present disclosure, the executable instructions 722 may include executable instructions related to performing the method 600 shown in FIG.

[0081] The executable instructions 722 may also reside, completely or at least partially, within the main memory 704 and / or processing unit 702, which also constitute computer-readable storage media during execution of the executable instructions 722 by the exemplary computing device 700, the main memory 704 and processing unit 702. The executable instructions 722 may also be transmitted or received across a network via the network interface device 708.

[0082] 7 illustrates computer-readable storage medium 728 as a single medium, the term "computer-readable storage medium" should be interpreted to include a single medium or multiple media (e.g., centralized or distributed databases and / or associated caches and servers) having stored thereon one or more sets of operating instructions. The term "computer-readable storage medium" is further interpreted to include any medium capable of storing or encoding a set of instructions for execution by a machine, the set of instructions causing the machine to perform one or more of the methodologies described herein. Accordingly, the term "computer-readable storage medium" is interpreted to include, but is not limited to, solid-state memory and optical and magnetic media.

[0083] Some portions of the above detailed descriptions are presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of steps leading to a desired result. These steps are steps requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or other such terms.

[0084] It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise, as will be apparent from the discussion that follows, throughout this description, discussions utilizing terms such as "identify," "determine," "store," "adjust," "cause," "return," "compare," "generate," "stop," "load," "copy," "inject," "exchange," "execute," or other similar terms will be understood to refer to operations and processes of a computer system or similar electronic computing device that manipulate data represented as physical (electronic) quantities in the computer system's registers and memory, and transform those data into other data similarly represented as physical quantities in the computer system's memory or registers, or other such information storage, transmission, or display device.

[0085] Examples of the present disclosure further relate to apparatus for performing the methods described herein. This apparatus may be specially constructed for the desired purposes or may be a general-purpose computer system selectively programmed by a computer program stored in the computer system. Such computer program may be stored on a computer-readable storage medium, such as any type of disk, including optical disks, compact disk read-only memories (CD-ROMs) and magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic disk storage media, optical storage media, flash memory devices, other types of machine-accessible storage media, or any type of media suitable for storing electronic instructions, each coupled to a computer system bus.

[0086] The methods and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems can be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these systems is set forth in the description below. Moreover, the scope of the present disclosure is not limited to any particular programming language. It will be understood that a variety of programming languages ​​can be used to implement the teachings of the present disclosure.

[0087] It should be understood that the above description is intended to be illustrative, and not limiting. Many other examples of embodiments will be apparent to those skilled in the art upon reading and understanding the above description. While the present disclosure describes particular examples, it is understood that the systems and methods of the present disclosure are not limited to the examples set forth herein, but can be practiced with modifications within the scope of the appended claims. Accordingly, the specification and drawings should be regarded as illustrative, and not limiting. The scope of the present disclosure should therefore be determined with reference to the appended claims and the full scope of equivalents to which such claims are entitled.

Claims

1. receiving, by at least one processing device, current metrology data of operations on a current sample in a plurality of manufacturing processes, the metrology data including current values ​​of parameters at each of one or more locations on the current sample; obtaining, by the at least one processing device, a reference rate of change of the parameter value of the parameter for each of the one or more locations; determining, by the at least one processing unit, a current rate of change of the parameter value for each of the one or more locations, the current rate of change of the parameter value relative to the current sample; comparing, by the at least one processing device, the current rate of change of the parameter value for each of the one or more locations to the reference rate of change of the parameter value for each of the one or more locations; retrieving, by the at least one processing device, one or more process dependencies of the plurality of manufacturing processes; and identifying, by the at least one processing device, from a plurality of root causes for a plurality of known anomaly instances in the plurality of manufacturing processes, a root cause for an anomaly instance among the plurality of known anomaly instances based on the comparison of the current rate of change of the parameter value with the reference rate of change of the parameter value and further based on the one or more process dependencies; Equipped with The anomaly instance includes at least one of a defective machine, tool, or equipment; method.

2. and modifying, by said at least one processing unit, at least one of a machine operation or process implementation associated with said anomaly instance. The method of claim 1 further comprising:

3. 2. The method of claim 1 , wherein the reference rate of change of the parameter value is determined using one or more historical rates of change of the parameter value from historical metrology data of the operation for one or more previous samples in the plurality of manufacturing processes.

