Method, device and equipment for evaluating service life of plunger packing combined seal and medium

Abstract

The invention relates to the field of sealing packing, and discloses a plunger packing combination sealing life evaluation method, device, equipment and medium, and the method comprises the steps: installing a to-be-evaluated plunger packing combination to a test bench, and obtaining a target test bench; operating the target test bed under a short-term no-load condition, and detecting a first performance parameter of the plunger packing combination; calculating a first dimensionless index according to the first performance parameter, and detecting a first physical parameter between a plunger and a packing in the plunger and packing combination; and inputting the first dimensionless index and the first physical parameter into a trained BP neural network model to obtain a life prediction value of the plunger packing combination. The problems that according to an existing plunger packing sealing life test method, test parameters are not comprehensive, and an evaluation system is not complete are solved.

Description

Technical Field

[0001] This invention relates to the field of sealing packing, and more specifically to a method, apparatus, equipment, and medium for evaluating the lifespan of plunger packing combination seals. Background Technology

[0002] As a key power device widely used in petroleum, chemical and other fields, the core working principle of the plunger pump relies on the reciprocating motion of the plunger within the cylinder to achieve fluid intake and discharge. In specific applications such as oilfield water injection, plunger pumps need to operate at high speeds under extreme conditions of high pressure and high corrosion, which places extremely high demands on the plunger pump's packing seal system. The performance of the packing seal system directly affects the operating efficiency and safety of the plunger pump. Poor sealing will lead to serious leakage problems, shorten the service life of the equipment, and even cause safety accidents.

[0003] Current methods for testing the lifespan of plunger packing seals primarily focus on wear and leakage, neglecting key parameters such as packing stress and frictional changes. While some tests monitor friction and velocity, they do not comprehensively consider contact stress distribution and its impact, resulting in limitations in the evaluation system. Existing technologies ignore the interactions of various factors within the system, such as dimensional tolerances, fluid pressure, and surface hardness, on sealing performance. Consequently, lifespan prediction accuracy is insufficient, impacting equipment maintenance plans and potentially leading to equipment failure or resource waste. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, equipment and medium for evaluating the life of plunger packing combination seals, in order to solve the problems of incomplete test parameters and incomplete evaluation system in existing plunger packing seal life test methods.

[0005] In a first aspect, embodiments of the present invention provide a method for evaluating the lifespan of a plunger packing assembly seal, the method comprising:

[0006] The plunger packing assembly to be evaluated is installed on the test bench to obtain the target test bench;

[0007] The target test bench was operated under short-term no-load conditions, and the first performance parameter of the plunger packing assembly was detected.

[0008] Calculate the first dimensionless index based on the first performance parameter, and detect the first physical parameter between the plunger and packing in the plunger packing assembly;

[0009] The first dimensionless index and the first physical parameter are input into the trained BP neural network model to obtain the predicted life value of the plunger packing assembly.

[0010] In an optional embodiment of this application, the first performance parameter includes: a first frictional force, a first contact stress distributed along the axial direction, and a first surface temperature;

[0011] The first dimensionless index includes the stress distribution index, the wear index, and the under-sealing index;

[0012] The first dimensionless exponent is calculated based on the first performance parameter, using the following formula:

[0013]

[0014] Where Y is the stress distribution index; M is the wear index; Q is the under-sealing index; W is the temperature index; σ MSD σ is the root mean square deviation of the first contact stress; MV σ is the average value of the first contact stress; MPD σ is the maximum positive deviation of the first contact stress; MND The maximum negative deviation of the first contact stress; t C t is the first surface temperature; S This is the current room temperature.

[0015] In an optional embodiment of this application, before inputting the first dimensionless exponent and the first physical parameter into the trained BP neural network model, the method further includes:

[0016] Obtain samples of various platy cord combinations;

[0017] A short-term no-load test was performed on the packing sample to obtain the second dimensionless index and the second physical parameter corresponding to the packing sample.

[0018] The packing assembly sample was subjected to a lifetime test to obtain the lifetime duration of the packing assembly sample.

[0019] A training dataset is constructed based on the second dimensionless exponent, the second physical parameter, and the lifetime duration.

[0020] The pre-constructed BP neural network model is trained using the training dataset to obtain a trained BP neural network model.

