Monitoring the volume of liquid in a container

Abstract

A system for monitoring liquid volume includes a processing circuit. The processing circuit inputs at least one image of liquid contained within a container from one or more optical sensors. The volume of liquid within the container is estimated from the input image(s). The estimated liquid volume is analyzed to determine whether it matches an expected liquid volume. The analysis can be based on a single estimated liquid volume or multiple liquid volumes (e.g., liquid volumes estimated from images captured at different times). An indicator is output based on the results of the analysis.

Description

[Technical Field]

[0001] The present disclosure, in some embodiments thereof, relates to monitoring the volume of a liquid, and more particularly, but not exclusively, to monitoring the volume of a liquid in a container. [Background technology]

[0002] Accurately measuring the amount of liquid in a container, such as a fuel tank, oil tank, water tank, storage tank, etc., is required in many industries. Proper estimation of liquid volume can be very important, for example, in vehicles, aircraft, and machinery, where an incorrect liquid level can lead to immediate or future failure. The need for accurate monitoring of liquid volume spans many industries, such as chemical plants, the pharmaceutical industry, and water purification plants.

[0003] Due to the difficulty of accurately estimating liquid volume, industrial maintenance is typically based on other factors. For example, industrial maintenance may be performed periodically at set time intervals (scheduled maintenance), based on statistical and / or historical data, based on certain usage levels (e.g., mileage or engine operating hours), or upon machine, part, or component failure (reactive maintenance). This type of maintenance is often wasteful and inefficient.

[0004] Monitoring liquid volume is particularly difficult when the container is in motion. The movement can cause the liquid surface to tilt, form bubbles and waves, or change rapidly, making conventional techniques for assessing the liquid surface inaccurate.

[0005] Therefore, there is a need for a system that provides constant monitoring of the liquid volume to provide an accurate measurement of the amount of liquid present in a container. Summary of the Invention [Means for solving the problem]

[0006] According to some embodiments, a system, method, and computer program product are provided for detecting a volume of liquid (also referred to herein as liquid volume) in a container.

[0007] Embodiments of the invention presented herein utilize image analysis to estimate the volume of liquid in a container. Images are provided by one or more optical sensors that capture images of respective portions of the container through which liquid may be visible. Portions of the images that indicate the presence of liquid in the container are used to estimate the volume of liquid in the container. Estimation of the liquid volume may be performed by geometric analysis based on the dimensions of the container and / or using a model of the container.

[0008] Information about liquid volume is crucial for predictive maintenance systems, such as prognostic health management (PHM), condition-based maintenance (CBM), and health and utilization management systems (HUMS). Unexpected changes in liquid volume can indicate improper operation of the vessel itself and / or elements associated with the vessel. For example, fuel consumption for a particular aircraft flight may be expected to be within a certain range. If the change in liquid volume is greater than the expected range, this may indicate a leak in the fuel system, which could be extremely dangerous. In another example, a slow decrease in liquid volume may indicate possible deterioration of a gasket or tube that should be inspected at the next scheduled maintenance. In another example, an inconsistent increase in liquid volume may indicate an obstruction in the liquid flow path.

[0009] As used herein, in accordance with some embodiments of the present invention, the terms "element associated with a vessel" and "associated element" refer to any element whose performance and / or health is affected by the liquid volume. Examples of such elements may include, but are not limited to, peripheral components, machines, vehicles, mechanisms, and / or other types of systems not explicitly listed herein.

[0010] As used herein, in accordance with some embodiments of the present invention, the terms "volume of liquid in a container" and "liquid volume" refer to the volume of liquid in a container. In some cases, there is knowledge of the volume of liquid that is in the system but not currently in the container. In such cases, the total liquid volume can be calculated as the sum of the two volumes (or by another calculation).

[0011] Embodiments of the present invention provide a technical solution to the technical problem of estimating the volume of liquid in a container. Liquid volume can be estimated using image analysis, thereby achieving greater accuracy than current mechanical liquid measurement techniques, such as the use of floats. Accurately monitoring liquid volume over time can enable faults to be identified and / or predicted before they become serious. Thus, the occurrence of such faults can be avoided through predictive maintenance.

[0012] The advantages of the present invention may include, but are not limited to: 1) Rapid detection of critical faults; 2) preventative and predictive maintenance can be based on the progression of fluid volume values over time; 3) Suitable for monitoring many types of systems and equipment, including manufacturing machinery, vehicles, aircraft, climate control systems, laboratory equipment and many more. 4) It can be used in a wide range of environmental conditions (eg, over a wide temperature range). 5) Suitable for use during movement and when subjected to forces that can cause sudden changes in the liquid and liquid surface, such as vibration, shaking and splashing. 6) Real-time detection of liquid volume during machine operation and thereby providing real-time preventative and predictive maintenance of the machine during its operation. 7) Allows for measurement of liquid volume by placing optical sensor(s) within or within view of a vessel that may not otherwise be monitored, in otherwise inaccessible areas that may require a high level of effort to inspect / maintain.

[0013] According to a first aspect of some embodiments of the present invention, there is provided a system for monitoring a liquid volume, the system comprising: acquiring at least one image of a liquid contained within the container from at least one optical sensor; estimating a volume of liquid in the container from the at least one image; and outputting an indication of the agreement of the estimated liquid volume with the expected liquid volume based on an analysis of the estimated volume of liquid; The processing circuitry is configured to:

[0014] According to a second aspect of some embodiments of the present invention, there is provided a method for monitoring a liquid volume, comprising: acquiring at least one image of a liquid contained within the container from at least one optical sensor; estimating a volume of liquid in the container from the at least one image; and outputting an indication of the agreement of the estimated liquid volume with the expected liquid volume based on an analysis of the estimated volume of liquid; Includes:

[0015] According to a third aspect of some embodiments of the present invention there is provided a non-transitory storage medium storing program instructions which, when executed by a processor, cause the processor to perform the method of the second aspect.

[0016] According to some embodiments of the present invention, the images are input from multiple optical sensors capturing images of the container in respective fields of view.

[0017] According to some embodiments of the invention, the indicators include an assessment of the health of at least one of the following: a) Container; b) Machines that utilize liquids; c) Vehicles utilizing liquids; d) Liquid-based mechanisms; e) Heating, ventilation and air conditioning (HVAC) systems; and f) Peripheral components.

[0018] According to some embodiments of the invention, the indicator includes at least one of the following: a) Estimated liquid volume; b) the rate of change of liquid volume over time; c) prediction of future liquid volume; d) at least one of the frequency and amplitude of the liquid wave motion in the container; e) color change of the liquid; f) Change in the opacity of the liquid; g) Change in the transparency of the liquid; h) Change in viscosity of the liquid; i) the presence of particles in the liquid; j) maintenance instructions; k) time to failure estimation; l) fault alerts; and m) Operational instructions in response to detected faults.

[0019] According to some embodiments of the invention, estimating includes analyzing a distribution of intensities in at least one channel of at least one image and identifying pixels having a distribution consistent with the presence of liquid.

[0020] According to some embodiments of the present invention, estimating comprises excluding pixels that are away from the main volume of liquid from the calculation of the liquid volume.

[0021] According to some embodiments of the invention, the estimating comprises calculating the liquid volume based on a geometric analysis of the container shape.

[0022] According to some embodiments of the present invention, the estimating is based on a statistical analysis of the sequence of images.

[0023] According to some embodiments of the present invention, the estimating is further based on data obtained from a non-optical sensor.

[0024] According to some embodiments of the present invention, the estimating is further based on data obtained from an external source.

[0025] According to some embodiments of the present invention, the selection of the indicator for output is based on the current liquid volume.

[0026] According to some embodiments of the present invention, the analysis is based on changes in liquid volume over time.

[0027] According to some embodiments of the present invention, the analysis is based on a trend analysis of changes in liquid volume over time.

[0028] According to some embodiments of the present invention, the at least one image shows at least two sides of the container.

[0029] According to some embodiments of the present invention, at least one image shows a portion of the container, the portion being wide enough to estimate the three-dimensional angle of the liquid relative to the container.

[0030] According to some embodiments of the invention, the at least one optical sensor is configured to capture at least one image while the container is moving relative to the ground.

[0031] According to some embodiments of the present invention, the at least one optical sensor is located external to the container.

[0032] According to some embodiments of the present invention, the at least one optical sensor is disposed inside the container.

[0033] According to some embodiments of the present invention, the index is obtained from the data structure using at least one of the following values: a) Estimated liquid volume; b) the rate of change of liquid volume over time; c) prediction of future liquid volume; and d) Prediction of variation in the rate of change of liquid volume over time.

[0034] According to some embodiments of the invention, the analysis is based on a machine learning model trained on a training set comprising at least one of the following: a) Images collected during periods of non-use of liquid; b) Images of similar containers collected during the period of use; c) Images of similar containers collected during periods of non-use; d) Images of different containers in similar machines collected during the period of use; e) Images of different containers in similar machines collected during periods of non-use; f) Images of other components; and g) Non-image data associated with some or all of the images in the training set.

[0035] According to some embodiments of the present invention, the machine learning model is a neural network.

[0036] According to some embodiments of the present invention, training of the machine learning model is performed using a supervised learning algorithm.

[0037] According to some embodiments of the present invention, training of the machine learning model is performed using an unsupervised learning algorithm.

[0038] According to some embodiments of the present invention, the training set includes non-image data associated with at least some of the images in the training set.

[0039] According to a fourth aspect of some embodiments of the present invention, there is provided a system and method for monitoring a volume of liquid and / or a change in the volume of liquid in a container and / or a rate of change of the volume of liquid in a container.

[0040] Optionally, the system includes an optical sensor, which according to some embodiments may be a camera.

[0041] According to some embodiments, the container may be in motion, for example, if the container is being carried by a moving vehicle or aircraft.

[0042] According to some embodiments of the present invention, there is provided a system for monitoring a volume of a liquid and / or a change in the volume of a liquid in a container, the system comprising: one or more optical sensors that may be configured to monitor the surface and / or contour of the liquid within the container; and at least one processor in communication with the one or more optical sensors; may include:

[0043] The processor receiving one or more signals from the optical sensor(s), the received one or more signals including at least a portion of a surface of the liquid and at least a surrounding portion of a perimeter of the container; and estimating the volume and / or change in volume of the liquid in the container based on at least the image(s) and one or more known parameters characterizing the container and / or the liquid; The method may be configured to perform the following.

[0044] According to some embodiments, at least one of the one or more optical sensors is disposed external to the container. Optionally, at least a portion of the container is at least partially transparent to the optical sensor(s). Optionally, the liquid is optically distinguishable from the container in the image(s). Optionally, the container includes at least one window.

[0045] Optionally, at least one of the optical sensor(s) is positioned in a respective field of view from the liquid surface. Optionally, the field of view is through at least one window.

[0046] Optionally, at least one of the optical sensor(s) is disposed inside the container. Optionally, at least one of the optical sensor(s) is mounted on an interior surface of the container. Optionally, at least a portion of the interior surface of the container is a lens of the optical sensor.

[0047] Optionally, at least one of the optical sensor(s) is at least partially immersed in the liquid.

[0048] According to some embodiments, the container includes a primary container and one or more secondary containers that may be in fluid communication with each other. Optionally, optical sensor(s) may be positioned in respective fields of view from the liquid surface of the secondary containers.

[0049] According to some embodiments, the processor may be further configured to calculate a change in the level of the liquid surface. Optionally, the processor may be further configured to calculate a rate of change of the level of the liquid surface.

[0050] According to some embodiments, the processor may be configured to receive parameters characterizing the motion of the vehicle, machine, and / or mechanism. Optionally, the processor may take the motion parameters into account when estimating the volume and / or change in volume of the liquid. Optionally, the processor may be in communication with one or more motion-related sensors. Optionally, the motion parameters are received from the motion sensors. Optionally, the one or more motion-related sensors may include an accelerometer, a navigation system (e.g., GPS), a gyroscope, a magnetometer, a magnetic compass, a Hall sensor, or a tilt sensor, an inclinometer, or a spirit level.

[0051] According to some embodiments, the container may be disposed within a vehicle, machine, and / or mechanism configured for motion. Optionally, the motion may be linear, rotational, or a combination thereof. According to some embodiments, the processor may be configured to direct the optical sensor(s) to acquire the image(s) based on an indication that the vehicle is moving at a constant speed and / or in a straight and level motion.

[0052] According to some embodiments, the optical sensor(s) may include a camera. Optional types of optical sensors include, but are not limited to, a charge-coupled device (CCD), a light-emitting diode (LED), and / or a complementary metal-oxide semiconductor (CMOS) sensor. Optionally, the optical sensor(s) include one or more lenses, optical fibers, or a combination thereof.

[0053] Optionally, the one or more images may include a portion of an image, a set of images, one or more video frames, or any combination thereof. Optionally, the system may include at least one illumination source configured to illuminate the container or portion thereof.

[0054] According to some embodiments, the one or more known parameters characterizing the container and / or liquid may include the shape and dimensions of the container, the graduations, the expected flow rate of the liquid into or out of the container, the period of operation since the container was last filled, the liquid type, the liquid viscosity, the liquid color, the ambient temperature and / or the pressure.

[0055] It should be noted that some parameters characterizing the container and / or liquid may vary based on environmental conditions and / or other factors. For example, liquid viscosity is affected by temperature. Thus, data from a thermal sensor in or near the liquid may improve the accuracy of the liquid volume determination when viscosity is one of the parameters used to make the determination.

[0056] According to some embodiments, determining the volume and / or change in volume of the liquid in the container comprises: receiving one or more signals from at least one optical sensor that may be configured to monitor a surface of the liquid in the container and at least a surrounding portion of the periphery of the container, wherein the received signal may be at least one image including at least three different dimensions that may allow for definition of a relative liquid level between the container and the liquid; Neutralizing plane angle and / or acceleration effects using a liquid level defined relative to a horizontal plane of the container and one or more known parameters characterizing the container, which may include the dimensions of the container, the scale number, or both; may include:

[0057] Thereby, the volume of liquid and / or changes in the volume of liquid in a container located in a moving vehicle, machine and / or mechanism may be estimated.

[0058] According to some embodiments, the processor may be further configured to apply an algorithm configured to classify whether the estimated volume of liquid and / or change in volume of liquid in the container conforms to a pre-calculated expected liquid volume and / or change in volume that may be associated with a particular time point or level of use, and output a signal indicative of any deviation therefrom.

[0059] According to some embodiments, the processor may be further configured to apply at least one determined change to the estimated volume of liquid in the container and / or a change in the volume of the liquid to an algorithm. The algorithm may analyze the determined change to classify whether the determined change may be associated with a failure mode of the container or the vehicle containing the container. If so, the identified change is labeled as a detected fault. Optionally, for a determined change classified as associated with a failure mode, a signal indicative of the determined change associated with the failure mode is output.

[0060] As used herein, according to some embodiments, the term "fault" may refer to an abnormality or undesirable effect or process in a vessel and / or liquid and / or associated elements that may or may not escalate into a failure but requires follow-up to analyze whether any components should be repaired or replaced. According to some embodiments, faults may include, among others, structural deformation, surface deformation, cracks, crack propagation, defects, swelling, bending, wear, corrosion, leaks, discoloration, appearance changes, and the like, or any combination thereof.

[0061] As used herein, according to some embodiments of the present invention, the term "failure" may refer to any problem that may cause the container and / or liquid and / or associated components to not operate as intended. In some cases, the failure may render the container and / or liquid and / or associated components unavailable or may even pose a danger to the associated components or users.

[0062] As used herein, according to some embodiments of the present invention, the term "failure mode" should be interpreted broadly to encompass any manner in which a fault or failure may occur, such as structural deformation, surface deformation, cracks, crack propagation, defects, swelling, bending, wear, corrosion, leaks, discoloration, appearance changes, shaking, bubbles in liquids, and the like, or any combination thereof. It is understood that a component may be subject to multiple failure modes related to different properties or its functionality.

[0063] Some failure modes may be common to different element types, while others may be more specific to one or more element types. For example, a crack may be associated with the vessel, while a bend may be associated with a connecting pipe, or a corrosion failure mode may be associated with an aluminum component of the system.

