CN117109909B

CN117109909B - Detection and early warning method and system for mechanical sealing performance of large-shaft-diameter semi-split type machine

Info

Publication number: CN117109909B
Application number: CN202311382404.7A
Authority: CN
Inventors: 徐卫煌; 陆平; 杜烨
Original assignee: Zhangjiagang Seth Mechanical Seal Co ltd
Current assignee: Zhangjiagang Seth Mechanical Seal Co ltd
Priority date: 2023-10-24
Filing date: 2023-10-24
Publication date: 2023-12-22
Anticipated expiration: 2043-10-24
Also published as: CN117109909A

Abstract

The invention discloses a detection and early warning method and a system for the performance of a large-shaft-diameter semi-split mechanical seal, which relate to the technical field of data processing and comprise the following steps: cutting open a mechanical seal to be subjected to performance detection, and collecting a first moving ring image, a second moving ring image, a first static ring image and a second static ring image; performing image characteristic processing, fitting to obtain a curve and calculating a curve change angle; calculating a matching coefficient corresponding to the curve change angle of the detection point to obtain a first matching coefficient and a second matching coefficient; obtaining a first matching performance parameter; and obtaining a plurality of elastic compression quantities, correcting and calculating the first matching performance parameters, and performing early warning when the second matching performance parameters are smaller than the matching performance parameter threshold. The invention solves the technical problems of low reliability and poor early warning accuracy of mechanical sealing performance detection and early warning in the prior art, and achieves the technical effects of improving the reliability of mechanical sealing performance detection and early warning and improving the early warning quality through correction.

Description

Detection and early warning method and system for mechanical sealing performance of large-shaft-diameter semi-split type machine

Technical Field

The invention relates to the technical field of data processing, in particular to a detection and early warning method and system for the sealing performance of a large-shaft-diameter half-section type machine.

Background

The stability and safety of the operation of the mechanical equipment are closely related to the quality of the mechanical sealing performance. At present, 3 leakage points are mainly solved in the design of the mechanical seal, and the leakage points are respectively positioned between the movable sealing ring and the main shaft, between the static sealing ring and the gland and between the movable sealing ring and the static sealing ring. The two are mainly static seal, while the latter is dynamic seal between the contact surface of dynamic seal ring and static seal ring. Because the dynamic sealing ring and the static sealing ring produce relative sliding between contact surfaces, the dynamic sealing performance between the dynamic sealing ring and the static sealing ring is mainly detected from appearance defects and flatness of sealing surfaces. The flatness of the sealing surface is mainly checked by a special tool, and meanwhile, performance detection is also performed by an intelligent means, but the detection result cannot provide reliable early warning basis due to the fact that the compensation effect of an elastic element in the mechanical seal installation process is ignored, so that the performance of the large-shaft-diameter half-split mechanical seal is invalid. In the prior art, the technical problems of low reliability and poor early warning accuracy of mechanical sealing performance detection and early warning exist.

Disclosure of Invention

The application provides a detection and early warning method and a system for mechanical sealing performance of a large shaft diameter and a semi-split type, which are used for solving the technical problems of low reliability and poor early warning accuracy of mechanical sealing performance detection and early warning in the prior art.

In view of the above problems, the application provides a method and a system for detecting and early warning the sealing performance of a large-shaft-diameter semi-split mechanical seal.

In a first aspect of the present application, a method for detecting and early warning of sealing performance of a large-shaft-diameter half-section type machine is provided, where the method includes:

the mechanical seal to be subjected to performance detection is split, a first dynamic seal ring, a second dynamic seal ring, a first static seal ring and a first dynamic seal ring image, a second dynamic seal ring image, a first static seal ring image and a second static seal ring image of the first dynamic seal ring, the second dynamic seal ring, the first static seal ring and the second static seal ring are collected, wherein the mechanical seal is a large-shaft-diameter half-split mechanical seal, the first dynamic seal ring and the second dynamic seal ring are assembled and fixed to form a dynamic seal ring, and the first static seal ring and the second static seal ring are assembled and fixed to form a static seal ring;

performing image feature processing on the first dynamic ring image, the second dynamic ring image, the first static ring image and the second static ring image, and fitting to obtain a first dynamic ring curve, a second dynamic ring curve, a first static ring curve and a second static ring curve of the edges of the dynamic sealing ring and the static sealing ring;

Calculating curve change angles at a plurality of detection points in the first movable ring curve, the second movable ring curve, the first static ring curve and the second static ring curve by adopting a seal detection step length to obtain a first movable curve angle set, a second movable curve angle set, a first static curve change angle set and a second static curve change angle set;

calculating matching coefficients of curve change angles of corresponding detection points in the first moving curve angle set, the first static curve change angle set, the second moving curve angle set and the second static curve change angle set to obtain a first matching coefficient and a second matching coefficient;

according to the first matching coefficient and the second matching coefficient, matching performance decision distribution of the dynamic sealing ring and the static sealing ring of the mechanical seal is carried out, and a first matching performance parameter is obtained;

assembling and fixing the mechanical seal, and collecting the change condition of the elastic compression quantity of a spring element of the mechanical seal in a preset monitoring window to obtain a plurality of elastic compression quantities;

and calculating and obtaining an elastic compression matching coefficient according to the plurality of elastic compression amounts, correcting and calculating the first matching performance parameter to obtain a second matching performance parameter, and performing early warning when the second matching performance parameter is smaller than a matching performance parameter threshold.

