Method and device for calibrating liquid flow in a peristaltic pump

Abstract

The application discloses a kind of peristaltic pump inner liquid flow's calibration method and device, the method includes: initialization calibration peristaltic pump;By liquid detection data, the actual delivery of the detection liquid in current peristaltic pump is obtained, and the flow deviation is calculated according to the initial liquid flow of peristaltic pump and actual delivery;The number of times of detecting continuous flow deviation, if the number of times of continuous flow deviation exceeds set threshold, then dynamically adjust the motor step number in peristaltic pump;According to historical residual data, LSTM network prediction model is established, motor step number compensation factor is calculated, and compensation factor is superimposed to the motor step number after dynamic adjustment, and target motor step number is obtained.The scheme can solve the error problem caused by aging and residual, realize accurate calibration, and also has the advantages of automatic adjustment, high calibration efficiency.

Description

Technical Field

[0001] This invention relates to peristaltic pumps, and more particularly to a method, apparatus, system, and readable storage medium for calibrating the liquid flow rate within a peristaltic pump. Background Technology

[0002] A peristaltic pump is a pumping device that combines the characteristics of a constant flow pump and a flexible hose pump. Due to its good liquid delivery accuracy, it is widely used in pharmaceuticals, chemicals, beverages, scientific research, and other application fields. However, over long-term use, the delivery accuracy of peristaltic pumps decreases due to internal mechanical aging and liquid residue, directly affecting the accuracy of test results. Traditional solutions rely on manual intervention or external sensors (such as pressure sensors), while POCT (point-of-care testing) equipment, due to size limitations, typically only has liquid detection capabilities and cannot integrate additional sensors. Static calibration methods cannot adapt to the dynamic changes in peristaltic pump performance, leading to frequent maintenance and high costs.

[0003] In view of this, it is necessary to propose an improved method for detecting the delivery accuracy of liquid flow in a peristaltic pump. Summary of the Invention

[0004] To solve at least one of the above-mentioned technical problems, the main objective of this invention is to provide a method and apparatus for calibrating the liquid flow rate in a peristaltic pump.

[0005] To achieve the above objectives, one technical solution adopted by the present invention is: providing a method for calibrating the liquid flow rate in a peristaltic pump, comprising:

[0006] Initialize and calibrate the peristaltic pump;

[0007] The actual volume of liquid being tested in the peristaltic pump is obtained by measuring the liquid test data, and the flow deviation is calculated based on the initial liquid flow rate and the actual volume being tested in the peristaltic pump.

[0008] The number of consecutive flow deviations is detected. If the number of consecutive flow deviations exceeds the set threshold, the number of motor steps in the peristaltic pump is dynamically adjusted.

[0009] An LSTM network prediction model is established based on historical residual data. The motor step count compensation factor is calculated and then superimposed on the dynamically adjusted motor step count to obtain the target motor step count.

[0010] Specifically, the initial calibration of the peristaltic pump includes:

[0011] Establish an initial flow model for the peristaltic pump.

[0012] Q = k·N·f(η,t)

[0013] Where Q is the flow rate, N is the number of motor steps, f(η,t) is the peristaltic pump attenuation model, η is the pump efficiency coefficient, t is the usage time, and k is the comprehensive coefficient;

[0014] Ideal flow rate is calculated based on Poiseuille's law and then modified into a multi-parameter coupled model.

[0015] Q=128LπD·μΔP·η(t)·N0N·(1-αe-βt)

[0016] η(t)=η0·(1-γt)

[0017] Where D is the inner diameter of the hose, L is the length of the pressure section, ΔP is the pressure difference, μ is the fluid viscosity, η(t) is the time decay term, representing the efficiency decrease caused by hose aging, γ is the material fatigue coefficient, N0 is the relationship between the initial number of steps and the flow rate, α is the error compensation coefficient, e is the error signal, β is the time compensation coefficient, and t is the time.

[0018] Under standard viscosity liquid conditions, the sensitivity coefficients of D, L, and μ to Q were determined separately using the controlled variable method, and finally combined into a comprehensive coefficient k.

[0019] Specifically, the liquid test data includes: reaction time, electrochemical signal, and optical intensity of electrolytes, metabolites, blood gas and blood oxygen detection reagents.

