Fluid flow rate

Abstract

A method for estimating the volume of liquid output from an electric pump during the operation period of the electric pump, the method comprising measuring a current delay of the pump, the current delay being a period between a first time point corresponding to a first current draw by the pump and a second time point corresponding to a second current draw by the pump, and generating an estimated value of the volume of liquid output from the electric pump during the operation period based on the current delay.

Description

Technical Field

[0001]

[0001] This technology relates to flow rate estimation in the field of electric pumps. More specifically, this technology relates to, but is not limited to, estimating the volume or flow rate of liquid output from an electric pump without using a flow meter.

Background Art

[0002]

[0002] Beverage preparation devices or liquid dispensing machines often include one or more electric pumps for passing liquid through a liquid path within the device or machine. In such situations, the flow rate of the liquid output from the electric pump (often expressed as volume per unit time) is measured and summed to measure the total volume of liquid output from the beverage preparation device, for example, indicating when to stop the liquid output from the beverage preparation device.

[0003]

[0003] Conventionally, flow meters have been used to measure the flow rate of liquid output from electric pumps. However, such flow meters can increase the complexity of manufacturing the entire system, increase manufacturing costs, introduce additional failure points, and introduce irregularities into the liquid path. Therefore, it may be appropriate to estimate the flow rate of the liquid output from the electric pump (used interchangeably herein with the conceptual description of volume per unit time) without using a flow meter.

[0004]

[0004] Known methods are presented in European Patent No. 2548483 and US Patent Application Publication No. 2013 / 094840 (A1). These attempt to estimate the water flowing through the heater based on the measured temperature of the water and a physical formula related to the energy required to heat a specific amount of water. Other known methods are presented in International Publication No. 12062628 and European Patent No. 3097827.

[0005]

[0005] However, as recognized by the inventors of the present method, existing methods for estimating the flow rate of a liquid without a dedicated flow meter may lack accuracy and, in some cases, require the introduction of other complex hardware devices or rely on estimating additional parameter values, thereby introducing further uncertainty into the flow rate estimation.

Summary of the Invention

[0006]

[0006] Certain aspects and embodiments are set forth in the appended claims.

[0007]

[0007] Viewed from a first aspect, a method is provided for estimating the volume of liquid output from an electric pump during an operating period of the electric pump. The method includes measuring a current delay of the pump, where the current delay is a period between a first time point corresponding to a first current draw by the pump and a second time point corresponding to a second current draw by the pump, and generating an estimated value of the volume of liquid output from the electric pump during the operating period based on the current delay. Thereby, a technique is provided for efficiently and accurately estimating the flow rate output from the electric pump by using parameters directly related to the operation of the electric pump. Therefore, a flow meter can be omitted.

[0008]

[0008] Viewed from a further aspect, a liquid dispensing machine is provided that includes an electric pump and a processing circuit configured to execute the method described herein. Thereby, a liquid dispensing machine is provided that is configured to efficiently and accurately estimate the flow rate output from the electric pump by using parameters directly related to the operation of the electric pump. Therefore, a flow meter can be omitted from the liquid dispensing machine.

[0009]

[0009] In a further aspect, there is provided a computer-readable medium including instructions that, when executed by a programmable liquid dispensing machine, cause the programmable liquid dispensing machine to perform the methods described herein. Thereby, there is provided a computer-readable medium including instructions that, when executed by a programmable liquid dispensing machine, cause the programmable liquid dispensing machine to efficiently and accurately estimate the flow rate output from an electric pump by using parameters directly related to the operation of the electric pump.

[0010]

[0010] In a further aspect, there is provided a method for training a regression model for estimating the volume of liquid output from an electric pump during an operation period of the electric pump, the method including obtaining training data including a value of a current delay of a test device and a volume of liquid output by the test device during operation of the test device, the test device corresponding to the electric pump and the current delay being a period between a first time point corresponding to a first current drawn by the test device and a second time point corresponding to a second current drawn by the test device, and performing regression analysis on the training data to provide one or more parameters usable for estimating the volume of liquid output from the electric pump based on a measured value of the current delay of the electric pump. Thereby, a technique for training a regression model for efficiently and accurately estimating the flow rate output from an electric pump by using parameters directly related to the operation of the electric pump is provided.

[0011]

[0011] In another aspect, a beverage preparation apparatus is provided, which includes a fluid input section connected to receive fluid for beverage preparation, an electric pump connected to the fluid input section and having a control input section, a current sensor connected to the power connection section of the electric pump, a beverage preparation output section connected to receive the fluid dispensed by the electric pump, and a controller connected to the current sensor and the control input section. The controller is configured to calculate the volume of the dispensed fluid by the electric pump based on the current draw delay measured by the current sensor, and to send a control signal to the control input section to deactivate the electric pump in response to the fluid volume reaching a threshold volume. Thereby, a beverage preparation apparatus is provided that is configured to efficiently and accurately estimate the flow rate output from the electric pump by using parameters directly related to the operation of the electric pump. Therefore, a flow meter can be omitted from the beverage preparation apparatus.

[0012]

[0012] Other aspects will also become apparent by considering the present disclosure, specifically by considering the brief description of the drawings, the detailed description, the drawings, and the claims.

Brief Description of the Drawings

[0013]

[0013] Next, with reference to the accompanying drawings, by way of example only, examples of the present disclosure will be described.

[0014]

Figure 1

[0014] FIG. 1 schematically shows a beverage preparation apparatus configured to operate in accordance with the teachings of the present disclosure.

[0015]

Figure 2

[0015] FIG. 2 shows the relationship between the flow rate and the current delay according to the teachings of the present disclosure.

[0016]

Figure 3

[0016] FIG. 3 schematically shows a method for estimating the volume of liquid output from an electric pump during the operation of the electric pump according to the teachings of the present disclosure.

[0017]

Figure 4

[0017] Figure 4 shows the relationship between current extraction by an electric pump and time according to the teachings of the present disclosure.

[0018]

Figure 5

[0018] Figure 5 shows the relationship between flow rate and current delay for three power supply voltages according to the technique of the present disclosure.

[0019]

Figure 6

[0019] Figure 6(a) shows the relationship between time and pump power according to the technique of the present disclosure, and Figure 6(b) shows the relationship between time and cumulative volume according to the technique of the present disclosure.

[0020]

Figure 7

[0020] Figure 7 shows the relationship between time and cumulative volume for liquids at different temperatures according to the technique of the present disclosure.

[0021]

Figure 8

[0021] Figure 8 schematically shows a method for calculating the cumulative volume of liquid output from an electric pump according to the technique of the present disclosure.

[0022]

Figure 9

[0022] Figure 9 schematically shows a method for estimating the volume of liquid output from an electric pump when the power supply voltage fluctuates according to the technique of the present disclosure.

[0023]

Figure 10

[0023] Figure 10 schematically shows a method for training a regression model to estimate the volume of liquid output from an electric pump during the operation of the electric pump.

[0024]

Figure 11

[0024] Figure 11 shows the estimation performance of the technique of the present disclosure for estimating the volume of liquid output from an electric pump during the operation of the electric pump.