In a second aspect of the present application, a large shaft diameter semi-split mechanical seal performance detection and early warning system is provided, the system includes:

the image acquisition module is used for sectioning a mechanical seal to be subjected to performance detection, and acquiring a first dynamic seal ring, a second dynamic seal ring, a first static seal ring and a first dynamic seal ring image, a second dynamic seal ring image, a first static seal ring image and a second static seal ring image of the first dynamic seal ring, the second dynamic seal ring, the first static seal ring and the second static seal ring, wherein the mechanical seal is a large-shaft-diameter half-sectioning mechanical seal, the dynamic seal rings are formed after being assembled and fixed, and the static seal rings are formed after being assembled and fixed;

the curve fitting module is used for carrying out image feature processing on the first dynamic ring image, the second dynamic ring image, the first static ring image and the second static ring image, and fitting to obtain a first dynamic ring curve, a second dynamic ring curve, a first static ring curve and a second static ring curve of the edges of the dynamic sealing ring and the static sealing ring;

the angle set obtaining module is used for calculating curve change angles at a plurality of detection points in the first movable ring curve, the second movable ring curve, the first static ring curve and the second static ring curve by adopting a seal detection step length to obtain a first movable curve angle set, a second movable curve angle set, a first static curve change angle set and a second static curve change angle set;

The matching coefficient obtaining module is used for calculating the matching coefficient of the curve change angle of the corresponding detection point in the first moving curve angle set, the first static curve change angle set, the second moving curve angle set and the second static curve change angle set to obtain a first matching coefficient and a second matching coefficient;

the performance parameter obtaining module is used for carrying out matching performance decision distribution on the dynamic sealing ring and the static sealing ring of the mechanical seal according to the first matching coefficient and the second matching coefficient to obtain a first matching performance parameter;

the elastic compression amount obtaining module is used for assembling and fixing the mechanical seal, collecting the change condition of the elastic compression amount of the spring element of the mechanical seal in a preset monitoring window and obtaining a plurality of elastic compression amounts;

and the early warning module is used for calculating and obtaining an elastic compression matching coefficient according to the plurality of elastic compression amounts, correcting and calculating the first matching performance parameter to obtain a second matching performance parameter, and carrying out early warning when the second matching performance parameter is smaller than a matching performance parameter threshold value.

One or more technical solutions provided in the present application have at least the following technical effects or advantages:

the method comprises the steps of sectioning a mechanical seal to be subjected to performance detection, collecting a first dynamic ring image, a second dynamic ring image, a first static ring image and a second static ring image of the first dynamic ring, the second dynamic ring image, the first static ring image and the second static ring image of the second static ring, wherein the mechanical seal is a large-shaft-diameter semi-sectioning mechanical seal, the first dynamic ring and the second dynamic ring are assembled and fixed to form the dynamic ring, the first static ring and the second static ring are assembled and fixed to form the static ring, then carrying out image feature processing on the first dynamic ring image, the second dynamic ring image, the first static ring image and the second static ring image, fitting to obtain a first dynamic ring curve, a second dynamic ring curve, a first static ring curve and a second static ring curve at the edges of the dynamic ring and the static ring, and further adopting a seal detection step length, calculating curve change angles at a plurality of detection points in a first movable ring curve, a second movable ring curve, a first static ring curve and a second static ring curve to obtain a first movable curve angle set, a second movable curve angle set, a first static curve change angle set and a second static curve change angle set, then calculating matching coefficients of curve change angles of corresponding detection points in the first movable curve angle set and the first static curve change angle set, the second movable curve angle set and the second static curve change angle set to obtain a first matching coefficient and a second matching coefficient, carrying out matching performance decision distribution of a movable sealing ring and a static sealing ring of the mechanical seal according to the first matching coefficient and the second matching coefficient to obtain a first matching performance parameter, further assembling and fixing the mechanical seal, collecting elastic compression change conditions of a spring element of the mechanical seal in a preset monitoring window to obtain a plurality of elastic compression quantities, and calculating to obtain an elastic compression matching coefficient according to the plurality of elastic compression amounts, correcting and calculating the first matching performance parameter to obtain a second matching performance parameter, and performing early warning when the second matching performance parameter is smaller than a matching performance parameter threshold. The technical effects of improving the reliability of detection and early warning of the large-shaft-diameter half-split mechanical sealing performance and improving the accuracy of detection and early warning are achieved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a detection and early warning method for the sealing performance of a large-shaft-diameter semi-section type machine according to an embodiment of the present application;

fig. 2 is a schematic flow chart of fitting to obtain a first moving ring curve, a second moving ring curve, a first static ring curve and a second static ring curve in the method for detecting and early warning the sealing performance of the large-shaft-diameter half-section machine according to the embodiment of the present application;

fig. 3 is a schematic flow chart of calculating and obtaining a second matching coefficient in the method for detecting and early warning the sealing performance of a large-shaft-diameter half-section type machine according to the embodiment of the present application;

fig. 4 is a schematic structural diagram of a detection and early warning system for mechanical sealing performance of a large-shaft-diameter semi-section type provided in an embodiment of the present application.

Reference numerals illustrate: the device comprises an image acquisition module 11, a curve fitting module 12, an angle set obtaining module 13, a matching coefficient obtaining module 14, a performance parameter obtaining module 15, an elastic compression amount obtaining module 16 and an early warning module 17.

Detailed Description

The application provides a detection and early warning method and a system for the mechanical sealing performance of a large shaft diameter semi-split type, which are used for solving the technical problems of low reliability and poor early warning accuracy of the mechanical sealing performance detection and early warning in the prior art.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.

