Peeling System Control

Abstract

A method of controlling a peeling system is provided, comprising monitoring at least one sensor configured to detect data indicative of characteristics of a flow of peelable product through the system, providing the data to a virtual model of the peeling system, and adjusting operation of the peeling system based on an output of the virtual model.

Description

[Technical Field]

[0001] The present invention relates to peeling systems, and in particular to the control of peeling systems using data provided from a virtual representation of the system. [Background technology]

[0002] Mechanical peeling methods are used on many food processing lines, including potato processing lines for shredded and sliced ​​potato product. Peeling machines can take many forms, including steam peelers, abrasive peelers, and knife peelers. Other forms of peeling machines can employ chemical peeling methods, such as caustic and alkaline peeling. In some cases, peeling devices are also used to remove some surface defects and blemishes. As used herein, the term "peeling" is intended to refer to any method of outer surface removal, including, but not limited to, steam, abrasive, knife, chemical, or abrasive peeling.

[0003] Peeling systems remove a thin layer of the product being peeled, ideally removing only the layer containing the peel or rind, with minimal or no removal and loss of adjacent good product material. However, some good product is removed, and all peeling systems must address this tradeoff: removing the maximum amount of skin and surface defects while minimizing the loss of good product. The greatest challenge for peeling systems is maximizing the removal of the skin or unwanted outer surface while minimizing good material loss. Within the scope of this invention, the term "peeling aggressiveness" is used to refer to this balance that must be achieved between over-peeling and under-peeling. A secondary, but important, concern for industries using peeling systems is the system's energy consumption, which should be minimized while still removing the peel at an economical production rate. An additional concern is the volume of waste and contaminated water produced by the peeling process, which must be filtered, treated, and disposed of.

[0004] High-quality peeling depends on numerous factors, including, for example, product size and quality (including product defects), as well as pressure and temperature at different points in the peeling system. A change in one of these factors during the peeling process, or indeed a miscalculation or misinterpretation of one of these factors prior to beginning the peeling process, can have a detrimental effect on peel quality. Furthermore, the peeling process may be ongoing for a period of time before a deterioration in peel quality is detected. This is often because such deterioration is highlighted by visual inspection, usually by personnel on the system floor or by visual inspection of a camera trained on the system's output.

[0005] Furthermore, many inefficiencies in current peeling systems result from downtime in the peeling process. Downtime can often be the result of stopping the process to change parameters in the system. The trigger for such parameter changes is generally an indication of a deterioration in peel quality at the system's output, again usually noted by visual inspection. Stopping and starting the process in this manner is inefficient and can also result in wasted energy. One example is the energy used to bring some equipment back up to temperature for optimal operation. Such problems lead to a combination of inefficient stop / start procedures and variable quality in the output product.

[0006] A control system that takes into account real-time data from the peeling process to ensure an optimized peeling process and the desired peeled product would be an improvement over current technology. This would provide an energy-efficient and cost-effective peeling system with increased peel quality, with more reliability and less system downtime. Summary of the Invention

[0007] 1. A method of controlling a peeling system, comprising: In real time, you can see the peeling process of the peeling system and the products being peeled by the peeling system. for monitoring at least one characteristic of the product; and To monitor the operation of the peeling process At least the first sensor to monitor using, acquiring data from at least a first sensor for a simulation to simulate, in the virtual model, the peeling process and the product flow through the peeling system, the simulation comprising: comparing at least one simulated output of the virtual model with at least one desired output of the peeling system using an optimizer for the virtual model; adjusting control parameters of the virtual model using the output of the optimizer and iteratively resimulating the peeling process and product flow until at least one simulated output from the virtual model matches at least one desired output of the peeling system within a specified tolerance. to have, to obtain, Applying the adjusted control parameters from the virtual model simulation to the peeling system in real time; Passing the product to be peeled through the peeling system; Monitor the production and peeling process and compare the results with simulations; Utilizing the identified differences between the measured output of the peeling system and the output of the virtual model to refine the virtual model for a more accurate representation of the output of the peeling system. A method is provided, comprising:

[0008] This is advantageous because data regarding the flow of product through the peeling system and / or regarding the product itself can be obtained in real time, which data can be processed or simulated and provided to a virtual model of the peeling system, allowing the operation of the peeling system to be adjusted based on that data, also in real time. This provides for optimizing the operation of a peeling system (i.e., a physical peeling system) in real time based on data derived from the system as it is in use. It will be appreciated by those skilled in the art that the "output" of the described peeling system may refer to the physical output of the peeler, such as in the case of an output peeled product. Furthermore, "output" may also refer to any product or system data output from a sensor in the system. Real time is given its ordinary interpretation with respect to processes and process control, i.e., real time is taken to mean the actual time during which a process or event takes place, and particularly as it relates to systems in which input data is processed frequently so that the input data is nearly immediately available as feedback to the process from which it was derived.

[0009] In effect, an iterative optimization loop is provided in which a simulation can be run and adjusted, and the output of the simulation can be compared to a desired result (e.g., peel quality or selected monitored system parameters) until the prediction from the simulation is deemed sufficiently close to the desired result. Once this is achieved, the resulting settings and parameters can be applied to the physical system. The virtual model of the system acts as a digital twin of the physical peeling system, providing a virtual or software environment in which the simulation of the physical system can be adjusted and analyzed, and further, in which the performance and output of the physical system can be compared to the simulation. The output of the physical system can be monitored and compared to the simulated prediction from the "twin" to improve the simulation. The simulation can then be used to improve the performance of the physical system. In this way, manual visual inspections of the production line in an attempt to verify product quality or peel quality can be minimized. Furthermore, peeling system downtime is minimized because the system does not necessarily have to be shut down to perform inspections or system adjustments. This results in an energy-efficient and cost-effective peeling system with increased peel quality accompanied by more reliability and less system downtime.

