Using measurement violation analysis to handle anomaly identification

Abstract

The subject matter of this specification can be implemented in a method, system, and / or apparatus, etc., to receive current measurement data of operations performed on a current sample during a manufacturing process. This measurement data includes the current value of a parameter at each of one or more locations on the current sample. The method includes obtaining a reference rate of change of the parameter value at each of the one or more locations. The method further includes determining the current rate of change of the parameter value at 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 with the reference rate of change of the parameter value and identifying anomalies in the manufacturing process based on the comparison.

Description

Technical Field

[0001] Some specific 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, such as in semiconductor device manufacturing, product quality can be measured directly using metrology tools or indirectly by monitoring sensors in processing equipment. This information is collected at different stages of the product's manufacturing lifecycle. When a process engineer needs to identify problems with processing tools or the final product, he or she must go through the laborious and costly process of analyzing large amounts of data points (e.g., metrology data from many samples with various measurement parameters). For example, when an engineer is informed of a potential problem with a product, he or she must review the corresponding metrology data to identify warning characteristics of the product. A common method 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 helps ensure that processes operate with controlled variation, producing more products that meet specifications with less waste (e.g., rework or scrap). SPC can be applied to various processes where the output of qualified products (e.g., products that meet specifications) can be measured. SPC can include industry-standard methods for measuring and controlling quality in manufacturing processes. Quality data in the form of product and process measurements can be obtained on-the-fly during the manufacturing process. The data can then be plotted on a graph with calculated control limits. Two common constraints used to constrain the data include: first, control limits that can be determined by the capacity of the process; and second, specification limits that can be determined by the desired outcome (e.g., a measurement range that meets a specific specification). Summary of the Invention

[0004] A method and system for identifying anomalies (e.g., sources) in a manufacturing process. The method includes receiving current metrology data of operations performed on a current sample during the manufacturing process. The metrology data includes current values ​​of parameters at each of one or more locations in the current sample and samples from previous metrology processing steps. The method includes obtaining a reference rate of change of the parameter values ​​at each of the one or more locations. The method further includes determining the current rate of change of the parameter values ​​at 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 values ​​with the reference rate of change of the parameter values ​​and identifying anomalies in the manufacturing process based on the comparison. Attached Figure Description

[0005] The invention is illustrated by way of example and not limitation in the various figures of the accompanying drawings, in which the same reference numerals indicate similar elements. It should be noted that different references to "a" or "an" specific embodiments in this disclosure do not necessarily refer to the same specific embodiment, and such references imply at least one specific embodiment.

[0006] Figure 1 This is a block diagram illustrating a manufacturing system according to aspects of this disclosure.

[0007] Figure 2 This is a block diagram illustrating the manufacturing process of a manufacturing system according to aspects of this disclosure.

[0008] Figure 3 The illustration shows the distribution of the rate of change of parameter values ​​for various samples of operations in the manufacturing process according to aspects of this disclosure.

[0009] Figure 4 An exemplary graphical user interface of an example pattern according to aspects of this disclosure is illustrated.

[0010] Figure 5 This is a block diagram illustrating the failure mode and effects analysis (FMEA) performed on aspects of this disclosure.

[0011] Figure 6 This is a flowchart of a method for identifying abnormal conditions in manufacturing processes, based on aspects of this disclosure.

[0012] Figure 7 The illustration shows a block diagram of an example computing device capable of identifying abnormal conditions in the manufacturing process. Detailed Implementation

[0013] In manufacturing (e.g., microfabrication, wafer fabrication, substrate generation, etc.), various processing tools and procedures are used to produce desired results (e.g., samples that meet desired specifications or have desired characteristics). Manufacturing processes may include various manufacturing steps and metrology steps. Metrology steps can be used between manufacturing steps to obtain metrology data indicating the quality and success of previously performed manufacturing steps. Metrology data may consist of multiple measurement parameter point values ​​(e.g., thickness, roughness, depth, particle count, surface gradient, etc.) measured at different locations on the wafer including the sample. As the sample progresses through the manufacturing process, historical metrology data can be acquired and stored from many metrology steps to show how the sample has achieved the current parameter values. Manufacturing systems can flag measurements that violate standards. For example, in SPC, a measurement may be considered non-compliant if it exceeds control limits, violates predetermined rules, exceeds specification limits, or is deemed unacceptable. Non-compliant measurements may be caused by defective manufacturing machines or processes. For example, manufacturing machines may include damaged tools or worn instruments that do not meet performance standards. Identifying the source of non-compliant measurements can be costly and elusive. For example, manufacturing downtime, inadequately manufactured products, and / or the costs of identifying and remediating sources of manufacturing anomalies can be expensive and resource-intensive.

[0014] Traditionally, SPC violation analysis is performed manually. SPC charts identifying measurement violations can be presented to the user. The user's task is to identify any anomalies in the manufacturing process using their knowledge, including potentially defective machines, devices, procedures, etc. However, as manufacturing systems become increasingly complex and automated, and the ability to measure and acquire more data increases, the sheer volume of data makes it difficult for users to process solely based on their own knowledge. Furthermore, manufacturing systems can be designed to handle many different processes (e.g., various substrate formulations and various samples using different machines, devices, and / or procedures to achieve manufacturing results), requiring knowledge and memory beyond human cognitive capabilities. Moreover, identifying anomalies based solely on SPC results is insufficient to pinpoint upstream faults in machines and / or processes used or performed prior to the current or final operation of the manufacturing process. For example, the first machine might be the source of an anomaly, but the process may utilize 20 machines, and subsequent use of these machines could mask or dilute the source of the error, making it difficult to identify.

[0015] This disclosure addresses these and other drawbacks of the prior art by using measurement data from samples associated with the manufacturing process to identify anomalies in the manufacturing process (e.g., faulty machines, defective operations, worn tools, etc.). Initially, the processing apparatus may receive current measurement data of the operations performed on the current sample during the manufacturing process. The measurement data may include the current value of a parameter at each of one or more locations on the current sample. The processing apparatus may obtain a reference rate of change of the parameter value at 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 apparatus may further include comparing the current rate of change of the parameter value with the reference rate of change of the parameter value and identifying anomalies in the manufacturing process based on the comparison.

[0016] The aspects of this disclosure offer significant technical advantages, including reduced energy consumption (e.g., battery consumption), bandwidth, latency, and more. For example, by processing and analyzing metering data in the disclosed manner, data can be processed faster than conventional systems, and data storage and retrieval can be made more efficient. Furthermore, compared to conventional systems, suggested corrective actions for anomalies can be identified and applied more quickly. This reduces the cost of manufacturing defective or faulty samples before correction, prevents further damage from wear, breakage, or other defective equipment, and allows for the prediction of anomalies, defects, malfunctions, and / or errors that may occur in the near future, enabling proactive corrective action.

