Controlling cleaning machine cycles using machine vision

Abstract

Image classification is used to dynamically control one or more wash parameters in an automated cleaning machine. An imaging device installed in a wash chamber of the cleaning machine captures one or more images of an article to be cleaned at various times throughout a cleaning process. A computing device analyzes the captured images to classify the images according to article type and rack capacity. Based on the article type classification and the rack capacity, the computing device dynamically controls one or more parameters of the cleaning process to achieve a satisfactory cleaning and / or sanitization result.

Description

[0001] This application claims the benefits of U.S. Provisional Application No. 62 / 899,592, filed September 12, 2019, entitled “Control of Cleaning Machine Cycles Using Machine Vision”. Background Technology

[0002] Automated cleaning machines are used in restaurants, healthcare facilities, and other locations to clean, sterilize, and / or disinfect a variety of items. In restaurants or food processing facilities, automated cleaning machines (such as dishwashing machines or dishwashers) are used to clean food preparation and dining items, such as tableware, glassware, deep pots, pans, utensils, food processing equipment, and other items. Generally, items to be cleaned are placed on a rack and fed into the cleaning chamber of the automated cleaning machine. In the chamber, one or more cleaning products and / or rinsing agents are applied to the items during the cleaning process. The cleaning process may include one or more washing stages and one or more rinsing stages. At the end of the cleaning process, the rack is removed from the cleaning chamber. Water temperature, water pressure, water quality, concentration of chemical cleaning agents and / or rinsing agents, duration of washing and / or rinsing cycles, and other factors can affect the effectiveness of the cleaning process. Summary of the Invention

[0003] Generally, this disclosure relates to systems and / or methods for analyzing one or more images of items to be cleaned to control the cleaning process of an automated cleaning machine. According to this disclosure, an imaging device compatible with the environment inside the cleaning chamber of the automated cleaning machine captures one or more images of the items to be cleaned. A computing device analyzes the captured images to extract information about the items. For example, the computing device may analyze the captured images based on a classification model to classify the item type and / or assign rack capacity corresponding to the items presented in the captured images. The computing device may also determine the degree of soiling of the items presented in the captured images. This information can be used to control one or more parameters of the cleaning process (e.g., the length of the washing and / or rinsing cycle, the washing and / or rinsing water temperature, detergent concentration, etc.) to achieve satisfactory cleaning and / or disinfection results for each individual rack. The computing device may also analyze the captured images to extract information about the rewash frequency, the type of utensil material, and / or other relevant information about the items to be cleaned.

[0004] The system can further correlate rack capacity with the amount of energy required to achieve adequate sterilization of the items in the rack. In this way, for each individual rack, the system can determine, based on rack capacity, whether sufficient heat energy has been transferred to the surface of the vessel to achieve adequate sterilization.

[0005] In one instance, this disclosure relates to a system comprising: at least one imaging device that captures a pre-cleaning image of an item to be cleaned in a cleaning chamber of a cleaning machine by an associated cleaning process; at least one processor; and a storage device including instructions executable by the at least one processor to: analyze the pre-cleaning image to classify the item as belonging to one of a plurality of item types; and determine one or more parameters of the associated cleaning process based on the classified item type.

[0006] In some instances, at least one imaging device may further capture post-cleaning images of the article after the associated cleaning process is completed, and the storage device may further include instructions executable by at least one processor to: analyze the post-cleaning images to determine the amount of dirt remaining on the article after the cleaning process is completed; determine an extended cleaning cycle time for the associated cleaning process based on the amount of dirt remaining; and initiate an extended cleaning cycle by a cleaning machine, having a cleaning cycle duration corresponding to the extended cleaning cycle time.

[0007] The storage device may further include instructions executable by at least one processor to perform the following operations: determining an extended rinsing cycle time for an associated cleaning process based on the amount of residual dirt; and initiating an extended cleaning cycle via a cleaning machine, having a cleaning cycle duration corresponding to the extended cleaning cycle time and a rinsing cycle duration corresponding to the extended rinsing cycle time.

[0008] The storage device may further include instructions executable by at least one processor to: analyze pre-cleaning images to allocate one of a plurality of rack capacities corresponding to the relative fullness of racks supporting items in the cleaning chamber; and determine one or more parameters of the associated cleaning process based on the allocated rack capacity.

[0009] The storage device may further include instructions executable by at least one processor to perform the following: initiating a cleaning cycle of the cleaning machine with a cleaning cycle duration set based on one of a plurality of item types and an allocated rack capacity.

[0010] In some instances, the storage device may further store one or more characteristic tank temperature changes, each characteristic tank temperature change corresponding to a different one among a variety of vessel materials. The storage device may further include instructions executable by at least one processor to: receive tank temperature information during a designated portion of the cleaning process; compare the received tank temperature information with one or more stored characteristic tank temperature changes; identify a corresponding one among the variety of vessel materials based on the comparison; and determine one or more cleaning cycle parameters based on the identified one among the variety of vessel materials.

[0011] In some instances, the storage device may further include instructions executable by at least one processor to perform the following operation: analyze post-cleaning images of the item to determine whether the item is presented in one or more images associated with the previous cleaning process.

[0012] In another instance, this disclosure relates to a method comprising: capturing a pre-cleaning image of an item to be cleaned in a cleaning chamber of a cleaning machine by an imaging device; analyzing the pre-cleaning image to classify the item as belonging to one of a plurality of item types; and determining one or more parameters of the associated cleaning process based on the classified item type.

[0013] The method may further include: capturing a post-cleaning image of the item using an imaging device after completing an associated cleaning process; analyzing the post-cleaning image to determine the amount of dirt remaining on the item after the cleaning process; determining an extended cleaning cycle time for the associated cleaning process based on the amount of residual dirt; and initiating an extended cleaning cycle with a cleaning cycle duration corresponding to the extended cleaning cycle time using a cleaning machine. The method may further include: determining an extended rinsing cycle time for the associated cleaning process based on the amount of residual dirt; and initiating an extended cleaning cycle with a cleaning cycle duration corresponding to the extended cleaning cycle time and a rinsing cycle duration corresponding to the extended rinsing cycle time using a cleaning machine.

[0014] The method may further include analyzing pre-cleaning images to allocate one of a plurality of rack capacities corresponding to the relative fullness of racks supporting items in the cleaning chamber; and determining one or more parameters of the associated cleaning process based on the allocated rack capacity.

[0015] The method may further include starting a cleaning cycle with a cleaning cycle duration set based on a sorted item type and an allocated rack capacity for the cleaning machine.

[0016] The method may further include storing one or more characteristic tank temperature changes, each characteristic tank temperature change corresponding to a different one among a variety of vessel materials. The method may further include: receiving tank temperature information during a designated portion of the cleaning process; comparing the received tank temperature information with one or more stored characteristic tank temperature changes; identifying a corresponding one among the variety of vessel materials based on the comparison; and determining one or more cleaning cycle parameters based on the identified one among the variety of vessel materials.

[0017] In another instance, this disclosure relates to a system configured to control a cleaning process for cleaning articles in a cleaning chamber of a cleaning machine, the articles comprising one of a plurality of utensil materials, the system comprising: at least one processor; and a storage device including one or more characteristic tank temperature variations, each characteristic tank temperature variation corresponding to a different one of the plurality of utensil materials, the storage device further comprising instructions executable by the at least one processor to: receive tank temperature information at one or more specified times during the cleaning process; compare the received tank temperature information with one or more stored characteristic tank temperature variations; identify one of the plurality of utensil materials corresponding to the article based on the comparison; and control one or more cleaning cycle parameters of the cleaning machine based on the identified one of the plurality of utensil materials.

[0018] The system may further include at least one imaging device that captures an image of the item before cleaning; the storage device further includes instructions executable by at least one processor to: analyze the image before cleaning to classify the item as belonging to one of a plurality of item types; and control one or more parameters of the cleaning process based on the classified item type and the material of the utensil.

[0019] In any of the examples above, the cleaning machine may be an automated dishwasher, and the multiple item types may include tableware, glassware, silverware, deep pans / pans, and a mix of item types. One or more parameters of the cleaning process may include at least one of the washing cycle duration and the rinsing cycle duration.

[0020] Details of one or more examples are illustrated in the accompanying figures and descriptions below. Attached Figure Description

[0021] Figure 1 An example of an automated cleaning machine according to this disclosure is shown, wherein an imaging device captures one or more digital images of dishes inside the cleaning chamber of the cleaning machine.

[0022] Figure 2The block diagram of the instance computing system according to this disclosure shows that the instance computing system uses machine vision to dynamically control the cycle of a cleaning machine.

[0023] Figure 3 The image provided is an example of a dishwasher rack according to this disclosure, which has 36 glasses and a "full" rack capacity, the glasses being of the item type "glassware".

[0024] Figure 4 The image provided is an example of a dishwasher rack according to this disclosure, which has 15 glasses and a rack capacity of "medium full", and the glasses are of the item type "glassware".

[0025] Figure 5 The dishwasher rack shown in the example image according to this disclosure has 5 glasses and a rack capacity of "minimum full", and the glasses are of the item type "glassware".

[0026] Figure 6 The image shows an example of a dishwasher rack according to this disclosure, the rack having a plate with an item type of "tableware".

[0027] Figure 7 The image provided is an example of a dishwasher rack according to this disclosure, the rack having tableware of an article type "silver-plated tableware".

[0028] Figure 8 This table presents the experimental results of the weight of dishes relative to the temperature drop of the storage tank in multiple dishwasher cycles.

[0029] Figure 9 The flowchart illustrates an example process according to this disclosure, wherein a computing device controls one or more washing and / or rinsing cycles in a cleaning machine based on the analysis of one or more captured images.