[0021] In an optional embodiment of this application, the step of performing a short-term no-load test on the packing assembly sample to obtain the second dimensionless index and the second physical parameter corresponding to the packing assembly sample includes:

[0022] The packing assembly sample is installed on the test bench to obtain the training test bench;

[0023] The training test bench was operated under short-term no-load conditions, and the second performance parameters of the packing assembly samples were detected.

[0024] The second dimensionless index is calculated based on the second performance parameter, and the second physical parameter between the plunger and packing in the packing assembly sample is detected.

[0025] In an optional embodiment of this application, the step of performing a lifetime test on the packing assembly sample to obtain the lifetime of the packing assembly sample includes:

[0026] The training test bench is operated under preset working conditions, and the third contact mechanical parameters of the packing assembly sample are detected.

[0027] Obtain the target curve of the three-contact mechanical parameters changing over time, and determine the current leakage rate of the packing assembly sample based on the target curve;

[0028] When the current leakage rate reaches the specified leakage rate, the running time of the training test bench under preset working conditions is obtained, and the running time is used as the lifetime of the packing assembly sample.

[0029] In an optional embodiment of this application, constructing the training dataset based on the second dimensionless exponent, the second physical parameter, and the lifetime includes:

[0030] The life evaluation index is calculated based on the second dimensionless index and the life duration.

[0031] The formula for calculating life evaluation indicators is:

[0032]

[0033] Where S is the life evaluation index; L is the life duration; Y is the stress distribution index; M is the wear index; Q is the under-sealing index; and W is the temperature index.

[0034] The life evaluation index is integrated with the corresponding second dimensionless index, second physical parameter and life duration to obtain the corresponding sample data;

[0035] A training dataset is constructed using the sample data corresponding to each root combination sample.

[0036] In one optional embodiment of this application, the pre-built BP neural network model includes an input layer, a hidden layer, and an output layer;

[0037] The input layer includes multiple input units, wherein the input units are used to receive the second dimensionless exponent and the second physical parameter;

[0038] The hidden layer includes at least one hidden layer, wherein the hidden layer is used to process the second dimensionless exponent and the second physical parameter received by the input layer, and to perform a nonlinear transformation on the second dimensionless exponent and the second physical parameter through an activation function to obtain the predicted life value of the plunger packing assembly.

[0039] The output layer includes an output unit, wherein the output unit is used to output the predicted life value of the plunger packing assembly.

[0040] Secondly, embodiments of the present invention provide a life evaluation device for a plunger packing combination seal, the device comprising:

[0041] The mounting module is used to install the plunger packing assembly to be evaluated onto the test bench to obtain the target test bench;

[0042] The detection module is used to operate the target test bench under short-term no-load conditions and detect the first performance parameter of the plunger packing assembly;

[0043] The calculation module is used to calculate the first dimensionless index based on the first performance parameter and to detect the first physical parameter between the plunger and the packing in the plunger packing assembly.

[0044] The input module is used to input the first dimensionless index and the first physical parameter into the trained BP neural network model to obtain the life prediction value of the plunger packing assembly.

[0045] Thirdly, embodiments of the present invention provide a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0046] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions that cause a computer to perform the method described in the first aspect or any of its corresponding embodiments.

[0047] The method provided in this application has the following beneficial effects:

[0048] The method provided in this application creates an unloaded working environment, runs a target test bench, and detects the first performance parameters of the plunger-packing assembly to gain a preliminary understanding of its basic performance. Introducing a dimensionless exponent eliminates the barrier to comparison between performance parameters of different dimensions, making the evaluation more objective and accurate. Performance parameters are converted into dimensionless exponents using a specific formula, facilitating data processing and model input. Simultaneously, the physical parameters between the plunger and packing are detected, providing direct information on structural and material properties. A trained BP neural network model is used to comprehensively consider the dimensionless exponent and physical parameters to accurately predict the lifespan of the plunger-packing assembly, improving the accuracy and reliability of the prediction.