[0017] Figure 1 This is a block diagram illustrating a manufacturing system 100 according to aspects of this disclosure. (See diagram below.) Figure 1 As shown, manufacturing system 100 includes manufacturing execution system 102, metering system 110, statistical process control (SPC) system 116, data storage 122, client device 128, and equipment engineering system 130. Manufacturing execution system 102, metering system 110, SPC system 116, data storage 122, and / or equipment engineering system 130 can each be hosted on one or more computing devices, including server computers, desktop computers, laptop computers, tablet computers, notebook computers, personal digital assistants (PDAs), mobile communication devices, mobile phones, smartphones, handheld computers, or similar computing devices.

[0018] Manufacturing execution system 102, metering system 110, SPC system 116, data storage 122, equipment engineering system 130, and client device 128 can be coupled to each other via network 140 for identifying anomalies in manufacturing execution system 102. In some embodiments, network 140 is a public network providing each element of manufacturing system 100 with access to each other and other publicly available computing devices. In some embodiments, network 140 is a private network providing each element of manufacturing system 100 with access to each other and other publicly available computing devices. 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., LTE networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof. Alternatively or additionally, any element of manufacturing system 100 may be integrated together or otherwise coupled without using network 140.

[0019] Client device 128 may include computing devices such as personal computers (PCs), laptops, mobile phones, tablets, netbooks, network-connected televisions (“smart TVs”), network-connected media players (e.g., Blu-ray players), set-top boxes, over-the-top (OTT) streaming devices, operator boxes, and the like. Client device 128 may include browsers, applications, and / or violation measurement tools. In some embodiments, client device 128 may be able to access manufacturing execution system 102, metrology system 110, SPC system 116, data storage 122, and / or equipment engineering system 130 (e.g., via network 140 using a browser or application) and transmit (e.g., send and / or receive) indications of violation measurement, identified anomalies, and metrology data at various stages of violation analysis, as described herein.

[0020] Manufacturing execution system 102 may include machine operations 104, processing implementations 106, and processing dependencies 108 for various manufacturing processes. Manufacturing processes may include various steps or operations of one or more machine operations 104 performed using one or more different processing implementations 106. For example, various machines may include dedicated chambers such as etching chambers, deposition chambers (including chambers for atomic layer deposition, chemical vapor deposition, or plasma-enhanced versions thereof), annealing chambers, etc. In another example, the machine may be incorporated into a sample transport system (e.g., a selectively compliant assembly robotic arm (SCARA) robot, a transfer chamber, a front-opening standard compartment (FOUP), a side storage compartment (SSP), and / or the like) to transport samples between the machine and processing steps.

[0021] Processing implementation 106 may include various specifications for performing machine operation 104 in a manufacturing process. For example, processing implementation 106 may include processing specifications such as the duration of machine operation 104, machine tools used for operation, temperature, flow rate, pressure, etc. of the machine (e.g., chamber), deposition sequence, and the like. In another example, processing implementation may include instructions for transporting samples to further processing steps or for measurement by metrology system 110.

[0022] Processing dependencies 108, also known as manufacturing recipes or manufacturing processing instructions, include the sequencing of machine operations 104 and processing implementation schemes 106, which, when applied in a specified order, create manufactured samples (e.g., substrates or wafers with predetermined characteristics or meeting predetermined specifications). In some embodiments, the processing dependencies 108 of the manufacturing processes are stored in a data storage device, or alternatively or additionally, in a manner that generates a data table instructing the steps or operations of the manufacturing processes. For example, one or more of the metrology system 110, SPC system 116, and / or equipment engineering system 130 may request processing dependencies for a sample currently being measured or for which relevant metrology data is being processed. In another example, processing dependencies may be requested for a specified number of steps (e.g., the last 5, 10, 15, or n processing steps of the manufacturing process) before operating on the current sample in the manufacturing process.

[0023] In some embodiments, the manufacturing execution system 102 includes all instructions, machines, and processes for manufacturing samples (e.g., substrates or wafers). In other embodiments, the manufacturing execution system 102 controls and coordinates various machines, tools, and processes during sample manufacturing. In other embodiments, the manufacturing execution system 102, combined with the metrology system 110, may form a system designed to alternate between manufacturing and metrology processes throughout the manufacturing process.

[0024] The metrology system 110 includes a metrology tool 114 for measuring parameters at various locations on samples manufactured by the manufacturing execution system 102. Parameters may include various measurements indicating the quality of operations performed by the manufacturing process of the manufacturing execution system 102. For example, parameters may include sample thickness, etching rate, resistivity, particle count, etc. In some embodiments, the metrology tool coordinates measurements to be performed at specific predetermined locations on each sample. For example, each sample is brought to the metrology system 110 after a specific manufacturing operation (e.g., deposition or etching operation). The metrology tool 114 measures one or more parameters at the same location for each sample. The metrology system 110 can transmit data to the SPC system 116 to create a historical record of measurements associated with specific operations of the manufacturing process. Historical sample data 124 may be used by the metrology system 110 and / or the SPC system 116 to create a record of parameter measurements for a series of samples that have been processed following the same operations of the manufacturing process.

[0025] In some embodiments, samples manufactured using manufacturing execution system 102 are measured by metrology system 110 after each step of the manufacturing recipe. In some embodiments, processing dependence 108 or manufacturing recipe may include a measurement step such that each sample is manufactured using the same processing dependence 108 and each sample is measured under the same conditions after the same operation.

[0026] like Figure 1 As shown, the Statistical Process Control (SPC) system 116 may include a statistical process tool 118 and an SPC data storage such as an SPC database 120. The SPC system 116 receives measurement data from the metrology system 110 and / or the equipment engineering system 130. The SPC system may receive contextual data (e.g., channel ID, equipment ID, product, process name, process step number, batch ID, etc.) from the manufacturing execution system 102, the metrology system 110, the data storage 122, and / or the equipment engineering system 130. The SPC system 116 applies the measurement data to appropriate charts (e.g., thickness, etch rate, resistivity, particle count, etc.), analyzes the measurement data to detect violations (e.g., product characteristics above or below predetermined thresholds), generates information about products with detected violations (e.g., batch ID, wafer ID, recipe name), and provides this information to the equipment engineering system 130. Furthermore, the SPC system 116 presents SPC charts to SPC clients, such as client device 128. For example, SPC charts can be displayed in client applications and / or web-based browser applications hosted by client devices 128 (e.g., personal computers, laptops, mobile phones, etc.).