[0064] For example, a failure mode of a liquid in a container according to an embodiment of the present invention may involve a change in liquid level. A fault may be a small change in the expected liquid level, i.e., a change of about 10 ml, and a breakdown would be a drastic change in the expected liquid level, such as a change of 1.5 liters.

[0065] According to some embodiments, a failure mode refers to the scale / range evolving between a fault and an actual failure, i.e., the state of a detected change varying from a fault to an actual failure (initially, a detected change is defined / determined as a fault). According to some embodiments, a failure mode may include, among other things, a detectable (e.g., revealed) visual indicator of failure.

[0066] Optionally, for the detected faults, at least one model of a trend of the identified fault is generated. Optionally, the trend model may include a rate of change of the fault.

[0067] Optionally, the processor may be further configured to alert a user of a predicted failure based at least in part on the generated model. Optionally, alerting a user of a predicted failure may include any one or more of a time or time range of the predicted failure, age of the element and characteristics of the mode of failure, or any combination thereof.

[0068] According to some embodiments, the processor may be further configured to output a prediction of when the detected fault is likely to lead to a failure of the vessel or a vehicle including the vessel based at least in part on the generated model. Optionally, the prediction of when a failure is likely to occur may be based at least in part on known future environmental parameters.

[0069] According to some embodiments, generating at least one model of a trend in the detected faults may include calculating a correlation of a rate of change of the faults with one or more environmental parameters. Optionally, the one or more environmental parameters may include, but are not limited to, temperature, season or time of year, barometric pressure, time of day, system operating hours, duration of operation since the container was last filled, duration of operation since the container was last checked, identified user, GPS location, system operating mode, or any combination thereof.

[0070] According to some embodiments, obtaining data associated with fault detection parameters for at least one failure mode of the element includes data associated with a location of the fault and / or a particular type of failure mode. Optionally, obtaining data associated with fault detection parameters for at least one failure mode of the container or vehicle including the container includes receiving input data from a user. Optionally, obtaining data associated with fault detection parameters for at least one failure mode of the element includes identifying a previously unknown failure mode by applying the plurality of images or portions thereof and / or volume change values to a machine learning algorithm configured to determine a failure mode of the container or vehicle including the container.

[0071] According to some embodiments, the fault may include a leak, evaporation, unexpected consumption, suspected tampering, or any combination thereof.

[0072] According to some embodiments, monitoring the volume of the liquid and / or changes in the volume of the liquid in the container may enable analysis of one or more parameters that may indicate the condition of the machine using the liquid. In a first example, if the liquid is engine oil and the monitoring is engine oil consumption, the analysis may be used to detect oil burning issues, worn valve seals and / or piston rings, and / or leaks. In a second example, if the liquid is coolant and the monitoring is machine or system coolant consumption, the analysis may be used to detect an overheated machine, cooling system leaks, damaged radiators, open radiator caps, clogged pipes and / or nozzles.

[0073] According to a fifth aspect of some embodiments of the present invention, there is provided a method for monitoring a volume of a liquid and / or a change in the volume of a liquid in a container, the method comprising: monitoring a surface of the liquid in the container with optical sensor(s) configured to monitor; and and communicating between the optical sensor(s) and at least one processor, the processor comprising: receiving one or more signals from the optical sensor(s), the received signals including one or more images of at least a portion of a surface of the liquid and at least a surrounding portion of a perimeter of the container; and estimating the volume and / or change in volume of the liquid in the container based on at least one or more images and one or more known parameters characterizing the container and / or the liquid; configured to: Includes:

[0074] According to some embodiments, estimating the volume and / or change in volume of the liquid in the container comprises: receiving one or more signals from at least one optical sensor configured to monitor a surface of the liquid in the container and at least a surrounding portion of the periphery of the container, the received signals being at least one image including at least three different dimensions that allow for the definition of a liquid level between the container and the liquid; Neutralizing plane angle and / or acceleration effects utilizing a liquid level defined relative to the horizontal plane of the container and one or more known parameters characterizing the container, thereby estimating the volume of the liquid and / or changes in the volume of the liquid in the container placed in a moving vehicle, machine and / or mechanism; may include:

[0075] Known parameters characterizing the container may include, but are not limited to, the dimensions and / or scale numbers of the container.

[0076] According to some embodiments, the processor may be further configured to apply an algorithm configured to classify whether the estimated volume of liquid and / or change in volume of the liquid in the container conforms to, and output a signal indicative of, a variance therefrom from, a predetermined or pre-calculated expected liquid volume and / or change in volume associated with a particular time point or level of use. Optionally, the algorithm may minimize or exclude effects such as splashing and / or agitation in the liquid when estimating the liquid volume.

[0077] Optionally, at least one optical sensor has processing capabilities (eg, and an embedded sensor) to perform at least some of the processing described herein.

[0078] According to some embodiments, the processor may be further configured to apply at least one determined change to the estimated volume and / or change in volume of the liquid in the container to an algorithm for analyzing the determined change and classifying whether the determined change is associated with a failure mode of the container or the vehicle including the container. The identified change may be labeled as a detected fault. For a determined change classified as associated with a failure mode, a signal indicative of the determined change associated with the failure mode is output.

[0079] Unless otherwise defined, all technical and / or scientific terms used herein have the meaning commonly understood by one of ordinary skill in the art to which this disclosure pertains. Methods and / or materials similar or equivalent to those described herein can be used in the practice and / or testing of embodiments of the present disclosure, and exemplary methods and / or materials are described below. With regard to the exemplary embodiments described below, the materials, methods, and examples are illustrative and not necessarily intended to be limiting.

[0080] Some embodiments of the present disclosure are embodied as a system, method, or computer program product. For example, some embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be referred to generally herein as a "circuit," "module," and / or "system."

[0081] Implementation of some embodiment methods and / or systems of the present disclosure may involve performing and / or completing selected tasks manually, automatically, or a combination thereof. Depending on the actual instrumentation and / or apparatus of some embodiment methods and / or systems of the present disclosure, some selected tasks may be implemented by hardware, software, or firmware, and / or a combination thereof, for example, using an operating system.

[0082] For example, hardware for performing selected tasks according to some embodiments of the present disclosure may be implemented as a chip or circuit. As software, selected tasks according to some embodiments of the present disclosure may be implemented as a plurality of software instructions executed by a computing device using, for example, any suitable operating system.

[0083] In some embodiments, one or more tasks according to some exemplary embodiments of the methods and / or systems as described herein are performed by a data processor, such as a computing platform for executing a plurality of instructions. Optionally, the data processor includes volatile memory for storing instructions and / or data and / or non-volatile storage, e.g., for storing instructions and / or data. Optionally, a network connection is also provided. User interface(s), e.g., display(s) and / or user input device(s), are optionally provided.

[0084] Some embodiments of the present disclosure may be described below with reference to flowcharts and / or block diagrams. For example, exemplary methods and / or apparatuses (systems) and / or computer program products according to embodiments of the present disclosure are illustrated. It will be understood that each step of the flowcharts and / or blocks of the block diagrams, and / or combinations of steps in the flowcharts and / or blocks in the block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to create a machine, such that the instructions, executing via the processor of the computer or other programmable data processing device, create means for implementing the function / act specified in the flowchart step and / or block diagram block or blocks.

[0085] These computer program instructions may also be stored in a computer-readable medium that can direct a computer (e.g., in memory, locally and / or cloud-hosted), other programmable data processing apparatus, or other device to function in a particular manner, such that the instructions stored in the computer-readable medium can be used to generate an article of manufacture including instructions that implement the function(s) / act(s) specified in the flowchart and / or block diagram block or blocks.

[0086] The computer program instructions may also be executed by one or more computing devices to cause a series of operational steps to be performed, for example, on the computing device, other programmable device, and / or other device to generate a computer-implemented process, such that the executing instructions provide a process for implementing the function / act specified in the flowchart and / or block diagram block or blocks.

[0087] In order to understand the present invention, embodiments will now be described, by way of non-limiting example only, with reference to the accompanying drawings, in which features shown in the drawings are intended to serve to illustrate some embodiments of the invention only, unless otherwise indicated, and in which like reference numerals are used to indicate corresponding parts.

[0088] In the block diagrams and flow diagrams, optional elements / components and optional steps may be included within dashed boxes. [Brief explanation of the drawings]

[0089] [Figure 1] 1A-1B are simplified block diagrams of systems for monitoring the volume of a liquid, according to respective embodiments of the present invention. [Figure 2-1] 2A-2B are simplified illustrations of imaging transparent or translucent containers containing respective amounts of liquid. [Figure 2-2] FIG. 2C is a simplified illustration of imaging a transparent or translucent container containing a respective amount of liquid, and FIG. 2D is a simplified illustration of imaging a container having a window through which liquid can be detected. [Figure 3] 3A-3B are simplified diagrams of an optical sensor disposed within a container in accordance with an exemplary embodiment of the present invention. [Figure 4-1] FIG. 4A is a simplified isometric representation of an exemplary tilted rectangular container containing a liquid, and FIGS. 4B-4C are simplified example images of each side of a tilted container having a flat liquid surface. [Figure 4-2] FIG. 4D is a simplified example of an image of the surface of a container containing wavy liquid, and FIG. 4E is a simplified example of an image of the surface of a container containing turbulent liquid. [Figure 5] FIG. 5 is a simplified flow diagram of a method for monitoring liquid volume according to an embodiment of the present invention. [Figure 6]FIG. 6 is a simplified schematic diagram of a system for monitoring potential faults in a vessel and / or associated components, according to some embodiments of the present invention. [Figure 7] FIG. 7 is a simplified flow diagram of a method for monitoring potential faults in a vessel and / or associated components, according to some embodiments of the present invention. [Figure 8] FIG. 8 is a simplified schematic diagram of a method for monitoring potential faults according to some embodiments of the present invention. [Figure 9] FIG. 9 is a simplified block diagram of a system for communicating with a cloud storage module and monitoring a liquid level, according to respective exemplary embodiments of the present invention. [Figure 10] FIG. 10 is a simplified block diagram of a system for communicating with a cloud storage module and monitoring a liquid level, according to respective exemplary embodiments of the present invention. [Figure 11] FIG. 11 is a simplified isometric representation of an exemplary rectangular container containing a liquid. [Figure 12] FIG. 12 is a simplified diagram of imaging a container with a window. [Figure 13] FIG. 13 is a simplified diagram imaging an exemplary vessel including a primary vessel and a secondary vessel. DETAILED DESCRIPTION OF THE INVENTION

[0090] Various embodiments of the present invention are described below with reference to the drawings, which are to be considered in all respects only as illustrative and not in any way restrictive.

[0091] The elements illustrated in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the invention. Moreover, two different objects in the same drawing may be drawn to different scales.

[0092] The present disclosure, in some embodiments thereof, relates to monitoring the volume of a liquid, and more particularly, but not exclusively, to monitoring the volume of a liquid in a container.

[0093] Many types of systems require liquids, such as lubricants, fuels, coolants, and feedstocks, for proper operation. These liquids are often stored in containers that supply the liquid to the associated system (or other associated elements). Maintaining the correct amount of liquid in the system can be extremely important. Therefore, it is desirable to monitor the liquid volume in any system that may lose and / or gain liquid due to factors such as leaks, evaporation, adsorption, liquid addition, etc.

[0094] The embodiments presented herein enable accurate, long-term monitoring of liquid within a container, and the results can be used to detect immediate problems associated with the container and / or the monitored system, such as a sudden decrease in liquid volume that may indicate damage to the container, surrounding elements, or other system components.

[0095] The principles, applications, and implementations of the teachings herein may be better understood with reference to the accompanying description and drawings. Upon perusal of the description and drawings presented herein, those skilled in the art will be able to implement the teachings herein without undue effort or experimentation.

[0096] Before describing at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details of construction and arrangement of components and / or methods set forth in the following description and / or illustrated in the drawings and / or examples. The invention is capable of other embodiments or of being practiced or carried out in various ways.

[0097] Embodiments of the invention presented herein include a system (also referred to herein as a monitoring system) for estimating the volume of liquid in a container using one or more images of the container or portion thereof. The images of the container are provided to a processing circuit by one or more optical sensors. The processing circuit determines the volume of liquid in the container by analyzing the image(s), as described in further detail below. An indication of the agreement of the estimated liquid volume to the expected liquid volume is output. A discrepancy may indicate a problem requiring immediate or future attention.

[0098] As used herein, according to some embodiments of the present invention, the term "optical sensor" refers to a device that detects optical signals and outputs an image.

[0099] As used herein, according to some embodiments of the present invention, the term "optical signal" encompasses ultraviolet (UV), visible and infrared (IR) radiation as well as electromagnetic radiation in other frequency bands.

[0100] As used herein, according to some embodiments of the present invention, the term "estimate liquid volume" and similar terms means determining a liquid volume that is expected to be equal to or close to the actual liquid volume.

[0101] As used herein, according to some embodiments of the present invention, the term "estimated liquid volume" refers to the result of the estimation.

[0102] As used herein, according to some embodiments of the present invention, the term "image" refers to any output of an optical sensor, including image and / or image data and / or another signal (e.g., an electrical signal) that can be processed to estimate liquid volume.

[0103] In some embodiments, the image(s) (e.g., image data) are provided by a single optical sensor. In alternative embodiments, the image(s) are input from multiple optical sensors capturing images of the container from different respective fields of view.

[0104] Optionally, multiple images are analyzed to obtain a more accurate determination of the liquid volume at a single point in time (by correlating images of different parts of the container) and / or to obtain information about changes in the liquid volume over time.

[0105] By monitoring the liquid volume over time, gradual changes in the liquid volume can be detected. These gradual changes may indicate a slow leak or aging of surrounding components. Additionally, changes (increases or decreases) in the liquid volume may indicate faults in surrounding components or other related elements. The time data may be reset periodically to avoid cumulative errors.

[0106] Accurate monitoring of liquid level over time can also be very useful for predictive maintenance by ensuring that, for example, a leak is repaired or a component is replaced before a problem becomes serious, e.g., before a fault becomes a failure. Furthermore, protocols for responding to information about the current liquid level and / or changes in liquid level can be updated periodically based on knowledge accumulated for the same or similar systems.

[0107] Reference is now made to FIGS. 1A-1B, which are simplified block diagrams of monitoring systems for monitoring a volume of a liquid, according to respective embodiments of the present invention.

[0108] As described below, embodiments of the monitoring system may be employed for many purposes, including, but not limited to: 1) monitoring the integrity of a vessel containing a liquid; 2) monitoring the functionality and / or health of relevant elements (e.g., mechanisms, machines, vehicles, aircraft, HVAC systems, etc.); 3) identifying faults in the vessel's peripheral components (e.g., hoses, tubing, gaskets, connectors, seals, etc.); 4) predicting potential failures of related or surrounding components; and 5) Determining when maintenance is or will be required for the vessel, surrounding components, mechanisms, machinery, vehicles, aircraft, etc.

[0109] As used herein, according to some embodiments, the term "health" of an element (e.g., a vessel, a machine, a surrounding component, etc.) refers to the overall condition, functionality, and status of that particular element. It encompasses the evaluation and monitoring of various operational parameters, metrics, or data points that indicate the element's current state, performance, and ability to operate as intended within an industrial system.

[0110] In some embodiments, the operating parameters, metrics and / or data points used to assess the health of an element are based on instructions and / or guidelines provided by a manufacturer, a user, or the like.

[0111] According to the embodiment of Figure 1A, to monitor liquid volume, monitoring system 1 includes processing circuitry 2. Processing circuitry 2 includes one or more processors 3 and, optionally, additional electronic circuitry. Processor(s) 3 process image(s) to perform the analysis described herein. Processor(s) 3 may also perform other tasks, such as providing a graphical user interface (GUI) to a user and processing input from the GUI and / or other input / output means.

[0112] Optionally, the processing circuitry is in communication with the optical sensor(s) via wireless communication (e.g., Bluetooth, cellular networks, satellite networks, local area networks, etc.) and / or wired communication (e.g., telephone networks, cable television or internet access, and fiber optic communication, etc.).

[0113] In some embodiments, processing circuitry 2 is located in a single location as shown in Figures 1A-1B for clarity.

[0114] In alternative embodiments, the processing circuitry is distributed across multiple locations. Optionally, at least one optical sensor includes processing circuitry that performs at least a portion of the processing described herein.

[0115] Optionally, some or all of the processing circuitry is located remotely, for example in a control room that oversees the machines in a factory.

