A reliability prediction and analysis method and prediction and analysis system for high-pressure plunger pumps

Abstract

The present invention discloses a reliability prediction and analysis method and prediction and analysis system for a high-pressure plunger pump, including adjusting representative equivalence class data and invalid equivalence class data to determine data boundaries, using a control variable method to control within the selected data boundary, i.e., within a threshold range, outputting response data of the high-pressure plunger pump under different input parameters, and then loading a single type of response data with varying variations into a prediction model for training; gradually increasing training sets corresponding to representative equivalence class data and / or invalid equivalence class data, and training the prediction model; extracting the input-output relationship of the trained prediction model, calculating data changes with different weights, and calculating the sum of variances, sorting according to the size of the variances, and outputting the reliability quantitative analysis results of the high-pressure plunger pump through the sorting of the sum of variances. The present invention provides a reliability analysis method for quantitatively observing different plunger pumps, and realizes scientific and intelligent analysis of the reliability of plunger pumps.

Description

Technical Field

[0001] The invention relates to data processing, and in particular to a reliability prediction and analysis method and a prediction and analysis system for a high-pressure plunger pump. Background Art

[0002] As the service requirements for machines in high-end equipment, aerospace, military industry and other fields have reached unprecedented heights, on the basis of meeting the requirements of low energy consumption, low pollution, long life and high efficiency, the wear problem between machine parts has become increasingly prominent due to the harsh service conditions such as high speed, high temperature and heavy load. The lubrication condition of the friction pair interface of mechanical equipment, high-precision processing technology of high-pressure plunger pumps, and life evaluation and prediction of plunger pumps are of great significance to improving the service life of machines and developing high-end equipment.

[0003] The high-pressure plunger pump contains multiple parts and connectors, such as pump body, plunger, connecting rod, bearing, seal, etc. These parts need to be coordinated to form a complete pump structure, and at the same time, they need to meet the use requirements under complex working conditions such as high pressure, high temperature, and high speed.

[0004] High-pressure plunger pumps operate under harsh working conditions such as high temperature, high pressure, high speed and high load. The wear, lubrication and cavitation problems of key friction pairs restrict the service life of high-pressure plunger pumps and reduce their reliability.

[0005] Therefore, a research method to explore whether the plunger pump is reliable is urgently needed to ensure the production and optimize the plunger pump in a degraded state. Summary of the invention

[0006] The present invention provides a high-pressure plunger pump reliability prediction and analysis method and a prediction and analysis system, which solve the problems of the prior art.

[0007] In a first aspect, the present invention provides a high-pressure plunger pump reliability prediction and analysis method, comprising:

[0008] Step B, the steps of classifying the plunger pump structural parameter training set include:

[0009] Step B1: classify the training data set to be judged into a valid equivalence class data set and an invalid equivalence class data set according to the experimental results of the piston pump under different experimental working conditions;

[0010] Step B2, selecting equivalent class data with the same output response of high-pressure plunger pumps with different structural parameters under the same working condition from the effective equivalent class data set, and defining the equivalent class data as representative equivalent class data; wherein the data that does not conform to the response status of the working condition change is invalid equivalent class data, and the data fluctuation conforms to the response of the working condition change is valid equivalent class data, wherein the structural parameters include thickness parameters, length parameters, and angle parameters at the wear part and the sealing part;

[0011] Step C, prediction model training steps:

[0012] Step C1, adjust the representative equivalent class data and the invalid equivalent class data to determine the data boundary, use the control variable method to control within the selected data boundary, i.e., the threshold range, output the response data of the high-pressure plunger pump under different input parameters, and then load the response data of a single class of staggered changes into the prediction model for training, and obtain the prediction model trained by the single staggered training set;

[0013] Step C2, gradually increase the training set corresponding to the representative equivalent class data and / or the invalid equivalent class data, and train the prediction model;

[0014] Step D, reliability analysis step;

[0015] Step D1: extract the input-output relationship of the trained prediction model, calculate the data changes with different weights, calculate the sum of variances, and sort by variance size;

[0016] Step D2: Obtain the operating environment parameters of the high-pressure plunger pump to be tested and input them into the prediction model. Output the percentage of the difference with the actual response data, and calculate the degree of discreteness between the output data of the prediction model and the actual response data. Output the quantitative analysis result of the reliability of the high-pressure plunger pump through the discreteness of the response data reflected by the variance sorting.