[0027] SPC database 120 includes historical metrology data. For example, historical metrology data may include past SPC charts (e.g., thickness, etching rate, resistivity, particle count, etc.) and measurement violation data. SPC database 120 can calculate a reference rate 121 for parameter variation of historical sample data 124. For example, an analysis of variance (ANOVA) can be calculated for one or more historical rates of variation of samples manufactured by manufacturing execution system 102 and measured by metrology system 110. In some embodiments, SPC system 116 stores the reference rate of variation 121 of parameter values ​​and historical sample data, while in other embodiments, SPC system 116 stores the rate of variation of parameter values ​​and historical sample data in data storage 122.

[0028] Data storage 122 may be a memory (e.g., random access memory), a drive (e.g., hard disk drive, flash drive), a database system, or another type of component or device capable of storing data. Data storage 122 may store one or more of historical sample data 124 and failure mode and effects analysis (FMEA) data 126. Historical sample data 124 may include data from various manufacturing processes (e.g., Figure 2 The parameter values ​​of various parameters measured on samples manufactured during manufacturing process 200. Historical sample data 124 may include reference rates of change of parameter values ​​for each parameter at each location on one or more previous samples previously manufactured in the manufacturing process. FMEA data 126 may store data associated with the Failure Mode and Effects Analysis tool 138, and more generally with processing Failure Mode and Effects Analysis (see, for example...) Figure 5 The data is related to the failure mode and impact analysis (FEM) of 500.

[0029] Equipment engineering system 130 may include measurement violation tool 132. Measurement violation tool includes process dependency tool 134, rate of change tool 135, pattern mapping tool 137, and failure mode and effects analysis (FMEA) tool 138. Equipment engineering system 130 receives measurement data from metrology system 110 and / or manufacturing execution system 102 and transmits the measurement data to SPC system 116. Equipment engineering system 130 receives SPC data associated with machines, tools, and / or processing operations (which are associated with the measurement data).

[0030] The processing dependency tool 134 requests processing dependency 108 data from the manufacturing execution system 102 and / or data storage 122, which is associated with metrological data acquired by the metrology tool 114. The processing dependency tool 134 matches the previous machine operation 104 and processing implementation scheme 106 with the measurements of the current sample.

[0031] The rate of change tool 135 calculates the current rate of change for the current sample measured by the measurement system 110. The current rate of change may include determining the rate of change of the current parameter value. For example, a parameter is measured by the measurement system 110 and a set of parameter values ​​are obtained at different locations in the sample. These parameter values ​​are compared with 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 with a sample immediately preceding the current sample. The difference between the current parameter value and the parameter value obtained from a sample immediately preceding the current sample can be used to generate the rate of change of the parameter value. In other embodiments, multiple historical measurements are used in conjunction with various parameter value rate of change calculation techniques. For example, the rate of change can be calculated using one of the following: moving average, average statistic, long-term statistic, short-term statistic, derivative, integral, and / or known rate of change calculation methods.

[0032] The rate of change tool 135 compares a reference rate of change (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 with 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 measurement data of operations performed on one or more previous samples during the manufacturing process.

[0033] In some specific implementations, based on a comparison of the current rate of change of the parameter value and a reference rate of change of the parameter value, the rate of change tool 135 identifies one or more violation locations, each violation location having a relevant current rate of change of the parameter value that is greater than the relevant reference rate of change of the parameter value.

[0034] The Analysis of Difference (ANOVA) tool 136 works in conjunction with the rate of change tool 135 to identify one or more violation locations. The ANOVA tool 136 performs ANOVA using one or more historical rates of change for the parameter values ​​to determine a reference rate of change for the parameter values. In a further embodiment, the ANOVA results can be used to determine a threshold range of acceptable or non-violation rates of change for the parameter values ​​at each of one or more locations during the manufacturing process on the current sample. In some embodiments, the reference rate of change for the parameter values ​​may be a series of non-violation values ​​statistically calculated by the analysis of difference tool 136 from one or more historical rates of change for the parameter values.

[0035] Pattern mapping tool 137 receives one or more violation locations from one of rate of change tool 135 and / or ANOVA tool 136, and generates sample patterns associated with one or more violation locations on the current sample. In some specific embodiments, 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.

[0036] Failure Mode and Effects Analysis (FMEA) tool 138 identifies manufacturing process anomalies based on a comparison of the current rate of change of parameter values ​​with a reference rate of change of parameter values. In some implementations, FMEA tool 138 receives sample patterns from pattern mapping tool 137 and identifies anomalies based on the sample patterns.

[0037] FMEA tool 138 can retrieve FMEA data 126 from data storage 122. FMEA data 126 may include a list of known problems and root causes for a given device, with known symptoms associated with each problem. Pattern sample data received by FMEA tool 138 is applied to the list of known problems and generates a report identifying common causes of violations. For example, FMEA tool 138 may receive sample patterns and identify defective tooling, machine, or manufacturing process operations.

[0038] In some embodiments, FMEA tool 138 may be used in conjunction with process dependency tool 134 to identify upstream tools, machines, or processes operating based on the current machine operation performed on the current sample (e.g., operation steps that occurred prior to the current manufacturing step of the same manufacturing process). For example, the current sample may have recently experienced its first operation on a first machine. In some embodiments, the combination of process dependency tool 134 and FMEA tool 138 can look for past operations of the sample, such as a second operation on a second machine or tool. FMEA tool 138 can use sample patterns to identify a second machine or tool as the source of an anomaly.

[0039] Once an anomaly is identified, the FMEA tool 138 can be performed by executing at least one of the implementations of changing machine operation or the processing associated with the anomaly, and / or by providing a graphical user interface (GUI) that presents visual indicators of the machine or processing associated with the anomaly. The GUI can be transmitted via network 140 and displayed on client device 128. In some specific embodiments, the implementation of changing machine operation or processing may include sending instructions to manufacturing execution system 102 to change machine operation 104 and / or processing implementation 106 associated with processing recipe or processing dependency 108.

[0040] It should be noted that although manufacturing system 100 is depicted and described as a plurality of different systems and / or devices, various devices can be combined together to perform the functions described above. Figure 1 The functions are described as separate entities. For example, Manufacturing Execution System 102 can be combined with Metrology System 110 to perform manufacturing processes through manufacturing and metrology operations. In another example, Equipment Engineering System 130 can be combined with SPC System 116 to analyze data from SPC analysis and rate of change analysis using Statistical Processing Tool 118 with Rate of Change Tool 135. In another example, Data Storage 122 can store data on one or more of Manufacturing Execution System 102, Metrology System 110, SPC System 116, Equipment Engineering System 130, and / or Client Device 128. Furthermore, although in Figure 1 The diagram depicts communication between the systems using network 140, but any of the manufacturing execution system 102, metering system 110, SPC system 116, data storage 122, client device 128, and / or equipment engineering system 130 can be directly coupled and communicate between each system without the need for network 140.