[0030] Figure 10 The flowchart illustrates another example of a process according to this disclosure, wherein a computing device controls one or more cleaning and / or rinsing cycles in a cleaning machine based on analysis of the tank temperature. Detailed Implementation

[0031] Generally, this disclosure relates to systems and / or methods for analyzing one or more images of items to be cleaned to control the cleaning process of an automated cleaning machine. According to this disclosure, an imaging device compatible with the environment inside the cleaning chamber of the automated cleaning machine captures one or more images of the items to be cleaned. A computing device analyzes the captured images to extract information about the items. For example, the computing device may analyze the captured images based on a classification model to classify the item type and / or assign rack capacity corresponding to the items presented in the captured images. The computing device may also determine the degree of soiling of the items presented in the captured images. This information can be used to control one or more parameters of the cleaning process (e.g., the length of the washing and / or rinsing cycle, the washing and / or rinsing water temperature, detergent concentration, etc.) to achieve satisfactory cleaning and / or disinfection results for each individual rack. The computing device may also analyze the captured images to extract information about the rewash frequency, the type of utensil material, and / or other relevant information about the items to be cleaned.

[0032] According to another aspect of this disclosure, machine learning is used to train a computational system to classify items to be cleaned in one or more training images in an image dataset. The classification model is generated based on one or more training images in the image dataset. The image classification model can be generated by any machine learning algorithm, such as a convolutional neural network, or other algorithms used to construct the image classification model. The training images may contain one or more images of different item types that may be exposed to the cleaning process in the cleaning chamber of a cleaning machine. For example, for an automated dishwasher, the training images may contain: one or more images of a dishwasher rack containing drinking glasses or other glassware; one or more images of a dishwasher rack containing plates, bowls, or other tableware; one or more images of a dishwasher rack containing tableware and other silverware; one or more images of a dishwasher rack containing deep pots and pans; and one or more images of a dishwasher rack containing a mixed combination of item types. For each item type, the training images may further contain multiple images containing different numbers of items. For example, if the items are drinking glasses, the training images may include at least one image of a dishwasher rack loaded with the maximum number of drinking glasses (i.e., a full rack), and one or more images of a dishwasher rack loaded with fewer than the maximum number of drinking glasses (i.e., a partially full rack).

[0033] Using a classification model, the computing device analyzes one or more images associated with the cleaning process to classify the items to be cleaned based on item type and / or the relative fullness or rack capacity (i.e., full or incomplete). The system can further correlate rack capacity with the amount of energy, in thermal equivalents (HUE), required to achieve adequate sterilization of the vessels. In this way, the system can determine whether the cycle has received the correct number of HUEs to achieve adequate sterilization of the vessels based on rack capacity. The system can further analyze tank temperature information associated with the cleaning process to further control one or more parameters of the cleaning process.

[0034] Figure 1 An example of an automated cleaning machine 100 according to this disclosure is shown, wherein an imaging device 120 captures one or more digital images of dishes 102A to 102N inside the cleaning chamber 152 of the cleaning machine 100. In this example, the cleaning machine 100 is a dishwashing machine or dishwasher for cleaning and / or sterilizing food and / or food preparation items 102A to 102N. In this example, items 102A to 102N are plates. However, it should be understood that items 102A to 102N may also include other tableware, such as bowls, coffee cups, glassware, silverware, cooking utensils, deep pots and pans, and any other type of item. It should be further understood that the cleaning machine 100 may include any other type of cleaning machine, such as a laundry or textile washing machine, a medical device reprocessor, an automated washer sterilizer, an autoclave, a sterilizer, or any other type of cleaning machine, and this disclosure is not limited in terms of the type of cleaning machine or the type of item to be cleaned.

[0035] The cleaning machine 100 includes a housing 158 defining one or more cleaning chambers 152 and having one or more doors 160, 161 allowing entry into and / or exit from the cleaning chambers 152. One or more removable racks 154 are sized to fit inside the cleaning chambers 152. Each rack 154 may be configured to receive items to be cleaned directly thereon, or may be configured to receive one or more trays or holders in which the items to be cleaned are held during the cleaning process. The racks 154 may be general-purpose or special-purpose racks and may be configured to accommodate large and / or small items, such as deep pots, saucepans, cooking utensils, etc., food processing / preparation equipment and / or glassware, plates and other eating utensils, etc. In hospital or healthcare applications, the racks may be configured to accommodate instrument trays, hard objects, medical devices, tubing, masks, basins, bowls, bedpans or other medical items. It should be understood that, as per [the relevant regulations], [further details may be needed]. Figure 1 The configuration of rack 154 and the description of items that may be placed on or in rack 154 shown and described throughout this specification are for illustrative purposes only, and this disclosure is not limited in this respect.

[0036] For example, a typical cleaning machine, such as cleaning machine 100, operates by spraying one or more cleaning solutions 164 (a mixture of water and one or more chemical cleaning products) into a cleaning chamber 152 and thus onto the items to be cleaned. The cleaning solution is pumped to one or more spray arms 162, which spray the cleaning solution 164 into the cleaning chamber 152 at appropriate times. Cleaning machine 100 has a fresh water source and, depending on the application, may also include one or more storage tanks, such as storage tank 110, to hold used cleaning and / or rinsing solutions 112 that will be reused in the next cleaning cycle. Cleaning machine 100 may also include or have a chemical product dispenser 190 that automatically dispenses appropriate chemical products at appropriate times during the cleaning process, mixes them with a diluent, and dispenses the resulting cleaning solution 164 into the cleaning chamber 152. Depending on the machine, the items to be cleaned, the amount of dirt on the items, and other factors, one or more cleaning cycles may be interspersed with one or more rinsing and / or disinfection cycles to form a complete cleaning process of cleaning machine 100.

[0037] The cleaning machine 100 further includes a controller 170. The controller 170 includes one or more processors that monitor and control various parameters of the cleaning machine 100, such as cleaning and rinsing cycle time and duration, cleaning solution concentration, timed application of one or more chemical products, amount of chemical products to be applied, cleaning and / or rinsing cycle water temperature, and timing for applying water and chemical products to the cleaning chamber.

[0038] The cleaning machine controller 170 can communicate with a system controller 180, which analyzes images captured by the imaging device 120 to dynamically adjust the washing and / or rinsing cycle time based on the image analysis. The system controller 180 transmits the adjusted washing and / or rinsing cycle time to the cleaning machine controller 170, which then sends appropriate command signals to the cleaning machine to achieve the adjusted washing and / or rinsing cycle time as determined by the system controller 180.

[0039] In another example, the functionality of system controller 180 may be incorporated into cleaning machine controller 170. In such an example, cleaning machine controller 170 is connected to control imaging device 120 to capture one or more digital images of racks 154 and / or dishes 102A to 102N in the cleaning chamber 152 of cleaning machine 100. In such an example, cleaning machine controller 170 further analyzes the captured images to identify the type, quantity, and / or degree of contamination of dishes within cleaning machine 100, and dynamically adjusts the timing of cleaning and / or rinsing cycles based on the analysis of the captured images. Therefore, it should be understood that one or more functions of system controller 180, cleaning machine controller 170, and product dispensing system 190 may be integrated into a single controller, and this disclosure is not limited in this respect.

[0040] like Figure 1 As shown, one or more items to be cleaned, such as plates 102A to 102N, can be placed on rack 154 and moved into cleaning chamber 152 at the start of the cleaning process. Rack 154 can be moved on conveyor belt 166 or other support structure.

[0041] The controller 180 activates the imaging device 120 to capture one or more images once or multiple times during the cleaning process. For example, one or more images of racks / items in the cleaning chamber of the cleaning machine can be captured before the start of a cleaning cycle, during a cleaning cycle, between cleaning and rinsing cycles, during a rinsing cycle, and / or after the completion of a rinsing cycle. That is, one or more images can be captured before the start of a cleaning cycle, for example, after the racks / items have been loaded into the cleaning chamber but before water / cleaning solution is pumped into the cleaning chamber. One or more images can be captured once or multiple times during cleaning and / or rinsing cycles, for example, when water / cleaning solution is pumped into the cleaning chamber. One or more images can also be captured during the residence time between a cleaning cycle and a rinsing cycle when no water / cleaning solution is pumped into the cleaning chamber. One or more images can also be captured after the completion of a rinsing cycle after water / cleaning solution stops being pumped into the cleaning chamber.

[0042] The system may also include a lighting system 157 that provides suitable illumination inside the cleaning chamber for image capture purposes. For example, the lighting system 157 may include one or more light sources that illuminate the items to be cleaned with substantially diffuse broadband light. The wavelength range of the light emitted by the light source may include the visible spectrum (i.e., white light) and may also extend into the ultraviolet (UV) and / or infrared (IR) wavelength ranges. In some instances, wavelengths in the UV and / or IR wavelength ranges may be advantageous for detecting specific types of food stains on the items to be cleaned. The light source may be positioned within the cleaning chamber to reduce (to the extent possible) obstruction of the light source by one or more internal components of the cleaning machine and to ensure that the items / racks are illuminated substantially uniformly.

[0043] System controller 180 analyzes one or more images associated with the cleaning process to determine the type of items to be cleaned. System controller 180 can adjust one or more cleaning parameters of the cleaning process based on the type of items being cleaned for each individual rack. These cleaning process parameters can be tailored to the types of dirt typically encountered when cleaning each item type. For example, deep pots and pans can be stained with large amounts of baked or cooked starch, sugar, protein, and grease. In contrast, drinking glasses or cups are usually not very dirty but have stubborn stains such as lipstick, coffee, and tea stains. Once system controller 180 analyzes one or more images associated with the cleaning process to classify the item type, it controls one or more cleaning parameters of the cleaning process based on the item type to achieve satisfactory cleaning and sanitizing results. The identification of the items to be cleaned allows dishwasher controller 180 to dynamically adjust the washing and / or rinsing cycle times for each individual rack. By performing image analysis to identify the type of utensils in the cleaning chamber 152 of the cleaning machine 100, the system of this disclosure can specifically customize one or more cleaning parameters based on the type of utensils, and the dishwasher can ensure adequate cleaning and disinfection results for each individual cleaning process of the cleaning machine 100.