[0049] The method provided in this application acquires various packing gland assembly samples, providing a rich data foundation for subsequent construction of training datasets and training of BP neural network models. Through short-term no-load testing, the second dimensionless index and second physical parameter of the packing gland assembly samples are obtained, providing necessary data for subsequent calculation of lifetime evaluation indicators and construction of training datasets. Through lifetime testing, the actual lifetime duration of the packing gland assembly samples is obtained, providing accurate label data for training the BP neural network model. By calculating lifetime evaluation indicators, the second dimensionless index, second physical parameter, and lifetime duration are integrated into sample data, facilitating subsequent construction of the training dataset. The pre-constructed BP neural network model is trained using the training dataset to obtain a model capable of accurately predicting the lifetime of plunger packing gland assemblies. The specific model structure (input layer, hidden layer, output layer) ensures the model's complexity and generalization ability, improving prediction accuracy. Attached Figure Description

[0050] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0051] Figure 1 This is a schematic flowchart of a life evaluation method for a plunger packing combination seal according to some embodiments of the present invention.

[0052] Figure 2 This is a schematic diagram of surface temperature measurement of the plunger packing assembly according to an embodiment of the present invention;

[0053] Figure 3 This is a schematic diagram of stress measurement for a plunger packing assembly according to an embodiment of the present invention;

[0054] Figure 4 This is a structural block diagram of a life evaluation device for a plunger packing combination seal according to an embodiment of the present invention.

[0055] Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] According to embodiments of the present invention, a method, apparatus, device, and medium for evaluating the life of a plunger packing combination seal are provided. It should be noted that the steps shown in the flowcharts in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0058] Example 1

[0059] This embodiment provides a method for evaluating the lifespan of a plunger packing assembly seal. Figure 1 This is a flowchart of a life evaluation method for a plunger packing assembly seal according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0060] Step S11: Install the plunger packing assembly to be evaluated onto the test bench to obtain the target test bench.

[0061] In this embodiment of the application, to evaluate the performance of the plunger packing assembly under specific test conditions, it is installed on a test bench to construct a test system. On this system, parameters such as friction, contact stress, and surface temperature are collected and measured, and short-term no-load test runs and life tests are conducted to comprehensively evaluate the performance of the plunger packing assembly.

[0062] Step S12: Run the target test bench under short-term no-load conditions and test the first performance parameters of the plunger packing assembly.

[0063] In this embodiment, a preliminary performance evaluation is performed on a plunger-packing assembly mounted on a test bench. Primary performance parameters such as friction, contact stress, and surface temperature are measured through short-term no-load operation. Friction reflects the fit and lubrication between the plunger and packing, contact stress reflects the tightness of contact and wear areas, and surface temperature reflects the material's heat resistance and potential thermal failure.

[0064] Specifically, Figure 2This is a schematic diagram of surface temperature measurement of the plunger packing assembly provided in this embodiment, as shown below. Figure 2 As shown, a temperature measurement point is set near the plunger surface of the injection ring of the inner packing box. The injection ring, as a key component for injecting lubricating or sealing fluid, has a temperature at its location adjacent to the plunger surface that is crucial for evaluating the working condition of the packing assembly. Temperature signals are extracted through test holes for recording and analysis. This measurement method can reflect the surface temperature changes of the plunger-packing assembly in real time during operation, providing important temperature data support for system performance evaluation and life prediction.

[0065] Specifically, Figure 3 This is a schematic diagram of stress measurement for the plunger packing assembly provided in this embodiment, as shown below. Figure 3 As shown, multiple strain gauges are uniformly arranged axially on the outer side of the inner packing box to measure minute deformations on the object's surface, indirectly reflecting the stress state. Signal lines are led out through test holes to measure and record stress changes in the plunger packing assembly during operation in real time, providing crucial stress data support for system performance evaluation and life prediction. This measurement method also helps to promptly identify and resolve stress concentration issues, ensuring the safe and stable operation of the system.

[0066] Step S13: Calculate the first dimensionless index based on the first performance parameter, and detect the first physical parameter between the plunger and packing in the plunger-packing assembly.

[0067] In this embodiment, the first performance parameter includes: a first frictional force, a first contact stress distributed along the axial direction, and a first surface temperature; the first dimensionless index includes a stress distribution index, a wear index, and a poor sealing index.

[0068] Specifically, the first dimensionless exponent is calculated based on the first performance parameter, using the following formula:

[0069]

[0070]

[0071] Where Y is the stress distribution index; M is the wear index; Q is the under-sealing index; W is the temperature index; σ MSD σ is the root mean square deviation of the first contact stress; MV σ is the average value of the first contact stress; MPD σ is the maximum positive deviation of the first contact stress; MND The maximum negative deviation of the first contact stress; t C t is the first surface temperature; S This is the current room temperature.

[0072] Specifically, the initial performance evaluation of the plunger packing sealing system is conducted by collecting primary performance parameters such as friction force, axially distributed contact stress, and surface temperature during short-term no-load test runs. Based on these parameters, primary dimensionless indices such as stress distribution index, wear index, and under-sealing index are calculated to further evaluate system performance. The stress distribution index reflects the distribution of contact stress, the wear index reflects the degree of localized wear, and the under-sealing index reflects the degree of localized leakage. Simultaneously, the influence of surface temperature on material wear properties is considered, and a temperature index is calculated. When calculating the primary dimensionless indices, it is also necessary to test primary physical parameters such as the dimensional tolerances of the plunger and packing, and surface hardness, as these parameters also affect system performance.

[0073] Step S14: Input the first dimensionless index and the first physical parameter into the trained BP neural network model to obtain the predicted life value of the plunger packing assembly.

[0074] In this embodiment, the first dimensionless index (including stress distribution index, wear index, and under-sealing index) calculated earlier and the first physical parameter (such as tolerance dimension and surface hardness) are used as input data to form the input layer of the BP neural network model. This data is fed into the trained BP neural network model, which predicts the plunger packing assembly life through algorithms and weight adjustments, and outputs the predicted value. Based on the predicted value, the lifespan is assessed, and an operational decision is made: if the lifespan is short, it is replaced early; if the lifespan is long, it continues to be used and monitored periodically.

[0075] Example 2

[0076] In this embodiment of the application, before inputting the first dimensionless exponent and the first physical parameter into the trained BP neural network model, the following steps S21-S25 are further included:

[0077] Step S21: Obtain samples of various root combinations.

[0078] In this embodiment, it is necessary to identify and select different types of plunger packing combinations, including different materials, structures, or sizes, to ensure comprehensiveness and diversity of testing. After determining the test type, samples are collected and preprocessed, and the type, material, structure, size, and other relevant information of each sample are recorded in detail. This information is crucial for subsequent performance testing and evaluation.

[0079] Step S22: Perform a short-term no-load test on the packing bundle sample to obtain the second dimensionless index and the second physical parameter corresponding to the packing bundle sample.

[0080] In this embodiment of the application, step S22 includes the following steps A1-A3:

[0081] Step A1: Install the packing assembly sample onto the test bench to obtain the training test bench.

[0082] In this embodiment, one or more plunger packing combination samples are selected from a variety of samples for installation, representing different materials, structures, or sizes, based on test requirements or evaluation objectives. The selected samples are installed on a specially designed test bench and configured as necessary, including adjusting operating parameters and setting appropriate test conditions, to ensure the stability and consistency of the test environment.

[0083] Step A2: Run the training test bench under short-term no-load conditions and test the second performance parameters of the packing assembly sample.

[0084] In this embodiment, a training test bench is operated under short-term no-load conditions to simulate the initial state of the plunger pump before actual operation, and the performance of the packing assembly samples is evaluated. Secondary performance parameters of the samples, such as friction, contact stress, and surface temperature, are measured to gain a preliminary understanding of their behavior. These data are collected and analyzed for subsequent performance evaluation and lifespan prediction.

[0085] Step A3: Calculate the second dimensionless index based on the second performance parameter, and detect the second physical parameter between the plunger and packing in the packing assembly sample.

[0086] In this embodiment, based on the second performance parameters (such as friction, contact stress, and surface temperature) from a short-term no-load test run, dimensionless indices such as the stress distribution index Y, wear index M, and under-sealing index Q are calculated to intuitively reflect the contact stress distribution, wear degree, and sealing capability between the plunger and packing. Simultaneously, other physical parameters of the packing assembly samples, such as dimensional tolerances and surface hardness, are tested; these parameters affect the tightness of the fit and wear resistance. Comprehensive analysis of the dimensionless indices and other physical parameters provides a comprehensive evaluation of the packing assembly sample performance, offering important reference for subsequent life tests and performance evaluations.

[0087] Step S23: Perform a lifetime test on the packing assembly sample to obtain the lifetime duration of the packing assembly sample.

[0088] In this embodiment of the application, step S23 includes the following steps B1-B3:

[0089] Step B1: Run the training test bench under preset working conditions and test the third contact mechanical parameters of the packing assembly sample.

[0090] In this embodiment, the plunger pump test bench is started and run under preset operating conditions (such as specific fluid pressure, temperature, and rotational speed) to ensure a consistent and controllable test environment. Sensors and measuring devices are used to detect the third contact mechanical parameters (such as contact stress, friction, and contact area) of the packing assembly samples; these parameters are crucial for evaluating sample performance. The detected parameters are recorded and preliminarily analyzed.

[0091] Step B2: Obtain the target curve of the third contact mechanical parameter changing over time, and determine the current leakage rate of the packing assembly sample based on the target curve.

[0092] In this embodiment, the changes in the third contact mechanical parameter over time are monitored and recorded in real time during the life test, and a target curve of surface temperature change over time is plotted. The target curve is analyzed to observe surface temperature changes, and the leakage rate of the packing assembly sample is evaluated in conjunction with other phenomena (such as changes in friction, contact stress, and fluid leakage). An abnormally high surface temperature indicates a decrease in sealing performance and an increase in leakage rate; therefore, the current leakage situation can be inferred from the trend of surface temperature changes.

[0093] Step B3: When the current leakage rate reaches the specified leakage rate, obtain the running time of the training test bench under the preset working conditions, and use the running time as the lifetime of the packing assembly sample.

[0094] In this embodiment, the leakage rate of the plunger packing seal system is monitored in real time during the life test, which is an important indicator for evaluating the performance of the sealing system. A specific leakage rate is preset as an evaluation standard, representing an acceptable leakage level in practical applications. When the leakage rate reaches or exceeds this specified value, the sealing system is considered to have reached the end of its life. The running time of the test bench at this time is recorded as the life duration of the packing assembly sample. This is an important parameter for evaluating the performance of the sample and is also the basis for subsequent performance evaluation and life prediction.

[0095] Step S24: Construct a training dataset based on the second dimensionless exponent, the second physical parameter, and the lifetime duration.

[0096] In this embodiment of the application, step S24 includes the following steps C1-C3:

[0097] Step C1: Calculate the life evaluation index based on the second dimensionless index and life duration.

[0098] Specifically, the formula for calculating life assessment indicators is as follows:

[0099]

[0100] Wherein, S is the life evaluation index; L is the life duration; Y is the stress distribution index; M is the wear index; Q is the under-sealing index; and W is the temperature index.

[0101] Specifically, a training dataset is constructed based on the second dimensionless index, the second physical parameter, and the lifespan. The second dimensionless index encompasses three key indicators closely related to contact stress: the stress distribution index Y, the wear index M, and the under-sealing index Q, as well as the temperature index W. These together reflect the contact state and sealing performance between the plunger and packing. The second physical parameter includes other important physical quantities besides the dimensionless index, such as the dimensional tolerances of the plunger and packing, fluid pressure, and surface hardness. To more comprehensively evaluate the overall performance of the plunger sealing system, a comprehensive lifespan evaluation index S is calculated based on the second dimensionless index (Y, M, Q) and the lifespan L. This index considers not only the distribution of contact stress, wear degree, and sealing capability, but also the factor of lifespan, thus more accurately reflecting the actual performance of the plunger sealing system. By comprehensively considering the values ​​of these parameters, a specific numerical index can be obtained for intuitively evaluating the quality of the plunger sealing system. This comprehensive evaluation method helps to more fully understand the performance characteristics of the plunger sealing system, providing strong support for subsequent performance optimization and lifespan prediction.

[0102] Step C2 involves integrating the life evaluation indicators with the corresponding second dimensionless index, second physical parameter, and life duration to obtain the corresponding sample data.

[0103] In this embodiment, the life evaluation index S is a comprehensive indicator for evaluating the performance of the plunger sealing system. It is calculated based on physical quantities such as contact stress and temperature, reflecting different aspects of the system's performance. The second dimensionless index includes the stress distribution index Y, wear index M, under-sealing index Q, and temperature index W, while also considering other physical parameters such as dimensional tolerances, fluid pressure, and surface hardness. The life duration L is obtained through life testing and represents the operating time of the system when it reaches a specified leakage rate. This step aims to integrate these evaluation indices and parameters to form sample data containing comprehensive performance information of the plunger sealing system for subsequent model training and prediction, in order to gain a more comprehensive understanding of the system performance and optimize it.

[0104] Step C3: Construct a training dataset using the sample data corresponding to each root combination sample.

[0105] In this embodiment, the packing combination sample refers to different types of plunger packing combinations, such as aramid packing, carbon fiber, and rubber-reinforced fabric. For each sample, multiple data points are collected during short-term no-load trial runs and life tests, including physical quantities (such as friction, contact stress, and surface temperature) and calculated dimensionless indices (such as stress distribution index Y, wear index M, under-sealing index Q, and temperature index W) and other parameters (such as dimensional tolerances, fluid pressure, and surface hardness). These data are formatted for machine learning model training to form a training dataset. This dataset covers various packing combination samples, each with a series of features (such as dimensionless indices and physical parameters) and a target variable (lifetime or remaining life), providing comprehensive information for model training and prediction.

[0106] Step S25: Train the pre-built BP neural network model using the training dataset to obtain the trained BP neural network model.

[0107] In this embodiment, the pre-constructed BP neural network model includes an input layer, a hidden layer, and an output layer. The input layer includes multiple input units, which are used to receive a second dimensionless exponent and a second physical parameter. The hidden layer includes at least one hidden layer, which is used to process the second dimensionless exponent and the second physical parameter received by the input layer, and to perform a nonlinear transformation on the second dimensionless exponent and the second physical parameter through an activation function to obtain the predicted life value of the plunger packing assembly. The output layer includes an output unit, which is used to output the predicted life value of the plunger packing assembly.

[0108] It should be noted that the pre-built BP neural network model is a neural network model based on the BP (backpropagation) algorithm, which includes an input layer, hidden layers, and an output layer. The structure of this model is designed according to the requirements of plunger packing seal system life prediction.

[0109] Specifically, the model structure includes an input layer, a hidden layer, and an output layer. The input layer receives various input data, such as the second dimensionless exponent (stress distribution exponent Y, wear exponent M, under-sealing exponent Q, temperature exponent W) and second physical parameters (tolerance dimensions, fluid pressure, surface hardness, etc.). This data is crucial for evaluating the performance of the plunger packing seal system. The hidden layer, containing at least one layer, processes the data from the input layer, performing nonlinear transformations through activation functions to learn the complex relationship between the input and output data, and generating a predicted life value for the plunger packing assembly. The output layer outputs this predicted value, calculated based on the data from the input layer and the nonlinear transformations from the hidden layer, providing an important reference for predicting the life of the plunger packing seal system.

[0110] Specifically, during the training process, a training dataset was used to train the BP neural network model. This dataset contains multiple sets of sample data, each covering the input data required by the input layer and the corresponding life prediction target value. By continuously adjusting the model parameters, the predicted values ​​gradually approach the target values, ultimately resulting in a successfully trained BP neural network model. This model learns to predict the life of the plunger packing assembly from the input data and can be applied to life prediction of new sample data, realizing the function of evaluating the performance and predicting the life of the plunger packing sealing system.

[0111] As an example, firstly, a combination of aramid packing, carbon fiber, and rubber-reinforced fabric was selected as the packing assembly for testing. The test bench was constructed, and the selected packing assembly was placed inside the packing box. A short-term no-load test run was conducted on the test bench with the packing assembly, and relevant data were recorded, including a friction force of 100N, axial contact stress values ​​of 200N, 210N, 200N, 300N, 400N, 250N, 200N, 300N, 400N, and 250N respectively, and a surface temperature of 30℃. Based on these data, the mean axial contact stress was calculated to be 500N, the root mean square deviation of the contact stress was 77.95N, the sum of the contact stresses was 2710N, the maximum positive deviation was 322.05N, and the maximum negative deviation was 122.05N. Simultaneously, the working pressure P was measured to be 30MPa. Further calculations showed that the stress distribution index Y = 11.63, the wear index M = 4.13, and the under-sealing index Q = 1.56.

[0112] Secondly, life tests were conducted on a test bench, recording the changes in friction, contact stress, and surface temperature over time. During operation, the measured friction value was 500 N, the average contact stress was 600 N, and the surface temperature was 70 °C. Leakage was detected after 400 hours of operation. Based on these data, the temperature index W = (80 °C - 30 °C) / 30 °C = 1.67 was calculated, and a preliminary life evaluation index S = 3.19 was constructed (based on previous no-load operation data and life test data).

[0113] Next, the input layer of the BP artificial neural network was determined to have 8 units, including the stress distribution index, wear index, undersealing index, temperature index, plunger and packing tolerance dimensions, fluid pressure, and surface hardness. The output layer was determined to have 1 unit, representing the remaining lifetime. Multiple sets of experimental data were collected through short- to medium-term experiments, and the plunger and packing tolerance dimensions and plunger surface hardness were measured. The model was trained using 95 sets of data, and the remaining 5 sets were used as a test set for model evaluation.

[0114] Finally, the trained model is used for life prediction. Inputting current data, the model provides the corresponding life prediction results. A plunger packing life prediction model is determined for packing combinations of aramid, carbon fiber, and rubber-reinforced fabric. After a period of time, the model is used to determine the life status of the plunger packing and make operational decisions accordingly. The remaining life of the plunger packing sealing system is predicted using four dimensionless indices (stress distribution index, wear index, under-sealing index, and temperature index), and the packing performance is evaluated using the lifespan evaluation index S.

[0115] Example 3

[0116] This embodiment also provides a life evaluation device for a plunger packing combination seal. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0117] This embodiment provides a life evaluation device for plunger packing combination seals, such as... Figure 4 As shown, it includes:

[0118] Mounting module 41 is used to install the plunger packing assembly to be evaluated onto the test bench to obtain the target test bench;

[0119] The detection module 42 is used to run the target test bench under short-term no-load conditions and detect the first performance parameters of the plunger packing assembly;

[0120] The calculation module 43 is used to calculate the first dimensionless index based on the first performance parameter and to detect the first physical parameter between the plunger and the packing in the plunger packing assembly.

[0121] Input module 44 is used to input the first dimensionless index and the first physical parameter into the trained BP neural network model to obtain the life prediction value of the plunger packing assembly.

[0122] In an optional embodiment of this application, the apparatus further includes: a training module for acquiring multiple root cluster samples; performing short-term no-load tests on the root cluster samples to obtain a second dimensionless index and a second physical parameter corresponding to the root cluster samples; performing lifetime tests on the root cluster samples to obtain the lifetime duration of the root cluster samples; constructing a training dataset based on the second dimensionless index, the second physical parameter, and the lifetime duration; and training a pre-constructed BP neural network model using the training dataset to obtain a trained BP neural network model.

[0123] In one optional embodiment of this application, a training module is used to install a packing assembly sample onto a test bench to obtain a training test bench; to run the training test bench under short-term no-load conditions and detect a second performance parameter of the packing assembly sample; to calculate a second dimensionless index based on the second performance parameter and to detect a second physical parameter between the plunger and the packing in the packing assembly sample.

[0124] In an optional embodiment of this application, the training module is used to run a training test bench under preset working conditions and detect the third contact mechanical parameters of the packing assembly sample; obtain a target curve of the third contact mechanical parameters changing over time, and determine the current leakage rate of the packing assembly sample based on the target curve; when the current leakage rate reaches a specified leakage rate, obtain the running time of the training test bench under preset working conditions, and use the running time as the lifetime of the packing assembly sample.

[0125] In an optional embodiment of this application, the training module is used to calculate the life evaluation index based on the second dimensionless index and the life duration; integrate the life evaluation index with the corresponding second dimensionless index, second physical parameter and life duration to obtain the corresponding sample data; and construct a training dataset using the sample data corresponding to each packing root combination sample.

[0126] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system).

[0127] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0128] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0129] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0130] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0131] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0132] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0133] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for evaluating the lifespan of a plunger packing assembly seal, characterized in that, The method includes: The plunger packing assembly to be evaluated is installed on the test bench to obtain the target test bench; The target test bench was operated under short-term no-load conditions, and the first performance parameter of the plunger packing assembly was detected. Calculate the first dimensionless index based on the first performance parameter, and detect the first physical parameter between the plunger and packing in the plunger packing assembly; The first dimensionless index and the first physical parameter are input into the trained BP neural network model to obtain the predicted life value of the plunger packing assembly.

