An adjustable balloon expansion pressure pump and intelligent control method thereof

Abstract

The application relates to the technical field of minimally invasive blood vessel intervention surgery, in particular to an adjustable balloon expansion pressure pump and an intelligent control method thereof, which comprises the following steps: acquiring a real-time image of a connecting pipe based on a perspective imaging device, identifying positioning information of an identifier in the connecting pipe, and generating an initial parameter set; constructing a fluid model according to the initial parameter set, taking distance information between a first identifier and a second identifier as a constraint condition, and generating a fluid parameter set; generating a pre-expansion parameter set according to the fluid parameter set and controlling the pump body to output pressure; updating the fluid model based on the pre-expansion parameter set, controlling the pump body to execute a pressure instruction in a dynamic pressure sequence, and acquiring a second change value of the distance information, and generating a regulation and control data set according to the second change value; optimizing the regulation and control data set, controlling the pump body to output pressure to a target value, and until the balloon is completely opened. The application significantly improves the success rate and safety of balloon expansion, and makes the balloon expansion process more controllable and efficient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of minimally invasive vascular intervention surgery, in particular to an adjustable balloon expansion pressure pump and an intelligent control method thereof. BACKGROUND

[0002] In the medical field, balloon expansion technology is applied to vascular intervention treatment, heart valve repair and other medical scenarios that require local expansion. The existing balloon expansion equipment controls the inflation and expansion process of the balloon through a manual or semi-automatic pressure pump. Doctors need to adjust the pressure based on experience to ensure that the balloon achieves proper expansion at the target site.

[0003] However, the existing pressure pump control method has a core technical defect, which is the lack of precise perception and real-time control ability for dynamic changes during balloon expansion. This deficiency often makes it difficult for doctors to accurately judge the actual expansion state of the balloon during operation, which may damage the blood vessel wall due to excessive pressure or fail to achieve the expected treatment effect due to insufficient pressure. In addition, the existing control method usually adopts a fixed pressure increment mode, ignoring the possible nonlinear changes during expansion, which limits the adaptability of the equipment in complex surgical scenarios, increasing the risk of surgery and possibly prolonging the operation time, affecting the treatment effect and postoperative recovery of patients.

[0004] Therefore, there is an urgent need for a new control method that can overcome the limitations of existing technology in dynamic perception and precise control, thereby improving the safety and treatment effect of balloon expansion equipment. SUMMARY

[0005] The main purpose of the present application is to provide an intelligent control method for an adjustable balloon expansion pressure pump, which aims to overcome the technical problem of the lack of precise perception and real-time control ability for dynamic changes during balloon expansion in existing technology.

[0006] To achieve the above-mentioned application problems, the present application proposes an intelligent control method for an adjustable balloon expansion pressure pump, which comprises:

[0007] Based on the real-time image of the connecting pipe obtained by the perspective imaging device, the positioning information of the markers in the connecting pipe is identified, and an initial parameter set is generated, wherein the markers include a first marker and a second marker;

[0008] According to the initial parameter set, a fluid model is constructed, the distance information between the first marker and the second marker is taken as a constraint condition of the fluid model, and a fluid parameter set is generated;

[0009] According to the fluid parameter set, the pump body outputs the pressure to an initial value, calculates the pressure deviation according to the first change value of the distance information, and generates a pre-expansion parameter set;

[0010] updating the fluid model based on the pre-dilation parameter set, and outputting a dynamic pressure sequence;

[0011] controlling the pump body to execute a pressure instruction in the dynamic pressure sequence, and obtaining a second change value of the distance information, and generating a control data set according to the second change value;

[0012] optimizing the control data set, and controlling the pump body to output pressure to a target value until the balloon is fully opened.

[0013] Further, the step of obtaining the real-time image of the connecting tube based on the perspective imaging device and identifying the positioning information of the marker in the connecting tube to generate the initial parameter set comprises:

[0014] preprocessing the original image data collected by the perspective imaging device to obtain a standardized image set;

[0015] identifying and segmenting the region containing the first marker and the second marker in the standardized image set to obtain a marker region image;

[0016] identifying the positioning information of the first marker and the second marker in the marker region image to generate the initial parameter set.

[0017] Further, the step of constructing a fluid model according to the initial parameter set and taking the distance information between the first marker and the second marker as a constraint condition of the fluid model to generate a fluid parameter set comprises:

[0018] extracting and processing the connecting tube image data according to the distance information between the first marker and the second marker in the initial parameter set to obtain a connecting tube geometric feature set;

[0019] modeling the initial state of the fluid according to the distance constraint and the inner diameter distribution in the connecting tube geometric feature set to generate a fluid model;

[0020] analyzing the pressure gradient of the fluid in the connecting tube based on the fluid model to obtain a pressure distribution parameter set;

[0021] correcting the fluid model according to the pressure distribution parameter set to obtain a fluid parameter set.

[0022] Further, the step of controlling the pump body to output pressure to an initial value according to the fluid parameter set, calculating the pressure deviation according to the first change value of the distance information, and generating a pre-dilation parameter set comprises:

[0023] grid decomposition of the fluid parameter set to generate an initial pressure distribution parameter containing the pressure value of each grid node;

[0024] Pre-adjusting the pump body driving signal according to the initial pressure distribution parameter to obtain an initial pressure control instruction;

[0025] Controlling the pump body to drive fluid into the connecting pipe according to the initial pressure control instruction, and acquiring real-time fluid state data, wherein the real-time fluid state data includes a first change value of distance information between the first identification body and the second identification body;

[0026] Calculating the deformation degree of the balloon according to the first change value, and calculating the actual pressure distribution inside the balloon according to the deformation degree to obtain a first pressure deviation;

[0027] Optimizing the initial pressure control instruction according to the first pressure deviation to obtain a corrected pressure control sequence;

[0028] Integrating the corrected pressure control sequence with the convergence trend of the first pressure deviation to generate a pre-expansion parameter set containing a corrected initial pressure, an actual flow rate and a deformation feature.

[0029] Further, the step of updating the fluid model based on the pre-expansion parameter set to output a dynamic pressure sequence includes:

[0030] Extracting the state features of the real-time blood vessel image obtained by the perspective imaging device to obtain a blood vessel state feature set;

[0031] Reconstructing the stress distribution of the initial fluid model according to the blood vessel state feature set to obtain an updated stress distribution model;

[0032] Predicting the flow rate of the stress distribution model to obtain a flow rate prediction sequence;

[0033] Optimizing the pressure curve of the initial pressure value in the pre-expansion parameter set according to the flow rate value and the time node in the flow rate prediction sequence to obtain a preliminary pressure sequence;

[0034] Integrating the preliminary pressure sequence into the fluid model for time sequence processing to obtain a dynamic pressure sequence.

[0035] Further, the step of predicting the flow rate of the stress distribution model to obtain a flow rate prediction sequence further includes:

[0036] Obtaining the shear stress and radial stress of each calculation unit in the stress distribution model, calculating the stress distribution features of each unit through a finite element analysis algorithm to obtain a stress distribution feature set;

[0037] The stress distribution feature set is combined with an initial flow rate value in the pre-dilation parameter set to simulate a flow rate change trend of the fluid in the connecting tube and the blood vessel, and a flow rate prediction sequence is generated.

