Analyzed-image liquid-level sensor

Abstract

In one embodiment, the disclosed subject-matter is a method for determining a level of a liquid in a container, which includes capturing multiple images of the liquid within the container and analyzing the multiple images to generate a liquid-level determination result. The analyzing includes differentiating components of the liquid including at least one component selected from components of foam and bubbles within the liquid. The analyzing further including at least one operation selected from operations of increasing the contrast of the components of the liquid, within the multiple images and increasing the edge detection of the components of the liquid within the multiple of images. Other apparatuses and systems are disclosed.

Description

Attorney Docket 4948.163WO1 / Client File 11586-1WO ANALYZED-IMAGE LIQUID-LEVEL SENSOR CLAIM OF PRIORITY

[0001] This application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 574,122, filed on April 3, 2024, which is incorporated by reference herein in its entirety. TECHNICAL FIELD

[0002] The subject matter disclosed herein relates to various types of equipment used in the semiconductor and allied industries. More specifically, the disclosed subject-matter relates to determining a level of a liquid in a container using an imaging analysis. BACKGROUND

[0003] In various types of semiconductor-manufacturing processes, such as during various types of deposition processes (including plasma-based tools such as atomic-layer deposition (ALD), chemical vapor deposition (CVD), plasma-enhanced CVD (PECVD)), liquid- source-based physical vapor-deposition (PVD), and other deposition processes, a liquid source, such as a precursor, is contained within a liquid container. A level of the liquid is monitored to determine when the liquid needs to be replenished. Also, the level of the liquid can be used to provide a signal to send to a bulk supply of a liquid to prevent possible overfill of the container and thereby avoid potential safety issues. Safety issues that can be monitored also include possible leak detections in the liquid supply system. Since usage levels are known for a given process (e.g., as volume per unit time or mass per unit time, such as milliliters per minute or milligrams per minute), the sensor system disclosed herein can also detect possible leakage conditions.

[0004] Currently, a level of a liquid within a liquid container or ampoule is measured by physically placing sensors in or proximate toAttorney Docket 4948.163WO1 / Client File 11586-1WO the liquid such that the sensors attempt to determine a level of the liquid. The sensors may then measure acoustic, capacitive, or resistive properties of the probe to determine the level of the liquid.

[0005] However, contact-type sensor systems are inaccurate, have slow response times, are large, and are costly. These contact-type systems can also be rendered inaccurate due to at least one of bubbles formed within the liquid, foam produced by the liquid, or sloshing of the liquid in a mobile environment or an environment in which vibrations are encountered by the liquid container. Also, the sensors must periodically be recalibrated.

[0006] Non-contact systems in which the sensor is placed proximate to the liquid (e.g., an ultrasonic sensor), a time-of-flight measurement, or resonance-cavity types of level sensors, can also be inaccurate and / or imprecise due to at least one of bubbles formed within the liquid, foam produced by the liquid, or sloshing of the liquid in a mobile environment or an environment in which vibrations are encountered by the liquid container. Non-contact sensors also tend to be quite large and expensive. Further, these sensor types must periodically be recalibrated as well.

[0007] Therefore, in various embodiments described herein, the disclosed subject-matter discloses an image-based analysis (e.g., from still captures or video captures of a liquid) to determine a level of the liquid in a container. One use of the image-based analysis may be for level control of liquid-precursor containers as used with fabrication tools for substrate depositions. However, the disclosed subject-matter could be used with any container type and any liquid type. Images obtained of the liquid are analyzed via an algorithm to determine the liquid level. The algorithms may utilize artificial intelligence (AI) and machine-learning (ML) image analysis as described herein.Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0008] The information described in this section is provided to offer a person of ordinary skill in the art a context for the following disclosed subject-matter and should not be considered as admitted prior art. SUMMARY

[0009] In one exemplary embodiment, the disclosed subject-matter describes a method for determining a level of a liquid in a container. The method includes capturing multiple images of the liquid within the container and analyzing the multiple images to generate a liquid- level determination result. The analyzing includes differentiating components of the liquid including at least one component selected from components of foam and bubbles within the liquid. The analyzing further including at least one operation selected from operations of increasing the contrast of the components of the liquid within the multiple images and increasing the edge detection of the components of the liquid within the multiple of images.

[0010] In another exemplary embodiment, the disclosed subject- matter describes a system to determine a level of a liquid within a container, the system including at least one imaging device to capture a multiple images of the liquid within the container and an analysis engine. The analysis engine includes one or more hardware-based processors of a machine coupled to the at least one imaging device to apply at least one transformation algorithm to produce a pre- processed image, where the pre-processed image includes pixel-based information related to the multiple images. The analysis engine is further configured to analyze the pixel-based information from the multiple images to perform operations to differentiate components of the liquid including at least one component selected from foam and bubbles within the liquid; the analyzing further including at least one operation selected from operations of increasing the contrast of the components of the liquid within the multiple images and increasingAttorney Docket 4948.163WO1 / Client File 11586-1WO the edge detection of the components of the liquid within the multiple images.

[0011] In another exemplary embodiment, the disclosed subject- matter describes a computer-readable medium containing instructions that, when executed by a machine, cause the machine to perform operations for determining a level of a liquid in a container. The operations include capturing multiple images of the liquid within the container and analyzing the multiple images to generate a liquid- level determination result. The analyzing includes transferring the multiple images to a preprocessor to apply at least one transformation algorithm to produce a pre-processed image, the pre-processed image including pixel-based information related to the multiple images. The method further includes analyzing the pixel-based information from the multiple images to perform operations to differentiate components of the liquid including at least one component of foam and bubbles within the liquid. The analyzing includes at least one operation selected from increasing the contrast of the components of the liquid within the multiple images and increasing the edge detection of the components of the liquid within the multiple images. BRIEF DESCRIPTION OF FIGURES

[0012] Various ones of the appended drawings merely illustrate examples of various implementations of the present disclosure and should not be considered as limiting its scope.