It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

As shown in fig. 1, the application provides a method for detecting and early warning the sealing performance of a large-shaft-diameter semi-split mechanical seal, wherein the method comprises the following steps:

a1: the mechanical seal to be subjected to performance detection is split, a first dynamic seal ring, a second dynamic seal ring, a first static seal ring and a first dynamic seal ring image, a second dynamic seal ring image, a first static seal ring image and a second static seal ring image of the first dynamic seal ring, the second dynamic seal ring, the first static seal ring and the second static seal ring are collected, wherein the mechanical seal is a large-shaft-diameter half-split mechanical seal, the first dynamic seal ring and the second dynamic seal ring are assembled and fixed to form a dynamic seal ring, and the first static seal ring and the second static seal ring are assembled and fixed to form a static seal ring;

in one embodiment of the present application, the mechanical seal is split from the central axis of the mechanical seal to be subjected to performance detection, that is, the movable sealing ring and the static sealing ring are divided into two halves on average from the central axis, so as to obtain a first movable sealing ring, a second movable sealing ring, a first static sealing ring and a second static sealing ring. And the first movable sealing ring, the second movable sealing ring, the first static sealing ring and the second static sealing ring are assembled to form a circular ring, so that the rotating instrument arm is wrapped for sealing, and the aim of avoiding fluid leakage is fulfilled. The mechanical seal is a large-shaft-diameter half-section mechanical seal, the first movable sealing ring and the second movable sealing ring are assembled and fixed to form a movable sealing ring, and the first static sealing ring and the second static sealing ring are assembled and fixed to form a static sealing ring. Further, the first moving seal ring, the second moving seal ring, the first stationary seal ring, and the second stationary seal ring are respectively image-captured by using a Charge Coupled Device (CCD), and the first moving seal ring image, the second moving seal ring image, the first stationary seal ring image, and the second stationary seal ring image are obtained. Wherein the first moving ring image reflects an appearance state of the first moving seal ring. The second moving ring image reflects an appearance state of the second moving seal ring. The first static ring image reflects an appearance state of the first static seal ring, and the second static ring image reflects an appearance state of the second static seal ring. The technical effect of providing basic detection analysis data for the subsequent mechanical sealing performance detection is achieved.

A2: performing image feature processing on the first dynamic ring image, the second dynamic ring image, the first static ring image and the second static ring image, and fitting to obtain a first dynamic ring curve, a second dynamic ring curve, a first static ring curve and a second static ring curve of the edges of the dynamic sealing ring and the static sealing ring;

further, as shown in fig. 2, image feature processing is performed on the first moving ring image, the second moving ring image, the first static ring image and the second static ring image, and a first moving ring curve, a second moving ring curve, a first static ring curve and a second static ring curve are obtained by fitting, where step A2 in the embodiment of the present application includes:

a21: extracting a history detection image in the mechanical seal splitting state to obtain a history first moving ring image set, a history second moving ring image set, a history first static ring image set and a history second static ring image set;

a22: extracting coordinates of a plurality of points at the edges of the movable sealing ring and the static sealing ring in the preprocessed historical first movable ring image set, the preprocessed historical second movable ring image set, the preprocessed historical first static ring image set and the preprocessed historical second static ring image set to obtain a historical first movable edge point coordinate set, a historical second movable edge point coordinate set, a historical first static edge point coordinate set and a historical second static edge point coordinate set;

A23: based on a convolutional neural network, a historical moving ring image or a historical static ring image is taken as input, a historical edge point coordinate set is taken as output, and a sealing ring edge point identification channel is constructed, wherein the sealing ring edge point identification channel comprises a first moving edge point identification path, a second moving edge point identification path, a first static edge point identification path and a second static edge point identification path;

a24: inputting the preprocessed first moving ring image, second moving ring image, first static ring image and second static ring image into the sealing ring edge point identification channel, and performing image convolution characteristic processing analysis to obtain a first moving edge point coordinate set, a second moving edge point coordinate set, a first static edge point coordinate set and a second static edge point coordinate set;

a25: and fitting and obtaining the first moving ring curve, the second moving ring curve, the first static ring curve and the second static ring curve according to the first moving edge point coordinate set, the second moving edge point coordinate set, the first static edge point coordinate set and the second static edge point coordinate set.

Further, step a25 of the embodiment of the present application further includes:

a25-1: and fitting to obtain a first movable ring curve, a second movable ring curve, a first static ring curve and a second static ring curve according to the first movable edge point coordinate set, the second movable edge point coordinate set, the first static edge point coordinate set and the second static edge point coordinate set by adopting a least square method.

In one possible design, after the first moving ring image, the second moving ring image, the first static ring image and the second static ring image are obtained, image feature processing is performed, features capable of reflecting edges of the moving sealing ring and the static sealing ring in the images are obtained, and then edge curve fitting is performed according to the obtained features, so that a first moving ring curve, a second moving ring curve, a first static ring curve and a second static ring curve are obtained. The first movable ring curve is used for describing the edge shape of the first movable sealing ring. The second moving ring curve is used for describing the edge shape of the second moving sealing ring. The first static ring curve is used to describe the edge shape of the first static seal ring. The second static ring curve is used to describe the edge shape of the second static seal ring. The method has the advantages that the edge curves of the dynamic sealing ring and the static sealing ring of the mechanical seal are fitted through image feature processing, and the reliability of performance detection data is improved.

In one embodiment of the present application, by extracting the detected image of the mechanical seal in the split state in the history period, preferably, by using the history detected image in the split state of the mechanical seal as an index, searching in the database, a history first moving ring image set, a history second moving ring image set, a history first static ring image set and a history second static ring image set meeting the requirements are obtained.