[0025]

[0025] While various modifications and alternative forms are possible for the present disclosure, specific exemplary approaches are shown by way of example in the drawings and described in detail herein. However, it should be understood that the accompanying drawings and the "Detailed Description of the Invention" are not intended to limit the present disclosure to the specific forms disclosed, but rather, are intended to cover all amendments, equivalents, and alternatives that fall within the spirit and scope of the claimed invention.

[0026]

[0026] It should be recognized that the features of the above examples of the present disclosure can be conveniently and interchangeably used in any suitable combination.

Detailed Description of the Invention

[0027]

[0027] The methods described below relate to estimating the flow rate output from an electric pump. Although these methods are described in the context of a beverage preparation apparatus, it should be understood that the techniques for flow rate estimation can be applied to a wide variety of configurations that use an electric pump to output a liquid flow. Such an estimation may be used for controlling the amount of liquid output by the pump, for example, to enable control of the pump's activation window to output a known volume of liquid. Such an estimation may additionally or alternatively be used, for example, to track the total liquid output by the pump over a particular period of time and / or over the operating life of the pump.

[0028]

[0028] FIG. 1 schematically shows a beverage preparation apparatus. The beverage preparation apparatus 100 or liquid dispensing machine can be, in some examples, a coffee machine or a capsule-based coffee machine. As described above, the techniques described herein can be applied to any apparatus or machine that includes an electric pump configured to output a liquid or fluid. In fact, such an electric pump can be, in some examples, a vibrating pump or a positive displacement pump, such as a vibrating piston pump or a vibrating plunger pump.

[0029]

[0029] In this example, the beverage preparation device 100 includes a fluid input unit 110 connected to receive a fluid for beverage preparation. The beverage preparation device 100 further includes an electric pump 130 connected to the fluid input unit 110 and having a control input unit 140. The fluid input unit 110 and the electric pump 130 are connected by a fluid path 115 to enable the passage of fluid from the fluid input unit 110 to the electric pump 130. The beverage preparation device 100 is connected to the power connection part of the electric pump 130 indicated by the connection part 155, and further includes a current sensor 160 configured to measure the current drawn by the electric pump 130.

[0030]

[0030] The beverage preparation device 100 further includes a beverage preparation output unit 150 connected to receive the fluid distributed by the electric pump 130. The electric pump 130 and the beverage preparation output unit 150 are connected by a fluid path 145 to enable the passage of fluid from the electric pump 130 to the beverage preparation output unit 150.

[0031]

[0031] The current sensor 160 is further connected to the controller 170 by the connection part 165 so that the measured value of the current drawn by the electric pump 130 is provided to the controller 170. The controller 170 is also connected to the control input unit 140 of the electric pump 130 by the connection part 175. The controller 170 is configured to calculate the distributed fluid volume by the electric pump 130 based on the current draw delay measured by the current sensor 160, and to send a control signal to the control input unit 140 of the electric pump 130 to deactivate the electric pump 130 in response to the fluid volume reaching a threshold volume.

[0032] It should be understood that the beverage preparation device 100 may include additional components not shown in FIG. 1. For example, the additional components may be present within the fluid path between the fluid input section 110 and the electric pump 130, and within the fluid path between the electric pump 130 and the beverage preparation output section 150. For example, some form of beverage preparation chamber and / or heating component may be provided between the electric pump 130 and the beverage preparation output section 150, and / or some form of fluid input filter may be present between the fluid input section 110 and the electric pump 130.

[0033]

[0033] FIG. 2 shows the relationship between the flow rate of the liquid output from the electric pump during the operation of the electric pump, or the volume of the liquid per unit time, and the current delay parameter of the electric pump. Specifically, the inventors of the present method have identified that the volume of the liquid output from the electric pump correlates with the current delay of the electric pump. This current delay of the electric pump used in this specification is the period between a first time point corresponding to a first current draw by the electric pump and a second time point corresponding to a second current draw by the electric pump. The first current and the second current will be described in more detail below with specific reference to FIG. 4.

[0034]

[0034] As shown in FIG. 2, generally, the greater the current delay of the electric pump, the smaller the volume of the liquid output from the electric pump per unit time. In other words, the flow rate of the liquid output from the pump becomes smaller. Conversely, the smaller the current delay, generally, the greater the flow rate of the liquid output from the pump. The inventors of the present invention who have identified this correlation recognize that this relationship enables the generation of an estimated value of the volume of the liquid output from the electric pump during the operation of the electric pump based on the measurement of the current delay of the electric pump.

[0035]

[0035] FIG. 3 schematically shows a method 300 for estimating the volume of the liquid output from the electric pump during the operation of the electric pump according to the teachings of the present disclosure. The method 300 includes the following steps.

[0036]

[0036] In step S301, the current delay of the electric pump is measured. As described above, the current delay is the period between a first time point corresponding to the first current extraction by the pump and a second time point corresponding to the second current extraction by the pump.

[0037]

[0037] In step S302, an estimated value of the volume of the liquid output from the electric pump during the operation period is generated based on the current delay.

[0038]

[0038] Therefore, this method enables the estimation of the volume of the liquid output from the electric pump during the operation period of the pump without using a dedicated flow meter. By doing so, the complexity of system manufacturing can be reduced, the manufacturing cost of the system can be reduced, the failure point (flow meter) of the system can be removed, and the irregularity of the liquid path can be reduced. Any one or more of these results may be provided in any specific implementation form, thereby providing a more efficient manufacturing process and / or a more reliable operation.

[0039]

[0039] Furthermore, since the estimation is generated based on the current delay of the electric pump, as a result, the need to introduce other complex hardware devices is avoided, and the dependence on parameters that are themselves estimated is also avoided. Therefore, this method can avoid introducing further uncertainty into the flow rate estimation when the flow meter is omitted. Therefore, this method can provide a more accurate estimation of the flow rate even in the absence of a flow meter. Furthermore, since the flow rate estimation is based on the current delay of the electric pump, that is, based on a single hardware device, the calculation efficiency is improved.

[0040]

[0040] The above description and FIG. 3 refer to the current delay of the pump, the first time point corresponding to the first current extraction by the pump, and the second time point corresponding to the second current extraction by the pump. Here, the measurement of the current delay, as well as the first and second time points and currents, will be described in more detail with reference to FIG. 4.

[0041]

[0041] FIG. 4 shows the relationship between the pump current, i.e., the current drawn by the electric pump, and time. More specifically, FIG. 4 shows five pump cycles over a period of about 100 ms. Each pump cycle is characterized in that the current drawn by the pump increases from substantially zero, increases rapidly substantially linearly (i.e., at a substantially constant rate of change) after a short period of noise-like behavior, then reaches the peak current without increasing as rapidly, returns to the noise-like behavior again, and finally reaches a time when no current is drawn. In the example shown in FIG. 4, the peak current is about 1 A, and the current at the transition from a substantially linear increase to a less linear increase is about 0.3 A. However, it should be understood that the present disclosure is not limited to such individual values, and in fact, the individual values for any given implementation will vary depending on the individual pump.

