CN114638174A - Fault tracing method, device, equipment and storage medium for multistage mechanical sealing system - Google Patents
Fault tracing method, device, equipment and storage medium for multistage mechanical sealing system Download PDFInfo
- Publication number
- CN114638174A CN114638174A CN202210146479.4A CN202210146479A CN114638174A CN 114638174 A CN114638174 A CN 114638174A CN 202210146479 A CN202210146479 A CN 202210146479A CN 114638174 A CN114638174 A CN 114638174A
- Authority
- CN
- China
- Prior art keywords
- mechanical seal
- fault
- model
- characteristic parameter
- stage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007789 sealing Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012544 monitoring process Methods 0.000 claims abstract description 60
- 230000008569 process Effects 0.000 claims abstract description 14
- 238000007476 Maximum Likelihood Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 6
- 238000013178 mathematical model Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000011144 upstream manufacturing Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000004445 quantitative analysis Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Abstract
The application discloses a multistage mechanical seal system fault tracing method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring boundary pressure of a multistage mechanical sealing system and a plurality of monitoring parameters acquired by a sensor; inputting the boundary pressure and a plurality of monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multi-stage mechanical sealing system in the solving process to obtain characteristic parameter values of the multi-stage mechanical sealing system; and matching the characteristic parameter values with the fault events, and tracing the fault of the multistage mechanical seal system according to the matching result. The embodiment of the application can judge the internal working state of the multi-stage seal, and identify the position where the fault is most likely to occur, so that a technician can make targeted treatment. Therefore, the problems that for the multi-stage sealing system, particularly, an abstracted mathematical model of the multi-stage sealing system is under-defined during solving, so that the solution cannot be determined and the like are solved.
Description
Technical Field
The present disclosure relates to the field of fluid sealing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for tracing a failure of a multi-stage mechanical sealing system.
Background
The mechanical seal is a dynamic end face seal device. It is desirable to reduce or eliminate the frictional wear of the friction pair (formed by the two end faces moving relative to each other and the fluid medium) while maintaining low or no leakage for extended life. For higher pressure applications, multiple mechanical seals are typically designed to reduce the pressure in stages, reducing the workload of each stage.
In order to detect the working state of the mechanical seal, the related art can monitor the pressure, flow rate, etc. in the external pipeline of the mechanical seal, usually by means of a matched auxiliary system.
However, when an enterprise applies the supporting auxiliary system, due to the limitation of monitoring conditions, the working state inside the mechanical seal, especially the leakage rate of each stage of seal, cannot be accurately calculated from the results obtained by monitoring the auxiliary system in the multistage mechanical seal system, so that when the system works abnormally, the reason and risk of abnormality cannot be determined, and a solution is needed.
Disclosure of Invention
The application provides a multistage mechanical seal system fault tracing method and device, electronic equipment and a storage medium, and aims to solve the problems that a mathematical model abstracted by the multistage mechanical seal system, especially the multistage mechanical seal system, is under-defined during solving, so that the solution cannot be determined and the like.
The embodiment of the first aspect of the application provides a method for tracing the fault of a multistage mechanical sealing system, which comprises the following steps: acquiring boundary pressure of a multistage mechanical sealing system and a plurality of monitoring parameters acquired by a sensor; inputting the boundary pressure and the monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multi-stage mechanical sealing system in the solving process to obtain characteristic parameter values of the multi-stage mechanical sealing system; and matching the characteristic parameter values with the fault events, and tracing the fault of the multistage mechanical seal system according to the matching result.
Optionally, in an embodiment of the present application, before acquiring the boundary pressure of the multistage mechanical seal system and the plurality of monitoring parameters acquired by the sensor, the method further includes: establishing a chamber model and a component model of the multistage mechanical sealing system; and constructing the system physical model according to the chamber model and the component model.
Optionally, in an embodiment of the present application, the introducing of the empirical knowledge of the failure event of the multistage mechanical seal system includes: empirical knowledge of possible failure events of the multi-stage mechanical seal system is introduced in the form of a prior probability distribution.
Optionally, in an embodiment of the present application, the inputting the boundary pressure and the multiple monitoring parameters into a pre-constructed system physical model for solution, and introducing experience knowledge of the fault event of the multistage mechanical seal system into the solution process to obtain the characteristic parameter values of the multistage mechanical seal system includes: and calculating the system physical model by utilizing the maximum likelihood to obtain the characteristic parameter value.