Preferably, the image quality in the image set is different due to the overlong storage time of the images and different storage media, and after some images are compressed, the definition is too low to be used for analysis. Therefore, the first moving ring image set, the second moving ring image set, the first static ring image set and the second static ring image set are preprocessed by utilizing an image enhancement technology, and then coordinates of a plurality of points at the edges of the moving seal ring and the static seal ring are extracted from the preprocessed first moving ring image set, the preprocessed second moving ring image set, the preprocessed first static ring image set and the preprocessed second static ring image set. The image enhancement technology is used for enhancing the contrast of the image, so that the image quality is improved, and the image enhancement technology comprises a histogram equalization technology, gamma transformation, laplace transformation and the like. Optionally, the coordinates of the plurality of points on the edges of the movable sealing ring and the static sealing ring are obtained by constructing a coordinate system by taking the common circle center of the movable sealing ring and the static sealing ring as the origin of the coordinate system and combining the positions of the plurality of points on the edges of the movable sealing ring and the static sealing ring in the coordinate system. Further, the set of historical first moving edge point coordinates, the set of historical second moving edge point coordinates, the set of historical first static edge point coordinates, and the set of historical second static edge point coordinates are determined. The historical first movable edge point coordinate set reflects the edge point coordinate condition of the first movable sealing ring in the historical performance detection. The historical second dynamic edge point coordinate set reflects the edge point coordinates of the second dynamic seal ring in the historical performance test. The historical first static edge point coordinate set reflects the edge point coordinate condition of the first static seal ring in the historical performance detection. The historical second static edge point coordinate set reflects the edge point coordinates of the second static seal ring in the historical performance test.

Specifically, a convolutional neural network is used as channel operation logic, a historical moving ring image or a historical static ring image is used as input, a historical edge point coordinate set is used as output, convolution analysis is carried out, and the seal edge point identification channel is generated, wherein the seal edge point identification channel is used for an intelligent channel for carrying out edge point identification on a dynamic seal ring or a static seal ring of a mechanical seal and comprises a first dynamic edge point identification path, a second dynamic edge point identification path, a first static edge point identification path and a second static edge point identification path. The first movable edge point identification path is used for identifying edge points of the first movable sealing ring. And the second movable edge point identification path is used for identifying the edge point of the second movable sealing ring. The first static edge point identification path is used for carrying out edge point identification on the first static sealing ring. And the second static edge point identification path is used for carrying out edge point identification on the second static sealing ring. The technical effects of improving the recognition efficiency of the edge points of the sealing ring and improving the recognition precision are achieved.

Specifically, the first moving edge point identification path, the second moving edge point identification path, the first static edge point identification path and the second static edge point identification path which are preprocessed by using an image enhancement technology are respectively input into the first moving edge point identification path, the second moving edge point identification path, the first static edge point identification path and the second static edge point identification path in the sealing ring edge point identification channel, and analysis is performed to obtain a first moving edge point coordinate set, a second moving edge point coordinate set, a first static edge point coordinate set and a second static edge point coordinate set.

Preferably, the coordinates in the first moving edge point coordinate set are fitted into the first moving ring curve by using a least square method, and the sum of absolute values of errors between the first moving edge point coordinate set and the curve can be minimized in the fitting process, so that the fitting error is reduced, and the accuracy of the fitted first moving ring curve is improved. Wherein the objective function is obtainedWherein L is an objective function, n is the number of coordinates in the edge point coordinate set, +.>Coordinates of the ith edge coordinate point, +.>To fit a curve. And inputting the first dynamic edge point into the objective function, and obtaining a first dynamic ring curve when the objective function obtains a minimum value. Based on the same principle, a second dynamic edge point coordinate set, a first static edge point coordinate set and a second static edge point coordinate set are respectively input into an objective function, the minimum value of the objective function is obtained, and the second dynamic ring curve and the first static ring curve are obtainedA loop curve and a second static loop curve.

A3: calculating curve change angles at a plurality of detection points in the first movable ring curve, the second movable ring curve, the first static ring curve and the second static ring curve by adopting a seal detection step length to obtain a first movable curve angle set, a second movable curve angle set, a first static curve change angle set and a second static curve change angle set;

Further, by adopting a seal detection step, calculating curve change angles at a plurality of detection points in the first moving ring curve, the second moving ring curve, the first static ring curve and the second static ring curve, a step A3 in the embodiment of the present application includes:

a31: setting and acquiring an outer seal detection step length and an inner seal detection step length according to the shaft diameter of the mechanical seal, wherein the size of the seal detection step length is positively correlated with the size of the shaft diameter;

a32: according to the outer seal detection step length and the inner seal detection step length, a plurality of first moving detection points are determined on the first moving ring curve, a plurality of first static detection points are determined on the first static ring curve, and the plurality of first moving detection points and the plurality of first static detection points are in one-to-one correspondence;

a33: drawing a circle by taking one of the first moving detection points as a circle center and taking the seal detection step length as a pre-aiming distance and the pre-aiming distance as a radius, taking an intersection point with the first moving ring curve as a pre-aiming point, and calculating to obtain one of the first moving curve angles according to the pre-aiming distance and the pre-aiming point, wherein the first moving curve angle is represented by the following formula:

；

wherein,for the first curve angle, +.>For one of the first moving detection points, the tangent line of the first moving ring curve is connected with the pretightening point and one of the first moving detection points Included angle of line->Is the pretarget distance;

a34: and continuing to calculate to obtain the first moving curve angle set, the second moving curve angle set, the first static curve change angle set and the second static curve change angle set.