[0116] Optionally, the monitoring system 1 further includes a memory 4 for internal storage of data for use by the monitoring system 1. The stored data may include, but is not limited to: a) image(s), b) Data associated with the image(s). Examples of associated data may include, but are not limited to, the time of capture of the image, the environmental conditions at the time of image capture, the speed of the vehicle carrying the container, and other parameters; c) program instructions; d) algorithms and rules for monitoring the liquid volume; and e) A model of the mechanism, optionally developed by machine learning from a training set of images of the mechanism or similar mechanism(s). For example, the model inputs an image of a vessel and outputs the current liquid volume, the health of the vessel, the liquid in use and / or the health of elements along the fluid flow path, fault alerts, maintenance instructions, etc.

[0117] Optionally, processing circuitry 2 further includes one or more interface(s) 5 for inputting and / or outputting data. For example, the interface(s) may serve to input image(s) and / or communicate with other components within the machine and / or communicate with external machines or systems and / or provide a user interface.

[0118] In one example, indicators and information regarding liquid volume, vessel health, etc. are provided via interface(s) 5 to a HUMS, CBM or similar system.

[0119] According to the embodiment of Figure 1B, the monitoring system 1 further includes one or more optical sensors 6.1-6.n that provide image(s) used to monitor the liquid volume. Optionally, the optical sensors 6.1-6.n provide the image(s) to a processor via a data bus 7.

[0120] According to some embodiments, the optical sensors 6.1-6.n may include cameras. According to some embodiments, the optical sensors 6.1-6.n may include electro-optical sensors. According to some embodiments, the optical sensors 6.1-6.n may include any one or more of charge-coupled devices (CCDs), light-emitting diodes (LEDs), and complementary metal-oxide semiconductor (CMOS) sensors (or active pixel sensors), photodetectors (e.g., IR sensors or UV sensors), or any combination thereof. According to some embodiments, the optical sensors 6.1-6.n may include any one or more of point sensors, distributed sensors, extrinsic sensors, intrinsic sensors, transmissive sensors, diffuse reflective sensors, retroreflective sensors, or any combination thereof.

[0121] Optionally, processing circuitry 2 controls one or more light sources, each illuminating at least a portion of the feature. Optionally, each light source is focused on a particular component or reference point, which may allow for reducing the required intensity of light.

[0122] Alternatively or additionally, the light source(s) are controlled by a user.

[0123] Optionally, the wavelength of the light source may be controlled by processing circuitry 2 and / or by a user.

[0124] Optionally, the light source may be configured to illuminate the container, the liquid, the liquid surface, or portions thereof.

[0125] By controlling the light source, processing circuitry 2 and / or a user can improve image characteristics to facilitate image processing and analysis. For example, the light source can be adjusted to increase the contrast between the container and the liquid within the container. Alternatively or additionally, the light source can be adjusted to increase shadows that highlight each area, thereby facilitating detection of defects and / or surface and / or structural imperfections.

[0126] According to some embodiments, the light source(s) include one or more of a light bulb, a light emitting diode (LED), a laser, an electroluminescent wire, and light transmitted via a fiber optic wire or cable (e.g., from an LED coupled to a fiber optic cable). Other types of light sources may also be suitable.

[0127] Optionally, processing circuitry 2 controls one or more of the following: 1) The direction of light source; 2) duration of irradiation; 3) irradiation frequency; 4) illumination intensity; and 5) Turning the light source on or off.

[0128] According to some embodiments, the light source may emit visible light, infrared (IR) radiation, near-IR radiation, ultraviolet (UV) radiation, or light within any other spectrum or frequency range.

[0129] According to some embodiments, the light source is a light source configured to illuminate with a strobe or short pulses. According to some embodiments, the light source may be configured to emit strobing light without the use of a shutter (such as a global shutter, a rolling shutter, a shutter or any other type of shutter).

[0130] The use of a strobe can be particularly useful during periods of agitation and other times when liquid is moving within the container.

[0131] Optionally, processing circuitry 2 selects optimal settings for each light source(s) based on a predefined algorithm. Optionally, the light sources are controlled according to the environment in which the monitored system is currently operating. For example, the light sources may be turned on during night work and turned off during the day.

[0132] Optionally, processing circuitry 2 dynamically changes light source operation during operation, for example by using different fibers of a fiber optic cable to emit light at different times, or by emitting light from two or more fibers simultaneously.

[0133] Optionally, the light source is part of the surveillance system 1 .

[0134] According to some embodiments, the one or more optical sensors may include one or more lenses and / or fiber optic sensors. According to some embodiments, optical sensors 6.1-6.n may include a software correction matrix configured to generate an image from the optical sensor output signals. According to some embodiments, the one or more optical sensors may include a focus sensor configured to enable the optical sensor to adjust its focus based on changes in the acquired data. According to some embodiments, the focus sensor may be configured to enable the optical sensor to detect changes in one or more pixels of the acquired signals. Optionally, the changes in focus may be used as further input data for processing circuit 2.

[0135] I. Indicators The indicators may provide many types of information regarding various aspects such as liquid volume, liquid properties, health assessments, alerts, and maintenance related information. Non-limiting examples of indicators are presented here.

[0136] Indicators that provide information regarding fluid volume and fluid movement may include, but are not limited to: 1) Estimated liquid volume; 2) the rate of change of liquid volume over time; 3) Prediction of future liquid volume; 4) the frequency of the liquid wave within the container; 5) the amplitude of the liquid wave in the container; and 6) the difference between the estimated fluid volume and the expected volume; and 7) The difference between the estimated liquid volume and liquid volume estimates received from other sources, such as other sensors or machine controls.

[0137] Indicators that provide information about the properties of a liquid may include, but are not limited to: 1) Color change of the liquid; 2) Changes in the opacity of the liquid; 3) Change in the transparency of the liquid; 4) Changes in the viscosity of the liquid; and 5) Presence of particles in the liquid.

[0138] Health-related indicators may include, but are not limited to: 1) Indicators of vessel integrity; 2) the health of the machinery utilizing the fluid; 3) the health of the vehicle utilizing the fluid; 4) the integrity of the mechanism using the fluid; 5) Heating, ventilation and air conditioning (HVAC) system health; 6) the integrity of the surrounding components; and 7) The health of other sensors, such as other liquid measurement sensors.

[0139] Maintenance-related metrics may include, but are not limited to: 1) Maintenance instructions; 2) time-to-failure estimation; 3) fault alerts; and 4) Operational instructions in response to detected faults.

[0140] The selection of the index based on the liquid volume analysis is described in more detail below.

[0141] II. Container Many types of containers are known for containing liquids. The containers may have a regular geometric shape (e.g., cube, rectangular prism, cylinder) or may have an irregular shape.

[0142] Optionally, the colour of the liquid is optically distinguishable from the colour of the container.

[0143] As used herein, according to some embodiments of the present invention, the term "optically distinguishable" means that the difference between the liquid and the container can be detectable in at least one channel of the optical sensor.

[0144] Optionally, as illustrated in Figures 2A-2C, at least one side of the container is transparent or translucent so that the liquid can be seen through it. Optical sensor 230 has a field of view of a portion of the side of 210. In one example, container 200 is cylindrical. In a second example, container 200 is a rectangular container.

[0145] The portion of the container 210 that is filled with liquid is optically distinguishable from the portion of the container that is empty 220. The image of the container captured by the optical sensor 230 will differ based on the liquid level in the container 200.

[0146] Optionally, the container has one or more transparent or translucent windows through which the liquid can be viewed, as illustrated in Figure 2D. Optical sensor 260 has a field of view that encompasses window 250.3.

[0147] If the container does not have a transparent or translucent portion, the optical sensor(s) may be placed inside the container, as described below with reference to Figures 3A-3B.

[0148] Non-limiting examples of containers for holding liquids include: 1) bottle; 2) Tanks (e.g. fuel tanks for vehicles or machinery); 3) Drums; 4) Reservoirs (e.g., for hydraulic or coolant fluids); 5) Lubricating oil container; 6) Coolant expansion tank; 7) Transmission fluid pan; 8) Brake fluid reservoir; 9) Radiator overflow tank.

[0149] Optionally, the container includes at least one liquid inlet and / or outlet, locations that are particularly susceptible to leaks.

[0150] Optionally, the container includes a primary container and a secondary container that are fluidly connected to one another. Optionally, at least one of the optical sensor(s) is positioned with a field of view of the secondary container. Because the two containers are fluidly connected to one another, an image(s) of the secondary container may be useful for determining the volume of liquid within the entire container. An example is shown and described below with respect to Figure 13.

[0151] III. Image Acquisition The images are acquired from one or more optical sensors positioned to have a respective field of view of at least a portion of the container through which the presence of liquid can be detected. For example, the portion of the container can be transparent or partially transparent, or can include a transparent or partially transparent window through which the liquid can be viewed.

[0152] Optionally, at least one optical sensor is located external to the container. Further optionally, the optical sensor is a non-contact sensor that is not in physical contact with the container. For example, the optical sensor may be mounted in a vehicle carrying the container or on a machine that uses the liquid in the container as fuel.

[0153] Optionally, at least one optical sensor is positioned inside the vessel, as illustrated in Figures 3A-3B. In Figure 3A, optical sensor 310 is positioned inside vessel 300, above liquid 330. In Figure 3B, optical sensor 310 is positioned inside vessel 300, submerged in liquid 330. In Figure 3A, the optical sensor's field of view includes both the empty and liquid-filled portions of the vessel. However, this is not always the case (e.g., when the vessel is completely filled or completely empty). In Figure 3B, optical sensor 310 looks inside the liquid and, through image analysis, identifies where the liquid ends (i.e., the liquid surface) to measure its height and angle from the bottom of the tank.

[0154] Optionally, at least one of the optical sensor(s) is attached to an interior surface of the container.

[0155] Optionally, at least a portion of the interior surface of the container is a lens of an optical sensor.

[0156] IV. Estimating Liquid Volume In some embodiments of the present invention, an analysis of the input image(s) is performed to determine which pixels are liquid and which are not.

[0157] In an exemplary embodiment, the determination of pixel type (i.e., liquid or non-liquid) is based on the distribution of pixel color values to distinguish between regions of the container image that exhibit liquid and regions of the container image that do not. Pixels having a distribution consistent with the presence of liquid are tagged as liquid. The distribution may be determined for multiple channels (e.g., RGB or RGB / IR) or, alternatively, for a single channel (e.g., grayscale). Optionally, the probability that a given pixel matches the expected distribution for liquid is performed using Earth Mover Distance analysis. As will be appreciated by those skilled in the art, other analyses may also be used.

[0158] Optionally, after the pixel type is determined, pixels that are far from the main volume of liquid are filtered out and not used in calculating the liquid volume. This is because liquid pixels are expected to be in close proximity, and therefore pixels that are far away may be considered false positives (e.g., droplets on the container surface). In an exemplary embodiment, false positives are removed by a max-flow min-cut calculation, although other approaches may be used.

[0159] Optionally, once the pixel type is finalized, the liquid volume is calculated based on a geometric analysis of the container shape.

[0160] In a simplified example based on geometric analysis of a single image, the height of the liquid level in a container can be used to identify what percentage of the container contains liquid. If the liquid level is in the middle of the container, the container can be considered half full. Thus, a 10 liter container would be considered to contain 5 liters of liquid. If the liquid level is one-quarter of the container's height, the container can be considered one-quarter full. Thus, a 10 liter container would be considered to contain 2.5 liters of liquid.

[0161] Alternatively or additionally, estimating the volume of the liquid from one or more images uses a model, for example, points of interest in the images (e.g., intersections of the liquid surface with the surface of the container) can be input into the model, which then outputs an estimated liquid volume.

[0162] According to some embodiments, the level of the liquid surface in the container may be indicated by a marking on the container. Optionally, the marking may be a feature and / or marking selected from one or more images of the container. Optionally, the marking may be a dot, line, tick, grid, intersection, sticker, vector, and / or any other symbol or code on the container. Optionally, the marking may be a defect, natural line, or boundary line on the container, or an intentional marking (e.g., a ruled line, grid, predetermined line or point, etc.). Optionally, the level of the liquid surface may be, for example, a point or line where the liquid in the container intersects the perimeter of the container. Optionally, algorithm(s) applied to one or more images from one or more optical sensors may automatically identify and / or select the marking. Optionally, an operator may identify and / or select the marking, for example, through an application.

[0163] Optionally, the geometric analysis includes determining the angle of the liquid surface relative to the container, so the volume of the liquid can be calculated even if the container is tilted or in motion.

[0164] Optionally, the image(s) show a portion of the container that is wide enough to estimate the three-dimensional angle of the liquid relative to the container.

[0165] In some embodiments involving a rectangular container, the image or images should show at least two sides of the container in order to calculate the volume of liquid in a tilted container. The two sides can be in a single image of a corner of the container or in separate images captured by different optical sensors. If the container is static, and therefore the liquid surface is not tilted, two edges may not be necessary.

[0166] To illustrate, reference is now made to Figures 4A-4C, which are simplified diagrams of a tilted rectangular container containing liquid and images of two sides of the container. Figure 4A is an isometric view of tilted container 400. Due to the tilt, the surface of the liquid is horizontal to the ground but tilted relative to the plane of the container. Optical sensors 410 and 420 capture images of opposite sides of container 400.

[0167] 4B and 4C are simplified diagrams of images captured by image sensors 410 and 420, respectively.

[0168] The height of the liquid in the image captured by image sensor 410 is h, while the height of the liquid on the surface facing image sensor 420 is h1. Heights h and h1 can be used to calculate the slope of the liquid surface relative to container 400 by geometric analysis.

[0169] Optionally, variations in the relative heights of the reference points (e.g., h with respect to h1) are used to estimate variations in the volume of liquid in the container. For example, the rate of change of liquid volume may be calculated from the time period it takes for the height of liquid in the container to change from h to h1. Optionally, variations in the height of liquid in different parts of the container are used to assess the health of the container and / or associated elements.

[0170] According to some embodiments, the container has an irregular shape whose volume is difficult to represent geometrically. Estimating the volume of liquid from an image of an irregularly shaped container can be complex. Optionally, to estimate the liquid volume in complex cases or to provide a more accurate estimate, additional information is used to estimate the liquid volume from the image(s), such as the use of a three-dimensional model, simulation results, or machine learning trained models.

[0171] 4A-4C show the case where the liquid surface is flat. In other situations, the liquid surface may be wavy, undulating, or have another shape that is not flat.

[0172] Reference is now made to Figures 4D-4E, which are simplified illustrations of images of the surface of a container containing wavy and turbulent liquid, respectively. Waves and turbulence can be caused by many factors, such as linear motion, objects striking the container, and other forces. These forces do not tilt the container but can nevertheless cause changes in the surface of the liquid.

[0173] Optionally, the image(s) are captured while the container is moving (e.g., linearly, rotationally, vibratingly, etc.) relative to the ground. If the relative position of the at least one optical sensor is static with respect to the container (i.e., the container and optical sensor move together), the movement of the container relative to the ground may not be reflected in a single image. However, the movement may be noticeable in the movement of the liquid within the container (e.g., waves and sway). Sudden movement of the container may cause rapid and irregular movements in the liquid, which may be discernible in the images captured by the optical sensor. The use of a strobe may be beneficial for imaging the liquid during periods of rapid and irregular movement.

[0174] Optionally, the determination of the liquid volume is based on analysis of multiple images. Aggregated data from multiple images may stabilize the results if the liquid is moving within the container. Further optionally, the liquid volume is estimated based on statistical analysis of a series of images. In a simplified example, the liquid volume is estimated by averaging results obtained over time. In another example, a contour of the liquid surface is identified in the image (and / or may be added as a line on the image). The contour is used to derive the shape of the liquid within the container, and the volume may be calculated therefrom.

[0175] The results of the image analysis may be correlated with information from one or more other sensors or external sources. Non-limiting examples include: 1) Motion sensors (e.g., accelerometers, gyroscopes, magnetometers, magnetic compasses, vibration or tilt sensors); 2) Temperature sensor; 3) Non-optical liquid level sensors (e.g., liquid level floats); 3) navigation system information (e.g., GPS); and 4) Control system information (e.g., flight control information).

[0176] For example, a motion sensor may provide information about times when the container was in motion, and images from those times may not be used to estimate liquid volume.

