Apparatus and method for controlling flow rate of pulsating pump

Abstract

An apparatus for controlling a flow rate of a pulsating pump according to an embodiment of the present invention comprises: a servo motor; an actuator; a piston; and a control unit, wherein the servo motor is connected to a linear actuator, which pushes a piston to perform pumping, and the control unit generates a desired flow rate by using a fixed piston diameter and an internal volume of a cylinder to control the longitudinal movement of the piston.

Description

Flow control device and method for a pulsating pump

[0001] The present disclosure relates to a flow control device and method for a pulsating pump, and more particularly, to a flow control device and method capable of producing a desired flow rate by controlling the longitudinal movement of a piston using a fixed piston diameter and the internal volume of a cylinder.

[0002] Unless otherwise indicated herein, the materials described in this section are not prior art to the claims of this application, and their inclusion in this section is not intended to be admitted as prior art.

[0003] A pulsatile pump is a pump that moves fluid through a pulsating motion of periodic compression and expansion. Pulsatile pumps are primarily used in medical and life science fields related to the movement of biological fluids and blood circulation. Pulsatile pumps effectively move fluids from specific areas by inducing a regular, periodic pulsatile motion.

[0004] Typically, flow rate is controlled by adjusting the size of the pulsating motion of a pulsating pump. Furthermore, flow rate can be controlled by adjusting the pump's output pressure. This principle applies: as pressure increases, flow rate also increases, and as pressure decreases, flow rate also decreases. Furthermore, valves installed in pipes can be used to control fluid flow, and the flow can be controlled by opening or closing these valves.

[0005] Meanwhile, when using silicone artificial blood vessels, pipes are used to connect them to the pump. Figure 1 is a drawing illustrating the connection between the pump and the pipe. Referring to Figure 1, in conventional medical imaging such as MRI, the pump itself is placed outside and a long pipe is used to reach the imaging room. In this case, the flow rate inside the cylinder or at the cylinder outlet can be adjusted to the desired flow pattern, but the flow rate decreases as it passes through the long pipe. This phenomenon causes problems in simulating the desired experimental environment.

[0006] In addition, in a pulsating pump, the flow rate or pressure waveform is affected by various factors, and there is a problem that it is difficult to precisely control the desired flow rate or pressure waveform due to these factors.

[0007] A flow control device for a pulsating pump according to an embodiment includes a motor, an actuator, and a piston, and is configured in the form of a pulsating pump. The flow control device and method for a pulsating pump according to an embodiment enable generation of a desired flow rate by controlling the longitudinal movement of the piston using a fixed piston diameter and the internal volume of a cylinder.

[0008] In a pulsating pump, flow rate and pressure waveforms are influenced by various factors. Therefore, in this embodiment, artificial intelligence learning is used to precisely control the desired flow rate or pressure waveform. This learning predicts changes in flow rate or pressure waveform based on changes in specific factors. Furthermore, the predicted values ​​can be used to match the desired flow rate or pressure waveform.

[0009] However, the problems to be solved according to one embodiment are not limited to those mentioned above.

[0010] A flow control device of a pulsating pump according to an embodiment comprises a servo motor, an actuator, a piston, and a control unit; wherein the servo motor is connected to a linear actuator, and the linear actuator pushes the piston to pump, and the control unit; generates a desired flow rate by controlling the longitudinal movement of the piston using a fixed piston diameter and an internal volume of a cylinder.

[0011] In addition, the control unit can calculate a gear ratio with the linear actuator to control the longitudinal movement of the piston and use the calculated gear ratio as a control value of the actuator.

[0012] In addition, the flow control device of the pulsating pump further includes a learning unit that learns flow change variables including pipe length, pipe elastic coefficient, maximum pressure at the inlet, and minimum pressure BPM as learning data to generate a flow control model in order to precisely control the pressure waveform, and the flow control model receives flow change variables from a servo motor, an actuator, and a piston, compares the input flow change variables with the learning data, and can predict changes in flow rate and pressure waveform based on the comparison result.