Optionally, in an embodiment of the present application, the calculating the system physical model by using the maximum likelihood to obtain the characteristic parameter value includes:
wherein the content of the first and second substances,
as a value of a characteristic parameter, pb(x) Is prior probability distribution, f (x; z) is system physical model, and y is monitoring parameter.
An embodiment of a second aspect of the present application provides a multistage mechanical seal system fault tracing device, including: the acquisition module is used for acquiring the boundary pressure of the multistage mechanical sealing system and a plurality of monitoring parameters acquired by the sensor; the calculation module is used for inputting the boundary pressure and the monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multistage mechanical sealing system in the solving process to obtain characteristic parameter values of the multistage mechanical sealing system; and the source tracing module is used for matching the characteristic parameter values with the fault events and carrying out fault source tracing on the multistage mechanical seal system according to matching results.
Optionally, in an embodiment of the present application, the method further includes: the first modeling module is used for establishing a chamber model and a component model of the multi-stage mechanical sealing system; and the second modeling module is used for constructing the system physical model according to the chamber model and the component model.
Optionally, in an embodiment of the present application, the introducing of the empirical knowledge of the failure event of the multistage mechanical seal system includes: empirical knowledge of the possible failure events of the multi-stage mechanical seal system is introduced in the form of a prior probability distribution.
Optionally, in an embodiment of the application, the calculation module is specifically configured to calculate the system physical model by using maximum likelihood to obtain the characteristic parameter value.
Optionally, in an embodiment of the application, the calculating the system physical model by using the maximum likelihood to obtain the characteristic parameter value includes:
wherein the content of the first and second substances,
as a value of a characteristic parameter, pb(x) Is prior probability distribution, f (x; z) is system physical model, and y is monitoring parameter.
An embodiment of a third aspect of the present application provides an electronic device, including: the failure tracing system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to execute the failure tracing method of the multistage mechanical sealing system according to the embodiment.
A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the failure tracing method for a multi-stage mechanical sealing system according to the foregoing embodiments.
Therefore, the application has at least the following beneficial effects:
according to the probability-based quantitative analysis scheme, the analysis result is output in the form of the maximum likelihood system state, the internal working state of the multistage seal is judged, the position where the fault is most likely to occur is identified, and technical personnel can make targeted treatment. Therefore, the problems that the multi-stage sealing system, especially an abstracted mathematical model of the multi-stage sealing system is under-defined during solving, so that the solution cannot be determined and the like are solved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a fault tracing method for a multistage mechanical seal system according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural view of a multi-stage mechanical seal system provided in accordance with an embodiment of the present application;
fig. 3 is a schematic logic diagram illustrating an implementation of a failure tracing method for a multi-stage mechanical seal system according to an embodiment of the present application;
fig. 4 is an exemplary diagram of a failure tracing apparatus of a multistage mechanical seal system according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Description of reference numerals: the system comprises an acquisition module-100, a calculation module-200, a source tracing module-300, a memory-501, a processor-502 and a communication interface-503.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
A multistage mechanical seal system fault tracing method, a multistage mechanical seal system fault tracing apparatus, an electronic device, and a storage medium according to embodiments of the present application are described below with reference to the drawings. In order to solve the problems mentioned in the background art, the application provides a fault tracing method for a multistage mechanical sealing system, wherein in the method, boundary pressure of the multistage mechanical sealing system and a plurality of monitoring parameters acquired by a sensor are acquired; inputting the boundary pressure and a plurality of monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multi-stage mechanical sealing system in the solving process to obtain characteristic parameter values of the multi-stage mechanical sealing system; and matching the characteristic parameter values with the fault events, and tracing the fault of the multistage mechanical seal system according to the matching result. Therefore, the internal working state of the multi-stage seal can be judged, the position where the fault is most likely to occur is identified, technical personnel can make targeted treatment, and the problems that the multi-stage seal system, particularly an abstracted mathematical model of the multi-stage seal system, is under-defined during solving, cannot be solved and the like are solved.
Specifically, fig. 1 is a flowchart of a failure tracing method for a multistage mechanical seal system according to an embodiment of the present disclosure.
As shown in fig. 1, the method for tracing the fault of the multistage mechanical seal system includes the following steps:
in step S101, a boundary pressure of the multi-stage mechanical seal system and a plurality of monitoring parameters collected by the sensor are obtained.