[0177] In one example, the container is mounted in an aircraft, and flight control data is used in image analysis to estimate the liquid volume. Optionally, the flight control data may provide the aircraft's speed, altitude, and direction (including turning direction), as well as the aircraft's deflection angle. This information is used to calculate the aircraft acceleration factor (in 3D) and gravitational acceleration (based on the altimetry) and the resulting forces acting on the liquid. From these calculations, the orientation of the liquid in three dimensions may be estimated. In this case, the use of two optical sensors or capturing two edges of the container in a single image may be redundant. Therefore, in such a case, an image of only one side of the container may be sufficient to estimate the liquid volume.

[0178] Optionally, the liquid volume estimation takes into account known properties of the liquid, for example, a highly viscous liquid may react more slowly to container movement or other forces than a less viscous liquid.

[0179] V. Indicator selection and output After the liquid volume is estimated (at a single time point or multiple time points), an indicator is selected and output. The indicator provides information regarding whether the liquid volume(s) estimated by analysis of the image(s) match the expected liquid volume. In some embodiments, the analysis may also indicate other characteristics of the imaged liquid that may be indicative of other failure modes of the machine or its components. For example, the output may indicate the amount of air bubbles in the liquid, the viscosity or color of the liquid, and the like.

[0180] As used herein, according to some embodiments of the present invention, the term "consistent with expected liquid volume" and similar terms means that a parameter obtained by analysis of one or more estimated liquid volumes behaves in accordance with expected behavior of the same parameter under normal conditions. The term "consistent with expected liquid volume" is not limited to an assessment of the current liquid volume, but may alternatively or additionally be assessed based on derived parameters such as the rate of change of liquid volume, indicators from other sensors and / or trends extracted from the progression of liquid volume values.

[0181] As used herein, according to some embodiments of the present invention, the term "expected rate of change of liquid volume" and similar terms refers to the difference in the amount and direction of change in liquid volume over different time periods.

[0182] Note that both the change in liquid volume and the rate of change in liquid volume can be in a positive or negative direction (eg, when fluid is added to a container or when liquid from a container is consumed).

[0183] The expected liquid volume may be calculated by any means known in the art. For example, the expected liquid volume may be the volume of liquid initially held by the container minus the volume expected to be consumed and / or lost (due to evaporation, evaporative absorption, etc.) under normal conditions since the container was filled.

[0184] The parameters and data used to estimate this match may include, but are not limited to: 1) Estimated liquid volume; 2) the rate of change of liquid volume over time; 3) Prediction of future liquid volume; 4) Prediction of variation in the rate of change of fluid volume over time (increase or decrease). 5) Data obtained from other sensors, such as another volumetric sensor or sensors indicating the amount of liquid expected to be consumed. 6) Data provided by the elements associated with the container. 7) Data provided by external systems (e.g., flight control systems).

[0185] The prediction may be based on a trend analysis of the change in liquid volume over time.

[0186] In one example, the estimated liquid volume is within an expected range, but the liquid volume is decreasing or increasing faster than expected. In this case, the analysis may determine that the liquid volume does not match the expected liquid volume, even though the current liquid volume is acceptable for system performance.

[0187] The time(s) at which the analysis is performed may be tailored to suit the needs of a particular system, machine, aircraft, etc. Examples of when the analysis and output of indicators may be performed include, but are not limited to, the following: 1) In progress; 2) regularly; 3)Only during operation; 4) both during operation and idle periods (since leakage may not necessarily be operation-related); 5) When problem indicators are received, for example, from other sensors in the system.

[0188] Optionally, the analysis is performed more frequently if certain conditions emerge (eg, certain flight conditions or indicators from other sensors indicate a problem).

[0189] Optionally, the index is obtained from a data structure indexed by one or more of the aforementioned parameters and / or data, as described below with reference to Tables 1-2.

[0190] Alternatively or additionally, the consistency analysis and / or selection of the output metrics may be based on a model. The model may be developed by any means known in the art. Further optionally, the model is based on machine learning, as described below.

[0191] Alternatively or additionally, the selection of the output metrics is based on a model developed by any means known in the art, and further optionally, the model is based on machine learning, as described below.

[0192] Optionally, the indicator is used by a control system and / or a preventative maintenance system to determine whether further action should be taken (e.g., decisions regarding operation and / or maintenance of elements associated with the liquid container).

[0193] Reference is now made to Tables 1 and 2, which are simplified examples of data structures that may be used to select indicators for output. In both cases, the indicators relate to fault detection and preventative maintenance.

[0194] In Table 1, indicators are selected based on two parameters related to liquid volume, the values of which are estimated by analysis of images of the container. Standard maintenance is indicated when the liquid volume and / or the rate of liquid volume loss are within expected ranges. [Table 1]

[0195] Optionally, the maintenance instruction may relate to a leak, e.g., the presence of fuel around the container, which may cause other problems, and therefore a fault alert may be provided even if the container is relatively full. In a second example, the container is not critical to the system, and therefore no fault alert is provided (e.g., the health of the air conditioning system in a vehicle may not be critical to the performance of the vehicle even if the air conditioning is not working).

[0196] In Table 2, an indicator is selected based on one parameter value related to liquid volume and data from a temperature sensor. For example, if the container contains fuel for a machine, the temperature may be related to the load under which the machine operates. Thus, fuel consumption may be expected to be higher at higher temperatures compared to fuel consumption at lower temperatures. The fuel consumption rate determined by the analysis is compared to the expected fuel consumption rate at a given temperature. The indicator indicates whether the rate of change of liquid volume (e.g., fuel consumption) is below an acceptable range, within an expected range, or higher than expected. [Table 2]

[0197] Further action can be taken in response to the output indicator. For example, in Table 2, both alerts can warn the operator to power down the machine to prevent a breakdown. If the indicator indicates expected fuel consumption over time, a regular maintenance schedule can be followed. Depending on the specific situation, low fuel consumption can be considered a problem requiring earlier maintenance, or a benefit that extends the time until the next maintenance is required.

[0198] VI. Monitoring of Other Components Optionally, the monitoring system also inputs images of other components within the machine / vehicle / aircraft / etc. to optionally perform additional assessments as described in PCT Publication WO2022162663, which is incorporated herein by reference. The images may be provided by optical sensors imaging the container and / or other optical sensors. Additional analysis may identify defects or faults not necessarily directly related to the container and liquid volume, such as corrosion, cracks, structural damage, etc.

[0199] Optionally, the results of the additional assessments are correlated with the results of the liquid volume estimation and analysis to select an indicator. For example, liquid accumulation in an unexpected location may explain why the liquid volume is low. As a result, maintenance instructions may be focused on the specific failure mode associated with the liquid accumulation at that location.

[0200] VII. Machine Learning In some embodiments, the model used to estimate the fluid volume level and / or select the indicator to be output is a machine learning model trained on a training set by a supervised learning algorithm or by an unsupervised learning algorithm.

[0201] Optionally, the model is a neural network.

[0202] Optionally, the training set includes one or more of the following: 1) Images collected during the liquid's use period; 2) images collected during periods of liquid non-use; 3) Images of similar containers or different containers in similar machines collected during the period of use; and 4) Images of similar containers or different containers in similar machines collected during periods of non-use. 5) Image(s) of other components, possibly provided by other optical sensors. 6) Non-image data associated with some or all of the images in the training set.

[0203] For example, the non-image data may include the environmental and operating conditions at the time the image was captured. In a further example, the training set includes flight control information that may be relevant to the time the image was captured.

[0204] Optionally, the images in the training set refer to image analysis, not necessarily the image data itself (e.g., for any or all of items 1-5 above); the results of image analysis are input, not the images themselves.

[0205] Optionally, the model is trained prior to actual use of the vessel or monitoring system (eg, during a preliminary training period).

[0206] Optionally, the model is periodically retrained based on image(s) and / or other data collected over time.

[0207] VIII. Methods for Monitoring Liquid Volume Reference is now made to FIG. 5, which is a simplified flow diagram of a method for monitoring liquid volume, in accordance with an embodiment of the present invention.

[0208] At 510, at least one image of the liquid contained within the container is acquired from at least one optical sensor.

[0209] The volume of liquid in the container is estimated from the image(s) at 520. Optionally, the volume of liquid is estimated according to the embodiments described above.

[0210] At 530, the estimated liquid volume(s) value is analyzed to assess whether it matches the expected liquid volume. Optionally, the match is assessed according to the embodiments described above.

[0211] An index is output at 540. The index is selected based on the results of the analysis at 530. The index may be a binary output (e.g., match / no match) and / or may include additional information, such as an estimated volume or properties of the imaged fluid.

[0212] Optionally, the image(s) are provided by a single optical sensor. The single optical sensor may image one, two, or more sides of the polygonal container. Alternatively, the images are provided by multiple optical sensors that capture images of the container in their respective fields of view.

[0213] Estimating the liquid volume from multiple images may improve the accuracy of the results, but may require more computational resources.

[0214] Optionally, the indicators include a health assessment of at least one of the following: container; Machines that utilize liquids; Vehicles or aircraft utilizing liquids; mechanisms utilizing liquids; Heating, ventilation and air conditioning (HVAC) systems; and Peripheral components.

[0215] Optionally, the indicator includes at least one of the following: estimated liquid volume; the rate of change of liquid volume over time; Predicting future liquid volumes; At least one of the frequency and amplitude of the liquid wave motion in the container; Color change of the liquid; Changes in the opacity of the liquid; Changes in the transparency of the liquid; Changes in the viscosity of the liquid; the presence of particles in the liquid; maintenance instructions; time-to-failure estimation; Fault alerts; and Operational instructions in response to detected faults.

[0216] In an exemplary embodiment, estimating the liquid volume includes analyzing the distribution of intensities in at least one channel of at least one image to identify pixels having a distribution consistent with the presence of liquid.

[0217] Optionally, estimating the liquid volume includes excluding pixels away from the main volume of the liquid from the calculation of the liquid volume.

[0218] Optionally, estimating the liquid volume comprises calculating the liquid volume based on a geometric analysis of the container shape.

[0219] Optionally, estimating the liquid volume is based on statistical analysis of the series of images.

[0220] Optionally, estimating the liquid volume is further based on data obtained from a non-optical sensor.

[0221] Optionally, estimating the liquid volume is further based on data obtained from an external source.

[0222] Optionally, the match of the estimated liquid volume(s) to the expected liquid volume is based on one or more of the following: Current liquid volume; Change in liquid volume over time. Trend analysis of fluid volume changes over time.

[0223] Optionally, at least one image shows two sides of the container.

[0224] Optionally, at least one image shows a portion of the container, the portion being wide enough to estimate the three-dimensional angle of the liquid relative to the container.

[0225] Optionally, the images are captured while the container is moving relative to the ground.

[0226] Optionally, the at least one optical sensor is located external to the container.

[0227] Optionally, the at least one optical sensor is disposed inside the container.

[0228] Optionally, the method further comprises obtaining an index from the data structure using one or more of the following values: estimated liquid volume; the rate of change of liquid volume over time; Prediction of future liquid volume; and Prediction of variation in rate of change of liquid volume over time.

[0229] Optionally, the analysis is based on a machine learning model trained on a training set, the training set including one or more of the following: Images collected during the period of use of the liquid; Images collected during periods of non-use of fluids; Images of similar containers collected during their use; and Images of similar containers collected during periods of non-use.

[0230] Optionally, the machine learning model is a neural network.

[0231] Optionally, the machine learning model is trained using a supervised learning algorithm.

[0232] Optionally, the machine learning model is trained using an unsupervised learning algorithm.

[0233] Optionally, the training set includes non-image data associated with at least some of the images in the training set.

[0234] IX. Illustrative Embodiments According to some embodiments, an exemplary system for monitoring the volume of liquid and / or the change in volume of liquid and / or the rate of change of volume of liquid in a container and / or the change in properties of liquid in the container is provided. The monitoring system includes an optical sensor. According to some embodiments, a system for monitoring the volume of liquid in a container and / or the change in volume of liquid and / or the rate of change of volume of liquid and / or the change in properties of liquid in the container may include a processor in communication with one or more optical sensors configured to observe the liquid level in the container.

[0235] According to some embodiments, the optical sensors and / or processors and / or other circuits of FIGS. 6-13 may follow the embodiments of the optical sensors, processing circuits and / or other circuits (e.g., illumination sources) as described with respect to FIGS. 1-5.

[0236] Optionally, the container is in motion. Optionally, the motion is linear, rotational, or both.

[0237] According to some embodiments, the container is disposed within a vehicle. Optionally, the vehicle is an automobile (e.g., a car, a truck, a construction vehicle, a motorcycle, an electric scooter, an electric bicycle, etc.), an aircraft (e.g., an airplane, a spaceship, a helicopter, a drone, etc.), or a watercraft (e.g., a ship, a boat, a submarine, a hovercraft, an underwater drone, etc.). According to alternative optional embodiments, the container is disposed within a machine (e.g., a multi-axis machining center, a crane, a robot used in a production line, a robot used in extreme environmental conditions, etc.) or mechanism (e.g., a manipulator, a gripper, a hydraulic piston, etc.).

[0238] According to some embodiments, the optical sensor(s) are positioned to provide one or more images of one or more sides of the container. Optionally, the one or more images are a still image, a portion of an image, a set of images, one or more video frames, or any combination thereof. Optionally, the monitoring system may include one or more additional sensors. Optionally, in a mobile system, the one or more additional sensors may include an accelerometer. Optionally, the optical sensor(s) may acquire one or more images while the vehicle is moving at a constant speed and / or in a straight line and / or horizontally. Alternatively, the optical sensor(s) may acquire images continuously, even when the vehicle is moving.

[0239] According to some embodiments, the container is filled to a degree with a liquid that is optically distinguishable from the container, such as by its color, viscosity, or color of the container (e.g., colored liquid, oil, mercury, syrup, etc.). Optionally, the container is partially or completely transparent, translucent, opaque, or translucent. Optionally, the container is a different color than the liquid contained therein. Optionally, the container is partially or completely transparent to the optical sensor.

[0240] According to some embodiments, at least one optical sensor is disposed external to the container. Optionally, at least one of the optical sensor(s) is positioned such that its field of view encompasses at least one wall or portion of a wall of the container.

[0241] Optionally, when the at least one optical sensor is disposed outside the container (also referred to herein as an external optical sensor), at least a portion of the container is at least partially transparent to the external optical sensor(s). Optionally, the container includes at least one window through which the liquid may be imaged. Optionally, the external optical sensor(s) are positioned such that their field of view encompasses some or all of the at least one window.

[0242] According to some embodiments, the container includes a primary container and a secondary container fluidly connected to one another, as shown in Figure 13. Optionally, at least one of the optical sensor(s) is positioned with a field of view of the secondary container.

[0243] Optionally, the monitoring system includes one or more illumination sources. Further optionally, the one or more illumination sources may be configured to illuminate the container, window, secondary container, or portions thereof.

[0244] According to some embodiments, at least one optical sensor (also referred to herein as an internal sensor) is disposed inside the container. Optionally, the at least one internal optical sensor is fully or partially immersed in the liquid. Optionally, the at least one internal optical sensor is positioned such that its field of view encompasses the liquid surface and at least one wall of the container, thereby enabling analysis of the liquid level within the container.

[0245] Optionally, the monitoring system includes one or more illumination sources. Optionally, each of the one or more illumination sources may be configured to illuminate the container and / or the liquid and / or the liquid surface and / or a portion thereof.

[0246] According to some embodiments, the optical sensor(s) comprise electro-optical sensors. According to some embodiments, the optical sensor(s) comprise cameras. According to some embodiments, the optical sensor(s) comprise any one or more of charge-coupled devices (CCDs) and complementary metal-oxide semiconductor (CMOS) sensors (or active pixel sensors), or any combination thereof. According to some embodiments, the optical sensor(s) comprise any one or more of point sensors, distributed sensors, external sensors, internal sensors, transmissive sensors, diffuse reflective sensors, retro-reflective sensors, or any combination thereof. According to some embodiments, the optical sensor(s) comprise one or more lenses. According to some embodiments, the optical sensor(s) comprise fiber optic sensors.

[0247] Optionally, the sensor operates in the IR and / or visible and / or UV frequencies.