[0010] The virtual model may include an optimizer and at least one of a simulator for representing the operation of the peeling system, a simulated product flow for simulating the impact of the peeling system on the product, and a simulated product for simulating the impact of the product on the operation of the peeling system and / or the impact of the peeling system on the product.

[0011] This is advantageous because the simulator and optimizer can iteratively work together to optimize one or more outputs of the virtual model. This provides for comparing the simulated output of the virtual model with the output of the peeling system, i.e., the physical system. Thus, an opportunity is provided to compare the simulated output with the "real-world" output of the physical system. This allows for adjustment of the behavior of the peeling system based on the difference between the idealized output of the simulator and the physical output of the peeling system.

[0012] The optimizer is i) Analyzing the simulator output and its impact on the simulated product and / or the impact of the peeling system on the product; ii) comparing the simulated output of the simulator with pre-specified outputs; and iii) adjusting the control parameters to minimize the difference or error between the simulated output and the predefined output; iv) iteratively repeating steps i) to iii) to provide optimized control parameters; The optimized control parameters are determined when the difference or error between the simulated output and the predefined output is within a predetermined tolerance, the predefined output being defined by a desired product specification. Repeat The device may be further configured to:

[0013] The method may further include applying the optimized control parameters to the peeling system.

[0014] This provides an optimization of the peeling system's operation, defined by the determined optimized control parameters. Mathematically, optimization can be viewed as minimizing the delta or error between the desired and simulated outputs of the peeling system, generally through iterative minimization steps. This provides a type of model predictive control for the peeling system's operation.

[0015] The control parameter may affect the adjustment of at least one component of the peeling system; Peeling system, Input product volume control, Primary peeler, Secondary peeler, Loose skin separator, cleaning systems, and / or Product sorting system The present invention may include adjusting at least one of the following components: a) the peeling system; b) the peeling system; c) the peeling system; d) the peeling system; e) the peeling system; f) the peeling system; g) the peeling system; h) the peeling system; h) the peeling system; h) the peeling system; f) the peeling system; g) the peeling system; h ...

[0016] The control parameters are: Product flow through the peeling system, temperature at the primary peeler by application of heat or heat transfer medium; temperature in the secondary peeler by application of heat or heat transfer medium; First, aggressive peeling in the peeler. Peeling aggressiveness in the secondary peeler, Sorting control for hides, Sorting control for defects, Sorting control to direct specific volumes of production; Steam pressure in the system, the container temperature in the primary peeler and / or secondary peeler; vessel agitation in the primary peeler and / or secondary peeler; the rotation speed of the primary peeler and / or secondary peeler; Number of rotation cycles in the primary peeler and / or the secondary peeler affecting the adjustment of at least one of the

[0017] Each of the above are parameters that should be defined when aiming for a particular peel quality at the output of the peeling system, and therefore providing for adjustment of at least one of these parameters is advantageous as it will have a significant impact on the peel quality of the peelable product flowing through the peeling system.

[0018] Certain product characteristics include product peelable skin coverage and quality. Visual inspection of the product can provide information regarding product skin quality to obtain an estimate of how difficult it will be to peel. Skin quality can also be assessed by type and age or storage time, and in some cases storage conditions. This information can be provided to the peeling system by the plant operator or through the plant process control network.

[0019] Further product characteristics include product non-peelable defect coverage, product size and / or surface area and / or volume. Information about what is peelable and what is non-peelable means that the peeling system will not misadjust for skins it cannot remove, resulting in over-peeling and product loss. Note that the term "non-peelable" can refer to skins that are non-peelable by the primary peeler if they should be directed to a secondary peeler that can remove them. Furthermore, the term can also refer to non-peelable defects, which need to be discarded because they cannot be peeled by either the primary or secondary peeling device. Further product characteristics include product temperature. Skin is a surface condition; i.e., more surface means more skin. Thermal transfer involves surface contact with a heat-conducting medium (steam). Therefore, measuring heat transfer provides a direct relationship to the correct heat energy to be applied. The temperature of the product is related to the initial amount of heat energy required to cook its skin.

[0020] A further characteristic of a product is the product type. Knowing the product type can provide information about other parameters related to the peelability and performance of that type in a peeling system.

[0021] Each of the above is a significant characteristic of the peelable product itself, which will have a direct impact on the effectiveness of the peeling process applied to the peelable product. Therefore, providing at least a first sensor for monitoring at least one characteristic of the product is advantageous, as it provides that such product-related data, which is directly linked to product quality, can be provided to a virtual model of the peeling system to optimize the operation of the peeling system.

[0022] The product flow is Product flow rate, Product flow volume and / or mass, Product flow duration, pauses or dwell times; Product flow piece count The signal may have at least one of:

[0023] These are significant characteristics of the product flow through the peeling system. Again, providing at least a first sensor for monitoring at least one characteristic of the product flow is advantageous because it provides that such data can be provided to a virtual model of the peeling system to optimize the operation of the peeling system.