[0020] Wherein, the liquid detection data is the reaction time difference of the electrolyte detection reagent, and the step of obtaining the actual delivery volume of the detection liquid in the peristaltic pump through the liquid detection data, and calculating the flow deviation based on the initial liquid flow rate and the actual delivery volume of the peristaltic pump, includes:

[0021] The reaction time of the electrolyte detection reagent was calibrated to determine the relationship between the reaction time and flow rate in the reagent colorimetric method.

[0022] T ref =QV chamber

[0023] Among them, T ref Where Q is the reaction time, and V is the flow rate. chamber The volume of the reaction chamber.

[0024] Calculate the actual reaction time and determine the actual flow rate.

[0025] Q actual =T actual V chamber

[0026] Among them, Q actual For actual traffic, T actual V represents the actual reaction time. chamber The volume of the reaction chamber.

[0027] Calculate the flow deviation.

[0028] ΔQ=Q t heory-Q actua l=k·N·f(μ,t)-T actual V chamber

[0029] Where ΔQ is the flow deviation, Q theory Where N is the theoretical flow rate and N is the number of motor steps.

[0030] The threshold for the number of times continuous flow deviation is detected is three.

[0031] The dynamic adjustment of the motor steps within the peristaltic pump includes: updating the peristaltic pump efficiency coefficient using a recursive least squares method and recalculating the motor steps.

[0032] N new =k v ·η^(t)·f(μ,t)Q target

[0033] Where, k v For the comprehensive correction coefficient, η^(t) is the peristaltic pump efficiency coefficient updated online using the recursive least squares method, f(μ,t) is the motor-flow transfer function, μ is the motor type, t is the time parameter, and Q... target For target traffic.

[0034] The step of establishing an LSTM network prediction model based on historical residual data, calculating a motor step count compensation factor, and then adding the compensation factor to the dynamically adjusted motor step count includes:

[0035] Obtain the historical delivery step sequence of the peristaltic pump and the corresponding measured residual sequence, and train an LSTM network prediction model.

[0036] The residual amount is predicted based on the current delivery step sequence of the peristaltic pump using an LSTM network prediction model.

[0037] Calculate the motor step count compensation factor.

[0038] C residual =Q per_step R^t·ξ

[0039] Among them, C residual Q is the motor step count compensation factor. per_step R^t represents the theoretical flow rate for a single step, R^t represents the residual amount, and ξ represents the safety factor.

[0040] To achieve the above objectives, another technical solution adopted by the present invention is: providing a calibration device for the liquid flow rate inside a peristaltic pump, comprising:

[0041] The initialization module is configured to initialize and calibrate the peristaltic pump.

[0042] The calculation module is configured to obtain the actual delivery volume of the detected liquid in the current peristaltic pump through liquid detection data, and calculate the flow deviation based on the initial liquid flow rate of the peristaltic pump and the actual delivery volume;

[0043] The adjustment module is configured to detect the number of consecutive flow deviations. If the number of consecutive flow deviations exceeds a set threshold, the number of motor steps in the peristaltic pump will be dynamically adjusted.

[0044] The compensation module is configured to build an LSTM network prediction model based on historical residual data, calculate the motor step compensation factor, and superimpose the compensation factor onto the dynamically adjusted motor step count to obtain the target motor step count.

[0045] To achieve the above objectives, another technical solution adopted by the present invention is to provide a peristaltic pump calibration system, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the steps in the above method.

[0046] To achieve the above objectives, another technical solution adopted by the present invention is to provide a readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the steps in the above method are implemented.