Specifically, the application of the embodiment of the present application may be a multi-stage mechanical seal system abstracted as the following model, as shown in conjunction with fig. 2:
1) the system interior and boundaries are chambers. A chamber contains a volume of medium and a chamber is considered to have a uniform pressure. Consider the case of only one medium. Transfer of media between chambers occurs, and the transfer rate is measured by the flow rate. The chambers are classified into two types, internal and boundary, the pressure of which is determined by the operating conditions outside the system and is not considered to be affected by the characteristics of the system itself.
2) The system contains several mechanical seals (typically 2 to 3). Single stage sealing is simple without the use of the present application). The multiple stages of seals are connected in series, namely a downstream chamber of a previous stage of seal is an upstream chamber of a next stage of seal. Each mechanical seal has a leakage rate (leakage rate is also a flow rate) that is determined by the environment surrounding the mechanical seal (including temperature, upstream pressure, downstream pressure, in some cases, the effect of temperature may be ignored) and the characteristic parameters of the mechanical seal.
3) The interior contains a plurality of throttling tubes (also called coil tubes). The flow rate of the throttle pipe is determined by its surroundings (upstream and downstream pressures, which are not very temperature dependent) and characteristic parameters.
4) Including a number of sensors. The sensor monitors the value of the specific physical quantity to obtain a monitoring result, and provides the monitoring result to the analysis method through software and hardware facilities such as a storage device and a database. The monitoring results may be subjected to some pre-processing prior to entering the algorithm.
Meanwhile, the above system includes multiple types of parameters, which are defined in the embodiments of the present application for convenience of description, as follows:
the first type: a characteristic parameter. They are unknown parameters in the component models of the mechanical seal and coil, are quantifications of potential faults, they are not monitored, and are the targets that the algorithm is to judge;
the second type: the boundary pressure. Pressure is the easiest quantity to monitor, so the embodiments of the present application consider that the boundary pressure is always monitored, which is substantially consistent with engineering practice;
in the third category: a monitored parameter of the parameters other than the above two categories; in the embodiment of the present application, the monitored parameter may refer to other parameters that can be monitored by a sensor, besides the boundary pressure and the characteristic parameter, in the multi-stage sealing system.
The fourth type: other parameters.
It will be appreciated that the task of the embodiments of the present application is to infer the characteristic parameters of the mechanical seal and the coil, the chamber pressure, and the flow rate between the chambers, based on the monitoring results provided by the sensors.
Optionally, in one embodiment of the present application, a chamber model and a component model of a multi-stage mechanical seal system are established; constructing a system physical model according to the chamber model and the component model, wherein the system physical model is represented by
Wherein the content of the first and second substances,
the calculation result of the system physical model on the monitoring parameters is shown, x is a characteristic parameter, and z is boundary pressure.
In particular, the above-mentioned component models are built by means of mechanical seals and coils to describe how their flow rates are calculated from the ambient parameters and from the intrinsic parameters (first-type parameters). There are a number of different modeling approaches for these models, particularly for mechanical seals.
The internal chambers may be modeled as described above to describe how their pressure is affected by the flow rate to the associated chamber. The model has two forms of compressible medium and incompressible medium:
(a) for incompressible media, the model can be simply expressed as "net flow 0";
(b) for a compressible media, the rate of change of pressure is affected by the net flow and the media characteristics.
It should be understood that the system physical model is defined as a model that inputs all characteristic parameters (first type parameters) and boundary pressure (second type parameters) and outputs predictions of all non-boundary pressure monitoring results (third type parameters). This model is solved concurrently from the component model and the chamber model described above.
In the embodiments of the present application, for convenience of description, all characteristic parameters are recorded as
(first type parameter) boundary pressure of
(second type of parameters), the monitoring results except for the boundary pressure are
(third type parameter). The definition of x makes it 0 at the design point for the fault diagnosis requirement.
The physical model of the system is
And representing the calculation result of the model on the monitoring result.
In fact, the first and second types of parameters can be used to solve not only the third type of parameters but also the fourth type of parameters. In embodiments of the present application, the fourth class of parameters is not listed in the output of the above mathematical expression.
In step S102, the boundary pressure and the plurality of monitoring parameters are input into a pre-constructed system physical model for solving, and empirical knowledge of a failure event of the multi-stage mechanical seal system is introduced during the solving process to obtain characteristic parameter values of the multi-stage mechanical seal system.
It should be noted that, depending on the model form and the implementation of the monitoring, the estimation of the parameters of the mechanical seal and the coil, the chamber pressure, the flow rate between the chambers, etc. may present different problem properties depending on the monitoring results provided by the sensors. The classification of the nature of these problems should not be understood from a purely analytical point of view, but should take into account the actual behavior of the problem after it is affected by numerical errors, model errors, etc. in the calculations. The specific problems are classified as follows:
(a) and (5) solving the problem. The system physical model can definitely solve all unknowns according to the monitoring result, and the analysis method thereof is not discussed below.