[0041] Figure 2 This illustrates a manufacturing system (e.g., based on aspects of this disclosure) Figure 1 A block diagram of manufacturing process 200 of manufacturing system 100. Manufacturing process 200 may include one or more manufacturing operations 202A-202B and one or more metering operations 204A-204B. Manufacturing operations 202A-202B may be performed by a manufacturing execution system (e.g., Figure 1 The manufacturing execution system 102) performs the metrology operations 204A-204B. The metrology operations 204A-204B can be performed by a metrology system (e.g., manufacturing execution system 102). Figure 1 The metering system 110) is executed.

[0042] In some specific embodiments, manufacturing process 200 may include a series of manufacturing operations 202A-202B and metrology operations 204A-204B, upon completion of which a manufacturing sample with predetermined characteristics and / or specifications is produced. For example, the manufacturing process for manufacturing a multilayer substrate may include various layer deposition operations, each layer deposition operation depositing a layer onto the substrate. Manufacturing operations 202A-202B may be designed to be completed in a predetermined sequence to produce a multilayer substrate with the correct layer order.

[0043] Manufacturing operations 202A-202B may include various methods for manufacturing samples. For example, manufacturing operations may 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 forms thereof), patterning (e.g., photolithography, masks, etc.), microforming, and / or similar methods.

[0044] Metrological operations 204A-204B may include various methods and techniques for measuring a set of parameters 206A-206D, 208A-206D at one or more locations on a manufactured sample at various stages of manufacturing process 200. This set of parameters 206A-206D, 208A-208D may include various measurements associated with manufacturing operations 202A-202B. For example, the parameter set 206A-206D, 208A-208D may include measuring channel thickness, layer or region thickness, etch rate, resistivity, particle count, etc., of the sample. The measured values ​​of the parameters can indicate the quality level of the performed manufacturing operation. In some specific embodiments, manufacturing process 200 measures 25-50 parameters at 12-20 locations per sample.

[0045] In some specific embodiments, parameters measured during metering operations 204A-204B indicate the quality of previous manufacturing operations. Alternatively, parameters measured during metering operations 204A-204B may indicate the quality of one or more previous manufacturing operations. For example, manufacturing operations 202A and 202B may both be layer deposition operations and parameters (e.g., 208A) may measure the thickness of the substrate. The thickness of the substrate during metering operation 204B may be affected by manufacturing operations 202A and 202B. The relationship between parameters and operations can be stored as a manufacturing process recipe or process dependency (e.g., Figure 1This is part of the processing dependency (108). Processing dependencies can track and manage the impact of manufacturing operations 202A-202B and downstream processes (e.g., machine operations and processing implementations that will be performed in the future with the same manufacturing process as the current machine operation or processing implementation), or processes that will occur after a specified manufacturing operation. Additionally, when processing or analyzing parameter values, processing dependency data can provide a link between previous operations and current manufacturing quality of a manufacturing sample at a specific stage of manufacturing process 200.

[0046] In some embodiments, manufacturing operations 202A-202B and metering operations 204A-204B alternate throughout the manufacturing process. It should be noted that in some embodiments, multiple manufacturing operations 202A-202B may be performed between metering operations 204A-204B. Similarly, various metering operations may be performed between manufacturing operations 202A-202B. The sequence and pace of manufacturing operations 202A-202B and metering operations 204A-204B may depend on the specific manufacturing process 200.

[0047] Figure 3 The figure illustrates the parameter variation rate distribution 300 for various samples of operations in the manufacturing process according to aspects of this disclosure. For example... Figure 2 As shown, manufacturing processes (e.g., Figure 2 The manufacturing process 200) may include various manufacturing operations (e.g., Figure 2 Manufacturing operations 202A-202B) and various metering operations associated with various manufacturing operations (e.g., Figure 2 The metrological operations 204A-204B). Multiple samples can be generated using manufacturing processes. As a result, a given parameter is measured at each of one or more locations within a set of samples (e.g., Figure 2 The values ​​of parameters 206A-206D and 208A-208D.

[0048] Reference Figure 3 The parameter is measured at a specified location on a set of samples (e.g., sample 1, sample 2, sample 3, and sample 4) during the manufacturing process. The rate of change tool (e.g., Figure 1 The rate of change tool (135) can be used to process raw measurement data to determine the current rate of change of parameter values ​​and the reference or historical rate of change of parameter values.

[0049] The current rate of change of a parameter value can be calculated using the current measurement of the current sample and the previous measurement of a sample manufactured immediately preceding the current sample. In some specific embodiments, sample 1 may be manufactured before sample 2, sample 2 may be manufactured before sample 3, sample 3 may be manufactured before sample 4, and sample 4 may be the current sample. The current rate of change of a sample may include calculating the difference between the current sample and the immediately preceding sample (e.g., sample 4 and sample 3, respectively). The current rate of change of a parameter value can be calculated for each subsequent position on the sample. Furthermore, the current rate of change of a parameter value can be calculated for all parameters.

[0050] Historical measurement data (e.g., historical sample data 124) can be used to calculate the reference rate of change for parameter values. For example, previous samples (e.g., Sample 1, Sample 2, and / or Sample 3) can be used to calculate the historical rate of change for parameter values ​​at specific locations on the sample. For example, the rate of change for parameter values ​​can be calculated using one of the following methods: moving average, average statistic, long-term statistic, short-term statistic, derivative, integral, and / or known rate of change calculation methods.

[0051] The current rate of change of a parameter value is compared to a reference rate of change of that parameter value. In one specific implementation, the comparison is performed by applying a statistical distribution to the reference rate of change of the parameter value to identify the difference between the current rate of change and the reference rate of change. For example, the mean and standard deviation are calculated based on 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 exist between the current rate of change of the parameter value and the mean of one or more historical rates of change of the parameter value.

[0052] In some specific implementations, predetermined control limits or threshold limits (e.g., one standard deviation, two standard deviations, three standard deviations, etc.) are used to identify locations with anomalous current rates of change for parameter values. It should be noted that the control limits identified here may differ from conventional SPC control limits. SPC controls identify threshold ranges for measured values, while the control limits identified herein identify threshold ranges for rates of change of parameter values, rather than assessments of static measurements of the sample. This difference can identify locations of violations that might otherwise not be flagged in known SPC analyses.