4. 4. The method of claim 3, wherein the baseline rate of change in the parameter value is determined by performing an analysis of variance (ANOVA) using the one or more of the historical rate of change in the parameter value.

5. identifying, by said processing unit, one or more violation locations each having an associated current rate of change of said parameter value that is greater than an associated reference rate of change of said parameter value; The method of claim 1 further comprising:

6. determining, by the processing unit, a sample pattern associated with the one or more violation locations; and identifying, by the processing unit, instances of the anomaly based on the sample pattern. The method of claim 5 further comprising:

7. providing, by said processing unit, a graphical user interface (GUI) that presents a visual indicator of a machine or process associated with said anomaly instance; The method of claim 1 further comprising:

8. Memory and at least one processing unit communicatively coupled to the memory; wherein the at least one processing device comprises: receiving current metrology data of operations on a current sample in a plurality of manufacturing processes, the metrology data including current values ​​of parameters at each of one or more locations on the current sample; obtaining a reference rate of change of the parameter value of the parameter for each of the one or more locations; determining a current rate of change of the parameter value for each of the one or more locations, the current rate of change of the parameter value being associated with the current sample; comparing the current rate of change of the parameter value for each of the one or more locations to the reference rate of change of the parameter value for each of the one or more locations; retrieving one or more process dependencies of the plurality of manufacturing processes; and identifying, from a plurality of root causes for a plurality of known anomaly instances in the plurality of manufacturing processes, a root cause for an anomaly instance among the plurality of known anomaly instances based on the comparison between the current rate of change of the parameter value and the reference rate of change of the parameter value and further based on the one or more process dependencies; A system for performing The anomaly instance includes at least one of a defective machine, tool, or equipment; system.

9. The processing device further comprises: Altering at least one of the operation of the machine or the implementation of the process associated with said anomaly instance. The system of claim 8 .

10. 9. The system of claim 8, wherein the reference rate of change of the parameter value is determined using one or more previous rates of change of the parameter value from previous metrology data of the operation for one or more previous samples in the plurality of manufacturing processes.

11. 11. The system of claim 10, wherein the baseline rate of change in the parameter value is further determined by performing an analysis of variance (ANOVA) using the one or more prior rates of change in the parameter value.

12. The processing device further comprises: Identifying one or more violation locations each having an associated current rate of change of said parameter value that is greater than an associated reference rate of change of said parameter value. The system of claim 8 .

13. The processing device further comprises: determining a sample pattern associated with the one or more violation locations; Identifying the anomaly instance based on the sample pattern. The system of claim 12 for:

14. The processing device further comprises: providing an embodiment of a machine operation or process associated with said anomaly instance for presentation on a graphical user interface (GUI); The system of claim 8 .

15. A non-transitory machine-readable storage medium containing instructions that, when executed by at least one processing unit, cause the at least one processing unit to: receiving current metrology data of operations on a current sample in a plurality of manufacturing processes, the metrology data including current values ​​of parameters at each of one or more locations on the current sample; obtaining a reference rate of change of the parameter value of the parameter for each of the one or more locations; determining a current rate of change of the parameter value for each of the one or more locations, the current rate of change of the parameter value being associated with the current sample; comparing the current rate of change of the parameter value for each of the one or more locations to the reference rate of change of the parameter value for each of the one or more locations; retrieving one or more process dependencies of the plurality of manufacturing processes; and identifying, from a plurality of root causes for a plurality of known anomaly instances in the plurality of manufacturing processes, a root cause for an anomaly instance among the plurality of known anomaly instances based on the comparison between the current rate of change of the parameter value and the reference rate of change of the parameter value and further based on the one or more process dependencies; 1. A non-transitory machine-readable storage medium for causing The anomaly instance includes at least one of a defective machine, tool, or equipment; A non-transitory machine-readable storage medium.

16. The processing device further comprises: Identifying one or more violation locations each having an associated current rate of change of said parameter value that is greater than an associated reference rate of change of said parameter value.

16. The non-transitory machine-readable storage medium of claim 15,

17. The processing device further comprises: determining a sample pattern associated with the one or more violation locations; Identifying the anomaly instance based on the sample pattern.

17. The non-transitory machine-readable storage medium of claim 16,

Images