[0042]

[0042] Time 410 in FIG. 4 may indicate the first time point, and time 420 may indicate the second time point. As shown, the first time point 410 corresponds to the first current draw 415 by the pump, and the second time point 420 corresponds to the second current draw 425 by the pump. The first current may substantially correspond to the zero crossing of the AC power supply voltage supplied to the pump. For example, the first current may be the current drawn by the pump when the AC power supply voltage supplied to the pump crosses the zero voltage point, or when the sign of the voltage of the AC voltage changes from negative to positive, but in other examples, this may be the reverse. Alternatively, the first current may be a pre-defined current, in which case the first time point is the time when the current drawn by the pump reaches this pre-defined current. Further, the first current may be the current drawn by the pump measured by analyzing the current drawn by the pump over a rolling time window, where it is measured that the current has increased after passing through the noise-like behavior. Alternatively, the first current may be the current measured by empirically or experimentally analyzing the current characteristics of the electric pump or the pump corresponding to the electric pump.

[0043]

[0043] The second time point 420 may correspond to a time close to the end of a period during which the current drawn by the pump has a substantially constant rate of change, or a time within that period. In other words, the second time point 420 may be at the end of, immediately after, or at a time within a period during which the current drawn by the pump is increasing at a constant rate. Referring to FIG. 4, the second time point 420 corresponds to the end of a period during which the current drawn by the pump has a substantially constant rate of change, and this time point is indicated by 425. As described above, in the example shown in FIG. 4, this second time point 420 and time point 425 correspond to the current drawn by the pump having a value of about 0.3 A, as indicated by time point 430 on the graph. The second time point 420 may be a time measured by performing an empirical or numerical analysis on the current drawn over time by an electric pump or a pump corresponding to the electric pump. Similar to the case of the first time point, the second time point 420 may be measured based on analyzing the current drawn by the pump over a rolling time window.

[0044]

[0044] Furthermore, in some examples, the second time point 420 may be a time measured based on the current drawn by the pump at that time. Specifically, it may be appropriate to ensure that the second time point 420 does not correspond to the current drawn by the pump exceeding a predetermined position on the current curve. This may be appropriate, for example, when allowing for fluctuations in the pressure of the liquid, such as when the pressure is low. This may be relevant in the context of a beverage preparation device, or indeed any machine where the liquid is supplied by a hydraulic connection pipe with low or inconsistent pressure rather than from a built-in reservoir.

[0045]

[0045] In some examples, the second time point 420 may be measured based on the second time point 420 being within a predetermined duration from the first time point 410. As an example, this predetermined duration may be X seconds, and the first time point may correspond to Y seconds. According to this example, the second time point 420 may be determined as a time within or equal to X + Y seconds.

[0046]

[0046] It should be understood that the first time point 410 and the second time point 420 may be measured by measuring the current drawn by the pump. For example, the current meter function may be used to measure the current throughout the operation of the pump. By doing so, the current delay can be measured solely by measuring the current drawn by the pump. This results in an efficient and fast generation of the estimated flow rate.

[0047]

[0047] Alternatively, in some examples, the first time point 410 may be measured based on the measured value of the AC power supply voltage supplied to the pump during the operation of the pump. The second time point 420 may be measured based on the measured value of the current drawn by the pump during the operation period. Therefore, the difference calculated between the first time point and the second time point provides the current delay of the pump. According to this example, referring to FIG. 4, the current delay can be calculated as the difference between the first time point 410 and the second time point 420, for example, by subtracting the first time point 410 from the second time point 420.

[0048]

[0048] In this way, the first time point 410 can be measured by measuring the AC power supply voltage of the pump, for example, by measuring the time corresponding to the zero crossing of the power supply voltage as the first time point. In some cases, as shown in FIG. 4, the current drawn by the pump is irregular and noisy and may be close to zero current. Therefore, if the first current is measured using a predefined current and then the first time point as the time when the pump draws this predefined current is measured, errors are likely to occur. Instead, as described, the measured value of the AC power supply voltage and the zero crossing of this AC power supply voltage can be used. By doing so, the accuracy of the measurement of the first time point 410 can be improved, leading to a more accurate estimation of the flow rate.

[0049]

[0049] As shown in FIG. 4, the current delay can be measured by subtracting the first time point 410 from the second time point 420. So far, the zero crossing of the AC power supply voltage has been referred to as the rising zero crossing, i.e., the zero crossing where the voltage changes from negative to positive. In other examples, the falling zero crossing of the AC power supply voltage, i.e., the falling zero crossing corresponding to the current draw by the pump in the second half of the pump cycle, may be used. In such an approach, the first time point at which the current reaches zero (or substantially zero) can be used as the zero crossing point, so it may be possible to ignore any noise-like behavior around the current zero point. This will be explained by referring to FIG. 4 again. The times labeled 435 and 440 may correspond to the falling zero crossing of the AC power supply voltage supplied to the pump. In this example, the current delay is measured as follows: Current delay = ((440 - 435) / 2) - (440 - 420). In some hardware configurations, measuring the current delay in this way may be more accurate.

[0050]

[0050] In some examples, before method 300 proceeds to volume estimate generation in step S302, current delay measurement may be repeated in step S301 of method 300. Thus, in this example, the volume estimate can be generated based on the average current delay of the pump. In some examples, the current delay is measured for each pump cycle, which may correspond to measuring the current delay approximately every 20 ms, and then, after five current delay measurements, an estimate of the volume can be generated based on the average of the five measured current delays. Thus, in some examples, the volume estimate can be generated every 100 ms, while the current delay can be measured every 20 milliseconds. It should be understood that the number of current delays used for the average can vary.

[0051] [

[0051] ]Referring back to FIG. 3, method 300 may also include steps S301a and S302a in some examples. In step S301a, the average of the AC power supply voltage supplied to the electric pump is determined. The average of the AC power supply voltage may be the power supply voltage supplied from a commercial power supply network or power grid. Thus, in some examples, this average refers to the root mean square of the AC power supply voltage over a period of time. Examples of the average AC power supply voltage that can be supplied to the electric pump include, among others, 110V, 120V, 220V, 230V, and 240V. It should be understood that the average AC power supply voltage supplied to the electric pump may refer to the nominal power supply voltage, i.e., the voltage at the interconnection point between electrical equipment and devices, or the voltage actually utilized by the electric pump. This AC power supply voltage can be measured in several ways, for example, from direct measurements, from measurements of the supply voltage from the power transmission network, or based on the phase cut applied to the supply voltage from the power transmission network.

[0052] [

[0052] ]Step S302a is shown in FIG. 3 as a separately shown step, but it should be understood that step S302a does not represent a further separate step, but rather optionally modifies step S302. In step S302a, an estimated value of the volume of liquid output from the electric pump during the operating period is generated based on the current delay and the average of the AC power supply voltage.

[0053] [

[0053] ]Thus, in this example, the current delay of the pump and the average of the AC power supply voltage supplied to the pump are measured, and the estimated value of the flow rate is generated based on both the current delay and the average of the AC power supply voltage. The inventors of this technique have identified that, as shown in FIG. 2, the correlation between the flow rate and the current delay depends on the power supply voltage, for example, whether 230V, 195V, or 265V is supplied from the power transmission network to the pump. This can be seen in FIG. 5, which shows the relationship between the liquid flow rate or the volume of liquid per unit time and the current delay for different levels of the average AC power supply voltage supplied to the pump. Generally, at a higher power supply voltage, in this case 265V, the average of the measured current flow is smaller.

