CN-121994464-A - Method, device, equipment and medium for evaluating service life of plunger packing combined seal

CN121994464ACN 121994464 ACN121994464 ACN 121994464ACN-121994464-A

Abstract

The invention relates to the field of sealing packing, and discloses a service life evaluation method, device, equipment and medium of plunger packing combined seal, wherein the method comprises the steps of installing a plunger packing combination to be evaluated on a test bed to obtain a target test bed; the method comprises the steps of operating a target test bed under a short-term no-load condition, detecting first performance parameters of a plunger packing combination, calculating a first dimensionality index according to the first performance parameters, detecting first physical parameters between a plunger and the packing in the plunger packing combination, and inputting the first dimensionality index and the first physical parameters into a trained BP neural network model to obtain a life prediction value of the plunger packing combination. The invention solves the problems of incomplete test parameters and incomplete evaluation system of the existing plunger packing sealing life test method.

Inventors

ZOU BIN
WANG XIAOJUN
SONG HUIFANG
QIAN WEIKUN
LI FENG
ZHANG JIN
GUAN XIN
ZHANG BOWEN
GUO ZHIYONG

Assignees

中国石油化工股份有限公司
中国石油化工股份有限公司胜利油田分公司

Dates

Publication Date: 20260508
Application Date: 20241108

Claims (10)

1. A method for evaluating the life of a plunger packing combination seal, the method comprising: installing a plunger packing combination to be evaluated on a test bed to obtain a target test bed; Operating the target test stand under short-term no-load conditions 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 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.
2. The method of claim 1, wherein the first performance parameter comprises a first friction force, a first contact stress distributed axially, and a first surface temperature; the first dimensionless index comprises a stress uniform distribution index, a wear index and an under-sealing index; Calculating a first dimensionless index according to the first performance parameter, wherein the calculation formula is as follows: Wherein Y is a stress uniform distribution index, M is a wear index, Q is an under-seal index, W is a temperature index, sigma MSD is a mean square error of first contact stress, sigma MV is a mean value of the first contact stress, sigma MPD is a maximum positive deviation of the first contact stress, sigma MND is a maximum negative deviation of the first contact stress, t C is a first surface temperature, and t S is a current room temperature.
3. The method of claim 1, wherein prior to inputting the first dimensionless index and the first physical parameter into the trained BP neural network model, the method further comprises: obtaining a plurality of packing combination samples; Carrying out short-term no-load test on the packing combination sample to obtain a second dimensionless index and a second physical parameter corresponding to the packing combination sample; Performing life test on the packing combination sample to obtain the life time of the packing combination sample; constructing a training data set based on the second dimensionless number, the second physical parameter, and the life duration; and training the pre-constructed BP neural network model by using the training data set to obtain a trained BP neural network model.
4. A method according to claim 3, wherein said performing a short-term empty test on said packing set samples results in a second dimensionless index and a second physical parameter corresponding to said packing set samples, comprising: mounting the packing combination sample to a test bed to obtain a training test bed; Operating the training test bed under a short-term no-load condition, and detecting a second performance parameter of the packing combination sample; and calculating a second dimensionless index according to the second performance parameter, and detecting a second physical parameter between the plunger and the packing in the packing combination sample.
5. The method of claim 4, wherein said performing a life test on said combined packing sample results in a life time of said combined packing sample, comprising: Operating the training test bed under a preset working condition, and detecting a third contact mechanical parameter of the packing combination sample; Acquiring a target curve of the three-contact mechanical parameter changing along with time, and determining the current leakage rate of the packing combination sample based on the target curve; When the current leakage rate reaches the specified leakage rate, acquiring the operation time length of the training test bed under the preset working condition, and taking the operation time length as the service life time length of the packing combination sample.
6. The method of claim 3, wherein the constructing a training data set based on the second dimensionless number, the second physical parameter, and the length of life comprises: calculating a life evaluation index according to the second dimensionless number and the life duration; The formula for calculating the life evaluation index is: Wherein S is a life evaluation index, L is a life duration, Y is a stress uniform distribution index, M is a wear index, Q is an under-seal index, and W is a temperature index; Integrating the life evaluation index with a corresponding second dimensionless index, a second physical parameter and life duration to obtain corresponding sample data; And constructing a training data set by using sample data corresponding to each packing combination sample.
7. The method of claim 3, wherein the pre-constructed BP neural network model comprises an input layer, a hidden layer, and an output layer; the input layer comprises a plurality of input units, wherein the input units are used for receiving the second dimensionless index and the second physical parameter; The hidden layer comprises at least one hidden layer, wherein the hidden layer is used for processing a second dimensionless index and a second physical parameter received by the input layer, and performing nonlinear transformation on the second dimensionless index and the second physical parameter through an activation function to obtain a life prediction value of the plunger packing combination; the output layer comprises an output unit, wherein the output unit is used for outputting a life prediction value of the plunger packing combination.
8. A device for evaluating the life of a plunger packing combination seal, the device comprising: the mounting module is used for mounting the plunger packing combination to be evaluated to the test bed to obtain a target test bed; The detection module is used for operating the target test bed under a short-term no-load condition and detecting a first performance parameter of the plunger packing combination; The calculation module is used for calculating a first dimensionality index according to the first performance parameter and detecting a first physical parameter between a plunger and a packing in the plunger packing combination; and the input module is used for 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.
9. A computer device, comprising: A memory and a processor in communication with each other, the memory having stored therein computer instructions which, upon execution, cause the processor to perform the method of any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 7.

Description

Method, device, equipment and medium for evaluating service life of plunger packing combined seal Technical Field The invention relates to the field of sealing packing, in particular to a service life evaluation method, device, equipment and medium for plunger packing combined sealing. Background The plunger pump is used as a key power device widely applied in the fields of petroleum, chemical industry and the like, and the core working principle of the plunger pump depends on the reciprocating motion of a plunger in a cylinder body to realize the suction and discharge of fluid. In specific application scenes such as oilfield water injection, the plunger pump needs to run at a high speed under the extreme working conditions of high pressure and high corrosion, and extremely high requirements are set for a packing sealing system of the plunger pump. The performance of the packing sealing system directly affects the operation efficiency and safety of the plunger pump, and if the packing sealing system is poor in sealing, serious leakage problems are caused, the service life of equipment is shortened, and even safety accidents are caused. The current plunger packing sealing life test method mainly focuses on abrasion leakage, ignores key parameters such as packing stress, friction force change and the like, and has the advantages that although part of the test is used for monitoring friction force and speed, the contact stress distribution and the influence thereof are not comprehensively considered, and the evaluation system is limited. The prior art ignores the effects of factors interactions within the system, such as tolerance dimensions, fluid pressure, surface hardness, etc., on sealing performance. Therefore, the life prediction accuracy is insufficient, and the equipment maintenance plan is affected, which may lead to equipment failure or resource waste. Disclosure of Invention In view of the above, the embodiment of the invention provides a method, a device, equipment and a medium for evaluating the service life of a plunger packing combined seal, which are used for solving the problems of incomplete test parameters and incomplete evaluation system of the existing plunger packing seal service life test method. In a first aspect, an embodiment of the present invention provides a method for evaluating the life of a plunger packing composite seal, where the method includes: installing a plunger packing combination to be evaluated on a test bed to obtain a target test bed; Operating the target test stand under short-term no-load conditions 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 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. In an alternative embodiment of the present application, the first performance parameter includes a first friction force, a first contact stress distributed along an axial direction, and a first surface temperature; the first dimensionless index comprises a stress uniform distribution index, a wear index and an under-sealing index; Calculating a first dimensionless index according to the first performance parameter, wherein the calculation formula is as follows: Wherein Y is a stress uniform distribution index, M is a wear index, Q is an under-seal index, W is a temperature index, sigma MSD is a mean square error of first contact stress, sigma MV is a mean value of the first contact stress, sigma MPD is a maximum positive deviation of the first contact stress, sigma MND is a maximum negative deviation of the first contact stress, t C is a first surface temperature, and t S is a current room temperature. In an alternative embodiment of the present application, before inputting the first dimensionless number and the first physical parameter into the trained BP neural network model, the method further comprises: obtaining a plurality of packing combination samples; Carrying out short-term no-load test on the packing combination sample to obtain a second dimensionless index and a second physical parameter corresponding to the packing combination sample; Performing life test on the packing combination sample to obtain the life time of the packing combination sample; constructing a training data set based on the second dimensionless number, the second physical parameter, and the life duration; and training the pre-constructed BP neural network model by using the training data set to obtain a trained BP neural network model. In an optional embodiment of the present application, the performing a short-term no-load test on the packing combination sample to obtain a second dimensionless index and a second physical parameter cor