Dynamic process endpoint determination based on process profile shape

Abstract

Embodiments of the present disclosure relate to dynamic process endpoint determination based on process profile shapes. In some implementations, a device may receive spectral data associated with iterations of a dynamic process. The device may generate a process profile associated with an iteration of the dynamic process based on the spectral data. The device may generate a slope profile associated with an iteration of the dynamic process based on the process profile. The device may determine a trend of the process profile. The device may identify a set of slope thresholds associated with an iteration of the dynamic process based on the trend.

Description

Background Technology

[0001] Dynamic processes (such as mixing processes, e.g., mixing processes associated with the manufacture of pharmaceuticals) may involve one or more state transitions, such as from a non-steady state (e.g., a non-homogeneous state of the mixture, where the properties of the mixture change over time) to a steady state (e.g., a homogeneous state of the mixture, where the properties of the mixture remain substantially constant over time). For example, a mixing process may involve a transition in which the spectral characteristics of the mixture change from a non-steady state (e.g., at the start of the mixing process) to a steady state (e.g., indicating the completion of the mixing process). Summary of the Invention

[0002] Some implementations described herein relate to a method. This method may include receiving spectral data associated with iterations of a dynamic process by a device. This method may include generating a process profile associated with iterations of the dynamic process by the device and based on the spectral data. This method may include generating a slope profile associated with iterations of the dynamic process by the device and based on the process profile. This method may include determining a trend in the process profile by the device. This method may include identifying a set of slope thresholds associated with iterations of the dynamic process by the device based on the trend.

[0003] Some implementations described herein relate to a device. This device may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be configured to acquire time-series spectral data associated with iterations of a dynamic process. The one or more processors may be configured to generate a process profile associated with iterations of the dynamic process based on the time-series spectral data. The one or more processors may be configured to generate a slope profile associated with iterations of the dynamic process based on the process profile. The one or more processors may be configured to compute a set of slope thresholds associated with iterations of the dynamic process based on the trend characteristics of the process profile and the slope profile.

[0004] Some implementations described herein relate to a non-transitory computer-readable medium storing a set of instructions. When executed by one or more processors of a device, the set of instructions can cause the device to acquire a process profile associated with iterations of a dynamic process based on spectral data associated with those iterations. When executed by one or more processors of the device, the set of instructions can cause the device to generate a slope profile associated with iterations of the dynamic process based on the process profile. When executed by one or more processors of the device, the set of instructions can cause the device to identify a set of slope thresholds associated with iterations of the dynamic process based on the slope profile and trends associated with the process profile. When executed by one or more processors of the device, the set of instructions can cause the device to determine the endpoint of another iteration of the dynamic process based on the set of slope thresholds. Attached Figure Description

[0005] Figures 1A-1J It is a graph associated with determining the endpoint of an iteration of a dynamic process based on the shape of the process profile;

[0006] Figure 2 It is a diagram of an example environment in which the systems and / or methods described in this article can be implemented;

[0007] Figure 3 This is a diagram of example components of the device, which may correspond to a spectrometer, detection equipment, and / or user equipment; and

[0008] Figure 4 This is a flowchart of an example process associated with determining the endpoint of an iteration of a dynamic process based on the shape of the process profile. Detailed Implementation

[0009] The following example implementation is described in detail with reference to the accompanying drawings. The same reference numerals in different drawings may identify the same or similar elements. The following description uses a spectrometer as an example. However, the techniques, principles, processes, and methods described herein can be used with any sensor, including but not limited to other optical and spectral sensors.

[0010] As described above, dynamic processes can involve the transition of the spectral properties of a test object from a non-steady state to a steady state. For example, a mixing process can involve the transition of the spectral properties of a material mixture from a non-steady state (e.g., a state where the properties of the material mixture change over time) to a steady state (e.g., a state where the properties of the material mixture remain substantially constant over time). A steady state indicates that mixing has been achieved. Therefore, accurately and reliably detecting the steady state based on the spectral properties of the test object can improve both the performance of dynamic processes (e.g., by ensuring thorough mixing) and the efficiency of dynamic processes (e.g., by enabling the mixing process to be terminated immediately after mixing is achieved).

[0011] A conventional technique for detecting the endpoint of an iteration in a mixing process based on spectral properties is to use moving block analysis, which may include using, for example, moving block standard deviation (MBSD), moving block mean (MBM), moving block relative standard deviation (MB-RSD), or moving F-test. Moving block analysis typically requires selecting thresholds for such variables (e.g., MBSD and / or MBM) based on calibration or historical data to determine when a steady state is reached. However, in practice, it is difficult to reproduce the same iterations of a dynamic process, especially during the development of a mixing process. This means that selecting an appropriate threshold for endpoint detection is challenging and can lead to inaccurate endpoint detection.