[0013] Additionally, the flow control model can predict monitoring variables including maximum flow rate, minimum flow rate, maximum pressure, and minimum pressure at the inlet of the silicone blood vessel model inside the MRI room, and maximum flow rate, minimum flow rate, maximum pressure, and minimum pressure at the inlet of the reservoir, depending on the flow rate change variables.

[0014] In addition, when a user's desired monitoring variable is input from an administrator terminal, the flow control model can calculate a flow change variable required to derive the user's desired monitoring variable, and calculate a control value based on the calculated flow change variable and transmit it to the control unit.

[0015] In addition, the control unit can control the longitudinal movement of the piston using the control value received from the flow control model.

[0016] Additionally, the flow control model receives a desired flow rate value as input, calculates a flow rate change variable through an augmented flow profile and an initial flow profile, and calculates a control value for generating a desired flow rate value based on the calculated flow rate change variable value, which can then be transmitted to a servo motor through the control unit.

[0017] Additionally, the desired flow rate values ​​may include maximum flow rate, minimum flow rate, maximum pressure, minimum pressure at the inlet of the silicone blood vessel model inside the MRI room, and maximum flow rate, minimum flow rate, maximum pressure, and minimum pressure at the inlet of the reservoir.

[0018] The flow control device and method for a pulsatile pump described above enable precise flow control without the need for expensive flow meters. Furthermore, the device and method for controlling the flow of a pulsatile pump can be used as a pulsatile pump for PIV (Particle Image Velocimetry) or PTV (Particle Tracking Velocimetry) experiments, and when combined with a silicone artificial blood vessel model, enable the development of a cardiovascular simulator capable of simulating the cardiovascular system.

[0019] This can be used as a training device for practicing vascular interventions such as PCI (percutaneous coronary intervention) or to evaluate the performance of various implantable medical devices.

[0020] The effects of the present invention are not limited to the effects described above, and should be understood to include all effects that can be inferred from the detailed description of the present invention or the composition of the invention described in the claims.

[0021] Figure 1 is a drawing showing the connection between the pump and the pipe.

[0022] Figure 2 is a drawing showing a pulsating pump and a flow control device according to an embodiment.

[0023] Figure 3 is a diagram showing the data processing configuration of a flow control device according to an embodiment.

[0024] Figure 4 is a diagram showing the data processing process of a flow control model according to an embodiment.

[0025] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components will be given the same reference numbers, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably only for the convenience of writing the specification, and do not in themselves have distinct meanings or roles. In addition, when describing the embodiments disclosed in this specification, if it is determined that a specific description of a related known technology may obscure the gist of the embodiments disclosed in this specification, a detailed description thereof will be omitted. In addition, the attached drawings are only intended to facilitate easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention.

[0026] Terms that include ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by these terms. These terms are used solely to distinguish one component from another.

[0027] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components intervening. Conversely, when a component is referred to as being "directly connected" or "connected" to another component, it should be understood that there are no other components intervening.

[0028] In this application, terms such as “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but should be understood not to exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0029] In this specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Furthermore, a single unit may be realized using two or more pieces of hardware, and two or more units may be realized by a single piece of hardware.

[0030] Some of the operations or functions described herein as being performed by a terminal, apparatus, or device may instead be performed by a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described herein as being performed by a server may also be performed by a terminal, apparatus, or device connected to the server.

[0031] Hereinafter, the present invention will be described in detail with reference to the attached drawings.

[0032] Fig. 2 is a drawing showing a pulsating pump and a flow control device according to an embodiment.

[0033] Referring to FIG. 2, a pulsating pump according to an embodiment includes a servo motor (motordriver), an actuator, and a piston (piston pump), and is connected to a flow control device (100). In the embodiment, the flow control device (100) communicates with a manager terminal (200).

