Methods for characterizing and repurposing drug product fill formulations

Abstract

A method for characterizing and / or matching a product fill recipe includes generating first and / or second flow data over a plurality of first and / or second fill cases corresponding to a first and / or second product fill recipe, generating a plurality of first and / or second fill case curves, generating a first and / or second flow profile based on the plurality of first and / or second fill case curves, and causing a display to present the first and / or second flow profile. Another method includes determining an adjustment to a parameter of the second product fill recipe based on the first and second flow profiles, and modifying the parameter of the second product fill recipe according to the adjustment. The system includes one or more flow sensors, one or more processors, and one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform any of the methods.

Description

[Technical field]

[0001] This application relates generally to characterizing and / or matching product fill recipes for use in pharmaceutical product filling systems. [Background technology]

[0002] Product filling systems may be used to fill containers with solid, liquid, and / or gaseous products. Product filling systems may be manual (e.g., operated by a hand lever used to pump the product through a tip), semi-automatic (e.g., operated by a pump controlled by an operator), or automatic (e.g., operated by a pump controlled by a computer system). Product filling systems may also be used across a variety of fields and industries, including, for example, life science / engineering, chemical science / engineering, medical science / engineering, mechanical science / engineering, food science / engineering, beverage science / engineering, and manufacturing and assembly corresponding to the above fields and industries.

[0003] Product fill systems are often used in drug discovery, pharmaceutical testing and clinical trials, and pharmaceutical manufacturing. A drug fluid fill system is a type of product fill system. Drug fluid fill systems often increase the speed and accuracy with which drug fluid suspensions can be made and are used by many pharmaceutical companies of various operation sizes. These drug fluid fill systems come in many formats, including small benchtop to large scale machines. Considerations for selecting a drug fluid fill system include the type of liquid, handling considerations, required throughput, and the manufacturing and maintenance budget of the operation.

[0004] In pharmaceutical applications, there are often more than one product fill system in use, each corresponding to one or more fill recipes. Multiple product fill systems may be used, with one smaller product fill system being used during drug discovery and another larger product fill system being used during drug manufacturing. In another example, multiple product fill systems may be used during drug manufacturing, for example to increase overall manufacturing throughput. However, it may be undesirable or even impossible to use multiple product fill systems if their operation produces different fill results. Thus, transferability between fill recipes may be crucial for pharmaceutical applications of multiple product fill systems. Transferability may be achieved, for example, between multiple product fill systems, if they produce the same results when filling containers with product. The results may be considered the same, for example, if the containers all have equal volumes or masses of product within a threshold value. The results may be considered the same, for example, if the containers all have product in the same condition (e.g., undamaged, bubble-free, etc.).

[0005] Parameters included in the fill recipe may relate to pump start, start ramp, stop ramp, end of pump, drip retraction, and main drive speed. Other factors that affect the fill recipe include the hardware components used in the product fill system including, for example, pumps, tubing, containers, conveyor systems, tips, etc.

[0006] Traditionally, to try to improve transferability, formulation operators may purchase multiple identical product fill systems from a common vendor. Nevertheless, there may be differences in fill results between multiple identical product fill systems from a common vendor. In some cases, non-transferability between fill formulas may prevent drug fill operations from working together. In other cases, non-transferability between specific instances of product fill systems may require the use of fewer product fill systems than desired. In other cases, formulation operators may attempt to standardize instances of product fill systems, but traditionally, there has been no efficient and effective method to achieve transferability. Traditional methods of standardizing product fill systems to achieve transferable fill formulas may have long lead times, high costs, and rely on operator experience (and thus may be inconsistently applied), and may still not achieve the desired transferability. Summary of the Invention [Means for solving the problem]

[0007] One aspect of the present disclosure provides a method for characterizing and / or matching a product fill recipe, the method including: (a) generating, by one or more flow sensors, first flow data across a plurality of first fill cases corresponding to a first product fill recipe; (b) generating, by one or more processors, a plurality of first fill case curves, each of the first fill case curves being a segment of the first flow data corresponding to a different first fill case of the plurality of first fill cases; (c) generating, by the one or more processors, a first flow profile based on the plurality of first fill case curves; and (d) causing, by the one or more processors, a display to present the first flow profile.

[0008] In some embodiments, the above aspect further includes: (a) generating, by the one or more flow sensors above or one or more other flow sensors, second flow data across a plurality of second fill cases corresponding to the second product fill formulation; (b) generating, by the one or more processors, a plurality of second fill case curves, each of the second fill case curves being a segment of the second flow data corresponding to a different second fill case of the plurality of second fill cases; (c) generating, by the one or more processors, a second flow profile based on the plurality of second fill case curves; and (d) causing, by the one or more processors, a display to present the second flow profile.

[0009] In some embodiments, the above aspect further includes determining an adjustment to one or more parameters of the second product fill recipe based on the first flow profile and the second flow profile.

[0010] In some embodiments, the above aspect further includes altering one or more parameters of the second product fill recipe according to the adjustment.

[0011] Another aspect of the present disclosure provides a system, the system including: (a) one or more flow sensors; (b) one or more processors; and (c) one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform a method of any one of the preceding aspects.