[0044] In use, the relative quantity or number of items to be cleaned will typically vary depending on the cleaning process. For example, some cleaning processes will be run with full racks, while others will be run with partially filled racks ranging from almost empty to almost full. The relative quantity of items in each rack can be defined as rack capacity for the purposes of this disclosure. Using the techniques of this disclosure, the system of the present invention can determine rack capacity for each individual cleaning process based on the analysis of one or more captured images associated with the cleaning process. According to this disclosure, rack capacity has been determined to affect the amount of heat energy required to achieve adequate sterilization of the utensil. In some instances, the systems and methods of this disclosure can dynamically adjust the washing and / or rinsing cycle times based on rack capacity to ensure that the items to be cleaned are exposed to at least a heat energy threshold during the cleaning process to achieve adequate sterilization of the items to be cleaned based on rack capacity.

[0045] In some instances, the cleaning machine 100 may include one or more sensors that provide additional information about parameters of the cleaning process. For example, the cleaning machine 100 may include one or more temperature sensors 153 that measure the temperature inside the cleaning chamber 152. Figure 1 In one example, temperature sensor 153 is positioned on a side wall inside the cleaning chamber 152 of cleaning machine 100. Cleaning machine 100 may further include a tank temperature sensor 114, which measures the temperature of solution 112 in tank 110. For example, the tank water temperature can be measured at the start of the cleaning process and at the end of the same cleaning process to determine the difference in tank water temperature that occurs during the cleaning process. As another example, the tank water temperature can be continuously measured or sampled throughout the cleaning process. Continuous tank water temperature data can be analyzed to identify the rate of change of tank water temperature at the start of the cleaning process or at any other point in time during the cleaning process (e.g., the slope or derivative of the temperature versus time curve at any given point in time). The system can analyze, alone or in combination with other data regarding the cleaning cycle, the difference in tank water temperature from one point in time to another, and / or the rate of change of tank water temperature at any point in time, to determine and / or adjust cleaning cycle parameters sufficiently to adequately clean and / or disinfect vessels exposed to the associated cleaning process of cleaning machine 100.

[0046] Once the cleaning process is complete, the imaging device 120 may capture one or more additional images of the vessels 102A to 102N. Post-cleaning image capture may be performed inside the cleaning chamber, as mentioned above, or outside the cleaning chamber. The cleaning machine controller 170 analyzes the post-cleaning images to determine the degree of contamination of the vessels 102A to 102N after the cycle. The degree of contamination of the vessels after the cycle is compared to a “clean” threshold to determine whether the dirt was adequately removed during the cleaning process. The “clean” threshold may depend on the type of vessel, the type of dirt, the type of information contained in the image data, the type of image analysis performed by the system, and other factors. If the degree of contamination of the vessels after the cycle does not meet the “clean” threshold, the controller 170 may determine an extended cleaning cycle time required to adequately clean the dirt remaining on the items. An extended cleaning / rinsing cycle for the determined extended cleaning cycle time may then be performed to achieve adequate cleaning of the remaining dirt.

[0047] The controller 170 can also analyze the rack capacity and the accumulated heat energy of the cycle and compare it with a sterilization threshold to determine whether the accumulated heat energy is sufficient to achieve adequate sterilization of the vessels. If the accumulated heat energy does not meet the sterilization threshold, the controller 170 can determine an extended rinsing cycle time required to achieve the heat energy level required to meet the sterilization threshold. An extended rinsing cycle for the determined extended rinsing cycle time can then be executed to achieve adequate sterilization of the vessels.

[0048] In this manner, the technology of this disclosure dynamically controls one or more parameters of the cleaning process based on the analysis of images associated with the cleaning process to ensure that items are thoroughly cleaned and disinfected. The system can therefore finely tune the washing and / or rinsing cycle parameters for each individual cleaning process based on the analysis of one or more captured images associated with the cleaning process to ensure thorough cleaning and disinfection of items. This allows for a reduction in the washing, rinsing, and / or total cycle time for individual cleaning cycles, and a reduction in the average washing, rinsing, and / or total cycle time required for multiple cleaning cycles. The technology of this disclosure thus allows for a reduction in the total amount of water and / or energy required for each cleaning process and the average amount of water and / or energy required for multiple cleaning cycles (due to, for example, shorter cycle time and less energy required for heating water), while ensuring that items exposed to the cleaning machine during the cleaning process are thoroughly cleaned and disinfected. In terms of the cost and / or time required to complete each individual cleaning process, this further reduces water, energy, and / or labor costs and increases efficiency.

[0049] In some instances, the system may generate one or more reports or notifications regarding the cleaning process. For example, the computing device may generate notifications for display, such as notifications for display on a user's computing device, based on cleaning machine cycle data generated during the cleaning process, such as notifications for display on a user's computing device. These notifications may include cleaning cycle parameters associated with the cleaning process, one or more images of the vessel captured by the imaging device 120 before, during, and / or after the completion of the cleaning process, data monitored during the cleaning process or data generated based on the analysis of the monitored data or images obtained before, during, or after the cleaning process, and / or any information associated with the cleaning process operated by one or more cleaning machines. The displayed data may further include one or more graphs or charts of data monitored or generated regarding the cleaning process and / or one or more targets of the cleaning process.

[0050] The identification of the types of utensils associated with each cleaning process, and the cleaning process data associated with each cleaning process, can be further analyzed to identify the number and type of cleaning processes within a specified time period, view historical data on problems encountered during one or more cleaning processes, view data on the general operation of one or more cleaning machines (e.g., number of cycles per day / week / month, drainage frequency, cycle time, temperature, amount of chemicals applied, etc.), the types of utensils cleaned during specific times and dates of the week, whether the racks are operating at full or partial capacity, etc., and this information can be used to generate reports to improve the management of utensil cleaning or other item cleaning facilities.

[0051] Figure 2 According to the block diagram of the example computing device 200 of this disclosure, the example computing device controls one or more cycles of a cleaning process based on the analysis of one or more captured images of the items to be cleaned. The computing device 200 may include, for example, a mobile computing device, smartphone, tablet computer, laptop computer, desktop computer, server computer, personal digital assistant (PDA), portable gaming device, portable media player, e-book reader, wearable computing device, smartwatch, television platform, or another type of computing device. In some instances, the functionality of the computing device may be integrated into a dishwasher controller 232 (or other associated cleaning machine controller), and it should be understood that this disclosure is not limited in this respect.

[0052] The computing device 200 includes one or more processors 202, one or more user interface components 204, one or more communication components 206, and one or more storage devices 208. The user interface components may include one or more audio interface, visual interface, and touch interface components, such as a touch-sensitive screen, display, speaker, button, keypad, stylus, mouse, or other mechanisms that allow personal interaction with the computing device. The communication components 206 allow the computing device 200 to communicate with other electronic devices, such as an imaging device 220, a dishwasher controller 222, a product applicator controller 242, and / or other remote or local computing devices. Communication can be achieved via wired and / or wireless connections.

[0053] Imaging device 220 may include one or more digital cameras, scanners, webcams, or any other type of imaging device. Imaging device 220 is compatible with the environment of the cleaning chamber of a cleaning machine and, in some instances, can withstand exposure to the conditions of a commercial cleaning machine's cleaning chamber for a minimum period of time, such as five years. For example, imaging device 220 should be sufficiently waterproof to withstand exposure to the environment inside a commercial dishwasher for a reasonable period of time, such as five years. In another instance, imaging device 220 may include or be mounted within a waterproof housing, the waterproof housing including a window for capturing images. The housing / window may be incorporated into or adhered to the internal sidewall of the dishwasher.

[0054] Imaging device 220 may be positioned within the cleaning chamber 152 of cleaning machine 100 such that the field of view of each captured image includes the area within cleaning chamber 152 where a rack can be positioned. In other words, the inspection area captured by imaging device 220 includes the entire outer perimeter of any rack that can be loaded into the dishwasher, such that all utensils loaded into each rack and present within cleaning chamber 152 are captured in the image. In some instances, computing device 200 may detect whether some utensils in the rack are obstructed (by some internal components of the dishwasher or by other utensils loaded onto the rack) during analysis of one or more captured images, and computing device 200 may be further configured in such cases to infer information about the obstructed utensils in the image based on information extracted from the rest of the image (e.g., type of utensils, degree of soiling, etc.).

[0055] The computing device 200 includes one or more storage devices 208, which include a sorting module 214, a cleaning process control module 212, and a verification module 216. Modules 212, 214, and 216 can perform the described operations using software, hardware, firmware, or a mixture of hardware, software, and firmware residing in and / or executing on the computing device 200. The computing device 200 can execute modules 212, 214, and 216 using one or more processors 202. The computing device 200 can execute modules 212, 214, and 216 as virtual machines executing on underlying hardware. Modules 212, 214, and 216 can execute as services or components of an operating system or computing platform. Modules 212, 214, and 216 can execute as one or more executable programs at the application layer of the computing platform. User interface 204 and modules 212, 214 and 216 may be arranged separately from computing device 200, for example, as one or more network services operating at a network in the cloud and accessible remotely by computing device 200.