In one possible embodiment, the seal detection step is a distance between two adjacent detection points detecting angles of change of the first moving ring curve, the second moving ring curve, the first stationary ring curve, the second stationary ring curve, the first gland curve, and the second gland curve. Preferably, the step of obtaining the outer seal detection step and the step of obtaining the inner seal detection step are set according to the shaft diameter of the mechanical seal, wherein the size of the seal detection step is positively correlated with the size of the shaft diameter.

Specifically, by taking any point on the first moving ring curve as a detection starting point, determining a plurality of first moving detection points according to the size of an outer seal detection step length, and determining a plurality of first static detection points on the first static ring curve according to the size of an inner seal detection step length, wherein the plurality of first moving detection points and the plurality of first static detection points are in one-to-one correspondence, that is, each moving detection point corresponds to one static detection point. The step length of the outer seal detection is the distance between two adjacent detection points of the movable sealing ring of the mechanical seal outer ring. The inner seal detection step length is the distance between two adjacent detection points of the static seal ring of the mechanical seal inner ring. And further, taking one of the first moving detection points as a circle center, taking the seal detection step length as a pretightening distance, taking the pretightening distance as a radius to draw a circle, taking the intersection point of the seal detection step length and the first movable ring curve as a pretightening point, and calculating to obtain one of the first moving curve angles according to the pretightening distance and the pretightening point. The first moving curve angle is used for describing an included angle between a straight line connected with the center of the first moving seal ring and the first moving detection point of the first moving ring curve and a straight line connected with the center of the pretightening point and the first moving seal ring.

Based on the same mode, calculating a first moving curve angle set corresponding to the rest first moving detection points to obtain the first moving curve angle set, and calculating curve change angles according to a plurality of detection points in a first static ring curve and a second static ring curve to obtain a second moving curve angle set, a first static curve change angle set and a second static curve change angle set.

A4: calculating matching coefficients of curve change angles of corresponding detection points in the first moving curve angle set, the first static curve change angle set, the second moving curve angle set and the second static curve change angle set to obtain a first matching coefficient and a second matching coefficient;

further, as shown in fig. 3, in the first moving curve angle set and the first static curve change angle set, the second moving curve angle set and the second static curve change angle set, matching coefficients corresponding to curve change angles of the detection points are calculated, and a first matching coefficient and a second matching coefficient are obtained, where step A4 in the embodiment of the present application includes:

a41: calculating deviation percentages of the first dynamic curve angles and the first static curve angles of the corresponding first dynamic detection points and the first static detection points in the first dynamic curve angle set and the first static curve change angle set to obtain a first curve angle deviation set;

A42: calculating the average value of the first curve angle deviation set to obtain the first matching coefficient;

a43: and calculating to obtain the second matching coefficient according to the second moving curve angle set and the second static curve change angle set.

In one possible embodiment, the first matching coefficient is obtained by performing matching analysis on the angle set at the detection points corresponding to the first moving curve angle set and the first static curve change angle set, to determine the matching condition between the first moving seal ring and the first static seal ring. And determining the matching condition between the second movable sealing ring and the second static sealing ring according to the second movable curve angle set and the second static curve change angle set, and obtaining the second matching coefficient.

Preferably, the difference between the first moving curve angle and the first static curve angle of the corresponding first moving detection point and the first static detection point is calculated, and the first curve angle deviation set is obtained by multiplying the difference by the percentage. Wherein the first set of curve angle deviations reflects a deviation between a plurality of detection points between the first moving seal ring and the first stationary seal ring. And determining the average deviation condition between the first movable sealing ring and the first static sealing ring for the average value of the first curve angle deviation set, and obtaining the first matching coefficient. Further, a difference between a second moving curve angle and a second static curve angle of the corresponding second moving detection point and second static detection point is calculated, and the second curve angle deviation set is obtained by multiplying the difference by a percentage. Wherein the second set of curve angle deviations reflects deviations between a plurality of detection points between the second moving seal ring and the second stationary seal ring. And determining the average deviation condition between the second movable sealing ring and the second static sealing ring for the average value of the second curve angle deviation set, and obtaining the second matching coefficient. The technical effect of quantitatively determining the sealing performance between the first movable sealing ring and the first static sealing ring and between the second movable sealing ring and the second static sealing ring is achieved.

A5: according to the first matching coefficient and the second matching coefficient, matching performance decision distribution of the dynamic sealing ring and the static sealing ring of the mechanical seal is carried out, and a first matching performance parameter is obtained;

further, according to the first matching coefficient and the second matching coefficient, matching performance decision allocation of the dynamic sealing ring and the static sealing ring of the mechanical seal is performed to obtain a first matching performance parameter, and step A5 of the embodiment of the present application further includes:

a51: extracting and processing historical sealing performance data of the mechanical seal to obtain a first sample matching coefficient set, a second sample matching coefficient set and a sealing performance parameter set, wherein the sealing performance parameter set comprises leakage amount of the mechanical seal, which is subjected to operation after the mechanical seal is assembled and fixed under different first sample matching coefficients and different second sample matching coefficients;

a52: according to the sealing performance parameter set, evaluating and obtaining a sample matching performance parameter set;

a53: taking the first matching coefficient and the second matching coefficient as decision features, and adopting the first sample matching coefficient set and the second sample matching coefficient set to construct a multi-layer decision node;

a54: obtaining a plurality of decision results of the multi-layer decision node, and marking by adopting a plurality of sample matching performance parameters in the sample matching performance parameter set to obtain a matching performance decision channel;

A55: and inputting the first matching coefficient and the second matching coefficient into the matching performance decision channel to carry out division decision so as to obtain the first matching performance parameter.

In one embodiment of the present application, the matching performance between the dynamic sealing ring and the static sealing ring of the mechanical seal is determined according to a first matching coefficient and a second matching coefficient, and the first matching performance parameter is obtained, wherein the first matching performance parameter reflects the sealing performance level of the mechanical seal. The technical effect of determining the sealing performance between the dynamic sealing ring and the static sealing ring of the mechanical seal is achieved.

In one embodiment, a sample first set of matching coefficients, a sample second set of matching coefficients, and a sealing performance parameter set are obtained by retrieving historical sealing performance data of a mechanical seal. The sealing performance parameter set comprises leakage amount of operation performed after mechanical sealing is assembled and fixed under different first matching coefficients of samples and second matching coefficients of samples. The greater the leakage amount, the lower the sealing performance, that is to say the smaller the performance parameter. Preferably, the mapping relationship between the sealing performance parameter and the matching performance parameter is set by a person skilled in the art. And taking the sealing performance parameter set as an index, and carrying out matching performance evaluation based on the mapping relation to obtain the sample matching performance parameter set.

Specifically, the multi-layer decision node is used for comparing and matching the first matching coefficient and the second matching coefficient. Preferably, the multi-layer decision node is constructed by constructing a set of first matching coefficients from the sample, and a set of second matching coefficients from the sample. Randomly selecting a first sample matching coefficient and a second corresponding sample matching coefficient from the first sample matching coefficient set and the second sample matching coefficient set without returning, storing the first sample matching coefficient and the second corresponding sample matching coefficient to a first decision node, randomly selecting a first sample matching coefficient and the second corresponding sample matching coefficient from the first sample matching coefficient set and the second sample matching coefficient set without returning, storing the first sample matching coefficient and the second corresponding sample matching coefficient to a second decision node, and obtaining a multi-layer decision node after multiple times of non-returning random selection. And inputting the first sample matching coefficient set and the second sample matching coefficient set into the multi-layer decision node, and storing the first sample matching coefficient set and the second sample matching coefficient set into a plurality of decision results of the multi-layer decision node if the matching coefficients are smaller than the first sample matching coefficient and the second sample matching coefficient stored in the multi-layer decision node. The plurality of decision results are then labeled with a plurality of sample matching performance parameters within a sample matching performance parameter set. And generating the matching performance channel according to the decision nodes and the marked decision results.

Specifically, the first matching coefficient and the second matching coefficient are input into the matching performance decision channel to carry out division decision, a corresponding decision result is obtained, and a first matching performance parameter is determined according to a mark of the corresponding decision result. The intelligent performance parameter matching method has the advantages that the intelligent performance parameter matching is determined, and the efficiency of determining the performance parameter matching between the movable sealing ring and the static sealing ring is improved.

A6: assembling and fixing the mechanical seal, and collecting the change condition of the elastic compression quantity of a spring element of the mechanical seal in a preset monitoring window to obtain a plurality of elastic compression quantities;

a7: and calculating and obtaining an elastic compression matching coefficient according to the plurality of elastic compression amounts, correcting and calculating the first matching performance parameter to obtain a second matching performance parameter, and performing early warning when the second matching performance parameter is smaller than a matching performance parameter threshold.

Further, according to the plurality of elastic compression amounts, an elastic compression matching coefficient is obtained through calculation, correction calculation is performed on the first matching performance parameter, and a second matching performance parameter is obtained, and step A7 of the embodiment of the present application further includes:

a71: calculating variances of the elastic compression amounts to obtain the elastic compression matching coefficients;

A72: according to the historical performance test data of the mechanical seal, a sample elastic compression matching coefficient set is obtained, and an average sample elastic compression matching coefficient is calculated and obtained;

a73: calculating the ratio of the elastic compression matching coefficient to the average sample elastic compression matching coefficient as a correction coefficient;

a74: and correcting and calculating the first matching performance parameter by adopting the correction coefficient to obtain the second matching performance parameter.

And acquiring the variation value of the elastic compression amount of the fixed spring element in a preset monitoring window by assembling and fixing the mechanical seal, so as to obtain a plurality of elastic compression amounts. The spring element is used for compensating the sealing between the dynamic sealing ring and the static sealing ring in the mechanical seal and comprises a spring, a corrugated pipe and the like. The preset monitoring window is a time period preset by a person skilled in the art for compensation monitoring. It is therefore necessary to obtain a plurality of elastic compression amounts to correct the previously obtained first matching performance parameters.

Preferably, the elastic compression matching coefficient is determined by analyzing the plurality of elastic compression amounts. The smaller the elastic compression coefficient is, the larger the fluctuation of the elastic element is, the larger the degree of sealing compensation between the dynamic sealing ring and the static sealing ring in the mechanical seal is, and the worse the sealing performance between the dynamic sealing ring and the static sealing ring is, the unstable elastic element can be caused. And correcting and calculating the first matching performance parameter by using the elastic compression matching coefficient to obtain a second matching performance parameter. The second matching performance parameter reflects the poor matching performance between the dynamic sealing ring and the static sealing ring of the mechanical seal after the compensation of the elastic element is considered. And when the second matching performance parameter is smaller than the matching performance parameter threshold, the mechanical sealing performance is indicated to be incapable of working normally, and early warning is needed.