[0024] The output of the virtual model provides an indication of the predicted peel removal quality and / or defect removal quality of the product, which enables adjustment of the operation of the peeling system based on the difference between the simulated peel quality derived from the output of the virtual model and the observed physical output of the peeling system.

[0025] The output of the virtual model can be used to generate machine learning and / or artificial intelligence data. data from at least a first sensor for simulating a peeling process and a product flow; Peeling system history data, Data from additional systems outside the peeling system, Data from additional simulations external to the peeling system, Data from cloud storage and / or cloud computer systems may be produced by applying at least one of

[0026] Within the scope of the present invention, artificial intelligence is understood to be a technique that enables machines to simulate human behavior. Machine learning is a subset of artificial intelligence that enables machines to automatically learn from past data without being explicitly programmed. References to these terms should therefore be understood in their broadest sense and include learning techniques such as deep learning and / or neural networks. In this manner, predictions regarding the behavior of the peeling system can be performed by the virtual model. This is advantageous because the predictions can be used to define the behavior of the peeling system in several ways. For example, the virtual model can be provided with initial starting data, and based on the provided data, predicted output of the product or parameters can be provided. The peeling system parameters can be adjusted to "match" the predicted output to the physical output within specified tolerances. Furthermore, the predicted output can provide an indication of an error or fault in the peeling system, where the predicted output is observed to deviate significantly from the output from the physical system. In this manner, the predicted output can provide preventative fault management, highlighting suboptimal physical behavior of peeling system components before further degradation or failure of those components. The output of the virtual model can therefore provide fault indications or warnings. This, in turn, offers the benefit of minimizing system downtime for part repair or replacement. Furthermore, the use of historical data is advantageous because the virtual model is thus provided with information related to previous product flows through the peeling system. This data can include, for example, data about peelable products with similar characteristics to the next proposed product ready to be loaded into the peeling system. The virtual model can therefore simulate product flows through the peeling system based on historical inputs. Again, the simulation output can be analyzed to determine whether it falls within an acceptable quality range.If it falls within an acceptable quality range, the peeling system can be configured with initial operating conditions based on historical data. This is advantageous because it provides for scenarios where data derived from similar product flows through the peeling system is available, so operating conditions do not have to be determined from scratch. The use of data from additional systems external to the peeling system, data from additional simulations external to the peeling system, or data from cloud storage is also advantageous.

[0027] In a further aspect of the present invention, there is provided a method of controlling a peeling system, comprising the steps of: providing an input to the virtual model of the peeling system having at least one initial operating condition based on characteristics of the flow of peelable product through the peeling system; simulating, in the virtual model, the product flow through the peeling system based on the inputs to obtain a simulation; Analyzing the output of the simulation to obtain an analysis; adjusting at least one operating condition based on the analysis to produce an updated initial operating condition; Providing updated initial operating conditions for the peeling system A method is provided, comprising:

[0028] This is advantageous because initial operating conditions for the peeling system can be provided to a virtual model of the peeling system to provide a simulated output. This simulated output can be analyzed to see if it falls within an acceptable quality range. The operating conditions can be adjusted until the output is of sufficient desired quality. Thus, these adjusted initial operating conditions can be provided to the peeling system prior to the start of the peeling process. In this way, the peeling system can be set up or calibrated prior to use to achieve a target quality based on the output of the simulation.

[0029] In a further aspect of the present invention, there is provided a peeling system having a primary peeler for receiving a peelable product, a first sensor configured to monitor the peelable product at the primary peeler, the first sensor further configured to provide monitored information to a virtual model of the peeling system to adjust operation of the peeling system based on the monitored information. In this manner, operation of the peeling system can be adjusted based on information provided to the virtual model of the peeling system from the sensor at the primary peeler.

[0030] The peeling system may further include a secondary peeler configured to receive the partially peeled product from the primary peeler, a second sensor configured to monitor the peelable product at the secondary peeling device, and the first sensor and the second sensor configured to provide monitored information to the virtual model of the peeling system to adjust operation of the peeling system based on the monitored information. In this manner, operation of the peeling system may be adjusted based on information provided to the virtual model of the peeling system from the first sensor at the primary peeler and the second sensor at the secondary peeler.

[0031] In a further aspect of the present invention, there is provided a peeling system comprising: In real time, you can see the peeling process of the peeling system and the products being peeled by the peeling system. at least a first sensor for monitoring at least one characteristic of the product and for monitoring the operation of the peeling process; means for monitoring using, means for acquiring data from at least a first sensor to simulate the peeling process and product flow through the peeling system in a virtual model to obtain a simulation, the simulation comprising: means for comparing at least one simulated output of the virtual model with at least one desired output of the peeling system using an optimizer for the virtual model; means for adjusting control parameters of the virtual model using the output of the optimizer and iteratively resimulating the peeling process and product flow until outputs from the virtual model match at least one desired output within a specified tolerance; means for means for applying, in real time, adjusted control parameters from the virtual model simulation to the peeling system; means for passing the product to be peeled through the peeling system; A means to monitor the production and peeling process and compare the results with simulations; and utilizing the identified differences between the measured output of the peeling system and the output of the virtual model to refine the virtual model for a more accurate representation of the output of the peeling system. A peeling system is provided, comprising:

[0032] Such control systems provide that data regarding the flow of product through the peeling system and / or regarding the product itself can be obtained in real time. This data can be processed or simulated and provided to a virtual model of the peeling system, allowing the operation of the peeling system to be adjusted based on that data. [Brief explanation of the drawings]

[0033] [Figure 1] FIG. 1 is a representation of the peeling process flow performed by the peeling system. [Figure 2] FIG. 1 is a diagram of a schematic representation of a Model Predictive Control (MPC) process. [Figure 3] Schematic representation of the model predictive control (MPC) process for the control of the peeling system. [Figure 4A] FIG. 1 is a schematic representation of a peeling system. [Figure 4B] 1 is a schematic representation of a peeling system further illustrating monitoring and control aspects according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0034] Before describing the functionality of the present invention, a brief description of the general peeling process and system is provided. Figure 1 is a representation of the peeling process flow performed by the peeling system.