[0012] Those skilled in the art will appreciate that the drawings described herein are included for illustrative purposes and are not intended to limit the disclosure. The drawings are not necessarily to scale, with emphasis instead being placed on illustrating the principles of the disclosure. It should be understood that in some instances, various aspects of the described implementations may be shown exaggerated or enlarged to facilitate understanding of the described implementations. In the drawings, similar key characters throughout the various views generally refer to functionally similar and / or structurally similar components. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a simplified block diagram of an example of a system for characterizing and / or matching a product fill recipe. [Diagram 2] 1 illustrates an example product filling system. [Diagram 3] 1 shows example flow data over a single filling instance. [Figure 4] 4 is a flow diagram 400 illustrating example data used in generating a flow profile from flow rate data over multiple filling instances. [Diagram 5] 1 is a flow diagram illustrating an example method for simultaneously displaying two fill profiles corresponding to two product fill systems. [Figure 6A] 1 is a flow diagram illustrating an example method for displaying a first flow profile. [Figure 6B] 11 is a flow diagram illustrating an example method for displaying a second flow profile. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The present disclosure aims to reduce problems (e.g., as described in the Background section) associated with conventional approaches by providing an improved method for characterizing and / or matching product fill recipes. The method includes (i) generating first flow data across a plurality of first fill cases corresponding to a first product fill recipe, (ii) generating a plurality of first fill case curves, (iii) generating a first flow profile based on the plurality of first fill case curves, and (iv) causing a display to present the first flow profile. Through generating and displaying a first flow profile associated with the first product fill recipe, the method aims to characterize the first product fill recipe such that transferability can be assessed and achieved, while avoiding many of the drawbacks associated with non-transferability between multiple fill recipes.

[0015] Moreover, in some embodiments, the disclosed methods can be partially or fully automated, thereby improving labor efficiency as well as eliminating inconsistencies due to reliance on operator technique.

[0016] The various concepts introduced above and discussed in more detail below may be implemented in any of numerous ways, and the concepts described are not limited to any particular manner of implementation. Example implementations are provided for illustrative purposes.

[0017] FIG. 1 is a simplified block diagram of an example system 100 for characterizing and / or matching a product fill recipe corresponding to a product fill system. In some embodiments, the product fill systems 102A and 102B can be independent equipment, while in other examples, the product fill systems 102A and 102B can be integrated into other equipment. The product fill systems 102A and 102B can be physical devices configured to be used for product fill. More specific examples of processes in which the product fill systems 102A and 102B can be used include drug fill, chemical fill, biological material fill, etc. In other embodiments, the system 100 is equipment used in processes unrelated to the development or production of pharmaceutical formulations (e.g., food or beverage manufacturing plants, oil processing plants, etc.). More detailed examples and descriptions of product fill systems are provided in FIG. 2 and the corresponding description of FIG. 2. In some embodiments, the product fill systems 102A and 102B are of the same type and / or are produced or provided by the same vendor. In other embodiments, product filling systems 102A and 102B are of different types and / or produced or provided by different vendors.

[0018] The system 100 also includes one or more flow sensors 104 configured to measure flow rates associated with the product fill systems 102A and 102B. For example, the flow sensors 104 may measure the flow of product in the product fill systems 102A and 102B in milliliters per second during operation. The flow sensors 104 may be ultrasonic flow sensors that measure flow rates by transmitting and receiving ultrasonic bursts. The flow sensors 104 may be another type of sensor that directly measures flow rates. Alternatively, the flow sensors 104 may measure flow rates indirectly (e.g., measuring the volume of product in a filled container). The flow sensors 104 may include one or more devices integrated on or within the product fill systems 102A and 102B and / or one or more devices attached to or located in proximity to the product fill systems 102A and 102B. Depending on the embodiment, the flow sensors 104 may not be viewed as part of the product fill systems 102A and 102B, or some or all of the flow sensors 104 may be viewed as part of the product fill systems 102A and 102B. Specifically, in embodiments in which the performance of any or all of the flow sensors 104 are included in an equipment performance analysis (as described further below), references herein to "product fill systems 102A and 102B" include those flow sensors 104. For example, a performance analysis of the product fill characterization and / or alignment may also include analyzing the performance of the flow sensors 104.

[0019] The system 100 also includes a computing system 110 coupled to the flow sensor 104. As discussed in more detail below, the computing system 110 may include a single computing device or multiple computing devices (e.g., one or more servers and one or more client devices) that are co-located or remote from each other. The computing system 110 is generally configured to: (a) generate, with the one or more flow sensors 104, flow data over multiple filling cases corresponding to a product filling recipe; (b) generate multiple filling case curves, each filling case curve being a segment of flow data corresponding to a different filling case of the multiple filling cases; (c) generate a flow profile based on the multiple filling case curves; and (d) cause a display to present the flow profile. In the exemplary embodiment shown in FIG. 1, the computing system 110 includes a processing unit 120, a network interface 122, a display 124, a user input device 126, and a memory 128.