[0248] According to some embodiments, the one or more illumination sources include any one or more of a light bulb, a light emitting diode (LED), a laser, a fiber optic illumination source, a fiber optic cable, and the like.

[0249] According to some embodiments, at least one processor is used to analyze one or more images from the optical sensor(s) to determine, for example, a liquid surface level and / or a liquid surface plane and / or a liquid surface plane vector.

[0250] Optionally, the processor is located remotely, for example in a control room monitoring machines in a factory.

[0251] Optionally, the at least one processor is in communication with the optical sensor(s). Optionally, the processor may be connected to the optical sensor(s) wirelessly (e.g., Bluetooth, cellular networks, satellite networks, local area networks, etc.) and / or by wired communication (e.g., telephone networks, cable television or internet access, fiber optic communication, etc.).

[0252] According to some embodiments, the at least one processor may receive signals from the optical sensor(s). Optionally, the received signals may include one or more images of at least a portion of the surface of the liquid and / or at least a surrounding portion of the perimeter of the container.

[0253] According to some embodiments, the volume of the liquid and / or the change in the volume of the liquid in the container is estimated from one or more images from the optical sensor(s). Optionally, the optical sensor(s) are configured to monitor the liquid surface in the container. According to some embodiments, the volume of the liquid and / or the change in the volume of the liquid in the container may be calculated from the level of the liquid surface in the container and one or more known parameters characterizing the container. Optionally, the known parameters characterizing the container may include dimensions of the container (e.g., container shape, total volume of the container, height, length, width, area, perimeter, circumference, weight, acceleration, pitch and roll angle, etc.), scale numbers (e.g., metric or imperial), or both.

[0254] According to some embodiments, the volume of the liquid and / or the change in volume of the liquid in the container may be estimated from one or more images from an optical sensor(s). Optionally, the optical sensor(s) are configured to monitor the liquid surface in the container. Optionally, from the one or more images, at least three different dimensions may be extracted, for example, from the intersection of the liquid surface with the perimeter of the container. Optionally, based on the points, the surface orientation (direction of a vector normal to a plane) of the liquid surface may be calculated. According to some embodiments, the selected dimensions may be estimated using an optical sensor(s) (e.g., a camera) of the monitoring system.

[0255] According to some embodiments, the plane of the liquid relative to the horizontal plane of the container, and optionally one or more known parameters characterizing the container, angle and / or acceleration effects may be removed. Optionally, the known parameters characterizing the container include one or more dimensions of the container (e.g., container shape, total container volume, height, length, width, area, circumference, perimeter, weight, acceleration, pitch and roll angle, etc.), scale numbers (e.g., metric or imperial), or both. Optionally, the volume of the liquid and / or changes in the volume of the liquid in the container may be estimated thereby. According to some embodiments, selected dimensions and / or the volume of the liquid and / or changes in the volume of the liquid in the container may be estimated by analyzing multiple images / video clips of a system, such as a machine and / or structure, to determine respective allowed ranges / limits for each selected point and / or orientation that may still be defined as allowed.

[0256] According to some embodiments, the volume of the liquid and / or the change in the volume of the liquid in the container may be calculated by taking into account the difference between a vector perpendicular to the plane of the liquid surface and a vector perpendicular to the horizontal plane of the container.

number

[0257] According to some embodiments, the vector of the plane of the liquid surface may be expressed as:

number

[0258] Alternatively and / or additionally, from this equation, a known or measured acceleration vector

number

number

number

number

[0259] According to some embodiments, the volume of liquid in the container may be monitored over a period of time (e.g., seconds, minutes, hours, days, travel duration, travel distance, number of operating hours, cycle time, etc.), and the rate of change of the volume of the liquid is calculated. Optionally, the rate of change of volume may be compared to a previously calculated, previously defined, and / or previously measured rate of change of the volume of the liquid in the container. Optionally, the rate of change of the volume of the liquid may be compared to a curve of the liquid volume over time. Optionally, the calculation of the rate of change of the volume of the liquid may be plotted on a graph. Optionally, the calculation of the rate of change of the volume of the liquid may take into account vehicle acceleration and / or deceleration and / or vehicle function. Optionally, the rate of change of the volume of the liquid in the container may be an average, weighted average, mean, etc. over a defined period of time.

[0260] According to some embodiments, the monitoring system may include one or more motion-related sensors. Further optionally, the one or more motion-related sensors include one or more of an accelerometer, a navigation system (e.g., GPS), a gyroscope, a magnetometer, a magnetic compass, a Hall sensor, or a tilt sensor, an inclinometer, a spirit level. Optionally, the monitoring system may also function as an accelerometer, for example, if the orientation is zero or known (e.g., from an inclinometer, gyroscope, etc.). Optionally, a plane angle may be determined using data from a motion detection device (e.g., an accelerometer). Optionally, the volume of liquid in the container may be calculated using a single optical sensor observing the container, without the need to identify and calculate the relative plane between the liquid and the container using data from both an inclinometer and a motion detection device (e.g., an accelerometer).

[0261] According to some embodiments, the liquid volume and / or change in liquid volume and / or rate of change of liquid volume in the container is analyzed to determine whether it is within a predefined deviation range from one or more predefined and / or predetermined values. Optionally, at least one inconsistency in the liquid volume and / or rate of change in liquid volume may be identified. Optionally, data associated with characteristics of faults, unexpected use, misuse, etc. in the container and / or related components may be obtained from a database. Optionally, the at least one identified inconsistency may be applied to an algorithm. Optionally, the algorithm may be configured to analyze the identified inconsistencies in one or more images received from the optical sensor(s). Optionally, the algorithm may be configured to classify, at least in part, based on the obtained data, whether the identified inconsistencies in the one or more images received from the optical sensor(s) are associated with a fault in the container. Optionally, for identified inconsistencies classified as associated with a fault, a signal may be output indicating the identified inconsistency being associated with an injury (e.g., the signal may indicate that maintenance may be required based on the associated fault).

[0262] According to some embodiments, the monitoring may further include identifying a change in the volume of the liquid and / or a change in the volume of the liquid in the container and / or a rate of change of the volume of the liquid in the container, which may be calculated based on a change from a reference angle measurement, a predetermined, and / or pre-calculated, and / or pre-defined value. According to some embodiments, the monitoring may further include identifying a change in the volume of the liquid and / or a change in the volume of the liquid and / or a rate of change of the volume of the liquid in the container, which may be calculated based on a change in deviation of the volume of the liquid and / or a change in the volume of the liquid and / or a rate of change of the volume of the liquid in the container from a predetermined, and / or pre-calculated, and / or pre-defined value.

[0263] According to some embodiments, monitoring may further include alerting a user to suspected and / or predicted malfunction / failure / damage / failure of the container.

[0264] According to some embodiments, a failure mode may be determined by analyzing multiple images / video clips / data acquired from the vessel and / or associated components to obtain a liquid volume and / or change in liquid volume and / or rate of change in the vessel that are typical of a failure. As one example of a failure, a significant decrease in oil volume and / or a high rate of decrease in the oil volume in the vessel may indicate high oil consumption in an engine, which may indicate an oil burning problem, which may be caused by, for example, a failed valve seal and / or a failed piston ring. As another example of a failure, high coolant consumption may indicate an overheated machine, a cooling system leak, a damaged radiator, an open radiator cap, etc. As another example, low lubricant or coolant consumption in a machine, such as a multi-axis machining center, may indicate clogged pipes and / or nozzles, etc.

[0265] According to alternative or additional embodiments, faults may be caused by broken vessels, primary and / or secondary vessels, pipes, hoses, loose screws, cracked lids and / or covers, etc., or components thereof, which may also be detected, for example, by analyzing multiple images / video clips / data acquired from the vessel and / or associated components.

[0266] According to some embodiments, the rate of deviation of the liquid volume and / or change in liquid volume and / or volume of liquid in the container from their respective expected liquid volume and / or change in liquid volume and / or rate of change in liquid volume in the container may be determined and / or utilized to predict a timeline to failure.

[0267] According to some embodiments, the level of the liquid surface in the container may be indicated by a marking on the container. Optionally, the marking may be a feature and / or marking selected from one or more images of the container. Optionally, the marking may be a dot, line, tick, grid, intersection, sticker, vector, and / or any other symbol or code on the container. Optionally, the marking may be a defect, natural line, or boundary line on the container, or an intentional marking (e.g., a ruled line, grid, predetermined line or point, etc.). Optionally, the level of the liquid surface may be, for example, a point or line where the liquid in the container intersects the perimeter of the container. Optionally, algorithm(s) applied to one or more images from one or more optical sensors may automatically identify and / or select the marking. Optionally, an operator may identify and / or select the marking, for example, through an application. Optionally, multiple changes in volume of the liquid and / or a single change in volume of the liquid and / or a rate of change of volume of the liquid in the container may indicate compromised structural integrity of the container and / or associated components. Optionally, the associated components may be primary or secondary containers, pipes, hoses, covers, screws, etc.

[0268] Additionally and / or alternatively, the monitoring system and / or method may be further configured to provide an indication of the integrity of the container and / or associated components. Optionally, the liquid volume and / or change in liquid volume and / or rate of change of liquid volume in the container may provide an indication of the integrity of the container and / or associated components and / or may provide a basis for predicting time to failure of the container and / or associated components. Optionally, the liquid volume and / or change in liquid volume and / or rate of change of liquid volume in the container may provide an indication that maintenance may be required.

[0269] According to some embodiments, the processor: receiving a signal from at least one optical sensor observing a liquid surface within the vessel to obtain data associated with at least one failure mode characteristic of the vessel and / or associated components; for the identified changes in the received signals, identifying at least one change in the received signals (e.g., a variation in the liquid surface level or liquid volume and / or a change in the liquid volume and / or a rate of change of the liquid volume in the container calculated at least in part therefrom from a pre-obtained or pre-calculated value for the liquid surface level, the liquid volume and / or the rate of change of the liquid volume in the container), and optionally applying the at least one identified change to an algorithm configured to analyze the identified changes in the received signals and classify whether the identified changes in the received signals are associated with a failure mode of the container and / or associated components, thereby labeling the identified change as a trend based, at least in part, on the acquired data, and classifying the identified change as being associated with a failure mode; outputting a signal indicative of the identified change associated with the failure mode; It may be feasible to do so.

[0270] According to some embodiments, for an identified fault, the processor may generate at least one model of a trend in the identified fault, where the trend may include a rate of change in the fault.

[0271] According to some embodiments, the monitoring system may be configured for smart maintenance of the vessel and / or associated components by using one or more algorithms configured to detect changes, identify faults, and determine whether the faults may escalate into structural failures.

[0272] According to some embodiments, for an identified trend, the processor may generate at least one model of the trend, which may include a rate of change.

[0273] According to some embodiments, the monitoring system may be configured for smart maintenance of the vessel and / or associated components by using one or more algorithms configured to detect changes, thereby identifying trends, and determining whether the trends may escalate into structural failure.

[0274] Advantageously, the monitoring system and / or method may enable volume measurements in inaccessible areas that may require significant effort to inspect / maintain by placing optical sensor(s) within or within view of a container that may not otherwise be monitored.

[0275] Advantageously, the monitoring system may enable trend identification and calculations, whereby trends in liquid volume and / or changes in liquid volume and / or rate of change of liquid volume within the container are analyzed, thereby enabling the prediction of failure even before there is a change in the normal behavior or operation of the container and / or associated components. According to some embodiments, a system for monitoring potential faults in a vessel and / or associated components is provided, the monitoring system including: a vessel containing a liquid optically distinguishable from the vessel; at least one optical sensor configured to be mounted within or having a field of view of the vessel; and at least one processor in communication with the optical sensor, the processor being executable to: receive signals from the at least one optical sensor observing the vessel; obtain data associated with at least one failure mode characteristic of the vessel and / or associated component; identify at least one change in the received signals; analyze the identified change in the received signals against the identified change in the received signals; apply an algorithm configured to classify whether the identified change in the received signals is associated with a failure mode of the vessel and / or associated component, thereby labeling the identified change as a fault based, at least in part, on the obtained data; classify the identified change as associated with the failure mode; and output a signal indicative of the identified change associated with the failure mode.

[0276] According to some embodiments, a computer-implemented method for monitoring a container is provided, the method including: receiving signals from at least one optical sensor observing a level of a liquid surface within the container, the liquid may be optically distinguishable from the container and configured to be mounted within or having a field of view of the container; acquiring data associated with at least one failure mode characteristic of the container and / or associated components; identifying at least one change in the received signals; analyzing the change identified in the received signals against the changes identified in the received signals; applying the at least one identified change to an algorithm configured to classify, at least in part, based on the acquired data, whether the change identified in the received signals is associated with a failure mode of the container and / or associated components; and, for the identified change classified as associated with the failure mode, outputting a signal indicative of the identified change associated with the failure mode.

[0277] According to some embodiments, for an identified trend, the method and / or monitoring system may include generating at least one model of the trend.

[0278] According to some embodiments, the trend may include the rate of change of the liquid surface level and / or volume.

[0279] According to some embodiments, generating at least one model of the trend may include calculating a correlation of the rate of change of the liquid surface level and / or volume with one or more environmental parameters.

[0280] According to some embodiments, in response to an identified trend, the method and / or monitoring system may include alerting a user of a predicted failure based, at least in part, on the generated model.

[0281] According to some embodiments, alerting the user of the predicted failure may include any one or more of the time (or time range) of the predicted failure, the age of the container and / or associated components, and the characteristics of the failure mode, or any combination thereof.

[0282] According to some embodiments, identifying at least one change in the received signal includes identifying a change in the rate of change in the received signal.

[0283] According to some embodiments, the processor and / or algorithm may take into account one or more environmental parameters including at least one of temperature, season or time of year, barometric pressure, time of day, vessel and / or vehicle operation time, vessel and / or vehicle operational duration (e.g., vessel and / or vehicle age, cycle time, run time, down time, etc.), identified user of the structure, GPS location, vessel and / or associated component operational mode (e.g., continuous, periodic, etc.), and / or any combination thereof. Optionally, the monitoring system may obtain data regarding the one or more environmental parameters from an online database, such as a mapping database, a weather database, a calendar, a database of previous measurements, etc., for inclusion in the analysis.

[0284] According to some embodiments, for an identified fault, the method and / or monitoring system may include outputting a prediction, based at least in part on the generated model, of when the identified fault is likely to lead to a failure in the vessel and / or associated components.

[0285] According to some embodiments, predicting when a failure is likely to occur in a vessel and / or associated components may be based, at least in part, on predicted future environmental parameters.

[0286] According to some embodiments, the failure mode may include at least one of a change in dimension, a change in position, a change in color, a change in texture, a change in size, a change in appearance, a fracture, structural damage, a crack, a crack size, a critical crack size, a crack location, a crack propagation, a change in orientation, a defined pressure applied to the container and / or associated components, a change in the movement of one component relative to another component, a leakage amount, a leakage rate, a change in leakage rate, an amount of accumulated liquid, a change in the amount of accumulated liquid, a size of a bubble formed, a change in the amount of evaporation, and the like, or any combination thereof.

[0287] According to some embodiments, for an identified fault and / or trend, the method and / or monitoring system includes, if the identified change is not classified as associated with a failure mode, storing and / or using data associated with the identified change for further investigation, which may include at least one of adding a failure mode, updating an algorithm configured to identify the change, and training an algorithm to ignore the identified change in the future, thereby improving the algorithm configured to identify the change.

[0288] According to some embodiments, obtaining data associated with the characteristics of at least one failure mode of the vessel and / or associated component may include data associated with the location of the failure mode on the structure and / or the specific type of failure mode.

[0289] According to some embodiments, obtaining data associated with the characteristic of at least one failure mode of the vessel and / or associated component may include receiving input data from a user.

[0290] According to some embodiments, for identified faults and / or trends, the method and / or monitoring system may include analyzing the received signal(s), and obtaining data associated with the characteristic of at least one failure mode of the vessel and / or associated component includes automatically obtaining data from a database based, at least in part, on the signal(s) received from the at least one optical sensor. Optionally, the monitoring system may obtain data regarding one or more environmental parameters from online databases, such as a mapping database, a weather database, a calendar, a database of previous measurements, etc., for inclusion in the analysis.