(b) The problem of over-constraint. Mathematically, the solution of the system state from the monitoring results is unsolved (the number of independent monitoring results is more than the number of independent characteristic parameters to be solved). Alternatively, the monitoring results may be contradictory. In this case, the system model should be changed (mainly to increase the number of characteristic parameters) or some monitoring results should be discarded to convert into other problem types, and the analysis method thereof will not be discussed below.
(c) The problem of under-constraint. Generally, there are a plurality of combinations of characteristic parameters to obtain the same monitoring results from the system physical model (the number of independent monitoring results is less than that of the independent characteristic parameters to be solved). Such problems are the most frequent case in practical applications, because the component models with more characteristic parameters to be determined can describe the possible fault variation range of the actual analysis object more accurately, but the monitoring information of the sensor cannot be easily and effectively increased. Although the characteristic parameters cannot be calculated with certainty, due to the universality of the situation, an analytical method is urgently needed in engineering application to solve such problems.
Optionally, in one embodiment of the present application, empirical knowledge of a failure event of a multi-stage mechanical seal system is introduced, including: empirical knowledge of the failure events that may occur with a multistage mechanical seal system is introduced in the form of a prior probability distribution.
In order to solve the under-constraint problem of the application embodiment, the embodiment of the application performs calculation based on a system physical model, prior probability and a monitoring result, and displays the result to a user in a mode of solving a certain specific probability problem.
Specifically, the embodiments of the present application analyze the under-constrained problem using a probabilistic approach. A prior probability distribution is assumed for x (in a specific process, x can be defined as a form for easily expressing the probability distribution when establishing a system physical model), and then the probability distribution of x is adapted to the monitoring result through a comparison result with y. Let the prior distribution probability density function of x be ρb(x) In that respect The prior distribution can be selected according to the understanding of the working mechanism, the engineering practice experience and the like, and meanwhile, the mathematical expression of the prior distribution is convenient for calculation and analysis as far as possible.
A specific prior probability distribution employed in the present application is shown below:
prior probability model extraction
Namely that
Wherein each one of
The setting is performed empirically. The amount of artificial setting in this form of a priori probability is small and computationally more convenient and stable.
Optionally, in an embodiment of the present application, inputting the boundary pressure and the plurality of monitoring parameters into a pre-constructed system physical model for solution, and introducing experience knowledge of a fault event of the multi-stage mechanical seal system during the solution to obtain a characteristic parameter value of the multi-stage mechanical seal system, including: and calculating the system physical model by utilizing the maximum likelihood to obtain a characteristic parameter value.
The embodiment of the application provides a probability-based quantitative analysis scheme, and the analysis result is output in the form of the maximum likelihood system state.
The maximum likelihood system state, given y and z, is found to satisfy the following conditional requirement
I.e. all outputs with the highest prior probability in x that are consistent with the monitoring. Wherein, the first and the second end of the pipe are connected with each other,
as a value of a characteristic parameter, pb() Is prior probability distribution, f (x; z) is system physical model, and y is monitoring parameter.
Then, by
And calculating the fourth type of parameters, and reconstructing a complete system state (the complete system state is a set of the first to fourth types of parameters).
In particular, s.t.f (x; z) in the maximum likelihood system state is not a conventional form of constraint in the optimization problem, and its computation is inconvenient. To facilitate the computation, the transformation is done for a specific problem, maximizing the prior probability and minimizing the residual between f (x; z) and y in the same computation step.
Considering the difference between the model output f (x; z) and the observed value y as obeying a probability distribution with a small variance, which is formally incorporated into the formula of the maximum likelihood analysis, the simplified form of the maximum likelihood analysis under the specific prior probability distribution in the embodiment of the present application, i.e., the algorithm output form, is shown as follows:
problem transformation into
Adjustment of
To a sufficiently low level until in the calculation
Is small enough.
In step S103, the characteristic parameter values are matched with the fault events, and the fault tracing is performed on the multi-stage mechanical seal system according to the matching result.
Therefore, the internal working state of the multi-stage seal is judged based on reasonable probability hypothesis, the position where the fault is most likely to occur is identified, and the technical personnel can make targeted treatment. A targeted solution is provided for the situation that the obtained information is not enough to accurately solve the state of the multi-stage sealing system and an under-defined problem is formed under the condition that the monitoring conditions generally applied in enterprises are limited.