[0054]

[0054] Thus, in some exemplary methods including steps S301a and S302a, the estimated flow rate value generation is further based on the power supply voltage. By introducing this additional parameter into the estimation method, in some implementations, the accuracy of the flow rate estimation can be further improved.

[0055]

[0055] In some examples, generating an estimated value of the volume of liquid output from the pump is further based on a technique selected from a plurality of techniques, and the selection is based on an indicator of whether the power of the pump during the operation period of the pump exceeds a predefined power threshold.

[0056]

[0056] FIG. 6a shows the power of an electric pump during operation over time. As shown, the power of the pump does not start at 100%, but instead there are ramp-up periods of various durations. In some examples, such as an example related to a beverage preparation device, the power of the pump is intentionally ramped up to the maximum power over a period of time, such as about 7 seconds as shown in FIG. 6a. This may be due to an indicator that a heating operation should be applied to the liquid passing through the pump, for example, to provide a warm beverage. In such a case, the temperature regulation may be such that for a warm beverage, the pump cannot be started at maximum power. This can occur, for example, when the heating of the liquid after output from the pump is performed by a heater and / or a heater with a low heat mass that requires a certain time to reach the full operating temperature (e.g., due to heat loss in the preheating stage). In such a pump ramp-up as shown in FIG. 6a, the cumulative volume of liquid output from the pump exhibits different behaviors at different times.

[0057]

[0057] This behavior is shown in FIG. 6b. During a period corresponding to the pump's power ramp-up period, which is about 7 seconds in this example, the cumulative volume increases at various speeds and at speeds different from when the pump is operating at 100%. Therefore, by taking the pump power into account when selecting the technique used to generate the estimate, a more accurate estimate of the flow rate and volume of the liquid output from the pump over time can be achieved.

[0058]

[0058] For example, one technique among a plurality of techniques may be optimized to generate an estimate when the pump power is below a predetermined amount of the pump's nominal operating power or maximum operating power, such as 100% of the total power or 70% of the total power. Another technique among the plurality of techniques may be optimized to generate an estimate when the pump power is operating near a predetermined power level, such as substantially at 100% or above 70% of a predetermined threshold. Therefore, depending on the pump power, specifically, depending on whether the power exceeds a pre-defined power threshold, by selecting which of the plurality of techniques to use in generating the estimate, a more accurate flow rate estimate can be provided for a particular implementation.

[0059]

[0059] As will be appreciated, the indicator of whether the pump power is above or below a pre-defined threshold can be measured or calculated directly or indirectly. Alternatively, the indicator may be received.

[0060]

[0060] In some examples, generating an estimate of the volume of liquid output from the pump is further based on a technique selected from a plurality of techniques, and the selection is based on an indicator of whether the temperature of the liquid is higher than a pre-defined temperature threshold or whether a heating operation should be applied to the liquid.

[0061]

[0061] As described above, when a heating operation should be applied to the pumped liquid, the pump may need to go through a power ramp-up. Thus, the selection may be based not on an indicator of whether the pump power exceeds a threshold or on a measured or calculated value of the actual pump power, but rather on an indicator that a heating operation should be applied to the liquid. In some cases, this selection may be brought about by the user of the beverage preparation device selecting a warm beverage for preparation. In other cases, the selection may be based on whether the temperature of the liquid is higher than a predefined temperature, and thus it is identified that a heating operation has been applied. In some examples, the temperature can be sensed by a temperature sensor. In other examples, the processing circuit is configured to receive an indicator that a heating operation should be applied to the liquid and select a technique based thereon.

[0062]

[0062] FIG. 7 shows the relationship between the cumulative volume and time for both warm and cold beverages in the context of a beverage preparation device. As shown, the rate of increase of the cumulative volume, i.e., the extraction rate of the liquid, depends on whether the beverage being extracted is warm or cold. In some examples, this can be due to a flow restriction caused by a heater path through which the liquid output from the pump passes to heat the pumped liquid and / or different physical properties of liquids at different temperatures. Thus, it may be appropriate to use separate or different techniques depending on the temperature of the liquid or whether a heating operation should be applied to the liquid, i.e., depending on the final temperature of the liquid.

[0063]

[0063] In some examples, generating an estimate of the volume of liquid output from the pump is further based on a technique selected from a plurality of techniques, and the selection is based on an indicator of whether the duration of the pump operation period is longer than a predefined duration threshold. As described above, instead of receiving an indicator of pump power, or an indicator that a heating operation should be applied, or an indicator of the temperature of the liquid, the selection may be based on the duration of the pump operation, i.e., the length of time the pump has been operating for its extraction or liquid output.

[0064]

[0064] As can be seen from FIG. 6a, in some examples, the pump ramp-up is reliably completed after a 7-second pump operation duration, so it can be expected that the pump is operating at 100% power after 7 seconds. Thus, the pump operation duration can be used as a proxy to indicate that the pump is operating at full power. Different pumps and different actual heating techniques can have different characteristics, so different pump operation durations indicate different full powers of the pump, and the predefined operation duration, which is 7 seconds in this example, will vary accordingly in different implementations.

[0065]

[0065] In some examples, the selection is based on a combination of the above selection criteria. In some examples, the selection is a two-stage selection. First, it is based on whether a heating operation is to be applied, and second, it is based on the pump operation duration. For example, it can first be determined whether a heating operation should be applied to the liquid. This can be determined in response to an indicator of whether the heating operation is to be applied or not. If it is determined that the heating operation should not be applied to the liquid, one of the techniques that may be suitable for cold liquid and / or optimized for cold water may be selected. Alternatively, if it is determined that the heating operation should be applied to the liquid, different techniques (suitable for and / or optimized for warm liquid) may be applied. For example, one technique may be optimized for a first operation period for warm beverages, and a second technique may be optimized for a second period after the first operation period for warm beverages. In other words, if it is determined that the heating operation should be applied to the liquid, the selection is based on the operation duration, i.e., time. In at least some implementations, since temperature regulation and thus the pump ramp-up are expected to be less (or not at all) relevant for cold beverages, a single technique may be suitable for cold beverages.

[0066]

[0066] FIG. 8 schematically shows a method 800 for calculating the cumulative volume of liquid output from an electric pump according to the techniques of the present disclosure. It should be understood that method 800 may operate continuously after method 300. From one perspective, method 300 provides an estimate of the volume output by the pump during a first operating period of the pump, e.g., 100 ms, and then method 800 repeats method 300 during a second operating period of the pump and sums the estimated values of the volume from the first and second operating periods to calculate the total volume of liquid output by the pump during a total period equal to the first and second operating periods.

[0067]

[0067] More specifically, in step S801, in response to determining that a second operation of the electric pump has elapsed, a second current delay of the electric pump is measured and a second estimated value of the volume of liquid output from the pump during the second operating period is generated. Method 300 and related examples may be repeated in step S801. Further, the elapse of the second operating period may be determined based on a timer, e.g., a timer indicating that a predefined period corresponding to the operating period has elapsed. In some examples, the length of the operating period is 100 ms and the first and second operating periods are the same.