[0056] According to this disclosure, classification data 218 includes item type and rack capacity information generated by machine learning analysis of one or more training images in the image dataset. The training images may contain one or more images of items of different item types. Each item type corresponds to a different type of item that can be exposed to the cleaning process in the cleaning chamber of the cleaning machine 230. For example, for an automated dishwasher, multiple item types may include glassware, cutlery, silverware, and deep pot / pan types, or mixed utensil types (a combination of glassware, cutlery, silverware, and / or deep pot / pan). The training images may therefore include: one or more images of dishwasher racks containing drinking glasses (“glassware” type); one or more images of dishwasher racks containing plates, bowls, or coffee cups (“tableware” type); one or more images of dishwasher racks containing eating utensils (“silverware” type); one or more images of dishwasher racks containing deep pots and pans (“deep pot / pan” type); and one or more images of dishwasher racks containing a combination of item types (“mixed utensil” type). In this way, each training image is classified according to the type of utensil presented in the training image, and this information (e.g., stored in classification data 218) can then be applied to classify one or more images associated with the cleaning process to determine the type of utensil to be cleaned and to control one or more parameters of the cleaning process based on the item type.

[0057] For each item type, the associated training image dataset may contain multiple images, each containing a different number of items. These training images can be used to allocate rack capacity to the images. For example, when the items are drinking glasses, the training images may include at least one image of a dishwasher rack loaded with the maximum number of drinking glasses (i.e., a full rack), and one or more images of a dishwasher rack loaded with fewer than the maximum number of drinking glasses (i.e., a partially full rack). In this way, the classification module 214 can classify the training images based on both the item type and the rack capacity.

[0058] Training images and their corresponding classifications are stored in data storage 218 for use by classification module 214 when analyzing captured images to control the cleaning process and achieve adequate cleaning and disinfection results.

[0059] The classification module 214 contains instructions executable by the processor 202 to perform various tasks. For example, the classification module 214 contains instructions executable by the processor 202 to: initiate the capture of one or more digital images of a rack containing unknown items to be cleaned; analyze the one or more digital images based on stored classification data from a training dataset; and classify the images according to the type of items identified based on the analysis of the one or more captured images. The classification module 214 can classify each of the captured images into one of a plurality of types, each type corresponding to a different type of item that may be exposed to the cleaning process in the cleaning chamber of the cleaning machine 230. For example, for an automated dishwasher, the types may include one or more of glassware types, cutlery types, silverware types, deep pot / pan types, and mixed cutlery types. The unknown items in the captured images may therefore include one or more images containing a dishwasher rack containing glassware, cutlery, silverware, deep pot / pan, or a mixed rack containing more than one type of cutlery. The classification module 214 contains instructions that, when executed, cause the processor to classify one or more captured images according to the type of utensils present in the images and therefore the type of utensils present in the cleaning chamber of the cleaning machine.

[0060] The classification module 214 may further include instructions executable by a processor to classify one or more captured images according to rack capacity. For example, if the item is a drinking glass, the captured image may be classified as a vessel type "glassware," and may also be assigned a rack capacity indicating the relative fullness of the rack. In some instances, rack capacity may be measured according to one or more fullness categories (e.g., "full," "medium full," or "minimum full"), as the absolute number of items in the rack, or as a scalar value between a minimum and a maximum value (e.g., a scalar value between 0 and 100, where 0 represents an empty rack and 100 represents a full rack, or any other range of normalized pure quantity values). It should be understood that the system may utilize any relevant measure to quantify or characterize the quantity, number, or volume of items in the rack, and it should be understood that this disclosure is not limited in this respect.

[0061] In this way, the classification module 214 can classify the captured images based on both the type of item and the rack capacity.

[0062] The cleaning process control module 212 contains instructions executable by the processor 202 to perform various tasks. For example, the cleaning process control module 212 contains instructions executable by the processor 202 to control one or more cycles of the cleaning process based on the analysis of one or more captured images, in accordance with this disclosure.

[0063] Cyclic data corresponding to one or more item type classifications and / or one or more rack capacity classifications can be stored in data storage 210. This information can be empirically determined based on experimental results of cleaning processes operated using different item types, dirt types, and rack capacities, along with cleaning machine parameters such as washing and rinsing water temperature, washing and rinsing cycle time and duration, water hardness, pH, turbidity, cleaning solution concentration, timing for applying one or more chemical products, and the quantity of chemical products applied.

[0064] Table 1 shows an example table that displays cyclical data corresponding to one or more item type categories and / or one or more rack capacity categories.

[0065] Table 1

[0066]

[0067] Rack capacity is related to the amount of energy, expressed in thermal equivalents (HUE), required to sterilize items inside the cleaning machine. Generally, according to FDA Food Codex guidance, "sterilization" means applying cumulative heat or chemicals to cleaned food contact surfaces sufficient to reduce representative disease-causing microorganisms of public health importance by 5-log. FDA Food Codex and NSF international standards have established a value of 3600 HUE as the requirement for achieving adequate sterilization.

[0068] For a given cleaning water temperature, the relative number of items loaded onto the rack affects the duration of the cleaning cycle required to accumulate the amount of energy needed to achieve adequate cleaning and / or disinfection of the items in the cleaning chamber of the cleaning machine. For example, in a fully loaded rack, the crowding, overlapping, or close spacing of items makes it difficult for the cleaning solution to reach certain areas of the utensils in the rack. This may translate into longer cleaning and / or rinsing cycle durations to ensure that all surfaces of the utensils are adequately cleaned and / or disinfected. According to the techniques of this disclosure, one or more images of the items to be cleaned can be analyzed to classify the items according to item type and determine rack capacity, allowing control of one or more parameters of the cleaning and / or rinsing cycles of the cleaning process to ensure that the items are adequately cleaned and disinfected by the cleaning process, regardless of item type or the volume of items loaded onto the rack.

[0069] Furthermore, the material of the utensil itself may affect the cleaning parameters required to achieve the minimum heat energy needed for adequate sterilization. This may be at least partly based on the heat capacity of the utensil material. For example, the cleaning process parameters required to achieve adequate sterilization of plastic tableware may differ from those required to achieve adequate sterilization of ceramic tableware. As another example, the cleaning process parameters required to achieve adequate sterilization of plastic tableware may differ from those required to achieve adequate sterilization of metal tableware. According to this disclosure, the heat capacity of the utensil material in the cleaning machine can cause characteristic changes in the tank water temperature during the cleaning process. In some instances, the tank water temperature measured once or multiple times during the cleaning process can be used to identify the type of utensil material, and one or more cleaning process parameters can be dynamically adjusted based on the type of utensil material to ensure adequate cleaning and sterilization results.

[0070] According to this disclosure, the cleaning process control module 212 may further include instructions executable by the processor 202 to: analyze one or more post-cleaning images to verify that dirt has been sufficiently removed from the items subjected to the cleaning process, and to further control one or more cycles of the cleaning process based on the analysis of the one or more post-cleaning images. For example, if the analysis of one or more post-cleaning images determines that dirt has not been sufficiently removed from the items, the cleaning process control module 212 may determine an extended cleaning cycle duration and an extended rinsing cycle duration required to sufficiently clean the dirt remaining on the items in the cleaning machine. Based on the analysis of the post-cleaning images, the computing device 200 controls the cleaning machine to automatically execute the extended cleaning and rinsing cycles with the determined durations. In this example, the cleaning cycle duration is extended because it is determined that dirt has not been sufficiently removed and therefore the items in the cleaning chamber require further cleaning to completely remove the dirt remaining on the items. In this example, the rinsing cycle is also extended to rinse the cleaning solution applied during the extended cleaning cycle.

[0071] In this way, the cleaning process control module 212 can dynamically control the total duration of the cleaning cycle (initial cleaning cycle duration and extended cleaning cycle duration) and the total duration of the rinsing cycle (initial rinsing cycle duration and extended rinsing cycle duration) based on the analysis of one or more images of the items in the cleaning chamber of the cleaning machine, to ensure adequate cleaning results (i.e., adequate dirt removal).

[0072] According to this disclosure, the cleaning process control module 212 may further include instructions executable by the processor 202 to: determine the accumulated heat energy during the cleaning process to determine whether sufficient disinfection of the items subjected to the cleaning process has been achieved, and further control one or more cycles of the cleaning process based on the result. For example, if the accumulated heat energy during the cleaning process is insufficient to achieve sufficient disinfection of the items, the cleaning process control module 212 may determine an extended rinsing cycle duration required to achieve sufficient disinfection of the items in the cleaning machine. The computing device 200 may then control the cleaning machine to automatically execute the extended rinsing cycle with the determined duration. In this example, assuming the computing device 200 previously determined based on analysis of one or more images that dirt had been sufficiently removed from the items, the rinsing cycle duration is extended because applying additional hot rinsing water during the extended rinsing cycle achieves the additional heat transfer required to meet the disinfection threshold. In this way, the cleaning process control module 212 may dynamically control the duration of the rinsing cycle based on the calculated heat energy accumulated during the duration of the cleaning process to ensure sufficient disinfection results.

[0073] According to this disclosure, the cleaning process control module 212 may further include instructions executable by the processor 202 to: analyze tank water temperatures measured once or multiple times during the cleaning process to identify the vessel material, and control one or more cleaning process parameters based on the vessel material to ensure adequate cleaning and disinfection results. For example, the cleaning process control module 212 may analyze tank water temperatures measured once or multiple times during the cleaning process to identify characteristic changes in tank water temperature corresponding to a specific vessel material. In some instances, the cleaning process control module 212 analyzes one or more tank water temperatures measured close to the start of the cleaning process to identify the vessel material of items present in the cleaning chamber, and may automatically adjust one or more cleaning process parameters based on the vessel material to ensure adequate cleaning and disinfection results. In other instances, the cleaning process control module 212 analyzes one or more tank water temperatures measured during the cleaning process to identify the vessel material of items present in the cleaning chamber, and may automatically determine an extended cleaning and / or rinsing cycle duration based on the vessel material to ensure adequate cleaning and disinfection results.