The method for tracing the fault of the multistage mechanical sealing system by using a specific embodiment will be explained in the following with reference to the attached drawings. Fig. 3 shows an execution logic of a specific failure tracing method for a multistage mechanical seal system according to the present application. As shown in fig. 3, algorithm parameters are first configured according to a system model, wherein the system is a multi-stage sealing system as shown in fig. 2. In the system of FIG. 2, it is required to operate at a pressure p1And a liquid medium of pressure p4The dynamic sealing is realized between the atmosphere and the leakage rate is only qL. Without regard to temperature variations. The medium is considered incompressible (a liquid with a pressure not too high usually represents a near incompressible, the model is calculated in incompressible).
Wherein, the chamber contains:
(a) upstream of the primary stage. Pressure of p1Is a boundary;
(b) second stageUpstream, i.e. one stage downstream, at a pressure p2Internal, monitored;
(c) three stages upstream, i.e. two stages downstream, at a pressure p3Internal, monitored;
(d) atmospheric, i.e. three stages downstream, at a pressure p4Is a boundary;
(e) high pressure leak line (generally so called, not actually a "leak", these flows being returned by other treatment means, not relevant for the present application), at a pressure p5Is a boundary.
In the embodiments of the present application, the pressures are gauge pressures. p is a radical of1The design value is 15.4MPa, and the actual fluctuation is small; atmospheric fixation as p40 MPa; high voltage leakage line pressure is fixed as p5＝0.25MPa。
All monitoring results were averaged over a 5 minute period and input to the algorithm (corresponding to the pre-processing of the monitoring results described above).
The system comprises 3 seals, 4 choke tubes. The designed leakage rate of the seal is 5L/h, and the designed flow rate of the coil is 375L/h.
From the flow relationship, the flow identified in FIG. 2 satisfies the following equation (i.e., the chamber model described above), as shown in the following equation:
q1+q12-q2-q25＝0
q2+q13-q3-q35＝0
definition of
qH＝q25+q35
In all flows, only qHIs monitored.
It is noted that q is most critical to sealing performanceLIn the prior art, q is for a plurality of multi-stage sealing systems in the same unitLThe sum is monitored, the monitoring results of all the units cannot be separated, and the units are not monitored in the embodiment of the application.
The characteristics of the seal and the choke are described by the following equations (i.e., the above component models):
q1 exp(s1)＝kSEAL(p1-p2)+bSEAL
q1 exp(s2)＝kSEAL(p2-p3)+bSEAL
q3 exp(s3)＝kSEAL(p3-p4)+bSEAL
q12 exp(s12)＝kTHROTTLE_5MPA(p1-p2)+bTHROTTLE_5MPA
q13 exp(s13)＝kTHROTTLE_10MPA(p1-p3)+bTHROTTLE_10MPA
q25 exp(s25)＝kTHROTTLE_5MPA(p2-p5)+bTHROTTLE_5MPA
q35 exp(s35)＝kTHROTTLE_10MPA(p3-p5)+bTHROTTLE_10MPA
wherein the following parameters are calculated theoretically:
kSEAL＝3×(5L/h)/(5MPa)
bSEAL＝-2×5L/h
kTHROTTLE_5MPA＝0.55×(375L/h)/(5MPa)
bTHROTTLE_5MPA＝-0.45×375L/h
kTHROTTLE_10MPA＝0.55×(375L/h)/(10MPa)
bTHROTTLE_10MPA＝-0.45×375L/h
the remainder s1，s2，s3，s12，s13，s25，s35The characteristic parameter to be determined, i.e. the parameter of the first type mentioned above. In the design state, they should both be 0. Definition x ═ x1 x2 … x7]＝[s1 s2 s3 s12 s13 s25 s35]。
The second type of parameter corresponds to z ═ z1 z2 z3]＝[p1 p4 p5]. Wherein p is1There is a small fluctuation and the other two components are fixed.
The third type of parameter corresponds to y ═ y1 y2 y3]＝[p2 p3 qH]。
Then, given the prior probability distribution:
wherein the flow is selected according to design flow
And
the maximum likelihood analysis method is as previously described.
For example, p is obtained by averaging the monitoring results over a certain 5-minute interval1＝15.440MPa，p2＝10.060MPa，p3＝5.155MPa，qH＝772.8L/h。
The inputs to the algorithm are y ═ 10.060MPa 5.155MPa 772.80L/h ], z ═ 15.440MPa 0.25MPa 0 MPa.