2. The method according to claim 1, characterized in that, The first performance parameters include: a first frictional force, a first contact stress distributed along the axial direction, and a first surface temperature; The first dimensionless index includes the stress distribution index, the wear index, and the under-sealing index; The first dimensionless exponent is calculated based on the first performance parameter, using the following formula: Where Y is the stress distribution index; M is the wear index; Q is the under-sealing index; W is the temperature index; σ MSD σ is the root mean square deviation of the first contact stress; MV σ is the average value of the first contact stress; MPD σ is the maximum positive deviation of the first contact stress; MND The maximum negative deviation of the first contact stress; t C t is the first surface temperature; S This is the current room temperature.

3. The method according to claim 1, characterized in that, Before inputting the first dimensionless exponent and the first physical parameter into the trained BP neural network model, the method further includes: Obtain samples of various platy cord combinations; A short-term no-load test was performed on the packing sample to obtain the second dimensionless index and the second physical parameter corresponding to the packing sample. The packing assembly sample was subjected to a lifetime test to obtain the lifetime duration of the packing assembly sample. A training dataset is constructed based on the second dimensionless exponent, the second physical parameter, and the lifetime duration. The pre-constructed BP neural network model is trained using the training dataset to obtain a trained BP neural network model.

4. The method according to claim 3, characterized in that, The step of performing a short-term no-load test on the packing assembly sample to obtain the second dimensionless index and second physical parameter corresponding to the packing assembly sample includes: The packing assembly sample is installed on the test bench to obtain the training test bench; The training test bench was operated under short-term no-load conditions, and the second performance parameters of the packing assembly samples were detected. The second dimensionless index is calculated based on the second performance parameter, and the second physical parameter between the plunger and packing in the packing assembly sample is detected.

5. The method according to claim 4, characterized in that, The process of performing a lifetime test on the packing assembly sample to obtain the lifetime of the packing assembly sample includes: The training test bench is operated under preset working conditions, and the third contact mechanical parameters of the packing assembly sample are detected. Obtain the target curve of the three-contact mechanical parameters changing over time, and determine the current leakage rate of the packing assembly sample based on the target curve; When the current leakage rate reaches the specified leakage rate, the running time of the training test bench under preset working conditions is obtained, and the running time is used as the lifetime of the packing assembly sample.

6. The method according to claim 3, characterized in that, The construction of the training dataset based on the second dimensionless exponent, the second physical parameter, and the lifespan includes: The life evaluation index is calculated based on the second dimensionless index and the life duration. The formula for calculating life evaluation indicators is: Where S is the life evaluation index; L is the life duration; Y is the stress distribution index; M is the wear index; Q is the under-sealing index; and W is the temperature index. The life evaluation index is integrated with the corresponding second dimensionless index, second physical parameter and life duration to obtain the corresponding sample data; A training dataset is constructed using the sample data corresponding to each root combination sample.

7. The method according to claim 3, characterized in that, The pre-built BP neural network model includes an input layer, a hidden layer, and an output layer; The input layer includes multiple input units, wherein the input units are used to receive the second dimensionless exponent and the second physical parameter; The hidden layer includes at least one hidden layer, wherein the hidden layer is used to process the second dimensionless exponent and the second physical parameter received by the input layer, and to perform a nonlinear transformation on the second dimensionless exponent and the second physical parameter through an activation function to obtain the predicted life value of the plunger packing assembly. The output layer includes an output unit, wherein the output unit is used to output the predicted life value of the plunger packing assembly.

8. A life evaluation device for a plunger packing combination seal, characterized in that, The device includes: The mounting module is used to install the plunger packing assembly to be evaluated onto the test bench to obtain the target test bench; The detection module is used to operate the target test bench under short-term no-load conditions and detect the first performance parameter of the plunger packing assembly; The calculation module is used to calculate a first dimensionless index based on the first performance parameter and to detect a first physical parameter between the plunger and the packing in the plunger packing assembly. The input module is used to input the first dimensionless index and the first physical parameter into the trained BP neural network model to obtain the life prediction value of the plunger packing assembly.

9. A computer device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images