[0068]

[0068] In step S802, the total volume of liquid output from the pump during the first and second operating periods is calculated by summing the first estimated value of the volume and the second estimated value of the volume. In this way, the total volume of liquid output can be measured. This calculated total volume may then be used to control the pump, e.g., deactivate the pump when a predetermined total volume is reached. In an example where the above-described method is executed in the context of a beverage preparation device, the beverage preparation device may stop outputting liquid based on determining that the calculated total volume has reached a predetermined threshold. In this example, the predefined threshold may be determined based on user input to the beverage preparation device, e.g., through the selection of a beverage having a predefined volume.

[0069]

[0069] In some examples, generating the second estimated value in step S801 is based on a second technique, and the estimated value from the first operating period is the first technique. This second technique can be selected from a plurality of techniques, for example, a plurality of techniques used to select a technique for the estimated value during the first operating period. In fact, the second technique is an indicator of whether the power of the pump during the second operating period of the pump exceeds a predefined power threshold, whether the temperature of the liquid exceeds a predefined temperature threshold or whether a heating operation should be applied to the liquid, and whether the durations of the first and second operating periods of the pump are longer than a predefined duration threshold. It can be selected from a plurality of techniques based on at least one of them. It should be understood that the predefined power threshold, the predefined temperature, and the predefined duration threshold may be the same or different for the first estimated value and the second estimated value.

[0070]

[0070] Thus, similar to the estimated value of the volume from the first operating period, the second estimated value can use a technique suitable for and / or optimized for the conditions experienced during the second operating period. Thus, in at least some implementations, a more accurate estimated value of the total volume output from the pump over the first and second operating periods can be achieved.

[0071]

[0071] In some examples, the first technique, i.e., the technique associated with generating a first estimate of the volumetric output during a first operation period, is the same as the second technique. For example, if the power of the pump does not cross a predefined power threshold between the first operation period and the second operation period, or if the total duration of the pump operation does not cross a predefined duration threshold, the first and second techniques for the first and second operation periods may be the same. Further, as described above, based on an indication that a heating operation should not be applied to the liquid, the techniques may be the same over the first and second operation periods. In some examples, based on determining that a heating operation should not be applied to the liquid, the second technique is automatically set to the first technique. In the case of a cold liquid, such as a cold beverage, a ramp-up of the pump power is not required, and thus a single technique may be used during the duration of the extraction of the cold liquid.

[0072]

[0072] Alternatively, the first technique and the second technique may be different. For example, the first and second operation periods may span a point at which the power of the pump crosses a predefined power threshold, or a point at which the duration of the pump operation crosses a predefined duration threshold. Thus, the techniques of the present disclosure enable the fine application of various different techniques that are optimal for the situation at that time, and thus enable one of ordinary skill in the art to adapt any given implementation to the particular situation of that implementation, thereby achieving a high-precision estimate of the volume output from the pump.

[0073]

[0073] FIG. 9 schematically shows a method for estimating the volume of liquid output during a second operating period after a first operating period. It should be understood that method 900 can be consecutive after method 300 or method 800. In fact, these methods can be combined in various ways. Although referring to the second operating period as in the case of method 800, these techniques do not have to be mutually exclusive alternatives. Rather, both techniques can be combined such that the two "second" periods can be the same period, or the two "second" periods can be different periods such that one of such "second" periods can conceptually be renamed the "third" period.

[0074]

[0074] The inventors of the present disclosure have identified that, in some cases, the AC power supply voltage can vary over the operating period of the pump. As shown in FIG. 5, current delay and flow rate estimation can depend on the power supply voltage for some electric pumps. Therefore, for a significantly fluctuating AC power supply voltage, a further series of techniques can be developed to improve the accuracy of flow rate / volume estimation. Thus, from one perspective, method 900 takes into account whether the power supply voltage, for example, the nominal power supply voltage (e.g., 230V) or the power supply voltage at the pump, varies outside a predetermined threshold between subsequent periods, and if such a variation occurs, processes accordingly.

[0075]

[0075] More specifically, in the method 900 of this example, following the determination in step S901, steps S902, S903, S904, and S905 can be executed. Specifically, these steps are executed in response to determining that the second operating period of the pump has elapsed and that the difference between the average of the AC power supply voltage in the first operating period and the average of the AC power supply voltage in the second operating period is greater than a predefined difference value. As described above, the AC power supply voltage can be the voltage supplied for use by the pump or the nominal power supply voltage from the commercial power transmission network, and thus can be the AC power supply voltage supplied to the electric pump. This AC power supply voltage can be measured in several ways, for example, from a direct measurement value, from a measurement of the supply voltage from the power transmission network, or based on a phase cut of the supply voltage from the power transmission network. The predefined difference value may be determined based on the percentage of the AC power supply voltage in the first operating period.

[0076]

[0076] In step S902, measure the second current delay of the electric pump. This can be measured as described in this specification.

[0077]

[0077] In step S903, based on the average of the AC power supply voltage in the second operating period and the second technique, generate an estimated value of the second current delay of the electric pump. In this example, the second technique is used to remove the influence of the varying voltage on the current delay and generate an estimated value of the current delay.

[0078]

[0078] In step S904, subtract the estimated value of the second current delay from the second current delay to calculate an adjusted current delay. In other words, calculate a normalized current delay by subtracting the predicted current delay predicted using the second technique from the measured current delay.

[0079]

[0079] In step S905, an estimated value of the volume of the liquid output from the pump during the second operation period is generated based on the adjusted current delay and the third technique. In this example, the third technique may be different from the second technique. The second technique in this example may be different from the second technique described in other examples of this specification.

[0080]

[0080] Therefore, in other words, method 900 provides a technique by which a more accurate estimated value of the volume output from the pump can be determined when the power supply voltage varies significantly, that is, when the power supply voltage is treated as a continuous variable. Depending on the situation and location, for example, it may not be possible to guarantee a power supply voltage that does not vary significantly such as the transmission grid voltage. Therefore, in such situations and locations, this technique can be used in the corresponding implementation forms so as to reduce the adverse effect on the accuracy of flow rate estimation in such situations without the need for a dedicated flow meter.

[0081]

[0081] In some examples, the techniques described herein, the first technique, the second technique, and / or the third technique are one or more trained regression models trained based on performing a regression analysis on training data including the value of the current delay of the test device and the volume of the liquid output by the test device during the operation of the test device, and the test device includes a corresponding pump in a manner related to the electric pump. In some examples, the trained regression model may be a trained linear regression model. Further, as described above, the technique corresponding to the first 7 seconds (or any predetermined period) of extraction may be a model that generates a constant value. For example, in some cases, the first 7 seconds of extraction may be preferably estimated using a constant value, and then, after the duration of 7 seconds has elapsed, a second technique, for example, a trained linear regression model, may be used. It should be understood that this duration is 7 seconds in this example, but may vary depending on the specific implementation form.

[0082]

[0082] In other examples, the technique corresponding to the first 7 seconds (or any predetermined period) of extraction may be a linear regression model. In this example, this first technique may be different from the linear regression model used after the first 7 seconds.

[0083]

[0083] In some examples, a plurality of test devices, such as a test pump or a test beverage preparation device, may be operated with a flow meter to measure the current delay of the pump and generate training data including the measured value of the flow rate and the current delay that can be used to generate an estimated value of the flow rate.