[0020] Processing unit 120 includes one or more processors, each of which may be a programmable microprocessor that executes software instructions stored in memory 128 to perform some or all of the functions of computing system 110 described herein. Alternatively, one or more of the processors in processing unit 120 may be other types of processors (e.g., application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), etc.).

[0021] Network interface 122 may include any suitable hardware (e.g., front-end transmitter and receiver hardware), firmware, and / or software configured to communicate with external devices and / or systems (e.g., sensor device 104, or a server, not shown in FIG. 1 , that provides an interface between computing system 110 and sensor device 104, etc.) using one or more communication protocols. For example, network interface 122 may be or include an Ethernet interface. Although not shown in FIG. 1 , computing system 110 may communicate with flow sensor 104 and / or any device that provides an interface between computing system 110 and flow sensor 104 over a single communication network or over one or more types of multiple communication networks (e.g., one or more wired and / or wireless local area networks (LANs) and / or one or more wired and / or wireless wide area networks (WANs), such as the Internet or an intranet).

[0022] The display 124 may use any suitable display technology (e.g., LED, OLED, LCD, etc.) to present information to a user, and the user input device 126 may be a keyboard or other suitable input device. In some embodiments, the display 124 and the user input device 126 are integrated into a single device (e.g., a touch screen display). In general, the display 124 and the user input device 126 may be combined to allow a user to interact with a graphical user interface (GUI) or other (e.g., text) user interface provided by the computing system 110 for purposes of, for example, displaying one or more flow profiles, displaying parameters, recommending changes to one or more parameters, notifying the user of equipment malfunctions or other deficiencies, etc.

[0023] The memory 128 may include one or more physical memory devices or units, including volatile and / or non-volatile memory, and may include memory located in various computing devices of the computing system 110. Any suitable type or types of memory may be used, such as a read-only memory (ROM), a solid-state drive (SSD), a hard disk drive (HDD), etc. The memory 128 stores instructions for one or more software applications, including a product filling prescription characterization / matching application 130. The product filling prescription characterization / matching application 130 includes a data collection unit 140, a filling case segmentation unit 142, a flow profile generation unit 144, a flow profile presentation unit 146, a parameter adjustment unit 148, and a data smoothing unit 150. The units 140-150 may be separate software components or modules of the product filling prescription characterization / matching application 130, or may simply represent functions of the product filling prescription characterization / matching application 130 that are not necessarily divided among different components / modules. For example, in some embodiments, the filling instance segmentation unit 142 and the data smoothing unit 150 are included in a single software module. Moreover, in some embodiments, the different units 140-150 may be distributed among multiple copies of the product filling recipe characterization / matching application 130 (e.g., running on different devices in the computing system 110) or among different types of applications stored and executed on one or more devices of the computing system 110. The operation of each of the units 140-150 is described in further detail below with reference to the operation of the system 100.

[0024] Figure 2 illustrates an example product filling system 200. The system 200 illustrated in Figure 2 may be a stand-alone machine, such as a VarioSys® filling machine, although in other examples, the system 200 may be integrated into other machines. The system 200 may be used to fill containers with products that may include liquids, solids, gases, or plasmas (e.g., drug products).

[0025] In this example, the system 200 includes a flow sensor 202 for measuring the flow rate of the product, a pump 204 for pumping the product, a tube 206 for flowing the product, a container 208 for receiving the product, a conveyor system 210 for moving the container 208, and a tip 212 where the product exits the tube 206.

[0026] The flow sensor may measure the amount of product flowing through the tube 206 during a given time interval. For example, the flow sensor 202 may measure the product flowing through the tube 206 in milliliters per second. The flow sensor 202 may be an ultrasonic flow sensor that measures the flow rate by transmitting and receiving ultrasonic bursts. Alternatively, the flow sensor 202 may be a mechanical flow sensor. The flow sensor 202 may be another type of sensor that directly measures the flow rate. Alternatively, the flow sensor 202 may measure the flow rate indirectly (e.g., measuring the volume of product in a filled container). The flow sensor 202 may include one or more devices integrated on or within the system 200 and / or one or more devices attached to or located in proximity to the system 200. For example, the flow sensor 202 may be integrated into one or more of the pump 204, the tube 206, the container 208, or the tip 212.

[0027] The pump 204 may pump the product through the tube 206, out the tip 212, and into the container 208. The pump 204 may be a positive displacement pump, such as a peristaltic pump. Alternatively, the pump 204 may be at least one of an impulse pump, a velocity pump, a gravity pump, a vapor pump, or a valveless pump. The pump 204 may have a main drive speed that is controllable via a controller and / or operator. The controller and / or operator may instruct the pump 204 when to begin pumping (e.g., when an empty container is placed under the tip 212) and when to begin pumping termination (e.g., to allow the container 208 to be filled with a desired amount of product). The pump 204 may be controlled by one or more processors (such as the one or more processors 120 of FIG. 1). During operation of the pump 204, the main drive speed may be constant or variable. The main drive speed of the pump 204 may be a parameter of the product fill recipe that is adjustable. In adjusting the main drive speed of the pump 204, it is important not to increase the main drive speed beyond a threshold value because doing so may cause the product (especially a fluid product) to splash, lose stability, foam, or become lost on the sides of the container 208.