[0053] In some implementations, a defined sampling window can be used to calculate a reference rate of change for the parameter values. For example, the reference rate of change for the parameter values ​​can be generated from n samples generated before the current sample. Alternatively, the reference rate of change for the parameter values ​​can be limited to samples manufactured within a certain time frame (e.g., the previous 24 hours, week, month, etc.) or a certain number of samples (e.g., the previous 10, 100, 1000 samples). It should also be noted that the reference rate of change for the parameter values ​​is calculated at each location or site on the sample. The current rate of change for the parameter values ​​is compared location-by-location across the entire sample surface.

[0054] In some implementations, the location of a violation on a sample can be indicated by a scoring system or by assigning each location to a violation level or degree, rather than by a binary indicator of violation measurement. For example, a location can be categorized into levels such as "compliant," "Level 1 violation," "Level 2 violation," and "Level 3 violation." The violation level can correspond to the variance of the current rate of change of the parameter value at each location compared to a reference rate of change. For instance, a location less than one standard deviation might be labeled "compliant," a location between one and two standard deviations might be labeled "Level 1 violation," a location between two and three standard deviations might be labeled "Level 2 violation," and so on. A weight or score can be assigned to each violation, and this weight or score can be used to further develop sample patterns, such as a reference... Figure 4 As stated above.

[0055] In some specific implementations, the rate of change of parameter values ​​is calculated for each sample transition. For example, refer to Figure 3 As shown, the rate of change from sample 1 to sample 2, sample 2 to sample 3, and sample 3 to sample 4 can be calculated to form the historical rate of change of the parameter value dataset.

[0056] In some embodiments, a first ANOVA is calculated for each processing step, parameter, and location to identify intra-sample and inter-sample variations within a specific processing step and parameter to compare wafer-to-wafer data. In some embodiments, a second ANOVA is calculated within and between locations of a specific processing step and parameter to compare locations within a wafer. In some embodiments, a third ANOVA (e.g., a combination of the first and second ANOVAs) is calculated over and between the entire historical rate of change of the parameter value dataset. The first, second, and / or third ANOVAs can then be used to generate a sample pattern for the current sample, as well as a sample pattern for previous historical samples of the manufacturing process for the given parameters and processing steps.

[0057] Figure 4An exemplary graphical user interface (GUI) 400 for sample pattern 404 is illustrated according to aspects of this 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 point conclusion 410, and an overall conclusion 412.

[0058] One or more locations 402 may include a first subset of locations identified as non-compliant and a second subset of locations identified as compliant or conforming. In some implementations, one or more locations 402 may include a score that quantifies the degree of non-compliance at each location (e.g., compliant, Level 1 non-compliance, Level 2 non-compliance, etc.).

[0059] Sample pattern 404 may include various combinations of violations that a sample may experience during manufacturing processes. These sample patterns 404 may be based on common violation groupings on the sample. For example, a malfunctioning tool may incorrectly process locations on the sample that are close to each other. In some implementations, sample pattern 404 is combined with processing function 502, parameter 504, potential failure mode 506, and other parameters. Figure 5 The described failure modes and impact analysis (FMEA) are associated with potential failure effects 508. For example, identifying sample mode 404 may include identifying edge sites or dents at the center of a wafer or orthogonal structure. In another example, sample mode 404 may identify specific locations, areas, or behaviors specific to a processing tool, machine, or operation.

[0060] As mentioned above (e.g. with) Figure 1 (Associated with ANOVA tool 136), in some embodiments, a first difference analysis (ANOVA) is calculated for each processing step, parameter, and location to identify intra-sample and inter-sample variations in a particular processing step and parameter to compare wafer-to-wafer data. In some embodiments, a second ANOVA is calculated intra- and inter-location for a particular processing step and parameter to compare intra-wafer locations. In some embodiments, a third ANOVA (e.g., a combination of the first and second ANOVAs) is calculated over and between the entire historical rate of change of the parameter value dataset. The first, second, and third ANOVAs can then be used to generate a sample pattern for the current sample, as well as a sample pattern for previous historical samples of the manufacturing process for the given parameters and processing steps.

[0061] Conclusion 408 concerns differences between wafers currently being processed. Conclusion 408 may include processing data related to the first ANOVA. For example, the first ANOVA may identify variations within and between samples in a specific processing step with specified parameters. Conclusions may be provided based on comparing the current wafer with previous wafers and analyzing processing logic for individual parameters to determine whether patterns of failures with common parameters exist between different wafers.

[0062] Point conclusion 410 focuses on changes present in the currently processed sample set. Point conclusion 410 can be provided by processing data associated with the second ANOVA. For example, the second ANOVA can identify specific points and determine how various parameters and samples perform at those specific points. Point conclusion 410 can be provided based on processing logic that compares data associated with specific points from current samples and historical samples to determine whether there are patterns in which the values ​​of various parameters and various samples fail at specific locations in each sample.

[0063] The overall conclusion focuses on identifying inherited variations from upstream processing that may influence the outcome of the current processing. Overall conclusion 412 can be provided by processing data associated with the third ANOVA. For example, the third ANOVA can identify patterns across the entire dataset, including processing dependencies at multiple locations across different samples. For instance, overall conclusion 412 can be based on processing logic that compares historical or inherited non-compliant measurements from upstream or historical measurements with current non-compliant measurements from current measurements of quantities associated with the third ANOVA, to determine whether a pattern exists between historical or inherited non-compliant measurements from upstream or historical measurements and current non-compliant measurements from current measurements of quantities associated with the third ANOVA.

[0064] Figure 5 This is a block diagram illustrating a Processing Failure Mode and Effects Analysis (FMEA) 500 based on aspects of this disclosure. The Processing FMEA includes processing functions 502, parameters 504, potential failure modes 506, and potential failure effects 508. Processing FMEA tools (e.g., [tool name missing]) can be used. Figure 1 The Failure Mode and Effects Analysis (FMEA) tool 138 is used to perform a process FMEA. The process FMEA receives processing functions 502 from one of the manufacturing system, metrology system, and / or SPC system. Process functions 502 can be organized into processing dependencies. For example, processing functions 502 can be stored in a dependency table, where dependencies identify parameters and locations on a sample that are affected by a specific processing function 502. For example, processing function 502 can define machine operations (e.g., photolithography, etching, deposition, etc.).

[0065] The FMEA receives data associated with parameter 504. In some implementations, the parameter data may be received as a sample pattern, such as a reference. Figure 4 As described. Alternatively, the parameter data can be received as a list of violation locations and parameters that violate a predetermined threshold range. The parameter data can identify locations with violation measurements. Violation measurements may include data that fails to meet a predetermined threshold, such as a rate of change of a measured parameter value for a given parameter at a specific location exceeding an acceptable reference rate of change of the parameter value (e.g., a reference). Figure 2 The above).