In one embodiment, the variance is used as the elastic compression matching coefficient by calculating variances of a plurality of elastic compression amounts. And extracting a plurality of sample elastic compression quantity sets in a preset monitoring window from historical performance test data of the mechanical seal, respectively calculating variances to obtain sample elastic matching coefficient sets, and carrying out mean value calculation on the sample elastic matching coefficient sets to obtain average sample elastic compression matching coefficients. Further, a ratio of the elastic compression matching coefficient to the average sample elastic compression matching coefficient is calculated as a correction coefficient. And obtaining the average correction degree by carrying out average value calculation on the difference value between the first matching performance parameter set of the sample and the second matching performance parameter set of the sample in the historical performance test data set. And multiplying the correction coefficient by the average correction degree to obtain the degree of correction of the first matching performance parameter, and obtaining the second matching performance parameter after correction. The technical effects of improving the reliability and the accuracy of the sealing performance detection and early warning are achieved.

In summary, the embodiments of the present application have at least the following technical effects:

according to the method, the mechanical seal is split, edge coordinate points of the first movable sealing ring, the second movable sealing ring, the first static sealing ring and the second static sealing ring are collected, so that a first movable ring curve, a second movable ring curve, a first static ring curve and a second static ring curve of the edges of the movable sealing ring and the static sealing ring are obtained through fitting, then the change angle of the curves is analyzed, matching performance decision distribution of the movable sealing ring and the static sealing ring of the mechanical seal is carried out according to analysis results, a first matching performance parameter is obtained, furthermore, the compression amount of a mechanical seal spring element after the mechanical seal is assembled and fixed is analyzed, the influence of compensation of the spring element on the sealing performance of the movable sealing ring and the static sealing ring in the mechanical seal is considered, the first matching performance parameter is corrected and calculated, a second matching performance parameter is obtained, and early warning is carried out when the second matching performance parameter is smaller than a matching performance parameter threshold value. The accuracy and the intelligent degree of the mechanical sealing performance detection and early warning are improved, and the technical effect of the detection and early warning efficiency is improved.

Example two

Based on the same inventive concept as the detection and early warning method for the mechanical sealing performance of the large-shaft-diameter half-section type in the foregoing embodiment, as shown in fig. 4, the present application provides a detection and early warning system for the mechanical sealing performance of the large-shaft-diameter half-section type, and the embodiments of the system and the method in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:

the image acquisition module 11 is used for sectioning a mechanical seal to be subjected to performance detection, and acquiring a first moving seal ring, a second moving seal ring, a first moving seal ring image, a second moving seal ring image, a first static seal ring image and a second static seal ring image of the first moving seal ring, the second moving seal ring, the first static seal ring image and the second static seal ring, wherein the mechanical seal is a large-shaft-diameter half-section mechanical seal, the moving seal ring is formed after the first moving seal ring and the second moving seal ring are assembled and fixed, and the static seal ring is formed after the first static seal ring and the second static seal ring are assembled and fixed;

the curve fitting module 12 is configured to perform image feature processing on the first moving ring image, the second moving ring image, the first static ring image and the second static ring image, and fit a first moving ring curve, a second moving ring curve, a first static ring curve and a second static ring curve of the edges of the moving seal ring and the static seal ring;

The angle set obtaining module 13 is configured to calculate curve change angles at a plurality of detection points in the first moving ring curve, the second moving ring curve, the first static ring curve and the second static ring curve by using a seal detection step length, so as to obtain a first moving curve angle set, a second moving curve angle set, a first static curve change angle set and a second static curve change angle set;

the matching coefficient obtaining module 14 is configured to calculate a matching coefficient corresponding to a curve change angle of the detection point in the first moving curve angle set and the first static curve change angle set, the second moving curve angle set and the second static curve change angle set, and obtain a first matching coefficient and a second matching coefficient;

the performance parameter obtaining module 15 is configured to perform matching performance decision allocation of the dynamic seal ring and the static seal ring of the mechanical seal according to the first matching coefficient and the second matching coefficient, so as to obtain a first matching performance parameter;

the elastic compression amount obtaining module 16 is used for assembling and fixing the mechanical seal, collecting the change condition of the elastic compression amount of the spring element of the mechanical seal in a preset monitoring window, and obtaining a plurality of elastic compression amounts;

The early warning module 17 is configured to calculate and obtain an elastic compression matching coefficient according to the plurality of elastic compression amounts, correct and calculate the first matching performance parameter to obtain a second matching performance parameter, and perform early warning when the second matching performance parameter is smaller than a matching performance parameter threshold.

Further, the early warning module 12 is configured to perform the following method:

extracting a history detection image in the mechanical seal splitting state to obtain a history first moving ring image set, a history second moving ring image set, a history first static ring image set and a history second static ring image set;

extracting coordinates of a plurality of points at the edges of the movable sealing ring and the static sealing ring in the preprocessed historical first movable ring image set, the preprocessed historical second movable ring image set, the preprocessed historical first static ring image set and the preprocessed historical second static ring image set to obtain a historical first movable edge point coordinate set, a historical second movable edge point coordinate set, a historical first static edge point coordinate set and a historical second static edge point coordinate set;

based on a convolutional neural network, a historical moving ring image or a historical static ring image is taken as input, a historical edge point coordinate set is taken as output, and a sealing ring edge point identification channel is constructed, wherein the sealing ring edge point identification channel comprises a first moving edge point identification path, a second moving edge point identification path, a first static edge point identification path and a second static edge point identification path;

Inputting the preprocessed first moving ring image, second moving ring image, first static ring image and second static ring image into the sealing ring edge point identification channel, and performing image convolution characteristic processing analysis to obtain a first moving edge point coordinate set, a second moving edge point coordinate set, a first static edge point coordinate set and a second static edge point coordinate set;

and fitting and obtaining the first moving ring curve, the second moving ring curve, the first static ring curve and the second static ring curve according to the first moving edge point coordinate set, the second moving edge point coordinate set, the first static edge point coordinate set and the second static edge point coordinate set.

and fitting to obtain a first movable ring curve, a second movable ring curve, a first static ring curve and a second static ring curve according to the first movable edge point coordinate set, the second movable edge point coordinate set, the first static edge point coordinate set and the second static edge point coordinate set by adopting a least square method.