[0012] One alternative technique for determining the endpoint of an iteration in a dynamic process is a visual inspection by an observer of the shape of the mixing profile (e.g., a profile generated based on spectral data). Here, the mixing process can be considered to be in a steady state when the mixing profile reaches stationarity. However, visual inspection is subjective and therefore unreliable. This is especially true for mixing profiles with slowly changing slopes, as different observers may draw different conclusions about whether the iteration has reached its endpoint (i.e., whether the mixing profile has reached stationarity). Furthermore, manually determining the endpoint during production is impractical when many (e.g., hundreds) iterations of a dynamic process need to be performed.

[0013] Some implementations described herein can determine the endpoint of an iteration of a dynamic process based on the shape of a process profile. That is, the techniques and apparatus described herein can determine the endpoint of an iteration of a dynamic process (e.g., a hybrid process) based on the slope of a process profile (e.g., a hybrid profile). In some implementations, an apparatus can receive spectral data associated with the iteration of a dynamic process. The apparatus can generate a process profile associated with the iteration of the dynamic process based on the spectral data. The apparatus can generate a slope profile associated with the iteration of the dynamic process based on the process profile. The apparatus can determine a trend in the process profile and identify a set of slope thresholds associated with the iteration of the dynamic process based on that trend. The apparatus can then use the set of slope thresholds based on the slope profile to determine the endpoint of the iteration of the dynamic process.

[0014] In some implementations, the techniques and apparatus described herein can determine the endpoint of an iteration of a dynamic process without requiring calibration or historical data, and furthermore, eliminate the subjectivity of endpoint detection by eliminating both the need for manually selecting thresholds and the need for visual inspection of hybrid profiles. As a result, the reliability of endpoint detection is improved. It is worth noting that although the examples described herein are in the context of hybrid processes, these techniques and apparatus can be used for any dynamic process proceeding from a non-steady state to a steady state. Further details are described below.

[0015] Figures 1A-1J It is a graph associated with determining the endpoint of an iteration of a dynamic process based on the shape of the process profile, as described in this paper. Figure 1A and Figure 1B This is a diagram illustrating an example implementation 100 associated with determining the endpoint of an iteration of a dynamic process based on the shape of the process profile. (See diagram for example.) Figure 1A and Figure 1B As shown, example implementation 100 includes a spectrometer 210, a detection device 220, and a user device 230.

[0016] like Figure 1AAs indicated by reference numeral 102, detection device 220 can receive spectral data associated with iterations of a dynamic process. For example, as shown, spectrometer 210 can measure spectral data at a given time during iterations of the mixing process and can provide the spectral data to detection device 220. In some implementations, the spectral data includes spectra measured by spectrometer 210 during iterations of the mixing process (e.g., multivariate time-series data, such as NIR spectra).

[0017] In some implementations, detection device 220 can receive spectral data in real-time or near real-time during iterations of the mixing process. For example, instead of spectrometer 210 acquiring spectral data during the mixing process, detection device 220 can receive spectral data measured by spectrometer 210 during iterations of the mixing process in real-time or near real-time. In some implementations, detection device 220 can determine the endpoint of iterations of the dynamic process based on the spectral data, as described herein.

[0018] In some implementations, the detection device 220 can preprocess the spectral data. For example, the raw spectral data may include a certain amount of noise, scattering effects, artifacts, or other types of unwanted features. Therefore, in some implementations, the detection device 220 can preprocess the spectral data to reduce the presence of unwanted features or remove these unwanted features from the spectral data. In some implementations, the detection device 220 can use techniques such as derivative calculation, standard normal variable (SNV) techniques, or multiplicative scattering correction (MSC) techniques to preprocess the spectral data.

[0019] As shown by reference numeral 104 in the attached figure, the detection device 220 can generate a process profile associated with the iteration of a dynamic process based on spectral data. In some implementations, the process profile can be generated using moving block analysis, which may include the MBSD, MBM, or MB-RSD within the time period of the iteration of the dynamic process.