[0013] FIG. 1A shows a three-dimensional view of exemplary embodiments of liquid-level-detection and analyzing systems, in accordance with various embodiments of the disclosed subject-matter;

[0014] FIG. 1B shows a detailed view of an embodiment of a sensor that may be used with the liquid-level-detection and analyzing systems of FIG. 1A;Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0015] FIG. 2 shows a cross-sectional elevational view of an exemplary embodiment of the liquid-level-detection and analyzing system in accordance with various embodiments of the disclosed subject-matter;

[0016] FIG. 3 shows a method for using the liquid-level-detection and analyzing systems, in accordance with various embodiments of the disclosed subject-matter;

[0017] FIG. 4 shows an example of a liquid-level-detection and analyzing system, in accordance with embodiments of the disclosed subject matter;

[0018] FIG. 5A shows an example of a pre-processing system that may be used with the liquid-level-detection and analyzing systems of FIG. 1A and FIG. 2, in accordance with various embodiments of the disclosed subject matter;

[0019] FIG. 5B shows an example of a framework to analyze images of liquid-levels in a container based on images obtained from the liquid-level-detection and analyzing systems of FIG. 1A and FIG. 2, in accordance with various embodiments of the disclosed subject matter; and

[0020] FIG. 6 shows a block diagram of an example comprising a machine upon which any one or more of the techniques (e.g., methods, analysis, or methodologies) discussed herein may be performed.Attorney Docket 4948.163WO1 / Client File 11586-1WO DETAILED DESCRIPTION

[0021] The following description includes a discussion of figures having illustrations given by way of examples of implementations of the disclosed subject-matter. The drawings should be understood by way of example, and not by way of limitation. As used herein, references to one or more ^embodiments^ are understood to be describing a particular feature, structure, or characteristic included in at least one implementation of the disclosed subject-matter. Thus, phrases such as ^in one embodiment,^ ^in an exemplary embodiment,^ or ^in an alternative embodiment^ appearing herein describe various embodiments and implementations of the disclosed subject-matter, and do not necessarily all refer to the same embodiment. However, the embodiments are also not necessarily mutually exclusive from one another. To identify easily the discussion of any particular element or act, the most significant digit or digits in a reference number (e.g., element number) refer to the figure (^FIG.^) number in which that element or act is first introduced.

[0022] In various embodiments described herein, the disclosed subject-matter discloses an image-based analysis (e.g., from still- captured images and / or video-captured images of a liquid) to determine a level of the liquid in a container. Compact low-cost still- mage cameras and video cameras are readily available to acquire a still image or a video image of the liquid inside of the container. Images obtained are then analyzed via an algorithm to determine, for example, periodically, the liquid level. The algorithms may utilize artificial intelligence (AI) and machine-learning (ML) image analysis to determine both an accurate and a precise level of liquid within the container.

[0023] For example, as disclosed herein, a deep-convolution artificial-neural-network (identified herein as a deep-convolution-type system or convnet for brevity of notation) can classify a level of aAttorney Docket 4948.163WO1 / Client File 11586-1WO liquid within a container, regardless of bubbles formed within the liquid, foam produced by the liquid, or sloshing of the liquid in a mobile environment or an environment in which vibrations are encountered by the liquid container. A bubble may be considered to be a thin sphere of liquid enclosing air or another gas (where ^thin^ is at least partially dependent on the surface tension of the liquid). Foam may be considered to be a colloidal system (e.g., a dispersion of particles in a continuous medium) in which the particles are gas bubbles and the medium is the liquid. Therefore, bubbles may be considered to be individually discernable ^particles,^ whereas foam is a mass of bubbles.

[0024] A generalized deep-convolution-type system is explained in detail below. However, based upon reading and understanding the disclosed subject matter, a person of ordinary skill in the art will recognize that any type of, for example, a deep-convolution-type system can be used with the disclosed subject matter described herein.

[0025] Using a deep-convolutional neural-network, in its simplest form, for a given input or set of inputs produces a given output. In this case, an input consisting of a number of images acquired of liquid levels within a liquid container will produce an accurate and precise liquid level at chosen or pre-determined intervals.

[0026] In various embodiments, the disclosed subject-matter can use a deep-convolutional neural-network to determine a liquid level. Images of the liquid and surrounding areas (e.g., an interior of the container as well as any bubbles or foam) may be used to match a trained convnet size of the original image that was used to train the system.Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0027] The disclosed subject-matter will now be described in detail with reference to a few general and specific embodiments as illustrated in various ones of the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the disclosed subject-matter. It will be apparent, however, to a person of ordinary skill in the art upon reading and understanding the disclosed subject-matter, that the disclosed subject-matter may be practiced without some or all of these specific details. In other instances, well-known process steps, construction techniques, or structures have not been described in detail so as not to obscure the disclosed subject-matter.

[0028] The disclosed subject-matter uses an imaging system, such as analysis of still-images or video-imaging captures, to determine a level of liquid in a container. One initial use of the disclosed subject- matter is for level control for liquid-precursor containers as used with semiconductor-substrate deposition systems (e.g., deposition tools). However, the disclosed subject-matter also applies to any container type and any liquid type, regardless of pressures or temperatures involved.

[0029] FIG. 1A shows a three-dimensional view of exemplary embodiments of a liquid-level-detection and analyzing system 100 (liquid-level-detection system), in accordance with various embodiments of the disclosed subject-matter. The liquid-level- detection system 100 is shown to include a container 101, a top- mounted window 103, a corner-mounted window 105, and a side- mounted window 107. Each of the windows may also be considered to be a viewport (although transparency to wavelengths of visible light is not necessarily needed). Further, the container 101 may be considered to be an ampoule, such as a sealed vial. In applications where the container 101 is transparent or semi-transparent at a desired wavelength, the windows 103, 105, 107 may not be needed. Instead,Attorney Docket 4948.163WO1 / Client File 11586-1WO sensors, as described below, may simply be affixed or placed proximate to the container at locations as described herein with regard to the windows.

[0030] The windows 103, 105, 107 may be formed from various types of transparent or semi-transparent plastics or glass types. Such plastic types can include, for example, various types of polycarbonate plastics, polyetheretherketone (PEEK) plastics, and polyetherimide plastics. Glass types that can be selected include, for example, various types of glass ceramic, borosilicate glass, and borophosphosilicate glass (BPSG). A selection of the plastic or glass may be based on factors such as, for example, a level of transparency desired at a given illumination wavelength or range of wavelengths and a level of temperature or pressure that may need to be endured by the windows 103, 105, 107.

[0031] As described in more detail with reference to FIG. 1B, below, an imaging sensor may be placed on the outside of the container to view the liquid level 109 within the container 101 through one or more of the windows 103, 105, 107. The imaging sensor may be coupled optically to the window or through, for example, an optical fiber as described in more detail, below. Further, although only three windows are shown in FIG. 1A, no such limitation is implied. For example, depending upon a level of accuracy or precision required for a determination of the liquid level 109, as well as possible environmental influences experienced by the container 101 (e.g., such as vibrations or a degree of levelness of the container 101), multiple windows may be desired. For example, it may be desirous in certain applications to use multiple ones of the top- mounted window 103 or the side-mounted window 107.