[0084]

[0084] Next, an exemplary trained linear regression model that can correspond to any of the techniques described above will be described. This trained linear regression model may include several determined constant model terms that can be used to calculate the predicted volume of the liquid output from the pump, together with the current delay and the power supply voltage. Specifically, in this example, the predicted volume per unit time = parameter 1 + (parameter 2 × current delay) + (parameter 3 × power supply voltage) + (parameter 4 × current delay × power supply voltage). In this example, parameter 1, parameter 2, parameter 3, and parameter 4 are constant terms identified using linear regression analysis. In this way, the current delay and the power supply voltage are input into the trained linear regression model (i.e., input into the equation as described above) and combined with the determined model parameters to generate an output corresponding to the estimation of the volume output over a certain period. It should be understood that other equations may characterize the linear regression model. The linear regression model described herein refers to one or more model parameters determined from linear regression analysis (i.e., training) and an equation that links the model parameters to input variables and output variables (in this example, the current delay, the power supply voltage, and the volume estimate).

[0085]

[0085] Here, an exemplary method for the selection of a trained linear regression model that can be used as part of any of the techniques described herein will be described. In this example, it is first determined whether a heating operation should be applied to the liquid. For example, this determination can be based on whether a user of a beverage preparation device has selected a warm beverage for preparation. For example, if it is determined that the heating operation is not to be applied because the user has selected a cold beverage, the model can be used to predict the volume of liquid output from the pump as follows: Predicted volume per unit time = Parameter 1 + (Parameter 2 × Current delay) + (Parameter 3 × Supply voltage). In this example, Parameter 1, Parameter 2, and Parameter 3 are constant terms identified using linear regression analysis. If it is determined that the heating operation should be applied to the liquid, then a determination is made as to whether the pump is operating at a predetermined amount or more of the nominal operating power or maximum operating power of the pump, for example, 100% of the total power or 70% of the total power. If it is determined that the pump is operating at this predetermined amount or more, the model can be used to predict the volume of liquid output from the pump as follows: Predicted volume per unit time = Parameter 1 + (Parameter 2 × Current delay) + (Parameter 3 × Supply voltage). In this example, Parameter 1, Parameter 2, and Parameter 3 are constant terms identified using linear regression analysis and may be different from the constant terms associated with a situation where the heating operation should not be applied to the liquid. If it is determined that the pump is operating below this predetermined amount of power, the model can be used to predict the volume of liquid output from the pump as follows: Predicted volume per unit time = Parameter 1 + (Parameter 2 × Pump power) + (Parameter 3 × Elapsed time since extraction start) + (Parameter 4 × Temperature of the liquid). In this example, Parameter 1, Parameter 2, Parameter 3, and Parameter 4 are constant terms identified using linear regression analysis and may be different from the constant terms associated with a situation where the heating operation should not be applied to the liquid or a situation where the pump is operating at a predetermined amount or more of power.

[0086]

[0086] In the above model, the current delay may be a normalized value. Such normalization can be applied to account for physical variations between beverage preparation devices of the same type. For example, in several beverage preparations of the same type, due to variations in performance such as those of pumps, power supply circuits, heaters, etc., there may be variations in behavior between separate devices among those devices. Thus, when manufacturing a given beverage preparation device, normalization can be performed by executing the beverage preparation operation several times at the maximum operating voltage of the device without using beverage preparation ingredients / capsules. In the case of machines designed to operate at commercial voltage in most Western European countries, this can be, for example, 265V. Since the current delay is smallest when the voltage is highest, these beverage preparation operations reveal the smallest possible current delay for the pump of a particular beverage preparation device. Subsequently, the subsequent normalization of the values when applying the model to control the pump during the operational use of the beverage preparation device can be composed of subtracting the smallest possible current delay for the pump of a particular beverage preparation device.

[0087]

[0087] In the above model, the power supply voltage value can be a normalized value. Such normalization can be applied to account for physical variations between beverage preparation devices of the same type. For example, in several beverage preparations of the same type, due to performance variations such as those of pumps, power supply circuits, heaters, etc., there may be variations in behavior between different ones of those devices. Thus, when manufacturing a given beverage preparation device, normalization can be performed by inspecting the voltage measured by a particular beverage preparation device when supplied with control voltages of two or more different voltage values. For example, the voltage measurement of a particular beverage preparation device can be measured at 195V, 230V, and 265V respectively. Next, the offset between the measured voltage at each supply value and the known power supply voltage is determined and can be used to adjust the measured voltage during operation of the beverage preparation device. Such measurements may be performed multiple times at each known power supply voltage, and an average offset may be determined. To account for the possibility that the magnitude of the offset and / or the percentage of the actual power supply voltage may be different at different measurement points, interpolation or fitting may be applied to find the offset value suitable for application at any given measured power supply voltage during operation.

[0088]

[0088] As described, each trained regression model can include one or more predetermined model parameters. Further, generating an estimated value of the volume can include inputting the current delay and the average of the AC power supply voltage supplied to the pump into the trained regression model and performing one or more mathematical operations using the one or more predetermined model parameters, the current delay, and the average of the AC power supply voltage.

[0089]

[0089] As shown in FIG. 10, in step S1001, training data including the value of the current delay of the test device and the volume of the liquid output by the test device during operation of the test device is acquired.

[0090]

[0090] In step S1002, perform a regression analysis on the training data to provide one or more parameters that can be used to estimate the volume of liquid output from the electric pump based on the measured value of the current delay of the electric pump.

[0091]

[0091] In an exemplary method 1000, the test apparatus corresponds to the electric pump, and the current delay is the period between a first time point corresponding to a first current extraction by the test apparatus and a second time point corresponding to a second current extraction by the test apparatus.

[0092]

[0092] In some examples, the test apparatus comprises a plurality of test beverage preparation apparatuses. Training may include operating the machine to perform a predefined number of extractions according to a test protocol that operates the pump over a variety of different set points (e.g., different performances). During this training, there may be a physical flow meter that measures the actual flow rate, and other variables including the current delay are also recorded. This data may be analyzed, and different types of regression models (having different combinations of parameters), in the example, a linear regression model, may be trained to fit the measured flow rate from the physical flow meter. For different regression models (i.e., models having different parameters), performance metrics are compared, for example, the percentage of extractions outside a predefined tolerance compared to the physical flow meter, the regression model is optimized, and a model with appropriate performance (such as the most performant model determined by the relevant operational considerations for any given implementation) is selected for use.

[0093]

[0093] In some examples, evaluating the performance of the selected regression model may include implementing the selected regression model within the firmware of the beverage preparation apparatus. The apparatus can be operated in a state where the electric pump is controlled by the model rather than a physical flow meter, and the physical flow meter can function as a ground truth for the evaluation of the model performance.

[0094]

[0094] This technique can provide an accurate estimation of the volume of liquid output from an electric pump during the operation period of the electric pump. An exemplary plot of the performance of this technique is shown in FIG. 11. Specifically, FIG. 11 shows the relative error for each extraction at different voltages, in this example 195V, 213V, 230V, 247V, and 265V. The relative error is calculated based on comparing the cumulative volume over time between a first device that measures the flow rate using a dedicated flow meter to calculate the cumulative volume, and a second device that estimates the flow rate and the cumulative volume output over time without using a dedicated flow meter but instead using this technique. FIG. 11 shows, as an example, the relative error of repeatedly comparing the volume prediction of the liquid output from the pump using the technique of the present disclosure with a device using a dedicated flow meter that measures the volume of the liquid output from the pump 5438 times. As shown in FIG. 11, among these repetitions, 90% of the volume predictions are within a relative error of ±10%, 96% are within a relative error of ±12%, and 99% are within a relative error of ±15%.