[0291] According to some embodiments, obtaining data associated with a characteristic of at least one failure mode of the vessel and / or associated component may include identifying a previously unknown failure mode by applying the received signals to a machine learning algorithm configured to determine a failure mode of the vessel and / or associated component.

[0292] According to some embodiments, identifying at least one change in the signal may include analyzing raw data of the received signal.

[0293] According to some embodiments, the at least one signal may include at least one image, a portion of an image, a set of images, a video, or a video frame.

[0294] According to some embodiments, identifying at least one change in the signal may include analyzing dynamic motion of the container and / or associated components, which may include any one or more of linear motion, rotational motion, vertical motion, cyclic (repetitive) motion, rocking motion, damage, defects, cracks, breaks, changes in orientation, changes in acceleration, cuts, warping, expansion, deformation, abrasion, wear, corrosion, oxidation, changes in dimension, changes in position, changes in size, or any combination thereof.

[0295] According to some embodiments, for identified faults and / or trends, the method and / or monitoring system may include outputting data associated with optimal locations for placing optical sensors, from which potential failure modes can be detected.

[0296] According to some embodiments, for identified faults and / or trends, the method and / or monitoring system may include at least one illumination source configured to illuminate at least a portion of the container, an associated component, the liquid surface, or a combination thereof, and classifying whether an identified change in the signal may be associated with a failure mode of the container and / or associated component may be based, at least in part, on any one or more of the placement(s) of the at least one illumination source, the duration of illumination, the wavelength, the intensity, the direction of illumination, and the frequency of illumination.

[0297] According to some embodiments, the monitoring system may be configured to generate at least one model of a trend and / or a trend in the identified faults, where the trend may include a rate of change in the faults and / or the trend.

[0298] According to some embodiments, the monitoring system may be configured to prevent structural failures by identifying faults and / or trends in real time and monitoring changes in faults and / or trends in real time.

[0299] Reference is now made to FIG. 6, which shows a schematic diagram of a system for monitoring potential faults in a vessel and / or associated components, according to some embodiments of the present invention.

[0300] According to some embodiments, a monitoring system 600 for monitoring for potential failures in a vessel and / or associated components may be configured to monitor one vessel and / or associated component, one associated component of one vessel, two or more associated components of one vessel, independent components of a vessel, interconnected components of a vessel, or any combination thereof.

[0301] According to some embodiments, system 600 may include a container containing a liquid optically distinguishable from the container, and one or more optical sensors 612 configured to be mounted within or within view of the container and / or its associated components. According to some embodiments, system 600 may be configured to monitor the container in real time. According to some embodiments, system 600 may include at least one processor 602 in communication with the optical sensor(s) 612. According to some embodiments, processor 602 may be configured to receive signals (or data) from the optical sensor(s) 612. According to some embodiments, processor 602 may include an embedded processor, a cloud computing system, or any combination thereof. According to some embodiments, processor 602 may be configured to process signals (or data) received from optical sensor(s) 612 (also referred to herein as received signals or received data). According to some embodiments, processor 602 may include an image processing module 606 configured to process signals received from optical sensor(s) 612.

[0302] According to some embodiments, the optical sensor(s) 612 may be configured to detect light reflected from the liquid surface within the container. Optionally, the liquid within the container may be selected for high-light and / or low-light environments; for example, selecting a liquid that may absorb little light and / or reflect more light may therefore provide a clearer image. Moreover, by changing the wavelength, intensity, and / or direction of the light, this phenomenon may be enhanced. According to some embodiments, and as described in further detail elsewhere herein, the monitoring system may include one or more illumination sources configured to illuminate the liquid surface within the container, the container, and / or related components.

[0303] According to some embodiments, changing the direction of the light may include moving the illumination light source. According to some embodiments, changing the direction of the light may include maintaining two or more fixed illumination light source positions while powering (or otherwise operating) the illumination light sources at different times, thereby changing the direction of light illuminating the liquid surface, the vessel, and / or associated components within the vessel. According to some embodiments, and as described in more detail elsewhere herein, the monitoring system may include one or more illumination light sources positioned such that their operation illuminates part or all of the liquid surface, the vessel, and / or associated components within the vessel. According to some embodiments, the monitoring system may include multiple illumination light sources, each positioned at a different position relative to the liquid surface, the vessel, and / or associated components within the vessel.

[0304] According to some embodiments, the wavelength, intensity, and / or direction of the one or more illumination sources may be controlled by a processor. According to some embodiments, varying the wavelength, intensity, and / or direction of the one or more illumination sources thereby enables detection of selected dimensions related to the liquid surface and / or the liquid surface within the container, the container, and / or associated components. According to some embodiments, the optical sensor(s) 612 may enable detection of small variations in the level of the liquid surface within the container, the volume of the liquid, and / or changes in the volume of the liquid within the container, which may not be visible to the naked eye, by analyzing the image.

[0305] According to some embodiments, the optical sensor(s) 612 may include a camera. According to some embodiments, the optical sensor(s) 612 may include an electro-optical sensor. According to some embodiments, the optical sensor(s) 612 may include any one or more of a charge-coupled device (CCD) and a complementary metal-oxide semiconductor (CMOS) sensor (or active pixel sensor), or any combination thereof. According to some embodiments, the optical sensor(s) 612 may include any one or more of a point sensor, a distributed sensor, an external sensor, an internal sensor, a transmissive sensor, a diffuse reflective sensor, a retro-reflective sensor, or any combination thereof.

[0306] According to some embodiments, the optical sensor(s) may include one or more lenses and / or fiber optic sensors. According to some embodiments, the one or more optical sensors may include a software correction matrix configured to generate an image from the acquired data. According to some embodiments, the optical sensor(s) may include a focus sensor configured to enable the optical sensor to detect changes in the acquired data. According to some embodiments, the focus sensor may be configured to enable the optical sensor to detect changes in one or more pixels of the acquired signal.

[0307] According to some embodiments, the system 600 may include one or more user interface modules 614 in communication with the processor 602. According to some embodiments, the user interface module 614 may be configured for receiving data from a user, the data being associated with any one or more of the vessel and / or associated components, the type of vessel and / or associated components, the type of system in which the vessel and / or associated components operate, the operational mode(s) of the vessel and / or associated components, the user(s) of the vessel and / or associated components, one or more environmental parameters, one or more failure modes of the vessel and / or associated components, or any combination thereof. According to some embodiments, the user interface module 614 may include any one or more of a keyboard, a display, a touchscreen, a mouse, one or more buttons, or any combination thereof. According to some embodiments, the user interface module 614 may include a configuration file that may be automatically and / or manually generated by a user. According to some embodiments, the configuration file may be configured to identify at least three dimensions and / or liquid levels within the vessel and / or associated components. According to some embodiments, the configuration file may be configured to allow the user to mark and / or select at least three dimensions.

[0308] According to some embodiments, the system 600 may include a storage module 604 configured to store data and / or instructions (or code) for execution by the processor 602. According to some embodiments, the storage module 604 may be in communication (or operative communication) with the processor 602. According to some embodiments, the storage module 604 may include a database 608 configured to store data associated with any one or more of the system 600, the structure, user input data, one or more training sets (or data sets used to train one or more of the algorithms), or any combination thereof. According to some embodiments, the storage module 604 may include one or more algorithms 610 (or at least one computer code) stored thereon and configured to be executed by the processor 602. According to some embodiments, the one or more algorithms 610 may be configured to analyze and / or classify received signals, as described in more detail elsewhere herein. According to some embodiments, and as described in more detail elsewhere herein, the one or more algorithms 610 may include one or more preprocessing techniques for preprocessing received signals. According to some embodiments, the one or more algorithms 610 may include one or more machine learning models.

[0309] According to some embodiments, the one or more algorithms 610 may include a change detection algorithm configured to identify a change in the received signal. According to some embodiments, the one or more algorithms 610 and / or change detection algorithm may be configured to receive signals from the optical sensor(s) 612 to obtain data associated with at least one failure mode characteristic of the structure and / or identify at least one change in the received signal.

[0310] According to some embodiments, the one or more algorithms 610 may include a classification algorithm configured to classify the identified changes. According to some embodiments, the classification algorithm may be configured to classify the identified changes as faults and / or trends. According to some embodiments, the classification algorithm may be configured to classify the identified changes as normal operation (or movement) of the container and / or associated components.

[0311] According to some embodiments, one or more algorithms 610 may be configured to analyze faults and / or trends (or identified changes classified as faults and / or trends). According to some embodiments, one or more algorithms 610 may be configured to output a signal (or alarm) indicative of the identified change associated with a failure mode.

[0312] According to some embodiments, such as that shown in FIG. 7, the method may include signal acquisition 802, i.e., receiving one or more signals. According to some embodiments, the method may include receiving the one or more signals from at least one optical sensor affixed on or near the vessel and / or associated components, such as, for example, one or more sensors 612 of system 600. According to some embodiments, the one or more signals may include one or more images. According to some embodiments, the one or more signals may include one or more portions of an image. According to some embodiments, the one or more signals may include a set of images, such as a packet of images. According to some embodiments, the one or more signals may include one or more videos. According to some embodiments, the one or more signals may include one or more video frames.

[0313] According to some embodiments, the method may include preprocessing (804) one or more received signals. According to some embodiments, the preprocessing may include converting the one or more received signals into electronic signals (e.g., from optical signals to electrical signals). According to some embodiments, the preprocessing may include generating one or more images, one or more sets of images, and / or one or more videos from the one or more signals. According to some embodiments, the preprocessing may include dividing the one or more images, one or more portions of one or more images, one or more sets of images, and / or one or more videos into multiple tiles. According to some embodiments, the preprocessing may include applying one or more filters to the one or more images, one or more portions of one or more images, one or more sets of images, one or more videos, one or more video frames, and / or multiple tiles. According to some embodiments, the one or more filters may include one or more noise reduction filters.

[0314] According to some embodiments, the method may include stitching together multiple signals obtained from two or more optical sensors. According to some embodiments, the method may include stitching together multiple signals in real time.

[0315] According to some embodiments, the method may include applying a change detection algorithm 808 (e.g., such as one or more algorithms 610 of system 600) to one or more received signals, one or more images, one or more portions of one or more images, one or more sets of images, and / or one or more videos configured to detect changes therein, i.e., values calculated based thereon, such as, for example, planes, vectors, angles, etc. According to some embodiments, the change detection algorithm may include one or more machine learning models 822.

[0316] According to some embodiments, faults and / or trends may indicate that the container and / or associated components need to be monitored, for example, for changes in volume and / or rate of volume change, cyclical changes in volume and / or rate of volume change, recurrence of changes in volume and / or rate of volume change, etc.

[0317] According to some embodiments, the method may include obtaining data associated with at least one failure mode characteristic of the vessel and / or associated components, or failure mode identification 806. According to some embodiments, the data associated with the at least one failure mode characteristic of the vessel and / or associated components may include a type of failure mode. According to some embodiments, the data associated with the at least one failure mode characteristic of the vessel and / or associated components may include a location or range of locations of the failure mode on the structure and / or a particular type of failure mode.

[0318] According to some embodiments, the failure mode may include one or more aspects that may cause failure in the vessel and / or associated components. According to some embodiments, and as described in more detail elsewhere herein, the failure mode may include a significant development of an identified fault and / or trend. According to some embodiments, the failure mode may include any one or more of a change in dimension, a change in position, a change in color, a change in texture, a change in size, a change in appearance, a fracture, damage to the structure, a crack, a crack size, a critical crack size, a crack location, a crack propagation, a change in orientation, a change in acceleration, a specified pressure applied to the structure, a change in the movement of one component relative to another component, a defect diameter, a cut, warping, expansion, deformation, abrasion, wear, corrosion, oxidation, a leak volume, a leak rate, a change in the leak rate, a volume of accumulated liquid, a rate of liquid accumulation, a change in evaporation rate, a size of a formed bubble, an eruption, a liquid flow rate, a liquid volume, a change in color, a change in appearance, or any combination thereof.

[0319] According to some embodiments, the method may include obtaining data associated with at least one failure mode characteristic of the vessel and / or associated components by receiving user input. According to some embodiments, the method may include obtaining data associated with at least one failure mode characteristic of the vessel and / or associated components by analyzing the received signals to detect at least one change that may be associated with a failure mode. According to some embodiments, the method may include obtaining data associated with at least one failure mode characteristic of the vessel and / or associated components by analyzing the received signals to detect potential failure modes. According to some embodiments, the method may include obtaining data associated with at least one failure mode characteristic of the vessel and / or associated components by analyzing the received signals to detect one or more previously unknown failure modes.

[0320] According to some embodiments, obtaining data associated with the characteristic of at least one failure mode of the vessel and / or associated components includes receiving input data from a user. According to some embodiments, the user may use the user interface module 614 to input data associated with the characteristic of at least one failure mode of the vessel and / or associated components. According to some embodiments, the method may include monitoring the structure based, at least in part, on the input data received from the user. According to some embodiments, the user may input a type of failure mode of the vessel and / or associated components. According to some embodiments, the user may input a location of the failure mode. According to some embodiments, the user may identify one or more locations as prone to failure and / or prone to fault development.

[0321] According to some embodiments, the method may include automatically obtaining data associated with at least one failure mode characteristic of the vessel and / or associated component. According to some embodiments, the method may include obtaining data associated with at least one failure mode characteristic of the vessel and / or associated component without user input. According to some embodiments, the method may include analyzing the received signals to automatically obtain data from a database, such as database 608. According to some embodiments, one or more algorithms 610 may be configured to identify one or more failure modes in the database, which may be associated with identified changes and / or trends in received signals of optical sensors configured to be mounted within or within view of the vessel and / or associated component and observing the vessel and / or associated component. According to some embodiments, the method may include searching the database for possible failure modes of the identified changes and / or trends. According to some embodiments, the method may include obtaining data from the database, the data associated with possible failure modes of the identified changes and / or trends.

[0322] According to some embodiments, the method may include obtaining data associated with characteristics of at least one failure mode of the vessel and / or associated components by identifying a previously unknown failure mode. According to some embodiments, identifying the previously unknown failure mode may include applying the received signals and / or the identified changes and / or trends to a machine learning algorithm 824 configured to determine a failure mode of the vessel and / or associated components. According to some embodiments, the machine learning algorithm 824 may be trained to identify potential failure modes of the identified changes and / or trends.

[0323] According to some embodiments, the method may include identifying at least one change and / or trend in the received signal at step 704. According to some embodiments, the method may include applying the received signal to a change detection algorithm, such as, for example, change detection algorithm 808, configured to detect (identify) at least one change and / or trend in the received signal.

[0324] According to some embodiments, identifying at least one change and / or trend in the signal may include identifying a change and / or trend in the rate of change in the signal. For example, the algorithm may be configured to identify periodically occurring changes and / or trends in the analyzed signal, and then the analyzed signal may be "reverted" to a previous state (e.g., prior to the change in the analyzed signal). According to some embodiments, the algorithm may be configured to identify a change and / or trend in the rate of occurrence of the identified changes and / or trends.

[0325] Advantageously, with respect to monitoring of a vessel and / or associated component that may rotate, the analyzed signals received from the inclinometers and associated optical sensors located near the vessel and / or associated component may vary periodically in correlation with the rotation of the vessel and / or associated component. Therefore, and as explained in more detail elsewhere herein, to detect changes in the vessel and / or associated component, an algorithm may first detect the periodic occurrence of changes while taking into account the rotation of the vessel and / or associated component.

[0326] Advantageously, for example, for monitoring a container and / or associated components that may move linearly (e.g., up and down, left and right, etc.), such as an elevator or train, the analyzed signals received from the inclinometer and associated optical sensor located near the elevator may change periodically in correlation with the movement of the container and / or associated components. Therefore, and as described in more detail elsewhere herein, to detect changes in the container and / or associated components, an algorithm may first detect the periodic occurrence of changes while taking into account the movement of the container and / or associated components.

[0327] According to some embodiments, the term "analyzed signal," as used herein, may describe any one or more of the received signals, such as raw signals from one or more optical sensors, processed or pre-processed signals from one or more optical sensors, one or more images, one or more packets of images, one or more portions of one or more images, one or more videos, one or more portions of one or more videos, or any combination thereof. According to some embodiments, identifying at least one change and / or trend in the analyzed signal may include analyzing raw data of the received signal.

[0328] According to some embodiments, the change detection algorithms 808 may include any one or more of binary change detection, quantitative change detection, and qualitative change detection.