[0020] Figures 1C-1F This is a diagram illustrating an example of a process profile associated with three iterations of a dynamic process. Figure 1C and Figure 1D These are MBM profiles for the first-stage mix and the second-stage mix in each of the three iterations of a dynamic process (e.g., iteration A, iteration B, and iteration C). Figure 1E and Figure 1F These are the MBSD profiles for the first-stage mix and the second-stage mix in each of the three iterations of the dynamic process. It is worth noting that for... Figure 1C and Figure 1DAs shown in the MBM profile, due to the inconsistency of MBM values ​​across different iterations, selecting the upper and lower limits of MBM from the visual inspection of the process profile as the endpoint detection thresholds for all three iterations of the dynamic process is not straightforward. Based on Figure 1E and Figure 1F Choosing the MBSD limit from the MBSD profile is equally difficult.

[0021] Back Figure 1A As shown by reference numeral 106 in the attached figure, the detection device 220 can generate a slope profile associated with the iterations of a dynamic process based on the process profile. The slope profile is a profile representing the slope of the process profile over the duration of the iterations of the dynamic process. In some implementations, to generate the slope profile, the detection device 220 calculates the slope of the process profile along its entire length (e.g., in the time domain) by fitting a low-order polynomial regression model within a sliding window and then differentiating the regression model.

[0022] In some implementations, the detection device 220 may perform normalization of the process profile before generating the slope profile. In some implementations, normalization of the process profile (i.e., process profiles from different iterations with different value ranges) makes the process profiles more directly comparable. The normalization technique used by the detection device 220 to normalize the process profile can be, for example, range-based normalization, or another type of normalization technique.

[0023] Figure 1G-Figure 1J This shows the above regarding Figures 1C-1F A graph of the slope profile of an example process profile associated with three iterations of the example dynamic process (after normalization of the process profile). Figure 1G and Figure 1H They are Figure 1C and Figure 1D The slope profile of the MBM profile shown is plotted. Figure 1I and Figure 1J They are Figure 1E and Figure 1F The diagram shows a slope profile of the MBSD profile. It is worth noting that in some cases, the spectral data in the early stages of an iteration of a dynamic process may be highly unstable and therefore should not be used in conjunction with determining the endpoint of the iteration of the dynamic process. Therefore, in some implementations, the detection device 220 may identify the start time point of the spectral data based on the spectral data to determine the endpoint of the iteration of the dynamic process. This time point may be referred to as the pseudo-steady state. Thus, in some implementations, the start time point associated with generating the slope profile is at or after the identified start time point of the spectral data.

[0024] A stationary process profile (i.e., when the slope of the process profile is close to zero) indicates that the iteration of the dynamic process has reached a steady state. Therefore, a slope close to zero in the process profile indicates the end point of the iteration of the dynamic process (i.e., the iteration of the dynamic process has reached a steady state). Thus, a set of slope thresholds (e.g., an upper slope threshold and a lower slope threshold) needs to be selected, where the slope threshold set defines a range of values ​​within which the slope is considered sufficiently close to zero to determine the end point of the iteration of the dynamic process. In some implementations, the detection device 220 may determine the slope threshold set based on the trend of the process profile, as described below.

[0025] like Figure 1B As shown by reference numeral 108 in the accompanying drawings, the detection device 220 can determine the trend of the process profile. The trend of the process profile is an indication of whether the process profile is trending upwards or downwards. In some implementations, the detection device 220 can determine the trend of the process profile based on the sign of the slope profile. For example, Figure 1C The MBM profile shown Figure 1E The MBSD profile shown and Figure 1F The MBSD profiles shown exhibit a downward trend (e.g., process profiles have an overall negative slope), while Figure 1D The MBM profile shown shows an upward trend (e.g., the process profile has an overall positive slope).

[0026] As indicated by reference numeral 110 in the attached figure, the detection device 220 can identify a set of slope thresholds associated with the iteration of the dynamic process based on this trend. In some implementations, if the trend of the process profile indicates an upward trend in the process profile, the detection device 220 can determine the set of slope thresholds based on the minimum value of the slope profile. In some implementations, if the trend of the process profile indicates a downward trend in the process profile, the detection device 220 can determine the set of slope thresholds based on the maximum value of the slope profile.

[0027] As shown by reference numeral 112 in the attached figure, detection device 220 can use a slope threshold set based on a slope profile to determine the endpoint of an iteration of a dynamic process. In some implementations, detection device 220 can determine the endpoint based on an endpoint criterion set. In one example, the endpoint criterion set may require a specific percentage (e.g., 80% of a specific number of consecutive values ​​in the slope profile) of a certain number of consecutive values ​​in the slope profile to be within a lower slope threshold and an upper slope threshold.