[0034] The servo motor of the pulsating pump is connected to a linear actuator, and the linear actuator operates by pushing a piston and pumping. In an embodiment, the flow control device (100) generates a desired flow rate desired by the user by controlling the longitudinal movement of the piston using a fixed piston diameter and the internal volume of the cylinder. In the flow control device (100) of the pulsating pump according to the embodiment, since the diameter of the piston is fixed in a manner in which the servo motor is connected to the linear actuator and the linear actuator pushes the piston and pumps, the longitudinal movement of the piston is controlled to generate a desired flow rate. This allows the flow rate of the fluid to be accurately determined. In addition, in the embodiment, the flow control device (100) receives measurement data including the flow rate and flow rate from a flow meter that measures the flow rate and flow rate of the liquid, compares the data with learning data, and controls the flow rate of the reservoir based on the comparison result.

[0035] In an embodiment, the flow meter collects flow rate change variables from a flow sensor installed in the reservoir. In an embodiment, the flow rate change variables may include pipe length, pipe elastic modulus, maximum pressure at the inlet, minimum pressure BPM, etc.

[0036] Fig. 3 is a diagram showing a data processing configuration of a flow control device according to an embodiment.

[0037] Referring to FIG. 3, a flow control device (100) according to an embodiment may be configured to include a collection unit (110), a preprocessing unit (120), a learning unit (130), a control unit (140), and a feedback unit (150). The term 'unit' used in this specification should be interpreted to include software, hardware, or a combination thereof, depending on the context in which the term is used. For example, the software may be machine language, firmware, embedded code, and application software. As another example, the hardware may be a circuit, a processor, a computer, an integrated circuit, an integrated circuit core, a sensor, a MEMS (Micro-Electro-Mechanical System), a passive device, or a combination thereof.

[0038] The collection unit (110) collects learning data for an artificial neural network model for flow control. In an embodiment, the collection unit (110) collects flow rate change variables as learning data. The flow rate change variables are data for learning the model for precise control of pressure waveforms, and may include pipe length, pipe elasticity coefficient, maximum pressure at the inlet, and minimum pressure BPM.

[0039] The preprocessing unit (120) preprocesses the collected training data to remove biased or discriminatory data from the collected artificial intelligence learning data set. In an embodiment, the preprocessing unit (120) preprocesses the collected training data set and processes it into a form suitable for artificial intelligence model learning. For example, the preprocessing unit (122) may perform processes such as noise removal, outlier removal, and missing value processing. In addition, the preprocessing unit (120) may normalize data, remove outliers, or adjust the scale of data through data preprocessing to prevent the model from learning unnecessary patterns.

[0040] The learning unit (130) trains a deep learning neural network with collected learning data to implement a flow control model. In an embodiment, the learning unit (130) trains flow change variables, including pipe length, pipe elastic coefficient, maximum pressure at the inlet, and minimum pressure BPM, as learning data to create a flow control model for precise control of pressure waveforms.

[0041] In an embodiment, the learning unit (130) applies a learning algorithm to preprocessed learning data to train a flow control model. The flow control model learns the relationship between input variables and output variables to enable precise flow control. In an embodiment, the input variables may include pipe length, pipe elastic modulus, maximum pressure, minimum pressure, and BPM, and the output variables may include an input waveform.

[0042] Afterwards, the learning unit (130) evaluates the learned model and performs tuning. This process aims to increase the model's accuracy and improve its generalization performance. A control system with the learned flow control model applied can precisely control pressure waveforms based on pipe conditions and environmental variables in real-world scenarios.

[0043] In addition, in the embodiment, the flow control model receives flow rate change variables from a servo motor, an actuator, and a piston, compares the input flow rate change variables with learning data, and predicts changes in flow rate and pressure waveforms based on the comparison results.