[0017] Furthermore, before the B training set classification step, the following steps are also included:

[0018] Step A, preset steps:

[0019] Step A1: collect the structural parameters of the high-pressure plunger pump and set a pump body model with the same structural parameters;

[0020] Step A2, setting different experimental working conditions for different pump models, loading the monitored historical working condition data of the high-pressure plunger pump, and outputting the response data of the high-pressure plunger pump under different experimental working conditions to generate a prediction model;

[0021] Step A3: Generate a training data set to be judged by combining the actual working conditions and the structural parameters of the plunger pump.

[0022] Furthermore, the step B2 further specifically includes:

[0023] According to the effective equivalent class data of different working condition change types, data simulation is performed on multiple groups of effective equivalent class data divided under different rules, and the rules include:

[0024] Simulate different types of data with multiple groups of different values ​​within multiple value ranges, simulate neighborhood data of dividing points of multiple value ranges, and simulate valid equivalence class subset data in the case of Boolean quantities.

[0025] Furthermore, the step B1 specifically includes:

[0026] The plunger pump operating condition change data corresponding to the output response data that conforms to the function law is judged as valid equivalent data;

[0027] The valid equivalent class data is divided into equivalent class levels, and the influence coefficient of each two valid equivalent class data in the influence degree of the plunger pump output response data under two different working condition change data is calculated;

[0028] The output response data changes caused by the self-change of a single effective equivalent data, the degree of mutual correlation of the two groups of change values ​​is compared, the input value of a single effective equivalent data is adjusted within the value range and then the output change of another effective equivalent data is monitored, and the mutual correlation functions of the two effective equivalent data are fitted for subsequent correction.

[0029] Furthermore, it also includes correction of the fitting function, by exchanging the process of generating the fitting function from two sets of change values, analyzing the change of the output response data caused by the change of the effective equivalent data, changing the input value of another effective equivalent data with a different value range from the effective equivalent data, analyzing the data influence direction of the other effective equivalent data on the effective equivalent data, fitting the data influence direction function, and correcting the influence of the data influence direction function on the fitting function.

[0030] Furthermore, after correcting the function of the change value of two sets of effective equivalent data, a function correction process is performed on three or more sets of different types of effective equivalent data in pairs, and then the two sets of effective equivalent data are changed at the same time to obtain the cross-correlation function between the four variables, including two sets of effective equivalent data and two sets of response data, and the influence of the value of the remaining effective equivalent data within different value ranges on the cross-correlation function between the four variables is judged, and the cross-correlation function of three or more sets of effective equivalent data is fitted for subsequent correction.

[0031] Furthermore, the C1 step further includes:

[0032] For the high-pressure plunger pump with different structural parameters under the invalid equivalent data, the regular function output response results related to different structural parameters are output, the corresponding invalid equivalent data types are screened out, and the corresponding invalid equivalent data prediction module is generated to verify and fill in the influence of the invalid equivalent data on the response data of the entire high-pressure plunger pump;

[0033] When invalid equivalence class data outputs an output response result of a regular function that is unrelated to different structural parameters in a high-pressure plunger pump with different structural parameters, the corresponding invalid equivalence class data type is screened out.

[0034] Furthermore, the step D1 specifically includes:

[0035] The logic from input to output of the trained prediction model is extracted to eliminate dimensional interference, set data type changes under different weights, obtain the fluctuations of the output multi-response data caused by different weights, sum up the sum of the fluctuation variances of each response data under different weights, and sort the sum of the fluctuation variances of the multi-response data caused by different data changes under different weight settings.

[0036] Furthermore, the D1 step specifically includes: before extracting the input-output relationship in the trained prediction model, normalizing the output multi-response data, and then executing the calculation of data changes with different weights, and calculating the sum of variances, and sorting according to the size of the variance.

[0037] In a second aspect, the present invention provides a high-pressure plunger pump reliability prediction and analysis system, including a preset module, a collection module, a training set analysis module, a prediction model training module and a reliability analysis module; the collection module is arranged at a wear part and a sealing part to monitor structural parameters, and the structural parameters include thickness parameters, length parameters and angle parameters;

[0038] Used to implement a high-pressure plunger pump reliability prediction and analysis method as described in any one of the first aspects, the preset module is used to execute step A, and the acquisition module is used to execute structural parameter acquisition of the high-pressure plunger pump and to acquire historical operating data of the high-pressure plunger pump monitored under different experimental operating conditions;

[0039] The training set analysis module is used to perform step B;

[0040] The prediction model training module is used to perform the C step, i.e., the prediction model training step;

[0041] The technical concept of the present invention:

[0042] In order to explore the performance degradation state of the plunger pump, a state perception accuracy threshold is set, and the production reliability of the plunger pump is achieved by improving the detection accuracy. However, since the performance degradation mechanism of the plunger pump is not clear, the performance degradation state cannot be perceived, and it is difficult to evaluate and predict the life of the plunger pump. The present invention predicts the plunger pump life through several aspects of weighting through model prediction, including starting from the first aspect, friction, secondary friction and interaction and its influence, starting from the second aspect, multi-source data processing from multiple working parameters, including: hydraulic oil quality, working temperature, working pressure, workload and other working parameters, and the mutual influence mechanism between the working parameters will also lead to the influence of a single parameter aggravating the degree of effect of other parameters; the analysis also includes the coordination analysis of the design, manufacturing and processing technology of the pump body structure. The high-pressure plunger pump contains multiple parts and connectors, such as pump body, plunger, connecting rod, bearing, seal, etc. These parts need to coordinate and cooperate to form a complete pump body structure, and at the same time, they also need to meet the use requirements under complex working conditions such as high pressure, high temperature and high speed. That is, for the high-pressure plunger pump, it is used as a hyperparameter in the product design stage to affect the basic life of the high-pressure plunger pump, and the working condition is a multi-conditional parameter that affects the basic life exhaustion speed of the high-pressure plunger pump. At the same time, the model prediction module of the present invention is added to adjust the acceleration of the basic life exhaustion speed to predict the life status of the simulated high-pressure plunger pump. The data acquisition direction is set in two aspects in the present invention. First, the force condition is analyzed through the physical quantity of the machine itself, and the internal friction is analyzed with reference to the mechanical manual. Since the sealing requirement is high, secondly, in the simulation state, sensors are installed to monitor the real-time changes of internal temperature, pressure, and load. The data model is corrected by the actual collected data content, and the influence of the force analysis caused by the physical quantity is adjusted by the output result of the data model.

[0043] The present invention provides a high-pressure plunger pump reliability prediction and analysis method and prediction and analysis system, which use known operating condition change data to correct the prediction model and adopt multiple analysis methods to recursively train different independent variables to correlate the reliability and impact of the high-pressure plunger pump.

[0044] The invention provides a reliability analysis method for quantitatively observing different plunger pumps, thereby realizing scientific and intelligent analysis of the reliability of the plunger pumps. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0046] Figure 1 A flow chart of a reliability prediction and analysis method for a high-pressure plunger pump provided as an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0048] The specific application scenario of the present invention is the predictive analysis of the reliability of a high-pressure plunger pump.

[0049] The present invention provides a high-pressure plunger pump reliability prediction and analysis method and a prediction and analysis system, aiming to solve the above technical problems in the prior art.

[0050] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0051] Embodiment 1: This embodiment provides a high-pressure plunger pump reliability prediction and analysis method, such as Figure 1 As shown, the specific implementation steps are as follows:

[0052] Step A, preset steps:

[0053] Step A1: collect the structural parameters of the high-pressure plunger pump and set a pump body model with the same structural parameters;

[0054] Step A2, setting different experimental working conditions for different pump models, loading the monitored historical working condition data of the high-pressure plunger pump, and outputting the response data of the high-pressure plunger pump under different experimental working conditions to generate a prediction model;

[0055] Step A3, generating a training data set to be judged by combining the actual working conditions and the structural parameters of the plunger pump;

[0056] Step B, training set classification step:

[0057] Step B1: Classify the training data set to be judged into a valid equivalence class data set and an invalid equivalence class data set according to the experimental results of the piston pump monitored under different experimental working conditions; judge the piston pump working condition change data corresponding to the output response data that conforms to the function law as valid equivalence class data; and divide the valid equivalence class data into equivalence class levels, and calculate the influence coefficient of each two valid equivalence class data in the influence degree of the piston pump output response data under two different working condition change data; compare the mutual correlation degree of the two groups of change values ​​through the output response data change caused by the self-change of a single valid equivalent data, and adjust The input value of a single effective equivalent data within the value range is then monitored, and the output change of another effective equivalent data is fitted, and the mutual correlation function of the two effective equivalent data is used for subsequent correction; it also includes correction of the fitting function, by exchanging the process of generating the fitting function from the two sets of change values, analyzing the change of the output response data caused by the change of the effective equivalent data, changing the input value of another effective equivalent data with a different value range from the effective equivalent data, analyzing the data influence direction of the other effective equivalent data on the effective equivalent data, fitting the data influence direction function, and correcting the influence of the data influence direction function on the fitting function. After correcting the function of the change value of the two sets of effective equivalent data, a function correction process is performed on three or more sets of different types of effective equivalent data in pairs, and then the two sets of effective equivalent data are changed at the same time to obtain the mutual correlation function between four variables, including two sets of effective equivalent data and two sets of response data, and the influence of the value of the remaining effective equivalent data in different value ranges on the mutual correlation function between the four variables is judged, and the mutual correlation function of the three or more sets of effective equivalent data is fitted for subsequent correction.

[0058] Step B2, select equivalent class data with the same output response of high-pressure plunger pumps with different structural parameters under the same working condition from the effective equivalent class data set, and define the equivalent class data as representative equivalent class data; wherein the structural parameters include thickness parameters, length parameters, and angle parameters at the wear part and the sealing part; according to different types of effective equivalent class data, perform data simulation on multiple groups of effective equivalent class data divided under different rules, and the rules include: simulating multiple groups of different types of data with different values ​​within multiple value ranges, simulating the neighborhood data of the boundary points of multiple value ranges, and simulating the effective equivalent class subset data in the case of Boolean quantities.

[0059] Step C, prediction model training steps:

[0060] Step C1, adjust the representative equivalent class data and the invalid equivalent class data to determine the data boundary, use the control variable method to control within the selected data boundary, i.e., the threshold range, output the response data of the high-pressure plunger pump under different input parameters, and then load the response data of a single class of staggered changes into the prediction model for training, and obtain the prediction model trained by the single staggered training set;

[0061] For the high-pressure plunger pump with different structural parameters under the invalid equivalent data, the regular function output response results related to different structural parameters are output, the corresponding invalid equivalent data types are screened out, and the corresponding invalid equivalent data prediction module is generated to verify and fill in the influence of the invalid equivalent data on the response data of the entire high-pressure plunger pump;

[0062] When invalid equivalence class data outputs an output response result of a regular function that is unrelated to different structural parameters in a high-pressure plunger pump with different structural parameters, the corresponding invalid equivalence class data type is screened out.

[0063] Step C2, gradually increase the training set corresponding to the representative equivalent class data and / or the invalid equivalent class data, and train the prediction model;

[0064] Step D, reliability analysis step;

[0065] Step D1, extract the input-output relationship of the trained prediction model, calculate the data changes with different weights, calculate the sum of variances, and sort according to the size of the variances; extract the logic from input to output of the trained prediction model, eliminate dimensional interference, set the data type changes under the influence of different weights, obtain the fluctuations of the output multi-response data caused by different weights, sum up the sum of the fluctuation variances of each response data under different weights, and sort the sum of the fluctuation variances of the multi-response data caused by different data changes under different weight settings.

[0066] Step D2: Obtain the operating environment parameters of the high-pressure plunger pump to be tested and input them into the prediction model. Output the percentage of the difference with the actual response data, and calculate the degree of discreteness between the output data of the prediction model and the actual response data. Output the quantitative analysis result of the reliability of the high-pressure plunger pump through the discreteness of the response data reflected by the variance sorting.

[0067] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0068] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0069] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0070] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0071] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods or systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0072] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0073] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

[0074] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention is indicated by the claims above.