[0047] The technical solution of this invention first initializes and calibrates the peristaltic pump, then obtains the actual liquid delivery volume within the pump using liquid detection data, calculates the flow deviation based on the initial liquid flow rate and the actual delivery volume, and then detects the number of consecutive flow deviations. If the number of consecutive flow deviations exceeds a set threshold, the motor step count within the pump is dynamically adjusted. Finally, an LSTM network prediction model is established based on historical residual data to calculate a motor step count compensation factor, which is then superimposed on the dynamically adjusted motor step count to obtain the target motor step count. This allows for real-time and accurate calibration of the peristaltic pump's liquid delivery volume, addressing errors caused by pump aging and liquid residue. Furthermore, it eliminates the need for manual operation, achieving automated calibration and improving calibration efficiency. In summary, this solution calibrates the liquid delivery flow rate of a peristaltic pump without external sensors, corrects the motor step count in real-time using liquid detection data, solves errors caused by aging and residue, and offers the advantages of automated calibration and high efficiency. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0049] Figure 1 This is a schematic flowchart of a method for calibrating the liquid flow rate inside a peristaltic pump according to an embodiment of the present invention;

[0050] Figure 2 This is a block diagram of a calibration device for liquid flow rate inside a peristaltic pump according to an embodiment of the present invention;

[0051] Figure 3 This is a block diagram of a peristaltic pump calibration system according to an embodiment of the present invention.

[0052] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0054] It should be noted that the descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0055] Unlike existing technologies where aging and residual liquid in peristaltic pumps cause errors in liquid delivery, this solution proposes a calibration method for the liquid flow rate within a peristaltic pump. This method aims to simultaneously address the errors in liquid delivery caused by both aging and residual liquid. The specific steps of this calibration method are detailed in the following embodiment.

[0056] Please refer to Figure 1 , Figure 1This is a schematic flowchart illustrating a method for calibrating the liquid flow rate within a peristaltic pump according to an embodiment of the present invention. In this embodiment, the method for calibrating the liquid flow rate within the peristaltic pump includes the following steps:

[0057] S110. Initialize and calibrate the peristaltic pump. When the peristaltic pump is working, it controls the delivery of liquid by controlling the number of motor steps inside. With long-term operation, the peristaltic pump is prone to aging, which will cause the accuracy of the motor step control to gradually decrease. In order to facilitate dynamic adjustment of the motor step count of the peristaltic pump, it is necessary to initialize and calibrate the peristaltic pump and establish a corresponding flow model for the peristaltic pump.

[0058] S120. Obtain the actual delivery volume of the detected liquid in the peristaltic pump using the liquid detection data, and calculate the flow deviation based on the initial liquid flow rate and the actual delivery volume of the peristaltic pump. The liquid detection data corresponds to the liquid flow rate in the peristaltic pump, which is the actual delivery volume of the peristaltic pump. In this step, the liquid detection result is used as the sole input source to achieve closed-loop calibration, breaking through the limitations of traditional sensor-dependent calibration. Specifically, in devices with only liquid detection function (no flow / pressure sensor), the actual flow deviation (ΔQ) is inferred from indirect data such as reagent reaction time difference and optical signal change rate, breaking through the hardware dependence of traditional calibration. In this process, it is necessary to establish a high-precision mapping model between the liquid detection signal and the flow rate, for example, by experimentally calibrating k. reaction coefficient.

[0059] S130. Detect the number of continuous flow deviations. If the number of continuous flow deviations exceeds a set threshold, dynamically adjust the motor step count of the peristaltic pump. When the detected number of continuous flow deviations is less than or equal to the set threshold, there is no need to adjust the motor step count of the peristaltic pump; in this case, the system automatically detects the number of continuous flow deviations again. When the number of continuous flow deviations exceeds the set threshold, dynamically adjust the motor step count of the peristaltic pump to overcome the problem of peristaltic pump aging affecting its delivery capacity.

[0060] Understandably, the number of consecutive flow deviations mentioned above can be selected according to actual requirements, such as the average number over a period of time, or if the number of flow deviations is too large in a short period of time. The threshold can be flexibly selected according to actual design requirements, such as four or five times, etc., and there is no restriction here.

[0061] S140. Based on historical residual data, an LSTM network prediction model is established to calculate the motor step compensation factor. This compensation factor is then added to the dynamically adjusted motor step count to obtain the target motor step count. An LSTM (Long Short-Term Memory) network prediction model is established based on the historical residual data of the peristaltic pump to predict the residual liquid flow rate. The motor step compensation factor is then calculated and added to the adjusted motor step count to obtain the target motor step count. This overcomes the impact of historical residual liquid accumulation on the peristaltic pump's liquid delivery capacity. Furthermore, the LSTM network algorithm's memory footprint is compressed to less than 50KB, making it compatible with low-performance processors (such as Cortex-M4) and ensuring real-time operation in POCT equipment.