[0074] Reporting module 216 (or any of cleaning process control module 212, classification module 214, or other software or modules stored in storage device 208) can generate one or more notifications or reports regarding the results of one or more cleaning processes for storage or display on user interface 204 of computing device 200 or on any other local or remote computing device. For example, the following is a sample report on a cleaning process performed on August 7, 2019, which includes a classification of vessel type (glass) and rack capacity (medium) extracted from analysis of one or more images captured during the cleaning process.

[0075] Cleaning Cycle Overview

[0076]

[0077] Cleaning cycle details

[0078]

[0079] In this example, the type of container is categorized as "glassware," and the rack capacity is categorized as "medium" or a scalar value of 45 (e.g., on a scale of 0-100). As another example, the report may contain data corresponding to one or more specific cleaning processes, or data about specific cleaning processes targeting one or more of the following: location, cleaning machine, date / time, employee, etc. This data can be used to identify trends, areas for improvement, or otherwise assist organizational personnel responsible for ensuring the effectiveness of cleaning processes in identifying and addressing problems during the cleaning process.

[0080] The report may further include information on one or more cleaning processes / cycles, and the data for each cleaning process may include information such as: the date and time of the cleaning process, a unique identifier of the cleaning machine, a unique identifier of the personnel running the cleaning process and / or cleaning validation procedure, the type of sorted items cleaned during the cleaning process, the rack capacity type of the racks or pallets used during the cleaning process, the type and quantity of chemicals applied during each cycle of the cleaning process, the amount of water applied during each cycle of the cleaning process, a "pass" or "fail" indication for the cleaning process, or other information related to the cleaning process or cleaning process validation procedure. The report may also include information about the location; the business entity / enterprise; the company's cleaning validation objectives and tolerances; cleaning scores by location, zone, machine type, date / time, personnel, and / or type of cleaning chemicals; energy costs; chemical costs; and / or any other cleaning process data collected or generated by the system or requested by the user.

[0081] Figures 3 to 5 The accompanying image shows an example of a dishwasher rack according to this disclosure, the rack holding a different number of glasses, which can be analyzed by a computing device to classify the type of ware (glassware) and determine the rack capacity of the ware in the dishwasher's cleaning chamber. More specifically, Figure 3 An example image shows a dishwasher rack holding 36 glasses. Based on... Figure 3 The rack capacity determined by the analysis of the image can be classified as a "full" rack; or if a scalar value from 0 to 100 is used, then the rack can be assigned a scalar value of "100". Figure 4 An example image shows a dishwasher rack loaded with 15 dishes, which are of the "glassware" type, and the dishwasher rack can be categorized as "medium full" or assigned a scalar value of "45". Figure 5 An example image shows a dishwasher rack loaded with 5 glasses, which can be categorized as a "minimum full" rack or assigned a scalar value such as "12".

[0082] In some instances, classification module 214 includes instructions executable by a processor to perform one or more image preprocessing techniques on the original image before analyzing it for classification purposes. For example, the processor may convert the original image to grayscale; apply one or more smoothing or denoising filters to the image; crop, resize, or compress the image; reduce the file size of the image; and / or perform any other appropriate image processing techniques to prepare the image for the classification phase of the process. In some instances, these image preprocessing techniques may reduce the amount of data in each of the images being analyzed to improve the speed and efficiency of image classification analysis while still ensuring accurate classification results.

[0083] Figures 6 to 7 Additional instance (raw or unprocessed) images of dishwasher racks according to this disclosure are provided, which can be analyzed by a computing device to classify each image according to the type of utensils and determine rack capacity. In the dishwasher examples, besides Figures 3 to 5 In addition to the glassware type shown in the example images, the item type may also include one or more of the following: cutlery type, silverware type, deep pot / pan type, and mixed utensil type (a combination of glassware, cutlery, silverware and / or deep pot and pan). Figure 6 The example image is a dishwasher rack loaded with plates according to the present disclosure. The example image can be analyzed by a computing device to classify the type of utensils (tableware) for the utensils in the dishwasher's cleaning chamber. Figure 7 The example image is provided as an illustration of a dishwasher rack loaded with silver-plated tableware according to this disclosure. This example image can be analyzed by a computing device to classify the type of tableware (silver-plated tableware). It can also be determined that... Figure 6 and 7 The rack capacity of each of the example images can be determined, and the cleaning process associated with each of the example images can be controlled based on the item type and rack capacity as described herein to achieve adequate cleaning and disinfection results.

[0084] Figure 9 This table presents the experimental results of dish weight relative to tank temperature drop over multiple dishwasher cycles. Wash and rinse cycle times were kept consistent throughout each cycle. Column 2 shows rack capacity (displayed as "Number of Dishes" in the column heading) for several dishwasher cycles. The first six cycles have a rack capacity of 3 plates, and the next six cycles have a "full" rack capacity. Columns 3 through 6 show dish weight, initial tank temperature, minimum tank temperature, and tank temperature drop, respectively.

[0085] Figure 9The tank temperature drop (maximum - minimum) for a cycle with a full rack is typically greater than that for a cycle with three trays per rack. This means that for a cycle with a full rack, the temperature drop in the tank is higher than that in a cycle with a partially full rack. Figure 9 The amount of heat energy accumulated during each of the cycles (with the same cleaning cycle time, rinsing cycle time, and total cycle time) is less.

[0086] To compensate for this, the technology of this disclosure controls the washing and / or rinsing cycle time based on the rack capacity as determined by the classification module 214. For example, when the processor executing the classification module 214 classifies the rack capacity as "full" (or other rack capacity characteristics) based on the analysis of captured images of the dishes inside the dishwasher's washing chamber, the cleaning process control module 212 can adjust the length of the washing and / or rinsing cycles of the cleaning process to ensure that sufficient energy (e.g., measured in HUE) is delivered to the dishes during the dishwasher cycle. More specifically, the cleaning process control module 212 can set a longer duration for the washing and / or rinsing cycles corresponding to racks classified as "full" compared to the duration of the washing and / or rinsing cycles corresponding to racks classified as "medium full" or "minimally full".

[0087] Figure 9 The flowchart illustrates an example process (300) according to this disclosure, wherein a computing device controls one or more cleaning parameters of a cleaning process in a cleaning machine based on analysis of one or more captured images.

[0088] Near the start of the cleaning process, the computing device (e.g., as...) Figure 1 The computer device 180 shown in the document or such Figure 2 The computing device 200 shown in the diagram initiates the capture of one or more pre-cleaning images (302) of the item to be cleaned by the cleaning process. For example, at the start of the cleaning process or at an appropriate time close to the start of the cleaning process, the computing device may send a command signal to the imaging device (or to multiple imaging devices in the case of an implementation that includes more than one imaging device), such as... Figure 1 The imaging device 120 shown in the diagram is instructed by the command signal to capture an image. In some instances, for example... Figure 1In one example, the imaging device is positioned inside the cleaning chamber of the cleaning machine to capture images of the utensils / racks inside. In this way, the imaging device can capture one or more images of the utensils / racks inside the cleaning chamber at any point in time, before the cleaning process begins, during the cleaning process, and after the cleaning process is completed. In other examples, an additional imaging device may be placed near the exterior of the cleaning chamber, such as on or near the entrance door, to capture images of the utensils / racks shortly before they enter the cleaning chamber. In other examples, an additional imaging device may be positioned on or near the exterior of the exit door to capture images of the utensils / racks after they have left the cleaning chamber.

[0089] Images captured by imaging devices inside the cleaning chamber or on or near the exterior of the entrance door before the cleaning process begins can be analyzed to extract information about the type of items to be cleaned during the cleaning process and rack capacity information. This information can then be used to control one or more parameters of the cleaning process to help ensure adequate cleaning and / or disinfection results. Images captured by imaging devices inside the cleaning chamber or on or near the exterior of the exit door after the cleaning process is completed can be analyzed to extract information about dirt removal from the items that were cleaned during the cleaning process, and this dirt removal information can be used to verify whether the items were cleaned satisfactorily.

[0090] In one instance, the timing for initiating pre-cleaning image capture could be based on the opening and / or closing of the cleaning chamber entrance door (e.g., Figure 1 The sensor (of the entrance door 160) can be used to detect the cleaning chamber. In another instance, manually activating the cleaning chamber, for example, by having a user actuate a "start" button or switch, can initiate the capture of one or more images. In some instances, pre-cleaning images of items / racks inside the cleaning chamber of the cleaning machine can be captured before cleaning solution is sprayed into the cleaning chamber. In other instances, pre-cleaning images can be captured while cleaning solution is being pumped into the cleaning chamber of the cleaning machine. In any case, pre-cleaning images can be captured close to the start of the cleaning process so that the extracted item type and / or rack capacity information can be used to control one or more parameters of the cleaning process.

[0091] Refer again Figure 9The computing device analyzes each pre-wash image to classify each image according to the type of item (304). In a dishwasher, for example, the type of item may include tableware, glassware, silverware, deep pot / pan, mixed types of tableware (a combination of glassware, tableware, silverware and / or deep pot and pan) and / or any other type of item that can be cleaned by an automated dishwasher. The computing device further analyzes each pre-wash image to classify each image according to the rack capacity (306). In a dishwasher, for example, the rack capacity may include full, medium full, and minimally full. In another instance, the rack capacity may be assigned a scalar value indicating the relative fullness of the rack. For example, the rack capacity may be assigned a scalar value from 0 to 100, where 0 represents an empty rack and 100 represents a full rack. Alternatively, scalar values ​​with different normalization ranges, such as the range from 0 to 1, where 0 represents an empty rack and 1 represents a full rack, may be used. Therefore, it should be understood that rack capacity can be presented in many different ways, and this disclosure is not limited in this respect.