Maximum likelihood analysis is obtained
The reconstructed non-boundary monitoring result is
Further calculate the unmonitorable amount
According to the fault tracing method for the multistage mechanical sealing system, provided by the embodiment of the application, the boundary pressure of the multistage mechanical sealing system and a plurality of monitoring parameters acquired by a sensor are obtained; inputting the boundary pressure and a plurality of monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multi-stage mechanical sealing system in the solving process to obtain characteristic parameter values of the multi-stage mechanical sealing system; and matching the characteristic parameter values with the fault events, and tracing the fault of the multistage mechanical seal system according to the matching result. Therefore, the internal working state of the multistage seal is judged, the position where the fault is most likely to occur is identified, and a technician can perform targeted treatment.
Next, a failure tracing device of a multistage mechanical seal system according to an embodiment of the present application is described with reference to the drawings.
Fig. 4 is a schematic block diagram of a failure tracing apparatus of a multi-stage mechanical seal system according to an embodiment of the present application.
As shown in fig. 4, the multistage mechanical seal system failure tracing apparatus 10 includes: an acquisition module 100, a calculation module 200, and a tracing module 300.
The acquiring module 100 is configured to acquire boundary pressure of the multi-stage mechanical seal system and a plurality of monitoring parameters acquired by the sensor. And the calculation module 200 is used for inputting the boundary pressure and the plurality of monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multi-stage mechanical sealing system in the solving process to obtain characteristic parameter values of the multi-stage mechanical sealing system. And the source tracing module 300 is configured to match the characteristic parameter values with the fault events, and perform fault source tracing on the multi-stage mechanical seal system according to a matching result.
Optionally, in an embodiment of the present application, the method further includes: the first modeling module is used for establishing a chamber model and a component model of the multi-stage mechanical sealing system; and the second modeling module is used for constructing a system physical model according to the chamber model and the component model.
Optionally, in one embodiment of the present application, empirical knowledge of a failure event of a multi-stage mechanical seal system is introduced, including: empirical knowledge of the possible failure events of a multi-stage mechanical seal system is introduced in the form of a prior probability distribution.
Optionally, in an embodiment of the present application, the calculation module 200 is specifically configured to calculate the system physical model by using maximum likelihood to obtain the characteristic parameter value.
Optionally, in an embodiment of the present application, calculating a system physical model by using maximum likelihood to obtain a characteristic parameter value includes:
wherein the content of the first and second substances,
as a value of a characteristic parameter, pb(x) Is prior probability distribution, f (x; z) is system physical model, and y is monitoring parameter.
It should be noted that the foregoing explanation of the embodiment of the method for tracing a fault of a multi-stage mechanical sealing system is also applicable to a device for tracing a fault of a multi-stage mechanical sealing system in this embodiment, and details are not repeated here.
According to the fault tracing device for the multistage mechanical sealing system, the boundary pressure of the multistage mechanical sealing system and a plurality of monitoring parameters acquired by a sensor are obtained; inputting the boundary pressure and a plurality of monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multi-stage mechanical sealing system in the solving process to obtain characteristic parameter values of the multi-stage mechanical sealing system; and matching the characteristic parameter values with the fault events, and tracing the fault of the multistage mechanical seal system according to the matching result. And (4) outputting an analysis result in a form of a maximum likelihood system state based on the quantitative analysis scheme of the probability. Therefore, the internal working state of the multistage seal can be judged, the position where the fault is most likely to occur is identified, and a technician can perform targeted treatment. The method solves the problem that the mathematical model abstracted by the multi-stage mechanical sealing system is under-defined and can not be solved.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
a memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502.
The processor 502 executes the program to implement the failure tracing method of the multi-stage mechanical seal system provided in the above embodiments.
Further, the electronic device further includes:
a communication interface 503 for communication between the memory 501 and the processor 502.
A memory 501 for storing computer programs operable on the processor 502.
The memory 501 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 5, but that does not indicate only one bus or one type of bus.
Optionally, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a chip, the memory 501, the processor 502, and the communication interface 503 may complete communication with each other through an internal interface.