[0075] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A reliability prediction and analysis method for a high-pressure plunger pump, characterized in that: The steps include: Step A, preset steps: Step A1: collect the structural parameters of the high-pressure plunger pump and set a pump body model with the same structural parameters; Step A2, setting different experimental working conditions for different pump models, loading the monitored historical working condition data of the high-pressure plunger pump, and outputting the response data of the high-pressure plunger pump under different experimental working conditions to generate a prediction model; Step A3, generating a training data set to be judged by combining the actual working conditions and the structural parameters of the plunger pump; Step B, the steps of classifying the plunger pump structural parameter training set include: Step B1, classify the training data set to be judged into a valid equivalence class data set and an invalid equivalence class data set according to the experimental results of the piston pump monitored under different experimental working conditions; wherein, the data that does not conform to the response status of the working condition change is the invalid equivalence class data, and the data fluctuation conforms to the response of the working condition change is the valid equivalence class data, and according to the valid equivalence class data of different working condition change types, perform data simulation on multiple groups of valid equivalence class data divided under different rules, and the rules include: simulating multiple groups of different types of data with different values ​​within multiple value ranges, simulating the neighborhood data of the demarcation point of multiple value ranges, and simulating the valid equivalence class subset data under the Boolean quantity; The step B1 specifically includes: The plunger pump operating condition change data corresponding to the output response data that conforms to the function law is judged as valid equivalent data; The valid equivalent class data is divided into equivalent class levels, and the influence coefficient of each two valid equivalent class data in the influence degree of the plunger pump output response data under two different working condition change data is calculated; By comparing the mutual correlation between the two groups of change values ​​caused by the self-change of a single effective equivalent data, adjusting the input value of a single effective equivalent data within the value range and then monitoring the output change of another effective equivalent data, the mutual correlation function of the two effective equivalent data is fitted for subsequent correction; The method also includes correcting the fitting function, by exchanging the process of generating the fitting function from two sets of change values, analyzing the change of the output response data caused by the change of the effective equivalent data, changing the input value of another effective equivalent data having a different value range from the effective equivalent data, analyzing the data influence direction of the other effective equivalent data on the effective equivalent data, fitting the data influence direction function, and correcting the influence of the data influence direction function on the fitting function; Step B2, selecting equivalent class data with the same output response of high-pressure plunger pumps with different structural parameters under the same working condition from the effective equivalent class data set, and defining the equivalent class data as representative equivalent class data; wherein the structural parameters include thickness parameters, length parameters, and angle parameters at the wear part and the sealing part; Step C, prediction model training steps: Step C1, adjust the representative equivalent class data and the invalid equivalent class data to determine the data boundary, use the control variable method to control within the selected data boundary, i.e., the threshold range, output the response data of the high-pressure plunger pump under different input parameters, and then load the response data of a single class of staggered changes into the prediction model for training, and obtain the prediction model trained by the single staggered training set; Step C2, gradually increase the training set corresponding to the representative equivalent class data and / or the invalid equivalent class data, and train the prediction model; Step D, reliability analysis step; Step D1: extract the input-output relationship of the trained prediction model, calculate the data changes with different weights, calculate the sum of variances, and sort by variance size; Step D2: Obtain the operating environment parameters of the high-pressure plunger pump to be tested and input them into the prediction model. Output the percentage of the difference with the actual response data, and calculate the degree of discreteness between the output data of the prediction model and the actual response data. Output the quantitative analysis result of the reliability of the high-pressure plunger pump through the discreteness of the response data reflected by the variance sorting.

2. A high-pressure plunger pump reliability prediction and analysis method according to claim 1, characterized in that: After correcting the function of the change value of two sets of effective equivalent data, a function correction process is performed on three or more sets of different types of effective equivalent data in pairs, and then the two sets of effective equivalent data are changed at the same time to obtain the cross-correlation function between the four variables, including two sets of effective equivalent data and two sets of response data, and the influence of the value of the remaining effective equivalent data within different value ranges on the cross-correlation function between the four variables is judged, and the cross-correlation function of three or more sets of effective equivalent data is fitted for subsequent correction.

3. A high-pressure plunger pump reliability prediction and analysis method according to claim 2, characterized in that: The C1 step specifically includes: For the high-pressure plunger pump with different structural parameters under the invalid equivalent data, the regular function output response results related to different structural parameters are output, the corresponding invalid equivalent data types are screened out, and the corresponding invalid equivalent data prediction module is generated to verify and fill in the influence of the invalid equivalent data on the response data of the entire high-pressure plunger pump; When invalid equivalence class data outputs an output response result of a regular function that is unrelated to different structural parameters in a high-pressure plunger pump with different structural parameters, the corresponding invalid equivalence class data type is screened out.

4. A high-pressure plunger pump reliability prediction and analysis method according to claim 3, characterized in that: The step D1 specifically includes: The logic from input to output of the trained prediction model is extracted to eliminate dimensional interference, set data type changes under different weights, obtain the fluctuations of the output multi-response data caused by different weights, sum up the sum of the fluctuation variances of each response data under different weights, and sort the sum of the fluctuation variances of the multi-response data caused by different data changes under different weight settings.

5. A high-pressure plunger pump reliability prediction and analysis method according to claim 4, characterized in that: The D1 step specifically also includes: before extracting the input-output relationship in the trained prediction model, normalizing the output multi-response data, then executing the calculation of data changes with different weights, and calculating the sum of variances, and sorting according to the size of the variance.

6. A high-pressure plunger pump reliability prediction and analysis system, characterized in that: It includes a preset module, a collection module, a training set analysis module, a prediction model training module and a reliability analysis module; the collection module is arranged on the wear part and the sealing part to monitor the structural parameters, and the structural parameters include thickness parameters, length parameters and angle parameters; Used to implement a high-pressure plunger pump reliability prediction and analysis method as described in any one of claims 1 to 5, the preset module is used to execute step A, the acquisition module is used to execute structural parameter acquisition of the high-pressure plunger pump, and the acquisition module is also used to acquire historical operating data of the high-pressure plunger pump monitored under different experimental operating conditions; The training set analysis module is used to perform the step B; The prediction model training module is used to execute the C step.

Images