A pipeline plugging test system and method for a plugging device

Abstract

The present invention discloses a pipeline plugging test system and method for a plugging device, relating to the technical field of plugging tests, including: performing a first physical test on the plugging device to determine first test data; introducing a mechanical environment by simulating a flow field cycle, building a test module based on the plugging simulation of the plugging device, introducing a discrimination component based on plugging characteristics, and embedding and deploying it in the test system; the discrimination component determines a first test result for the first test data, triggers the test module, performs a two-stage mechanical test, determines second simulation data, and makes a determination based on the discrimination component to determine a second test result; and displaying the second test result on a terminal interface. The present invention solves the technical problems in the prior art of relying on a single physical test method, being difficult to comprehensively evaluate the plugging performance, and lacking an intelligent evaluation mechanism and standard unity, and achieves the technical effect of realizing systematic and intelligent testing of the performance of the plugging device.

Description

Technical Field

[0001] The present invention relates to the technical field of plugging tests, and particularly to a pipeline plugging test system and method for a plugging device. Background Art

[0002] At present, the performance evaluation of plugging devices mainly relies on single physical detection means, such as static pressure tests or manual visual inspections. The test process often fails to cover the complex and variable environments faced by plugging devices in actual applications, such as in-vivo fluid flow disturbances, tissue reactions, and other factors. At the same time, existing test means usually lack systematic process design and standardized evaluation indicators, and do not have the ability of intelligent discrimination and dynamic adjustment, resulting in strong subjectivity and poor stability of test results, and it is difficult to accurately reflect the plugging effect and reliability of plugging devices in real scenarios. Summary of the Invention

[0003] This application provides a pipeline plugging test system and method for a plugging device, which are used to solve the technical problems in the prior art that rely on single physical test means, are difficult to comprehensively evaluate plugging performance, and lack intelligent evaluation mechanisms and standard unity.

[0004] In view of the above problems, this application provides a pipeline plugging test system and method for a plugging device.

[0005] In the first aspect of this application, a pipeline plugging test system for a plugging device is provided. The system includes:

[0006] A test unit for performing a first physical test on the plugging device to determine first test data; A deployment unit for introducing a mechanical environment through a simulated flow field cycle, building a test module for the plugging simulation of the plugging device, introducing a discrimination component based on plugging characteristics, and being embedded in the test system, wherein the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination; A determination unit for the discrimination component to determine the first test data to obtain a first test result, trigger the test module, perform a two-stage mechanical test, determine second simulation data, and perform a determination based on the discrimination component to obtain a second test result, where the two-stage mechanical test includes a static test and a dynamic test, and is driven by the cross-linking of plugging condition variables and mechanical environment variables; A display unit for displaying the second test result on a terminal interface.

[0007] In the second aspect of this application, a pipeline plugging test method for a plugging device is provided. The method includes:

[0008] Perform the first physical test on the plugging device to determine the first test data; introduce a mechanical environment by simulating a flow field cycle, build a test module based on the plugging simulation of the plugging device, introduce a discrimination component based on plugging characteristics, and deploy it embedded in the test system, where the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination; the discrimination component determines the first test result by judging the first test data, triggers the test module, performs a two-stage mechanical test, determines the second simulation data and makes a judgment based on the discrimination component to determine the second test result, where the two-stage mechanical test includes a static test and a dynamic test, which are driven by cross-linking the plugging condition variables and the mechanical environment variables; display the second test result on the terminal interface.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application performs the first physical test on the plugging device to determine the first test data; introduces a mechanical environment by simulating a flow field cycle, builds a test module based on the plugging simulation of the plugging device, introduces a discrimination component based on plugging characteristics, and deploys it embedded in the test system, where the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination; the discrimination component determines the first test result by judging the first test data, triggers the test module, performs a two-stage mechanical test, determines the second simulation data and makes a judgment based on the discrimination component to determine the second test result, where the two-stage mechanical test includes a static test and a dynamic test, which are driven by cross-linking the plugging condition variables and the mechanical environment variables; displays the second test result on the terminal interface. The present invention solves the technical problems in the prior art, such as relying on a single physical test method, being difficult to comprehensively evaluate the plugging performance, and lacking an intelligent evaluation mechanism and standard unity. By introducing a mechanical simulation environment and a double-layer discrimination component based on adversarial training, a closed-loop test process of hierarchical detection and variable driving is constructed, achieving the technical effect of realizing the systematic and intelligent testing of the performance of the plugging device. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic structural diagram of a pipeline plugging test system for a plugging device provided by an embodiment of this application;

[0013] Figure 2 It is a schematic flowchart of a pipeline plugging test method for a plugging device provided by an embodiment of this application.