[0066] Processing FMEA500 includes manufacturing systems (e.g., Figure 1 The FMEA (Factorization Management Expert) tool includes potential failure modes 506 and potential failure effects 508 for the manufacturing system 100. For example, the FMEA table includes a list of known problems and root causes for a given machine, tool, and / or equipment, along with symptoms associated with each problem and root cause. The processing FMEA 500 may include logic linking processing functions 502 and / or parameters 504 to potential failure modes 506 and / or potential failure effects 508. The processing FMEA 500 may receive processed metrology data and identify anomalies in the manufacturing system. For example, metrology data may be processed using other specific implementations described herein and received by the processing FMEA tool. The processing FMEA tool may analyze the data and identify one or more defective machine, tool, and / or equipment parts, and the impact of defective tools on the manufactured sample. For example, the processing FMEA may identify deposition tools as damaged, faulty, or requiring repair or replacement, and describe the impact of the current state of the deposition tool on performing its function at different locations on the sample (uniform layers, layers that are too thin or too thick, etc.).

[0067] In some specific implementations, processing FMEA 500 can be performed by equipment engineering systems (e.g., Figure 1 The equipment engineering system 130) generates instructions to modify one of the processing implementation schemes or machine operations associated with the anomalies identified by FMEA 500 in the manufacturing process.

[0068] In some specific implementations, processing FMEA 500 can be performed by equipment engineering systems (e.g., Figure 1 The equipment engineering system 130 generates instructions to provide a graphical user interface (GUI) to present visual indicators of the processing or machine associated with the abnormal situation. For example, the visual indicators can be sent to a client device (e.g., Figure 1 The client device 128 allows engineers or operators of the manufacturing process to manually change the manufacturing execution system that performs the manufacturing process.

[0069] In some embodiments, machine learning (ML) algorithms, deep ML algorithms, and / or other signal processing algorithms for analyzing parameter data that generate one or more trained machine learning models 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 compute, predict, and evaluate combinations of processing functions 502 and parameters 504 to predict and identify potential failure modes 506 and potential failure effects 508. In some embodiments, this can be achieved through a metrology system (e.g., Figure 1 The measurement system 110) or historical sample data (e.g., Figure 1 Historical sample data (124) are used to obtain training data for training ML models.

[0070] One type of machine learning model that can be used is an artificial neural network, such as a deep neural network. Artificial neural networks typically include feature representation components with classifiers or regression layers that map features to a desired output space. For example, a convolutional neural network (CNN) has multiple layers of convolutional filters. Pooling is performed at lower layers, and nonlinear problems can be solved at lower layers, typically topped by a multilayer perceptron that maps the top-level features extracted by the convolutional layers to a decision (e.g., classification output). Deep learning is a class of machine learning algorithms that uses cascaded, multi-layered nonlinear processing units for feature extraction and transformation. Each successive layer uses the output of the previous layer as input. Deep neural networks can learn in a supervised (e.g., classification) and / or unsupervised (e.g., pattern analysis) manner. Deep neural networks consist of a hierarchical structure, where different layers learn different levels of representation corresponding to different levels of abstraction. In deep learning, each level learns to transform its input data into a slightly more abstract and complex representation. For example, in anomaly processing applications, the raw input might be current and historical measurement data; the first representation layer can extract location and parameter values; the second layer can combine and encode basic violation locations; the third layer can encode sample patterns; and the fourth layer can identify the data and match it with potential failure patterns and potential failure effects in the manufacturing process. It's worth noting that deep learning processes can learn on their own which features are best placed at which level. The "depth" in "deep learning" refers to the number of layers through which the data is transformed. More precisely, deep learning systems have a considerable credit allocation path (CAP) depth. CAP is a chain of transformations from input to output. CAP describes the underlying causal relationship between the input and output. For a feedforward neural network, the CAP depth could be the network depth or the number of hidden layers plus one. For a recurrent neural network where one signal may propagate through a layer more than once, the CAP depth could be infinite.

[0071] In one embodiment, a training dataset comprising multiple data points is used to train the neural network, where each data point includes parameters 504, a location on a sample, and a processing function 502. Each training data point may additionally include or be associated with a potential failure mode 506 and / or a potential failure effect 508. The neural network can be trained using the training dataset to receive inputs of the processing function, the location on a sample, and the parameters, and to output an identifier of an anomaly in the manufacturing system. Alternatively or additionally, the neural network may incorporate sample patterns as input or output to the training dataset, as described in Reference Figure 4 As described.

[0072] Figure 6 This is a flowchart of a method 600 for identifying anomalies in a manufacturing process according to aspects of this disclosure. For simplicity, method 600 is depicted and described as a series of actions. However, actions according to this disclosure may occur in various sequences and / or simultaneously with other actions not presented and described herein. Furthermore, according to the disclosed subject matter, it is not necessary to perform all the actions shown to implement method 600. Additionally, those skilled in the art will understand and recognize that method 600 may alternatively be represented as a series of interrelated states via a state diagram or events.

[0073] refer to Figure 6 In block 601, the processing logic receives current measurement data from operations performed on the current sample during the manufacturing process. The measurement data may include parameter values ​​at each of one or more locations on the current sample. The current measurement data can be obtained from a measurement system (e.g., Figure 1 Measurement system 110), Manufacturing execution system ( Figure 1 Manufacturing system 102) or SPC system (e.g., Figure 1 The SPC system 116) receives the measurement data. The measurement data can be compared with manufacturing processes (e.g., Figure 2 Manufacturing processes 200) machine operations (e.g., Figure 1 Machine operation 104) and / or processing implementation scheme (e.g., Figure 1 This is associated with the processing implementation method 106.

[0074] In block 602, the processing logic obtains a reference rate of change for the parameter value at each of one or more locations. In some embodiments, the reference rate of change for the parameter value is determined using one or more historical rates of change for the parameter value from historical measurement data of operations performed on one or more previous samples during the manufacturing process. Alternatively or additionally, the reference rate of change can be obtained through any of the disclosed embodiments herein (e.g., reference...). Figure 1 and Figure 3The reference rate of change of parameter values ​​is calculated as described. In some specific embodiments, the reference rate of change is determined by an SPC system (e.g., Figure 1 SPC system 116) or rate of change tool (e.g., Figure 1 The rate of change tool (135) is used for calculation.

[0075] In block 603, the processing logic determines the current rate of change of the parameter value at each of one or more locations. The 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 publicly disclosed statistical and data processing techniques (e.g., combined with...) Figure 3 (Open statistical and data processing techniques).