[0062] In summary, this solution can resolve calibration inaccuracies caused by the coupling of multiple factors by using aging compensation and residual compensation of the peristaltic pump.

[0063] In one specific embodiment, the initial calibration of the peristaltic pump specifically includes:

[0064] Establish an initial flow model for the peristaltic pump.

[0065] Q = k·N·f(η,t)

[0066] Where Q is the flow rate, N is the number of motor steps, f(η,t) is the peristaltic pump attenuation model, η is the pump efficiency coefficient, t is the usage time, and k is the comprehensive coefficient;

[0067] Ideal flow rate is calculated based on Poiseuille's law and then modified into a multi-parameter coupled model.

[0068] Q=128LπD·μΔP·η(t)·N0N·(1-αe-βt)

[0069] η(t)=η0·(1-γt)

[0070] Where D is the inner diameter of the hose, L is the length of the pressure section, ΔP is the pressure difference, μ is the fluid viscosity, η(t) is the time decay term, representing the efficiency decrease caused by hose aging, γ is the material fatigue coefficient, N0 is the relationship between the initial number of steps and the flow rate, α is the error compensation coefficient, e is the error signal, β is the time compensation coefficient, and t is the time.

[0071] Under standard viscosity liquid (such as physiological saline), the sensitivity coefficients of D, L, and μ to Q were determined separately by the controlled variable method, and finally combined into a comprehensive coefficient k.

[0072] In this step, by introducing the efficiency decay model f(η,t) of the peristaltic pump, the aging of the peristaltic pump can be addressed, avoiding the impact of aging on the accuracy of its liquid delivery. The sensitivity coefficients of D, L, and μ to Q are determined separately using the controlled variable method. Specifically, the sensitivity coefficient of Q can be tested by selecting different hose inner diameters D, different pressure section lengths L, and different fluid viscosities u. Finally, these are combined into a comprehensive coefficient k.

[0073] In one specific embodiment, the types of liquid test data specifically include: reaction times, electrochemical signals, and optical intensity of electrolytes, metabolites, blood gas and blood oxygenation detection reagents. It is understood that this liquid test data can be selected based on the mapping relationship between other data and flow rates, and no limitation is imposed here.

[0074] Specifically, the liquid detection data is the reaction time difference of the electrolyte detection reagent. The step of obtaining the actual delivery volume of the detection liquid in the peristaltic pump using the liquid detection data, and calculating the flow deviation based on the initial liquid flow rate and the actual delivery volume of the peristaltic pump, includes:

[0075] The reaction time T for calibrating electrolyte detection reagents ref Determine the reaction time T using the reagent colorimetric method. ref Relationship with flow Q

[0076] T ref =QV chamber

[0077] Among them, T ref Where Q is the reaction time, and V is the flow rate. chamber The volume of the reaction chamber.

[0078] Calculate the actual reaction time T actual And determine the actual flow rate Q actual ,

[0079] Q actual =T actual V chamber

[0080] Among them, Q actual For actual traffic, T actual V represents the actual reaction time. chamber The volume of the reaction chamber.

[0081] Calculate the flow deviation.

[0082] ΔQ=Q theory -Q actual =k·N·f(μ,t)-T actual V chamber

[0083] Where ΔQ is the flow deviation, Q theory Where N is the theoretical flow rate and N is the number of motor steps.

[0084] In this step, the reaction time T for the reagent colorimetric method is... ref The flow rate Q can be calibrated experimentally using k. reaction A coefficient is used to determine the high-precision mapping relationship between liquid test data and flow rate. Then, combined with the flow rate model of the peristaltic pump constructed earlier, the flow rate deviation can be calculated.

[0085] Specifically, the threshold for the number of consecutive flow deviations detected is three. This threshold can be flexibly selected according to actual requirements; that is, the threshold can be more than three or less than three.

[0086] In one specific embodiment, the dynamic adjustment of the motor steps within the peristaltic pump includes: updating the peristaltic pump efficiency coefficient using a recursive least squares method and recalculating the motor steps.