[0038] Further, the step of controlling the pump body to execute the pressure instruction in the dynamic pressure sequence and obtaining a second change value of the distance information, and generating a control data set according to the second change value, comprises:

[0039] The pump body is controlled to execute the pressure instruction in the dynamic pressure sequence, and an actual pressure change in the balloon is obtained, and an actual pressure feedback set is generated;

[0040] A sliding window of a preset bit number is constructed, and the actual pressure feedback set is smoothed based on the sliding window to obtain a smoothed feedback signal set;

[0041] The pressure values in the smoothed feedback signal set are compared with the instruction pressure values in the initial execution instruction set point by point, and a deviation value between the two is calculated;

[0042] The second change value between the first identification body and the second identification body is weighted and corrected to the deviation value to generate a pressure deviation set containing the deviation value, the time sequence and the distance change;

[0043] The actual pressure feedback set and the pressure deviation set are integrated, a future short-time pressure change trend is analyzed by a time sequence prediction technology, and a real-time control data set is generated.

[0044] Further, the step of optimizing the control data set, controlling the pump body to output pressure to a target value, and until the balloon is completely opened, comprises:

[0045] The time sequence, the deviation value and the distance change information in the control data set are fused to obtain a comprehensive control parameter set;

[0046] The comprehensive control parameter set is iteratively optimized to generate an optimized pressure output instruction sequence;

[0047] The pump body is controlled to output pressure according to the optimized pressure output instruction sequence until the actual pressure in the balloon reaches a preset target pressure value;

[0048] A third change value of the distance between the first identification body and the second identification body is monitored, and when the third change value reaches a preset stable threshold, it is determined that the balloon is completely opened;

[0049] The pressure output of the pump body is stopped, and a balloon completely open state signal is output.

[0050] This application also discloses an adjustable balloon inflation pressure pump, applied to any of the above-described intelligent control methods, wherein the adjustable balloon inflation pressure pump comprises:

[0051] Pump body;

[0052] A connecting cavity, which is connected to the pump body;

[0053] An outer tube, one end of which extends into the connecting cavity and is connected to the output port of the pump body, and the other end is connected to the balloon through a connecting tube to transmit the pressure generated by the pump body to the balloon. A first marker and a second marker are provided inside the connecting tube.

[0054] A fluid storage tank, connected to the connecting cavity, is used to store fluid media for pumping and pressurizing output.

[0055] Furthermore, the first and second markers are disposed at the end of the connecting tube away from the connecting cavity. The first marker is provided with a reflective groove, and an elastic element is provided on the side of the first marker near the outer tube, and the elastic element is disposed inside the connecting tube.

[0056] Beneficial effects:

[0057] This application proposes an intelligent control method for an adjustable balloon expansion pressure pump. It utilizes fluoroscopic imaging to acquire real-time images of the connecting tube and generates an initial parameter set by identifying the positioning information of the first and second markers. This method captures minute changes during balloon expansion in real time, significantly improving sensing accuracy. By using the distance information between markers as a constraint to construct a fluid model and generate a fluid parameter set, it achieves accurate simulation of fluid behavior in complex physiological environments. This overcomes the shortcomings of existing technologies that use fixed pressure increment patterns to ignore nonlinear changes, allowing pressure control to better adapt to individual patient differences and dynamic changes in the vascular environment. The pressure deviation is calculated based on the first change value of the distance information, generating a pre-expansion parameter set. Combined with the output of the dynamic pressure sequence and the optimization of the control dataset, the model is continuously updated and the pressure output is finely adjusted during expansion until the balloon is fully opened. This closed-loop feedback mechanism ensures the real-time performance and accuracy of pressure regulation, effectively avoiding vascular damage caused by excessive pressure or incomplete expansion caused by insufficient pressure. Attached Figure Description

[0058] Figure 1 This is a schematic diagram of the overall steps of an intelligent control method for an adjustable balloon expansion pressure pump according to an embodiment of the present invention.

[0059] Figure 2 This is a schematic diagram of the overall structure of an adjustable balloon expansion pressure pump according to an embodiment of the present invention.

[0060] Figure 3 is a side sectional structure schematic diagram of an adjustable balloon expansion pressure pump according to an embodiment of the present application;

[0061] Figure 4 is an enlarged structure schematic diagram of A in Figure 3

[0062] wherein the reference signs are:

[0063] 1, pump body; 2, connecting cavity; 3, outer tube; 4, connecting tube; 5, first marker; 51, reflective groove; 6, second marker; 7, elastic member; 8, fluid storage tank.

[0064] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0066] Those skilled in the art can understand that, unless specifically stated, the singular forms "a", "an" and "the" used herein also include the plural forms. It should be further understood that the use of the term "include" in the specification of the present application means that the features, integers, steps, operations, elements, modules and / or components exist, but do not exclude the existence or addition of one or more other features, integers, steps, operations, elements, modules, components and / or their combinations. It should be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element, or there can be an intermediate element. In addition, the "connection" or "coupling" used herein can include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any of the associated listed items and all combinations thereof.

[0067] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as that generally understood by those skilled in the art to which the present application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have meanings consistent with those in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as such.

[0068] Reference is made to Figure 1 ​The embodiment of the application provides an intelligent control method of an adjustable balloon expansion pressure pump, and the method comprises the following steps:

[0069] S1: acquiring real-time images of the connecting pipe based on a perspective imaging device, identifying positioning information of an identifier in the connecting pipe, and generating an initial parameter set, wherein the identifier comprises a first identification body and a second identification body;

[0070] In step S1, dynamic images of the blood vessel and the connecting pipe are captured in real time by an X-ray perspective imaging device, high-resolution two-dimensional or three-dimensional image data are generated, and deep learning analysis and processing are performed on the perspective images. The convolutional neural network (CNN) algorithm is mainly used for image segmentation and feature extraction. The first identification body and the second identification body are embedded in the connecting pipe. The two identification bodies can be cylindrical structures with specific optical characteristics. The convolutional neural network can segment the outlines of the identification bodies and extract the optical characteristics of the through holes, such as the contrast of the edges or the uniqueness of the geometric shapes, through layer-by-layer convolution and pooling operations on the images. After identifying the identification bodies, the spatial positions and directions of the first identification body and the second identification body are calculated, and positioning data in a three-dimensional coordinate system are generated. For example, the X-ray device captures multiple images from different angles, and the coordinates of the identification bodies in the three-dimensional space are determined by triangulation. It is assumed that the first identification body is located at coordinates (x1, y1, z1) and the second identification body is located at (x2, y2, z2). These coordinate data can directly reflect the relative positions and distances between the identification bodies, and analyze the geometric characteristics between the identification bodies, such as the gap size between the first identification body and the second identification body, estimate the relative distance between the connecting pipe and the blood vessel wall, calculate the resistance coefficient of the fluid passing through the connecting pipe based on the principle of fluid mechanics, integrate all analysis results, and generate an initial parameter set containing the position coordinates of the first identification body and the second identification body, the blood vessel diameter, the resistance coefficient and the like.