[0028] In some implementations, detection device 220 can perform endpoint detection on a single slope profile from a single iteration of a dynamic process. In such an implementation, detection device 220 can use predefined endpoint criteria associated with determining the endpoint. In one example, detection device 220 can determine the time points at which a specific percentage (e.g., 80%) of a specific number of consecutive values ​​(e.g., 30 consecutive values) of the slope profile is greater than or equal to a lower slope threshold and less than or equal to an upper slope threshold.

[0029] In some implementations, detection device 220 can perform endpoint detection associated with multiple iterations of a dynamic process. For example, the process described above can be performed separately for each iteration of the dynamic process, and a set of slope thresholds with specific characteristics (e.g., the widest range) can be identified as the master slope threshold set for the dynamic process. Detection device 220 can then use the master slope threshold set to determine the endpoint of each iteration. Thus, in some implementations, detection device 220 can identify at least two slope threshold sets (each associated with a corresponding iteration of the dynamic process), and can identify the master slope threshold set based on at least two slope threshold sets. The master slope threshold set can then be used to determine the endpoint of an iteration of the dynamic process. For example, the master slope threshold set can be used to determine the endpoint of a previously executed iteration or a later executed iteration (e.g., for real-time or near-real-time endpoint detection).

[0030] In Figure 1C-Figure 1J In a related example, the endpoint criteria may require that at least 24 out of 30 consecutive data points in the slope profile are within the downslope and upslope thresholds of the first-stage mixing, and at least 16 out of 20 consecutive data points in the slope profile are within the upslope and downslope thresholds of the second-stage mixing. The endpoints determined based on the above techniques are shown in Table 1.

[0031]

[0032]

[0033] Table 1

[0034] The results shown in Table 1 are consistent with... Figures 1C-1F The visual observations of the process profiles shown are consistent. Here, thresholds based on the slope of the process profile are relatively more robust than thresholds based on the parameter values ​​of the process profile itself (e.g., MBM and MBSD), while eliminating subjectivity in endpoint detection.

[0035] As indicated by reference numeral 114 in the accompanying drawings, detection device 220 may (optionally) provide an indication of the endpoint of an iteration of a dynamic process. For example, detection device 220 may provide user device 230 with an indication of the endpoint of an iteration of a dynamic process determined by detection device 220. In some implementations, detection device 220 may provide user device 230 with information associated with the endpoint to, for example, to visualize a slope threshold during an iteration of the dynamic process performed later.

[0036] Additionally or alternatively, the detection device 220 may provide or store information associated with a slope threshold set. For example, the detection device 220 may store an indication of a slope threshold set determined by the detection device 220 (e.g., such that the slope threshold set can be used to detect the endpoint of another iteration of a later-executed dynamic process). As another example, the detection device 220 may provide an indication of the slope threshold set to the user device 230 (e.g., to enable visualization of the evolution of the dynamic process via the user device 230).

[0037] In this way, detection device 220 can employ qualitative methods (e.g., moving block analysis) while eliminating subjectivity in the selection of thresholds for endpoint detection, and furthermore, can achieve endpoint detection without the need for calibration or historical data. Furthermore, according to the techniques and apparatus described herein, detection device 220 is capable of (1) automatically selecting a threshold for endpoint detection, thereby eliminating subjectivity in the analysis; (2) performing post-analysis on a single spectral dataset without the need for calibration or historical data to select a threshold to be used for endpoint detection (e.g., for iterations of a previously performed dynamic process or iterations of a later performed dynamic process); (3) performing post-analysis on multiple iterations to achieve automatic selection of a threshold for endpoint detection, which can be used to monitor future iterations of the dynamic process (e.g., in real time); and / or (4) selecting a threshold for endpoint detection based on the slope of the process profile, which is relatively more robust than a threshold selected based on parameter values ​​of the process profile.

[0038] As mentioned above, Figures 1A-1J Provided as an example only. Other examples are also possible and can be discussed in relation to... Figures 1A-1J The differences mentioned.

[0039] Figure 2 This is a schematic diagram of an example environment 200 in which the systems and / or methods described herein can be implemented. (See diagram 200 for example environment 200.) Figure 2 As shown, environment 200 may include one or more spectrometers 210-1 to 210-n (n≥1) (collectively referred to herein as spectrometer 210, or individually as spectrometer 210), detection equipment 220, user equipment 230, and network 240. The equipment in environment 200 may be interconnected via wired connections, wireless connections, or a combination of wired and wireless connections.