[0092] Additionally, at the start of the cleaning process or at an appropriate time close to the start of the cleaning process, the computing device receives tank initiation temperature information (308). For example, the tank temperature can be sensed by a temperature sensor that determines the temperature of the cleaning solution in the tank, such as... Figure 1 The sensor 114, reservoir 110, and cleaning solution 112 are shown in the diagram. The reservoir temperature information can be used to: determine or control one or more parameters of the cleaning process, such as whether the initial temperature of the reservoir meets the target temperature of the reservoir; control the pouring and filling process of the reservoir; and / or control the duration of the cleaning and / or rinsing cycles to achieve adequate cleaning and disinfection of the vessels subjected to the cleaning process according to this disclosure.

[0093] After classifying the pre-cleaning images associated with the cleaning process and determining the rack capacity, the computing device determines the cleaning cycle time and / or rinsing cycle time of the cleaning process based on the associated item type classification and rack capacity (310). For example, because drinking glasses generally have less grime than deep pots and pans, the cleaning cycle duration of a cleaning process with the item type classification "glassware" can be relatively shorter than the cleaning cycle duration of a cleaning process with the item type classification "deep pots and pans". As another example, because more heat energy may be required to achieve satisfactory sterilization of the dishes in the dishwasher when cleaning a full rack compared to an empty rack, the cleaning cycle duration and / or rinsing cycle duration of a cleaning process with the rack capacity classification "minimally full" or "medium full" can be relatively shorter than the cleaning cycle duration and / or rinsing cycle duration of a cleaning process with the rack capacity classification "full".

[0094] In some instances, process (310) may also include identifying when a particular rack is re-cleaned. In other words, when a rack that has undergone a completed cleaning process undergoes a second cleaning process with the cleaning machine. Determining whether items in a rack associated with the current cleaning process have undergone a previous cleaning process can be achieved by comparing one or more images associated with the current cleaning process with one or more images associated with the same or previous cleaning processes to determine whether the racks containing the items presented in the current and previous cleaning processes are the same. For example, the system may compare the item type and rack capacity, along with one or more features of the image, with one or more previously cleaned racks to determine whether the current rack is a re-cleaned rack. In some instances, when a rack is re-cleaned, the items in the rack are not rearranged, and therefore the arrangement of items in a re-cleaned rack will match the arrangement of items in the previous rack. Additionally, because the temperature of a re-cleaned rack has increased during the previous cleaning process, the tank temperature difference of a re-cleaned rack may be lower than that of a rack that has not been re-cleaned. In some instances, where items in a rewashed rack are rearranged before being rewashed (to better expose residual food contaminants to the cleaning process), the process can identify rewashed racks based on item type, rack capacity, and analysis of tank temperature differences during the cleaning cycle. One or more cleaning process parameters, such as washing and / or rinsing cycle times, can also be controlled based on whether the current rack is a rewashed rack.

[0095] The system can also determine re-cleaning frequency statistics by determining the total number of racks re-cleaned within a specified time period and comparing it to the total number of racks cleaned within the specified time period. Re-cleaning frequency statistics can provide managers or other employees of an enterprise or group of enterprises with information about the efficiency of the cleaning processes implemented within the enterprise. For example, a relatively high re-cleaning frequency may require further investigation to determine whether rack re-cleaning is actually necessary based on the cleaning process results. Sometimes, employees may re-clean racks "just in case" when they perceive a high initial level of dirt on items or when rack re-cleaning may not be necessary to achieve adequate cleaning and disinfection results. In such cases, employee training can help reduce the re-cleaning frequency and subsequently improve efficiency in terms of time, water, energy, and cost. At other times, rack re-cleaning may be necessary due to one or more malfunctions of the cleaning machine or other parts of the cleaning process. In any case, re-cleaning frequency statistics can indicate the need for some investigation into the reasons for a relatively high re-cleaning frequency.

[0096] After determining cleaning process parameters, such as washing and / or rinsing cycle parameters, the computing device initiates the cleaning process (312). For example, the computing device may send command signals to the dishwasher (e.g., as shown in the image). Figure 1 The dishwasher 100 shown in the image initiates the cleaning process using a determined washing cycle and / or rinsing cycle duration. Alternatively, if the cleaning process has already started, the computing device can adjust the washing cycle and / or rinsing cycle parameters based on item type classification and rack capacity classification associated with the cleaning process. The computing device can further control the washing cycle parameters based on tank temperature information.

[0097] Throughout the cleaning process (312), the computing device may receive tank temperature information once or multiple times. For example, the computing device may continuously sample the tank temperature information during the cleaning process. The computing device may also initiate the capture of one or more images of the items in the cleaning chamber throughout the cleaning process. For example, one or more images may be captured periodically during the execution of the cleaning process. As another example, one or more images may be captured during the residence time between the end of the cleaning cycle and the start of the rinsing cycle (i.e., the time between the cleaning cycle and the rinsing cycle when no cleaning fluid or rinsing water is pumped into the cleaning chamber).

[0098] Upon completion of the cleaning process, the computing device may initiate the capture of one or more post-cleaning images (314) of the racks / vessels in the cleaning chamber of the cleaning machine. The computing device may also receive the post-cleaning tank temperature (315). The post-cleaning images may be analyzed to determine the degree of contamination remaining on the vessels exposed to the cleaning process (316). The amount of residual contaminant may be compared to one or more thresholds to determine whether the contaminant has been adequately removed (318).

[0099] If the dirt is sufficiently removed (318), the computing device can determine the amount of heat energy accumulated during the cleaning process (e.g., measured in thermal equivalents (HUE)) (320). For example, the computing device can determine the amount of heat energy in part based on the tank start and / or end temperatures, the type of item, and / or rack capacity. If the accumulated heat energy meets the selected disinfection threshold (322) to ensure satisfactory disinfection of the utensils exposed to the cleaning process, then the cleaning process is completed (324).

[0100] If dirt is not adequately removed during the cleaning process (318), the computing device can determine an extended cleaning and / or rinsing cycle time (326) required to complete the cleaning process. That is, the computing device can determine an extended cleaning and / or rinsing cycle time required to adequately remove the amount of dirt remaining on the vessel, as determined by analysis of post-cleaning images. For example, the cleaning cycle duration can be extended by a sufficient amount of time to adequately clean the remaining dirt. The rinsing cycle duration can also be extended to remove the cleaning solution applied to the vessel during the extended cleaning cycle. The computing device can then control the cleaning machine to automatically execute the extended cleaning and rinsing cycles (336) with the determined duration. In this way, the process (300) can dynamically control the total duration of the cleaning cycle (initial cleaning cycle duration and extended cleaning cycle duration) and the total duration of the rinsing cycle (initial rinsing cycle duration and extended rinsing cycle duration) based on analysis of one or more images of the items in the cleaning chamber of the cleaning machine to ensure adequate cleaning results (i.e., adequate dirt removal).

[0101] If the accumulated heat energy during the cleaning process is insufficient to achieve adequate disinfection of the items (322), the computing device can determine the extended rinsing cycle duration (334) required for adequate disinfection of the items in the cleaning machine. The computing device 200 can then control the cleaning machine to automatically execute the extended rinsing cycle (336) with the determined duration. In this example, it is assumed that the computing device 200 previously determined, based on analysis of one or more images, that dirt has been adequately removed from the items (318), and the rinsing cycle duration is extended because applying additional hot rinsing water during the extended rinsing cycle achieves the additional heat transfer required to meet the disinfection threshold. In this way, the cleaning process (300) can dynamically control the duration of the rinsing cycle based on the calculated heat energy accumulated during the duration of the cleaning process to ensure adequate disinfection results.

[0102] In some instances, the material of the utensil itself may affect the cleaning parameters required to achieve the minimum heat energy needed for adequate sterilization. This may be based at least in part on the heat capacity of the utensil material. For example, the cleaning process parameters required to achieve adequate sterilization of plastic tableware may differ from those required to achieve adequate sterilization of ceramic tableware. As another example, the cleaning process parameters required to achieve adequate sterilization of plastic tableware may differ from those required to achieve adequate sterilization of metal tableware. According to this disclosure, the heat capacity of the utensil material in the cleaning machine can cause characteristic changes in the tank water temperature during the cleaning process. According to this disclosure, the tank water temperature measured once or multiple times during the cleaning process can be used to identify the type of utensil material, and one or more cleaning process parameters can be dynamically adjusted based on the type of utensil material to ensure adequate cleaning and sterilization results.

[0103] Figure 10 The flowchart illustrates another example of a process (350) according to this disclosure, wherein a computing device controls one or more cleaning and / or rinsing cycles in a cleaning machine based on analysis of the tank temperature. The computing device receives, once or multiple times before, during, and / or after the cleaning process, temperature information associated with the cleaning solution in the tank and associated with the cleaning process (referred to herein as the "tank temperature") (352). In some instances, the tank temperature information is received at the start or near the start of the cleaning process and at the end or near the end of the cleaning process to determine the absolute difference in tank temperature occurring during the cleaning process. As another example, the tank temperature is continuously measured or sampled throughout at least a designated portion of the cleaning process and / or throughout the entire cleaning process.