[0071] S2: constructing a fluid model according to the initial parameter set, taking the distance information between the first identification body and the second identification body as a constraint condition of the fluid model, and generating a fluid parameter set;

[0072] In step S2, based on the initial parameter set, a fluid mechanics model of the connecting tube and the balloon is constructed in the control unit. The construction of the model is based on the fundamental principles of fluid mechanics, such as the Navier-Stokes equation, which describes the velocity distribution and pressure gradient of fluid in a complex geometric environment. In the connecting tube and balloon system, the fluid is a liquid (such as saline), whose movement is influenced by the tube wall geometry, fluid viscosity, and external pressure. Through the Navier-Stokes equation, the velocity distribution of the fluid in the connecting tube can be analyzed, and the pressure gradient can be derived. When constructing the fluid model, the distance information between the first marker and the second marker is used as a constraint condition. By incorporating the distance information into the fluid model, the boundary conditions can be dynamically adjusted in the simulation, thereby more realistically reflecting the behavior of the fluid in the connecting tube and the balloon. Specifically, the distance information can be used to correct the geometric parameters in the model, such as the equivalent length or cross-sectional area of the connecting tube, thereby optimizing the calculation results of the fluid flow. During the calculation of the fluid parameters, the characteristics of the blood vessel are combined to further improve the model. Specifically, by estimating the elastic parameters of the blood vessel wall based on the blood vessel diameter, the boundary conditions can be dynamically adjusted in the fluid model, thereby more accurately simulating the mechanical response of the blood vessel. This process can be combined with the finite element analysis method to calculate the deformation of the blood vessel wall under different pressures through numerical simulation, and then derive the interaction force between the fluid and the blood vessel wall. In another embodiment, the fluid flow in the connecting tube and balloon system is not completely laminar, especially at the through hole where turbulent flow may occur. The finite element analysis method is used to numerically simulate the turbulent flow characteristics at the through hole, and the geometric model of the connecting tube and the balloon is discretized into a finite number of grid elements, and the velocity and pressure distribution of the fluid in each element is solved. By analyzing the turbulent flow characteristics, a local resistance correction factor can be generated to correct the resistance parameters in the fluid model, thereby improving the accuracy of the model. After completing the above modeling and analysis, a fluid parameter set containing the predicted pressure, flow rate, and resistance correction factor is generated.

[0073] S3: Control the pump body to output pressure to the initial value according to the fluid parameter set, calculate the pressure deviation according to the first change value of the distance information, and generate a pre-dilation parameter set;

[0074] In step S3, the pump output pressure is adjusted to an initial value based on the predicted pressure in the fluid parameter set, which is the starting point of the balloon expansion process and determines the initial driving force of the fluid injected into the balloon. The fluid (e.g., saline) is injected into the balloon in a controllable manner through the pump. After the initial pressure is set and the fluid injection begins, the distance change between the first marker and the second marker during the balloon expansion process is monitored, which reflects the interaction between the balloon internal pressure and the blood vessel wall deformation. By analyzing the relative position change of the markers in the image, the geometric deformation of the balloon during the expansion process is derived. Based on the gap deformation characteristics, the actual pressure inside the balloon is calculated, and the deformation characteristics are combined with the mechanical parameters in the fluid model to calculate the difference between the actual pressure and the initial set pressure. By comparing the actual pressure with the initial pressure, the pressure deviation is generated, and the proportional-integral-derivative (PID) control algorithm is used to dynamically adjust the pump output pressure. The PID algorithm is a classic feedback control method that quickly responds to deviations through proportional terms, eliminates steady-state errors through integral terms, and predicts deviation trends through derivative terms to achieve precise control of pump output. Specifically, the proportional term directly adjusts the output pressure according to the size of the pressure deviation, the integral term accumulates the deviation to eliminate long-term errors, and the derivative term adjusts the pressure in advance according to the rate of change of the deviation to prevent system overshoot or oscillation. Through the PID algorithm, the initial pressure can be dynamically corrected according to the real-time deviation to generate a revised initial pressure that better meets the actual needs, while recording the changes in the actual flow rate to form a pre-expansion parameter set containing the revised initial pressure and the actual flow rate.

[0075] S4: updating the fluid model based on the pre-expansion parameter set, and outputting a dynamic pressure sequence;

[0076] In step S4, the image data of the blood vessel and the connecting tube obtained by the real-time perspective imaging device is used to further analyze the deformation characteristics of the blood vessel. Specifically, the perspective image can capture the geometric changes of the blood vessel under the action of the balloon pressure, such as the radial expansion or local bending of the blood vessel wall, and through image processing technology, the local stress distribution and elastic modulus of the blood vessel wall can be identified. The local stress distribution reflects the pressure intensity received by the blood vessel wall in different regions, and the elastic modulus characterizes the material properties of the blood vessel wall. When updating the fluid mechanics model, the corrected initial pressure and the actual flow rate in the pre-expansion parameter set are input, and the distance change between the first marker and the second marker is taken as the constraint condition. Through real-time monitoring of the distance change, the boundary conditions in the model can be dynamically adjusted, thereby generating new pressure and flow rate prediction values, while considering the influence of the local stress distribution and elastic modulus of the blood vessel wall. Specifically, the deep deterministic policy gradient (DDPG) reinforcement learning algorithm is applied, which takes stress balance as the optimization goal, and through multiple rounds of iterative learning of the pressure curve under different blood vessel states, the DDPG algorithm takes the current state of the blood vessel (such as stress distribution, elastic modulus, distance change, etc.) as input, predicts the next step pressure adjustment action, and evaluates the effect of the action according to the blood vessel deformation feedback. In each iteration, the algorithm will calibrate the pressure value according to the gap change between the cylinder and the small cylinder feedback by the real-time perspective image. For example, if the gap change indicates that the balloon expansion speed is too fast, the algorithm may reduce the pressure increment to slow down the expansion; on the contrary, if the gap change is small, the pressure is increased to speed up the expansion. Through multiple rounds of learning, a dynamic pressure sequence containing multiple time nodes is gradually constructed, and each node corresponds to a specific pressure instruction.

[0077] S5: controlling the pump body to execute the pressure instruction in the dynamic pressure sequence, and obtaining a second change value of the distance information, and generating a regulation and control data set according to the second change value;

[0078] In step S5, the pump body is controlled to execute the pressure instructions in the dynamic pressure sequence, guiding the balloon to gradually expand to the target state. Specifically, through high-frequency sampling technology, instructions are sent to the pump body at extremely short time intervals, ensuring the real-time and accuracy of pressure output. By continuously monitoring the gap change (i.e., the second change value) between the first marker and the second marker through real-time fluoroscopy imaging equipment, the possible nonlinear response during balloon expansion is perceived, and the actual pressure of the balloon is accurately calculated. The actual pressure signal can be noise suppressed through Kalman filtering algorithm, by establishing a state space model, combining previous pressure estimates and current measurement data, generating a smooth pressure feedback signal, comparing the smooth pressure feedback signal with the instruction pressure in the dynamic pressure sequence, calculating the deviation between the two, which reflects the gap between the current pressure and the target pressure. Based on the size of the pressure deviation, the driving signal of the pump body is adjusted in real time, such as increasing or decreasing the fluid injection rate, so that the actual pressure gradually approaches the instruction pressure. At the same time, the output frequency of the fluid storage tank is optimized to ensure the stability of the flow. The stability of the flow is crucial for balloon expansion, because fluctuations in flow can lead to uneven pressure distribution, and even trigger uneven balloon expansion. By analyzing the pressure fluctuation trend in the future short time through time series analysis, the historical pressure data and the current system state can be used to build a prediction model to estimate the possible pressure changes during balloon expansion, so as to adjust and correct the pressure sequence in advance. The prediction results are combined with real-time pressure deviation analysis to form a real-time control data set containing the corrected pressure sequence, flow rate sequence and adjustment data.

[0079] S6: Optimize the control data set and control the pump body to output pressure to the target value until the balloon is fully opened.

[0080] In step S6, the control data set is analyzed to extract key dynamic response features, and by combining the real-time images obtained by the perspective imaging device, the geometric changes after vessel expansion are analyzed, such as the increment of vessel diameter, the change of the gap between the balloon and the vessel wall, and the uniformity of stress distribution. Through the Bayesian optimization algorithm, the resistance correction factor and pressure adjustment parameter in the fluid mechanics model are iteratively adjusted. The Bayesian optimization algorithm is a global optimization method based on a probability model. In this embodiment, the goal is to find a set of pressure and flow rate values that enable the balloon to fully open in the current vessel environment in the most optimal way, while ensuring uniform pressure distribution and avoiding excessive stress on the vessel wall. Specifically, the corrected pressure sequence and flow rate sequence in the control data set are used as the initial input, and the dynamic response features of vessel expansion (such as diameter change rate, local peak value of stress distribution, etc.) are combined to construct a probability model for predicting the balloon expansion effect under different pressure and flow rate combinations. Through multiple iterations, the algorithm will gradually converge to a set of optimal parameter values that maximize the stability and uniformity of the balloon opening, while minimizing potential damage to the vessel. After generating the optimized parameters, these parameters are converted into specific control instructions for the pump body, i.e. the optimized pressure and flow rate values. These values are used to drive fluid injection into the balloon, thereby pushing the balloon to further expand until it is fully open. It is worth noting that here fully open not only means that the balloon reaches the expected geometric shape, but also includes that its fit with the vessel wall reaches the ideal state, and the pressure distribution remains uniform throughout the contact area. To achieve this goal, the interaction state of the balloon and the vessel is monitored in real time, and the distance change value between the first marker and the second marker is obtained. If the gap change shows that the expansion speed of a certain part of the balloon is too fast or too slow, the output pressure or flow rate of the pump body is adjusted to correct the local pressure distribution, thereby ensuring that the opening process of the balloon is smooth and uniform as a whole, and a balloon opening parameter set containing optimized pressure, flow rate, and vessel response features is generated. In actual execution, the pump body will continue to operate according to the optimized pressure and flow rate values until the monitoring data indicates that the balloon has fully opened. At this time, the state of the balloon is verified by the perspective imaging device, such as whether it is fully fitted with the vessel wall or whether there is local stress concentration. If deviations are found, a new round of fine tuning will be triggered until all indicators meet the requirements.

[0081] In one embodiment, the step of generating an initial parameter set based on the real-time images of the connecting tube obtained by the perspective imaging device, identifying the positioning information of the markers in the connecting tube, includes:

[0082] The original image data collected by the perspective imaging device is preprocessed to obtain a standardized image set;

[0083] The regions containing the first marker and the second marker in the standardized image set are identified and segmented to obtain a marker region image;

[0084] identify the first and second marker positioning information in the marker region image to generate an initial parameter set.

[0085] In this embodiment, by capturing the original image sequence containing the connecting tube and its internal markers in real time through X-ray or other imaging techniques, the brightness and contrast of the original image can be adjusted through image gray scale normalization technology, so that the gray value distribution of different frames of images tends to be consistent, and a standardized image set is obtained. From the standardized image set, the region containing the first and second markers is identified and segmented, and the unique visual features of the first and second markers are captured through layer-by-layer feature extraction of the standardized image set, such as the first marker being a structure with a through hole, which has a high degree of recognition in terms of its elliptical shape and boundary profile, while the second marker may have specific surface texture or landmark points. During the segmentation process, the network will automatically identify and label the region containing the markers according to the trained model parameters, while excluding irrelevant background information, to obtain a marker region image containing only the first and second markers. Fine feature extraction and spatial positioning analysis are performed on the marker region image, taking the first marker as an example. The first marker has a through hole structure, and deep learning feature detection algorithms can be used to analyze its optical features, such as detecting the elliptical shape and boundary profile of the through hole to determine the center point position and radius information. For the second marker, its unique surface texture or landmark feature is extracted, such as analyzing its gray scale distribution or local contrast to determine the position of the landmark point. After feature extraction, a feature set containing the through hole geometry, center coordinates, and second marker landmark position is generated. Using the multi-view geometric principle of perspective imaging, combined with the time sequence information of the image sequence, three-dimensional reconstruction is performed. Specifically, by analyzing the position changes of the first marker through hole center coordinates and the second marker landmark points in multiple frames of images, the triangular measurement method can be applied to reconstruct the position of the marker in three-dimensional space, to obtain a three-dimensional coordinate set with the connecting tube center line as the reference, and to calculate the relative distance and angle information between the first and second markers, thereby forming an initial parameter set. Specifically, by using the Euclidean distance calculation method, the straight-line distance between the first marker through hole center and the second marker landmark point is determined, and the distance is corrected in combination with the curvature information of the connecting tube to reflect the actual geometric relationship. At the same time, the dynamic profile changes of the connecting tube in the perspective image sequence can be combined to estimate its internal diameter, wall thickness, and other parameters through time sequence analysis method, and the resistance coefficient of the fluid passing through the first marker through hole is calculated, and the initial parameter set generated contains the spatial coordinates of the marker, the through hole resistance coefficient, the connecting tube internal diameter, and the relative distance, etc.

[0086] In one embodiment, the step of constructing a fluid model according to the initial parameter set, taking the distance information between the first and second markers as a constraint condition of the fluid model, generating a fluid parameter set, comprises:

[0087] According to the distance information between the first and second markers in the initial parameter set, perform geometric constraint extraction processing on the connecting pipe image data to obtain a connecting pipe geometric feature set;

[0088] According to the distance constraint and the inner diameter distribution in the connecting pipe geometric feature set, perform modeling processing on the initial state of the fluid to generate a fluid model;

[0089] Based on the fluid model, analyze the pressure gradient of the fluid in the connecting pipe to obtain a pressure distribution parameter set;

[0090] According to the pressure distribution parameter set, correct the fluid model to output a fluid parameter set.

[0091] In the above embodiments, the distance between the first and second markers is calculated using their three-dimensional coordinates, and the curvature of the axis of the connecting tube is vector-analyzed to generate a set of geometric features including distance constraints, inner diameter distribution, and curvature characteristics. Using the information in the set of geometric features, combined with the basic principles of fluid mechanics, such as mass conservation and momentum conservation, the initial state of the fluid in the connecting tube is simulated. The specific modeling process includes determining the radial constraints of the fluid according to the inner diameter distribution, and calculating the axial flow characteristics of the fluid between the first and second markers in combination with the distance constraints. By iteratively solving the continuity equation, the velocity distribution and initial pressure field of the fluid can be preliminarily determined, thereby generating a preliminary model containing fluid dynamics characteristics. After generating the preliminary fluid model, the pressure transmission characteristics of the fluid in the connecting tube are analyzed based on the preliminary fluid model. Since the velocity distribution of the fluid is closely related to the pressure gradient, the pressure variation trend in each section of the connecting tube is calculated using the correlation between the velocity gradient and the shear stress. For example, in the region between the first and second markers, the distance constraint may cause local changes in fluid velocity, thereby causing pressure fluctuations. To ensure the accuracy of the analysis, the abnormal values of the local pressure distribution are corrected in combination with the curvature information in the set of geometric features. Through this series of calculations, the system generates a set of pressure distribution parameters including axial pressure distribution, local pressure peak value, and pressure gradient coefficient. Using the information in the set of pressure distribution parameters, the influence of the pressure gradient on the fluid model is analyzed. For example, if the pressure distribution shows that there is a significant pressure peak in a certain section of the connecting tube, the velocity distribution or boundary conditions in that region are adjusted to reduce the deviation between the model and the actual physical phenomenon. In addition, the dynamic response of the fluid in the model is comprehensively evaluated in combination with the inner diameter and curvature information in the set of geometric features of the connecting tube. Through an iterative optimization algorithm, the parameters of the fluid model are calibrated, including flow rate, resistance coefficient, and local turbulent characteristics, and finally a set of fluid parameters including predicted pressure, flow rate, and resistance correction factor is generated.

[0092] In one embodiment, the step of controlling the pump body output pressure to an initial value according to the set of fluid parameters, calculating a pressure deviation according to a first change value of the distance information, and generating a set of pre-expansion parameters includes:

[0093] Grid decomposition is performed on the set of fluid parameters to generate an initial pressure distribution parameter containing pressure values of each grid node;

[0094] The pump body driving signal is pre-adjusted according to the initial pressure distribution parameter to obtain an initial pressure control instruction;

[0095] The pump body is controlled to drive the fluid into the connecting tube according to the initial pressure control instruction, and real-time fluid state data is obtained, wherein the real-time fluid state data includes a first change value of the distance information between the first and second markers;

[0096] calculating a deformation degree of the balloon according to the first change value, and calculating an actual pressure distribution inside the balloon according to the deformation degree to obtain a first pressure deviation;

[0097] optimizing the initial pressure control instruction according to the first pressure deviation to obtain a corrected pressure control sequence;

[0098] integrating the corrected pressure control sequence with a convergence trend of the first pressure deviation to generate a pre-expansion parameter set containing a corrected initial pressure, an actual flow rate and a deformation feature.

[0099] In the above embodiment, the fluid parameter set contains information such as fluid density, viscosity, and geometric characteristics of the connecting tube and the balloon. Using these data, the pressure distribution of the fluid in the connecting tube and the balloon is analyzed by the finite element analysis method. The internal space of the connecting tube and the balloon is divided into a plurality of small grid units, and the fluid state of each grid node is simulated and calculated. In the calculation process, the distance constraint between the first marker and the second marker is combined to simulate the pressure distribution characteristics of the fluid under static conditions, and an initial pressure distribution parameter containing the pressure value of each grid node is generated. According to the pressure value of each grid node in the initial pressure distribution parameter, the predicted pressure value at the inlet of the balloon is extracted, which reflects the theoretical pressure required when the fluid enters the balloon. Combined with the resistance coefficient and the pipe length in the fluid model, the initial driving force required by the pump body is calculated. The resistance coefficient reflects the friction loss of the fluid flowing in the pipe, and the pipe length affects the pressure attenuation of the fluid transmission. By comprehensively considering these factors, control parameters corresponding to the motor frequency and pulse width modulation signal of the pump body are generated. These parameters are converted into executable driving signals through a signal conversion module to form an initial pressure control instruction. The pump body is controlled to operate according to the initial pressure control instruction, and the fluid is injected into the connecting tube and the balloon. The flow rate and the dynamic pressure data at the inlet of the balloon are collected in real time through the flow sensor and the pressure sensor, and the real-time image obtained by the perspective imaging device is combined to extract the distance change characteristics between the first marker and the second marker, and to generate real-time fluid state data containing the flow rate, the pressure, and the distance change. The distance change value is analyzed using an image processing algorithm to calculate the deformation degree of the balloon. The deformation degree can be quantified by the relative displacement between the markers, which reflects the expansion state of the balloon under the action of fluid pressure. Combined with the flow rate and the pressure in the real-time fluid state data, the control unit further calculates the actual pressure distribution inside the balloon. The actual pressure distribution is compared with the predicted pressure in the initial pressure distribution parameter to generate a first pressure deviation. The first pressure deviation is the difference between the actual pressure and the predicted pressure, which reflects the deviation degree of the initial pressure control instruction. In the optimization stage, based on the size and direction of the first pressure deviation, an adaptive control algorithm is used to adjust the driving signal of the pump body in real time to generate a series of pressure control signals that change over time, forming a corrected pressure control sequence. The pressure control sequence is analyzed in time sequence to extract the pressure value, the flow rate, and the corresponding distance change characteristics at each time point in the sequence, and the convergence trend of the first pressure deviation is combined to evaluate whether the pressure adjustment effect tends to be stable. Through a data fusion algorithm, these parameters are weighted and integrated to form a pre-expansion parameter set, which contains the corrected initial pressure, the actual flow rate, and the deformation characteristics of the balloon, and can comprehensively guide the pressure regulation in the pre-expansion stage of the balloon.

[0100] In one embodiment, the step of updating the fluid model based on the pre-expansion parameter set and outputting a dynamic pressure sequence comprises:

[0101] extracting a state feature of a real-time blood vessel image acquired by the perspective imaging device to obtain a blood vessel state feature set;

[0102] performing stress distribution reconstruction processing on the initial fluid model according to the blood vessel state feature set to obtain an updated stress distribution model;

[0103] predicting a flow rate of the stress distribution model to obtain a flow rate prediction sequence;

[0104] performing pressure curve optimization processing on an initial pressure value in the pre-dilation parameter set according to a flow rate value and a time node in the flow rate prediction sequence to obtain a preliminary pressure sequence;

[0105] performing time sequence integration processing on the fluid model by using the preliminary pressure sequence to obtain a dynamic pressure sequence.

[0106] In the above embodiments, edge detection techniques (such as Canny algorithm or Sobel operator) can be employed to locate the boundary profile of the blood vessel, and the boundary points are fitted into a three-dimensional surface through geometric modeling, so as to describe the local curvature and inflation trend of the blood vessel, and the deformation rate of the blood vessel wall is calculated in combination with the dynamic distance change between the first marker and the second marker provided in the pre-inflation parameter set. The deformation rate is obtained by analyzing the time series of the distance change, and reflects the dynamic behavior of the blood vessel in the inflation process. The information such as the estimated values of the vessel diameter and wall thickness and the deformation rate is integrated to form a vessel state feature set. The geometric parameters (such as diameter and wall thickness) in the vessel state feature set and the deformation rate are used in combination with the principles of fluid mechanics to recalculate the shear stress and radial stress distribution under the interaction of the fluid and the blood vessel wall. In specific implementation, the finite element analysis method can be used to discretize the blood vessel wall into multiple calculation units, each unit corresponding to the mechanical properties of a local area. Based on the deformation rate provided in the feature set, the stress increment of each unit is derived, and a wall thickness non-uniformity correction factor is introduced to reflect the influence of the changes of the wall thickness at different parts of the blood vessel on the mechanical behavior. The stress distribution is continuously updated through iterative calculation until the stress field of the entire model converges to a stable state. The boundary conditions in the stress distribution model are extracted, such as the stress distribution of the blood vessel wall and the inlet velocity of the fluid, and then the fluid velocity field is calculated by numerical integration method (such as finite difference or finite volume method). In the calculation process, the geometric constraints (such as the change of the blood vessel diameter) and the viscous resistance characteristics of the fluid are comprehensively considered to predict the flow rate value at different time points. In order to ensure the accuracy of the prediction, a multi-step time advancing strategy can be used to verify the coupling relationship between the flow rate and the stress distribution point by point, and the possible numerical errors are eliminated through iterative optimization to generate a flow rate prediction sequence containing multiple time nodes, each node corresponding to a flow rate value. The reinforcement learning framework is used to take the flow rate balance and stress stability as the objective function, and the pressure parameters are gradually optimized through multiple rounds of trial and error. In each iteration, the algorithm records the deviation of the flow rate from the expected value, and updates the pressure adjustment strategy according to the deviation, thereby generating a pressure curve containing time nodes. Time series analysis method is used to decompose the preliminary pressure sequence into multiple time segments, and the matching degree of each segment with the flow rate and stress distribution is verified. In each time segment, the algorithm dynamically adjusts the model parameters, such as time step or pressure increment, to generate a dynamic pressure sequence containing multiple time nodes, which can describe the dynamic behavior of the fluid in the blood vessel.

[0107] In another embodiment, the calculation expression of the deformation rate in the above embodiments is:

[0108] ; wherein the deformation rate Quantifying the dynamic deformation behavior of the vessel wall during expansion, reflecting the rate of change in the geometric shape (e.g., diameter or boundary contour) over time under the action of fluid pressure or other external forces; Dynamic distance change, representing the change in distance between the first and second markers at time t, reflecting the local geometric deformation of the vessel wall during expansion or contraction. For example, when the vessel diameter increases, the distance between the markers increases, Positive value; Initial reference distance, representing the distance between the first and second markers in the initial state (without deformation) of the vessel, measured by imaging techniques (e.g., ultrasound or CT) under the force-free state of the vessel; Time interval, representing the time interval between measuring the distance of the markers, which is the time step in time series analysis; Local curvature, representing the local curvature of the vessel wall at time t, calculated from the boundary points by geometric modeling (e.g., three-dimensional surface fitting); Relative deformation, representing the ratio of dynamic distance change to initial reference distance, quantifying the relative deformation degree of the vessel wall; Time derivative factor, representing the derivative of the deformation with respect to time, used to convert the relative deformation to a rate; Curvature correction factor, based on the local curvature of the correction factor, used to adjust the deformation rate to reflect the influence of the vessel geometry; when the curvature is large, the correction factor reduces the deformation rate, reflecting the constraint effect of curvature on deformation; when the curvature approaches 0 (straight pipe section), the correction factor approaches 1, and the deformation rate approaches the uncorrected value.

[0109] In one embodiment, the step of predicting the flow rate of the stress distribution model to obtain a flow rate prediction sequence further comprises:

[0110] Obtain the shear stress and radial stress of each calculation unit in the stress distribution model, calculate the stress distribution characteristics of each unit by finite element analysis algorithm, and obtain a set of stress distribution characteristics;

[0111] Combine the set of stress distribution characteristics with the initial flow rate value in the set of pre-expansion parameters, simulate the flow rate change trend of the fluid in the connecting pipe and the vessel, and generate a flow rate prediction sequence.

[0112] In this embodiment, a recurrent neural network architecture such as a long short-term memory network (LSTM) or a gated recurrent unit (GRU) can be used, taking the stress distribution feature set as input features and the initial flow rate value and its historical changes as training labels. Through the training process, the model learns the flow rate variation law of the fluid in the blood vessel. After training, the model can predict the future flow rate variation trend according to the new stress distribution feature set and generate a more accurate flow rate prediction sequence. In addition, to enhance the generalization ability of the model, data from different individuals, different blood vessel sites, and different expansion conditions can be collected as training samples to ensure that the model maintains high prediction accuracy when dealing with various complex situations.

[0113] In one embodiment, the step of controlling the pump body to execute the pressure instruction in the dynamic pressure sequence and obtaining the second change value of the distance information comprises:

[0114] controlling the pump body to execute the pressure instruction in the dynamic pressure sequence and obtaining the actual pressure change in the balloon, and generating an actual pressure feedback set;

[0115] constructing a sliding window of a preset number of bits, and smoothing the actual pressure feedback set based on the sliding window to obtain a smoothed feedback signal set;

[0116] point-by-point comparing the pressure values in the smoothed feedback signal set with the instruction pressure values in the initial execution instruction set, and calculating the deviation values therebetween;

[0117] weighting and correcting the deviation values by the second change value between the first and second identification bodies, to generate a pressure deviation set containing deviation values, time series, and distance changes;

[0118] integrating the actual pressure feedback set and the pressure deviation set, analyzing the future short-term pressure change trend through time series prediction technology, and generating a real-time regulation data set.

[0119] In the above embodiment, each pressure command in the dynamic pressure sequence is sent to the pump body in timestamp order, driving the pump body to output pressure at a specific frequency and intensity. Using the known relationship between the output pressure and flow rate of the pump body, combined with the instructions of the dynamic pressure sequence and the operating parameters of the pump body, the actual pressure changes delivered to the balloon can be directly reflected, generating an actual pressure feedback set containing multi-dimensional data. A sliding window of a preset number of bits is constructed to smooth the pressure data, and the number of bits of the sliding window can be determined according to the sampling frequency of the system and the expected smoothing degree, for example, a 10-point or 20-point window. The data in the window is processed by weighted average or low-pass filtering method to reduce the influence of high-frequency noise. By comparing the actual pressure values in the smoothed feedback signal set with the command pressure values one by one, the deviation values at each time point can be calculated. The deviation value can be calculated by a simple difference method, i.e. actual pressure value minus command pressure value, or a more complex measurement method can be introduced according to specific applications, such as relative error or weighted error. In order to improve the accuracy of deviation analysis, the second change value between the first and second markers is introduced to weight and correct the deviation value. The second change value can be understood as the dynamic change of the distance between the markers within a certain time period (second time), reflecting the physical state of the balloon expansion. By taking the distance change as a weighting factor, the influence of the geometric change of the balloon on the pressure demand can be considered comprehensively, generating a pressure deviation set containing deviation values, time series and distance changes. The actual pressure feedback set and the pressure deviation set are integrated, the integration process includes data alignment, normalization and feature extraction, and time series prediction techniques such as autoregressive model (ARIMA), long short-term memory network (LSTM) or other machine learning algorithms are used to analyze the short-term trend of pressure changes. These prediction models will infer the pressure demand in the next few seconds or milliseconds based on historical data (including deviation values, actual pressure values and distance changes), and combine the flow rate constraints in the fluid model and the dynamic characteristics of balloon expansion to correct the prediction results, generating a real-time control data set. This data set contains the corrected pressure sequence, as well as the flow rate sequence, deviation data and prediction trend.

[0120] In one embodiment, the step of optimizing the control data set to control the pump body to output pressure to a target value until the balloon is fully opened comprises:

[0121] Fusing the time series, deviation values and distance change information in the control data set to obtain a comprehensive control parameter set;

[0122] Iteratively optimizing the comprehensive control parameter set to generate an optimized pressure output command sequence;

[0123] The pump body outputs pressure according to the optimized pressure output instruction sequence until the actual pressure inside the balloon reaches the preset target pressure value;

[0124] The third change value of the distance between the first marker body and the second marker body is monitored, and when the third change value reaches the preset stable threshold, it is determined that the balloon is fully opened;

[0125] The pressure output of the pump body is stopped, and a balloon fully opened state signal is output.

[0126] In the above embodiment, the time series, deviation values and distance change information in the regulation data set are fused and processed, and these information is integrated through a data fusion algorithm to generate a data set containing comprehensive regulation parameters. The comprehensive regulation parameter set contains pressure information and integrates the geometric characteristics and dynamic behavior of balloon expansion. Iterative optimization is performed on the comprehensive regulation parameter set, and the goal is to generate a pressure output instruction sequence that can accurately control the output pressure of the pump body. The iterative optimization process can use gradient-based optimization algorithms such as conjugate gradient method or quasi-Newton method, or heuristic optimization algorithms such as genetic algorithm or particle swarm algorithm. In each iteration, the error between the output pressure and the target pressure is calculated according to the current parameter set, and the parameter set is updated according to the size and direction of the error until the error converges to an acceptable range. The pump body outputs pressure according to the optimized pressure output instruction sequence, which requires precise control of the operating parameters of the pump body, such as motor frequency and pulse width modulation signal, to ensure that the pump body can output pressure according to the requirements of the instruction sequence. At the same time, by monitoring the actual pressure inside the balloon in real time, it can be determined whether the balloon has reached the preset target pressure value and maintained for a period of time to ensure full expansion of the balloon. The third change value of the distance between the first marker body and the second marker body is monitored to determine whether the balloon has been fully opened. When the third change value reaches the preset stable threshold, it can be considered that the balloon has been fully opened, at which point the pressure output of the pump body can be stopped, and a balloon fully opened state signal can be output. The state signal can be a signal sent by the control system when the third change value reaches the preset stable threshold.

[0127] Reference Figures 2 to 4The application further discloses a balloon expansion pressure pump with adjustable pressure, which is applied to the intelligent control method and comprises a pump body 1, a connecting cavity 2 in communication with the pump body 1, an outer tube 3 with one end extending into the connecting cavity 2 and connected with an output port of the pump body 1 and the other end connected with a balloon through a connecting tube 4 to transfer the pressure generated by the pump body 1 to the balloon, first and second markers 5 and 6 arranged in the connecting tube 4, and a fluid storage tank 8 connected with the connecting cavity 2 and used for storing fluid medium to be extracted and pressurized by the pump body 1.

[0128] In this embodiment, the pump body 1 is the power source of the entire pressure pump, responsible for extracting and pressurizing the fluid medium. The pump body 1 communicates with the connecting cavity 2 through its output port, which is a transition area for fluid transmission, connecting the pump body 1 with the external pipeline, and also connected with the fluid storage tank 8. The function of the fluid storage tank 8 is to store fluid medium, such as physiological saline or contrast agent, for continuous extraction by the pump body 1 during operation. One end of the outer tube 3 extends into the connecting cavity 2 and is directly connected to the output port of the pump body 1, thereby receiving the pressurized fluid generated by the pump body 1; the other end is connected to the balloon through the connecting tube 4, transmitting the pressure to the balloon to achieve the expansion of the balloon. The first marker 5 and the second marker 6 are arranged in the connecting tube 4, and the two markers are located at the end of the connecting tube 4 away from the connecting cavity 2, close to the balloon, so as to more directly perceive the changes of the balloon under pressure. The reflective groove 51 on the first marker 5 can enhance the identification ability of the marker by the perspective imaging device. The reflective groove 51 reflects light, making the marker present higher contrast in imaging, thereby facilitating the real-time image acquisition system to accurately capture its position information. The first marker 5 is provided with an elastic member 7 on the side close to the outer tube 3, and the elastic member 7 is located inside the connecting tube 4. The function of the elastic member 7 is to realize the dynamic change measurement of the distance between the first marker 5 and the second marker 6. Specifically, the second marker 6 is relatively fixed in the connecting tube 4, while the first marker 5 is connected to the inner wall of the connecting tube 4 through the elastic member 7. When the pressure fluid output by the pump body 1 flows through the connecting tube 4 to the balloon, the pressure of the fluid will push the first marker 5 to approach the second marker 6, thereby compressing the elastic member 7 and reducing the distance between the two. The elastic property of the elastic member 7 ensures that when the pressure decreases, the first marker 5 can be pulled back to the original position, thereby restoring the initial distance. Through the real-time images captured by the perspective imaging device, the system can identify the positioning information of the first marker 5 and the second marker 6, and calculate the pressure deviation based on the distance change value, to generate a pre-expansion parameter set and a dynamic pressure sequence. Further, in the control method, the pump body 1 needs to generate a control data set according to the second change value of the distance information, and optimize the output pressure to the target value. The existence of the elastic member 7 enables the first marker 5 to respond sensitively to slight changes in pressure, thereby providing high-precision data support for the generation of the control data set. For example, when the balloon gradually expands, the fine adjustment of the fluid pressure will cause a slight change in the distance between the first marker 5 and the second marker 6. The elastic member 7 ensures that these changes can be accurately captured and fed back to the control system, ultimately achieving precise control of the complete opening of the balloon.

[0129] To sum up, the embodiment builds an efficient and sensitive pressure transmission and monitoring system through the pump body 1, the connecting cavity 2, the outer tube 3, the fluid storage tank 8 and the connecting tube 4 with the first marker 5, the second marker 6 and the elastic member 7. The pump body 1 and the fluid storage tank 8 ensure the stable supply of fluid, the outer tube 3 and the connecting tube 4 realize the accurate transmission of pressure, and the first marker 5 and the second marker 6 dynamically perceive the pressure change through the cooperation of the elastic member 7, which can effectively realize the accurate regulation and control of the balloon expansion in actual application.

[0130] It is worth noting that the first marker 5, the second marker 6 and the elastic member 7 are arranged inside the connecting tube 4, and there are gaps on the inner circumferential side for the liquid to flow through, and the first marker 5 and the second marker 6 can be hollow structures to reduce the resistance to fluid flow and avoid hindering the fluid transmission.

[0131] The above only describes the preferred embodiments of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An intelligent control method for an adjustable balloon inflation pressure pump, characterized by, The method comprises: acquiring real-time images of the connecting tube based on a perspective imaging device, identifying positioning information of markers in the connecting tube, and generating an initial parameter set, wherein the markers comprise a first marker body and a second marker body; constructing a fluid model according to the initial parameter set, taking distance information between the first marker body and the second marker body as a constraint condition of the fluid model, and generating a fluid parameter set; controlling the pump body to output pressure to an initial value according to the fluid parameter set, calculating a pressure deviation according to a first change value of the distance information, and generating a pre-expansion parameter set; updating the fluid model based on the pre-expansion parameter set and outputting a dynamic pressure sequence; controlling the pump body to execute pressure instructions in the dynamic pressure sequence, acquiring a second change value of the distance information, and generating a regulation and control data set according to the second change value; optimizing the regulation and control data set, controlling the pump body to output pressure to a target value, and until the balloon is fully opened; The step of acquiring real-time images of the connecting tube based on a perspective imaging device, identifying positioning information of markers in the connecting tube, and generating an initial parameter set comprises: preprocessing original image data collected by the perspective imaging device to obtain a standardized image set; identifying regions containing the first marker body and the second marker body in the standardized image set and performing segmentation processing to obtain a marker region image; identifying positioning information of the first marker body and the second marker body in the marker region image, and generating an initial parameter set; The step of controlling the pump body to output pressure to an initial value according to the fluid parameter set, calculating a pressure deviation according to a first change value of the distance information, and generating a pre-expansion parameter set comprises: grid decomposition of the fluid parameter set to generate an initial pressure distribution parameter containing pressure values of each grid node; pre-adjusting a pump body driving signal according to the initial pressure distribution parameter to obtain an initial pressure control instruction; controlling the pump body to drive fluid into the connecting tube according to the initial pressure control instruction, and acquiring real-time fluid state data, wherein the real-time fluid state data includes a first change value of the distance information between the first marker body and the second marker body; calculating the deformation degree of the balloon according to the first change value, and calculating the actual pressure distribution inside the balloon according to the deformation degree to obtain a first pressure deviation; optimizing the initial pressure control instruction according to the first pressure deviation to obtain a corrected pressure control sequence; integrating the corrected pressure control sequence with the convergence trend of the first pressure deviation to generate a pre-expansion parameter set containing a corrected initial pressure, an actual flow rate, and a deformation characteristic.

2. The intelligent control method of an adjustable balloon inflation pressure pump according to claim 1, wherein, The step of constructing a fluid model according to the initial parameter set, taking distance information between the first marker body and the second marker body as a constraint condition of the fluid model, and generating a fluid parameter set comprises: performing geometric constraint extraction processing on the connecting tube image data according to the distance information between the first marker body and the second marker body in the initial parameter set to obtain a connecting tube geometry feature set; According to the distance constraint and the inner diameter distribution in the connection pipe geometry feature set, the initial state of the fluid is modeled and processed to generate a fluid model; Based on the fluid model, the pressure gradient of the fluid in the connection pipe is analyzed to obtain a pressure distribution parameter set; According to the pressure distribution parameter set, the fluid model is corrected to output a fluid parameter set.

3. The intelligent control method of an adjustable balloon inflation pressure pump according to claim 1, wherein, The step of updating the fluid model based on the pre-dilation parameter set and outputting a dynamic pressure sequence includes: Extracting the state features of the real-time blood vessel image obtained by the perspective imaging device to obtain a blood vessel state feature set; According to the blood vessel state feature set, the initial fluid model is stress distribution reconstructed to obtain an updated stress distribution model; Predicting the flow rate of the stress distribution model to obtain a flow rate prediction sequence; According to the flow rate value and the time node in the flow rate prediction sequence, the initial pressure value in the pre-dilation parameter set is pressure curve optimized to obtain a preliminary pressure sequence; The preliminary pressure sequence is time sequence integrated to the fluid model to obtain a dynamic pressure sequence.

4. The intelligent control method of an adjustable balloon inflation pressure pump according to claim 3, wherein, The step of predicting the flow rate of the stress distribution model to obtain a flow rate prediction sequence further includes: Obtaining the shear stress and radial stress of each calculation unit in the stress distribution model, calculating the stress distribution characteristics of each unit by a finite element analysis algorithm to obtain a stress distribution characteristic set; Combine the stress distribution characteristic set with the initial flow rate value in the pre-dilation parameter set to simulate the flow rate trend of the fluid in the connection pipe and the blood vessel to generate a flow rate prediction sequence.

5. The intelligent control method of an adjustable balloon inflation pressure pump of claim 1, wherein, The step of controlling the pump body to execute the pressure instruction in the dynamic pressure sequence and obtaining the second change value of the distance information to generate a control data set includes: Control the pump body to execute the pressure instruction in the dynamic pressure sequence, and obtain the actual pressure change in the balloon to generate an actual pressure feedback set; Construct a sliding window of a preset number of bits, smooth the actual pressure feedback set based on the sliding window to obtain a smooth feedback signal set; Compare the pressure values in the smooth feedback signal set with the instruction pressure values in the initial execution instruction set point by point to calculate the deviation value between them; The second change value between the first and second identification bodies is weighted and corrected to the deviation value to generate a pressure deviation set containing deviation value, time sequence and distance change; Integrate the actual pressure feedback set and the pressure deviation set, analyze the future short-term pressure change trend through time sequence prediction technology, and generate a real-time control data set.

6. The intelligent control method of an adjustable balloon inflation pressure pump of claim 1, wherein, The step of optimizing the control data set, controlling the pump body to output pressure to the target value, and opening the balloon completely includes: Fuse the time sequence, deviation value and distance change information in the control data set to obtain a comprehensive control parameter set; Iteratively optimize the comprehensive control parameter set to generate an optimized pressure output instruction sequence; Control the pump body to output pressure according to the optimized pressure output instruction sequence until the actual pressure in the balloon reaches the preset target pressure value; Monitoring the third change value of the distance between the first marker and the second marker, when the third change value reaches a preset stable threshold, it is determined that the balloon is fully opened; Stop the pressure output of the pump body, and output a balloon fully opened state signal.

7. An adjustable balloon inflation pressure pump for use in the intelligent control method of any one of claims 1 to 6, characterized in that, The adjustable balloon expansion pressure pump comprises: a pump body (1); a connecting cavity (2) in communication with the pump body (1); an outer tube (3) having one end extending into the connecting cavity (2) and connected with the output port of the pump body (1), and the other end connected with the balloon through a connecting tube (4) to transmit the pressure generated by the pump body (1) to the balloon, the connecting tube (4) being provided with a first marker (5) and a second marker (6); a fluid storage tank (8) connected with the connecting cavity (2) for storing fluid medium for pumping and pressurizing output by the pump body (1).

8. The adjustable balloon dilation pressure pump of claim 7, wherein, The first marker (5) and the second marker (6) are arranged at the end of the connecting tube (4) away from the connecting cavity (2), the first marker (5) is provided with a reflective groove (51), the side of the first marker (5) close to the outer tube (3) is provided with an elastic member (7), and the elastic member (7) is arranged in the connecting tube (4).

Images