[0087] N new =k v ·η^(t)·f(μ,t)Q target

[0088] Where, k v The comprehensive correction factor includes motor step angle error (e.g., 0.045% step-1) and gearbox transmission ratio fluctuation. η^(t) is the peristaltic pump efficiency coefficient updated online via recursive least squares method. f(μ,t) is the motor-flow transfer function, where μ is the motor type, t is the time parameter, and Q... target For target traffic.

[0089] Among the parameters mentioned above, the iterative formula for η^(t) is as follows:

[0090] η^(t)=η^(t-1)+λ+φ(t)TP(t-1)φ(t)P(t-1)·φ(t)·ΔQ

[0091] Where φ(t) is the observation vector (a linear combination of N, μ, and t), λ is the forgetting factor (recommended 0.95-0.99), T is the row vector coefficient, and TP(t-1) is the inverse matrix of P(t-1), which is the error covariance matrix.

[0092] In an update example, if the current η0 = 0.92 and ΔQ = +8% is detected, then after the update,

[0093] η new =0.92×(1-0.08 / 1.08)≈0.85,

[0094] The number of motor steps N (the number of motor steps in the flow model) can be corrected in reverse.

[0095] This step updates the peristaltic pump efficiency coefficient using the recursive least squares method and recalculates the motor steps, which can solve the problem of peristaltic pump aging affecting the accuracy of liquid delivery.

[0096] In one specific embodiment, the step of establishing an LSTM network prediction model based on historical residual data, calculating a motor step count compensation factor, and superimposing the compensation factor onto the dynamically adjusted motor step count includes:

[0097] Obtain the historical delivery step sequence of the peristaltic pump and the corresponding measured residual sequence, and train an LSTM network prediction model.

[0098] The residual amount is predicted based on the current delivery step sequence of the peristaltic pump using an LSTM network prediction model.

[0099] Calculate the motor step count compensation factor.

[0100] C residual =Q per_step R^t·ξ

[0101] Among them, C residual Q is the motor step count compensation factor. per_step R^t is the theoretical conveying capacity for a single step, ξ is the residual amount, and ξ is the safety factor.

[0102] In this step, the historical delivery step sequence {N1, N2, ..., Nt-1} of the peristaltic pump motor is acquired, along with the measured residual sequence {R1, R2, ..., Rt-1}. This residual sequence can be used to train an LSTM network prediction model via a weighing sensor or conductivity detector. The LSTM network prediction model consists of an input layer, hidden layers, and an output layer. The input layer has a step sequence with 10 time steps (sliding window), the hidden layer has two LSTM layers (32 units per layer), Dropout = 0.2, and the output layer predicts the residual amount R^t. The LSTM network prediction model predicts the residual amount based on the current delivery step sequence of the peristaltic pump and calculates a motor step compensation factor. This compensation factor is then superimposed with the motor step count adjusted during peristaltic pump aging to obtain the target motor step count. This compensation factor, as compensation for accumulated historical residuals, further improves the calibration accuracy of the peristaltic pump.

[0103] Please refer to Figure 2 , Figure 2 This is a block diagram of a calibration device for the liquid flow rate inside a peristaltic pump according to an embodiment of the present invention. In this embodiment, the calibration device for the liquid flow rate inside the peristaltic pump includes:

[0104] Initialization module 110 is configured to initialize and calibrate the peristaltic pump;

[0105] The calculation module 120 is configured to obtain the actual delivery volume of the detected liquid in the current peristaltic pump through liquid detection data, and calculate the flow deviation based on the initial liquid flow rate of the peristaltic pump and the actual delivery volume.

[0106] The adjustment module 130 is configured to detect the number of continuous flow deviations. If the number of continuous flow deviations exceeds a set threshold, the number of motor steps in the peristaltic pump will be dynamically adjusted.

[0107] The compensation module 140 is configured to establish an LSTM network prediction model based on historical residual data, calculate the motor step compensation factor, and superimpose the compensation factor onto the dynamically adjusted motor step count to obtain the target motor step count.