[0032] Further, although the liquid-level-detection system 100 shows three windows, in various embodiments only one of the windows 103, 105, 107 may be used to detect a level 109 of a liquidAttorney Docket 4948.163WO1 / Client File 11586-1WO contained within the container 101. Additionally, in other embodiments, two or all three of the windows 103, 105, 107 may be used concurrently to detect the level 109 of the liquid. In other embodiments, two or all three of the windows 103, 105, 107 may be used at various times sequentially, at least partially depending on the level 109 of the liquid.

[0033] For example, when the level 109 of the liquid is fairly low in the container 101 (e.g., at a level of 10% or lower of a total capacity of the container 101), a person of ordinary skill in the art or an analysis program (described in more detail below) may find it to be more accurate (and / or precise) to use, for example, the corner-mounted window 105 through which the sensor is to capture images of the liquid within the container. At another time, when the when the level 109 of the liquid is fairly high in the container 101 (e.g., at a level of 90% or higher of a total capacity of the container 101), the person of ordinary skill in the art or the analysis program may find it to be more accurate (and / or precise) to use, for example, the top-mounted window 103 through which the sensor is to capture images of the liquid within the container. The skilled artisan, upon reading and understanding the disclosed subject-matter, will recognize which of the window or windows to use for a given application.

[0034] With reference now to FIG. 1B, a detailed view 130 of an embodiment of a sensor 133 that may be used with the liquid-level- detection and analyzing systems 100 of FIG. 1A is shown. The sensor 133 may either attached (e.g., mechanically or adhesively coupled to) or proximate to a window 131. In embodiments, one or more versions of the sensor 133 (e.g., at one or more physical locations) may be optically-coupled to the window 131 by, for example, a fiber-optic cable or fiber-optic bundle. The window 131 may be the same as or similar to any one of the windows 103, 105, 107 of FIG. 1A.Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0035] In various embodiments, the sensor 133 may comprise, for example, various types of imaging devices including a CCD array, a CMOS-based sensor, an active-pixel sensor, a video camera (e.g., a compact, low-cost motion-imaging camera), or other sensor type. Further, although not shown explicitly, the sensor 133 may include an illumination or lighting source, such as one or more light-emitting diodes (LEDs), an array of LEDs, or an array of micro-LEDs.

[0036] FIG. 2 shows a cross-sectional elevational view of an exemplary embodiment of the liquid-level-detection and analyzing system 200 (liquid-level-detection system) in accordance with various embodiments of the disclosed subject-matter. The liquid-level- detection system 200 is shown to include a container 201, a level 207 of a liquid within the container 201, a first sensor 203 and a second sensor 205.

[0037] In various embodiments, either or both of the first sensor 203 and the second sensor 205 may comprise an imaging camera that is similar to or the same as the sensor 133 of FIG. 1B. Further, although not shown explicitly, either or both of the first sensor 203 and the second sensor 205 may include an illumination source or lighting source, such as one or more light-emitting diodes (LEDs), an array of LEDs, or an array of micro-LEDs. In other embodiments, one of the two sensors 203, 205 may comprise an imaging camera and the other of the two sensors comprises an illumination or lighting source.

[0038] A volume above the level 207 of the liquid within the container 201 may be considered to be a gas-phase volume (e.g., a headspace). One or both of the sensors 203, 205 may be positioned above or below the headspace. Also, the sensors may be movable relative to a position of the level 207 of the liquid within the container 201. One or both of the first sensor 203 and the second sensor 205 can view and / or detect a level 207 from the gas-phase volume above the liquid or from and through the liquid. An illumination source or aAttorney Docket 4948.163WO1 / Client File 11586-1WO light source may be placed on or near one of the two sensors 203, 205. In other embodiments, an illumination source or a light source may be placed separately from (e.g., within the container or illuminating through the container 201) or in addition to an illumination source placed on one of the two sensors 203, 205.

[0039] In various embodiments, light from an illumination source can be transmitted, reflected, or diffracted from the liquid and detected either by one of the sensors (e.g., the first sensor 203 or the second sensor 205) or imaged or illuminated by one of the two sensors and detected by the other one of the two sensors. Also, although only two sensors 203, 205 are shown in FIG. 2, no such limitation is implied. For example, depending upon a level of accuracy or precision required for a determination of the liquid level 207, as well as possible environmental influences experienced by the container 201 (e.g., such as vibrations or a degree of levelness of the container 201), one or more additional sensors may be desired. Further, although the sensors 203. 205 are shown on one side of the container 201, other locations can be considered. For example, the sensors may be mounted across from one another (e.g., one on either side of the sensor or one on the top of the container 201 and one placed underneath the sensor). Also, multiple ones of the sensors 203, 205 can be mounted on two or more sides of the container 201 or multiple sides in addition to the top and bottom of the container 201.

[0040] Upon reading and understanding the disclosed subject- matter, a person of ordinary skill in the art will recognize various ways in which the sensors 203, 205 can be used to determine a level of the liquid within the container 201. For example, one of the sensors may be a segmented sensor or imaging device, having spatially- differentiated areas for detecting an angle and distance for which an illumination source was diffracted through a liquid. By knowing a pre-determined refractive index for the liquid to be stored within theAttorney Docket 4948.163WO1 / Client File 11586-1WO container 201, a level 207 of the liquid can readily be determined. In other examples, one of the sensors may be an imaging device, through which the angle and distance the illumination source was diffracted through the liquid. The level 207 can also then be determined based on the known refractive index information. In various embodiments, the disclosed subject-matter can also detect reference marks on walls of the container 201 (e.g., interior walls) and determine a difference in the level 207 of the liquid relative to the marks. In various exemplary embodiments, one or more of the sensors, used as an imaging device, may also be used to diagnose a condition of the liquid based on optical properties of the liquid, such as a color of the liquid or a turbidity level of the liquid. Further, other optical conditions and properties of the liquid may be gathered and reported to provide process information such as an incorrect or contaminated fluid.

[0041] FIG. 3 shows a method 300 for using the liquid-level- detection and analyzing systems described herein, in accordance with various embodiments of the disclosed subject-matter. The method, or any of the methods disclosed herein, may be used to analyze collected images substantially in real time or near real time. At operation 301, images of a liquid from within a container are recorded on one or more of the sensor types described above. At operation 303, an optional step may include processing one or more of the images by various methods, such as those methods described below with reference to FIGS. 4, 5A, and 5B.

[0042] At operation 305, A determination is made as to whether the pre-determined level of the liquid has been reached (e.g., a maximum-fill level, a minimum-fill level (e.g., a refill or replenishment level), or some other level. By knowing the level of the liquid at a given time after the last replenishment of the fluid, a determination may also be made as to, for example, a precursor- dosage use. Knowing the precursor-dosage use can help with variousAttorney Docket 4948.163WO1 / Client File 11586-1WO costs (as part of a cost-of-ownership determination) for a given tool. The determinations may be made based on the recorded images.

[0043] At operation 307, an update-level indicator or a flag may be updated in, for example, a software, firmware, or hardware-based program. Such software, firmware, or hardware-based programs are described in more detail below. At operational loop 309, the method 300 may be performed and updated again. The method 300 may automatically be updated periodically, updated on a manual determination basis, or based on another determination, such as being tied into a process recipe of the deposition tool in a fabrication environment.

[0044] FIG. 4 shows an example of liquid-level-detection and analyzing system 400 (detection and analyzing system), in accordance with embodiments of the disclosed subject matter. The detection and analyzing system 400 can be used to perform one or more techniques shown and described herein and includes a system to determine a level of a liquid within a container. The detection and analyzing system 400 includes at least a portion of a machine-learning network.

[0045] In various embodiments, the detection and analyzing system 400 may first be used in a training mode to train a machine-learning network and may then later be used in a normal-operation mode to detect and determine a level of a liquid within a container. In various examples, the training mode may be performed by a manufacturer of the detection and analyzing system 400. Data obtained from the training mode may then be used at, for example, a fabrication facility to determine a level of a liquid within a container as described above with reference to FIGS. 1A, 1B, and 2 in a normal-operation mode. Example frameworks using data from the detection and analyzing system 400 are described with reference to FIGS. 5A and 5B, below. In embodiments, the detection and analyzing system 400 may be usedAttorney Docket 4948.163WO1 / Client File 11586-1WO directly in a normal-operation mode to detect and determine a level of a liquid within a container.

[0046] In an exemplary embodiment, the detection and analyzing system 400 is shown to include a liquid container 405, an optional light source 401 to illuminate the liquid within the liquid container 405, and a camera 403. The camera 403 may be used to detect a level 407 of the liquid within the liquid container 405. In various embodiments, both the optional light source 401 and the camera 403 are coupled to a data-collection and control system 410.

[0047] The optional light source 401 may comprise a broadband light source, a number of predominantly monochromatic (e.g., single- wavelength) light sources, or a combination of broadband and monochromatic light sources. The optional light source 401 may also include light sources impinging upon the liquid within the liquid container at one or more angles-of-incidence, with different polarization states, intensities of radiation, and so on. A selection of the optional light source 401 may be used based on specific reflection and / or transmission characteristics of various liquids used within the liquid container 405. However, in various embodiments, ambient light from within a local environment in which the liquid container is placed may be sufficient to illuminate the liquid.

[0048] In various embodiments, the camera 403 may comprise two or more cameras. For example, in order to detect the liquid within the liquid container 405, a second camera may be desirable. Also, the camera 403 may comprise multiple cameras. In embodiments, the combination of the optional light source 401, the camera 403, and the container 405 may be the same as or similar to the liquid-level- detection systems 100, 200 of FIGS. 1A and 2, respectively.

[0049] The camera 403 may comprise one or more lenses (e.g., there may be a single variable focal-length lens or a plurality of single focal-Attorney Docket 4948.163WO1 / Client File 11586-1WO length lenses) and an image sensor (e.g., a CCD array, a CMOS-based sensor, an active-pixel sensor, or other sensor types), and camera boards having related circuitry to facilitate image extraction. In one example, the camera 403 is a color camera, which can also be an aid in detection of the liquid. A color camera may be desirable since liquids are often a different color than the liquid placed into the liquid container 405, thus making the liquid more readily discernible from the container. Also, common networks are often trained on color images, which may otherwise cause integration challenges for gray- scale images collected from a monochrome camera. However, with a known liquid using a network trained using gray-scale images, a monochromatic camera may be used as well. In embodiments, multiple cameras may be used as noted above. For example, two cameras can be used to capture stereo images, which may be useful in making a determination of a liquid level versus foam generated by the liquid and contained in the headspace above the liquid.

[0050] In various embodiments, a remote data storage and processing unit 430 may be used for data collection and analysis as described herein. The remote data storage and processing unit 430 may comprise, for example, one or more instantiations of a general- purpose computing device such as a server, a cloud-processing system, a data warehouse, a laptop, a tablet, a smart-phone, a desktop computer, or the like.

[0051] The data-collection and control system 410 is also shown to include a central processing unit (CPU) 411, a graphics processing unit (GPU) 419, a field programmable gate array (FPGA) 417 (or other suitable hardware, such as an application-specific integrated circuit (ASIC) or accelerators such as a data processing unit (DPU), artificial-neuron network (ANN) and the like), a memory 421, a display 413, an input device 423, and a communication interface 415 (e.g., a high-performance network (HPN)).Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0052] The data-collection and control system 410 can also include front-end circuitry such as transmit signal chains, receive signal chains, switch circuitry, digital circuitry, analog circuitry, and so on. In embodiments, the transmit signal chain may provide control signals to the optional light source 401. The receive signal chain may receive image signals from the camera 403. The front-end circuitry may be coupled to and controlled by one or more processor circuits, such as the CPU 411, the GPU 419, and the FPGA 417. The CPU 411 may be implemented as one or more multi-core processors. The GPU 419 and the FPGA 417 may be used to accelerate processing of image data collected from the camera 403 and the performance of the machine-learning network as described herein. The techniques shown and described herein can be executed by, for example, the CPU 411 working in conjunction with the GPU 419 for faster processing.

[0053] The CPU 411 and the GPU 419, as well as other components of the data-collection and control system 410, may be coupled to the memory 421, such as to execute instructions that cause the data- collection and control system 410 to perform one or more of light source illumination, image acquisition, processing, or storage of data relating to the image acquisition, or to otherwise perform techniques as shown and described herein. The data-collection and control system 410 can be coupled communicatively to other portions of the detection and analyzing system 400, such as by using a wired or wireless version of the communication interface 415.

[0054] The performance of one or more techniques as shown and described herein can be accomplished in the data-collection and control system 410 or using other processing or storage facilities, such as using the remote data storage and processing unit 430. For example, processing tasks that may be undesirably slow if performed on the data-collection and control system 410, or beyond the capabilities of data-collection and control system 410, can beAttorney Docket 4948.163WO1 / Client File 11586-1WO performed remotely (e.g., on a separate system), such as in response to a request from data-collection and control system 410. Similarly, storage of imaging data or intermediate data can be accomplished using remote facilities communicatively coupled to the data-collection and control system 410. The data-collection and control system 410 may also include the display 413, such as for presentation of configuration information or results, and the input device 423, such as including one or more of a keyboard, a trackball, function keys or soft keys, a mouse-interface, a touch-screen, a stylus, or the like, for receiving operator commands, configuration information, or responses to queries.

[0055] As described above, the data-collection and control system 410 may receive one or more images of liquid within the liquid container 405. The data-collection and control system 410 may perform one or more techniques as shown and described herein to classify a level of the liquid. Further, some or all aspects of the data- collection and control system 410 can be run and controlled remotely.

[0056] With reference now to FIG. 5A, an example of a pre- processing system 500 that may be used with the liquid-level- detection and analyzing systems 100, 200 of FIG. 1A and FIG. 2, in accordance with various embodiments of the disclosed subject matter, is shown. Upon reading and understanding the disclosed subject matter, a person of ordinary skill in the art will recognize that a number of different deep-convolutional neural-networks, such as a residual-neural network, may be used instead of or in addition to the example pre-processing system of FIG. 5A.

[0057] An imaging system, such as a camera of one of the sensors described above with reference to FIG. 1B or 2, is used to obtain a number of raw images of a liquid within a liquid container. Each of the images may then be processed concurrently or sequentially. For example, a raw image 501 (or multiple raw images) of the liquid mayAttorney Docket 4948.163WO1 / Client File 11586-1WO be manipulated by various techniques. In one example, the raw image may be manipulated using transformation techniques (e.g., transformation algorithms) to form a transformed image in an abstract Hilbert space. In other examples, the transformation may include Fourier transformations, Laplace transformations, or other suitable transformation techniques. Other types of algorithms may be used as well or in addition to the transformation techniques. For color images, these process may apply to one or a combination of the original colors, if present, provided by the imaging system.

[0058] The raw image 501 (or transformed image) may then be filtered by one or more filters in real space and / or Hilbert space, including linear and non-linear filters. For example, the raw image 501 (or transformed image) may be filtered by a first filter 521 (filter 1) to generate a first set of intermediate images 503, 505 (the example of FIG. 5A shows only two intermediate images but any number of intermediate images may be generated if and as needed). The first filter 521 may be provided as one or more linear filters in, for example, different bandwidths of light.

[0059] The first set of intermediate images 503, 505 may then be combined and filtered by a second filter 523 (filter 2) to generate a second intermediate image 507. The second filter 523 may be provided as one or more linear or other types of filter. The second intermediate image 507 may be filtered by a third filter 525 (filter 3) to generate a pre-processed image 509. The third filter 525 may be provided as one or more non-linear filters or other types of filter. For example, any one or more of the filters 521, 523, 525 or the intermediate images 503, 505, 507 may include feature extraction techniques to remove noise, irrelevant features (e.g., portions of the images related bubbles and foam), or other features that tend to obscure the actual level of the liquid. Any one or more of these components may therefore be referred to as an analysis engine.Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0060] In embodiments, the pre-processing may make, for example, the contrast in the plurality of images more pronounced (e.g., enhanced-contrast levels differentiating the liquid from other components in or proximate to the liquid, such as portions of the images related to foam and bubbles). In addition to or instead of increasing the contrast from the images, the pre-processing may, for example, increase a level of edge detection between the liquid and other components in or proximate to the liquid, thereby differentiating the liquid from the other components in the liquid. Overall, the pre-processing can aid in detecting and analyzing a level of the liquid as described herein by one or more of increasing the contrast of the components of the liquid within the plurality of images and increasing the edge detection of the components of the liquid within the plurality of images. Each of the contrast-enhancing and edge-detection operations can also occur within a machine-learning network as described with reference to FIG. 5B, below.

[0061] FIG. 5B shows an example of a framework 550 to analyze images of liquid-levels in a container based on images obtained from the liquid-level-detection and analyzing systems 100, 200 of FIG. 1A and FIG. 2, in accordance with various embodiments of the disclosed subject matter. As described above, the framework 550 may be used in a training mode to train the machine-learning network and may then be used in normal-operation mode to determine and analyze a level of a liquid in a fabrication or other type of environment in which a determination of liquid levels may be useful.

[0062] As shown in FIG. 5B, the framework 550 is shown to include a preprocessor 553 and a machine-learning network 570. A raw image 551 (or multiple images) is provided to the preprocessor 553. In this example, the preprocessor 553 filters or otherwise processes the raw image 551 to, for example, crop, scale, or otherwiseAttorney Docket 4948.163WO1 / Client File 11586-1WO change or enhance the raw image 551 and to generate a preprocessed image 555, as described above with reference to FIG. 5A.

[0063] The preprocessed image 555 may then be input into the machine-learning network 570. The machine-learning network 570 may be provided as a multi-layered machine-learning model. For example, in one embodiment, the machine-learning network 570 may include four layers including an input layer 571, a feature-extraction layer 573, a features-relationship layer 575, and a decision layer 577. In embodiments, only a portion of the four layers is used. In various types of machine-learning network types, the feature-extraction layer 573 and the features-relationship layer 575 may be referred to as hidden layers.

[0064] Pixel-based information from the preprocessed image 555 may be sent to the input layer 571. Each node in the input layer 571 may correspond to a pixel of the preprocessed image 555. The machine-learning network 570 may, in an iterative fashion, be trained in one or more of the layers 571, 573, 575, 577. The decision layer 577 may output a decision regarding a level of a given liquid based on information from the pixel-based information. A liquid-level determination result 557 is then generated. The liquid-level determination result 557 may provide a textual indication or value to an operator of one or more of the liquid-level-detection and analyzing systems 100, 200 described herein. In an embodiment, the liquid-level determination result 557 may be input as a command to direct replenishment or refilling of a liquid container along with a prompt to halt a given processing operation. In an embodiment, the liquid-level determination result 557 may stop replenishment of the container from receiving a further replenishment of liquid from a bulk supply.

[0065] As mentioned above, the framework 550 may first be used in a training mode to train the machine-learning network 570 to determine a level of liquid in a container. The framework 550 mayAttorney Docket 4948.163WO1 / Client File 11586-1WO then be used in a normal-operation mode to determine levels in a fabrication or other environment in which a knowledge of liquid levels is useful. In other embodiments, the framework 550 may be used directly in a normal-operation mode to determine liquid levels in a fabrication or other environment. The training of the machine- learning network 570 may be a supervised process and may be performed offsite from where the liquid-determination process is performed. The training may use a set of training images (e.g., one or more training images) with known liquid levels to train the machine- learning network 570.