[0104] The computing device analyzes tank temperature data associated with the cleaning process to identify characteristic tank temperature changes corresponding to specific vessel materials (354). For example, the tank temperature information can be linked to multiple stored characteristic tank temperature changes (stored in, for example, ... Figure 2 The data is compared in the data storage 210 shown. Each of the multiple stored characteristic tank temperature changes may correspond to a different one of multiple combinations of item types / utensil materials. Examples of combinations of item types / utensil materials may include glassware / glass, glassware / plastic, tableware / ceramic, tableware / plastic, silver-plated tableware / metal, silver-plated tableware / plastic, deep pot / pan / metal, deep pot / pan / glass, etc. Each of these combinations may be associated with a different characteristic tank temperature change, which, when identified, can be used to identify the utensil material and thus control one or more parameters of the associated cleaning process.

[0105] In some instances, the characteristic tank temperature change may include, for example, the absolute difference in tank temperature measured from the start to the end of the cleaning process. In other instances, the characteristic tank temperature change may include, for example, a specified rate of change of tank temperature measured at one or more time points during the cleaning process (e.g., the slope or derivative of a time curve for tank temperature). In still other instances, the characteristic tank temperature change may include a tank temperature profile (e.g., the "shape" of a time curve for tank temperature measured from the start to the end of the cleaning process or during a specified portion of the cleaning process).

[0106] Once a characteristic temperature change associated with the cleaning process is identified, the computing device can identify the material of the vessel based on the characteristic temperature change (356). The computing device can then control one or more washing or rinsing cycle parameters based on the vessel material to achieve a cleaning process sufficient to thoroughly clean and / or disinfect the vessels in the cleaning chamber of the cleaning machine (358).

[0107] For example, the washing and / or rinsing cycle time may differ depending on the material of the tableware. For instance, the washing and / or rinsing cycle time for plastic tableware may differ from that for ceramic tableware in terms of ensuring thorough removal of dirt and ensuring adequate sterilization. Similarly, the washing and / or rinsing cycle time for silver-plated plastic tableware may differ from that for silver-plated metal tableware in terms of ensuring thorough removal of dirt and ensuring adequate sterilization.

[0108] Analysis of tank temperature information associated with the cleaning process can be used alone or in combination with the analysis of one or more images associated with the cleaning process. When used alone, tank temperature information can be used to identify the type and material of the vessel, and this information can be used to control one or more parameters of the associated cleaning process. When used in conjunction with image analysis, tank temperature information can be used to confirm the classification of item types and identify the corresponding vessel materials. Alternatively, the results of image analysis can be used to confirm the type of item, as determined by the analysis of tank temperature information, or used in conjunction with the analysis of tank temperature information to identify characteristic tank temperature variations and thus identify the type of vessel.

[0109] While the examples presented herein describe automated cleaning machines (such as dishwashers or dishwashing machines) for use in food preparation / processing applications, it should be understood that the cleaning process validation techniques described herein can be applied to a variety of other applications. Such applications may include, for example, food and / or beverage processing equipment, laundry applications, agricultural applications, hospitality applications, and / or any other applications where the cleaning, sterilization, or disinfection of items may be useful.

[0110] In one or more instances, the functionality described herein may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality may be stored as one or more instructions or code on or transmitted over a computer-readable medium and executed by a hardware-based processing unit. A computer-readable medium may comprise a computer-readable storage medium corresponding to a volatile medium such as a data storage medium or a communication medium that facilitates, for example, transferring a computer program from one place to another according to a communication protocol. In this manner, a computer-readable medium may generally correspond to (1) a non-transitory tangible computer-readable storage medium or (2) a communication medium such as a signal or carrier wave. A data storage medium may be any available medium that can be accessed by one or more computers or one or more processors to retrieve instructions, code, and / or data structures for implementing the techniques described herein. Computer program products may include computer-readable media.

[0111] By way of example and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, flash memory, or any other medium that can be used to store required program code in the form of instructions or data structures and is accessible by a computer. Furthermore, any connection is appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but rather refer to non-transient volatile storage media. As used, disks and optical discs include compact optical discs (CDs), laser discs, optical discs, digital versatile optical discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while optical discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0112] The instructions can be executed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable arrays (FPGAs), or other equivalent integrated or discrete logic circuit systems. Therefore, the term "processor" as used can refer to any of the foregoing structures or any other structure suitable for implementing the described techniques. Additionally, in some instances, the described functionality can be housed within dedicated hardware and / or software modules. Furthermore, the technology can be entirely implemented within one or more circuit or logic elements.

[0113] The techniques disclosed herein can be implemented in various devices or apparatuses, including wireless handheld devices, integrated circuits (ICs), or IC sets (e.g., chipsets). Various components, modules, or units are described in this disclosure to emphasize functional aspects of a device configured to perform the disclosed techniques, but they do not necessarily need to be implemented through different hardware units. Rather, as described above, the various units can be combined in a hardware unit or provided by a series of interoperable hardware units including one or more processors as described above, in conjunction with suitable software and / or firmware.

[0114] It should be recognized that, depending on the instance, some actions or events in any of the methods described herein may be performed in a different order, added, combined, or omitted entirely (e.g., practicing the methods does not require all of the described actions or events). Furthermore, in some instances, actions or events may be performed simultaneously, for example, through multithreading, interrupt handling, or multiple processors, rather than sequentially.

[0115] In some instances, computer-readable storage media may contain non-transitory media. The term "non-transitory" may indicate that the storage medium is not embodied in a carrier wave or propagating signal. In some instances, non-transitory storage media may store data that may change over time (e.g., in RAM or cache memory).

[0116] Example

[0117] Example 1. A system comprising: at least one imaging device for capturing a pre-cleaning image of an item to be cleaned in a cleaning chamber of a cleaning machine by an associated cleaning process; at least one processor; and a storage device including instructions executable by the at least one processor to: analyze the pre-cleaning image to classify the item as belonging to one of a plurality of item types; and determine one or more parameters of the associated cleaning process based on the classified item type.

[0118] Example 2. The system according to Example 1, wherein the cleaning machine is an automated dishwasher, and the plurality of item types include tableware type, glassware type, silver-plated tableware type, deep pot / frying pan type, and mixed tableware type.

[0119] Example 3. The system according to Example 1, wherein one or more parameters of the associated cleaning process include at least one of the cleaning cycle duration and the rinsing cycle duration.

[0120] Example 4. The system according to Example 1, wherein at least one imaging device further captures a post-cleaning image of an article after completing an associated cleaning process, and wherein the storage device further includes instructions executable by at least one processor to perform the following operations: analyzing the post-cleaning image to determine the amount of dirt remaining on the article after the cleaning process is completed; determining an extended cleaning cycle time for the associated cleaning process based on the amount of dirt remaining; and initiating an extended cleaning cycle with a cleaning cycle duration corresponding to the extended cleaning cycle time via a cleaning machine.

[0121] Example 5. The system according to Example 4, wherein the storage device includes instructions executable by at least one processor to: determine an extended rinsing cycle time for an associated cleaning process based on the amount of residual dirt; and initiate an extended cleaning cycle via a cleaning machine, having a cleaning cycle duration corresponding to the extended cleaning cycle time and a rinsing cycle duration corresponding to the extended rinsing cycle time.

[0122] Example 6. The system according to Example 1, wherein the storage device further comprises instructions executable by at least one processor to: analyze a pre-cleaning image to allocate one of a plurality of rack capacities corresponding to the relative fullness of racks supporting items in the cleaning chamber; and determine one or more parameters of an associated cleaning process based on the allocated rack capacity.

[0123] Example 7. The system according to Example 6, wherein the storage device further comprises instructions executable by at least one processor to perform: initiating a cleaning cycle of a cleaning machine having a cleaning cycle duration set based on one of a plurality of item types and an allocated rack capacity.

[0124] Example 8. The system according to Example 6, wherein the storage device further stores one or more characteristic tank temperature changes, each characteristic tank temperature change corresponding to a different one of a variety of vessel materials.

[0125] Example 9. The system according to Example 8, wherein the storage device further includes instructions executable by at least one processor to perform the following operations: receiving tank temperature information during a designated portion of the cleaning process; comparing the received tank temperature information with one or more stored characteristic tank temperature changes; identifying a corresponding one among a variety of vessel materials based on the comparison; and determining one or more cleaning cycle parameters based on the identified one among the variety of vessel materials.

[0126] Example 10. The system according to Example 1, wherein the storage device further includes instructions executable by at least one processor to perform the following operation: analyze post-cleaning images of an item to determine whether the item is presented in one or more images associated with a previous cleaning process.

[0127] Example 11. A method comprising: capturing a pre-cleaning image of an item to be cleaned in a cleaning chamber of a cleaning machine by an imaging device; analyzing the pre-cleaning image to classify the item as belonging to one of a plurality of item types; and determining one or more parameters of the associated cleaning process based on the classified item type.

[0128] Example 12. According to the method of Example 11, the cleaning machine is an automated dishwasher, and the plurality of item types include tableware type, glassware type, silver-plated tableware type, deep pot / frying pan type, and mixed tableware type.

[0129] Example 13. The method according to Example 12, wherein one or more parameters of the associated cleaning process include at least one of the cleaning cycle duration and the rinsing cycle duration.

[0130] Example 14. The method according to Example 11 further includes: capturing a post-cleaning image of an article by an imaging device after the associated cleaning process is completed; analyzing the post-cleaning image to determine the amount of dirt remaining on the article after the cleaning process is completed; determining an extended cleaning cycle time for the associated cleaning process based on the amount of dirt remaining; and initiating an extended cleaning cycle by a cleaning machine to perform an extended cleaning cycle with a cleaning cycle duration corresponding to the extended cleaning cycle time.