[0044] In an embodiment, the flow control model predicts monitoring variables at the inlet of a silicone blood vessel model inside an MRI room based on flow rate change variables. In an embodiment, the monitoring variables include maximum flow rate, minimum flow rate, maximum pressure, minimum pressure, and maximum flow rate, minimum flow rate, maximum pressure, and minimum pressure at the reservoir inlet. In an embodiment, the flow control model receives input of flow rate change variables based on the states of a servo motor, actuator, piston, etc. in an actually monitored scenario, performs predictions, and predicts and controls changes in flow rate and pressure waveforms based on the input.

[0045] In addition, in the embodiment, when a user-desired monitoring variable is input from the administrator terminal, the flow control model calculates a flow change variable required to derive the user-desired monitoring variable, and calculates a control value based on the calculated flow change variable and transmits the calculated control value to the control unit (140).

[0046] To this end, the administrator terminal receives user input for desired monitoring variables. These variables may include data related to specific control targets that the system intends to observe and maintain. In the embodiment, the flow control model then calculates the flow rate change variables necessary to derive the user's desired monitoring variables. These flow rate change variables are values ​​that are adjusted to control the behavior of the control target to achieve the desired monitoring variables.

[0047] Afterwards, the flow control model calculates the calculated flow rate change variable. This is the process of calculating the control value based on the flow rate change variable calculated by the model. The control value is a value that must be adjusted to achieve the target given to the control target. The calculated control value is transmitted to the control unit (140). The control unit (140) controls the servo motor, actuator, piston, etc. based on the control value to change the flow rate and controls the system so that the system achieves the target monitoring variable.

[0048] In the embodiment, the control unit (140) controls the system using the transmitted control values. This allows flow rate adjustment or other necessary operations to be performed to achieve the user's desired monitoring variables.

[0049] The control unit (140) controls the longitudinal movement of the piston using the control value received from the flow control model. In addition, the control unit (140) can generate a desired flow rate by controlling the longitudinal movement of the piston using the piston diameter and the internal volume of the cylinder. In order to control the longitudinal movement of the piston, the control unit (140) controls the movement of the servo motor according to the control value. In the embodiment, the control value calculates the gear ratio of the linear actuator and uses the calculated gear ratio as the control value.

[0050] Fig. 4 is a diagram showing the data processing process of a flow control model according to an embodiment.

[0051] Referring to FIG. 4, a flow control model according to an embodiment receives a desired flow rate value as input. In the embodiment, the desired flow rate value may include a maximum flow rate, a minimum flow rate, a maximum pressure, a minimum pressure at the inlet of a silicone blood vessel model inside an MRI room, and a maximum flow rate, a minimum flow rate, a maximum pressure, and a minimum pressure at the inlet of a reservoir.

[0052] Afterwards, the flow rate change variable is calculated through the augmented flow profile and the initial flow profile. Then, based on the calculated flow rate change variable value, a control value for generating a desired flow rate is calculated and transmitted to a servo motor through a control unit. The servo motor generates the flow rate through a piston pump. Afterwards, the flow sensor measures the flow rate data and inputs it back into the flow rate control model. In an embodiment, the degree of discrepancy between the flow rate data measured by the flow sensor and the flow rate value desired by the user can be calculated and inputted back into the flow rate control model.

[0053] In this embodiment, the flow control model first measures and acquires an initial flow profile in the system. At this time, the flow control model determines the initial fluid state and flow characteristics. The initial flow profile represents the initial state of the system or device.

[0054] The flow control model then measures and acquires an augmented flow profile. An augmented flow profile represents information that incorporates additional information or measurements into the initial flow profile. This information may include, for example, sensor data, external environmental variables, or operating conditions at a specific time period. The flow control model then compares or combines the initial and augmented flow profiles to derive flow rate variation variables. This involves analyzing the differences between the two profiles or utilizing the additional information to estimate variables that affect flow rate. The system is then controlled or optimized based on the derived flow rate variation variables. This may involve adjusting the flow rate of a fluid or the pressure at a specific location to achieve a specific system or process objective.

[0055] The feedback unit (125) evaluates the learned artificial neural network model and deep learning model. In an embodiment, the feedback unit (125) can evaluate the artificial neural network model through at least one of accuracy, precision, and recall. Accuracy is an index that measures how much the results predicted by the artificial neural network model match the actual results. Precision is an index that measures the ratio of actual positives among the results predicted as positive. Recall is an index that measures the ratio of actual positives predicted by the model as positives. In an embodiment, the feedback unit (125) can calculate the accuracy, precision, and recall of the artificial neural network model, and evaluate the artificial neural network model based on at least one of the calculated indices.

[0056] In an embodiment, the feedback unit (125) can measure the accuracy of the artificial neural network model using an evaluation dataset. The evaluation dataset consists of data that the model did not use for training and is used to objectively evaluate the model's performance. In an embodiment, the feedback unit (125) executes the artificial neural network model using the evaluation dataset and compares the predicted value of the artificial neural network model for each input data with the actual correct answer value of the corresponding data. Thereafter, the accuracy of the model's predictions can be measured based on the comparison results. For example, the accuracy in the feedback unit (125) can be calculated as the ratio of data correctly predicted by the model among the entire data.

[0057] In addition, the feedback unit (125) can calculate the F1 score, which is an index indicating the balance of precision and recall, which is an index calculated as the harmonic mean of precision and recall, evaluate the artificial neural network model based on the calculated F1 score, generate an AUC-ROC curve, which is an index that visualizes the performance of the classification model in a graph, and evaluate the artificial neural network model based on the generated AUC-ROC curve. In an embodiment, the feedback unit (125) can evaluate that the performance of the model is better as the area under the ROC curve (AUC) is closer to 1.

[0058] In addition, the feedback unit (125) can evaluate the interpretability of the artificial neural network model. In an embodiment, the feedback unit (125) evaluates the interpretability of the artificial neural network model through SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) methods. SHAP (SHapley Additive exPlanations) is a library that provides an interpretation of the results predicted by the model, and the feedback unit (125) extracts SHAP values ​​from the library. In an embodiment, the feedback unit (125) can predict how much the characteristic information input to the model influenced the model prediction through the SHAP value extraction.

[0059] The Local Interpretable Model-agnostic Explanations (LIME) method is a method for explaining model predictions for individual samples. In one embodiment, the feedback unit (125) uses the LIME method to approximate the sample as an interpretable model and calculate the importance of each characteristic. Furthermore, the feedback unit (125) can estimate the influence of each characteristic variable by analyzing the model's internal weights and bias values.

[0060] A model in this specification may refer to any form of computer program that operates based on a network function, an artificial neural network, and / or a neural network. Throughout this specification, the terms model, neural network, network function, and neural network may be used interchangeably. A neural network is a network in which one or more nodes are interconnected through one or more links to form input node and output node relationships within the neural network. The characteristics of a neural network can be determined based on the number of nodes and links within the neural network, the correlation between the nodes and links, and the weight value assigned to each link. A neural network may be composed of a set of one or more nodes. A subset of the nodes constituting the neural network may constitute a layer.

[0061] A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder, a generative adversarial network (GAN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, a generative adversarial network (GAN), a transformer, and the like. The description of the above-described deep neural network is merely an example, and the present disclosure is not limited thereto.

[0062] Neural networks can learn through at least one of the following methods: supervised learning, unsupervised learning, semi-supervised learning, self-supervised learning, or reinforcement learning. Neural network learning can be the process of applying knowledge to the neural network to perform a specific action.

[0063] Neural networks can be trained to minimize output errors. This process involves repeatedly inputting training data into the neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error. In supervised learning, labeled data is used for each training data, while unsupervised learning uses unlabeled data. The amount of change in the connection weights of each updated node can be determined by the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate can vary depending on the number of iterations in the neural network's training cycle. Additionally, to prevent overfitting, methods such as increasing the learning data, regularization, dropout that disables some nodes, and batch normalization layers can be applied.

[0064] In one embodiment, the model may include, but is not limited to, at least one of a Recurrent Neural Network (RNN), a Long Short Term Memory (LSTM) network, a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), and a Bidirectional Recurrent Deep Neural Network (BRDNN).

[0065] In one embodiment, the model may be a model trained using transfer learning. Transfer learning, in this context, refers to a learning method that pre-trains a large amount of unlabeled training data using semi-supervised or self-learning methods to obtain a pre-trained model for a first task, then fine-tunes the pre-trained model to suit a second task, and trains it on labeled training data using supervised learning to implement a target model.

[0066] The flow control device and method for a pulsatile pump described above enable precise flow control without the need for expensive flow meters. Furthermore, the device and method for controlling the flow of a pulsatile pump can be used as a pulsatile pump for Particle Image Velocimetry (PIV) or Particle Tracking Velocimetry (PTV) experiments, and, when combined with a silicone artificial blood vessel model, enables the development of a cardiovascular simulator that can simulate the cardiovascular system. This can be utilized as a training device for practicing vascular interventions such as percutaneous coronary intervention (PCI) or for evaluating the performance of various implantable medical devices.

[0067] The disclosed content is merely an example, and various modifications and implementations can be made by a person skilled in the art without departing from the gist of the claims claimed in the patent, so the scope of protection of the disclosed content is not limited to the specific embodiments described above.

Claims

1. In a flow control device for a pulsating pump, including a servo motor, an actuator, a piston and a control unit; The above servo motor is connected to a linear actuator, and the linear actuator pushes the piston and pumps. The above control unit; A flow control device for a pulsating pump that generates a desired flow rate by controlling the longitudinal movement of the piston using a fixed piston diameter and the internal volume of the cylinder.

2. In the first paragraph, the control unit; A flow control device for a pulsating pump, characterized in that it calculates a gear ratio with a linear actuator to control the longitudinal movement of a piston and uses the calculated gear ratio as a control value of the actuator.

3. In paragraph 1, the flow control device of the pulsating pump; In order to precisely control the pressure waveform, the flow rate change variables including pipe length, pipe elasticity coefficient, maximum pressure at the inlet, and minimum pressure BPM are learned as learning data. Further comprising a learning unit for generating a control model; The above flow control model; A flow control device for a pulsating pump, characterized in that it receives a flow rate change variable from a servo motor, an actuator, and a piston, compares the input flow rate change variable with learning data, and predicts changes in flow rate and pressure waveforms based on the comparison results.

4. In the third paragraph, the flow control model A flow control device for a pulsatile pump, characterized in that it predicts monitoring variables including maximum flow rate, minimum flow rate, maximum pressure, minimum pressure at the inlet of a silicone blood vessel model inside an MRI room, and maximum flow rate, minimum flow rate, maximum pressure, and minimum pressure at the inlet of a reservoir according to flow rate change variables.

5. In the third paragraph, the flow control model A flow control device for a pulsating pump, characterized in that when a user's desired monitoring variable is input from an administrator terminal, a flow rate change variable required for deriving the user's desired monitoring variable is calculated, and a control value is calculated based on the calculated flow rate change variable and transmitted to the control unit.

6. In paragraph 5, the control unit; A flow control device for a pulsating pump characterized by controlling the longitudinal movement of a piston using a control value received from a flow control model.

7. In the 6th paragraph, the flow control model A flow control device for a pulsating pump, characterized in that it receives a desired flow rate value, calculates a flow rate change variable through an augmented flow profile and an initial flow profile, and calculates a control value for generating a desired flow rate value based on the calculated flow rate change variable value and transmits the calculated control value to a servo motor through a control unit.

8. In paragraph 7, the desired flow rate value is A flow control device of a pulsatile pump, characterized by including a maximum flow rate, a minimum flow rate, a maximum pressure, and a minimum pressure at the inlet of a silicone blood vessel model inside an MRI room, and a maximum flow rate, a minimum flow rate, a maximum pressure, and a minimum pressure at the inlet of a reservoir.

Images