[0066] In various embodiments, any one or more of the preprocessor 553 or one or more of the layers 571, 573, 575, 577 may include feature extraction techniques to remove noise, irrelevant features (e.g., portions of the images related bubbles and foam), or other features that tend to obscure the actual level of the liquid. Any one or more of these components may therefore be referred to as an analysis engine. Further, any one or more of these components may be used along with, or in addition to, the similar or same components discussed above with reference to FIG. 5A.

[0067] The techniques shown and described herein can be performed using a portion or an entirety of at least one of the liquid- level-detection and analyzing systems 100, 200 of FIG. 1A and FIG. 2, or otherwise using a machine 600 as discussed below in relation to FIG. 6.

[0068] FIG. 6 shows an exemplary block diagram comprising a machine 600 upon which any one or more of the techniques (e.g., methods, analysis, or methodologies) discussed herein may be performed herein may be performed. In various examples, the machine 600 may operate as a standalone device or may be connected (e.g., networked) to other machines. In a networked deployment, the machine 600 may operate in the capacity of a server machine, a clientAttorney Docket 4948.163WO1 / Client File 11586-1WO machine, or both in server-client network environments. In an example, the machine 600 may act as a peer machine in peer-to-peer (P2P) (or other distributed) network environment. The machine 600 may be a personal computer (PC), a tablet device, a set-top box (STB), a personal digital assistant (PDA), a mobile telephone, a web appliance, a network router, switch or bridge, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while only a single machine is illustrated, the term ^machine^ shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein, such as cloud computing, software as a service (SaaS), other computer cluster configurations.

[0069] Examples, as described herein, may include, or may operate by, logic or a number of components, or mechanisms. Circuitry is a collection of circuits implemented in tangible entities that include hardware (e.g., simple circuits, gates, logic, etc.). Circuitry membership may be flexible over time and underlying hardware variability. Circuitries include members that may, alone or in combination, perform specified operations when operating. In an example, hardware of the circuitry may be immutably designed to carry out a specific operation (e.g., hardwired). In an example, the hardware comprising the circuitry may include variably connected physical components (e.g., execution units, transistors, simple circuits, etc.) including a computer-readable medium physically modified (e.g., magnetically, electrically, such as via a change in physical state or transformation of another physical characteristic, etc.) to encode instructions of the specific operation. In connecting the physical components, the underlying electrical properties of a hardware constituent may be changed, for example, from an insulating characteristic to a conductive characteristic or vice versa. The instructions enable embedded hardware (e.g., the execution unitsAttorney Docket 4948.163WO1 / Client File 11586-1WO or a loading mechanism) to create members of the circuitry in hardware via the variable connections to carry out portions of the specific operation when in operation. Accordingly, the computer- readable medium is communicatively coupled to the other components of the circuitry when the device is operating. In an example, any of the physical components may be used in more than one member of more than one circuitry. For example, under operation, execution units may be used in a first circuit of a first circuitry at one point in time and reused by a second circuit in the first circuitry, or by a third circuit in a second circuitry at a different time.

[0070] The machine 600 (e.g., computer system) may include a hardware processor 601 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), a main memory 603 and a static memory 605, some or all of which may communicate with each other via an interlink 630 (e.g., a bus). The machine 600 may further include a display device 609, an input device 611 (e.g., an alphanumeric keyboard), and a user interface (UI) navigation device 613 (e.g., a mouse). In an example, the display device 609, the input device 611, and the UI navigation device 613 may comprise at least portions of a touch screen display. The machine 600 may additionally include a storage device 620 (e.g., a drive unit), a signal generation device 617 (e.g., a speaker), a network interface device 650, and one or more sensors 615, such as a global positioning system (GPS) sensor, compass, accelerometer, or other type of sensor. The machine 600 may include an output controller 619, such as a serial controller or interface (e.g., a universal serial bus (USB)), a parallel controller or interface, or other wired or wireless (e.g., infrared (IR) controllers or interfaces, near field communication (NFC), etc., coupled to communicate or control one or more peripheral devices (e.g., a printer, a card reader, etc.).Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0071] The storage device 620 may include a machine-readable medium on which is stored one or more sets of data structures or instructions 624 (e.g., software or firmware) embodying or utilized by any one or more of the techniques or functions described herein. The instructions 624 may also reside, completely or at least partially, within a main memory 603, within a static memory 605, within a mass storage device 607, or within the hardware-based processor 601 during execution thereof by the machine 600. In an example, one or any combination of the hardware-based processor 601, the main memory 603, the static memory 605, or the storage device 620 may constitute machine readable media.

[0072] While the machine-readable medium is considered as a single medium, the term ^machine-readable medium^ may include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) configured to store the one or more instructions 624.

[0073] The term ^machine-readable medium^ may include any medium that is capable of storing, encoding, or carrying instructions for execution by the machine 600 and that cause the machine 600 to perform any one or more of the techniques of the present disclosure, or that is capable of storing, encoding or carrying data structures used by or associated with such instructions. Non-limiting machine- readable medium examples may include solid-state memories, and optical and magnetic media. Accordingly, machine-readable media are not transitory propagating signals. Specific examples of massed machine-readable media may include: non-volatile memory, such as semiconductor memory devices (e.g., Electrically Programmable Read- Only Memory (EPROM), Electrically Erasable Programmable Read- Only Memory (EEPROM)) and flash memory devices; magnetic or other phase-change or state-change memory circuits; magnetic disks,Attorney Docket 4948.163WO1 / Client File 11586-1WO such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.

[0074] The instructions 624 may further be transmitted or received over a communications network 621 using a transmission medium via the network interface device 650 utilizing any one of a number of transfer protocols (e.g., frame relay, internet protocol (IP), transmission control protocol (TCP), user datagram protocol (UDP), hypertext transfer protocol (HTTP), etc.). Example communication networks may include a local area network (LAN), a wide area network (WAN), a packet data network (e.g., the Internet), mobile telephone networks (e.g., cellular networks), Plain Old Telephone (POTS) networks, and wireless data networks (e.g., the Institute of Electrical and Electronics Engineers (IEEE) 802.22 family of standards known as Wi-Fi®, the IEEE 802.26 family of standards known as WiMax®), the IEEE 802.25.4 family of standards, peer-to- peer (P2P) networks, among others. In an example, the network interface device 650 may include one or more physical jacks (e.g., Ethernet, coaxial, or phone jacks) or one or more antennas to connect to the communications network 621. In an example, the network interface device 650 may include a plurality of antennas to wirelessly communicate using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) techniques. The term ^transmission medium^ shall be taken to include any intangible medium that is capable of storing, encoding or carrying instructions for execution by the machine 600, and includes digital or analog communications signals or other intangible medium to facilitate communication of such software.