[0329] According to some embodiments, binary change detection may include an algorithm configured to classify an analyzed signal as having a change or not having a change. According to some embodiments, binary change detection may include an algorithm configured to compare two or more analyzed signals. According to some embodiments, for comparisons indicating that the compared analyzed signals are the same or essentially the same, the classifier labels the analyzed signal as having no detected (or identified) change. According to some embodiments, for comparisons indicating that the compared analyzed signals are different, the classifier labels the analyzed signal as having a detected (or identified) change. According to some embodiments, two or more analyzed signals that are different may have at least one pixel that is different. According to some embodiments, two or more analyzed signals that are the same may have identical characteristics and / or pixels. According to some embodiments, the algorithm may be configured to set a threshold number of different pixels above which two analyzed signals may be considered different.

[0330] Advantageously, the change detection algorithm 808 allows for rapid detection of changes in the analyzed signal and can be very sensitive to even the slightest changes therein. Even more so, binary change detection detection and alerting can occur within a single signal, e.g., within a few milliseconds depending on the signal output rate of an optical sensor, or for optical sensors including cameras, within a single image frame, e.g., within a few milliseconds depending on the frame rate of the camera.

[0331] According to some embodiments, a binary change detection algorithm may, for example, analyze the analyzed signal to determine whether non-black pixels change to black over time, thereby indicating a possible change in the position of the structure, possibly due to deformation or due to a change in the position of other components of the vessel and / or associated components. According to some embodiments, if the binary change detection algorithm detects a change in the signal, a warning signal (or alarm) may be generated to alert the device or a technician that maintenance may be required.

[0332] According to some embodiments, the binary change detection algorithm may be configured to determine the cause of the identified change using one or more machine learning models. According to some embodiments, the method may include determining the cause of the identified change by applying the identified change to a machine learning algorithm. For example, for black pixels that may change to a color other than black over time (or through successive analyzed signals), the machine learning algorithm may output that the change indicates a change in the container and / or associated components, e.g., due to overheating. According to some embodiments, the method may include generating a signal, such as an informational or warning signal, if necessary. According to some embodiments, the warning signal may be a one-time signal or a continuous signal that may require some form of action to reset the warning signal, for example.

[0333] According to some embodiments, the method may include identifying at least one change in the signal by analyzing dynamic motion of the container and / or associated components. According to some embodiments, dynamic motion may include any one or more of vertical motion, linear motion, rotational motion, cyclic (repetitive) motion, rocking motion, damage, defects, cracks, fractures, structural damage, changes in orientation, rotation, warping, expansion, deformation, abrasion, wear, corrosion, oxidation, changes in dimension, changes in position, changes in size, or any combination thereof.

[0334] According to some embodiments, change detection may include quantitative change detection. According to some embodiments, quantitative change detection may include an algorithm configured to determine whether a change in magnitude above a certain threshold has occurred in the analyzed signal. According to some embodiments, a change in magnitude above a certain threshold may include a cumulative change in magnitude regardless of time, and / or a rate of change (or rates of change) in magnitude. For example, a value reflecting a change in magnitude may represent the number of pixels that have changed, the percentage of pixels that have changed, the total difference in the numerical values of one or more pixels within the field of view (or analyzed signal), combinations thereof, and the like. According to some embodiments, the quantitative change detection algorithm may output quantitative data associated with the change in the analyzed signal.

[0335] According to some embodiments, the change detection may include a qualitative change detection algorithm. According to some embodiments, the qualitative change detection algorithm may include an algorithm configured to classify the analyzed signal as indicative of a change in the structure. According to some embodiments, the qualitative change detection algorithm may include a machine learning model configured to receive the analyzed signal and classify the analyzed signal into categories including at least: including a change in behavior of the vessel and / or associated components, and not including a change in behavior of the vessel and / or associated components.

[0336] According to some embodiments, the change detection algorithm may be configured to analyze other, more complex changes in the analyzed signal generated by the optical sensor with the assistance of a machine learning model. According to some embodiments, the machine learning model may be trained to recognize complex and diverse changes. According to some embodiments, the machine learning model may be able to identify complex changes, such as for a signal generated by an optical sensor that may begin to exhibit some periodic instability, such that the signal appears normal for a period of time, then abnormal for a period of time before appearing normal again. The signal may then exhibit some similar, but different, abnormality, and the change detection algorithm may be configured to analyze the changes and train itself to detect probable causes of the instability over time. According to some embodiments, the change detection algorithm may be configured to generate a warning or informational signal, if necessary, to alert a user to changes in the container and / or related components.

[0337] Reference is made to FIG. 9 , which illustrates an exemplary schematic block diagram of a system for monitoring potential failures of a vessel and / or associated components, according to some embodiments of the present invention, and FIG. 10 , which illustrates an exemplary schematic block diagram of a system for monitoring potential failures in a structure in communication with a cloud storage module, according to some embodiments of the present invention.

[0338] As shown in the exemplary monitoring systems of FIGS. 9 and 10 , an optical sensor may receive one or more signals from a container and / or associated components 902. According to some embodiments, the optical sensor may generate a signal, such as, for example, an image or video, and transmit the generated signal to an image processing module 906. According to some embodiments, the image processing module processes the signal generated by the optical sensor (or image sensor 904 in FIG. 9 and FIG. 5 ) so that the data can be analyzed by a data analysis module 918 (or algorithms 610 as described herein). According to some embodiments, the image processing module 906 may include any one or more of an image / frame acquisition module 908, a frame rate control module 910, an exposure control module 912, a noise reduction module 914, a color correction module 916, and the like. According to some embodiments, the data analysis module (or algorithms 610 as described herein) may include a change detection algorithm, such as, for example, a change detection algorithm 808. According to some embodiments, user interface module 932 (described below) may issue any warning signals resulting from signal analysis performed by the algorithms. According to some embodiments, any one or more of the signals and / or algorithms may be stored on cloud storage 1002. According to some embodiments, the processor may be located on the cloud, such as, for example, cloud computing 1004, which may be co-located with the embedded processor.

[0339] According to some embodiments, the data analysis module 918 may include any one or more of a binary (visual) change detector 920 (or a binary change detection algorithm as described in more detail elsewhere herein), a quantitative (visual) change detector 922 (or a quantitative change detection algorithm as described in more detail elsewhere herein), and / or a qualitative (visual) change detector 924 (or a qualitative change detection algorithm as described in more detail elsewhere herein). According to some embodiments, the qualitative (visual) change detector 924 may include any one or more of an edge detector 926 and / or a shape (deformation) detector 928. According to some embodiments, the data analysis module 918 may include and / or be in communication with a user interface module 932. According to some embodiments, and as described in more detail elsewhere herein, the user interface module 932 may include a monitor 934. According to some embodiments, the user interface module 932 may be configured to output alarms and / or notifications 936 / 826.

[0340] According to some embodiments, a change detection algorithm, such as, for example, change detection algorithm 808, may be implemented on an embedded processor or a processor near the optical sensor. Thus, a change detection algorithm, such as, for example, change detection algorithm 808, may enable rapid detection and avoid time lags associated with transmitting data to a remote server (such as the cloud).

[0341] According to some embodiments, once changes are identified using a change detection algorithm, the identified changes may be classified using a classification algorithm. According to some embodiments, at step 706, the method may include analyzing the changes identified in the received signals (or analyzed signals) and classifying whether the changes identified in the received signals (or analyzed signals) are associated with a failure mode of the vessel and / or associated components, thereby labeling the identified changes as faults and / or trends. According to some embodiments, the method may include applying the received signals (or analyzed signals) to an algorithm configured to analyze the changes identified in the received signals and classify whether the changes identified in the received signals are associated with a failure mode of the structure based, at least in part, on the acquired data.

[0342] According to some embodiments, the method may include applying the identified change to an algorithm configured to perform a match between the identified change and the acquired data associated with a failure mode. According to some embodiments, the algorithm may be configured to determine whether the identified change may potentially develop into one or more failure modes. According to some embodiments, the algorithm may be configured to determine whether the identified change may potentially develop into one or more failure modes based at least in part on the acquired data. According to some embodiments, the method may include labeling the identified change as a fault and / or trend if the algorithm determines that the identified change may potentially develop into one or more failure modes.

[0343] For example, an identified change in liquid surface level, liquid volume and / or change in liquid volume and / or rate of change of liquid volume in the container may be identified as a fault and / or trend once the liquid surface level liquid volume and / or liquid volume and / or change in liquid volume and / or rate of change of liquid volume in the container reaches a certain size which may be associated with a failure mode that is a critical crack size or critical defect size.

[0344] For example, an identified change in liquid surface level, liquid volume and / or rate of change of liquid volume and / or rate of change of liquid volume in the container may be identified as a fault and / or trend once the identified change in liquid surface level, liquid volume and / or rate of change of liquid volume and / or rate of change of liquid volume in the container reaches a certain threshold that may be associated with a significant failure mode.

[0345] For example, an identified change in the rate of variation of the liquid surface level, the volume of the liquid and / or the rate of change of the volume of the liquid within the container is a fault and / or a trend once the rate of variation reaches a certain threshold that may be associated with a significant failure mode.

[0346] According to some embodiments, changes in liquid surface level, liquid volume and / or change in liquid volume and / or rate of change of liquid volume in a container may be associated with any one or more of structural damage, cracks, defects, evaporation, leaks, rotation, warping, expansion, deformation, overheated engines and / or machinery, clogged pipes and / or nozzles, open and / or leaking plugs, worn gaskets and / or piston rings, linear motion, rotational motion, cyclic (repetitive) motion, oscillating motion, changes in speed of motion, or any combination thereof.

[0347] According to some embodiments, changes in the liquid surface level, the volume of the liquid, and / or the rate of change of the volume of the liquid in the container can be used to monitor and / or measure the flow and / or consumption of the liquid. Optionally, this can be analyzed to provide an indication of the condition of the machine using the liquid. For example, measuring the oil level in the container can be used to monitor engine oil consumption, which can be used to detect oil burning problems, faulty (e.g., worn) valve seals, faulty piston rings, and / or leaks; measuring the coolant level in the container can be used to monitor coolant consumption of a machine or system, for example, high consumption can indicate an overheated machine, a leak in the cooling system, a damaged radiator, an open radiator cap, etc., while low consumption can indicate clogged pipes and / or nozzles.

[0348] According to some embodiments, the algorithm may identify faults and / or trends using one or more machine learning models. According to some embodiments, and as described in more detail elsewhere herein, the machine learning models may be trained over time to identify one or more faults and / or trends. According to some embodiments, the machine learning models may be trained to identify previously unknown faults and / or trends by analyzing baseline behavior of the vessel and / or associated components.

[0349] Advantageously, using a machine learning model to identify faults and / or trends allows for the detection of different types of faults and / or trends, or even similar faults and / or trends that may appear differently in different containers and / or associated components, or even at different angles of the optical sensor. Thus, the machine learning model may increase the sensitivity of the detection of one or more faults and / or trends.

[0350] According to some embodiments, the monitoring system and / or one or more algorithms may include one or more suppressor algorithms 810 (also referred to herein as suppressors 810). According to some embodiments, the one or more suppressor algorithms may be configured to classify whether detected faults and / or trends may escalate into failures, such as those illustrated by failure mode nodal points 812 in FIG. 8. According to some embodiments, the one or more suppressor algorithms 810 may include one or more machine learning models 820. According to some embodiments, the one or more suppressor algorithms 810 may classify the faults and / or trends as benign.

[0351] According to some embodiments, in step 708, for identified faults and / or trends, the method may include outputting a signal, such as a warning signal, indicating the identified change associated with the failure mode. According to some embodiments, the method may include storing the identified change in a database, thereby augmenting the data set for training one or more machine learning models.

[0352] According to some embodiments, the method may include labeling data associated with any one or more of the classifications as indicated by failure mode identification 806, change detection algorithm 808, suppressor 810, and failure mode nodal point 812. According to some embodiments, the method may include supervised labeling 816, such as manual labeling of data using user input (or expert knowledge).

[0353] According to some embodiments, if an identified change is classified as not associated with a failure mode (such as that indicated by arrow 850 in FIG. 8 ), it may be identified (or classified) as normal, or in other words, as normal behavior or operation of the vehicle and / or vessel and / or associated components. According to some embodiments, for an identified change classified as normal, the method may include storing data associated with the identified change, thereby adding the identified change to a database to augment the data set for training 818 one or more machine learning models (e.g., one or more machine learning models 820 / 822 / 824). According to some embodiments, the method may include using the data associated with the identified change for further investigation, which may include at least one of adding a failure mode, updating an algorithm configured to identify the change, and training the algorithm to ignore the identified change in the future, thereby improving the algorithm configured to identify the change.

[0354] According to some embodiments, if the identified change is classified as associated with a failure mode (such as that indicated by arrow 855 in FIG. 8 ), the method may include trend analysis and failure prediction 814. According to some embodiments, in step 710, the method may include generating at least one trend model. According to some embodiments, the method may include generating at least one trend model based on the plurality of analyzed signals. According to some embodiments, the method may include generating at least one trend model by calculating the evolution of the identified change in the analyzed signals over time. According to some embodiments, the trends may include rates of change of faults and / or trends. According to some embodiments, the method may include generating at least one trend model by calculating correlations of rates of change of faults and / or trends with one or more environmental parameters. According to some embodiments, the one or more environmental parameters may include any one or more of temperature, season or time of year, barometric pressure, time of day, operational hours of the structure, operational duration of the vessel and / or associated components (e.g., age, cycle time, run time, down time, etc. of the vessel and / or associated components), identified users of the vessel and / or associated components, GPS location, operational mode of the vessel and / or associated components (e.g., continuous, periodic, etc.), and / or any combination thereof.

[0355] According to some embodiments, the operational mode of the vessel and / or associated components may include any one or more of the distance traveled or moved by the vehicle and / or vessel and / or associated components, the frequency of movement, the speed of movement, the power consumption during operation, the change in power consumption during operation, and the like. According to some embodiments, generating at least one trend model by calculating a correlation of the rate of change of the fault and / or trend with one or more environmental parameters may include taking into account different influences in the surroundings of the vessel and / or associated components. According to some embodiments, the method may include mapping different environmental parameters that affect the operation of the vessel and / or associated components, where the environmental parameters may change over time. Optionally, the monitoring system may obtain data regarding one or more environmental parameters from an online database, such as a mapping database, a weather database, a calendar, etc., for inclusion in the analysis.

[0356] According to some embodiments, at step 712, the method may include alerting a user of the predicted failure based at least in part on the generated model. According to some embodiments, the method may include outputting a notice and / or alert 826 to the user. According to some embodiments, the method may include alerting a user of the predicted failure. According to some embodiments, the method may include alerting a user of the predicted failure by outputting any one or more of the time (or time range) of the predicted failure and characteristics of the failure mode, or any combination thereof. According to some embodiments, the method may include outputting a prediction of when an identified trend is likely to result in a failure of the vessel and / or associated components based at least in part on the generated model. According to some embodiments, predicting when a failure is likely to occur in the vessel and / or associated components may be based at least in part on known future environmental parameters. According to some embodiments, predicting when a failure is likely to occur in the vessel and / or associated components may be based at least in part on known schedules, such as, for example, a calendar.

[0357] According to some embodiments, a system for monitoring potential faults in a vessel and / or associated components, such as system 600, may include one or more illumination sources configured to illuminate at least a portion of the liquid surface level, the vessel, and / or associated components. According to some embodiments, the one or more illumination sources may include any one or more of a light bulb, a light-emitting diode (LED), a laser, a fiber optic illumination source, a fiber optic cable, and the like. According to some embodiments, a user may input the location (or location) of the illumination source, the illumination direction (or, in other words, the direction the light is pointed), the duration of illumination, wavelength, intensity, and / or frequency of illumination of the illumination source associated with one or more optical sensors. According to some embodiments, one or more algorithms may be configured to automatically position one or more illumination sources. According to some embodiments, one or more algorithms may direct the operating mode of one or more illumination sources. According to some embodiments, the one or more algorithms may direct and / or manipulate any one or more of the illumination intensity of one or more illumination sources, the number of powered illumination sources, the location of the powered illumination sources, and the wavelength, intensity, and / or frequency of illumination of one or more illumination sources, or any combination thereof.

[0358] Advantageously, an algorithm configured to direct and / or operate one or more illumination sources may increase the clarity of the received signal by reducing dark areas (e.g., areas from which light is not reflected and / or areas that were not illuminated) and may modify (or optimize) the color saturation of the received signal (or image).

[0359] According to some embodiments, the one or more algorithms may be configured to detect and / or calculate the position of the one or more illumination sources relative to the optical sensor(s), the duration of illumination, wavelength, intensity, and / or frequency of illumination. According to some embodiments, the one or more algorithms may be configured to detect and / or calculate the position of the one or more illumination sources relative to the optical sensor(s), the duration of illumination, wavelength, intensity, and / or frequency of illumination based at least in part on the analyzed signals. According to some embodiments, the processor may control the operation of the one or more illumination sources. According to some embodiments, the processor may control any one or more of the duration of illumination, wavelength, intensity, and / or frequency of illumination of the one or more illumination sources.

[0360] According to some embodiments, the method may include obtaining a location of one or more illumination sources relative to the optical sensor(s), a duration of illumination, a wavelength, an intensity, and / or a frequency of illumination. According to some embodiments, the method may include obtaining the location of the one or more illumination sources via any one or more of user input, detection, and / or using one or more algorithms. According to some embodiments, the method may include classifying whether an identified change in the (analyzed) signal is associated with a failure mode of the structure based, at least in part, on any one or more of the location(s), duration of illumination, wavelength, intensity, and frequency of illumination of the at least one illumination source.

[0361] According to some embodiments, the method may include outputting data associated with optimal locations for placement (or locations) of the one or more optical sensors, from which potential failure modes can be detected. According to some embodiments, the one or more algorithms may be configured to calculate at least one optimal location for placement (or location) of the optical sensor(s) based, at least in part, on the acquired data, data stored in a database, and / or user-entered data.

[0362] According to some embodiments, the illumination source may illuminate the liquid surface level, the container, and / or its associated components with one or more wavelengths from a broad spectral range, both visible and invisible. According to some embodiments, the illumination source may include a strobe and / or an illumination source configured to illuminate with short pulses. According to some embodiments, the illumination source may be configured to emit strobe light without the use of a global shutter sensor.

[0363] According to some embodiments, the wavelengths may include any one or more light in the ultraviolet region, the infrared region, or a combination thereof. According to some embodiments, the one or more illumination sources may be mobile or movable. According to some embodiments, the one or more illumination sources may change output wavelength during operation, change illumination direction during operation, change one or more lenses, and the like. According to some embodiments, the illumination source may be configured to change illumination using one or more optical fibers (FOs), for example, by using different fibers to generate light at different times or by combining two or more fibers simultaneously. According to some embodiments, the optical fiber may include one or more illumination sources, such as, for example, LEDs, attached thereto. According to some embodiments, the light intensity and / or wavelength of the LEDs may be changed using one or more algorithms, as described in more detail elsewhere herein.

[0364] Advantageously, illuminating the liquid surface level, the container and / or associated components may enable an optical sensor and / or processor to detect the dimensions of the container by analyzing shadows and / or reflections to verify that the system is intact and / or faulty (e.g., leakage and / or evaporation of liquid in the container, etc.). For example, defects may produce shadows that can be analyzed by one or more algorithms to detect as defects.

[0365] Advantageously, illuminating the container and / or associated components while receiving optical signals from the optical sensor(s) may enable detection of changes and / or trends in the liquid surface level, the liquid volume and / or the rate of change of the liquid volume in the container, which may be invisible to the human eye. According to some embodiments, the size of the change in the liquid surface level, the liquid volume and / or the rate of change of the liquid volume in the container may be less than about 25%, 20%, 15%, 10%, 5%, 3%, 1%, 0.5%, 0.25%. Each is a separate embodiment. According to some embodiments, the deviation of the liquid surface level, the liquid volume and / or the rate of change of the liquid volume in the container from a previously predetermined or pre-calculated value may be less than about 25%, 20%, 15%, 10%, 5%, 3%, 1%, 0.5%, 0.25%. Each is a separate embodiment.

[0366] Reference is now made to FIG. 11 , which is a simplified diagram of an exemplary vessel containing a liquid having a surface that is inclined relative to the vessel floor. The field of view 1114 of the optical sensor 1102 may be sufficient to identify several dimensional points (e.g., at least three dimensions, h1, h2, and h3, etc.), such as the liquid surface level and / or the intersection of the surface of the liquid 1110 in the vessel 1104 with the vessel wall 1118. Optionally, the field of view 1114 may be sufficient to view all or a portion of the vessel and / or may be enlarged to focus on one or more portions. From the dimensions, a liquid surface plane vector 1106 (perpendicular to the liquid surface plane 1112) may be calculated based on the liquid surface plane 1112. An orientation may be calculated from the deviation of the liquid surface plane vector 1106 from a vector perpendicular to the vessel horizontal plane 1108. Optionally, the height (h) of the liquid 1110 in the vessel 1104 may be measured relative to the height (H) of the vessel 1104. Optionally, the relative height of liquid 1110 in container 1104 may provide an indication of the volume of liquid in the container. Optionally, variations in the relative height of liquid 1110 in container 1104 may provide an indication of variations in the volume of liquid in the container. Optionally, variations in the relative height of liquid 1110 in container 1104 may provide an indication of the "health" of the container. Optionally, the container may be sealed (e.g., with a lid, cap, cover, cork, etc.). Optionally, the container may be hermetically sealed.

[0367] According to some embodiments, the container 1104 may have an undefined and / or amorphous shape whose volume can be calculated from its known data and / or height (H), length (L) and width (W), which may be equal, different, or a combination thereof. Optionally, the container may be any shape whose volume can be calculated, for example, using information from measurements, drawings, 3D files, etc.

[0368] According to some embodiments, the container may include a primary container and a secondary container fluidly connected to each other. Optionally, at least one of the optical sensor(s) is positioned with a field of view of the secondary container.

[0369] 12 is a simplified schematic diagram of a system for estimating liquid level, and therefrom liquid volume, according to some embodiments of the present invention. An optical sensor 1208 is positioned such that its field of view 1206 passes through a window 1204 in a container 1202, so that the level of a liquid surface 1212 of a liquid 1210 in the container 1202 can be determined.

[0370] 13 is a schematic diagram of a system for estimating liquid level and, therefrom, liquid volume, according to some embodiments of the present invention. For example, a vessel may include a primary vessel 1302 and a secondary vessel 1304 that are fluidly connected to each other. A liquid level 1310 in the secondary vessel 1304 is located within at least one field of view 1306 of one or more optical sensors 1308. The liquid level 1310 in the secondary vessel 1304 is the same as a liquid level 1314 in the primary vessel 1302, thereby allowing the liquid level 1314 of the liquid 1316 in the vessel to be determined. Optionally, the system may include one or more illumination sources. Optionally, the one or more illumination sources may be configured to illuminate the vessel, a window, the secondary vessel, or portions thereof.

[0371] General The terms "comprise," "comprising," "include," "including," "having," and their cognates mean "including, but not limited to."

[0372] The term "consisting of" means "including and limited to."

[0373] As used herein, singular forms such as "a," "an," and "the" include plural references unless the content clearly dictates otherwise.

[0374] Within this application, various quantifications and / or expressions may include the use of ranges. The range format should not be construed as an inflexible limitation on the scope of the disclosure. Accordingly, statements containing ranges should be considered to specifically disclose all possible subranges and individual numerical values within that range. For example, statements of a range such as 1 to 6 should be considered to specifically disclose subranges such as 1 to 3, 1 to 4, 1 to 5, 2 to 4, 2 to 6, 3 to 6, etc., as well as individual numbers within the stated range and / or subrange, e.g., 1, 2, 3, 4, 5, and 6. Whenever a numerical range is given in this document, it is meant to include any recited number (fractional or integer) within the stated range.

[0375] It will be understood that certain features that are described in the context of separate embodiments (e.g., for clarity) may also be provided in combination in a single embodiment. Various features of the present disclosure that are described in the context of a single embodiment (e.g., for brevity) may also be provided separately or in any suitable subcombination or suitable for use with any other described embodiment. Features described in the context of various embodiments should not be considered essential features of those embodiments unless the embodiment is inoperable without those elements.

[0376] While this disclosure has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications, and variations will be apparent to those skilled in the art. Accordingly, this application is intended to embrace all such alternatives, modifications, and variations that fall within the spirit and broad scope of the appended claims.

[0377] All references (e.g., publications, patents, patent applications) mentioned within this application are incorporated herein by reference in their entirety, e.g., as if each individual publication, patent, or patent application was individually indicated to be incorporated herein by reference. Citation or identification of any reference in this application should not be construed as an admission that such reference is available as prior art to the present disclosure. Additionally, any priority document(s) and / or document(s) (e.g., co-filed applications) related to this application are hereby incorporated herein by reference in their entirety.

[0378] Where section headings are used in this document, they should not necessarily be construed as limiting.

Claims

1. 1. A system for monitoring a liquid volume, comprising: acquiring at least one image of a liquid contained within the container from at least one optical sensor; estimating a volume of the liquid in the container from the at least one image; outputting an indication of the agreement of the estimated liquid volume with an expected liquid volume based on an analysis of the estimated volume of liquid; a processing circuit configured to perform the

2. The system of claim 1 , wherein the images are input from a plurality of optical sensors capturing images of the container in respective fields of view.

3. The indicator is the container; a machine utilizing said liquid; a vehicle utilizing said liquid; a mechanism utilizing said liquid; Heating, ventilation and air conditioning (HVAC) systems; and peripheral components, The system of claim 1 , further comprising assessing the health of at least one of:

4. The indicators are: the estimated liquid volume; the rate of change of the liquid volume over time; Predicting future liquid volumes; at least one of a frequency and an amplitude of liquid waves within the vessel; a color change of the liquid; a change in the opacity of the liquid; a change in the transparency of said liquid; a change in the viscosity of the liquid; the presence of particles in said liquid; Maintenance instructions; time-to-failure estimates; Fault alerts; and, Operational instructions in response to detected faults; The system of claim 1 , comprising at least one of:

5. 2. The system of claim 1, wherein the estimating comprises analyzing a distribution of intensities in at least one channel of the at least one image and identifying pixels having a distribution consistent with the presence of liquid.

6. The system of claim 1 , wherein the estimating comprises excluding pixels away from a main volume of the liquid from the liquid volume calculation.

7. The system of claim 1 , wherein the estimating comprises calculating the liquid volume based on a geometric analysis of a container shape.

8. The system of claim 1 , wherein the estimating is based on a statistical analysis of a sequence of images.

9. The system of claim 1 , wherein the estimating is further based on data obtained from a non-optical sensor.

10. The system of claim 1 , wherein the estimating is further based on data obtained from an external source.

11. The system of claim 1 , wherein the selection of the indicator for output is based on the current liquid volume.

12. The system of claim 1 , wherein the analysis is based on changes in the liquid volume over time.

13. The system of claim 1 , wherein the analysis is based on a trend analysis of changes in the liquid volume over time.

14. The system of claim 1 , wherein the at least one image shows at least two sides of the container.

15. The system of claim 1 , wherein the at least one image shows a portion of the container, the portion being wide enough to estimate a three-dimensional angle of the liquid relative to the container.

16. The system of claim 1 , wherein the at least one optical sensor is configured to capture the at least one image while the container is moving relative to a ground surface.

17. The system of claim 1 , wherein the at least one optical sensor is located external to the container.

18. The system of claim 1 , wherein the at least one optical sensor is disposed inside the container.

19. The indicators are: the estimated liquid volume; the rate of change of the liquid volume over time; A prediction of future liquid volume; and a prediction of variation in the rate of change of the liquid volume over time; The system of claim 1 , wherein the value is obtained from the data structure using at least one value of

20. The analysis: images collected during the use of said liquid; images collected during periods of non-use of said liquid; Images of similar containers collected during their use; Images of similar containers collected during periods of non-use; Images of different containers in similar machines collected over the course of their use; Images of different containers in similar machines collected during periods of non-use; Images of other components; and non-image data associated with some or all of the images in the training set; The system of claim 1 is based on a machine learning model trained with a training set including at least one of:

21. The system of claim 20 , wherein the machine learning model is a neural network.

22. The system of claim 20 , wherein the training of the machine learning model is performed using a supervised learning algorithm.

23. 21. The system of claim 20, wherein the training of the machine learning model is performed using an unsupervised learning algorithm.

24. The system of claim 20 , wherein the training set includes non-image data associated with at least some of the images in the training set.

25. 1. A method for monitoring a liquid volume, comprising: acquiring at least one image of a liquid contained within the container from at least one optical sensor; estimating a volume of the liquid in the container from the at least one image; outputting an indication of the agreement of the estimated liquid volume with an expected liquid volume based on an analysis of the estimated volume of liquid; A method comprising:

26. 26. The method of claim 25, wherein the images are input from a plurality of optical sensors capturing images of the container in respective fields of view.

27. The indicators are: the container; a machine utilizing said liquid; a vehicle utilizing said liquid; a mechanism utilizing said liquid; Heating, ventilation and air conditioning (HVAC) systems; and peripheral components, 26. The method of claim 25, comprising assessing the health of at least one of:

28. The indicators are: the estimated liquid volume; the rate of change of the liquid volume over time; Predicting future liquid volumes; at least one of a frequency and an amplitude of liquid waves within the vessel; a color change of the liquid; a change in the opacity of the liquid; a change in the transparency of said liquid; a change in the viscosity of the liquid; the presence of particles in said liquid; Maintenance instructions; time-to-failure estimates; Fault alerts; and Operational instructions in response to detected faults; 26. The method of claim 25, comprising at least one of:

29. 26. The method of claim 25, wherein the estimating comprises analyzing a distribution of intensities in at least one channel of the at least one image and identifying pixels having a distribution consistent with the presence of liquid.

30. 26. The method of claim 25, wherein the estimating comprises excluding pixels away from the main volume of the liquid from the calculation of the liquid volume.

31. 26. The method of claim 25, wherein the estimating comprises calculating the liquid volume based on a geometric analysis of a container shape.

32. The method of claim 25 , wherein the estimating is based on a statistical analysis of a series of images.

33. The method of claim 25 , wherein the estimating is further based on data obtained from a non-optical sensor.

34. 26. The method of claim 25, wherein the estimating is further based on data obtained from an external source.

35. 26. The method of claim 25, wherein the analysis is based on a current liquid volume.

36. 26. The method of claim 25, wherein the analysis is based on changes in the liquid volume over time.

37. 26. The method of claim 25, wherein the analysis is based on a trend analysis of changes in the liquid volume over time.

38. 26. The method of claim 25, wherein the at least one image shows at least two sides of the container.

39. 26. The method of claim 25, wherein the at least one image shows a portion of the container, the portion being wide enough to estimate a three-dimensional angle of the liquid relative to the container.

40. 26. The method of claim 25, wherein the images are captured while the container is moving relative to the ground.

41. 26. The method of claim 25, wherein the at least one optical sensor is located external to the container.

42. 26. The method of claim 25, wherein the at least one optical sensor is disposed inside the container.

43. The indicator: the estimated liquid volume; the rate of change of the liquid volume over time; A prediction of future liquid volume; and a prediction of variation in the rate of change of the liquid volume over time; 26. The method of claim 25, further comprising retrieving from the data structure using at least one value of

44. The analysis: images collected during the use of said liquid; images collected during periods of non-use of said liquid; Images of similar containers collected during their use; Images of similar containers collected during periods of non-use; Images of different containers in similar machines collected over the course of their use; Images of different containers in similar machines collected during periods of non-use; Images of other components; and non-image data associated with some or all of the images in the training set; 26. The method of claim 25, based on a machine learning model trained with a training set including at least one of:

45. 45. The method of claim 44, wherein the machine learning model is a neural network.

46. 45. The method of claim 44, wherein the training of the machine learning model is performed using a supervised learning algorithm.

47. 45. The method of claim 44, wherein the training of the machine learning model is performed using an unsupervised learning algorithm.

48. 45. The method of claim 44, wherein the training set includes non-image data associated with at least some of the images in the training set.

49. 26. A non-transitory storage medium storing program instructions which, when executed by a processor, cause the processor to perform the method of claim 25.

Images