[0095]

[0095] It should be understood that instead of the beverage preparation device 100 of FIG. 1, a liquid dispensing machine may be provided that includes a processing circuit and an electric pump configured to perform the methods described herein.

[0096]

[0096] Thus, from one aspect, a method for estimating the volume of liquid output from an electric pump during the operation period of the electric pump has been described, and this method includes measuring the current delay of the pump, where the current delay is the period between a first time point corresponding to a first current draw by the pump and a second time point corresponding to a second current draw by the pump, and generating an estimated value of the volume of liquid output from the electric pump during the operation period based on the current delay.

[0097]

[0097] Further examples of this approach are presented in the following numbered clauses.

[0098]

[0098] [Clause 1] A method for estimating the volume of liquid output from the electric pump during the operation period of the electric pump, the method comprising measuring a current delay of the pump, wherein the current delay is a period between a first time point corresponding to a first current draw by the pump and a second time point corresponding to a second current draw by the pump, and generating an estimated value of the volume of the liquid output from the electric pump during the operation period based on the current delay.

[0099]

[0099] [Clause 2] The method according to clause 1, wherein the first current substantially corresponds to the zero crossing of the AC power supply voltage supplied to the pump.

[0100]

[0100] [Clause 3] The method according to clause 1 or 2, further comprising determining an average of the AC power supply voltage supplied to the electric pump, and wherein generating the estimated value of the volume is further based on the average of the AC power supply voltage.

[0101]

[0101] [Clause 4] Measuring the current delay of the pump includes measuring the first time point based on a measured value of the AC power supply voltage supplied to the pump during the operation period, measuring the second time point based on a measured value of the current draw by the pump during the operation period, and calculating the difference between the first time point and the second time point as the current delay of the pump. The method according to any one of clauses 1 to 3.

[0102]

[0102] [Clause 5] The method according to any one of clauses 1 to 4, wherein the second time point corresponds to a time close to the end of a period during which the current draw by the pump has a substantially constant rate of change, or a time within the period.

[0103]

[0103] [Clause 6] Generating the estimated value of the volume of the liquid output from the pump is further based on a technique selected from a plurality of techniques, and the selection is based on an index of whether the power of the pump during the operation period of the pump exceeds a predefined power threshold, the method according to any one of Clauses 1 to 5.

[0104]

[0104] [Clause 7] Generating the estimated value of the volume of the liquid output from the pump is further based on a technique selected from a plurality of techniques, and the selection is based on an index of whether the temperature of the liquid is higher than a predefined temperature threshold or whether a heating operation should be applied to the liquid, the method according to Clauses 1 to 5.

[0105]

[0105] [Clause 8] Generating the estimated value of the volume of the liquid output from the pump is further based on a technique selected from a plurality of techniques, and the selection is based on an index of whether the duration of the operation period of the pump is longer than a predefined duration threshold, the method according to Clauses 1 to 5.

[0106]

[0106] [Clause 9] The operation period of the pump is a first operation period, the current delay is a first current delay, the estimated value of the volume is a first estimated value of the volume, and the method includes, in response to determining that a second operation period of the electric pump has elapsed, measuring a second current delay of the electric pump, and based on the second current delay, generating a second estimated value of the volume of the liquid output from the pump during the second operation period, and calculating the total volume of the liquid output from the pump during the first operation period and the second operation period by summing the first estimated value of the volume and the second estimated value of the volume, the method according to Clauses 6 to 8.

[0107]

[0107] [Clause 10] The method according to clause 9, wherein the technique is a first technique, the second estimated value of the volume is generated based on a second technique selected from the plurality of techniques, and the selection is based on at least one of an indicator of whether the power of the pump during the second operating period of the pump exceeds the predefined power threshold, an indicator of whether the temperature of the liquid is higher than the predefined temperature threshold or whether a heating operation should be applied to the liquid, and an indicator of whether the durations of the first operating period and the second operating period of the pump are longer than the predefined duration threshold.

[0108]

[0108] [Clause 11] The method according to clause 10, wherein the first technique and the second technique are the same.

[0109]

[0109] [Clause 12] The method according to clause 10, wherein the first technique and the second technique are different.

[0110]

[0110] [Clause 13] In response to determining that the operating period of the pump is a first operating period, that the second operating period of the pump has elapsed, and that the difference between the average of the AC power supply voltage during the first operating period and the average of the AC power supply voltage during the second operating period is greater than a predefined difference value, measuring a second current delay of the electric pump; generating an estimated value of the second current delay of the electric pump based on the average of the AC power supply voltage during the second operating period and the second technique; subtracting the estimated value of the second current delay from the second current delay to calculate an adjusted current delay; and generating an estimated value of the volume of the liquid output from the pump during the second operating period based on the adjusted current delay and a third technique. The method according to clauses 6 to 8 further includes the above steps.

[0111]

[0111] [Clause 14] The method according to clauses 6 to 13, wherein the technique, the first technique, the second technique, and / or the third technique is a trained regression model trained based on performing a regression analysis on training data including a value of current delay of a test device and a volume of a liquid output by the test device during operation of the test device, and the test device corresponds to the electric pump.

[0112]

[0112] [Clause 15] The trained regression model includes one or more predetermined model parameters, and generating the estimated value of the volume includes inputting the current delay and an average of an AC power supply voltage supplied to the pump into the trained regression model, and performing one or more mathematical operations using the one or more predetermined model parameters, the current delay, and the average of the AC power supply voltage. The method according to clause 14.

[0113]

[0113] [Clause 16] A liquid dispensing machine comprising an electric pump and a processing circuit configured to execute the method according to clauses 1 to 15.

[0114]

[0114] [Clause 17] The liquid dispensing machine according to clause 16, wherein in response to determining that the estimated value of the volume of the liquid output from the pump is equal to a predetermined threshold volume, the liquid dispensing machine is configured to stop dispensing the liquid.

[0115]

[0115] [Clause 18] A computer-readable medium including instructions that, when executed by a programmable liquid dispensing machine, cause the programmable liquid dispensing machine to execute the method according to clauses 1 to 15.

[0116]

[0116] [Article 19] A method for training a regression model for estimating the volume of liquid output from the electric pump during the operation period of the electric pump, the method comprising: obtaining training data including a value of the current delay of the test device and the volume of liquid output by the test device during the operation of the test device, wherein the test device corresponds to the electric pump, and the current delay is a period between a first time point corresponding to a first current extraction by the test device and a second time point corresponding to a second current extraction by the test device; and performing a regression analysis on the training data to provide one or more parameters usable for estimating the volume of the liquid output from the electric pump from the measured value of the current delay of the electric pump.