[0040] Spectrometer 210 includes a device capable of performing spectral measurements on a sample (e.g., a sample associated with a manufacturing process). For example, spectrometer 210 may include a benchtop (i.e., non-handheld) spectrometer device, a handheld spectrometer device, or a portable spectrometer device performing spectroscopy (e.g., vibrational spectroscopy, such as NIR spectroscopy, mid-infrared spectroscopy (mid-IR), Raman spectroscopy, etc.). In some implementations, spectrometer 210 may be mounted or included in a device associated with the iterative execution of a dynamic process. For example, in some implementations, spectrometer device 210 may be mounted or otherwise included in a mixing device for performing iterative mixing processes. In some implementations, spectrometer 210 may be able to provide spectral data acquired by spectrometer 210 for analysis by another device (such as detection device 220).

[0041] The detection device 220 includes one or more devices, as described herein, capable of performing one or more operations associated with determining the endpoint of an iteration of a dynamic process based on the shape of a process profile. For example, the detection device 220 may include a server, a group of servers, a computer, a cloud computing device, etc. In some implementations, the detection device 220 may receive and / or send information to another device in the environment 200, such as spectrometer 210 and / or user equipment 230.

[0042] User equipment 230 includes one or more devices, as described herein, capable of receiving, processing, and / or providing information associated with determining the endpoint of an iteration of a dynamic process based on the shape of a process profile. For example, user equipment 230 may include communication and computing devices such as desktop computers, mobile phones (e.g., smartphones, cordless phones, etc.), laptop computers, tablet computers, handheld computers, wearable communication devices (e.g., smartwatches, smart glasses, etc.) or similar types of devices.

[0043] Network 240 includes one or more wired and / or wireless networks. For example, network 240 may include cellular networks (e.g., 5G networks, 4G networks, Long Term Evolution (LTE) networks, 3G networks, Code Division Multiple Access (CDMA) networks, etc.), Public Land Mobile Networks (PLMN), Local Area Networks (LAN), Wide Area Networks (WAN), Metropolitan Area Networks (MAN), Telephone Networks (e.g., Public Switched Telephone Network (PSTN)), Private Networks, Ad Hoc Networks, Intranets, the Internet, Fiber-based Networks, Cloud Computing Networks, etc., and / or combinations of these or other types of networks.

[0044] Figure 2 The number and arrangement of devices and networks shown are provided as examples. In practice, with Figure 2Compared to what is shown, there can be more devices and / or networks, fewer devices and / or networks, different devices and / or networks, or devices and / or networks arranged differently. Furthermore, Figure 2 The two or more devices shown can be implemented within a single device, or Figure 2 The single device shown can be implemented as multiple distributed devices. Additionally or alternatively, a group of devices in environment 200 (e.g., one or more devices) can perform one or more functions described as being performed by another group of devices in environment 200.

[0045] Figure 3 This is a diagram of example components of device 300, which may correspond to spectrometer 210, detection device 220, and / or user equipment 230. In some implementations, spectrometer 210, detection device 220, and / or user equipment 230 may include one or more devices 300 and / or one or more components of device 300. For example... Figure 3 As shown, device 300 may include bus 310, processor 320, memory 330, input component 340, output component 350 and / or communication component 360.

[0046] Bus 310 includes one or more components that enable wired and / or wireless communication between components of device 300. Bus 310 can... Figure 3 Two or more components are coupled together, such as via operational coupling, communication coupling, electronic coupling, and / or electrical coupling. Processor 320 includes a central processing unit, graphics processing unit, microprocessor, controller, microcontroller, digital signal processor, field-programmable gate array, application-specific integrated circuit, and / or other types of processing components. Processor 320 is implemented in hardware, firmware, or a combination of hardware and software. In some implementations, processor 320 includes one or more processors capable of being programmed to perform one or more operations or processes described elsewhere herein.

[0047] Memory 330 includes volatile and / or non-volatile memory. For example, memory 330 may include random access memory (RAM), read-only memory (ROM), hard disk drive, and / or another type of memory (e.g., flash memory, magnetic storage, and / or optical storage). Memory 330 may include internal memory (e.g., RAM, ROM, or hard disk drive) and / or removable memory (e.g., removable via a universal serial bus). Memory 330 may be a non-transitory computer-readable medium. Memory 330 stores information, instructions, and / or software (e.g., one or more software applications) related to the operation of device 300. In some implementations, memory 330 includes one or more memories, such as those coupled to one or more processors (e.g., processor 320) via bus 310.