[0075] Although described as a liquid-level-detection and analyzing system for use within a semiconductor fabrication environment, the disclosed subject-matter contained herein describes or relatesAttorney Docket 4948.163WO1 / Client File 11586-1WO generally to any type of environment in which an accurate and precise determination of a level of a liquid within a liquid container may be desired. For example, the disclosed subject-matter can be used in a number of machine-tool environments such as manufacturing and machining environments (e.g., including those operations using, for example, physical vapor deposition (PVD tools)), as well as a variety of other environments. Upon reading and understanding the disclosure provided herein, a person of ordinary skill in the art will recognize that various embodiments of the disclosed subject-matter may be used with other types of process tools as well as a wide variety of other tools, equipment, and components.

[0076] As used herein, the term ^or^ may be construed in an inclusive or exclusive sense. Further, other embodiments will be understood by a person of ordinary skill in the art upon reading and understanding the disclosure provided. Further, upon reading and understanding the disclosure provided herein, the person of ordinary skill in the art will readily understand that various combinations of the techniques and examples provided herein may all be applied in various configurations.

[0077] Although various embodiments are discussed separately, these separate embodiments are not intended to be considered as independent techniques or designs. As indicated above, each of the various portions may be inter-related and each may be used separately or in combination with other embodiments discussed herein. For example, although various embodiments of methods, operations, and processes have been described, these methods, operations, and processes may be used either separately or in various combinations.

[0078] Consequently, many modifications and variations can be made, as will be apparent to a person of ordinary skill in the art upon reading and understanding the disclosure provided herein. Further,Attorney Docket 4948.163WO1 / Client File 11586-1WO functionally equivalent methods and devices within the scope of the disclosure, in addition to those enumerated herein, will be apparent to the skilled artisan from the foregoing descriptions. Portions and features of some embodiments, materials, and construction techniques may be included in, or substituted for, those of others. Such modifications and variations are intended to fall within a scope of the appended claims. Therefore, the present disclosure is to be limited only by the terms of the appended claims, along with the full scope of equivalents to which such claims are entitled. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.

[0079] The Abstract of the Disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. The abstract is submitted with the understanding that it will not be used to interpret or limit the claims. In addition, in the foregoing Detailed Description, it may be seen that various features may be grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as limiting the claims. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment. As used herein, the terms ^about,^ ^approximately,^ and ^substantially^ may refer to values that are, for example, within +10% of a given value or range of values. Also, the term ^exemplary^ is used herein to indicate an example of an embodiment or concept, and not necessarily the best or sole means of achieving or practicing the embodiment or concept.Attorney Docket 4948.163WO1 / Client File 11586-1WO THE FOLLOWING NUMBERED EXAMPLES ARE SPECIFIC EMBODIMENTS OF THE DISCLOSED SUBJECT-MATTER

[0080] In an embodiment, the disclosed subject-matter is a method for determining a level of a liquid in a container. The method includes capturing multiple images of the liquid within the container and analyzing the multiple images to generate a liquid-level determination result. The analyzing includes differentiating components of the liquid including at least one component selected from components of foam and bubbles within the liquid. The analyzing further including at least one operation selected from operations of increasing the contrast of the components of the liquid within the multiple images and increasing the edge detection of the components of the liquid within the multiple of images.

[0081] Example 2. The method of Example 1, further including making a determination as to whether a pre-determined level of the liquid has been reached. Based on the determination that the pre- determined level of the liquid has been reached; updating a level indicator, and, based on the determination that the pre-determined level of the liquid has not been reached, performing the method again.

[0082] Example 3. The method of Example 2, further including replenishing the liquid within the container based on the determination that the pre-determined level of the liquid has been reached.

[0083] Example 4. The method of Example 2, further including stopping a supply of the liquid from a bulk supply of the liquid from filling the container to prevent possible overfill of the container based on the determination that the pre-determined level of the liquid has been reached.

[0084] Example 5. The method of any one of the preceding Examples, further including transferring the multiple images to a pre-trained deep-convolutional neural-network.Attorney Docket 4948.163WO1 / Client File 11586-1WO

[0085] Example 6. The method of Example 5, wherein the analyzing of the pixel-based information from the multiple images to perform operations to differentiate components of the liquid occurs within the pre-trained deep-convolutional neural-network.

[0086] Example 7. The method of any one of the preceding Examples, further including illuminating the liquid within the container prior to and while capturing the multiple images of the liquid within the container.

[0087] Example 8. The method of Example 7, further including selecting a wavelength of light used to illuminate the liquid.

[0088] Example 9. The method of any one of the preceding Examples, further including transferring the multiple images to an analysis engine to apply at least one transformation algorithm to produce a pre-processed image, the pre-processed image including pixel-based information related to the multiple images; and analyzing the pixel-based information from the multiple images to perform operations to further differentiate components of the liquid including at least one component selected from components of foam and bubbles within the liquid.

[0089] Example 10. In an embodiment, the disclosed subject- matter is a system to determine a level of a liquid within a container, the system including at least one imaging device to capture a multiple images of the liquid within the container and an analysis engine. The analysis engine includes one or more hardware-based processors of a machine coupled to the at least one imaging device to apply at least one transformation algorithm to produce a pre-processed image, where the pre-processed image includes pixel-based information related to the multiple images. The analysis engine is further configured to analyze the pixel-based information from the multiple images to perform operations to differentiate components of the liquidAttorney Docket 4948.163WO1 / Client File 11586-1WO including at least one component selected from foam and bubbles within the liquid; the analyzing further including at least one operation selected from operations of increasing the contrast of the components of the liquid within the multiple images and increasing the edge detection of the components of the liquid within the multiple images.

[0090] Example 11. The system of Example 10, wherein the at least one imaging device comprises a still-mage camera.

[0091] Example 12. The system of Example 10, wherein the at least one imaging device comprises a video camera.

[0092] Example 13. The system of any one of Example 10 through Example 12, further including forming at least one type of window selected from a top-mounted window, a corner-mounted window, and a side-mounted window into the container.

[0093] Example 14. The system of Example 13, wherein the at least one type of window is selected to withstand a temperature of the liquid.

[0094] Example 15. The system of Example 14, wherein the at least one type of window is selected to withstand a pressure of the liquid.

[0095] Example 16. The system of any one of Example 10 through Example 15, wherein the at least one imaging device includes an illumination source.