[0076] In block 604, the processing logic compares the current rate of change of the parameter value at each of one or more locations. In some specific implementations, the processing logic may further identify one or more violation locations, each of which has a relevant current rate of change of the parameter value greater than a relevant reference rate of change for that parameter value. Identifying violation measurements may include any or all of the statistical and data processing techniques disclosed herein (e.g., referencing...). Figure 3 (Open statistical and data processing techniques).

[0077] In block 605, the processing logic identifies manufacturing process anomalies based on a comparison of the current rate of change of the parameter value and a reference rate of change of the parameter value. In some embodiments, the processing may further retrieve one or more processing dependencies of the manufacturing process and identify manufacturing process anomalies based on one or more processing dependencies. Anomalies may include defective machines, tools, or equipment, or improper processing operations. Identifying anomalies may include identifying the source of the anomaly (e.g., machine, tool, equipment, process, etc.) or the impact of the anomaly (e.g., damaged samples, potential damage to other machines, parameters that may not meet specification requirements).

[0078] In block 606, optionally, at least one of the implementation schemes for changing the operation or processing of the machine associated with an abnormal situation is described. The implementation scheme for changing the operation or processing of the machine may involve shutting down the machine, pausing processing, or indicating an error and waiting for user input to stop or adjust the operating mode before resuming operation.

[0079] In some implementations, the processing logic may provide a graphical user interface (GUI) that presents visual indicators of the machine or process associated with the anomaly. For example, a measurement tool for violations (e.g., Figure 1The measurement violation tool 132) can identify anomalies (e.g., defective machines, tools, processing implementations) and prepare them for use on client devices (e.g., Figure 1 A visual indicator of the abnormal situation is displayed on the client device 128. Users (e.g., engineers or manufacturing system operators) can use the indicator to guide remedial actions to correct the abnormality.

[0080] In some implementations, the processing logic may further identify one or more violation locations, where the current rate of change of a parameter value at each violation location is greater than the relevant reference rate of change of that parameter value. In another implementation, the processing logic may further determine sample patterns associated with one or more violation locations and identify anomalies based on these sample patterns.

[0081] Figure 7 A block diagram of an example computing device 700 capable of identifying anomalies in the manufacturing process is illustrated. Various components of the computing device 700 can be represented in various illustrative examples. Figure 1 Various components of the manufacturing execution system 102, metering system 110, SPC system 116, data storage 122, client device 128, equipment engineering system 130, and network 140 are shown.

[0082] The example computing device 700 can be connected to other computing devices in a LAN, intranet, extranet, and / or internetwork. The computing device 700 can operate as a server in a client-server network environment. The computing device 700 can be a personal computer (PC), a set-top box (STB), a server, a network router, a switch, or a bridge, or any device capable of executing a set of instructions (sequentially or otherwise) that specifies the action of the device. Furthermore, although a single example computing device is shown, the term "computer" should also be considered as a collection of any machines that individually or jointly execute a set (or more) of instructions to perform any one or more methods described herein.

[0083] Example computing device 700 may include processing device 702 (also referred to as processor or CPU), main memory 704 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM, such as synchronous DRAM (SDRAM) etc.)), static memory 706 (e.g., flash memory, static random access memory (SRAM) etc.), and auxiliary memory (e.g., data storage device 718) that can communicate with each other via bus 730.

[0084] Processing device 702 represents one or more general-purpose processing devices, such as microprocessors, central processing units, etc. More specifically, processing device 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 device 702 may also be one or more special-purpose processing devices, such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal system processors (DSPs), network system processors, etc. According to one or more aspects of this disclosure, processing device 702 may be configured to execute implementations of... Figure 6 The instructions for method 600 are shown.

[0085] The example computing device 700 may also include a network interface device 708 communicatively coupled to a network 720. The example computing device 700 may also include a video display 710 (e.g., a liquid crystal display (LCD), a touchscreen, or a cathode ray tube (CRT)), an alphanumeric input device 712 (e.g., a keyboard), a cursor control device 714 (e.g., a mouse), and an acoustic signal generating device 716 (e.g., a speaker).

[0086] Data storage device 718 may include a machine-readable storage medium (or more specifically, a non-transitory machine-readable storage medium) 728 thereon storing one or more sets of executable instructions 722. According to one or more aspects of this disclosure, the executable instructions 722 may include those for executing... Figure 6 The executable instructions associated with method 600 are shown.

[0087] The executable instructions 722 may also reside wholly or at least partially in the main memory 704 and / or the processing device 702 during execution by the example computing device 700, thus the main memory 704 and the processing device 702 also constitute computer-readable storage media. The executable instructions 722 may also be transmitted or received over a network via the network interface device 708.

[0088] Although Figure 7The computer-readable storage medium 728 shown in the exemplary example is illustrated as a single medium, but the term "computer-readable storage medium" should be considered as encompassing a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) storing one or more sets of executable instructions. The term "computer-readable storage medium" should also be considered as encompassing any medium capable of storing or encoding a set of instructions for execution by a machine and causing the machine to perform any or more of the methods described herein. Therefore, the term "computer-readable storage medium" should be considered as including, but not limited to, solid-state memory, as well as optical and magnetic media.

[0089] Some of the detailed descriptions above are presented based on algorithms and symbolic representations of operations on data bits within computer memory. These algorithmic descriptions and representations are the means by which those skilled in the art of data processing most effectively convey the essence of their work to others skilled in the art. The algorithms described here (and generally) are considered to be self-consistent sequences of steps that produce desired results. These steps are those that require physical manipulation of physical quantities. Typically (but not necessarily), these quantities take the form of electrical or magnetic signals that can be stored, transmitted, combined, compared, and otherwise manipulated. Sometimes, primarily for reasons of general use, it has proven convenient to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc.

[0090] However, it should be remembered that all these and similar terms should be associated with appropriate physical quantities and are merely convenient labels applied to those quantities. Unless otherwise explicitly stated, it will be apparent from the following discussion that, throughout the specification, the use of terms such as “identify,” “determine,” “store,” “adjust,” “cause,” “return,” “compare,” “generate,” “stop,” “load,” “copy,” “discard,” “replace,” “execute,” etc., refers to the actions and procedures of a computer system or similar electronic computing device that manipulate and transform data represented as physical (electronic) quantities in the registers and memory of the computer system into other data similarly represented as physical quantities in the computer system’s memory or temporary registers or other such information storage, transmission, or display devices.