[0035] The steps undertaken during the peeling / sorting phase are summarized in more detail below.

[0036] A - Starting Batch Step A involves first evaluating the raw material (e.g., potatoes) for size, temperature, skin type, and defects. A batch size is selected based on an estimate of the size distribution and the system's throughput constraints, i.e., what product flow rate is achievable through a given system. The available steam pressure and steam vessel temperature are assessed. A peel time is set based on the raw material evaluation, batch size, and steam temperature information. The batch is loaded into the steam vessel and the cycle is initiated.

[0037] B-Peel Batch The steam canister acts as the primary peeler for the loaded batch. The canister rotates the potatoes in a pressurized steam environment. The pressure is assessed throughout the cycle. At the end of the set peel time, a dump cycle is performed and the canister is rotated to eject the potatoes.

[0038] C - Purification Batch The potatoes are transported to the DPS by an auger discharge. The potatoes are passed through the DPS to remove loose skin from the potatoes. A brusher removes any remaining attached skin. The product is then passed over a hex-feed to remove product debris and to spread the product evenly for sorting.

[0039] D-sort A sorter removes foreign material and defects to be discarded and sorts the remaining product into "in-specification" and "out of specification."

[0040] E-Re-Peel Batch The secondary peeler peels all the products it receives from the sorter. The peeled output from the secondary peeler is re-sorted through the paths in the sorter. The under-peeled output from the secondary peeler is again sorted to be re-peeled.

[0041] F-Exit An "in-spec" product is output and a final inspection and scoring of the output product is undertaken to ensure that it is of the required quality.

[0042] Controlling such systems presents several challenges. In existing peeling systems, the sorter and steam canister may be controlled by a powertrain control module (PCM) system. Such systems offer limited control and visibility of system parameters and product characteristics that determine peel quality. For example, whether a product is determined to be in-spec or out-of-spec may not be known until the quality control stage following peeling / sorting. The peeling / sorting stage, in turn, is not capable of accommodating the full range of input product quality without significant adjustments. Also, sorter control may not be dependent on peeling control. Furthermore, peel efficiency depends on steam quality in the steam canister, but steam quality may remain unmonitored and ultimately unknown throughout the process. Furthermore, incoming product specification, product batch size, and steam canister temperature have interdependencies that affect peel quality. However, this dependency is not assessed by current control systems. The method of the present invention attempts to address these shortcomings.

[0043] Figure 2 is a schematic representation of a system, e.g., a peeling system, implemented with a control method in accordance with the present invention. The method utilizes a form of model predictive control (MPC). MPC is a method used to control a system or process while satisfying a set of constraints. A model predictive controller relies on a dynamic or virtual model of the process under control. Data obtained from operating the process is provided to the model, which is used to generate simulated outputs. The simulated outputs can be compared to actual outputs to adjust control parameters for the system.

[0044] With respect to FIG. 2, the process 20 depicted therein can be considered to be the peeling / sorting process described with respect to FIG. 1 and FIGS. 4A and 4B, which are further described below.

[0045] The method of the present invention provides for monitoring, in real time, the peeling and / or sorting process of the system and the products being peeled and sorted by the system using at least a first sensor 21 for monitoring at least one characteristic of the products and for monitoring the operation of the process.

[0046] Several sensors may be placed at different points throughout the system to collect relevant process state data regarding the operation of the peeling / sorting equipment and the product flowing through it (see, for example, FIG. 4B). This sensed data is provided to a virtual model 22 of the peeling system. The virtual model 22 is shown as having an optimizer 23 and a simulator 24 or simulation model. The simulator 24 functions to represent the operation of the peeling and sorting system. Additionally, a simulated product is provided (but not shown) to simulate the product's impact on the operation of the peeling system and the system's impact on the product. Additionally, a simulated product flow (not shown) is provided to simulate the impact of the peeling system on the product. Product flow describes the movement of product through the peeling system. Product flow is defined by several factors, including, but not limited to, product flow rate, product flow volume and / or mass, product flow duration, pause or residence time, and product flow count.

[0047] Data obtained from at least a first sensor is utilized to simulate, in a virtual model, the peeling process and product flow through the peeling system. The simulation includes comparing at least one simulated output of the virtual model 22 with at least one desired output of the peeling system using an optimizer 23. Control parameters of the virtual model are adjusted using the optimizer's output. The peeling process and product flow are then iteratively resimulated until outputs from the virtual model match at least one desired output within a specified tolerance.