[0096] Example 17. The system of Example 16, wherein a wavelength of light used to illuminate the liquid is selectable.

[0097] Example 18. The system of any one of Example 10 through Example 17, further including an illumination source. The at least one imaging device is configured to capture the multiple images of theAttorney Docket 4948.163WO1 / Client File 11586-1WO liquid within the container based on the liquid being illuminated by the illumination source.

[0098] Example 19. The system of any one of Example 10 through Example 18, wherein the at least one imaging device is optically coupled to the container by at least one optical fiber.

[0099] Example 20. The system of any one of Example 10 through Example 19, wherein the data-collection and control system includes a deep-convolutional neural-network. [000100] Example 21. In an embodiment, the disclosed subject- matter is a computer-readable medium containing instructions that, when executed by a machine, cause the machine to perform operations for determining a level of a liquid in a container. The operations include capturing multiple images of the liquid within the container and analyzing the multiple images to generate a liquid-level determination result. The analyzing includes transferring the multiple images to a preprocessor to apply at least one transformation algorithm to produce a pre-processed image, the pre-processed image including pixel-based information related to the multiple images. The method further includes analyzing the pixel-based information from the multiple images to perform operations to differentiate components of the liquid including at least one component of foam and bubbles within the liquid. The analyzing includes at least one operation selected from increasing the contrast of the components of the liquid within the multiple images and increasing the edge detection of the components of the liquid within the multiple images. [000101] Example 22. The computer-readable medium of Example 21, further including transferring the plurality of images to an analyzing engine to apply at least one transformation algorithm to produce a pre-processed image, the pre-processed image including pixel-based information related to the plurality of images; and analyzing theAttorney Docket 4948.163WO1 / Client File 11586-1WO pixel-based information from the plurality of images to perform operations to further differentiate components of the liquid including at least one component selected from components of foam and bubbles within the liquid.

Claims

Attorney Docket 4948.163WO1 / Client File 11586-1WO CLAIMS What is claimed is:

1. A method for determining a level of a liquid in a container, the method comprising: capturing a plurality of images of the liquid within the container; and analyzing the plurality of images to generate a liquid-level determination result, the analyzing including differentiating components of the liquid including at least one component selected from components of foam and bubbles within the liquid, the analyzing further including at least one operation selected from operations of increasing the contrast of the components of the liquid within the plurality of images and increasing the edge detection of the components of the liquid within the plurality of images.

2. The method of claim 1, further comprising: making a determination as to whether a pre-determined level of the liquid has been reached; and based on the determination that the pre-determined level of the liquid has been reached; updating a level indicator; and based on the determination that the pre-determined level of the liquid has not been reached, performing the method again.

3. The method of claim 2, further comprising replenishing the liquid within the container based on the determination that the pre- determined level of the liquid has been reached.Attorney Docket 4948.163WO1 / Client File 11586-1WO 4. The method of claim 2, further comprising stopping a supply of the liquid from a bulk supply of the liquid from filling the container to prevent possible overfill of the container based on the determination that the pre-determined level of the liquid has been reached.

5. The method of claim 1, further comprising transferring the plurality of images to a pre-trained deep-convolutional neural- network.

6. The method of claim 5, wherein the analyzing of the pixel-based information from the plurality of images to perform operations to differentiate components of the liquid occurs within the pre- trained deep-convolutional neural-network.

7. The method of claim 1, further comprising illuminating the liquid within the container prior to and while capturing the plurality of images of the liquid within the container.

8. The method of claim 7, further comprising selecting a wavelength of light used to illuminate the liquid.

9. The method of claim 1, further comprising: transferring the plurality of images to an analysis engine to apply at least one transformation algorithm to produce a pre-processed image, the pre-processed image including pixel-based information related to the plurality of images; and analyzing the pixel-based information from the plurality of images to perform operations to further differentiate components of the liquid including at least one component selected from components of foam and bubbles within the liquid.Attorney Docket 4948.163WO1 / Client File 11586-1WO 10. A system to determine a level of a liquid within a container, the system comprising: at least one imaging device to capture a plurality of images of the liquid within the container; and an analysis engine, including one or more hardware-based processors of a machine coupled to the at least one imaging device, the analysis engine to apply at least one transformation algorithm to produce a pre-processed image, the pre-processed image including pixel-based information related to the plurality of images, the analysis engine further to analyze the pixel-based information from the plurality of images to perform operations to differentiate components of the liquid including components selected from at least one component of foam and bubbles within the liquid, the analyzing further including at least one operation selected from operations of increasing the contrast of the components of the liquid within the plurality of images and increasing the edge detection of the components of the liquid within the plurality of images.

11. The system of claim 10, wherein the at least one imaging device comprises a still-mage camera.

12. The system of claim 10, wherein the at least one imaging device comprises a video camera.

13. The system of claim 10, further comprising forming at least one type of window selected from a top-mounted window, a corner- mounted window, and a side-mounted window into the container.Attorney Docket 4948.163WO1 / Client File 11586-1WO 14. The system of claim 13, wherein the at least one type of window is selected to withstand a temperature of the liquid.

15. The system of claim 13, wherein the at least one type of window is selected to withstand a pressure of the liquid.

16. The system of claim 10, wherein the at least one imaging device includes an illumination source.

17. The system of claim 16, wherein a wavelength of light used to illuminate the liquid is selectable.

18. The system of claim 10, further comprising an illumination source, the at least one imaging device being configured to capture the plurality of images of the liquid within the container based on the liquid being illuminated by the illumination source.

19. The system of claim 10, wherein the at least one imaging device is optically coupled to the container by at least one optical fiber.

20. The system of claim 10, wherein the data-collection and control system includes a deep-convolutional neural-network.Attorney Docket 4948.163WO1 / Client File 11586-1WO 21. A computer-readable medium containing instructions that, when executed by a machine, cause the machine to perform operations for determining a level of a liquid in a container, the operations comprising: capturing a plurality of images of the liquid within the container; and analyzing the plurality of images to generate a liquid-level determination result, the analyzing including differentiating components of the liquid including at least one component of foam and bubbles within the liquid, the analyzing further including at least one operation selected from operations including increasing the contrast of the components of the liquid within the plurality of images and increasing the edge detection of the components of the liquid within the plurality of images.

22. The computer-readable medium of claim 21, further comprising: transferring the plurality of images to an analyzing engine to apply at least one transformation algorithm to produce a pre-processed image, the pre-processed image including pixel-based information related to the plurality of images; and analyzing the pixel-based information from the plurality of images to perform operations to further differentiate components of the liquid including at least one component selected from components of foam and bubbles within the liquid.

Images