[0014] Description of the accompanying drawings: testing unit 11, deployment unit 12, determination unit 13, display unit 14. DETAILED DESCRIPTION

[0015] The present application provides a pipeline occlusion test system and method for an occluder, aiming to solve the technical problems in the prior art that the occluder performance is difficult to be comprehensively evaluated by relying on a single physical testing method, and that there is a lack of intelligent evaluation mechanism and standard uniformity. By introducing a mechanical simulation environment and a two-layer discrimination component based on adversarial training, a hierarchical detection and variable-driven closed-loop test process is constructed, thereby achieving the technical effect of realizing systematic and intelligent testing of the occluder performance.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, an embodiment of the present application provides a pipeline blocking test system of an occluder, the system comprising:

[0019] The testing unit 11 is used to perform a first physical test on the occluder to determine first test data.

[0020] In an embodiment of the present application, the test unit 11 is used to perform a first physical test on the occluder and determine the first test data. The test is performed by installing the occluder to be tested in a closed test pipeline, and gradually applying a preset liquid pressure by constant pressure injection to make the occluder enter a stable occluding state, and continuously collecting its pressure response information during the pressure process through the pressure difference sensors arranged at both ends of the occluder, and at the same time using the leakage channel to record the liquid seepage per unit time under the occluding state. As the test time progresses, the plugging onset time, the pressure difference holding capacity and the key physical changes in the leakage process are synchronously collected to generate the first test data. The data includes the plugging pressure difference value, the leakage per unit time, the plugging response time, etc.

[0021] The deployment unit 12 is used to introduce a mechanical environment through a simulated fluid field circulation, build a test module for the plugging simulation of the plugging device, introduce a discrimination component based on the plugging characteristics, and be embedded in the test system, wherein the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination.

[0022] In the embodiment of the present application, the deployment unit 12 is used to introduce a mechanical environment through a simulated fluid field circulation, build a test module for the plugging simulation of the plugging device, and introduce a discrimination component based on the plugging characteristics, and be embedded in the test system, wherein the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination. Specifically, the deployment unit 12 first constructs a simulated fluid field circulation system, which forms a closed fluid loop by using a variable-speed circulation pump and a control valve array, and realizes the reproduction of periodic mechanical disturbances in a typical engineering environment by controlling the flow rate fluctuation, the pressure pulse frequency, and the fluid viscosity, such as simulating the high-frequency variable pressure conditions in blood circulation or the suction load characteristics in a respiratory negative pressure environment. In this simulated fluid field, in combination with the actual plugging application requirements, the plugging device structure is installed and a plugging simulation test module is established around its working cavity to ensure that it operates in the simulated mechanical boundary under the action of controlled variables.

[0023] Subsequently, the deployment unit 12 introduces a discrimination component based on the plugging characteristics and integrates it into the internal communication and control bus of the test system in an embedded deployment manner. The discrimination component is constructed based on an adversarial training mechanism and is in the form of a two-layer architecture. Among them, the first-layer test discrimination is responsible for quickly binary-classifying the initial physical test data to determine whether the plugging state meets the standard, and the second-layer adjustable discrimination adjusts the discrimination boundary according to the disturbance input from the environmental variables to achieve accurate determination for dynamic load changes. The entire process completes data interface registration and control parameter synchronization through the embedded deployment method to ensure the efficient cooperation between the simulation test module and the discrimination component.

[0024] Further, in the system provided by the embodiment of the application, the deployment unit 12 is further used for:

[0025] Determine the plugging characteristics, where the plugging characteristics at least include airtightness, targeting, and stability; for the plugging characteristics, perform supervised training based on the adversarial principle to determine the discrimination component, where the discrimination component is the discrimination architecture disassembled after the training of the generative-discriminative architecture; embed the discrimination component in the test system and establish a communication connection with the test module.

[0026] In the embodiment of the present application, the key performance parameters of the occluder, i.e., the occluding characteristics, are first clarified. The occluding characteristics include three indicators: air tightness, targeting, and stability, which are used to characterize the sealing effect, positioning accuracy, and performance sustainability of the occluder in actual use under long-term working conditions. The air tightness is reflected by measuring the pressure difference maintenance ability and the leakage per unit time at both ends of the occluder after applying a constant liquid pressure. If the leakage is close to zero and the pressure difference is stably maintained within the set range, it means that the air tightness is good. Targeting is reflected by comparing the spatial coordinate difference between the occluder placement position and the preset target occluding position. If the deviation is less than the set tolerance, it is determined to be accurately positioned. Stability reflects the ability of the occluder to maintain under dynamic disturbances such as voltage change and current change. It is quantified by monitoring the structural deformation rate, pressure difference fluctuation amplitude, and leakage trend of the occluding state within a certain disturbance cycle. If the sealing state is still maintained under the disturbance and the recovery ability is strong, it means that the stability is high.