Further, the angle set obtaining module 13 is configured to perform the following method:

setting and acquiring an outer seal detection step length and an inner seal detection step length according to the shaft diameter of the mechanical seal, wherein the size of the seal detection step length is positively correlated with the size of the shaft diameter;

According to the outer seal detection step length and the inner seal detection step length, a plurality of first moving detection points are determined on the first moving ring curve, a plurality of first static detection points are determined on the first static ring curve, and the plurality of first moving detection points and the plurality of first static detection points are in one-to-one correspondence;

drawing a circle by taking one of the first moving detection points as a circle center and taking the seal detection step length as a pre-aiming distance and the pre-aiming distance as a radius, taking an intersection point with the first moving ring curve as a pre-aiming point, and calculating to obtain one of the first moving curve angles according to the pre-aiming distance and the pre-aiming point, wherein the first moving curve angle is represented by the following formula:

；

wherein,for the first curve angle, +.>For one of the firstAn included angle between the tangent line of the first moving ring curve at one moving detection point and the connecting line of the pretightening point and one of the first moving detection points,/and%>Is the pretarget distance;

and continuing to calculate to obtain the first moving curve angle set, the second moving curve angle set, the first static curve change angle set and the second static curve change angle set.

Further, the matching coefficient obtaining module 14 is configured to perform the following method:

calculating deviation percentages of the first dynamic curve angles and the first static curve angles of the corresponding first dynamic detection points and the first static detection points in the first dynamic curve angle set and the first static curve change angle set to obtain a first curve angle deviation set;

Calculating the average value of the first curve angle deviation set to obtain the first matching coefficient;

and calculating to obtain the second matching coefficient according to the second moving curve angle set and the second static curve change angle set.

Further, the performance parameter obtaining module 15 is configured to perform the following method:

extracting and processing historical sealing performance data of the mechanical seal to obtain a first sample matching coefficient set, a second sample matching coefficient set and a sealing performance parameter set, wherein the sealing performance parameter set comprises leakage amount of the mechanical seal, which is subjected to operation after the mechanical seal is assembled and fixed under different first sample matching coefficients and different second sample matching coefficients;

according to the sealing performance parameter set, evaluating and obtaining a sample matching performance parameter set;

taking the first matching coefficient and the second matching coefficient as decision features, and adopting the first sample matching coefficient set and the second sample matching coefficient set to construct a multi-layer decision node;

obtaining a plurality of decision results of the multi-layer decision node, and marking by adopting a plurality of sample matching performance parameters in the sample matching performance parameter set to obtain a matching performance decision channel;

and inputting the first matching coefficient and the second matching coefficient into the matching performance decision channel to carry out division decision so as to obtain the first matching performance parameter.

Further, the early warning module 17 is configured to perform the following method:

calculating variances of the elastic compression amounts to obtain the elastic compression matching coefficients;

according to the historical performance test data of the mechanical seal, a sample elastic compression matching coefficient set is obtained, and an average sample elastic compression matching coefficient is calculated and obtained;

calculating the ratio of the elastic compression matching coefficient to the average sample elastic compression matching coefficient as a correction coefficient;

and correcting and calculating the first matching performance parameter by adopting the correction coefficient to obtain the second matching performance parameter.

It should be noted that the sequence of the embodiments of the present application is merely for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The foregoing description of the preferred embodiments of the present application is not intended to limit the invention to the particular embodiments of the present application, but to limit the scope of the invention to the particular embodiments of the present application.

The specification and drawings are merely exemplary of the application and are to be regarded as covering any and all modifications, variations, combinations, or equivalents that are within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims

1. The method for detecting and early warning the performance of the large-shaft-diameter half-section mechanical seal is characterized by comprising the following steps:

2. The method of claim 1, wherein performing image feature processing on the first moving ring image, the second moving ring image, the first stationary ring image, and the second stationary ring image, fitting to obtain a first moving ring curve, a second moving ring curve, a first stationary ring curve, and a second stationary ring curve, comprises:

3. The method according to claim 2, characterized in that the method comprises:

4. The method of claim 1, wherein calculating curve change angles at a plurality of detection points within the first moving ring curve, the second moving ring curve, the first stationary ring curve, the second stationary ring curve using seal detection steps comprises:

；

wherein,for the first curve angle, +.>For the included angle between the tangent line of the first moving ring curve at one of the first moving detection points and the connecting line of the pretightening point and one of the first moving detection points, +. >Is the pretarget distance;

5. The method of claim 1, wherein calculating the matching coefficients for the curve change angles of the detection points within the first set of moving curve angles and the first set of static curve change angles, the second set of moving curve angles and the second set of static curve change angles to obtain the first matching coefficient and the second matching coefficient comprises:

6. The method of claim 1, wherein performing matching performance decision assignments for the dynamic seal ring and the static seal ring of the mechanical seal based on the first and second matching coefficients to obtain a first matching performance parameter comprises:

7. The method of claim 1, wherein calculating an elastic compression matching coefficient based on the plurality of elastic compression amounts, performing a correction calculation on the first matching performance parameter, and obtaining a second matching performance parameter, comprises:

8. The utility model provides a big footpath half split type mechanical seal performance detects early warning system which characterized in that, the system includes: