Systems and methods for detecting anomalies associated with dispensers using machine learning and vision

Abstract

A system configured to determine a presence of an anomaly associated with a dispensing system component, fluid supply, and / or a tool of a dispenser includes a fluid supply for containing a fluid, a tool for supporting a part, one or more sensors configured to sense characteristics of the dispensing system component, fluid supply, and / or tool, and a controller configured to actuate the one or more sensors to capture initial data associated with the dispensing system component, fluid supply, and / or tool at a first time, process the initial data in a trained neural network to determine a presence of an anomaly associated with the dispensing system component, fluid supply, and / or tool, log the presence of the anomaly, generate and send an alert to a human machine interface indicating the presence of the anomaly, actuate the one or more sensors to capture subsequent data associated with the dispensing system component, fluid supply, and / or tool at a second time after the first time, and process the subsequent data to determine whether the anomaly has been corrected.

Description

SYSTEMS AND METHODS FOR DETECTING ANOMALIES ASSOCIATED WITH DISPENSERS USING MACHINE LEARNING AND VISIONCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 520,557 filed on August 18, 2023 and U.S. Provisional Application Serial No. 63 / 520,565 filed on August 18, 2023, each of which are hereby incorporated by reference in their entireties for all purposes as if fully set forth herein.TECHNICAL FIELD

[0002] The present disclosure relates to systems and methods for determining a presence of an anomaly associated with a dispensing system component of a dispenser (e.g., a low level of fluid in a fluid supply, a high level of fluid accumulation on a tool), namely by capturing and processing data associated with the dispensing system component in a trained neural network.BACKGROUND

[0003] Dispensing system components and characteristics thereof (e.g., fluid levels of a fluid supply, fluid accumulation on a tool) are important to monitor in automated dispensing systems so that operators and / or automated processes can determine the presence of an anomaly associated with the dispensing system components and / or predict when corrective action should be taken to correct the anomaly so as to maintain productivity, prevent yield problems in production, and / or make efficient use of materials.

[0004] Certain schemes for monitoring dispensing system components, namely fluid syringes, are known but suffer from various shortcomings, such as by requiringconsistent operator oversight or calibration and / or being limited in some regard (e.g., accuracy, breadth). For example, a fluid level within a fluid syringe is typically monitored using one or more of the following methods, each of which suffers from one or more shortcomings:

[0005] Therefore, there is a need for systems and methods for determining a presence of an anomaly associated with a dispensing system component of a dispenser (e.g., a low level of fluid in a fluid supply, a high level of fluid accumulation on a tool), namely by capturing and processing data associated with the dispensing systemcomponent in a trained neural network. Such systems and methods are particularly useful and desirable in high volume electronics processing I packaging where process monitoring and predictive maintenance are valued.SUMMARY

[0006] In an example, a system configured to determine a presence of an anomaly associated with a fluid supply of a dispenser is provided. The system includes a fluid supply for containing a fluid. The system further includes a tool for supporting a part. The system further includes one or more sensors configured to sense characteristics of the dispensing system component. The system further includes a controller. The controller is configured to actuate the one or more sensors to capture initial data associated with the fluid supply at a first time. The controller is further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the fluid supply. The controller is further configured to log the presence of the anomaly. The controller is further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly. The controller is further configured to actuate the one or more sensors to capture subsequent data associated with the fluid supply at a second time after the first time. The controller is further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0007] In certain examples, the one or more sensors may include a camera. In such examples, the controller may be configured to actuate the camera to capture an initial image of the fluid supply at the first time and actuate the camera to capture a subsequent image of the fluid supply at the second time. In examples, the anomaly may be a level of fluid in the fluid supply. In such examples the trained neural networkmay be trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold. In such examples, the controller may be configured to categorize the level of fluid in the fluid supply utilizing the trained neural network as high, medium, or low. In the same or other examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. In the same or other examples, the alert may indicate that the level of fluid in the fluid supply is less than the predetermined threshold. In the same or other examples, the alert may provide directions to the user for refilling the fluid supply such that the level of fluid is greater than or equal to the predetermined threshold. In the same or other examples, the alert may provide directions to the user for replacing the fluid supply with a second fluid supply having a level of fluid greater than or equal to the predetermined threshold. In examples, the controller may be configured to determine a predicted level of fluid in the fluid supply based on an amount of fluid dispensed by the dispenser, determine a sensed level of fluid in the fluid supply based on the initial image of the fluid supply, and compare the predicted level of fluid in the fluid supply to the sensed level of fluid in the fluid supply to identify an excursion. In examples, the trained neural network may be trained based on data associated with a plurality of fluid supplies. In such examples, the controller may determine the presence of the anomaly associated with the fluid supply utilizing the trained neural network based on a classification of the initial data.

[0008] In examples, the system may further include a dispensing head. In such examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. In further examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head tocease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. In further examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0009] In another example, a system configured to determine a presence of an anomaly associated with a tool of a dispenser is provided. The system includes a fluid supply for containing a fluid. The system further includes a tool for supporting a part. The system further includes one or more sensors configured to sense characteristics of the dispensing system component. The system further includes a controller. The controller is configured to actuate the one or more sensors to capture initial data associated with the tool at a first time. The controller is further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the tool. The controller is further configured to log the presence of the anomaly. The controller is further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly. The controller is further configured to actuate the one or more sensors to capture subsequent data associated with the tool at a second time after the first time. The controller is further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0010] In certain examples, the one or more sensors may include a camera. In such examples, the controller may be configured to actuate the camera to capture an initial image of the tool at the first time and actuate the camera to capture a subsequent image of the tool at the second time. In examples, the anomaly may be a level of fluid accumulation on the tool. In such examples, the trained neural network may be trainedbased on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. In the same or other examples, the alert may indicate that the level of fluid accumulation is greater than the predetermined threshold. In the same or other examples, the alert may provide directions to the user for cleaning the tool such that the level of fluid accumulation is less than the predetermined threshold. In examples, the controller may be configured to determine a predicted level of fluid accumulation on the tool based on a number of parts unloaded from the tool, determine a sensed level of fluid accumulation on the tool based on the initial image of the tool, and compare the predicted level of fluid accumulation on the tool to the sensed level of fluid accumulation on the tool to identify an excursion. In examples, the trained neural network may be trained based on data associated with a plurality of tools. In such examples, the controller may determine the presence of the anomaly associated with the tool utilizing the trained neural network based on a classification of the initial data. In examples, the controller may be configured to repeat capturing and processing the initial data and the subsequent data each time a part is unloaded from the tool.

[0011] In examples, the system may further include a dispensing head. In such examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. In further examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. In further examples, the controller may be configured to send a signal to thedispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0012] In a further example, a system configured to determine a presence of an anomaly associated with a fluid supply and / or a tool of a dispenser is provided. The system includes a fluid supply for containing a fluid. The system further includes a tool for supporting a part. The system further includes one or more sensors configured to sense characteristics of the dispensing system component. The system further includes a controller. The controller is configured to actuate the one or more sensors to capture initial data associated with at least one of the fluid supply and the tool at a first time. The controller is further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the at least one of the fluid supply and the tool. The controller is further configured to log the presence of the anomaly. The controller is further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly. The controller is further configured to actuate the one or more sensors to capture subsequent data associated with the at least one of the fluid supply and the tool at a second time after the first time. The controller is further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0013] In examples, the system may further include a dispensing head. In such examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. In further examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of theanomaly. In further examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0014] In another example, a system configured to determine a presence of an anomaly associated with a dispensing system component of a dispenser is provided. The system includes a fluid supply for containing a fluid. The system further includes a tool for supporting a part. The system further includes one or more sensors configured to sense characteristics of the dispensing system component. The system further includes a controller. The controller is configured to actuate the one or more sensors to capture initial data associated with the dispensing system component at a first time. The controller is further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the dispensing system component. The controller is further configured to log the presence of the anomaly. The controller is further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly. The controller is further configured to actuate the one or more sensors to capture subsequent data associated with the dispensing system component at a second time after the first time. The controller is further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0015] In examples, the controller may determine the presence of the anomaly utilizing the trained neural network based on training with data associated with a plurality of dispensing system components.

[0016] In examples, the one or more sensors may include a camera. In such examples, the controller may be configured to actuate the camera to capture an initialimage of the dispensing system component of the dispenser at the first time and actuate the camera to capture a subsequent image of the dispensing system component of the dispenser at the second time.

[0017] In examples, the anomaly may be a level of fluid in the fluid supply. In such examples, the trained neural network may be trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0018] In examples, the anomaly may be a level of fluid accumulation on the tool. In such examples, the trained neural network may be trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0019] In examples, the anomaly may be a presence of a foreign object in a work area of the dispenser. In such examples, the trained neural network may be trained based on at least one image of the work area of the dispenser devoid of any foreign objects. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0020] In examples, the anomaly may be at least one of a full purge cup and a dirty cleaning strip of a service station of the dispenser. In such examples, the trained neural network may be trained based on at least one image of at least one of a non-full purge cup and a non-dirty cleaning strip of the service station of the dispenser. In suchexamples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0021] In examples, the anomaly may be a misloading of the part on the tool. In such examples, the trained neural network may be trained based on at least one image of a part properly loaded on the tool. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0022] In examples, the anomaly may be a misposition of a bubble on a scale level of the dispenser. In such examples, the trained neural network may be trained based on at least one image of a properly positioned bubble on the scale level of the dispenser. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0023] In examples, the anomaly may be an unauthorized user of the dispenser. In such examples, the trained neural network may be trained based on at least one of facial recognition, biometric information, and a unique badge of an authorized user. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0024] In examples, the anomaly may be a characteristic of the dispensing system component selected from the group consisting of a leak associated with the dispensing system component, damage or wear associated with the dispensing system component, and a jam or disconnection associated with the dispensing system component. In such examples, the trained neural network may be trained based on at least one image of a dispensing system component that is not leaking, damaged orworn, and / or jammed or disconnected. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

[0025] In examples, the anomaly may be a temperature and / or an LED status of the dispensing system component. In such examples, the trained neural network may be trained based on at least one image of a temperature and / or an LED status of a dispensing system component having a temperature less than a predetermined threshold and / or an operational LED status. In such examples, the controller may be configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the temperature and / or the LED status of the dispensing system component. In the same or other examples, the one or more sensors may include an infrared camera configured to determine the temperature and / or the LED status of the dispensing system component.

[0026] In examples, the system may further include a dispensing head. In such examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. In further examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. In further examples, the controller may be configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The following description of the illustrative examples may be better understood when read in conjunction with the appended drawings. It is understood thatpotential examples of the disclosed systems and methods are not limited to those depicted.

[0028] FIG. 1 illustrates a system configured to determine a presence of an anomaly associated with a dispensing system component of a dispenser according to one example;

[0029] FIG. 2 illustrates a method for determining a presence of an anomaly associated with a dispensing system component of a dispenser according to one example;

[0030] FIG. 3A illustrates a fluid supply having a fluid level categorized as high utilizing a trained neural network according to one example;

[0031] FIG. 3B illustrates a fluid supply having a fluid level categorized as medium utilizing a trained neural network according to one example;

[0032] FIG. 3C illustrates a fluid supply having a fluid level categorized as low utilizing a trained neural network according to one example;

[0033] FIG. 4A illustrates a fluid supply containing a fluid;

[0034] FIG. 4B illustrates a masking of the fluid color of the fluid supply of FIG. 4A;

[0035] FIG. 4C illustrates an extraction of the fluid color of the masking of FIG. 4B;

[0036] FIG. 5A illustrates a tool lacking any fluid accumulation detected utilizing a trained neural network according to one example;

[0037] FIG. 5B illustrates another tool lacking any fluid accumulation detected utilizing a trained neural network according to one example;

[0038] FIG. 5C illustrates a tool having multiple instances of fluid accumulation detected utilizing a trained neural network according to one example;

[0039] FIG. 5D illustrates another tool have a single instance of fluid accumulation detected utilizing a trained neural network according to one example; and

[0040] FIG. 6 illustrates a process for training and / or retraining a model each time a new dispensing system component and / or potential anomaly is introduced according to one example.DETAILED DESCRIPTION

[0041] In the following detailed description, reference is made to the accompanying drawings, which form a part hereof. In the drawings, similar symbols identify similar components, unless context dictates otherwise. The illustrative examples described in the detailed description and drawings are not meant to be limiting and are for explanatory purposes. Other examples may be utilized, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein. It will be readily understood that the aspects of the present disclosure, as generally described herein and illustrated in the drawings, may be arranged, substituted, combined, and designed in a wide variety of different configurations, each of which are explicitly contemplated and form a part of this disclosure.

[0042] While conventional schemes for monitoring and / or inspecting dispensers for anomalies have been adequate for their intended purpose, there is a need for systems and methods for determining a presence of an anomaly associated with a dispensing system component of a dispenser (e.g., a low level of fluid in a fluid supply, a high level of fluid accumulation on a tool), namely by capturing and processing data associated with the dispensing system component in a trained neural network, which are particularly useful and desirable in high volume electronics processing I packaging where process monitoring and predictive maintenance are valued.

[0043] Referring first to FIG. 1 , an example system 10 is shown. As depicted, the system 10 may include a dispenser 100, such as a jetting dispenser. The dispenser 100 may include a dispensing head or nozzle 102. The dispenser 100 may further include a motion control system, such as a robot 104, for moving the dispenser (e.g., the dispensing head or nozzle 102 thereof), such as in three or more degrees of freedom. The dispenser 100 may, in certain examples, be mounted to the robot 104, and the robot 104 may, in examples, be configured to move the dispenser (e.g., the dispensing head or nozzle 102 thereof) in a pattern relative to a part, such as across a surface of a circuit board bearing a component. By way of non-limiting example, the robot 104 may be configured to move the dispenser 100 to an appropriate dispensing location for dispensing a material therefrom onto a corresponding area or component of a circuit board and then move the dispenser to a next area or component destined to receive the material. By way of further non-limiting example, underfill materials may be dispensed by the dispenser 100 in successive continuous events to define short line segments, with the robot 104 configured to move the dispenser 100 between successive areas or components of a circuit board. In examples, the robot 104 may include a plurality of dispensers.

[0044] The dispenser 100 may further include various other components or stations typically included in jetting dispensing systems, such as a fluid supply 110 (e.g., syringe, cartridge, reservoir) for containing a fluid, a tool 120 (e.g., wafer chuck, vacuum fixture, transporting elements, such as a loading / unloading robot or conveyor) for supporting a part, a dispensing head or nozzle, a robot for moving the dispenser (e.g., the dispensing head or nozzle thereof), a work area, a service station (e.g., including a purge cup, cleaning strip, etc.), a conveyor, pumps, associated hoses and electronics, etc.

[0045] The system 10 may include a controller 140 configured to carry out the operations described herein (e.g., actuating the sensor(s), processing the captured data, determining the presence of an anomaly, logging the anomaly, generating and sending an alert regarding the anomaly). Although the present disclosure is described with respect to controller 140 carrying out the operations described herein, it is to be understood that the term “controller,” as used herein, could include one or more controllers, microprocessors, or the like that work in concert with one another to carry out the operations described herein.

[0046] The system 10 may further include one or more sensors 130. In the example illustrated in FIG. 1 , the sensor 130 is in the form of a single camera, although other examples are not so limited and may include one, two, three, four, five, or more sensors in the form of cameras or other sensors. Each implementation of the sensor 130 is generally configured to sense characteristics of a dispensing system component of the dispenser, such as the fluid supply 110, the tool 120, and / or any other component of the system 10. In examples in which the sensor 130 is one or more cameras, the camera(s) may generally be configured to capture images of the dispenser, namely a desired dispensing system component of the dispenser 100.

[0047] The sensor(s) 130 may, in certain examples, be mounted to and / or in near proximity to the dispenser 100, which may include mounting components, mounting structures, mounting fasteners, and / or the like. In some examples, the sensor(s) 130 may be configured to rotate about the dispenser 100, such as for capturing images of one or more dispensing system components from multiple sides thereof. In this regard, the system 10 may include components, controllers, motors, and / or the like to implement rotation of the sensor(s) relative to components, controllers, motors, and / or the like to implement rotation of the same relative to the sensor(s). Aswill be appreciated by those skilled in the art, in addition and / or alternatively to capturing one or more still images of the dispensing system component, the sensor(s) 130 may be configured to capture one or more videos of the dispensing system component and / or other data or characteristics associated with the dispensing system component (e.g., temperature, LED status).

[0048] Further, the system 10 may include a neural network 160. The neural network 160 may be implemented as a trained neural network. In examples, the neural network 160 may be trained by the system 10. In examples, the neural network 160 may be trained by the controller 140 of the system 10. The neural network 160 may implement artificial neurons in an artificial neural network or simulated neural network. The neural network 160 may implement the artificial neurons in an interconnected group of natural or artificial neurons that may use a mathematical or computational model for information processing within the system 10 based on a connectionistic approach to computation. In most cases, the neural network 160 may implement an adaptive system that changes its structure based on external or internal information received within and / or from the system 10. In examples, the sensor(s) 130 may be directly connected to the neural network 160. In examples, the controller 140 may trigger or poll the neural network, such as to communicate information between the controller 140 and the neural network 160 (e.g., data captured by the sensor(s) 130 and / or determinations processed by the neural network 160), as described herein. The controller 140 is generally configured to utilize the neural network 160 to carry out various operations described herein, and the neural network 160 may, in certain examples, be part of the controller 140 or the neural network 160 may, in other examples, be separate from the controller 140.

[0049] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured for inspection of the tooling area to detect spilled fluid or other foreign objects on the tooling to prevent damage to a part.

[0050] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to monitor the conveyor system for anomalies such as worn belts, broken belts, jammed parts, etc.

[0051] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to monitor a payload on a robot for anomalies such as loose parts, disconnected wires and hoses, bent needles, and / or the like.

[0052] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to monitor for foreign objects (e.g., hands I body parts or misplaced or mispositioned components, such as a loose wire) in the work area. The equipment should be interlocked to prevent this, but it is common practice (unfortunately) for users to bypass the interlock mechanism.

[0053] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to monitor the service station for full purge cups, dirty cleaning strips, or other anomalies.

[0054] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to monitor the customer part to make sure it is properly loaded and locked in position before the dispensing process.

[0055] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to use an infrared camera to monitor the temperature of various elements of the equipment to ensure they are in thecorrect I expected temperature range. This may include fluid temperature, valve temperature, tooling temperature, bearings, and / or the like

[0056] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to use a camera that uses facial recognition, biometric information, or reads the users badge to ensure they are authorized to use the equipment.

[0057] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to use a camera mounted on the outside of the machine to monitor bulk material feed systems for leak or anomalies.

[0058] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to, after cleaning I maintenance, check to see if everything is put back in the proper place.

[0059] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to use a camera in the electronics area to monitor temperatures and / or LED status.

[0060] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to inspect for nozzle contamination.

[0061] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to monitor bubble on scale level to make sure it is level.

[0062] In aspects, the system 10, the neural network 160, the controller 140, the sensor(s) 130, and / or the like, may be configured to, if the machine is open and the safety interlock is triggered, take a picture to make sure everything is back in normal condition before restarting.

[0063] Turning now to FIG. 2, a method for determining a presence of an anomaly associated with a dispensing system component of a dispenser is illustrated according to one example. Specifically, the anomaly detection method 200 may be executed on a system 10, such as, for example, the system 10 of FIG. 1. The anomaly detection method 200 may, for example, be executed within the system 10 of FIG. 1 using the controller 140 and / or the neural network 160. The forthcoming description of the anomaly detection method 200 will be described with reference to system 10 and the components thereof, though it will be appreciated that the anomaly detection method 200 and the techniques thereof are equally applicable to other related systems and components.

[0064] As illustrated in FIG. 2, the anomaly detection method 200 may begin at step 202. The anomaly detection method 200 (and step 202) may be initiated by a trigger. In examples, the anomaly detection method 200 may be automatically performed at predetermined intervals in response to commands from the controller 140, in response to user input, and / or continuously. In some examples, each time a specific action is taken with respect to a dispensing system component, the anomaly detection method 200 may be initiated, such that the sensor(s) 130 are actuated to capture or recapture data associated with the dispensing system component. By way of non-limiting example, each time that a new fluid supply 110 is installed, the anomaly detection method 200 may be initiated and the sensor(s) 130 may be actuated by the controller 140 to capture data associated with the fluid supply 110 as described herein. By way of further non-limiting example, each time that a part is unloaded from the tool 120, the anomaly detection method 200 may be initiated and the sensor(s) 130 may be actuated by the controller 140 to capture data associated with the tool 120 as described herein. In examples, the user input may be provided to a human machine interface (HMI), suchas one or more buttons, touchscreens, and / or the like. Further, user input may be provided to the controller 140. Further, the HMI may be configured to provide output to the user, which may include visual output, audible output, haptic output, sensory output, and / or the like. In non-limiting examples, the HMI may be implemented remotely (e.g., over a network) from system 10.

[0065] At step 202, initial data associated with a dispensing system component is captured at a first time. As described herein, the initial data may be captured by the sensor(s) 130, which may be actuated by the controller 140. In examples, the initial data may, for example, be an initial image of the dispensing system component of the dispenser at the first time. By way of non-limiting example, the initial data may be an initial image of the fluid supply 110 at the first time, such as to identify a level of fluid in the fluid supply 110. By way of further non-limiting example, the initial data may be an initial image of the tool 120 at the first time, such as to identify a level of fluid accumulation on the tool 120. The initial data may generally be any data or characteristics (e.g, temperature or LED status of the dispensing system component) associated with a chosen dispensing system component. Step 202 may generally be repeated each time that the chosen dispensing system component is replaced, cleaned, or the like, or any time it becomes desirable to determine or re-determine the presence of any anomaly associated with the dispensing system component.

[0066] At step 204, the captured initial data associated with the dispensing system component is processed. As described herein, the captured initial data may be processed by the controller 140 and / or the neural network 160. In examples, the captured initial data may be processed (e.g., by the controller 140 and / or the neural network 160) to generate an initial value, which may generally be based on an aspect or parameter associated with the dispensing system component. By way of non-limitingexample, the value may be based on the level of fluid in the fluid supply 110. By way of further non-limiting example, the value may be based on the presence and / or amount of fluid accumulation on the tool 120. The value may generally be based on an operational status of the dispensing system component or any other characteristics of the dispensing system component.

[0067] Further, the various above-noted values, data, images, and / or the like may be utilized by the system 10 and / or the controller 140 to train the neural network 160 to determine an existence of an anomaly associated with a dispensing system component and / or also determine a non-existence of an anomaly associated with a dispensing system component. Once the neural network 160 has been trained, the neural network 160 may be implemented as a trained neural network by the system 10 and / or the controller 140.

[0068] As depicted in FIG. 3A-3C, a predetermined subset of images depicting the dispensing system component may be captured, which may be input to a neural network for training thereof and then processed to generate the initial value and / or to determine a presence of an anomaly associated with the dispensing system component, as described herein. As described herein, the value may, in some examples, be based on a pixel intensity of the initial image. In such examples, the initial image may be processed (e.g., by the controller 140) by classifying the initial image (e.g., according to weighted statistics), such as by making a prediction of the statistical likelihood that the initial image belong to a certain category or class (e.g., whether the statistical likelihood is greater than a threshold probability). In examples, the neural network 160 may analyze one or more pixels of the captured initial image, such as to identify pixel intensity, which may be used to create the trained neural network. In examples, the neural network 160 may be trained on any captured data (e.g., images),such as standard images (refer to fluid supply 110D in FIG. 4A) and / or modified images (refer to fluid supplies 110E and 11 OF in FIG. 4B and FIG. 4C, respectively). In examples, the captured data may be modified, such as in the form of images modified to increase contrast. In examples, the neural network 160 may be trained with one or more images of a dispensing system component and then process captured data associated with the same or another dispensing system component to determine the presence of a possible anomaly associated with the dispensing system component from which the data was captured, as described herein. By way of non-limiting example, the neural network 60 may generally process the captured data that is presented (e.g., input) to the neural network by performing a very large number of simple calculations on the captured data, which coefficients of the formulas used to perform such calculations being determined by a process for training the neural network, as described herein. For example, during training of the neural network 160, the coefficients of the formulas used to perform such calculations may be randomly varied and optimized until the neural network model is shown to be successful in predicting to what class new input data should be assigned (e.g., by comparing the prediction to the annotated class). Further, as described herein, the training dataset may be saved or otherwise retained (e.g., as a historical dataset) and / or modified for retraining the neural network, as desired (e.g., to include new classes or supplement examples of existing classes, such as when data associated with a new dispensing system component is captured). It is to be understood that the foregoing example for processing the initial image is merely one method for processing the initial image and other examples are not so limited.

[0069] In examples, the trained neural network may include data (e.g., images) associated with a plurality of dispensing system components, including dispensing system components of other dispensers. For example, data from all dispensing systemcomponents of a certain type may be captured and input into the neural network so as to train the neural network. In the same or other examples, data from a plurality of different dispensing system component conditions (e.g., lighting, appearance) may be captured and input into the neural network so as to train the neural network, which has been found to be increase accuracy. Additionally or alternatively to the foregoing, each time a new dispensing system component of the type is added to a production line, the controller could capture and process the initial data (and additionally, in examples, the subsequent data) as described herein, update the neural network dataset with the newly captured and processed data, retrain the neural network model, and deploy the retrained neural network model to other dispensers having a dispensing system component of the same type. In examples, the neural network may be trained on both historical data (e.g., test or training data from past or other dispensing system components) and new data (e.g., test or training data from a new dispensing system component). By way of non-limiting example, as illustrated in the process 600 of FIG. 6, any time a new dispensing system component and / or potential anomaly is introduced 602, data associated with the same may be captured and / or processed 604 as described herein (e.g., according to the anomaly detection method 200). The newly captured and processed data 606 may be annotated and / or categorized at 607, such as by employing supervised learning to classify the data (e.g., images). That newly annotated and / or categorized data may then be randomly separated at 608 into new training and test datasets 614 and a new validation dataset 616. The training and test datasets 614 may in turn be input to and used to train or retrain 610 the model (e.g., neural network). As illustrated, in addition to the newly captured and processed data 606 and / or the randomly separated training and test datasets 614, historical training and / or test data 612 (e.g., from past or other dispensing system components) may beinput to and used to train or retrain 610 the model. In examples, the historical training and / or test data 612 may have already been annotated and / or classified prior to be input to and used to train or retain 610 the model. The model may then be validated at 618 using the validation dataset 616. As illustrated, in addition to the randomly separated validation dataset 616, the historical training and / or test data 612 (e.g., from past or other dispensing system components) and / or an output from the retrained model network is input to and used for validation at 618. It is then determined at 620 whether the precision and / or accuracy are sufficient (e.g., are within an acceptable range and / or greater than or equal to a confidence threshold). If the precision and / or accuracy are determined at 620 to be insufficient, the process 600 loops to 604 to re-capture and / or re-process additional data. Conversely, if the precision and / or accuracy are determined at 620 to be sufficient, the new model is employed at 622. In examples, the new model may be deployed to other dispensers or systems having similar or the same type of dispensing system component, thereby increasing the accuracy and / or precision of determining the presence of an anomaly associated with the dispensing system components across a plurality of dispensers or systems. It is to be understood that while the illustrated example of process 600 has been described herein, although other examples are not so limited, and other processes of training the neural network or model of the present disclosure may be employed.

[0070] By way of non-limiting example, FIG. 3A depicts a captured image of a fluid supply 110A having a level of fluid categorized as “high” utilizing the trained neural network. In the example illustrated in FIG. 3A, the fluid supply 110A thus lacks any discernable anomaly with respect to the level of fluid because the level of fluid is greater than or equal to a predetermined fluid level threshold. When employing the anomaly detection method 200 of FIG. 2, the controller 140 may therefore determine, at step206, that no anomaly is present. In response, in certain examples, the controller 140 may be configured to cause the system 10 to begin or continue a dispensing operation. For comparison, FIG. 3B depicts a captured image of a fluid supply 110B after a certain number of dispensing cycles. As seen, the captured image of the fluid supply 110B has a level of fluid categorized as “medium” utilizing the trained neural network. Depending upon the predetermined fluid level threshold or range described herein, such level may generally be great enough to avoid reducing dispensing efficiency or accuracy. When employing the anomaly detection method 200 of FIG. 2, the controller 140 may therefore determine, at step 206, that no anomaly is present. In response, in certain examples, the controller 140 may be configured to cause the system 10 to begin or continue the dispensing operation. On the other hand, FIG. 3C depicts a captured image of a fluid supply 110C after even more dispensing cycles. As seen, the captured image of the fluid supply 110C has a level of fluid categorized as “low” utilizing the trained neural network. As will be appreciated, the fluid level may be insufficient to continue the dispensing operation, thereby potentially compromising the quality of dispensing to an unacceptable level. Based on the processing of FIG. 3C, the controller 140 may determine the presence of an anomaly (i.e., unacceptably low level of fluid in the fluid supply) when processing the image of FIG. 3C. In response, in certain examples, the controller 140 may be configured to cause the system 10 to cease a dispensing operation, log the anomaly, and / or generate and send an alert indicating the presence of the anomaly, as described herein. In examples, the trained neural network may include data (e.g., images) associated with a plurality of fluid supplies, including fluid supplies of other dispensers. For example, data from all fluid supplies of a certain type may be captured and input into the neural network so as to train the neural network. In the same or other examples, data from a plurality of different fluid supplyconditions (e.g., lighting, appearance) may be captured and input into the neural network so as to train the neural network, which has been found to be increase accuracy. Additionally or alternatively to the foregoing, each time a new fluid supply of the type is added to a production line, the controller could capture and process the initial data (and additionally, in examples, the subsequent data) as described herein, update the neural network dataset with the newly captured and processed data, and deploy the updated dataset to other dispensers having a fluid supply of the same type.

[0071] In some examples, an initial image of a fluid supply 110D containing a colored fluid is captured, such as is illustrated in FIG. 4A. As illustrated in FIG. 4B, a mask of the fluid color may be created, and the color may be extracted, as illustrated in FIG. 4C. In such examples, the extracted color and / or mask may be classified by the trained neural network, which may be trained based on one or more images of a fluid supply (e.g., having a full level of fluid), to determine the level of fluid, thereby determining whether an anomaly associated with the fluid supply (e.g., an unacceptably low level of fluid) is present. In other examples, the trained neural network may be used to classify and / or categorize the level of fluid in the fluid supply based on a classification of the initial image, such as by the trained neural network trained on images of other fluid supplies (e.g., using object detection and / or classification).

[0072] By way of further non-limiting example, FIG. 5A and FIG. 5B each depict captured images of tools 120A and 120B, respectively, each having no discernable level of fluid accumulation thereon utilizing the trained neural network. In the examples illustrated in FIG. 5A and 5B, the tools 120A and 120B thus lack any discernable anomaly with respect to the level of fluid accumulation thereon because the level of fluid accumulation is below a predetermined fluid accumulation threshold.When employing the anomaly detection method 200 of FIG. 2, the controller 140 (e.g.,utilizing the neural network 160) may therefore determine, at step 206, that no anomaly is present. In response, in certain examples, the controller 140 may be configured to cause the system 10 to begin or continue a dispensing operation. For comparison, FIG. 5C and FIG. 5D depict captured images of tools 120C and 120D, respectively, after a certain number of dispensing cycles. As seen, the captured images of the tools 120C and 120D each have a discernable level of fluid accumulation thereon utilizing the trained neural network, with FIG. 5C illustrating a tool 120C having multiple instances of fluid accumulation thereon as detected utilizing a trained neural network and FIG. 5D illustrating a tool 120D having a single instance of fluid accumulation thereon as detected utilizing a trained neural network, as described herein. As will be appreciated, the fluid accumulation may be significant enough to potentially compromise the quality of dispensing to an unacceptable level and / or damage subsequent parts. Based on the processing of FIG. 5C and FIG. 5D, the controller 140 may utilize the neural network 160 to determine the presence of an anomaly (i.e., unacceptably high level of fluid accumulation on the tools) when processing the image of FIG. 5C and FIG. 5D. In response, in certain examples, the controller 140 may be configured to cause the system 10 to cease a dispensing operation, log the anomaly, and / or generate and send an alert indicating the presence of the anomaly, as described herein. In examples, the controller 140 may be configured to send an alert indicating the presence of the anomaly to the HMI (e.g., over a network), display an image of the anomaly on the HMI (e.g., remotely from system 10), annotate the image displayed on the HMI indicating the location of the anomaly, a description of the anomaly, directions for correcting the anomaly, and / or the like.

[0073] In examples, the trained neural network may be trained on data (e.g., images) associated with a plurality of tools, including tools of other dispensers. Forexample, data from all tools of a certain type may be captured and used to train the neural network. In the same or other examples, data from a plurality of different tool conditions (e.g., lighting, appearance) may be captured and used to train the neural network, which has been found to be increase accuracy. Additionally or alternatively to the foregoing, each time a new tool of the type is added to a production line, the controller could capture and process the initial data (and additionally, in examples, the subsequent data) as described herein, update the neural network dataset with the newly captured and processed data, retrain the neural network and deploy the retrained neural network model to other dispensers having a tool of the same type.

[0074] At step 206, the captured initial image (and, in examples in which it is generated, the initial value) is utilized to determine a presence of a possible anomaly. In certain examples, the presence of an anomaly associated with the dispensing system component may be determined by the statistical likelihood of the image belonging to a category of anomalies to determine if the statistical likelihood is above the acceptable value, thereby indicating the presence or non-existence of an anomaly associated with the dispensing system component. If no anomaly is determined to be present (e g., by the controller 140 utilizing the neural network 160), the controller 140 may thereby determine that the dispensing system component is clean or otherwise sufficiently operational for a chosen dispensing operation, and the controller 140 may cause the system to begin or continue dispensing until it is necessary or desirable to once again determine the presence of a possible anomaly associated with the dispensing system component. Conversely, if an anomaly is determined to be present (e.g., by the controller 140 utilizing the neural network 160, such as by determining the statistical likelihood that the captured initial data belongs to the category of an anomaly), thecontroller 140 may cease a dispensing operation, log the anomaly, and / or generate and send an alert indicating the presence of the anomaly, as described herein.

[0075] At step 206, the controller 140 (e.g., utilizing the neural network 160) may, in certain examples, perform and / or be trained to perform any of the functions described herein (e.g., by utilizing the neural network 160 to classify and / or categorize captured data and perform predictions of anomalies) to determine a presence of an anomaly associated with the dispensing system component, such as by analyzing timeoffset or time-lapsed images, video, or other data from multiple sources. If the controller 140 (e.g., utilizing the neural network 160) determines, for example, that the statistical likelihood of an anomaly is below a certain value, the controller 140 may determine that no anomaly associated with the dispensing system component is present and may cause the system 10 to begin or continue dispensing. In such situations, the controller 140 may nevertheless log the inspection (e.g., log that the initial data was captured and processed and / or that no anomaly was determined to be present). Conversely, if the controller 140 (e.g., utilizing the neural network 160) determines that the statistical likelihood of an anomaly is above a certain value, the controller 140 may determine that an anomaly associated with the dispensing system component is present, and, in response to such a determination, the controller 140 may, at step 208, log the presence of the anomaly associated with the dispensing system component and / or cease a dispensing operation.

[0076] At step 210, the controller 140 may generally generate and send an alert to the HMI (e.g., over a network), which may be implemented remotely from system 10. The alert may generally indicate (e.g., to a user of the HMI) the presence of the anomaly associated with the dispensing system component.

[0077] Additionally, the alert may generally provide location information to the user relating to the anomaly associated with the dispensing system component. By way of non-limiting example, if the controller 140 (e.g., utilizing the neural network 160) determines the presence of an anomaly associated with the fluid supply 110, the alert may indicate that the fluid supply 110 is experiencing an anomaly and / or may include specific details with respect to the anomaly (e.g., the level of fluid in the fluid supply is unacceptably low). By way of further non-limiting example, if the controller 140 (e.g., utilizing the neural network 160) determines the presence of an anomaly associated with the tool 120, the alert may indicate that the tool 120 is experiencing an anomaly and / or may include specific details with respect to the anomaly (e.g., the level of fluid accumulation on the tool is unacceptably high and / or a part is misloaded on the tool).

[0078] Additionally or alternatively to the foregoing, the alert may provide directions to the user for correcting the anomaly. By way of non-limiting example, if the controller determines the presence of an anomaly associated with the fluid supply 110, the alert may provide directions to the user for refilling or replacing the fluid supply 110 (e.g., such that the level of fluid in the fluid supply is acceptably high). By way of further non-limiting example, if the controller 140 (e.g., utilizing the neural network 160) determines the presence of an anomaly associated with the tool 120, the alert may provide directions to the user for cleaning the tool 120 and / or repositioning the part on the tool 120 (e.g., such that the level of fluid accumulation on the tool is acceptably low and / or the part is properly loaded on the tool). The alert may include any visual, auditory, haptic, or sensory indicators as desired to suit a particular application. By way of non-limiting example, in response to determining the presence of an anomaly associated with a dispensing system component, the controller 140 may be configuredto cause an LED associated with the dispensing system component to indicate the presence of the anomaly (e.g., by turning from green to red).

[0079] In some examples, the controller 140 may be configured to automatically initiate corrective actions intended to correct the anomaly (e.g., automated refilling of the fluid supply when the level of fluid in the fluid supply is below a predetermined fluid level threshold or automated cleaning of the tool when the level of fluid accumulation on the tool is above a predetermined threshold).

[0080] After initiating corrective actions and / or generating and sending an alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly, it may generally be desirable to determine whether the anomaly has been corrected (i.e. , whether the value of the characteristic of the dispensing system component is within an acceptable range). As such, at step 212, subsequent data of the dispensing system component is captured. As with the initial data, the subsequent data may be one or more images, videos, or other data or characteristics associated with the dispensing system component (e.g., temperature, LED status). The subsequent data may generally be captured using the same or a different sensor 130 as is used to capture the initial data. In examples, it may be desirable for purposes of more accurate classification and / or categorization to capture the subsequent data (e.g., one or more subsequent images) using the same sensor (e.g., camera) and / or from the same angle relative to the dispensing system component as used to capture the initial data (e.g., one or more initial images). The subsequent data is generally captured at a second time after the first time (e.g., after any corrective actions intended to correct the anomaly have been performed, such as by the user or the controller 140).

[0081] At step 214, the captured subsequent data associated with the dispensing system component is then processed. As described herein, the captured subsequent data may be processed by the controller 140. In examples, the captured subsequent data may be processed (e.g., by the controller 140) to generate a subsequent value, which may generally be based on an aspect or parameter associated with the dispensing system component. By way of non-limiting example, the value may be based on the level of fluid in the fluid supply 110. By way of further non-limiting example, the value may be based on the presence and / or amount of fluid accumulation on the tool 120. The value may generally be based on an operational status of the dispensing system component or any other characteristics of the dispensing system component.

[0082] The subsequent data may generally be processed (and, in examples in which the subsequent value is generated, the subsequent value may be generated) using any of the techniques described herein with respect to processing the initial data and generating the initial value. The subsequent data may be processed to determine whether the anomaly has been corrected. In some examples, the generated second value may be utilized to determine whether the corrective actions were successful (i.e. , whether the subsequent value is within the acceptable range). If the controller 140 (e.g., utilizing the neural network 160) determines, in step 214, that the anomaly has been corrected, the controller 140 may generally cause the system 10 to begin, resume, or continue dispensing. Conversely, if the controller 140 (e.g., utilizing the neural network 160) determines, in step 214, that the anomaly has not been corrected, the controller 140 may generally repeat step 210 (generating and sending alter indicting the continued presence of the anomaly) and / or cause the system 10 to cease dispensing. In general, the controller 140 may be configured to generate and send the alert and / orceasing dispensing with sufficient time to allow the system and / or the user to take corrective action to avoid production delays and prevent yield loss.

[0083] In some examples, at step 214, the generated subsequent value may be utilized to determine the presence of an anomaly (including the continued presence of any originally-identified anomaly or the presence of another anomaly) associated with the dispensing system component. By way of non-limiting example, the subsequent data may be captured at a second time after a first time at which the initial data is captured, and the generated subsequent value may be compared to the generated initial value to determine whether the value (e.g., pixel intensity) is varying over time, which may be indicative of an anomaly as described herein.

[0084] The controller 140 (e.g., utilizing the neural network 160) may generally be capable of determining the presence of an anomaly associated with one or more dispensing system components of the dispenser 100, such as by monitoring (e.g., remotely) such dispensing system components, which anomalies may, for example, take any of the non-limiting forms described herein.

[0085] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a level of fluid in the fluid supply 110 (e.g., an unacceptably low level of fluid) utilizing the trained neural network, such as based on a classification of an initial image of the fluid supply 110 by a trained neural network trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold (e.g., an acceptably high level of fluid). In such examples, the controller 140 (e.g., utilizing the neural network 160) may be configured to categorize the level of fluid in the fluid supply 110 utilizing the trained neural network, such as by categorizing the level of fluid as being less than or as being greater than or equal to a predetermined fluid level threshold and / or by categorizing the level of fluid ashigh, medium, or low. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that the level of fluid in the fluid supply is less than the predetermined threshold and / or may provide directions to the user for refilling the fluid supply such that the level of fluid is greater than or equal to the predetermined threshold and / or replacing the fluid supply with a second fluid supply having a level of fluid greater than or equal to the predetermined threshold. In some such examples, the controller 140 may be configured to determine a predicted level of fluid in the fluid supply, such as based on an amount of fluid dispensed by the dispenser. The predicted level of fluid may then be compared to a sensed level of fluid in the fluid supply (e.g., based on the initial image of the fluid supply and the processing thereof) to identify a possible excursion (e.g., a deviation between the two values suggesting a problem with the fluid supply or dispenser).

[0086] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a level of fluid accumulation on the tool 120 (e.g., an unacceptably high level of fluid accumulation) utilizing the trained neural network, such as based on a classification of an initial image of the tool 120 by a trained neural network trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold (e.g., an acceptably low level of fluid accumulation). In such examples, the controller 140 (e.g., utilizing the neural network 160) may be configured to categorize the level of fluid accumulation on the tool 120 utilizing the trained neural network, such as by categorizing the level of fluid accumulation as being less than or as being greater than or equal to a predetermined fluid accumulation threshold and / or by categorizing the level of fluid accumulation as high, medium, or low. The controller 140 is generally configured to log the anomaly andgenerate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that the level of fluid accumulation on the tool is greater than the predetermined threshold and / or may provide directions to the user for cleaning the tool such that the level of fluid accumulation is less than the predetermined threshold. In some such examples, the controller 140 may be configured to determine a predicted level of fluid accumulation on the tool, such as based on a number of parts unloaded from the tool. The predicted level of fluid accumulation may then be compared to a sensed level of fluid accumulation on the tool (e.g., based on the initial image of the tool and the processing thereof) to identify a possible excursion (e.g., a deviation between the two values suggesting a problem with the tool or dispenser).

[0087] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a foreign object in a work area of the dispenser utilizing the trained neural network, such as based on a classification of an initial image of the work area of the dispenser by a trained neural network trained based on at least one image of the work area of the dispenser devoid of any foreign objects. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that a foreign object (e.g., a body part or a misplaced or mispositioned component, such as a loose wire) has been detected in the work area and / or may provide directions to the user for clearing the work area such that no foreign objects are in the work area.

[0088] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a full purge cup and / or a dirty cleaning strip in a service station of the dispenser utilizing the trained neural network, such as based on aclassification of an initial image of the service station by a trained neural network trained based on at least one image of at least one of a non-full purge cup and a non-dirty cleaning strip of the service station of the dispenser. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that a full purge cup and / or a dirty cleaning strip has been detected in the service station and / or may provide directions to the user for emptying or replacing the purge cup and / or cleaning or replacing the cleaning strip.

[0089] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a misleading of a part on the tool utilizing the trained neural network, such as based on a classification of an initial image of the part loaded to the tool by a trained neural network trained based on at least one image of a part properly loaded on the tool. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that the part has been misloaded on the tool and / or may provide directions to the user for properly loading the part on the tool.

[0090] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a misposition of a bubble on a scale level of the dispenser utilizing the trained neural network, such as based on a classification of an initial image of the bubble on the scale level by a trained neural network trained based on at least one image of a properly positioned bubble on the scale level of the dispenser. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that the bubble on the scalelevel is mispositioned on the tool and / or may provide directions to the user for properly positioning the bubble on the scale level.

[0091] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of an unauthorized user of the dispenser utilizing the trained neural network, such as based on a classification an initial image of the user by a trained neural network trained based on at least one of facial recognition, biometric information, and a unique badge of an authorized user. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that the user is not an authorized user of the dispenser and / or may provide directions to the user for identifying an authorized user of the dispenser.

[0092] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a characteristic of the dispensing system component such as a leak, damage or wear, and / or a jam or disconnection utilizing the trained neural network, such as based on a classification of an initial image of the dispensing system component by a trained neural network trained based on at least one image of a dispensing system component that is not leaking, damaged or worn, and / or jammed or disconnected. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that the user is not an authorized user of the dispenser and / or may provide directions to the user for identifying an authorized user of the dispenser.

[0093] In examples, the controller 140 may be capable of determining the presence of an anomaly in the form of a temperature and / or an LED status of the dispensing system component utilizing the trained neural network, such as based on aclassification of the temperature and / or the LED status of the dispensing system component by a trained neural network trained based on at least one image of a temperature and / or an LED status of a dispensing system component having a temperature less than a predetermined threshold and / or an operational LED status. The controller 140 is generally configured to log the anomaly and generate and send an alert to the HMI indicating the presence of the anomaly, as described herein. In some such examples, the alert may indicate that the temperature of the dispensing system component is above a predetermined temperature threshold and / or that the LED status is a non-operational LED status and / or may provide directions to the user for correcting the anomaly. In such examples, the sensor(s) may include an infrared camera configured to determine the temperature and / or the LED status of the dispensing system component.

[0094] As will be appreciated, various techniques may be employed for processing captured data associated with a dispensing system component, generating one or more values based upon such captured data, and / or utilizing such generated one or more values to determine the presence of an anomaly associated with the dispensing system component. For example, the techniques described herein may utilize or incorporate machine learning and / or artificial intelligence. Machine learning could include the use of any of various machine learning tools that employ machine learning algorithms, including neural networks such as Deep Neural Networks (DNN). Other examples of machine learning tools include, but are not limited to: XGBoost, Convolutional Machine Learning Tool (CNN), Support Vector Machine (SVM), Multiple Linear Regression, Random Forest, AdaBoost, Artificial Machine Learning Tool (ANN): “Conventional” Machine Learning Tool, Decision Tree (DT), Naive Bayes, K Nearest Neighbor (KNN), Hidden Markov Model (HMM), cybernetics and brain simulation,symbolic, cognitive simulation, logic-based, anti-logic, knowledge-based, sub-symbolic, embodied intelligence, computational intelligence and soft computing, and / or the like. The machine learning may utilize feature vector processes, classification processes, grouping processes, classification processes, regression processes, analysis processes, matching processes, training processes, diagnostic processes, and / or the like. In one example, one or more images of the dispensing system component may be input into a machine learning tool for closed loop control, such as for determining a classification of the one or more images, and a value may be generated based on such classification. In another example, one or more images of the dispensing system component may be assigned a quality class to train a machine learning tool for closed loop control, such as by assigning each of the one or more images a quality class, in accordance with a quality classification system, to train the machine learning tool to associate quality classes with images. Depending on the quality class assigned to an image, the trained machine learning tool may control the system 10, such as to begin, continue, or cease dispensing depending upon a determination as to the presence of an anomaly associated with a dispensing system component of the dispenser as described herein.

[0095] Examples of the system 10 may include various drivers, control modules, and / or the like for controlling operation of the dispensing head or nozzle 102, the fluid supply 110, the tool 120, the sensor(s) 130, the controller 140, and / or any other components of the system 10. Examples of the system 10 may include communication channels for communication of control signal, data, images, and / or the like between the dispensing head or nozzle 102, the fluid supply 110, the tool 120, the sensor(s) 130, the controller 140, and / or any other components of the system 10. The communication channels may be any type of wired or wireless electronic communications network, suchas, e.g., a wired / wireless local area network (LAN), a wired / wireless personal area network (PAN), a wired / wireless home area network (HAN), a wired / wireless wide area network (WAN), a campus network, a metropolitan network, an enterprise private network, a virtual private network (VPN), an internetwork, a backbone network (BBN), a global area network (GAN), the Internet, an intranet, an extranet, an overlay network, and / or the like.

[0096] The system 10 and / or the controller 140 may be implemented in any type of computing devices, such as, e.g., a desktop computer, personal computer, a laptop / mobile computer, a personal data assistant (PDA), a mobile phone, a tablet computer, cloud computing device, and the like, with wired / wireless communications capabilities via the communication channels. In examples, the controller 140 may be implemented as an inspection controller, a cleaning controller, a camera operation controller, a dispensing system controller, and / or the like.

[0097] Further in accordance with various examples of the disclosure, the anomaly detection method 200 may be intended for operation with dedicated hardware implementations including, but not limited to, PCs, PDAs, semiconductors, application specific integrated circuits (ASIC), programmable logic arrays, cloud computing devices, and other hardware devices constructed to implement the methods described herein.

[0098] It should also be noted that the controller 140 and / or the anomaly detection method 200 may utilize software implementations that may be optionally stored on a tangible storage medium, such as: a magnetic medium such as a disk or tape; a magneto-optical or optical medium such as a disk; or a solid state medium such as a memory card or other package that houses one or more read-only (non-volatile) memories, random access memories, or other re-writable (volatile) memories. A digital file attachment to email or other self-contained information archive or set of archives isconsidered a distribution medium equivalent to a tangible storage medium. Accordingly, the disclosure is considered to include a tangible storage medium or distribution medium, as listed herein and including art-recognized equivalents and successor media, in which the software implementations herein are stored.

[0099] Additionally, the various examples of the system 10 and / or the controller 140 may be implemented in a non-generic computer implementation. Moreover, the various examples of the disclosure set forth herein improve the functioning of the system 10 as is apparent from the disclosure hereof. Furthermore, the various examples of the disclosure involve computer hardware that it specifically programmed to solve the complex problem addressed by the disclosure. Accordingly, the various examples of the disclosure improve the functioning of the system overall in its specific implementation to perform the process set forth by the disclosure and as defined by the claims.

[0100] The sensor(s) may include a camera. The camera may include a charge coupled device (CCD), CMOS image sensors, Back Side Illuminated CMOS, or the like. Images captured by the camera may be converted and stored in various formats including a JPEG file format, RAW feature format such as the Android (operating system) 5.0 Lollipop, and the like. The system 10 may include a plurality of cameras. Other sensor types may be used alone or in combination with a camera, such as temperature sensors, accelerometers, pressure sensors, or motion sensors, including combinations thereof, any of which may be used alone, in combination with one another, or in combination with one or more cameras.

[0101] It should be noted that the illustrations and descriptions of the examples shown in the figures are for exemplary purposes only, and should not be construed limiting the disclosure. One skilled in the art will appreciate that the present disclosurecontemplates various examples. Additionally, it should be understood that the concepts described above with the above-described examples may be employed alone or in combination with any of the other examples described above. It should further be appreciated that the various alternative examples described above with respect to one illustrated example can apply to all examples as described herein, unless otherwise indicated.

[0102] The following are a number of nonlimiting EXAMPLES of aspects of the disclosure. One EXAMPLE includes: EXAMPLE 1. A system configured to determine a presence of an anomaly associated with a fluid supply of a dispenser includes: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of the fluid supply; and a controller configured to actuate the one or more sensors to capture initial data associated with the fluid supply at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the fluid supply; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller further configured to actuate the one or more sensors to capture subsequent data associated with the fluid supply at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0103] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 2. The system of any EXAMPLE herein where the one or more sensors includes a camera and the controlleris configured to: actuate the camera to capture an initial image of the fluid supply at the first time; and actuate the camera to capture a subsequent image of the fluid supply at the second time. 3. The system of any EXAMPLE herein where the anomaly is a level of fluid in the fluid supply. 4. The system of any EXAMPLE herein where the controller is configured to: categorize the level of fluid in the fluid supply utilizing the trained neural network as high, medium, or low. 5. The system of any EXAMPLE herein where the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 6. The system of any EXAMPLE herein where the alert indicates that the level of fluid in the fluid supply is less than the predetermined threshold. 7. The system of any EXAMPLE herein where the alert provides directions to the user for refilling the fluid supply such that the level of fluid is greater than or equal to the predetermined threshold. 8. The system of any EXAMPLE herein where the alert provides directions to the user for replacing the fluid supply with a second fluid supply having a level of fluid greater than or equal to the predetermined threshold. 9. The system of any EXAMPLE herein where the controller is configured to: determine a predicted level of fluid in the fluid supply based on an amount of fluid dispensed by the dispenser; determine a sensed level of fluid in the fluid supply based on the initial image of the fluid supply; and compare the predicted level of fluid in the fluid supply to the sensed level of fluid in the fluid supply to identify an excursion. 10. The system of any EXAMPLE herein where the trained neural network is trained based on data associated with a plurality of fluid supplies and the controller determines the presence of the anomaly associated with the fluid supply utilizing the trained neural network based on a classification of the initial data. 11 . The system of any EXAMPLEherein further including a dispensing head, where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 12. The system of any EXAMPLE herein where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 13. The system of any EXAMPLE herein where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0104] One EXAMPLE includes: EXAMPLE 14. A system configured to determine a presence of an anomaly associated with a tool of a dispenser includes: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of the tool; and a controller configured to actuate the one or more sensors to capture initial data associated with the tool at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the tool; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller further configured to actuate the one or more sensors to capture subsequent data associated with the tool at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0105] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 15. The system of anyEXAMPLE herein where the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the tool at the first time; and actuate the camera to capture a subsequent image of the tool at the second time. 16. The system of any EXAMPLE herein where the anomaly is a level of fluid accumulation on the tool. 17. The system of any EXAMPLE herein where the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 18. The system of any EXAMPLE herein where the alert indicates that the level of fluid accumulation is greater than the predetermined threshold. 19. The system of any EXAMPLE herein where the alert provides directions to the user for cleaning the tool such that the level of fluid accumulation is less than the predetermined threshold. 20. The system of any EXAMPLE herein where the controller is configured to: determine a predicted level of fluid accumulation on the tool based on a number of parts unloaded from the tool; determine a sensed level of fluid accumulation on the tool based on the initial image of the tool; and compare the predicted level of fluid accumulation on the tool to the sensed level of fluid accumulation on the tool to identify an excursion. 21 . The system of any EXAMPLE herein where the trained neural network is trained based on data associated with a plurality of tools and the controller determines the presence of the anomaly associated with the tool utilizing the trained neural network based on a classification of the initial data to data. 22. The system of any EXAMPLE herein where the controller is configured to repeat capturing and processing the initial data and the subsequent data each time a part is unloaded from the tool. 23. The system of any EXAMPLE herein further including a dispensing head, where the controller is further configured to send a signal to the dispensing head tocause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 24. The system of any EXAMPLE herein where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 25. The system of any EXAMPLE herein where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0106] One EXAMPLE includes: EXAMPLE 26. A system configured to determine a presence of an anomaly associated with a fluid supply and / or a tool of a dispenser includes: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of at least one of the fluid supply and the tool; and a controller configured to actuate the one or more sensors to capture initial data associated with at least one of the fluid supply and the tool at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the at least one of the fluid supply and the tool; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller further configured to actuate the one or more sensors to capture subsequent data associated with the at least one of the fluid supply and the tool at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0107] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 27. The system of any EXAMPLE herein further including a dispensing head, where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 28. The system of any EXAMPLE herein where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 29. The system of any EXAMPLE herein where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0108] One EXAMPLE includes: EXAMPLE 30. A process for determining a presence of an anomaly associated with a fluid supply of a dispenser includes: configuring one or more sensors to sense characteristics of the fluid supply; and configuring a controller to actuate the one or more sensors to capture initial data associated with the fluid supply at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the fluid supply; configuring the controller to log the presence of the anomaly; configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; configuring the controller to actuate the one or more sensors to capture subsequent data associated with the fluid supply at a second time after the first time;and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.

[0109] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 31 . The process of any EXAMPLE herein where the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the fluid supply at the first time; and actuate the camera to capture a subsequent image of the fluid supply at the second time. 32. The process of any EXAMPLE herein where the anomaly is a level of fluid in the fluid supply. 33. The process of any EXAMPLE herein where the controller is configured to: categorize the level of fluid in the fluid supply utilizing the trained neural network as high, medium, or low. 34. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 35. The process of any EXAMPLE herein where the alert indicates that the level of fluid in the fluid supply is less than the predetermined threshold. 36. The process of any EXAMPLE herein where the alert provides directions to the user for refilling the fluid supply such that the level of fluid is greater than or equal to the predetermined threshold. 37. The process of any EXAMPLE herein where the alert provides directions to the user for replacing the fluid supply with a second fluid supply having a level of fluid greater than or equal to the predetermined threshold. 38. The process of any EXAMPLE herein where the controller is configured to: determine a predicted level of fluid in the fluid supply based on an amount of fluid dispensed by the dispenser; determine a sensed level of fluid in the fluid supply based on the initial image of the fluid supply; and compare the predicted level of fluid in thefluid supply to the sensed level of fluid in the fluid supply to identify an excursion. 39. The process of any EXAMPLE herein where the trained neural network is trained based on data associated with a plurality of fluid supplies and the controller determines the presence of the anomaly associated with the fluid supply utilizing the trained neural network based on a classification of the initial data. 40. The process of any EXAMPLE herein further including configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 41 . The process of any EXAMPLE herein further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 42. The process of any EXAMPLE herein further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0110] One EXAMPLE includes: EXAMPLE 43. A process for determining a presence of an anomaly associated with a tool of a dispenser includes: configuring one or more sensors to sense characteristics of the tool; and configuring a controller to actuate the one or more sensors to capture initial data associated with the tool at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the tool; configuring the controller to log the presence of the anomaly; configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; configuring the controller to actuate the one or more sensors to capture subsequent data associated with the tool at a second time after thefirst time; and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.

[0111] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 44. The process of any EXAMPLE herein where the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the tool at the first time; and actuate the camera to capture a subsequent image of the tool at the second time. 45. The process of any EXAMPLE herein where the anomaly is a level of fluid accumulation on the tool. 46. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 47. The process of any EXAMPLE herein where the alert indicates that the level of fluid accumulation is greater than the predetermined threshold. 48. The process of any EXAMPLE herein where the alert provides directions to the user for cleaning the tool such that the level of fluid accumulation is less than the predetermined threshold. 49. The process of any EXAMPLE herein where the controller is configured to: determine a predicted level of fluid accumulation on the tool based on a number of parts unloaded from the tool; determine a sensed level of fluid accumulation on the tool based on the initial image of the tool; and compare the predicted level of fluid accumulation on the tool to the sensed level of fluid accumulation on the tool to identify an excursion. 50. The process of any EXAMPLE herein where the trained neural network is trained based on data associated with a plurality of tools and the controller determines the presence of the anomaly associated with the tool utilizing the trained neural network based on a classification of the initial data. 51 . The process of anyEXAMPLE herein where the controller is configured to repeat capturing and processing the initial data and the subsequent data each time a part is unloaded from the tool. 52. The process of any EXAMPLE herein further including configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 53. The process of any EXAMPLE herein further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 54. The process of any EXAMPLE herein further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0112] One EXAMPLE includes: EXAMPLE 55. A process for determining a presence of an anomaly associated with a fluid supply and / or a tool of a dispenser includes: configuring one or more sensors to sense characteristics of at least one of the fluid supply and the tool; and configuring a controller configured to actuate the one or more sensors to capture initial data associated with at least one of the fluid supply and the tool at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the at least one of the fluid supply and the tool; configuring the controller to log the presence of the anomaly; configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; configuring the controller to actuate the one or more sensors to capture subsequent data associated with the at least one of the fluid supply and the tool at asecond time after the first time; and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.

[0113] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 56. The process of any EXAMPLE herein where further including configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 57. The process of any EXAMPLE herein where further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 58. The process of any EXAMPLE herein further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0114] One EXAMPLE includes: EXAMPLE 59. A system configured to determine a presence of an anomaly associated with a dispensing system component of a dispenser includes: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of the dispensing system component; a controller configured to actuate the one or more sensors to capture initial data associated with the dispensing system component at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the dispensing system component; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller furtherconfigured to actuate the one or more sensors to capture subsequent data associated with the dispensing system component at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

[0115] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 60. The system of any EXAMPLE herein where the controller determines the presence of the anomaly utilizing the trained neural network based on training with data associated with a plurality of dispensing system components. 61. The system of any EXAMPLE herein where the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the dispensing system component of the dispenser at the first time; and actuate the camera to capture a subsequent image of the dispensing system component of the dispenser at the second time. 62. The system of any EXAMPLE herein where the anomaly is a level of fluid in the fluid supply, the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 63. The system of any EXAMPLE herein where the anomaly is a level of fluid accumulation on the tool, the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 64. The system of any EXAMPLE herein where the anomaly is a presence of a foreign object in a work area of the dispenser. 65. The system of any EXAMPLE herein where the trained neural network is trained based on atleast one image of the work area of the dispenser devoid of any foreign objects and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 66. The system of any EXAMPLE herein where the anomaly is at least one of a full purge cup and a dirty cleaning strip of a service station of the dispenser. 67. The system of any EXAMPLE herein where the trained neural network is trained based on at least one image of at least one of a non-full purge cup and a non-dirty cleaning strip of the service station of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 68. The system of any EXAMPLE herein where the anomaly is a misleading of the part on the tool. 69. The system of any EXAMPLE herein where the trained neural network is trained based on at least one image of a part properly loaded on the tool and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 70. The system of any EXAMPLE herein where the anomaly is a misposition of a bubble on a scale level of the dispenser. 71. The system of any EXAMPLE herein where the trained neural network is trained based on at least one image of a properly positioned bubble on the scale level of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 72. The system of any EXAMPLE herein where the anomaly is an unauthorized user of the dispenser. 73. The system of any EXAMPLE herein where the trained neural network is trained based on at least one of facial recognition, biometric information, and a unique badge of an authorized user and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 74. The system of any EXAMPLE herein where the anomaly is a characteristicof the dispensing system component selected from the group consisting of a leak associated with the dispensing system component, damage or wear associated with the dispensing system component, and a jam or disconnection associated with the dispensing system component. 75. The system of any EXAMPLE herein where the trained neural network is trained based on at least one image of a dispensing system component that is not leaking, damaged or worn, and / or jammed or disconnected and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 76. The system of any EXAMPLE herein where the anomaly is a temperature and / or an LED status of the dispensing system component. 77. The system of any EXAMPLE herein where the trained neural network is trained based on at least one image of a temperature and / or an LED status of a dispensing system component having a temperature less than a predetermined threshold and / or an operational LED status and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the temperature and / or the LED status of the dispensing system component. 78. The system of any EXAMPLE herein where the one or more sensors includes an infrared camera configured to determine the temperature and / or the LED status of the dispensing system component. 79. The system of any EXAMPLE herein further including a dispensing head, where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 80. The system of any EXAMPLE herein where the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 81 . The system of any EXAMPLE herein where the controller is further configured to send a signal tothe dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0116] One EXAMPLE includes: EXAMPLE 82. A process for determining a presence of an anomaly associated with a dispensing system component of a dispenser includes: configuring one or more sensors to sense characteristics of the dispensing system component; configuring a controller to actuate the one or more sensors to capture initial data associated with the dispensing system component at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the dispensing system component; configuring the controller to log the presence of the anomaly; configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; configuring the controller to actuate the one or more sensors to capture subsequent data associated with the dispensing system component at a second time after the first time; and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.

[0117] The above-noted EXAMPLE may further include any one or a combination of more than one of the following EXAMPLES: 83. The process of any EXAMPLE herein where the controller determines the presence of the anomaly utilizing the trained neural network based on training with data associated with a plurality of dispensing system components. 84. The process of any EXAMPLE herein where the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the dispensing system component of the dispenser at the first time; and actuate the camera to capture a subsequent image of thedispensing system component of the dispenser at the second time. 85. The process of any EXAMPLE herein where the anomaly is a level of fluid in a fluid supply, the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 86. The process of any EXAMPLE herein where the anomaly is a level of fluid accumulation on a tool, the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 87. The process of any EXAMPLE herein where the anomaly is a presence of a foreign object in a work area of the dispenser. 88. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of the work area of the dispenser devoid of any foreign objects and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 89. The process of any EXAMPLE herein where the anomaly is at least one of a full purge cup and a dirty cleaning strip of a service station of the dispenser. 90. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of at least one of a non-full purge cup and a non-dirty cleaning strip of the service station of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 91 . The process of any EXAMPLE herein where the anomaly is a misloading of a part on a tool. 92. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of a part properly loaded on the tool and the controller is configured to determinethe presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 93. The process of any EXAMPLE herein where the anomaly is a misposition of a bubble on a scale level of the dispenser. 94. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of a properly positioned bubble on the scale level of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 95. The process of any EXAMPLE herein where the anomaly is an unauthorized user of the dispenser. 96. The process of any EXAMPLE herein where the trained neural network is trained based on at least one of facial recognition, biometric information, and a unique badge of an authorized user and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image. 97. The process of any EXAMPLE herein where the anomaly is a characteristic of the dispensing system component selected from the group consisting of a leak associated with the dispensing system component, damage or wear associated with the dispensing system component, and a jam or disconnection associated with the dispensing system component. 98. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of a dispensing system component that is not leaking, damaged or worn, and / or jammed or disconnected and the controller is configured to determine the presence of an anomaly utilizing the trained neural network based on a classification of the initial image. 99. The process of any EXAMPLE herein where the anomaly is a temperature and / or an LED status of the dispensing system component. 100. The process of any EXAMPLE herein where the trained neural network is trained based on at least one image of a temperature and / or an LED status of a dispensing system component having a temperature less than apredetermined threshold and / or an operational LED status and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the temperature and / or the LED status of the dispensing system component. 101 . The process of any EXAMPLE herein where the one or more sensors includes an infrared camera configured to determine the temperature and / or the LED status of the dispensing system component. 102. The process of any EXAMPLE herein further including configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data. 103. The process of any EXAMPLE herein further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly. 104. The process of any EXAMPLE herein further including configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

[0118] Conditional language used herein, such as, among others, “can,” “could,” “might,” “may,” “e.g.,” and the like, unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain examples include, while other examples do not include, certain features, elements, and / or steps. Thus, such conditional language is not generally intended to imply that features, elements, and / or steps are in any way required for one or more examples or that one or more examples necessarily include these features, elements and / or steps. The terms “comprising,” “including,” “having,” and the like are synonymous and are used inclusively, in an open-ended fashion, and do not exclude additional elements, features, acts, operations, and so forth.

[0119] While certain examples have been described, these examples have been presented by way of example only and are not intended to limit the scope of the inventions disclosed herein. Thus, nothing in the foregoing description is intended to imply that any particular feature, characteristic, step, module, or block is necessary or indispensable. Indeed, the novel methods and articles described herein may be embodied in a variety of other forms; furthermore, various omissions, substitutions, and changes in the form of the methods and articles described herein may be made without departing from the spirit of the inventions disclosed herein. The accompanying claims and their equivalents are intended to cover such forms or modifications as would fall within the scope and spirit of certain of the inventions disclosed herein.

[0120] It should be understood that the steps of the exemplary methods set forth herein are not necessarily required to be performed in the order described, and the order of the steps of such methods should be understood to be merely exemplary. Likewise, additional steps may be included in such methods, and certain steps may be omitted or combined, in methods consistent with various examples of the present invention.

[0121] Although the elements in the following method claims are recited in a particular sequence with corresponding labeling, unless the claim recitations otherwise imply a particular sequence for implementing some or all of those elements, those elements are not necessarily intended to be limited to being implemented in that particular sequence.

[0122] It will be understood that reference herein to “a” or “one” to describe a feature such as a component or step does not foreclose additional features or multiples of the feature. For instance, reference to a device having or defining “one” of a feature does not preclude the device from having or defining more than one of the feature, aslong as the device has or defines at least one of the feature. Similarly, reference herein to “one of” a plurality of features does not foreclose the invention from including two or more, up to all, of the features. For instance, reference to a device having or defining “one of a X and Y” does not foreclose the device from having both the X and Y.

Claims

What is Claimed:1 . A system configured to determine a presence of an anomaly associated with a fluid supply of a dispenser, the system comprising: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of the fluid supply; and a controller configured to actuate the one or more sensors to capture initial data associated with the fluid supply at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the fluid supply; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller further configured to actuate the one or more sensors to capture subsequent data associated with the fluid supply at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

2. The system of claim 1 , wherein the one or more sensors includes a camera and the controller is configured to:actuate the camera to capture an initial image of the fluid supply at the first time; and actuate the camera to capture a subsequent image of the fluid supply at the second time.

3. The system of claim 2, wherein the anomaly is a level of fluid in the fluid supply.

4. The system of claim 3, wherein the controller is configured to: categorize the level of fluid in the fluid supply utilizing the trained neural network as high, medium, or low.

5. The system of claim 3, wherein the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

6. The system of claim 3, wherein the alert indicates that the level of fluid in the fluid supply is less than the predetermined threshold.

7. The system of claim 6, wherein the alert provides directions to the user for refilling the fluid supply such that the level of fluid is greater than or equal to the predetermined threshold.

8. The system of claim 7, wherein the alert provides directions to the user for replacing the fluid supply with a second fluid supply having a level of fluid greater than or equal to the predetermined threshold.

9. The system of claim 2, wherein the controller is configured to: determine a predicted level of fluid in the fluid supply based on an amount of fluid dispensed by the dispenser; determine a sensed level of fluid in the fluid supply based on the initial image of the fluid supply; and compare the predicted level of fluid in the fluid supply to the sensed level of fluid in the fluid supply to identify an excursion.

10. The system of claim 1 , wherein the trained neural network is trained based on data associated with a plurality of fluid supplies and the controller determines the presence of the anomaly associated with the fluid supply utilizing the trained neural network based on a classification of the initial data.11 . The system of claim 1 , further comprising a dispensing head, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.

12. The system of claim 1 1 , wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.

13. The system of claim 12, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

14. A system configured to determine a presence of an anomaly associated with a tool of a dispenser, the system comprising: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of the tool; and a controller configured to actuate the one or more sensors to capture initial data associated with the tool at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the tool; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller further configured to actuate the one or more sensors to capture subsequent data associated with the tool at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

15. The system of claim 14, wherein the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the tool at the first time; and actuate the camera to capture a subsequent image of the tool at the second time.

16. The system of claim 15, wherein the anomaly is a level of fluid accumulation on the tool.

17. The system of claim 16, wherein the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

18. The system of claim 17, wherein the alert indicates that the level of fluid accumulation is greater than the predetermined threshold.

19. The system of claim 18, wherein the alert provides directions to the user for cleaning the tool such that the level of fluid accumulation is less than the predetermined threshold.

20. The system of claim 15, wherein the controller is configured to: determine a predicted level of fluid accumulation on the tool based on a number of parts unloaded from the tool;determine a sensed level of fluid accumulation on the tool based on the initial image of the tool; and compare the predicted level of fluid accumulation on the tool to the sensed level of fluid accumulation on the tool to identify an excursion.21 . The system of claim 14, wherein the trained neural network is trained based on data associated with a plurality of tools and the controller determines the presence of the anomaly associated with the tool utilizing the trained neural network based on a classification of the initial data to data.

22. The system of claim 14, wherein the controller is configured to repeat capturing and processing the initial data and the subsequent data each time a part is unloaded from the tool.

23. The system of claim 14, further comprising a dispensing head, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.

24. The system of claim 23, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.

25. The system of claim 24, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to resumedispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

26. A system configured to determine a presence of an anomaly associated with a fluid supply and / or a tool of a dispenser, the system comprising: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of at least one of the fluid supply and the tool; and a controller configured to actuate the one or more sensors to capture initial data associated with at least one of the fluid supply and the tool at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the at least one of the fluid supply and the tool; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller further configured to actuate the one or more sensors to capture subsequent data associated with the at least one of the fluid supply and the tool at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

27. The system of claim 26, further comprising a dispensing head, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.

28. The system of claim 27, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.

29. The system of claim 28, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

30. A process for determining a presence of an anomaly associated with a fluid supply of a dispenser, the process comprising: configuring one or more sensors to sense characteristics of the fluid supply; and configuring a controller to actuate the one or more sensors to capture initial data associated with the fluid supply at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the fluid supply; configuring the controller to log the presence of the anomaly; configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location informationto a user relating to the anomaly and / or directions to the user for correcting the anomaly; configuring the controller to actuate the one or more sensors to capture subsequent data associated with the fluid supply at a second time after the first time; and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.31 . The process of claim 30, wherein the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the fluid supply at the first time; and actuate the camera to capture a subsequent image of the fluid supply at the second time.

32. The process of claim 31 , wherein the anomaly is a level of fluid in the fluid supply.

33. The process of claim 32, wherein the controller is configured to: categorize the level of fluid in the fluid supply utilizing the trained neural network as high, medium, or low.

34. The process of claim 32, wherein the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold and the controller is configured to determine the presenceof the anomaly utilizing the trained neural network based on a classification of the initial image.

35. The process of claim 32, wherein the alert indicates that the level of fluid in the fluid supply is less than the predetermined threshold.

36. The process of claim 35, wherein the alert provides directions to the user for refilling the fluid supply such that the level of fluid is greater than or equal to the predetermined threshold.

37. The process of claim 36, wherein the alert provides directions to the user for replacing the fluid supply with a second fluid supply having a level of fluid greater than or equal to the predetermined threshold.

38. The process of claim 31 , wherein the controller is configured to: determine a predicted level of fluid in the fluid supply based on an amount of fluid dispensed by the dispenser; determine a sensed level of fluid in the fluid supply based on the initial image of the fluid supply; and compare the predicted level of fluid in the fluid supply to the sensed level of fluid in the fluid supply to identify an excursion.

39. The process of claim 30, wherein the trained neural network is trained based on data associated with a plurality of fluid supplies and the controller determinesthe presence of the anomaly associated with the fluid supply utilizing the trained neural network based on a classification of the initial data.

40. The process of claim 30, further comprising configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.41 . The process of claim 40, further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.

42. The process of claim 41 , further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

43. A process for determining a presence of an anomaly associated with a tool of a dispenser, the process comprising: configuring one or more sensors to sense characteristics of the tool; and configuring a controller to actuate the one or more sensors to capture initial data associated with the tool at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the tool; configuring the controller to log the presence of the anomaly;configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; configuring the controller to actuate the one or more sensors to capture subsequent data associated with the tool at a second time after the first time; and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.

44. The process of claim 43, wherein the one or more sensors includes a camera and the controller is configured to: actuate the camera to capture an initial image of the tool at the first time; and actuate the camera to capture a subsequent image of the tool at the second time.

45. The process of claim 44, wherein the anomaly is a level of fluid accumulation on the tool.

46. The process of claim 45, wherein the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

47. The process of claim 46, wherein the alert indicates that the level of fluid accumulation is greater than the predetermined threshold.

48. The process of claim 47, wherein the alert provides directions to the user for cleaning the tool such that the level of fluid accumulation is less than the predetermined threshold.

49. The process of claim 44, wherein the controller is configured to: determine a predicted level of fluid accumulation on the tool based on a number of parts unloaded from the tool; determine a sensed level of fluid accumulation on the tool based on the initial image of the tool; and compare the predicted level of fluid accumulation on the tool to the sensed level of fluid accumulation on the tool to identify an excursion.

50. The process of claim 43, wherein the trained neural network is trained based on data associated with a plurality of tools and the controller determines the presence of the anomaly associated with the tool utilizing the trained neural network based on a classification of the initial data.51 . The process of claim 43, wherein the controller is configured to repeat capturing and processing the initial data and the subsequent data each time a part is unloaded from the tool.

52. The process of claim 43, further comprising configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.

53. The process of claim 52, further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.

54. The process of claim 53, further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

55. A process for determining a presence of an anomaly associated with a fluid supply and / or a tool of a dispenser, the process comprising: configuring one or more sensors to sense characteristics of at least one of the fluid supply and the tool; and configuring a controller configured to actuate the one or more sensors to capture initial data associated with at least one of the fluid supply and the tool at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the at least one of the fluid supply and the tool; configuring the controller to log the presence of the anomaly; configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly;configuring the controller to actuate the one or more sensors to capture subsequent data associated with the at least one of the fluid supply and the tool at a second time after the first time; and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.

56. The process of claim 55, further comprising configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.

57. The process of claim 56, further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.

58. The process of claim 57, further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

59. A system configured to determine a presence of an anomaly associated with a dispensing system component of a dispenser, the system comprising: a fluid supply for containing a fluid; a tool for supporting a part; one or more sensors configured to sense characteristics of the dispensing system component; rea controller configured to actuate the one or more sensors to capture initial data associated with the dispensing system component at a first time; the controller further configured to process the initial data in a trained neural network to determine a presence of an anomaly associated with the dispensing system component; the controller further configured to log the presence of the anomaly; the controller further configured to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; the controller further configured to actuate the one or more sensors to capture subsequent data associated with the dispensing system component at a second time after the first time; and the controller further configured to process the subsequent data to determine whether the anomaly has been corrected.

60. The system of claim 59, wherein the controller determines the presence of the anomaly utilizing the trained neural network based on training with data associated with a plurality of dispensing system components.61 . The system of claim 59, wherein the one or more sensors includess a camera and the controller is configured to: actuate the camera to capture an initial image of the dispensing system component of the dispenser at the first time; andactuate the camera to capture a subsequent image of the dispensing system component of the dispenser at the second time.

62. The system of claim 61 , wherein the anomaly is a level of fluid in the fluid supply, the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

63. The system of claim 61 , wherein the anomaly is a level of fluid accumulation on the tool, the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

64. The system of claim 61 , wherein the anomaly is a presence of a foreign object in a work area of the dispenser.

65. The system of claim 64, wherein the trained neural network is trained based on at least one image of the work area of the dispenser devoid of any foreign objects and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

66. The system of claim 61 , wherein the anomaly is at least one of a full purge cup and a dirty cleaning strip of a service station of the dispenser.

67. The system of claim 66, wherein the trained neural network is trained based on at least one image of at least one of a non-full purge cup and a non-dirty cleaning strip of the service station of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

68. The system of claim 61 , wherein the anomaly is a misloading of the part on the tool.

69. The system of claim 68, wherein the trained neural network is trained based on at least one image of a part properly loaded on the tool and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

70. The system of claim 61 , wherein the anomaly is a misposition of a bubble on a scale level of the dispenser.71 . The system of claim 70, wherein the trained neural network is trained based on at least one image of a properly positioned bubble on the scale level of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

72. The system of claim 61 , wherein the anomaly is an unauthorized user of the dispenser.

73. The system of claim 72, wherein the trained neural network is trained based on at least one of facial recognition, biometric information, and a unique badge of an authorized user and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

74. The system of claim 61 , wherein the anomaly is a characteristic of the dispensing system component selected from the group consisting of a leak associated with the dispensing system component, damage or wear associated with the dispensing system component, and a jam or disconnection associated with the dispensing system component.

75. The system of claim 74, wherein the trained neural network is trained based on at least one image of a dispensing system component that is not leaking, damaged or worn, and / or jammed or disconnected and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

76. The system of claim 61 , wherein the anomaly is a temperature and / or an LED status of the dispensing system component.

77. The system of claim 76, wherein the trained neural network is trained based on at least one image of a temperature and / or an LED status of a dispensing system component having a temperature less than a predetermined threshold and / or anoperational LED status and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the temperature and / or the LED status of the dispensing system component.

78. The system of claim 77, wherein the one or more sensors includes an infrared camera configured to determine the temperature and / or the LED status of the dispensing system component.

79. The system of claim 59, further comprising a dispensing head, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.

80. The system of claim 79, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.81 . The system of claim 80, wherein the controller is further configured to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

82. A process for determining a presence of an anomaly associated with a dispensing system component of a dispenser, the process comprising:configuring one or more sensors to sense characteristics of the dispensing system component; configuring a controller to actuate the one or more sensors to capture initial data associated with the dispensing system component at a first time; configuring the controller to process the initial data in a trained neural network to determine a presence of an anomaly associated with the dispensing system component; configuring the controller to log the presence of the anomaly; configuring the controller to generate and send an alert to a human machine interface indicating the presence of the anomaly, the alert providing location information to a user relating to the anomaly and / or directions to the user for correcting the anomaly; configuring the controller to actuate the one or more sensors to capture subsequent data associated with the dispensing system component at a second time after the first time; and configuring the controller to process the subsequent data to determine whether the anomaly has been corrected.

83. The process of claim 82, wherein the controller determines the presence of the anomaly utilizing the trained neural network based on training with data associated with a plurality of dispensing system components.

84. The process of claim 82, wherein the one or more sensors includes a camera and the controller is configured to:actuate the camera to capture an initial image of the dispensing system component of the dispenser at the first time; and actuate the camera to capture a subsequent image of the dispensing system component of the dispenser at the second time.

85. The process of claim 84, wherein the anomaly is a level of fluid in a fluid supply, the trained neural network is trained based on at least one image of a fluid supply having a level of fluid greater than or equal to a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

86. The process of claim 84, wherein the anomaly is a level of fluid accumulation on a tool, the trained neural network is trained based on at least one image of a tool having a level of fluid accumulation less than a predetermined threshold, and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

87. The process of claim 84, wherein the anomaly is a presence of a foreign object in a work area of the dispenser.

88. The process of claim 87, wherein the trained neural network is trained based on at least one image of the work area of the dispenser devoid of any foreign objects and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

89. The process of claim 84, wherein the anomaly is at least one of a full purge cup and a dirty cleaning strip of a service station of the dispenser.

90. The process of claim 89, wherein the trained neural network is trained based on at least one image of at least one of a non-full purge cup and a non-dirty cleaning strip of the service station of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.91 . The process of claim 84, wherein the anomaly is a misloading of a part on a tool.

92. The process of claim 91 , wherein the trained neural network is trained based on at least one image of a part properly loaded on the tool and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

93. The process of claim 84, wherein the anomaly is a misposition of a bubble on a scale level of the dispenser.

94. The process of claim 93, wherein the trained neural network is trained based on at least one image of a properly positioned bubble on the scale level of the dispenser and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

95. The process of claim 84, wherein the anomaly is an unauthorized user of the dispenser.

96. The process of claim 95, wherein the trained neural network is trained based on at least one of facial recognition, biometric information, and a unique badge of an authorized user and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the initial image.

97. The process of claim 84, wherein the anomaly is a characteristic of the dispensing system component selected from the group consisting of a leak associated with the dispensing system component, damage or wear associated with the dispensing system component, and a jam or disconnection associated with the dispensing system component.

98. The process of claim 97, wherein the trained neural network is trained based on at least one image of a dispensing system component that is not leaking, damaged or worn, and / or jammed or disconnected and the controller is configured to determine the presence of an anomaly utilizing the trained neural network based on a classification of the initial image.

99. The process of claim 84, wherein the anomaly is a temperature and / or an LED status of the dispensing system component.

100. The process of claim 99, wherein the trained neural network is trained based on at least one image of a temperature and / or an LED status of a dispensing system component having a temperature less than a predetermined threshold and / or an operational LED status and the controller is configured to determine the presence of the anomaly utilizing the trained neural network based on a classification of the temperature and / or the LED status of the dispensing system component.101 . The process of claim 99, wherein the one or more sensors includes an infrared camera configured to determine the temperature and / or the LED status of the dispensing system component.

102. The process of claim 82, further comprising configuring the controller to send a signal to a dispensing head to cause the dispensing head to dispense a fluid therefrom prior to actuating the one or more sensors to capture the initial data.

103. The system of claim 102, further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to cease dispensing of the fluid therefrom if the controller determines the presence of the anomaly.

104. The system of claim 103, further comprising configuring the controller to send a signal to the dispensing head to cause the dispensing head to resume dispensing of the fluid therefrom if the controller determines that the anomaly has been corrected.

Images