[0027] After clarifying the blocking characteristics, a supervised training architecture based on the adversarial principle is constructed, using the generative adversarial network as the basic framework. The overall model is divided into a generation end and a discrimination end. The data required for training comes from the principle database of the occluder, which covers a large amount of historical sample test data, experimental condition records and corresponding blocking result labels, providing structured support for model training. The discrimination architecture is a two-layer structure, including a layer of test discrimination and a second layer of adjustable discrimination. The first layer of test discrimination is used to identify whether the occluder meets the basic performance requirements under standard working conditions; the second layer of adjustable discrimination dynamically adjusts the judgment threshold under the premise of environmental variable disturbance to judge the stability and adaptability of the occluder under changing conditions.

[0028] During the training process, the first layer of test discrimination training is performed with the plugging characteristics as input, and the labels of air tightness, targeting, and stability are matched through supervised learning, and the discrimination accuracy is optimized; then, the second layer of adjustable discrimination is trained with various disturbance conditions data in the principle database as input, so that it can automatically adjust the discrimination boundary according to external conditions such as flow rate changes and pressure disturbances, and realize accurate identification of abnormal states. For example, in a flow field with severe pressure fluctuations, the second layer of discrimination can actively relax the tolerance range of the target offset to avoid misjudgment.

[0029] After training, the entire generation-discrimination architecture is structurally disassembled, the discrimination end is retained as an independent component, and its parameters are compressed and encapsulated to build a lightweight discrimination module suitable for embedded systems. The discrimination component is embedded and deployed in the test system, and a communication connection is established with the test module through an interface protocol to achieve real-time reception and processing of test data. During system operation, the discrimination component can continuously receive the first physical test data and simulation test data, execute a two-layer discrimination logic, support dynamic decision-making and feedback control of the test process, and ultimately achieve intelligent identification and closed-loop verification of the airtightness, targeting, and stability of the occluder.

[0030] Further, in the system provided by the application embodiment, the deployment unit 12 is further configured to:

[0031] Obtain the principle database of the plugging device; the discrimination architecture is a two-layer architecture, including a first-layer test discrimination and a second-layer adjustable discrimination; based on the plugging characteristics, perform the first-layer test discrimination training, and based on the principle database, perform the second-layer adjustable discrimination training.

[0032] In the embodiment of the present application, first, the pre-established principle database of the plugging device is called. A large amount of key performance data of the plugging device in different test scenarios is stored in this database. The data content includes the pressure difference change curve (used to reflect airtightness), the leakage volume per unit time, the spatial offset between the center point of the plugging device and the target area (used to characterize targeting), and the plugging holding time and performance fluctuation amplitude under disturbance conditions (used to evaluate stability). All data has been standardized and is labeled with the plugging result tags manually, clearly indicating whether each group of data is "plugging standard condition" or "plugging anomaly" for supervised training.

[0033] Based on this database, a discrimination architecture is constructed, and a two-layer structure design is adopted, including a first-layer test discrimination and a second-layer adjustable discrimination. Among them, the first-layer test discrimination training takes three performance indicators of the plugging device as inputs, namely airtightness, targeting, and stability. First, the maximum-minimum normalization method is used to perform unified scale conversion on the original data. Subsequently, statistical analysis methods are used to calculate the distribution intervals of various features in the standard condition and the abnormal state, and based on this, performance boundary values are determined, such as the leakage volume is less than 0.01 mL / min, the offset distance is less than 2 mm, etc. Based on these boundary values as the discrimination basis, a training data set is constructed and the support vector machine (SVM) algorithm is used for training to realize the automatic identification of the plugging standard condition and the plugging anomaly.

[0034] When the output of the first-layer test discrimination is "abnormal", the second-layer adjustable discrimination is further called for refined judgment. During the training process, the data samples labeled as "abnormal" are screened out from the principle database, and the corresponding external operation parameters and environmental variables of each group of data are extracted, including the insertion force, the plugging deployment angle, the flow rate change amplitude, etc. To clarify the relationship between these variables and the plugging anomaly, the univariate linear regression analysis method is used to model the correlation between each operation variable and the abnormal label, and the influence degree of the variable on the anomaly is judged through the regression coefficient, and the interference items with weak influence are removed.

[0035] After obtaining the set of effective variables, a discriminant model is constructed using the logistic regression method, with the operating parameters as the input and the abnormal type label as the output. Through training, a model is formed so that the system can determine the source of the abnormality based on the operating conditions and environmental status. For example, it can determine whether it is slippage caused by insufficient insertion force or positioning failure caused by deviation in the deployment angle. The finally trained two-layer adjustable discriminant model has the ability to classify the causes of plugging abnormalities and can work in coordination with the first-layer model to complete the intelligent and hierarchical plugging device performance identification and diagnosis process.