The processor 502 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program is executed by a processor to implement the method for tracing the failure of the multi-stage mechanical sealing system as above.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
Claims (12)
1. A multi-stage mechanical sealing system fault tracing method is characterized by comprising the following steps:
acquiring boundary pressure of a multistage mechanical sealing system and a plurality of monitoring parameters acquired by a sensor;
inputting the boundary pressure and the monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multi-stage mechanical sealing system in the solving process to obtain characteristic parameter values of the multi-stage mechanical sealing system;
and matching the characteristic parameter values with the fault events, and tracing the fault of the multistage mechanical seal system according to the matching result.
2. The method of claim 1, wherein before obtaining the boundary pressure of the multi-stage mechanical seal system and the plurality of monitoring parameters collected by the sensor, the method further comprises:
establishing a chamber model and a component model of the multistage mechanical sealing system;
and constructing the system physical model according to the chamber model and the component model.
3. The method of claim 1, wherein said introducing empirical knowledge of said multi-stage mechanical seal system failure event comprises:
empirical knowledge of possible failure events of the multi-stage mechanical seal system is introduced in the form of a prior probability distribution.
4. The method of claim 3, wherein inputting the boundary pressure and the plurality of monitoring parameters into a pre-constructed system physical model for solution and introducing empirical knowledge of a failure event of the multi-stage mechanical seal system during the solution to obtain the characteristic parameter values of the multi-stage mechanical seal system comprises:
and calculating the system physical model by utilizing the maximum likelihood to obtain the characteristic parameter value.
5. The method of claim 4, wherein said calculating the system physics model using maximum likelihood to obtain the characteristic parameter value comprises:
wherein the content of the first and second substances,
as a value of a characteristic parameter, pb(x) Is prior probability distribution, f (x; z) is system physical model, and y is monitoring parameter.
6. The utility model provides a multistage mechanical seal system trouble device of tracing to source which characterized in that includes:
the acquisition module is used for acquiring the boundary pressure of the multistage mechanical sealing system and a plurality of monitoring parameters acquired by the sensor;
the calculation module is used for inputting the boundary pressure and the monitoring parameters into a pre-constructed system physical model for solving, and introducing experience knowledge of fault events of the multistage mechanical sealing system in the solving process to obtain characteristic parameter values of the multistage mechanical sealing system;
and the source tracing module is used for matching the characteristic parameter values with the fault events and carrying out fault source tracing on the multistage mechanical seal system according to matching results.
7. The apparatus of claim 6, further comprising:
the first modeling module is used for establishing a chamber model and a component model of the multi-stage mechanical sealing system;
and the second modeling module is used for constructing the system physical model according to the chamber model and the component model.
8. The apparatus of claim 6, wherein said introducing empirical knowledge of said multi-stage mechanical seal system failure event comprises:
empirical knowledge of possible failure events of the multi-stage mechanical seal system is introduced in the form of a prior probability distribution.
9. The device according to claim 8, characterized in that the calculation module is specifically configured to,
and calculating the system physical model by utilizing the maximum likelihood to obtain the characteristic parameter value.
10. The apparatus of claim 9, wherein said calculating the system physics model using maximum likelihood to obtain the characteristic parameter value comprises:
wherein the content of the first and second substances,
as a value of a characteristic parameter, pb(x) Is prior probability distribution, f (x; z) is system physical model, and y is monitoring parameter.
11. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the multistage mechanical seal system fault tracing method according to any one of claims 1 to 5.