[0028] The tube 206 may be of variable or constant diameter and may be of flexible or rigid construction. Examples of possible tube materials may include polyethylene, nylon, urethane, copper, stainless steel, plastic, polyvinyl chloride, silicone rubber, thermoplastic, fluoroelastomer, etc. The diameter, construction, material, or other tube parameters of the tube 206 may depend on the pump 204, including, for example, the pump's main drive speed. Thus, the tube 206 may be selected as part of a product fill recipe to allow for specific adjustments to parameters of the product fill recipe, such as the main drive speed.

[0029] The containers 208 may be of a variety of different types, for example, the containers 208 may be at least one of a vial, a syringe, a cartridge, a tube, a beaker, a cup, or any other holding structure suitable for the product. In some embodiments, more than one of the containers 208 may be filled at once (i.e., the product filling system may be configured to fill multiple of the containers 208 simultaneously). Different types of containers 208 may correspond to different main drive speed thresholds beyond which increasing the main drive speed may cause the product (particularly in the case of fluid products) to splash, lose stability, foam, or be lost on the sides of the container 208. Thus, the containers 208 may be selected as part of a product filling recipe to allow for specific adjustments to parameters of the product filling recipe, such as the main drive speed.

[0030] The conveyor system 210 for moving the container 208 into position relative to the tip 212 may be at a constant or variable speed. The conveyor system 210 may be controlled by one or more processors (such as the one or more processors 120 of FIG. 1). The type of conveyor system 210 or parameters of the conveyor system 210 (e.g., speed) may be selected based on parameters of the product fill recipe. For example, parameters of the product fill recipe, such as a fill start ramp or a fill stop ramp, may affect the type of conveyor system 210 or parameters of the conveyor system 210.

[0031] The tip 212 may be, for example, a sprayer, a pipette tip, a dropper, a nozzle, or any other device suitable for facilitating the expulsion of product from the tube 206 into the container 208. The tip 212 may be capable of being used in conjunction with product drip retraction to prevent the last drops of product from being expelled into the container 208. Thus, the tip 212 may be selected as part of a product fill recipe to allow for specific adjustments to parameters of the product fill recipe, such as drip retraction.

[0032] Figure 3 shows example flow rate data over a single fill case 300. In general, the example experimental results contained in Figure 3 can be used to generate flow profiles and thus characterize and / or match product fill recipes.

[0033] The example experimental data included in FIG. 3 may correspond to a single fill instance performed by a product fill system, such as product fill system 200 of FIG.

[0034] In Figure 3, the flow rate (mL / sec) of a single fill instance is plotted as a function of time (measured in seconds). Marked on the flow rate curve are: start time 302, pump injection start point 304, injection start ramp point 306, injection stop ramp point 308, pump injection end point 310, drip retraction end point 312, and end time 314. Also marked in Figure 3 are drip retraction curve 316 and drip retraction distance 318.

[0035] The start time 302 may be the time at which collection of flow data begins. The start time 302 may correspond to the power-up of a flow sensor (which may be the same as or similar to the flow sensor 202 of FIG. 2 and / or the flow sensor 104 of FIG. 1) or the start of data collection by the flow sensor.

[0036] The pump injection start point 304 may correspond to the beginning of operation of a pump, which may be the same as or similar to pump 204 of Figure 2. In a peristaltic pump embodiment, the pump injection start point 304 may correspond to when the peristaltic pump just begins to rotate. The time at which the pump injection start point 304 occurs may be an adjustable product fill recipe parameter.

[0037] The region between the pump infusion start point 304 and the infusion start ramp point 306 may correspond to the increase in pumping by the pump from zero (at the pump infusion start point 304) to the main drive speed (at the infusion start ramp point 306). In a peristaltic pump embodiment, this region may correspond to the peristaltic pump ramping from zero revolutions per minute to a certain number of revolutions per minute (i.e., the main drive speed). The behavior of the pump in ramping from zero to the main drive speed (e.g., how quickly the pumping rate increases, the length of time the pump increases the pumping rate, the pattern of pumping rate increase, etc.) may comprise adjustable product fill recipe parameters.

[0038] The region between the start fill ramp point 306 and the stop fill ramp point 308 may correspond to the pump operating at the main drive speed with little, if any, change in pumping rate. In a peristaltic pump embodiment, this region may correspond to the peristaltic pump operating at a constant number of revolutions per minute (i.e., the main drive speed). The main drive speed and / or the length of time the pump operates at the main drive speed may be adjustable product fill recipe parameters.

[0039] The region between the stop pump ramp point 308 and the pump end point 310 may correspond to the pump reducing the pumping rate from the main drive speed (at the stop pump ramp point 308) to zero or near zero (the pump end point 310). In a peristaltic pump embodiment, this region may correspond to the peristaltic pump reducing from a certain number of revolutions per minute (i.e., the main drive speed) to zero revolutions per minute. The behavior of the pump in reducing from the main drive speed to zero (e.g., how quickly the pumping rate is reduced, the length of time the pump reduces the pumping rate, the pattern of pumping rate reduction, etc.) may comprise adjustable product fill recipe parameters.