[0036] Further, in the system provided by the application embodiment, the deployment unit 12 is further configured to:

[0037] Determine the characteristic boundary values of the plugging standard conditions and plugging abnormalities according to the plugging characteristics; based on the characteristic boundary values, take the plugging standard conditions and plugging abnormalities as the discriminant targets, and perform the first-layer test discriminant training.

[0038] In the embodiment of the present application, when performing the first-layer test discriminant training, first, feature extraction is performed on the labeled samples in the principle database based on the three indicators of airtightness, targeting, and stability in the plugging characteristics. The airtightness is represented by the leakage volume per unit time, the targeting is reflected by the offset distance between the center point of the plugging device and the target plugging position, and the stability is measured by the time for maintaining the plugging state under a perturbed environment. For the convenience of subsequent processing, a normalization method is used to unify the three types of characteristic values into the same numerical interval.

[0039] Next, statistical analysis methods are used to calculate the value ranges of various features in the "plugging standard conditions" and "plugging abnormality" samples respectively, and the characteristic boundary values are set accordingly. Specifically, the airtightness qualification standard is that the leakage amount is not greater than 0.01 mL / min, the targeting compliance standard is that the plugging offset distance does not exceed 2 mm, and the stability judgment threshold is set that the plugging maintenance time is greater than 30 seconds.

[0040] Based on these characteristic boundary values, the training samples are re-divided, and a binary classification data set of "plugging standard conditions" and "plugging abnormalities" is constructed. The support vector machine (SVM) method is used for model training, with the three normalized plugging characteristics as the input features and the annotation result as the output target. After training, the obtained first-layer test discriminant model can accurately identify whether the current state meets the basic performance requirements according to the input plugging characteristic data, providing a decision basis for the subsequent discriminant process.

[0041] Further, in the system provided by the application embodiment, the deployment unit 12 is further configured to:

[0042] An analog terminal interface and a physical terminal interface are opened in the discrimination component; a communication connection between the discrimination component and the test module is established according to the analog terminal interface, and a data import thread is deployed according to the physical terminal interface.

[0043] In the embodiment of the present application, to achieve data interaction with different test paths, an analog terminal interface and a physical terminal interface are first opened inside the discrimination component. The analog terminal interface is used to receive simulation environment data from the test module, including simulation parameters such as flow field pressure, velocity field distribution, and perturbation characteristics; the physical terminal interface is used to receive the original monitoring data collected during the first physical test, such as leakage volume, plugging offset, and structural stability measurement values.

[0044] To achieve real-time discrimination of simulation data, a communication connection between the discrimination component and the test module is established based on the analog terminal interface. This connection is established through a standard data bus protocol (such as UART, CAN, or RS485), enabling the variable output during the simulation process to be transmitted into the discrimination component in real time, for triggering the subsequent state determination process. At the same time, to ensure the orderly import of physical test data, based on the physical terminal interface, a data import thread is deployed. This thread uses a sequential buffer mechanism and timestamp marking to perform queue caching and batch import of multiple indicator data collected from the test platform, achieving temporal alignment with the simulation data.

[0045] The determination unit 13 is used for the discrimination component to determine the first test data, determine the first test result, trigger the test module, perform a two-stage mechanical test, determine the second simulation data, and determine the second test result based on the discrimination component. The two-stage mechanical test includes a static test and a dynamic test, which are driven by cross-linking of the plugging condition variable and the mechanical environment variable.

[0046] In the embodiment of the present application, the discrimination component is first called to identify and process the first test data. The first test data is provided by the test unit 11 and contains the key performance indicators of the plugging device in a static environment, such as leakage volume, plugging offset distance, and plugging maintenance time. A pre-trained one-layer test discrimination model is loaded inside the discrimination component, and a support vector machine (SVM) algorithm is used for binary classification identification. Using the preset airtightness, targeting, and stability boundary values as the classification criteria, it is determined whether the current sample is "qualified" or "abnormal", generating the first test result.

[0047] When the first test result meets the standard, the determination unit 13 triggers the test module to perform a two-stage mechanical test. The test process is based on the plugging condition variables and mechanical environment variables, generates multiple variable pairs through cross-linking combination, constructs various typical test conditions, and drives the test module to run based on the preset drive mapping relationship. By setting the timing test variables, with the variable switching as the independent variable and the response result as the dependent variable, the drive control of the static test and dynamic test is completed, and the performance simulation of the plugging device under stable state and disturbed environment is realized.

[0048] During the test, a tracking medium is introduced to assist data collection. The tracking medium is respectively arranged inside the plugging device and in the flow field environment to obtain information such as flow direction change, plugging effect, and disturbance response. The above process forms the second simulation data, and the discrimination component performs re-analysis based on this data, outputs the second test result, and finally realizes the systematic identification and classification judgment of the comprehensive performance of the plugging device.

[0049] Furthermore, the system provided by the application embodiment is also used for:

[0050] If the first test result does not meet the standard, execute the pipeline plugging abnormal alarm; if the first test result meets the standard, trigger the test module to perform a two-stage mechanical test.

[0051] In the embodiment of the present application, after the discrimination component outputs the first test result, if it is determined that the standard is not met, that is, any one of the airtightness, targeting, or stability indicators of the plugging device does not meet the set boundary value, the pipeline plugging abnormal alarm is immediately executed, and the current plugging device is prompted with an abnormal signal for basic performance defects, and the subsequent test process is terminated. If the first test result meets the standard, that is, the basic performance of the plugging device meets the requirements, the test module is triggered to continue performing the two-stage mechanical test.

[0052] Furthermore, in the system provided by the application embodiment, the determination unit 13 is also used for:

[0053] Perform cross-linking combination on the plugging condition variables and the mechanical environment variables to determine N variable pairs; determine the drive plug-in of the test module, establish the drive mapping between the drive plug-in and each variable, and determine the drive relationship; perform simulation test drive on the test module according to the drive relationship and the N variable pairs.

[0054] In the embodiment of the present application, first perform cross-linking combination on the plugging condition variables and the mechanical environment variables. This process uses the Cartesian product arrangement method, that is, each plugging condition variable (such as insertion force, deployment angle, plugging depth) is combined with each mechanical environment variable (such as flow velocity disturbance frequency, periodic pressure amplitude, shear stress level) in pairs to construct variable pairings covering various typical plugging scenarios, and finally obtain N variable pairs.

[0055] After the variable combination is completed, identify the execution units in the test module for controlling each test operation, that is, identify the driver plug-ins. This process uses the parameter-function matching method. For each control dimension involved in a variable pair, match the corresponding driver interface. For example, the deployment angle variable is executed by a plug-in with the ability to rotate output, and the flow rate perturbation is completed by a plug-in that controls the pump speed. By establishing a plug-in-variable mapping table, bind the variable input to the control channels of specific plug-ins, and then determine the control path corresponding to each variable, forming a clear driving relationship.

[0056] After that, in the simulation test driving stage, according to the driving relationship and N variable pairs, first determine the timing test variables for the driving process, that is, arrange multiple variable pairs in order as the test input sequence; then use the input parameters during the variable switching process as independent variables and the corresponding execution responses in the driving relationship as dependent variables to perform a dynamic loading operation on the test module, so as to realize the continuous simulation test of the plugging device under different working conditions.

[0057] Furthermore, in the system provided by the application embodiment, the determination unit 13 is further configured to:

[0058] Determine the timing test variables according to the N variable pairs, where the timing test variables include at least one variable pair; use the variable switching of the timing test variables as the independent variable and the dependent variable based on the driving relationship as the dependent variable to perform a simulation test drive on the test module.

[0059] In the embodiment of the present application, first, according to the N variable pairs, use the time scheduling method to arrange them in an orderly manner to determine the timing test variables. The timing test variables include at least one variable pair and are used to construct a static or dynamic test process. In the static test scenario, load a variable pair within a fixed time period, such as "insertion force is 3N, flow rate perturbation frequency is 5Hz", to keep the loading state constant and evaluate the response characteristics of the plugging device under steady-state conditions. In dynamic testing, set multiple variable pairs to switch in sequence according to time, and simulate complex working conditions by continuously changing the loading parameters, such as continuously applying combinations such as "deployment angle 15°, flow rate perturbation 10Hz" to "deployment angle 25°, flow rate perturbation 15Hz", etc., to test the adaptability and transition stability of the plugging device.

[0060] During the execution process, use the variable switching in the timing test variables as a trigger event, and extract the plugging condition variables and mechanical environment variables in each variable pair as independent variables. These independent variables are used as test input parameters and directly affect the loading state during the test process, such as the magnitude of the insertion force and the level of the perturbation frequency. The scheduler calls these parameters one by one according to the test time points and issues control instructions to achieve variable switching that advances according to the predetermined test plan.

[0061] Subsequently, based on the established driving relationship and according to the control content corresponding to the current independent variable, its corresponding dependent variable is determined, that is, the controlled response action matching the independent variable. For example, when the insertion force is the independent variable, its corresponding dependent variable is to load the insertion action of the corresponding magnitude; when the flow rate perturbation frequency is the independent variable, its corresponding dependent variable is to apply a perturbation signal of the matching frequency. After each variable switch, the control path is rematched according to the driving relationship to achieve seamless transition between different loading combinations.

[0062] Finally, according to the pairing relationship between the above-mentioned independent variable and the dependent variable, a simulation test drive is implemented on the test module. Under the timing control, different variable pairs are gradually loaded to ensure that each pair of parameters acts on the test process at the correct time point, and a loading environment that meets the expectations is constructed. This process can cover the performance changes of the plug under various plugging conditions and mechanical perturbation combinations, improving the integrity and authenticity of the test.

[0063] Furthermore, in the system provided by the application embodiment, the determination unit 13 is further configured to:

[0064] Introduce a tracking medium, where the tracking medium includes a first tracking medium inside the plug and a second tracking medium in the mechanical environment; assist the tracking medium to perform a two-order mechanical test to obtain the second simulation data.

[0065] In the embodiment of the present application, a tracking medium is introduced to assist in observing and recording the real state changes of the plug during the loading process. The tracking medium includes a first tracking medium inside the plug and a second tracking medium in the mechanical environment, which are respectively used to reflect the flow and force changes in the internal plugging channel and the external flow field environment.

[0066] First, a first tracking medium is injected into the plug. Usually, a fluid medium with high visibility or signal response ability such as a fluorescent tracer liquid, a microparticle tracer liquid, or a contrast liquid is selected. Through the change of its flow trajectory in the internal flow channel, the pressure distribution, seal integrity, and micro-leakage path inside the plugging cavity can be reflected. For example, in the static test stage, the first tracking medium should remain in a stable state. If it is observed that it shows irregular diffusion in the sealing area, it indicates that there may be plugging defects.

[0067] Secondly, a second tracking medium is arranged in the simulated external mechanical environment to visualize the conduction path and action range of controlled perturbations (such as flow rate pulses, shear loads) on the external fluid environment. This type of medium is mostly used in the dynamic test stage to assist in showing the stress transfer effect of external perturbation loading on the surface or edge area of the plug. For example, in a flow rate perturbation environment, by tracking the perturbation trajectory of the second medium, the stability and stress response ability of the plug in a periodic flow field can be evaluated.

[0068] During the test execution, the behavior trajectories of the first tracking medium and the second tracking medium are synchronously recorded by means of a high-frame-rate image acquisition device, an optical sensor, a magnetic probe, etc. Combining the loading timings of the plugging condition variables and the mechanical environment variables, the dynamic mapping of the test response process is realized. Finally, these trajectory data are integrated to form the second simulation data for quantitatively analyzing the response performance of the plugging device under the full-field stress loading.

[0069] A display unit 14 is configured to display the second test result on a terminal interface.

[0070] In the embodiment of the present application, after the test is completed, the second test result is output to the interface in real time through the display unit 14, presenting key data including the sealing performance change of the plugging device in the two-stage mechanical test, the tracking medium trajectory, and the determination result, etc., enabling the user to directly view the performance of the plugging device under various test conditions on the terminal interface.

[0071] In the embodiment of the present application, in summary, the embodiment of the present application has at least the following technical effects:

[0072] The present application conducts the first physical test on the plugging device to determine the first test data; introduces the mechanical environment by simulating the flow field cycle, builds a test module based on the plugging simulation of the plugging device, introduces a discrimination component based on the plugging characteristics, and is embedded in the test system, where the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination; the discrimination component determines the first test result for the first test data, triggers the test module to perform a two-stage mechanical test, determines the second simulation data and makes a determination based on the discrimination component to determine the second test result, where the two-stage mechanical test includes a static test and a dynamic test, and is driven by the cross-linking of the plugging condition variables and the mechanical environment variables; displays the second test result on a terminal interface. The present invention solves the technical problems in the prior art that rely on a single physical test method, are difficult to comprehensively evaluate the plugging performance, and lack an intelligent evaluation mechanism and standard unity. By introducing a mechanical simulation environment and a double-layer discrimination component based on adversarial training, a closed-loop test process of hierarchical detection and variable drive is constructed, achieving the technical effect of realizing the systematic and intelligent test of the plugging device performance.

[0073] Embodiment 2, based on the same inventive concept as the pipeline plugging test system of a plugging device in the foregoing embodiment, as Figure 2 shown, the embodiment of the present application provides a pipeline plugging test method for a plugging device, and the method includes:

[0074] Perform the first physical test on the occluder to determine the first test data; introduce a mechanical environment through a simulated flow field cycle, build a test module based on the occlusion simulation of the occluder, introduce a discrimination component based on the occlusion characteristics, and deploy it embedded in the test system, where the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination; the discrimination component determines the first test result for the first test data, triggers the test module, performs a two-stage mechanical test, determines the second simulation data, and makes a determination based on the discrimination component to determine the second test result, where the two-stage mechanical test includes a static test and a dynamic test, and is driven by the cross-linking of the occlusion condition variables and the mechanical environment variables; display the second test result on the terminal interface.

[0075] Furthermore, when introducing a discrimination component based on the occlusion characteristics, the method further includes:

[0076] Determine the occlusion characteristics, where the occlusion characteristics at least include airtightness, targeting, and stability; for the occlusion characteristics, perform supervised training based on the adversarial principle to determine the discrimination component, where the discrimination component is the discrimination architecture disassembled after training of the generative-discriminative architecture; embed and deploy the discrimination component in the test system and establish a communication connection with the test module.