[0131] Example 15. The method according to Example 14 further includes: determining an extended rinsing cycle time for an associated cleaning process based on the amount of residual dirt; and initiating an extended cleaning cycle via a cleaning machine, having a cleaning cycle duration corresponding to the extended cleaning cycle time and a rinsing cycle duration corresponding to the extended rinsing cycle time.

[0132] Example 16. The method according to Example 11 further includes: analyzing pre-cleaning images to allocate one of a plurality of rack capacities corresponding to the relative fullness of racks supporting items in the cleaning chamber; and determining one or more parameters of an associated cleaning process based on the allocated rack capacity.

[0133] Example 17. The method according to Example 16 further includes initiating a cleaning cycle of a cleaning machine with a cleaning cycle duration set based on a sorted one of a plurality of item types and an allocated rack capacity.

[0134] Example 18. The method according to Example 16 further includes storing one or more characteristic tank temperature variations, each characteristic tank temperature variation corresponding to a different one of a variety of vessel materials.

[0135] Example 19. The method according to Example 18 further includes: receiving tank temperature information during a designated portion of the cleaning process; comparing the received tank temperature information with one or more stored characteristic tank temperature changes; identifying a corresponding one among a variety of vessel materials based on the comparison; and determining one or more cleaning cycle parameters based on the identified one among the variety of vessel materials.

[0136] Example 20. A system configured to control a cleaning process for cleaning articles in a cleaning chamber of a cleaning machine, the articles comprising one of a plurality of utensil materials, the system comprising: at least one processor; and a storage device including one or more characteristic tank temperature variations, each characteristic tank temperature variation corresponding to a different one of the plurality of utensil materials, the storage device further comprising instructions executable by the at least one processor to perform the following operations: receiving tank temperature information at one or more specified times during the cleaning process; comparing the received tank temperature information with one or more stored characteristic tank temperature variations; identifying one of the plurality of utensil materials corresponding to the article based on the comparison; and controlling one or more cleaning cycle parameters of the cleaning machine based on the identified one of the plurality of utensil materials.

[0137] Example 21. The system according to Example 20, wherein the cleaning machine is an automated dishwasher, and the various utensil materials include ceramic, metal, plastic and glass.

[0138] Example 22. The system according to Example 20, wherein one or more parameters of the associated cleaning process include at least one of the cleaning cycle duration and the rinsing cycle duration.

[0139] Example 23. The system according to Example 20 further includes: at least one imaging device that captures a pre-cleaning image of an item; the storage device further includes instructions executable by at least one processor to: analyze the pre-cleaning image to classify the item as belonging to one of a plurality of item types; and control one or more parameters of the cleaning process based on one of the classified item types and the material of the utensil.

[0140] Example 24. The system according to Example 23, wherein the cleaning machine is an automated dishwasher, and the plurality of item types include tableware type, glassware type, silver-plated tableware type, deep pot / frying pan type, and mixed tableware type.

[0141] Various examples have been described.

Claims

1. A system for controlling the cleaning process of an automated cleaning machine, comprising: At least one processor; and A storage device comprising instructions executable by the at least one processor to perform the following operations: Analyzing pre-cleaning images to classify items into one of several item types, the pre-cleaning images being images of items to be cleaned in the cleaning chamber of a cleaning machine during the cleaning process, the pre-cleaning images being captured by an imaging device; Analyze the pre-cleaning images to allocate one of a plurality of rack capacities corresponding to the relative fullness of the racks supporting the items in the cleaning chamber; One or more parameters of the cleaning process are determined based on the type of item; During the cleaning process, tank temperature information is received at one or more times. During the cleaning process, the amount of heat energy transferred to the items is determined based on the tank temperature information, the type of items, and the allocated rack capacity. and In response to determining during the cleaning process that the amount of heat energy transferred to the item does not meet the disinfection threshold: Determine the duration of the extended rinsing cycle; and The rinsing cycle is controlled based on the extended rinsing cycle duration.

2. The system of claim 1, wherein the cleaning machine is an automated dishwasher, and the plurality of item types include tableware type, glassware type, silver-plated tableware type, deep pot / frying pan type, and mixed tableware type.

3. The system of claim 1, wherein the one or more parameters of the cleaning process include at least one of the cleaning cycle duration and the rinsing cycle duration.

4. The system according to claim 1, wherein, The storage device further includes instructions executable by the at least one processor to perform the following operations: Analyze post-cleaning images to determine the amount of dirt remaining on the item after the cleaning process is completed; the post-cleaning images were captured after the cleaning process was completed. The extended cleaning cycle time of the cleaning process is determined based on the amount of residual dirt. and The cleaning machine is used to initiate and execute an extended cleaning cycle with a cleaning cycle duration corresponding to the extended cleaning cycle time.

5. The system of claim 4, wherein the storage device includes instructions executable by the at least one processor to perform the following operations: The duration of the extended rinsing cycle in the cleaning process is determined based on the amount of residual dirt; and The cleaning machine is used to initiate and execute an extended cleaning cycle, the extended cleaning cycle having a cleaning cycle duration corresponding to the extended cleaning cycle time and a rinsing cycle duration corresponding to the extended rinsing cycle duration.

6. The system of claim 1, wherein the storage device further comprises instructions executable by the at least one processor to perform the following operation: initiating a cleaning cycle of the cleaning machine having a cleaning cycle duration set based on the type of item and the allocated rack capacity.

7. The system of claim 1, wherein the storage device further stores one or more characteristic tank temperature changes, each characteristic tank temperature change corresponding to a different one of a variety of vessel materials.

8. The system of claim 7, wherein the storage device further comprises instructions executable by the at least one processor to perform the following operations: The temperature information of the storage tank is compared with the temperature changes of one or more characteristic storage tanks; Identify the vessel material from the various vessel materials based on comparison; and One or more cleaning cycle parameters are determined based on the identified vessel material.

9. The system of claim 1, wherein the storage device further comprises instructions executable by the at least one processor to perform the following operations: Analyze images of the item after cleaning to determine whether the item appears in one or more images associated with the previous cleaning process.

10. The system according to claim 1, wherein, The at least one processor is further configured to: When the cleaning process is complete, initiate the capture of one or more post-cleaning images of the items in the cleaning chamber; Receive the temperature of the storage tank after cleaning; Analyze the one or more post-cleaning images to determine the extent of contamination remaining on the item; as well as The degree of contamination is compared to one or more thresholds to determine whether the dirt has been sufficiently removed. Furthermore, the at least one processor is also configured to: determine the amount of heat energy transferred to the article if the dirt has been sufficiently removed.

11. A method for controlling the cleaning process of an automated cleaning machine, comprising: One or more processors analyze pre-cleaning images of items to be cleaned in the cleaning chamber of a cleaning machine to classify the items into one of several item types. The one or more processors analyze the pre-cleaning image to allocate one of a plurality of rack capacities corresponding to the relative fullness of the racks supporting the items in the cleaning chamber; The one or more processors determine one or more parameters of the cleaning process based on the type of item; The one or more processors receive tank temperature information at one or more times during the execution of the cleaning process; The amount of heat energy transferred to the items is determined by the one or more processors during the execution of the cleaning process based on the tank temperature information, the item type, and the allocated rack capacity; and In response to determining during the cleaning process that the amount of heat energy transferred to the item does not meet the disinfection threshold: the extended rinsing cycle duration is determined by the one or more processors; and The rinsing cycle is controlled by one or more processors based on the extended rinsing cycle duration.

12. The method of claim 11, wherein the cleaning machine is an automated dishwasher, and wherein the plurality of item types includes tableware type, glassware type, silver-plated tableware type, deep pot / frying pan type, and mixed tableware type.

13. The method of claim 12, wherein the one or more parameters of the cleaning process include at least one of the cleaning cycle duration and the rinsing cycle duration.

14. The method of claim 11, further comprising: One or more processors analyze post-cleaning images to determine the amount of dirt remaining on the item after the cleaning process is completed; the post-cleaning images are captured after the cleaning process is completed. The extended cleaning cycle time of the cleaning process is determined by the one or more processors based on the amount of residual dirt; and An extended cleaning cycle, having a cleaning cycle duration corresponding to the extended cleaning cycle time, is initiated and executed by the one or more processors via the cleaning machine.

15. The method of claim 14, further comprising: The extended rinsing cycle duration of the cleaning process is determined by the one or more processors based on the amount of residual dirt; and The extended cleaning cycle is initiated and executed by the one or more processors via the cleaning machine. The extended cleaning cycle has a cleaning cycle duration corresponding to the extended cleaning cycle time and a rinsing cycle duration corresponding to the extended rinsing cycle duration.

16. The method of claim 11, further comprising: A cleaning cycle of the cleaning machine is initiated by one or more processors, with a cleaning cycle duration set based on the type of item and the allocated rack capacity.

17. The method of claim 11, further comprising storing one or more characteristic tank temperature variations, each characteristic tank temperature variation corresponding to a different one of a variety of vessel materials.

18. The method of claim 17, further comprising: The one or more processors compare the storage tank temperature information with one or more characteristic storage tank temperature changes; The one or more processors identify the vessel material from the plurality of vessel materials based on comparison; and The one or more processors determine one or more cleaning cycle parameters based on the identified vessel material.

19. The method according to claim 11, wherein, The method further includes: When the cleaning process is completed, the one or more processors initiate the capture of one or more post-cleaning images of the items in the cleaning chamber; The temperature of the storage tank after cleaning is received by the one or more processors; The one or more processors analyze the one or more post-cleaning images to determine the degree of contamination remaining on the article; and The one or more processors compare the degree of contamination with one or more thresholds to determine whether the dirt has been sufficiently removed. Furthermore, the one or more processors are configured to determine the amount of heat energy transferred to the article if the dirt has been sufficiently removed.

Images