[0117]

[0117] [Article 20] A beverage preparation device, comprising: a fluid input unit connected to receive a fluid for beverage preparation; an electric pump connected to the fluid input unit and having a control input unit; a current sensor connected to the power connection unit of the electric pump; a beverage preparation output unit connected to receive the fluid dispensed by the electric pump; and a controller connected to the current sensor and the control input unit, wherein the controller is configured to calculate the volume of the dispensed fluid by the electric pump based on the current extraction delay measured by the current sensor and to transmit a control signal to the control input unit to deactivate the electric pump in response to the volume of the fluid reaching a threshold volume.

[0118]

[0118] The above method can be executed under the control of a computer program that is executed in a computing device such as, for example, a programmable beverage preparation apparatus or a programmable liquid dispensing machine. Accordingly, the computer program can include instructions for controlling the computing device to execute any of the methods described above. The program can be incorporated into a computer-readable medium. The computer-readable medium can include non-transitory types of media such as physical storage media, for example, magnetic disks and solid-state devices. The computer-readable medium can include, additionally or alternatively, transitory media such as carrier signals and transmission media that can occur, for example, for communicating instructions between several separate computer systems and / or between components within a single computer system.

[0119]

[0119] Accordingly, the present teachings provide a technique for estimating the flow rate of liquid output by an electric pump so as to provide an accurate estimate without requiring a flow meter. These techniques are based on the use of the current lag of the pump, but can be adapted by using supplementary techniques and methods to address complexities such as variable qualities of liquid temperature, power supply voltage, etc. The estimates obtained by these methods can be used to control when to turn off the pump that is used to dispense a measured amount or a predetermined amount of liquid, which can be useful in a device such as a beverage preparation machine where a defined amount of liquid is specified for any given beverage prepared by the machine.

[0120]

[0120] The various embodiments described herein are presented only to assist in the understanding and teaching of the claimed features. These embodiments are provided only as representative samples of the embodiments and are not comprehensive and / or exclusive. The advantages, embodiments, examples, functions, features, structures, and / or other aspects described herein should not be regarded as limitations to the scope of the disclosure defined by the claims or limitations to the equivalents of the claims, and it should be understood that other embodiments may be utilized and modifications may be made without departing from the scope and / or spirit of the claims.

Claims

1. A method for estimating the volume of liquid output from an electric pump during an operating period of the electric pump, comprising: measuring a current delay of the pump, the current delay being a period between a first time point corresponding to a first current draw by the pump and a second time point corresponding to a second current draw by the pump; generating an estimated value of the volume of the liquid output from the electric pump during the operating period based on the current delay; A method comprising the steps of:

2. The method according to claim 1, wherein the first current substantially corresponds to a zero crossing of an AC power supply voltage supplied to the pump.

3. Further comprising determining an average of an AC power supply voltage supplied to the electric pump, The method according to claim 1 or 2, wherein generating the estimated value of the volume is further based on the average of the AC power supply voltage.

4. Measuring the current delay of the pump comprises: measuring the first time point based on a measured value of an AC power supply voltage supplied to the pump during the operating period; measuring the second time point based on a measured value of a current draw by the pump during the operating period; Calculating a difference between the first time point and the second time point as the current delay of the pump. The method according to any one of claims 1 to 3.

5. The method according to any one of claims 1 to 4, wherein the second time point corresponds to a time near the end of a period during which the current draw by the pump has a substantially constant rate of change, or a time within the period.

6. Generating the estimated value of the volume of the liquid output from the pump is further based on a technique selected from a plurality of techniques, the selection being based on an indicator of whether the power of the pump during the operating period of the pump exceeds a predefined power threshold, and / or Generating the estimated value of the volume of the liquid output from the pump is further based on a technique selected from a plurality of techniques, the selection being based on an indicator of whether the temperature of the liquid is higher than a predefined temperature threshold, or whether a heating operation should be applied to the liquid, and / or Generating the estimated value of the volume of the liquid output from the pump is further based on a technique selected from a plurality of techniques, and the selection is based on an indicator as to whether the duration of the operation period of the pump is longer than a predefined duration threshold. The method according to any one of claims 1 to 5.

7. The operation period of the pump is a first operation period, the current delay is a first current delay, the estimated value of the volume is a first estimated value of the volume, and the method is In response to determining that a second operation period of the electric pump has elapsed, measuring a second current delay of the electric pump, and based on the second current delay, during the second operation period Generating a second estimated value of the volume of the liquid output from the pump; Calculating the total volume of the liquid output from the pump during the first operation period and the second operation period by summing the first estimated value of the volume and the second estimated value of the volume; The method according to claim 6, further comprising:

8. The technique is a first technique, The second estimated value of the volume is generated based on a second technique selected from the plurality of techniques, and the selection is An indicator as to whether the power of the pump during the second operation period of the pump exceeds the predefined power threshold, An indicator as to whether the temperature of the liquid is higher than a predefined temperature threshold or whether a heating operation should be applied to the liquid, and Based on at least one of an indicator as to whether the durations of the first operation period and the second operation period of the pump are longer than a predefined duration threshold, Optionally, the first technique and the second technique are the same or different. The method according to claim 7.

9. The operation period of the pump is a first operation period, In response to determining that the second operation period of the pump has elapsed and that the difference between the average of the AC power supply voltage in the first operation period and the average of the AC power supply voltage in the second operation period is greater than a predefined difference value, Measuring a second current delay of the electric pump; Generating an estimated value of the second current delay of the electric pump based on the average of the AC power supply voltage in the second operation period and a second technique; Subtracting the estimated value of the second current delay from the second current delay to calculate an adjusted current delay; Generating an estimated value of the volume of the liquid output from the pump during the second operating period based on the adjusted current delay and a third technique; The method according to claim 6, further comprising.

10. The technique, the first technique, the second technique, and / or the third technique is a trained regression model trained based on performing a regression analysis on training data including a value of a current delay of a test device and a volume of liquid output by the test device during operation of the test device; The method according to any one of claims 6 to 9, wherein the test device corresponds to the electric pump.

11. The trained regression model includes one or more predetermined model parameters, Generating the estimated value of the volume, Inputting the current delay and an average of an AC power supply voltage supplied to the pump into the trained regression model; The method according to claim 10, comprising: performing one or more mathematical operations using the one or more predetermined model parameters, the current delay, and the average of the AC power supply voltage.

12. A liquid dispensing machine comprising an electric pump and a processing circuit configured to perform the method according to any one of claims 1 to 11.

13. The liquid dispensing machine according to claim 12, wherein in response to determining that the estimated value of the volume of the liquid output from the pump is equal to a predetermined threshold volume, the liquid dispensing machine is configured to stop dispensing the liquid.

14. A computer-readable medium including instructions that, when executed by a programmable liquid dispensing machine, cause the programmable liquid dispensing machine to perform the method according to any one of claims 1 to 11.

15. A method for training a regression model for estimating a volume of liquid output from an electric pump during an operating period of the electric pump, the model comprising: Obtaining training data including a value of a current delay of a test device and a volume of liquid output by the test device during operation of the test device, The test device corresponding to the electric pump, Obtaining training data, wherein the current delay is a period between a first time point corresponding to a first current extraction by the test device and a second time point corresponding to a second current extraction by the test device; Performing a regression analysis on the training data to provide one or more parameters that can be used to estimate the volume of the liquid output from the electric pump from the measured value of the current delay of the electric pump; A method comprising.

Images