[0048] Input component 340 enables device 300 to receive input, such as user input and / or sensed input. For example, input component 340 may include a touchscreen, keyboard, keypad, mouse, button, microphone, switch, sensor, GPS sensor, accelerometer, gyroscope, and / or actuator. Output component 350 enables device 300 to provide output, such as via a display, speaker, and / or light-emitting diode. Communication component 360 enables device 300 to communicate with other devices via wired and / or wireless connections. For example, communication component 360 may include a receiver, transmitter, transceiver, modem, network interface card, and / or antenna.

[0049] Device 300 may perform one or more operations or procedures described herein. For example, a non-transitory computer-readable medium (e.g., memory 330) may store a set of instructions (e.g., one or more instructions or code) for execution by processor 320. Processor 320 may execute the set of instructions to perform one or more operations or procedures described herein. In some implementations, execution of the set of instructions by one or more processors 320 causes one or more processors 320 and / or device 300 to perform one or more operations or procedures described herein. In some implementations, hardwired circuitry is used in place of or in combination with instructions to perform one or more operations or procedures described herein. Additionally or alternatively, processor 320 may be configured to perform one or more operations or procedures described herein. Therefore, the implementations described herein are not limited to any particular combination of hardware circuitry and software.

[0050] Figure 3 The number and arrangement of components shown are provided as an example. Figure 3 Compared to the examples shown, device 300 may include more components, fewer components, different components, or components arranged differently. Additionally or alternatively, a set of components of device 300 (e.g., one or more components) may perform one or more functions described as being performed by another set of components of device 300.

[0051] Figure 4 This is a flowchart of an example process 400 associated with determining the endpoint of an iteration of a dynamic process based on the shape of the process profile. In some implementations, Figure 4 One or more process frames are executed by a device (e.g., detection device 220). In some implementations, Figure 4 One or more process frames are performed by another device or group of devices that are separate from or include the device, such as a spectrometer (e.g., spectrometer 210) and / or user equipment (e.g., user equipment 230). Additionally or alternatively, Figure 4One or more process frames may be executed by one or more components of the device 300, such as processor 320, memory 330, input component 340, output component 350 and / or communication component 360.

[0052] like Figure 4 As shown, process 400 may include receiving spectral data associated with iterations of a dynamic process (box 410). For example, the device may receive spectral data associated with iterations of a dynamic process, as described above.

[0053] like Figure 4 As further shown, process 400 may include generating a process profile (box 420) associated with the iteration of a dynamic process based on spectral data. For example, the device may generate a process profile associated with the iteration of a dynamic process based on spectral data, as described above.

[0054] like Figure 4 As further shown, process 400 may include generating a slope profile associated with iterations of the dynamic process based on the process profile (box 430). For example, the device may generate a slope profile associated with iterations of the dynamic process based on the process profile, as described above.

[0055] like Figure 4 As further shown, process 400 may include determining a trend in the process profile (box 440). For example, the device may determine a trend in the process profile as described above.

[0056] like Figure 4 As further shown, process 400 may include identifying a set of slope thresholds associated with iterations of the dynamic process based on this trend (box 450). For example, the device may identify a set of slope thresholds associated with iterations of the dynamic process based on this trend, as described above.

[0057] Process 400 may include additional implementations, such as any single implementation or any combination of implementations described below and / or implementations related to one or more other processes described elsewhere in this document.

[0058] In the first implementation, process 400 includes using a slope threshold set based on a slope profile to determine the endpoint of the iteration of the dynamic process.

[0059] In the second implementation, either alone or in combination with the first implementation, the endpoint is also determined based on the endpoint criterion set.

[0060] In the third implementation, either alone or in combination with one or more of the first and second implementations, the slope threshold set includes a downslope threshold and an upslope threshold, and the endpoint criterion set requires a certain percentage of a certain number of consecutive values ​​of the slope profile to fall within the downslope threshold and the upslope threshold.

[0061] In the fourth implementation, either alone or in combination with one or more of the first to third implementations, the trend indication process profile shows an upward trend, and determining the slope threshold set includes: determining the slope threshold set based on the minimum value of the slope profile.

[0062] In the fifth implementation, either alone or in combination with one or more of the first to fourth implementations, the trend indication process profile shows a downward trend, and determining the slope threshold set includes: determining the slope threshold set based on the maximum value of the slope profile.