[0040] The pumping end point 310 may correspond to the end of pump operation. In peristaltic pump embodiments, the pumping end point 310 may correspond to when the peristaltic pump finishes a revolution. The time at which the pumping end point 310 occurs may be an adjustable product fill recipe parameter.

[0041] The end time 312 may be the time when the recording of flow data stops. The end time 312 may correspond to the flow sensor being powered off or the flow sensor ceasing to collect data.

[0042] As shown in FIG. 3, pump injection end point 310 does not correspond to a strict zero flow rate. This may be due to residual product exiting at least one of the pump, the tube (which may be the same as or similar to tube 206 in FIG. 2), or the tip (which may be the same as or similar to tip 212 in FIG. 2) after the pump has finished operating. Thus, in some embodiments, drip retraction is used to counteract residual product exiting at least one of the pump, the tube, or the tip. A drip retraction curve 316 is shown in FIG. 3 as having a negative flow rate, corresponding to residual product being removed before entering the container (which may be the same as or similar to container 208 in FIG. 2). Also shown in FIG. 3 is a drip retraction distance 318 that corresponds to the drip retraction curve. Whether or not to use drip retraction may be an adjustable product fill recipe parameter. Additionally, the behavior of the drip retraction implementation (eg, the shape of the drip retraction curve 316, the drip retraction distance 318, etc.) may include adjustable product fill recipe parameters.

[0043] 4 is a flow diagram 400 illustrating example data used in generating a flow profile from flow rate data over multiple filling cases. The example experimental data included in FIG. 4 may correspond to 13 filling cases performed by a product filling system, such as product filling system 200 of FIG.

[0044] In Figure 4, flow rates (mL / sec) for the fill cases are plotted as a function of time (measured in seconds). To generate a flow profile from the flow data, four stages of data are shown in Figure 4, including flow data 402, smoothed flow data 404, segmented smoothed flow data 406, and flow profile 408. Generating at least one of the four stages of data may include using a machine learning algorithm.

[0045] The flow data 402 may correspond to the product fill system 200 of FIG. 2 or some other product fill system and may be generated and / or collected using a flow sensor (which may be the same as or similar to the flow sensor 202 of FIG. 2 and / or the flow sensor 104 of FIG. 1) and a data collection unit (which may be the same as or similar to the data collection unit 140 of FIG. 1). As shown in FIG. 4, there are thirteen fill cases that the flow data 402 includes. There may be noise between each of the fill cases. All thirteen fill cases may correspond to a single product fill system (which may be the same as or similar to the product fill system 200 of FIG. 2). Although each of the thirteen fill cases may correspond to a single product fill system, there may still be some variation in parameters of the single product fill system among the thirteen fill cases, such as variation in one or more of the following: pump injection start point, injection start ramp point, injection stop ramp point, pump injection end point, drip retraction end point, main drive speed, etc. The magnified window shows one fill case out of the thirteen fill cases included in the flow data 402. The expanded window of 402 illustrates clipping, chopping, and / or other possible undesirable characteristics of the flow data 402 .

[0046] The smoothed flow data 404 may be smoothed data corresponding to the flow data 402 and may be generated using a data smoothing unit (which may be the same as or similar to the data smoothing unit 150 of FIG. 1). The smoothed flow data 404 may smooth clipping, chopping, and / or other possible undesirable characteristics of the flow data 402. Smoothing the flow data 402 to generate the smoothed flow data 404 may be done, for example, through creating an approximation function to capture significant patterns in the flow data 402 while filtering out noise or other fine structure / abrupt phenomena (i.e., the data points of the flow data 402 are altered such that fewer individual points are higher than their neighbors (possibly due to noise) and more data points are lower than their neighbors (possibly due to noise)) to generate a smoother signal. The smoothed flow data 404 offers advantages over the flow data 402, such as it may be possible to extract more information from the smoothed flow data 404 (if smoothing is appropriate) and it may be possible to perform analysis on the flexible and robust smoothed flow data 404. The expanded window of 404 shows more smoothed flow data than is shown in the expanded window of 402.

[0047] The segmented smoothed flow data 406 may be segmented data corresponding to the smoothed flow data 404 and may be generated using a filling case segmentation unit (which may be the same as or similar to the filling case segmentation unit 142 of FIG. 1). The segmented smoothed flow data 406 may segment each of the thirteen filling cases included in the flow data 402 and the smoothed flow data 404. Each of the thirteen filling cases may be segmented to include only data corresponding between the pump infusion start point and the pump infusion end point of each filling case. The segmented filling cases are shown with solid lines, while data points excluded from the segmented smoothed flow data 406 are shown with dashed lines. Identifying each filling case for segmenting the smoothed flow data 404 may be based on factors or characteristics of the smoothed flow data 404, including, for example, one or more of the following: prominentness of filling case peaks, minimum spacing between filling cases, minimum height of filling case peaks, minimum threshold value of filling case peaks, or minimum width of filling case peaks. Therefore, data points between the fill cases may be excluded from the segmented smoothed flow data 406. By smoothing the smoothed flow data 404 into 13 fill cases, each fill case may be analyzed individually. In some embodiments, the beginning and ending fill cases may be excluded from the segmented flow data 406, as shown in Figure 4. Excluding the beginning and ending fill cases may be done to improve the accuracy and representation of the data regarding the corresponding product fill system.