[0091] Examples of this disclosure also relate to apparatus for performing the methods described herein. This apparatus may be specifically constructed for a desired purpose, or it may be a general-purpose computer system selectively programmed by a computer program stored in a computer system. Such a computer program may be stored in a computer-readable medium, such as, but not limited to, any type of disk, including optical discs, optical disc read-only memory (CD-ROM) and magneto-optical discs, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disk storage media, optical storage media, flash memory storage media, other types of machine-accessible storage media, or any type of medium suitable for storing electronic instructions, each connected to a computer system bus.

[0092] The methods and demonstrations presented herein are not inherently related to any particular computer or other device. Various general-purpose systems can be used with the programs taught herein, or it may be demonstrated that constructing more specialized devices to perform the required method steps is convenient. The necessary structures for various such systems will be described below. Furthermore, the scope of this disclosure is not limited to any particular programming language. It should be understood that the teachings of this disclosure can be implemented using a variety of programming languages.

[0093] It should be understood that the above description is intended to be illustrative and not restrictive. Many other embodiments will be apparent to those skilled in the art upon reading and understanding the above description. Although specific examples are described in this disclosure, it will be recognized that the systems and methods of this disclosure are not limited to the examples described herein but can be implemented with modifications within the scope of the appended claims. Therefore, the specification and drawings should be regarded as illustrative rather than restrictive. Consequently, the scope of the disclosure should be determined by reference to the appended claims and the full scope of their equivalents.

Claims

1. A method comprising the following steps: The current measurement data, which includes the current value of a parameter at each of one or more locations on the current sample, is received by at least one processing device for operations performed on the current sample during the manufacturing process. A reference rate of change of the parameter value at each of the one or more locations is obtained by the at least one processing device, 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 measurement data of the operation performed on one or more previous samples in the manufacturing process; The at least one processing device determines the current rate of change of the parameter value at each of the one or more locations, the current rate of change of the parameter value being associated with the current sample; The at least one processing device compares the current rate of change of the parameter value at each of the one or more locations with the reference rate of change of the parameter value at each of the one or more locations; Anomalies in the manufacturing process are identified by the at least one processing device based on a comparison between the current rate of change of the parameter value and the reference rate of change of the parameter value. and This prompts the implementation of corrective measures associated with the manufacturing processing equipment based on the aforementioned anomaly.

2. The method according to claim 1, further comprising the following steps: At least one of the implementation schemes for altering the operation or processing of the machine associated with the abnormal situation using the at least one processing device.

3. The method of claim 1, wherein the reference rate of change of the parameter value is determined by performing a difference analysis on the one or more historical rates of change of the parameter value.

4. The method according to claim 1, further comprising the following steps: The at least one processing device identifies one or more violation locations, where the current rate of change of the parameter value at each violation location is greater than the reference rate of change of the parameter value.

5. The method according to claim 4, further comprising the following steps: The at least one processing device determines sample patterns associated with the one or more violation locations; and The at least one processing device identifies the anomaly based on the sample pattern.

6. The method according to claim 1, further comprising the following steps: Retrieve one or more processing dependencies of the manufacturing process through the at least one processing device; and The at least one processing device identifies the anomaly in the manufacturing process based on one or more of the processing dependencies.

7. The method according to claim 1, further comprising the following steps: A graphical user interface is provided through the at least one processing device, the graphical user interface presenting visual indicators of the machine or process associated with the abnormal situation.

8. A system comprising: Memory; and At least one processing device, the at least one processing device being communicatively coupled to the memory, for: Receive current measurement data of operations performed on the current sample during the manufacturing process, the current measurement data including the current value of a parameter at each of one or more locations on the current sample; Obtain a reference rate of change of the parameter value at each of the one or more locations, 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 measurement data of the operation performed on one or more previous samples in the manufacturing process; Determine the current rate of change of the parameter value at each of the one or more locations, the current rate of change of the parameter value being associated with the current sample; The current rate of change of the parameter value at each of the one or more locations is compared with the reference rate of change of the parameter value at each of the one or more locations; Anomalies in the manufacturing process are identified by comparing the current rate of change of the parameter value with the reference rate of change of the parameter value. and This prompts the implementation of corrective measures associated with the manufacturing processing equipment based on the aforementioned anomaly.

9. The system of claim 8, wherein the processing device is further configured to: At least one of the implementation schemes for changing the operation or processing of the machine associated with the abnormal situation.

10. The system of claim 8, wherein the reference rate of change of the parameter value is determined by performing a difference analysis on the one or more previous rates of change of the parameter value.

11. The system of claim 8, wherein the processing device is further configured to: Identify one or more violation locations, where the current rate of change of the parameter value at each violation location is greater than the relevant reference rate of change of the parameter value.

12. The system of claim 11, wherein the processing device is further configured to: Determine sample patterns associated with the one or more violation locations; and The abnormal situation is identified based on the sample pattern.

13. The system of claim 8, wherein the processing device is further configured to: Retrieve one or more processing dependencies of the manufacturing process; and The anomaly in the manufacturing process is identified based on one or more of the processing dependencies.

14. The system of claim 8, wherein the processing device is further configured to: Provide an implementation scheme for the operation or handling of the machine associated with the aforementioned abnormal situation, presented on a graphical user interface.

15. A non-transitory machine-readable storage medium, comprising instructions that, when executed by at least one processing device, cause the at least one processing device to: Receive current measurement data of operations performed on the current sample during the manufacturing process, the current measurement data including the current value of a parameter at each of one or more locations on the current sample; Obtain a reference rate of change of the parameter value at each of the one or more locations, 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 measurement data of the operation performed on one or more previous samples in the manufacturing process; Determine the current rate of change of the parameter value at each of the one or more locations, the current rate of change of the parameter value being associated with the current sample; The current rate of change of the parameter value at each of the one or more locations is compared with the reference rate of change of the parameter value at each of the one or more locations; Anomalies in the manufacturing process are identified by comparing the current rate of change of the parameter value with the reference rate of change of the parameter value. and This prompts the implementation of corrective measures associated with the manufacturing processing equipment based on the aforementioned anomaly.

16. The non-transitory machine-readable storage medium of claim 15, wherein the processing apparatus further comprises: Identify one or more violation locations, where the current rate of change of the parameter value at each violation location is greater than the relevant reference rate of change of the parameter value.

17. The non-transitory machine-readable storage medium of claim 16, wherein the processing apparatus further comprises: Determine sample patterns associated with the one or more violation locations; and The abnormal situation is identified based on the sample pattern.

18. The non-transitory machine-readable storage medium of claim 15, wherein the processing apparatus further comprises: Retrieve one or more processing dependencies of the manufacturing process; and The anomaly in the manufacturing process is identified based on one or more of the processing dependencies and the comparison between the current rate of change of the parameter value and the reference rate of change of the parameter value.

Images