[0063] In the sixth implementation, either alone or in combination with one or more of the first through fifth implementations, process 400 includes performing normalization of the process profile before generating the slope profile.

[0064] In the seventh implementation, either alone or in combination with one or more of the first through sixth implementations, process 400 includes identifying the start time point of the spectral data to be used to determine the endpoint of the iteration of the dynamic process based on the spectral data, wherein the start time point associated with the generation of the slope profile is at or after the identified start time point of the spectral data.

[0065] In the eighth implementation, either alone or in combination with one or more of the first to seventh implementations, the iteration of the dynamic process is the first iteration of the dynamic process, the slope threshold set is the first slope threshold set, and process 400 includes identifying a second slope threshold set associated with the second iteration of the dynamic process; and identifying a master slope threshold set based on the first slope threshold set and the second slope threshold set.

[0066] In the ninth implementation, either alone or in combination with one or more of the first through eighth implementations, process 400 includes using a set of principal slope thresholds to determine the endpoint of at least one of the first iteration or the second iteration of the dynamic process.

[0067] although Figure 4 An example box for process 400 is shown, but in some implementations, it differs from... Figure 4 Compared to the examples shown, process 400 includes more boxes, fewer boxes, different boxes, or boxes arranged differently. Additionally or alternatively, two or more boxes of process 400 can be executed in parallel.

[0068] The foregoing disclosure provides illustrations and descriptions, but is not intended to be exhaustive or to limit implementation to the precise forms disclosed. Modifications and variations can be made based on the foregoing disclosure, or modifications and variations can be derived from the practice of implementation.

[0069] As used herein, the term "component" is intended to be interpreted broadly as hardware, firmware, or a combination of hardware and software. It is clear that the systems and / or methods described herein can be implemented in various forms of hardware, firmware, or combinations of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods is not limiting in its implementation. Therefore, while the operation and behavior of the system and / or method are described herein without reference to any specific software code—it should be understood that software and hardware can be used to implement the system and / or method based on the description herein.

[0070] As used in this article, depending on the context, a value satisfying a threshold can mean that the value is greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, not equal to the threshold, etc.

[0071] Although specific combinations of features are referenced in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various implementations. In fact, many of these features can be combined in ways not specifically referenced in the claims and / or disclosed in the specification. While each dependent claim listed below may directly depend on only one claim, the disclosure of various implementations includes a combination of each dependent claim with every other claim in the claim set. As used herein, the phrase “at least one” in the list of referenced items refers to any combination of these items, including individual members. For example, “at least one of a, b, or c” is intended to cover a, b, c, ab, ac, bc, and abc, as well as multiple combinations of the aforementioned items.

[0072] When the term "processor" or "one or more processors" (or another device or component, such as "controller" or "at least one controller") is described or claimed (within a single claim or across multiple claims) to perform or be configured to perform multiple operations, this language is intended to broadly cover a wide range of processor architectures and environments. For example, unless otherwise expressly required (e.g., via the use of "first processor" and "second processor" or other language used in the claims to distinguish processors), this language is intended to cover a single processor performing or configured to perform all operations, a group of processors jointly performing or configured to perform all operations, a first processor performing or configured to perform a first operation and a second processor performing or configured to perform a second operation, or any combination of processors performing or configured to perform operations. For example, when a claim takes the form "one or more processors configured to: perform X; perform Y; and perform Z," the claim should be interpreted as meaning "one or more processors configured to perform X; one or more (possibly different) processors configured to perform Y; and one or more (possibly different) processors configured to perform Z."

[0073] No element, action, or instruction used herein should be construed as critical or necessary unless explicitly stated otherwise. Furthermore, as used herein, the articles “a” and “an” are intended to include one or more items and are interchangeable with “one or more.” Furthermore, as used herein, the article “the” is intended to include one or more items referenced by the article “the” and is interchangeable with “one or more.” Furthermore, as used herein, the term “set” is intended to include one or more items (e.g., related items, unrelated items, or a combination of related and unrelated items) and is interchangeable with “one or more.” If only one item is intended, the phrase “only one” or similar language is used. Furthermore, as used herein, the terms “has,” “have,” “having,” etc., are intended to be open-ended terms. Furthermore, unless explicitly stated otherwise, the phrase “based on” is intended to mean “at least partially based on.” Furthermore, as used herein, the term “or” is intended to be included when used in a series of forms and may be used interchangeably with “and / or” unless otherwise expressly stated (e.g., if used in conjunction with “any one” or “only one”).