[0048] The flow profile 408 may be generated based on the segmented smoothed flow data 406 using a flow profile generation unit (which may be the same as or similar to the flow profile generation unit 144 of FIG. 1). More specifically, the flow profile 408 shown in FIG. 4 may be based on eleven (excluding the beginning and ending filling cases of the thirteen filling cases of the segmented smoothed flow data 406) filling cases of the smoothed flow data 406. To generate a flow profile from the segmented smoothed flow data 406, a dynamic time warping method may be performed on each of the filling cases of the segmented smoothed flow data 406. By performing the dynamic time warping method, the effect of the variability of the segmentation of the filling cases on the average of the filling cases may be reduced. After the dynamic time warping method is applied, many different methods may be used to calculate the average value of each of the filling cases of the segmented smoothed flow data 406, but in one embodiment, a k-means method may be used. Indeed, in the example data contained in FIG. 4, dynamic time warping and k-means are applied to each of eleven filling instances of the segmented smoothed flow data 406 (shown as dashed lines) to generate the flow profile 408 (shown as solid lines) as shown.

[0049] 5 is a flow diagram 500 illustrating an example method for altering parameters of a fill recipe of at least one of two product fill systems to achieve transferability between the two product fill systems. The example method may include the following steps: (1) collecting flow data from the two product fill systems (steps 502A and 502B), (2) generating two flow profiles corresponding to the flow data from each of the two product fill systems (step 504), (3) comparing the two flow profiles to determine adjustments to parameters of the fill recipe of at least one of the two product fill systems to achieve transferability (step 506), and (4) altering parameters of the fill recipe of at least one of the two product fill systems (step 508).

[0050] Collecting flow data from the two product fill systems (steps 502A and 502B) may use one or more flow sensors, such as flow sensor 104 of FIG. 1 and / or flow sensor 202 of FIG. 2, and possibly data collection unit 140 of FIG. 1. The two product fill systems may be of the same type and / or produced or provided by the same vendor. In other embodiments, the two product fill systems may be of different types and / or produced or provided by different vendors. At least one of the two product fill systems may be, for example, product fill systems 102A and 102B of FIG. 1 and / or product fill system 200 of FIG. 2.

[0051] Generating two flow profiles corresponding to the flow data from each of the two product filling systems (step 504) may use a computing device, such as the computing device 110 of FIG. 1, and possibly one or more of the filling case segmentation unit 142, the flow profile generation unit 144, or the data smoothing unit 150 of FIG. 1. The computing device may perform steps similar to those corresponding to the example data used in generating the flow profile from the flow data across multiple filling cases in FIG. 4, for example. For example, the computing device may (i) generate flow data, (ii) generate smoothed flow data, (iii) generate segmented flow data, and (iv) generate a flow profile. The two flow profiles corresponding to the flow data from each of the two product filling systems may be generated in parallel or in series.

[0052] Comparing the two flow profiles to determine adjustments to parameters of the fill recipe of at least one of the two product filling systems to achieve transferability (step 506) may use a computing device, which may be the same computing device as used in step 504 or a different computing device. The comparison (step 506) may use the computing device 110 of FIG. 1 and possibly the parameter adjustment unit 148 of FIG. 1. Comparing the two flow profiles to determine adjustments to parameters of the fill recipe of at least one of the two product filling systems to achieve transferability (step 506) may include causing the computing device to display the two flow profiles, possibly on a shared axis set (which may use the flow profile presentation unit 146 of FIG. 1). The adjustments to the parameters may relate to one or more of pump infusion start, infusion start ramp, infusion stop ramp, pump infusion end, drip retraction, or main drive speed. Determining the adjustments may be based on a Fréchet distance between the first flow profile and the second flow profile.

[0053] Changing the parameters of the fill recipe of at least one of the two product filling systems 508 may use a computing device, which may be the same or a different computing device as used in steps 504 and / or 506. The changing in step 508 may use the computing device 110 of FIG. 1 and possibly the parameter adjustment unit 148 of FIG. 1. The parameters may be changed, for example, via an operator providing instructions to the computing system via a user input device, such as the user input device 126 of FIG. 1. Changing the parameters may include a user directly replacing and / or modifying one or more components of the product filling systems. For example, an operator may increase the main drive speed of one of the product filling systems and, in response to increasing the main drive speed, replace the containers of all the product filling systems with new containers suitable for the increased main drive speed.

[0054] Changing 508 parameters of the fill recipe of at least one of the two product fill systems may further include verifying that transferability has been achieved after the parameters have been changed. Verifying that transferability has been achieved may include an iterative method of performing steps 502A, 502B, 504, and 506 (in part) again after the parameters have been changed, thereby (1) collecting new flow data from the two product fill systems (steps 502A and 502B), (2) generating two new flow profiles corresponding to the flow data from each of the two product fill systems (step 504), and (3) comparing the two new flow profiles to verify that transferability has been achieved (step 506, in part). If transferability has been achieved, the method may end because the desired condition has been met. If transferability has not been achieved, the method may continue by determining new adjustments to the parameters of the fill recipe of at least one of the two product fill systems (step 506, in part) and again modifying the parameters of the fill recipe of at least one of the two product fill systems (step 508) to achieve transferability. The iterative method may continue further iteratively until the transferability condition is met.

[0055] 6A and 6B are flow diagrams illustrating example methods 600A and 600B, respectively, for displaying a first flow profile and a second flow profile, respectively.

[0056] In the illustrated method 600A / 600B, first / second flow rate data is generated across a plurality of first / second fill cases corresponding to the first / second product fill formulation (block 602A / 602B). For example, there may be 10 first fill cases for which first flow rate data is generated and 100 second fill cases for which second flow rate data is generated. This example may correspond to the first flow rate data corresponding to a first product fill system used in drug discovery and the second flow rate data corresponding to a second product fill system used in drug manufacturing, where the second product fill system has a greater production capacity and / or throughput than the first product fill system.

[0057] Next, in the illustrated method 600A / 600B, a plurality of first / second filling case curves are generated, each of which is a segment of the first / second flow data corresponding to a different first / second filling case of the plurality of first / second filling cases (block 604A / 604B). The plurality of first / second filling case curves may correspond to all or a portion of the first / second filling cases. For example, the plurality of first / second filling case curves may correspond to each of the first / second filling cases except for the beginning and ending filling cases. Segmenting the first / second flow data into the first / second filling cases may be based on one or more of saliency, minimum spacing, minimum height, minimum threshold, or minimum width.

[0058] Next, the method 600A / 600B is shown to generate first / second flow profiles based on the plurality of first / second fill case curves (block 604A / 604B). For example, the first / second flow profiles may be generated using dynamic time warping and / or k-means.

[0059] Finally, the illustrated method 600A / 600B includes having a display present the first / second flow profile. In some embodiments, the first and second flow profiles may be displayed separately, possibly on separate displays. In other embodiments, the first and second flow profiles may be displayed simultaneously on a display on a shared set of axes. Displaying the first and second flow profiles simultaneously on a shared set of axes allows an operator to compare the flow profiles.

[0060] Method 600A / 600B may be performed entirely by a human operator in some embodiments. Alternatively, method 600A / 600B may be performed entirely by automation, for example, by one or more processors (e.g., CPUs and / or GPUs) executing instructions stored in one or more non-transitory computer-readable storage media (e.g., volatile or non-volatile memory, read-only memory, random access memory, flash memory, electronically erasable program read-only memory, and / or one or more other types of memory). Method 600A / 600B may be performed entirely or in part by a machine learning algorithm. In yet other embodiments, method 600A / 600B is performed in part by a human operator and in part by one or more processors executing instructions. For example, a human may input a command (e.g., pressing a virtual button on a graphical user interface generated by the one or more processors) to initiate collection of first / second flow data, and in response, the one or more processors may trigger the initiation of an action by one or more components of the first / second product filling system, including a flow sensor. Method 600A / 600B may use any of the components of FIG. 1 and / or FIG. 2.

[0061] Some of the figures described herein show example block diagrams having one or more functional components. It will be understood that such block diagrams are for illustrative purposes and that the devices described and shown may have more, fewer, or alternative components than those illustrated. Furthermore, in various embodiments, the components (and the functionality provided by each component) may be associated with or otherwise integrated as part of any suitable component.

[0062] Some embodiments of the present disclosure relate to a non-transitory computer-readable storage medium having instructions / computer-readable storage media for performing various computer-implemented operations. The term "instructions / computer-readable storage medium" is used herein to include any medium that can store or encode a set of instructions or computer code for performing the operations, methods, and techniques described herein. The medium and computer code may be specially designed and constructed for the purposes of the embodiments of the present disclosure, or may be of a type known and available to those skilled in the art of computer software technology. Examples of computer-readable storage media include, but are not limited to, magnetic media such as hard disks, floppy disks, magnetic tapes, optical media such as CD-ROMs, holographic devices, magneto-optical media such as optical disks, hardware devices specially configured for storing and executing program code, such as ASICs, programmable logic devices ("PLDs"), and ROM and RAM devices.

[0063] Examples of computer code include machine code produced by a compiler and files containing high-level code executed by a computer using an interpreter or compiler. For example, embodiments of the present disclosure may be implemented using Java, C++, or other object-oriented programming languages ​​and development tools. Additional examples of computer code include encryption and compression code. Furthermore, embodiments of the present disclosure may be downloaded as a computer program product and transferred from a remote computer (e.g., a server computer) to a requesting computer (e.g., a client computer or another server computer) over a transmission channel. Other embodiments of the present disclosure may be implemented in hardwired circuitry in the alternative to or in combination with machine-executable software instructions.

[0064] As used herein, the singular terms "a," "an," and "the" may include plural referents unless the context clearly dictates otherwise.