[0077] Furthermore, when performing supervised training based on the adversarial principle to determine the discrimination component, the method further includes:

[0078] Obtain the principle database of the occluder; the discrimination architecture is a two-layer architecture, including a first-layer test discrimination and a second-layer adjustable discrimination; based on the occlusion characteristics, perform the first-layer test discrimination training, and based on the principle database, perform the second-layer adjustable discrimination training.

[0079] Furthermore, when performing the first-layer test discrimination training based on the occlusion characteristics, the method further includes:

[0080] According to the occlusion characteristics, determine the characteristic boundary values of the normal occlusion condition and the abnormal occlusion; based on the characteristic boundary values, take the normal occlusion condition and the abnormal occlusion as the discrimination targets, and perform the first-layer test discrimination training.

[0081] Furthermore, after the embedded deployment in the test system, the method further includes:

[0082] Open a simulation end interface and a physical end interface in the discrimination component; establish a communication connection between the discrimination component and the test module according to the simulation end interface, and deploy a data import thread according to the physical end interface.

[0083] Furthermore, the method further includes:

[0084] If the first test result fails to meet the standard, execute the abnormal warning for pipeline blockage; if the first test result meets the standard, trigger the test module and execute the two-stage mechanical test.

[0085] Further, when executing the two-stage mechanical test, the method further includes:

[0086] Cross-link and combine the blockage condition variables and the mechanical environment variables to determine N variable pairs; determine the drive plug-in of the test module, establish the drive mapping between the drive plug-in and each variable, and determine the drive relationship; according to the drive relationship and the N variable pairs, perform a simulation test drive on the test module.

[0087] Further, when performing a simulation test drive on the test module according to the drive relationship and the N variable pairs, the method further includes:

[0088] According to the N variable pairs, determine the timing test variables, where the timing test variables include at least one variable pair; use the variable switching of the timing test variables as the independent variable, and use the dependent variable that changes with the drive relationship as the dependent variable to perform a simulation test drive on the test module.

[0089] Further, when executing the two-stage mechanical test to determine the second simulation data, the method further includes:

[0090] Introduce a tracking medium, where the tracking medium includes a first tracking medium in the plug and a second tracking medium in the mechanical environment; assist the tracking medium to execute the two-stage mechanical test to obtain the second simulation data.

[0091] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0093] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A pipeline plugging test system for a plugging device, characterized in that, The system includes: A test unit for performing a first physical test on the occluder to determine first test data. Specifically, the test is carried out by installing the occluder to be tested in a closed test pipeline, gradually applying a preset liquid pressure in a constant-pressure liquid injection manner to make the occluder enter a stable occlusion state, continuously collecting the pressure response information of the occluder during the pressurization process through differential pressure sensors arranged at both ends of the occluder, and simultaneously using a leakage channel to record the liquid leakage situation per unit time in the occlusion state. As the test time progresses, the occlusion onset time, differential pressure holding ability, and key physical changes during the leakage process are synchronously collected, thereby generating the first test data; A deployment unit for introducing a mechanical environment through a simulated flow field cycle, building a test module based on the occlusion simulation of the occluder, and introducing a discrimination component based on occlusion characteristics, which is embedded in the test system. The discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination; Specifically, the deployment unit first constructs a simulated flow field cycle system. This system forms a closed fluid loop using a variable-speed circulation pump and a control valve array, and realizes the reproduction of periodic mechanical disturbances by controlling the flow rate fluctuation, pressure pulse frequency, and fluid viscosity. In this simulated flow field, in combination with the actual occlusion application requirements, the occluder structure is installed and a occlusion simulation test module is established around its working cavity to ensure that it operates within the simulation mechanical boundary under the action of controlled variables; Subsequently, the deployment unit introduces a discrimination component based on occlusion characteristics and integrates it into the internal communication and control bus of the test system in an embedded deployment manner. This discrimination component is constructed based on an adversarial training mechanism and is in the form of a double-layer architecture. The first-layer test discrimination is responsible for quickly performing binary classification on the initial physical test data to determine whether the occlusion state meets the standard, and the second-layer adjustable discrimination adjusts the discrimination boundary according to the perturbation input from environmental variables to achieve accurate determination for dynamic load changes; A determination unit for the discrimination component to determine the first test data to obtain a first test result, trigger the test module, perform a two-stage mechanical test to determine second simulation data, and make a determination based on the discrimination component to obtain a second test result. The two-stage mechanical test includes a static test and a dynamic test, which are driven by the cross-linking of occlusion condition variables and mechanical environment variables; Specifically, first, the discrimination component is called to identify and process the first test data, which is provided by the test unit and contains the key performance indicators of the occluder in a static environment. The first-layer test discrimination model pre-trained is loaded inside the discrimination component, and the support vector machine algorithm is used for binary classification identification. Using the preset airtightness, targeting, and stability boundary values as the classification criteria, it is determined whether the current sample meets the standard or is abnormal, and a first test result is generated; Among them, when the first test result meets the standard, the determination unit triggers the test module to perform two-stage mechanical tests. The test process is based on the plugging condition variables and mechanical environment variables, generates multiple variable pairs through cross-linking combination, constructs various test conditions, and drives the test module to run based on the preset drive mapping relationship. By setting the timing test variables and using the variable switching as the independent variable and the response result as the dependent variable, the drive control of the static test and the dynamic test is completed, and the performance simulation of the plugging device under the stable state and the disturbed environment is realized; Among them, during the test process, a tracking medium is introduced to assist data collection. The tracking medium is respectively arranged inside the plugging device and in the flow field environment to obtain information on flow direction changes, plugging effects, and disturbance responses. The above process forms the second simulation data, and the discrimination component performs re-analysis based on this data and outputs the second test result, finally realizing the systematic identification and grading judgment of the comprehensive performance of the plugging device; A display unit for displaying the second test result on the terminal interface.

2. The pipeline plugging test system for a plugging device according to claim 1, characterized in that, The deployment unit is used for: Determine the plugging characteristics, where the plugging characteristics at least include airtightness, targeting, and stability; Based on the adversarial principle, perform supervised training for the plugging characteristics to determine the discrimination component, where the discrimination component is the discrimination architecture disassembled after the generation-discrimination architecture training; Embed and deploy the discrimination component in the test system and establish a communication connection with the test module.

3. The pipeline plugging test system for a plugging device according to claim 2, characterized in that, The deployment unit is used for: Obtain the principle database of the plugging device; The discrimination architecture is a two-layer architecture, including a first-layer test discrimination and a second-layer adjustable discrimination; Based on the plugging characteristics, perform the first-layer test discrimination training, and based on the principle database, perform the second-layer adjustable discrimination training.

4. The pipeline plugging test system for a plugging device according to claim 3, characterized in that, The deployment unit is used for: According to the plugging characteristics, determine the characteristic boundary values of the plugging standard condition and the plugging abnormality; Based on the characteristic boundary values, and taking the plugging standard condition and the plugging abnormality as the discrimination targets, perform the first-layer test discrimination training.

5. The pipeline plugging test system for a plugging device according to claim 4, characterized in that The deployment unit is used for: Open a simulation end interface and a physical end interface in the discrimination component; According to the simulation end interface, establish a communication connection between the discrimination component and the test module, and according to the physical end interface, deploy a data import thread.

6. The pipeline plugging test system for a plugging device according to claim 1, characterized in that, If the first test result does not meet the standard, execute a pipeline plugging abnormality alarm; If the first test result meets the standard, trigger the test module to perform two-stage mechanical tests.

7. The pipeline plugging test system for a plugging device according to claim 1, characterized in that The determination unit is used for: Perform cross-linking combination on the plugging condition variables and the mechanical environment variables to determine N variable pairs; Determine the drive plug-in of the test module, establish the drive mapping between the drive plug-in and each variable, and determine the drive relationship; According to the drive relationship and the N variable pairs, perform simulation test drive on the test module.

8. The pipeline plugging test system for a plugging device according to claim 7, characterized in that, The determination unit is used for: According to the N variable pairs, determine the timing test variables, where the timing test variables include at least one variable pair; Taking the variable switching of the timing test variables as the independent variable and the dependent variable based on the drive relationship as the dependent variable, perform simulation test drive on the test module.

9. The pipeline plugging test system for a plugging device according to claim 1, characterized in that, The determination unit is used for: Introduce a tracking medium, wherein the tracking medium includes a first tracking medium within the plugging device and a second tracking medium within the mechanical environment; Assist the tracking medium to perform a two-stage mechanical test to obtain the second simulation data.

10. A pipeline plugging test method for a plugging device, characterized in that, The method is executed by a pipeline plugging test system for a plugging device according to any one of claims 1 to 9, and includes: Perform a first physical test on the plugging device to determine the first test data; Introduce a mechanical environment through a simulated flow field cycle, build a test module for the plugging simulation of the plugging device, introduce a discrimination component based on the plugging characteristics, and deploy it embedded in the test system, wherein the discrimination component includes a first-layer test discrimination and a second-layer adjustable discrimination; The discrimination component determines the first test result for the first test data, triggers the test module, performs a two-stage mechanical test, determines the second simulation data, and determines the second test result based on the discrimination component, wherein the two-stage mechanical test includes a static test and a dynamic test, and is driven by the cross-linking of the plugging condition variable and the mechanical environment variable; Display the second test result on the terminal interface.

Images