Claims

1. A method comprising: The device receives spectral data associated with the iteration of the dynamic process; The device generates a process profile associated with the iteration of the dynamic process based on the spectral data; The device generates a slope profile associated with the iteration of the dynamic process based on the process profile; The trend of the process profile is determined by the device; as well as The device identifies a set of slope thresholds associated with the iteration of the dynamic process based on the trend.

2. The method of claim 1, further comprising using the slope threshold set to determine the endpoint of the iteration of the dynamic process based on the slope profile.

3. The method of claim 2, wherein the endpoint is further determined based on an endpoint criteria set.

4. The method of claim 3, wherein the slope threshold set includes a downslope threshold and an upslope threshold, and the endpoint criterion set requires a specific percentage of a certain number of consecutive values ​​of the slope profile to be within the downslope threshold and the upslope threshold.

5. The method of claim 1, wherein the trend indicates that the process profile is trending upward, and determining the slope threshold set comprises: The slope threshold set is determined based on the minimum value of the slope profile.

6. The method of claim 1, wherein the trend indicates that the process profile is in a downward trend, and determining the slope threshold set comprises: The slope threshold set is determined based on the maximum value of the slope profile.

7. The method of claim 1, further comprising performing normalization of the process profile before generating the slope profile.

8. The method of claim 1, further comprising identifying a start time point of the spectral data to be used to determine the endpoint of the iteration of the dynamic process based on the spectral data, wherein the start time point associated with generating the slope profile is at or after the identified start time point of the spectral data.

9. The method of claim 1, wherein the iteration of the dynamic process is a first iteration of the dynamic process, the slope threshold set is a first slope threshold set, and the method further comprises: Identify the second slope threshold set associated with the second iteration of the dynamic process; as well as The main slope threshold set is identified based on the first slope threshold set and the second slope threshold set.

10. The method of claim 9, further comprising using the principal slope threshold set to determine the endpoint of at least one of the first iteration of the dynamic process or the second iteration of the dynamic process.

11. An apparatus comprising: One or more memory units; as well as One or more processors, coupled to the one or more memories, are configured to: Acquire time-series spectral data associated with the iteration of a dynamic process; A process profile associated with the iteration of the dynamic process is generated based on the time-series spectral data; Based on the process profile, a slope profile is generated that is associated with the iteration of the dynamic process; as well as The slope threshold set associated with the iteration of the dynamic process is calculated based on the trend characteristics of the process profile and the slope profile.

12. The device of claim 11, wherein the one or more processors are further configured to use the slope threshold set to determine the endpoint of the iteration of the dynamic process based on the slope profile.

13. The device of claim 12, wherein the endpoint is further determined based on a set of endpoint criteria.

14. The device of claim 11, wherein the trend characteristic indicates that the process profile is trending upward, and determining the slope threshold set comprises: The slope threshold set is determined based on the minimum value of the slope profile.

15. The device of claim 11, wherein the trend characteristic indicates that the process profile is trending downward, and in order to determine the slope threshold set, the one or more processors are configured to: The slope threshold set is determined based on the maximum value of the slope profile.

16. The apparatus of claim 11, wherein the one or more processors are further configured to perform normalization of the process profile prior to generating the slope profile.

17. The apparatus of claim 11, wherein the one or more processors are further configured to identify a start time point of the spectral data to be used to determine the endpoint of the iteration of the dynamic process based on the time-series spectral data, wherein the start time point associated with generating the slope profile is at or after the identified start time point of the spectral data.

18. The device of claim 11, wherein the iteration of the dynamic process is a first iteration of the dynamic process, the slope threshold set is a first slope threshold set, and the one or more processors are further configured to: Identify the second slope threshold set associated with the second iteration of the dynamic process; and The main slope threshold set for the dynamic process is identified based on the first slope threshold set and the second slope threshold set.

19. The device of claim 18, wherein the one or more processors are further configured to use the main slope threshold set to determine the endpoint of the third iteration of the dynamic process.

20. A non-transitory computer-readable medium storing an instruction set, the instruction set comprising: One or more instructions, which, when executed by one or more processors of the device, cause the device to: A process profile associated with the iteration of the dynamic process is obtained based on spectral data associated with the iteration of the dynamic process. Based on the process profile, a slope profile is generated that is associated with the iteration of the dynamic process; The slope threshold set associated with the iteration of the dynamic process is identified based on the slope profile and the trend associated with the process profile. as well as The endpoint of another iteration of the dynamic process is determined based on the slope threshold set.

Images