[0065] As used herein, the terms "nearly," "substantially," "substantial," "generally," and "about" are used to describe and explain slight differences. When used with events or circumstances, these terms may refer to the exact occurrence of the event or circumstances, as well as the approximation of the occurrence of the event or circumstances. For example, when used with a numerical value, these terms may refer to a variation range of ±10% or less of the numerical value, such as ±5% or less, ±4% or less, ±3% or less, ±2% or less, ±1% or less, ±0.5% or less, ±0.1% or less, or ±0.05% or less. For example, two numerical values ​​can be considered "substantially" identical if the difference between the two numerical values ​​is ±10% or less of the average of the numerical values, such as ±5% or less, ±4% or less, ±3% or less, ±2% or less, ±1% or less, ±0.5% or less, ±0.1% or less, or ±0.05% or less.

[0066] Additionally, amounts, ratios, and other numerical values ​​may be presented herein in a range format. It should be understood that such range formats are used for convenience and brevity and should be understood to be flexible and include not only the numerical values ​​explicitly stated as the limits of a range, but also all individual numerical values ​​or subranges contained within that range as if each numerical value and subrange were expressly stated.

[0067] Although the present disclosure has been described and illustrated primarily with reference to certain embodiments, these descriptions and illustrations are not intended to limit the present disclosure. Those skilled in the art will understand that various modifications may be made and equivalents may be substituted without departing from the true spirit and scope of the present disclosure as defined by the appended claims. The drawings are not necessarily drawn to scale. The artistic depictions in the present disclosure may differ from the actual device due to manufacturing processes, tolerances, and / or other reasons. There may be other embodiments of the present disclosure that are not specifically illustrated. The present specification and drawings (other than as claimed) should be regarded as illustrative and not restrictive. Changes may be made to adapt a particular situation, material, composition of matter, technique, or process to the objective, concept, and scope of the present disclosure. All such modifications are intended to be within the scope of the claims appended hereto. Although the techniques disclosed herein have been described primarily with certain operations performed in a particular order, it will be understood that these operations may be combined, divided into parts, or reordered to form equivalent techniques without departing from the teachings of the present disclosure. Thus, unless specifically indicated herein, the order and grouping of the operations is not a constraint on the present disclosure.

Claims

1. 1. A method for characterizing and / or matching a product fill formula, comprising: generating, with one or more flow sensors, first flow rate data across a plurality of first fill instances corresponding to a first product fill recipe; generating, by one or more processors, a plurality of first fill case curves, each first fill case curve being a segment of the first flow data corresponding to a different first fill case among the plurality of first fill cases; generating, by the one or more processors, a first flow profile based on the plurality of first fill case curves; causing, by the one or more processors, a display to present the first flow profile; A method comprising:

2. generating second flow rate data across a plurality of second fill instances corresponding to a second product fill recipe with the one or more flow sensors or one or more other flow sensors; generating, by the one or more processors, a plurality of second fill case curves, each second fill case curve being a segment of the second flow data corresponding to a different second fill case among the plurality of second fill cases; generating, by the one or more processors, a second flow profile based on the plurality of second fill case curves; causing, by the one or more processors, a display to present the second flow profile; The method of claim 1 further comprising:

3. The method of claim 2 , comprising causing the display to simultaneously present the first flow profile and the second flow profile on a set of shared axes.

4. 3. The method of claim 2, further comprising determining adjustments to one or more parameters of the second product fill recipe based on the first flow profile and the second flow profile.

5. The method of claim 4 , wherein determining the adjustment comprises determining the adjustment based on a Fréchet distance between the first flow profile and the second flow profile.

6. The method of claim 4 , further comprising altering the one or more parameters of the second product fill formula according to the adjustment.

7. 7. The method of claim 6, further comprising substituting and / or modifying equipment of a second product fill system corresponding to the second product fill recipe in response to changing the one or more parameters of the second product fill recipe.

8. 5. The method of claim 4, wherein the one or more parameters relate to one or more of: pump initiation, initiation ramp, initiation ramp, termination ramp, drip retraction, or main drive speed.

9. smoothing, by the one or more processors, the first flow rate data before generating the plurality of first fill case curves; smoothing, by the one or more processors, the second flow rate data before generating the plurality of second fill case curves; The method of claim 2 further comprising:

10. The method of claim 1 , wherein generating the first flow profile includes using dynamic time warping.

11. The method of claim 10 , wherein generating the first flow profile includes using dynamic time warping and averaging.

12. The method of claim 11 , wherein generating the first flow profile includes using dynamic time warping and k-means.

13. 2. The method of claim 1, wherein generating at least one of the first fill case curves comprises segmenting the first flow data based on one or more of a saliency, a minimum spacing, a minimum height, a minimum threshold, or a minimum width.

14. 2. The method of claim 1, wherein the plurality of first fill cases includes at least three first fill cases, and generating the plurality of first fill case curves includes excluding segments of the first flow data corresponding to a start of a first fill case and an end of a first fill case.

15. 1. A system comprising: one or more flow sensors; one or more processors; one or more non-transitory computer readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the method of any one of claims 1 to 14; A system including:

Images