[0108] Please see Figure 3 , Figure 3 This is a block diagram of a peristaltic pump calibration system according to an embodiment of the present invention. This peristaltic pump calibration system can be used to implement the calibration method for the liquid flow rate within the peristaltic pump described in the aforementioned embodiment. Figure 3 As shown, the peristaltic pump calibration system includes a memory 301, a processor 302, a bus 303, and a computer program stored in the memory 301 and executable on the processor 302. The memory 301 and the processor 302 are connected via the bus 303. When the processor 302 executes the computer program, it implements the functions described in the foregoing embodiments. The number of processors can be one or more.

[0109] The memory 301 can be a high-speed random access memory (RAM) or a non-volatile memory, such as a disk storage device. The memory 301 is used to store executable program code, and the processor 302 is coupled to the memory 301.

[0110] Furthermore, embodiments of this application also provide a computer-readable storage medium, which may be disposed in the peristaltic pump calibration system of the above embodiments, and the computer-readable storage medium may be the aforementioned... Figure 3 The memory in the illustrated embodiment.

[0111] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method for calibrating the liquid flow rate within the peristaltic pump described in the foregoing embodiments. Furthermore, the computer-readable storage medium can also be various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), RAM, magnetic disk, or optical disk.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0113] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0114] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0115] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0116] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0117] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0118] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for calibrating the liquid flow rate in a peristaltic pump, characterized in that, The calibration method for the liquid flow rate in the peristaltic pump includes: Initialize and calibrate the peristaltic pump, specifically including: Establish an initial flow model for the peristaltic pump. Q = k N f ( η , t ) in, Q For traffic, N This represents the number of motor steps. f ( η , t This is a peristaltic pump attenuation model. η The pump efficiency coefficient. t For usage duration, k This is a comprehensive coefficient; Ideal flow rate is calculated based on Poiseuille's law and then modified into a multi-parameter coupled model. Q =128 LπD μ D P η ( t ) N 0 N (1 αe βt ) η ( t )= η 0 (1 γt ) in, D The inner diameter of the hose. L Δ is the length of the compressed section. P For pressure difference, μ For fluid viscosity, η ( t The term ) represents the time decay, indicating the efficiency decrease caused by hose aging. γ The fatigue coefficient of the material. N 0 represents the initial step count and its correspondence with the flow rate. α This is the error compensation coefficient. e For error signals, β This is the time compensation coefficient. t For time; Under standard viscosity liquid conditions, measurements were performed using the controlled variable method. D , L , μ right Q The sensitivity coefficients are ultimately combined into a comprehensive coefficient. k ; The actual volume of liquid being tested in the peristaltic pump is obtained by measuring the liquid test data, and the flow deviation is calculated based on the initial liquid flow rate and the actual volume being tested in the peristaltic pump. The system detects the number of consecutive flow rate deviations. If the number of consecutive flow rate deviations exceeds a set threshold, the motor step count within the peristaltic pump is dynamically adjusted. Specifically, this includes updating the peristaltic pump efficiency coefficient using a recursive least squares method and recalculating the motor step count. Nnew=k v η^(t) f(μ,t)Q target in, k v For comprehensive correction factors, η^(t) The peristaltic pump efficiency coefficient is updated online using the recursive least squares method. f (μ,t) For motor-flow transfer function, μ Motor type t For time parameters, Q target For target traffic; An LSTM network prediction model is established based on historical residual data. The motor step count compensation factor is calculated and superimposed on the dynamically adjusted motor step count to obtain the target motor step count. Specifically, this includes obtaining the historical delivery step count sequence of the peristaltic pump and the corresponding measured residual sequence and training the LSTM network prediction model. The residual amount is predicted based on the current delivery step sequence of the peristaltic pump using an LSTM network prediction model. Calculate the motor step count compensation factor. Cresidual = Q per_step R ^ t ξ in, Cresidual This is the motor step count compensation factor. Q per_step To deliver flow rate for single-step theory, R ^ t This is the residual amount. ξ This is for the safety factor.

2. The calibration method for liquid flow rate in a peristaltic pump as described in claim 1, characterized in that, The liquid test data specifically includes: the reaction time, electrochemical signal, and optical intensity of electrolytes, metabolites, blood gas and blood oxygen detection reagents.

3. The calibration method for liquid flow rate in a peristaltic pump as described in claim 2, characterized in that, The liquid detection data is the reaction time difference of the electrolyte detection reagent. The step of obtaining the actual delivery volume of the detection liquid in the peristaltic pump using the liquid detection data, and calculating the flow deviation based on the initial liquid flow rate and the actual delivery volume of the peristaltic pump, includes: The reaction time of the electrolyte detection reagent was calibrated to determine the relationship between the reaction time and flow rate in the reagent colorimetric method. Tref = QV chamber in, Tref For reaction time, Q For traffic, Vchamber The volume of the reaction chamber. Calculate the actual reaction time and determine the actual flow rate. Qactual = T actual V chamber in, Qactual This represents the actual traffic volume. T actual This is the actual reaction time. Vchamber The volume of the reaction chamber. Calculate the flow deviation. D Q = Qtheory Qactual = k N f ( μ , t ) T actual V chamber Where, Δ Q For flow deviation, Qtheory Where N is the theoretical flow rate and N is the number of motor steps.

4. The calibration method for liquid flow rate in a peristaltic pump as described in claim 1, characterized in that, The threshold for the number of times continuous flow deviation is detected is three.

5. A calibration device for liquid flow rate in a peristaltic pump, characterized in that, The calibration device for the liquid flow rate inside the peristaltic pump includes: The initialization module, configured to initialize and calibrate the peristaltic pump, specifically includes: Establish an initial flow model for the peristaltic pump. Q = k N f ( η , t ) in, Q For traffic, N This represents the number of motor steps. f ( η , t This is a peristaltic pump attenuation model. η The pump efficiency coefficient. t For usage duration, k This is a comprehensive coefficient; Ideal flow rate is calculated based on Poiseuille's law and then modified into a multi-parameter coupled model. Q =128 LπD μ D P η ( t ) N 0 N (1 αe βt ) η ( t )= η 0 (1 γt ) in, D The inner diameter of the hose. L Δ is the length of the compressed section. P For pressure difference, μ For fluid viscosity, η ( t The term ) represents the time decay, indicating the efficiency decrease caused by hose aging. γ The fatigue coefficient of the material. N 0 represents the initial step count and its correspondence with the flow rate. α This is the error compensation coefficient. e For error signals, β This is the time compensation coefficient. t For time; Under standard viscosity liquid conditions, measurements were performed using the controlled variable method. D , L , μ right Q The sensitivity coefficients are ultimately combined into a comprehensive coefficient. k ; The calculation module is configured to obtain the actual delivery volume of the detected liquid in the current peristaltic pump through liquid detection data, and calculate the flow deviation based on the initial liquid flow rate of the peristaltic pump and the actual delivery volume; The adjustment module is configured to detect the number of consecutive flow deviations. If the number of consecutive flow deviations exceeds a set threshold, the motor step count within the peristaltic pump is dynamically adjusted. Specifically, this includes updating the peristaltic pump efficiency coefficient using a recursive least squares method and recalculating the motor step count. Nnew=k v η^(t) f(μ,t)Q target in, k v For comprehensive correction factors, η^(t) The peristaltic pump efficiency coefficient is updated online using the recursive least squares method. f (μ,t) For motor-flow transfer function, μ Motor type t For time parameters, Q target For target traffic; The compensation module is configured to build an LSTM network prediction model based on historical residual data, calculate the motor step compensation factor, and superimpose the compensation factor onto the dynamically adjusted motor step number to obtain the target motor step number. Specifically, it includes obtaining the historical delivery step sequence of the peristaltic pump and the corresponding measured residual sequence and training the LSTM network prediction model. The residual amount is predicted based on the current delivery step sequence of the peristaltic pump using an LSTM network prediction model. Calculate the motor step count compensation factor. Cresidual = Q per_step R ^ t ξ in, Cresidual This is the motor step count compensation factor. Q per_step To deliver flow rate for single-step theory, R ^ t This is the residual amount. ξ For safety reasons, the calibration device for the liquid flow rate inside the peristaltic pump is used to implement the steps in the method according to any one of claims 1-4.

6. A peristaltic pump calibration system, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the steps of the method according to any one of claims 1-4.

7. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-4.

Images