[0048] The adjusted control parameters from the simulation of the virtual model are applied to the peeling system in real time. A product flow of the product to be peeled is then passed through the peeling system. The product and peeling process are monitored, and the results are compared to the simulation. Identified differences between the measured output of the peeling system and the output of the virtual model 22 are used to refine the virtual model for a more accurate representation of the peeling system's output. The measured output of the peeling system can be the physical output of the peeler, as in the case of peeled product. Additionally, the measured output can be a product or data output from the system or sensors in the system.

[0049] The optimizer 23 may further be provided with external inputs from an operator or external control 25. The external inputs may include, for example, output specifications, specific heat values, and dry solids content. FIG. 3 shows how an information loop is created to provide process data from the physical equipment (i.e., detected from sensors distributed throughout the system) to the simulator 24. A further loop is created by providing updated simulation predictions from the simulator 24 to the optimizer 23. This allows the optimizer 23 to provide updated control actions to the simulator 24, which ultimately become updated control parameters for the physical equipment.

[0050] The optimizer is configured to: i) analyze the output of the simulator and its effect on the simulated product; ii) compare the simulated output of the simulator with predefined outputs; and iii) adjust the control parameters to minimize the difference or error between the simulated output and the predefined outputs.

[0051] Further, the optimizer is configured to iteratively repeat steps i)-iii) to provide optimized control parameters. The optimized control parameters are determined when a difference or error between the simulated output and the predefined output is within a predetermined tolerance. The predefined output is defined by a desired product specification. For example, the predefined output can be peel quality for a given peelable product. The predefined output can also be a data output of any aspect of the peeling system. The optimized control parameters can then be applied to the peeling system.

[0052] Further, adjusting the control parameters 24 can include minimizing the error between the simulator output and the target output of the peeling system. The output can be selected parameters or thresholds defined for any of the process portions described above as A-F. The output of the virtual model is produced by applying machine learning and / or artificial intelligence to at least one of the data from sensors in the peeling system to simulate the peeling process and product flow. The output of the virtual model can also be produced by applying machine learning and / or artificial intelligence to historical data from the peeling system, data from additional systems external to the peeling system (e.g., additional peeling systems in different production environments), data from additional simulations external to the peeling system, and data from cloud storage. Furthermore, the output of the virtual model is configured to provide an overall indication of peel quality for a given peelable product. 22 This virtual peel quality can be compared to the output from the physical system. For example, the physical output at sorter 13 can be examined for overall peel quality and to see if the output product is within or outside of specifications. Additionally, the physical output can be compared to the predicted simulated output, i.e., virtual peel quality, from virtual model 22. In this manner, the accuracy of the predicated simulated output can be confirmed. Simulator 24 can be adjusted, for example, by manual input, to adjust the simulated output based on the observed physical output.

[0053] It should be noted that providing the circulation of information as described provides for iterative adjustment of the operation of the peeling system.

[0054] Figure 3 is a schematic representation of a control method for controlling a peeling system. Figure 3 indicates how the control method described with respect to Figure 3 can be applied throughout the peeling / sorting process described in Figures 1 and 2. In effect, the individual controls and control parameters described can be applied to several steps A through F of the peeling / sorting process: batch size control is applied to step A—the starting batch; steam time control is applied to step B—the peel batch; sorter and ejection control is applied to step D—the sort batch; and re-peel control is applied to step E—the re-peel batch. This effectively provides a series of distributed MPC controls distributed throughout the process, with a master MPC providing overall control and oversight. User input can also be applied to the master control as needed. Additionally, overall production line control or plant supervision can be linked to the master control. In this manner, centralized control and monitoring of the entire production line can be provided.

[0055] Applying batch size control in step A provides enhanced monitoring and iterative control of several process aspects undertaken in step A. For example, additional monitoring and evaluation may be provided by sensors configured to assess raw material size, temperature, peel type, and defects. Additional monitoring and evaluation may be provided by sensors configured to assess available steam pressure and temperature and measure vessel temperature. Furthermore, applying batch size control may enable dynamic adjustments to the process based on data from the process, model simulations, and required product specifications. Primary peeler adjustments may be undertaken. Further, batch size and volume adjustments may be provided. Adjustments to peel time for a batch may also be provided.

[0056] Applying steam time control in step B provides enhanced monitoring and iterative control of several process aspects undertaken in step B. For example, additional monitoring and evaluation can be provided by sensors configured to open the steam inlet of the steam vessel, pressurize the vessel, and measure the steam pressurization cycle. Further data can be obtained from sensors configured to release the steam pressure and measure the steam release profile while venting the steam.

[0057] Applying sorter and discharge control in step D provides enhanced monitoring and iterative control of some process aspects undertaken in step D. For example, additional monitoring and evaluation may be provided by sensors configured to obtain data regarding defects identified from images taken of the output of steps A-D, obtain data regarding how much product is sent to the secondary peeler, and send data regarding size and defects regarding product sent to the re-peel stage. Furthermore, applying sorter and discharge control may make it possible to provide dynamic adjustments to the process. For example, adjustments may be provided to sorter operation with respect to which products are sorted as in-spec and which products are sorted as out-spec and discarded. Adjustments may also be provided to brusher operation.

[0058] Applying re-peel control in step E provides enhanced monitoring and iterative control of some process aspects undertaken in step E. For example, additional monitoring and evaluation may be provided by sensors configured to obtain data regarding the effectiveness of the re-peel. Furthermore, applying re-peel control may enable dynamic adjustments to the process based on data from the process, model simulations, and required product specifications. For example, adjustments to secondary peeler operation may be provided.

[0059] It should be noted that in addition to the described adjustments, additional adjustments to the system can be made to optimize the operation of the peeling system. Several aspects of the peeling system and process can ultimately be controlled and optimized by adjusting control parameters. Adjusting the control parameters affects adjustments to at least one of the following components of the peeling system: input product volume control, primary peeler, secondary peeler, loose skin separator, washing system, and product sorting system.

[0060] Additionally, it should be noted that sensors may be deployed at multiple locations throughout the peeling system to obtain data for process optimization. The sensors may be configured to obtain data related to the product itself, such as data indicative of product defect rate, product temperature, product surface area, or product skin depth. Additionally, the sensors may be configured to obtain data related to product flow, such as data indicative of product flow rate, product flow duration, product volume, or system throughput through the system. Additionally, the control parameters affect product flow through the peeling system, temperature in the primary peeler due to application of heat or heat transfer medium, temperature in the secondary peeler due to application of heat or heat transfer medium, peeling aggressiveness in the primary peeler, peeling aggressiveness in the secondary peeler, sort control for peel, sort control for defects, sort control to direct a specific volume of product, where directing may mean redirection of product through the system or ejection from the product flow, steam pressure in the system, vessel temperature in the primary peeler and / or secondary peeler, vessel agitation in the primary peeler and / or secondary peeler, rotation speed of the primary peeler and / or secondary peeler, and adjustment of the number of rotation cycles in the primary peeler and / or secondary peeler.

[0061] It should be noted that aspects of the described method may also be applied prior to initiating the peeling process so that initial conditions for the peeling process for a given peelable product are optimized. Thus, an operator or external control may provide an input having at least one initial operating condition to a virtual model of the peeling system. The initial operating condition may be the operating parameters of a component of the peeling system, such as the primary peeler, secondary peeler, or sorter. A combination optimizer and simulator may then simulate the product flow through the peeling system based on the input and then analyze the output of the simulation. The output may be, for example, an indication of overall peel quality. If the peel quality is not within specification, the initial operating conditions may be adjusted and updated based on the analysis to provide an optimized simulated output that is within specification. This updated initial operating condition may then be provided as an input to the physical peeling system, so that the system is set up or calibrated to provide the desired specified output based on the simulation. As the process progresses in the peeling system, it can be adjusted in real time as previously described, for example, if feedback indicates that the output is deviating outside of specifications.

[0062] Input to the peeling system can also take the form of historical data of product flow through the peeling system. This historical data can be used to prepare the peeling system to operate in a manner based on product flows that have already been initiated. For example, if the product parameters of a historical product flow appear to be similar to the parameters of a new product to be loaded into the system, the system parameters can be initialized for the new product based on the parameters used for the historical flows for similar products.

[0063] Figure 4A is a schematic representation of a peeling system. The representation provides an overview of a type of peeling system suitable for control by the method of the present invention. This peeling system will be briefly described before an embodiment of the present invention providing enhanced monitoring and control is described with reference to Figure 4B.

[0064] During the peeling process, the products go through several preparatory steps that transform them from raw products into final packaged products suitable for sale and consumption. Broadly, these steps are: receiving raw products -> washing / sizing / and blending -> Peeling / Sorting The representation in Figure 4A shows the process of peelable product. Peeling / SortingThe equipment utilized for this step is shown. The operation of the peeling and sorting process is briefly described. Some issues regarding existing control methods for such systems are also discussed. While the peeling and sorting process undertaken by the peeling system is described with reference to potatoes, it should be noted that the process and system can be used to peel and sort other types of peelable produce and peelable food products. Therefore, the described method and system should not be construed as being directed solely to potatoes. Different types of peelable produce can be peeled by the peeling system. Produce has several characteristics, including, but not limited to, product peelable skin area, product peelable skin quality, product non-peelable defect area, product size and / or surface area and / or volume, product temperature, and product variety or type. These characteristics are used to define the product type that undergoes peeling by the system. Furthermore, peelable produce is understood to mean any product, particularly a food product, that can be peeled to remove the outer layer of the product. Peelable produce is intended to include unpeeled, partially peeled, or fully peeled produce. Furthermore, "produce" can mean one or more of a given item, but more generally, a plurality of produce items, e.g., thousands of potatoes or other peelable foodstuffs.

[0065] Infeed Control This part of the process utilizes a metering conveyor or product transfer mechanism and load cells. Washed, unpeeled potatoes are fed from the conveyor into a batch hopper. A volume measurement system may also be employed to measure the depth of fill to estimate the product volume to be processed.

[0066] Primary Peeler - Active Peel Separation From the batch hopper, the potatoes reach the steam vessel, which acts as the primary peeler 11 of the system. High-pressure steam is fed into the steam vessel, which, combined with a high-speed decompression, provides active peel separation. Once the peeling cycle is complete, the steam is removed from the vessel by a steam exhaust.

[0067] Removal of loose and attached skins and starch An auger discharge transports the potatoes from the steamer to a Dry Peel Separator (DPS). The peel separator and brusher / washer device remove loose and partially attached skins from the product prior to inspection.

[0068] Sorting and secondary peeler The potatoes are fed into a sorter 13 device via a hex-roller, which ensures even distribution and removes debris. The device is configured to sort the potatoes into i) potatoes that have been peeled within the required specification or peel quality ("in-spec"), ii) potatoes that have been peeled below the required specification or peel quality or contain defects that can be removed by a secondary peeler ("out-of-spec"), and iii) defective potatoes and detected foreign material. The defective potatoes and foreign material are discarded, and the potatoes that have been peeled within specification are directed out of the sorter 13, while the potatoes that have been peeled below the required specification are directed to the secondary peeler 12, where any remaining skin and surface defects can be removed. The re-peeled potatoes are then redirected back to sorter 13 where they may again be sorted as in i), ii) or iii) above. In some applications, this re-peeled product may be combined directly with in-order product without re-inspection and sorting.

[0069] Figure 4B illustrates several enhancements that provide greater control and monitoring than the system shown in Figure 4A. Referring to Figure 4B, a method of controlling a peeling system of the present invention provides for monitoring, in real time, the peeling process of the peeling system and the product being peeled by the peeling system using at least a first sensor for monitoring at least one characteristic of the product and for monitoring the operation of the process.

[0070] With reference to FIG. 4B, it should be noted that at least one sensor may be positioned at one of several different points throughout the peeling system, thus providing the ability to monitor product characteristics and / or the operation of different equipment components forming the peeling system. For example, a sensor may be deployed to monitor aspects of washed, unpeeled potatoes. For example, a sensor may be deployed and configured to monitor incoming product input specifications. These may be used to define a “raw product score” or initial product classification. Furthermore, the incoming product input specifications may be used to define feedforward control parameters. One or more sensors may be positioned around the measuring conveyor, which may provide information regarding product weight / mass, product level or volume, and product temperature. One or more sensors may be positioned around the steam vessel, which may provide information regarding steam pressure, valve operation, and vessel temperature. Again, this information may be used to determine and / or adjust control parameters. Additionally, one or more sensors may monitor the weight / mass of the product at the auger discharge and the product volume. One or more sensors may also be deployed at an inspection point after the peel separator. One or more sensors may be placed around the sorter and secondary peeler. These sensors provide data from the sorter regarding the product, including peelable and non-peelable defects. Additionally, information regarding primary and secondary peeler performance may be obtained. This allows parameters such as sort settings for sorter program control to be defined and adjusted. A sensor in the secondary peeler provides more intelligent monitoring of secondary peeler performance. This provides for re-peel load management as well as product direction control.

[0071] It should be noted that the described sensor locations are only one indication of possible sensor locations. One or more sensors may be placed throughout the system to allow different types of information to be obtained depending on what type of system performance is to be monitored. Furthermore, it should be noted that a single sensor may be capable of monitoring more than a single system aspect and may be capable of obtaining more than one data type.

[0072] It is noted that acquiring data from the sensors provides a simulation for simulating the peeling process and product flow through the peeling system in a virtual model. The acquired sensor data can be utilized by the model predictive control process described with respect to Figure 2 to refine the virtual model for a more accurate representation of the peeling system output. Additionally, process 20 highlighted in Figure 2 can be implemented by the system outlined in Figure 4B.

[0073] In addition to the described methods of control, a further embodiment provides a peeling system having a primary peeler for receiving a peelable product, a first sensor configured to monitor the peelable product at the primary peeler, the first sensor further configured to provide the monitored information to a virtual model as described to adjust operation of the peeling system based on the monitored information.

[0074] The secondary peeler may also be configured to receive partially peeled product from the primary peeler. As described, partially peeled product may also be provided to the secondary peeler from the sorter. A second sensor may be configured to monitor the peelable product at the secondary peeling device. The first and second sensors may be configured to provide the monitored information to a virtual model of the peeling system to adjust operation of the peeling system based on the monitored information. Furthermore, a third sensor may be configured to monitor the peelable product at the sorter, and the first, second, and third sensors may be configured to provide the monitored information to a virtual model of the peeling system to adjust operation of the peeling system based on the monitored information.

[0075] The described methods can be controlled by a computer system, and further, the methods can be implemented in software or any computer program product having instructions that, when executed by a computer, cause the computer to perform the described control methods. The described methods can be performed by a control system integrated with a physical peeling system having a combination of mechanical, electrical, electronic, and software means configured to perform the methods. The control system for the peeling system has means for monitoring, in real time, the peeling process of the peeling system and the product being peeled by the peeling system using at least a first sensor for monitoring at least one characteristic of the product and for monitoring the operation of the process.

[0076] The control system includes means for acquiring data from at least a first sensor to simulate, in a virtual model, the peeling process and the product flow through the peeling system, the simulation including: means for comparing at least one simulated output of the virtual model with at least one desired output of the peeling system using an optimizer for the virtual model; means for adjusting control parameters of the virtual model using the output of the optimizer and iteratively resimulating the peeling process and product flow until outputs from the virtual model match at least one desired output within a specified tolerance; The method further comprises the steps of:

[0077] The control system includes means for applying, in real time, adjusted control parameters from the simulation of the virtual model to the peeling system, and means for passing the product to be peeled through the peeling system; Means for monitoring the production and peeling process and comparing the results to a simulation, and means for utilizing identified differences between the measured output of the peeling system and the output of the virtual model to refine the virtual model for a more accurate representation of the output of the peeling system. It further has:

[0078] It was described how existing control methods for peeling systems provide limited control over the system and the peeling process undertaken by the system. Furthermore, there is insufficient visibility into whether the process is operating sufficiently within the range of operating parameters to produce an output product that meets desired specifications. The described method provides increased system uptime and increased peeling effectiveness, which maximizes product yield and reduces waste.

[0079] As used herein in relation to the present invention, the words "comprises / comprising" and "having / including" are used to specify the presence of stated features, integers, steps or components, but do not exclude the presence or addition of one or more other features, integers, steps, components or groups thereof.

[0080] It will be appreciated that certain features of the invention that are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention that are, for clarity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination.

Claims

1. A method for controlling a peeling system, A step of monitoring the peeling process of the peeling system and the product being peeled by the peeling system in real time, the step of monitoring using at least a first sensor for monitoring at least one characteristic of the product and for monitoring the operation of the process, A step of acquiring data from at least the first sensor for simulation, wherein the simulation is for simulating the peeling process and the product flow through the peeling system in a virtual model, and the simulation is Using the optimizer of the virtual model, compare at least one simulated output of the virtual model with at least one desired output of the peeling system, and The output of the optimizer is used to adjust the control parameters of the virtual model, and the peeling process and product flow are iteratively resimulated until the at least one simulated output from the virtual model matches the at least one desired output of the peeling system within a specified tolerance. Steps including, The steps include applying the adjusted control parameters from the simulation of the virtual model to the peeling system in real time, The steps include passing the product to be peeled through the peeling system, A step of monitoring the product and the peeling process and comparing the results with the simulation, A step of utilizing the identified difference between the measured output of the peeling system and the output of the virtual model, thereby improving the virtual model for a more accurate representation of the output of the peeling system. A method having.

2. The aforementioned virtual model, The aforementioned optimizer, A simulator for representing the operation of the aforementioned peeling system, A simulated product flow for simulating the effect of the peeling system on the aforementioned products, A simulated product for simulating the effect of the peeling system on the operation of the product and / or the effect of the peeling system on the product. at least one of the following and The method according to claim 1, comprising:

3. The aforementioned optimizer, i) A step of analyzing the output of the simulator and its impact on the simulated product and / or product flow, ii) A step of comparing the simulated output of the simulator with a predefined output, iii) The step of adjusting the control parameters to minimize the difference or error between the simulated output and the predefined output, iv) A step of iteratively repeating steps i) to iii) in order to provide optimized control parameters, The optimized control parameters are determined when the difference or error between the simulated output and the predefined output is within a predetermined tolerance, and the predefined output is defined by the desired product specifications. Steps and The method according to claim 2, further configured to perform

4. The method according to claim 3, further comprising the step of applying the optimized control parameters to the peeling system.

5. The control parameters of the peeling system Input production volume control, Primary peeler, Secondary peeler, Loose skin separator, Cleaning system, and / or Product sorting system The method according to claim 1, which affects at least one of the adjustments.

6. The aforementioned control parameter is The product flow passing through the aforementioned peeling system, The temperature in the primary peeler due to the application of heat or a heat transfer medium, The temperature in the secondary peeler due to the application of heat or a heat transfer medium, The peeling aggressiveness in the first peeler, The peeling aggressiveness in the aforementioned secondary peeler, Sorting control for the skin, Sorting control for defects, Sorting control to direct production of a specific volume, Steam pressure in the aforementioned system, The container temperature in the primary peeler and / or the secondary peeler, The container stirring in the primary peeler and / or the secondary peeler, The rotation speed of the primary peeler and / or the secondary peeler, Number of rotation cycles in the primary peeler and / or the secondary peeler The method according to claim 5, which affects at least one of the adjustments.

7. The production flow is Product flow speed, Product flow volume and / or mass, Product flow duration, pause, or dwell time, Production flow quantity The method according to claim 1, comprising at least one of the following.

8. The characteristics of the aforementioned product are, Product peelable epidermal area, Product peelable epidermal quality, Scope of non-peeling defects in manufactured products, Product size and / or surface area and / or volume, Product temperature, Product type or type The method according to claim 1, comprising at least one of the following.

9. The method according to claim 1, wherein the output of the virtual model provides an indication of the predicted deskinning quality and / or defect removal quality of the product.

10. The output of the virtual model is machine learning and / or artificial intelligence. Data from at least the first sensor for simulating the peeling process and the product flow, Historical data of the aforementioned peeling system, Data from at least one additional system outside the peeling system, Data from additional simulations outside the aforementioned peeling system, Data from cloud storage and / or cloud computing systems The method according to claim 1, produced by applying it to at least one of the following.

11. A control system for a peeling system, Means for monitoring the peeling process of the peeling system and the product being peeled by the peeling system in real time, the means for monitoring using at least one characteristic of the product and at least one first sensor for monitoring the operation of the process, Means for acquiring data from at least the first sensor for simulation, wherein the simulation is for simulating the peeling process and the product flow through the peeling system in a virtual model, and the simulation is Means for comparing at least one simulated output of the virtual model with at least one desired output of the peeling system using the optimizer of the virtual model, and Means for iteratively resimulating the peeling process and the product flow by adjusting the control parameters of the virtual model using the output of the optimizer until the output from the virtual model matches the at least one desired output within a defined tolerance. Having means, Means for applying the adjusted control parameters from the simulation of the virtual model to the peeling system in real time, Means for passing the product to be peeled through the peeling system, Means for monitoring the product and the peeling process and comparing the results with the simulation, Means for utilizing the identified difference between the measured output of the peeling system and the output of the virtual model, thereby improving the virtual model for a more accurate representation of the output of the peeling system; A control system having

12. The system according to claim 11, further configured to perform the method described in any one of claims 2 to 10.

Images