12. A computer-readable storage medium having stored thereon a computer program, the program being executable by a processor for implementing the method for tracing a failure of a multistage mechanical seal system as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146479.4A CN114638174B (en) | 2022-02-17 | 2022-02-17 | Multistage mechanical seal system fault tracing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146479.4A CN114638174B (en) | 2022-02-17 | 2022-02-17 | Multistage mechanical seal system fault tracing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114638174A true CN114638174A (en) | 2022-06-17 |
| CN114638174B CN114638174B (en) | 2023-11-21 |
Family
ID=81945796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210146479.4A Active CN114638174B (en) | 2022-02-17 | 2022-02-17 | Multistage mechanical seal system fault tracing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638174B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100121609A1 (en) * | 2008-11-10 | 2010-05-13 | Mitek Analytics Llc | Method and system for diagnostics of apparatus |
| US20120022350A1 (en) * | 2010-07-21 | 2012-01-26 | Streamline Automation, Llc | Sensor fusion and probabilistic parameter estimation method and apparatus |
| CN109116188A (en) * | 2018-09-05 | 2019-01-01 | 广东电网有限责任公司 | A kind of electric power system fault deduction method, device, equipment and readable storage medium storing program for executing |
| US20200124494A1 (en) * | 2018-10-18 | 2020-04-23 | Aquarius-Spectrum Ltd. | Methods Circuits Assemblies Devices Systems and Functionally Associated Machine Executable Code For Mechanical Failure Classification Condition Assessment and Remediation Recommendation |
| US20210089928A1 (en) * | 2018-03-16 | 2021-03-25 | Hitachi, Ltd. | Failure probability evaluation system and method |
| CN113323891A (en) * | 2021-06-30 | 2021-08-31 | 北京航空航天大学 | Nuclear power station main pump seal fault diagnosis method based on hybrid model |
-
2022
- 2022-02-17 CN CN202210146479.4A patent/CN114638174B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100121609A1 (en) * | 2008-11-10 | 2010-05-13 | Mitek Analytics Llc | Method and system for diagnostics of apparatus |
| US20120022350A1 (en) * | 2010-07-21 | 2012-01-26 | Streamline Automation, Llc | Sensor fusion and probabilistic parameter estimation method and apparatus |
| US20210089928A1 (en) * | 2018-03-16 | 2021-03-25 | Hitachi, Ltd. | Failure probability evaluation system and method |
| CN109116188A (en) * | 2018-09-05 | 2019-01-01 | 广东电网有限责任公司 | A kind of electric power system fault deduction method, device, equipment and readable storage medium storing program for executing |
| US20200124494A1 (en) * | 2018-10-18 | 2020-04-23 | Aquarius-Spectrum Ltd. | Methods Circuits Assemblies Devices Systems and Functionally Associated Machine Executable Code For Mechanical Failure Classification Condition Assessment and Remediation Recommendation |
| CN113323891A (en) * | 2021-06-30 | 2021-08-31 | 北京航空航天大学 | Nuclear power station main pump seal fault diagnosis method based on hybrid model |
Non-Patent Citations (2)
| Title |
|---|
| ZHAO X R 等: "A Study on Intelligence Rconginition Alorithm Based on Mechanical Seal Fault Feature", KEY ENGINEERING MATERIALS, vol. 426 * |
| 姜洪权;王金宇;高建民;高智勇;索海龙;: "面向复杂系统故障溯源的SDG-FG模型建模方法", 计算机集成制造系统, no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114638174B (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9983114B2 (en) | Methods and systems for monitoring loading of an air filter | |
| WO2018138880A9 (en) | Model parameter value estimation device and estimation method, program, recording medium with program recorded thereto, and model parameter value estimation system | |
| CN109523027B (en) | Boiler operation data monitoring method and device based on Bayesian network | |
| US11165799B2 (en) | Anomaly detection and processing for seasonal data | |
| CN102880170A (en) | System failure early warning method based on baseline model and Bayesian factor | |
| CN106250709A (en) | Gas turbine abnormality detection based on sensors association network and fault diagnosis algorithm | |
| AU2015315838A1 (en) | Apparatus and method for ensembles of kernel regression models | |
| JP6973377B2 (en) | Analyst, analysis method, and program | |
| CN110431499B (en) | Method for characterizing one or more faults in a system | |
| CN114638174A (en) | Fault tracing method, device, equipment and storage medium for multistage mechanical sealing system | |
| CN113227642B (en) | Method for detecting leaks in a gas network under pressure or vacuum and gas network | |
| Wang et al. | A Bayesian method for on-line evaluation of uncertainty in measurement of Coriolis flow meters | |
| WO2021140942A1 (en) | Diagnosing device, diagnosing method, and program | |
| US11669082B2 (en) | Online fault localization in industrial processes without utilizing a dynamic system model | |
| US20090037155A1 (en) | Machine condition monitoring using a flexible monitoring framework | |
| JP7127477B2 (en) | LEARNING METHOD, APPARATUS AND PROGRAM, AND EQUIPMENT FAILURE DIAGNOSIS METHOD | |
| JP6874847B2 (en) | State analyzer, state analysis method and program | |
| WO2015040683A1 (en) | Sensor soundness determination method and sensor soundness determination device | |
| JP2020163300A (en) | Management system of water treatment apparatus | |
| JP2020009080A (en) | System and method for monitoring device state | |
| JP7397623B2 (en) | Plant condition evaluation device, plant condition evaluation method and program | |
| Du et al. | A novel critical point detection method for mechanical deformation in tightening processes | |
| Meynen et al. | Robust Fault Detection with a Distributed and Decentralized State-Set Observer | |
| US11734594B1 (en) | State monitoring system | |
| JP7153585B2 (en) | Abnormality cause estimation method and abnormality cause estimation device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |