CN114638174B - Multi-stage mechanical seal system fault traceability method, device, equipment and storage medium - Google Patents

Abstract

This application discloses a multi-stage mechanical seal system fault traceability method, device, electronic equipment and storage medium. The method includes: obtaining the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by the sensor; and multiple monitoring parameters are input into the pre-built system physical model for solution, and the empirical understanding of multi-stage mechanical seal system failure events is introduced during the solution process to obtain the characteristic parameter values of the multi-stage mechanical seal system; the characteristic parameter values and faults are The events are matched, and the fault source of the multi-stage mechanical sealing system is traced based on the matching results. Embodiments of the present application can determine the internal working status of multi-stage seals and identify the most likely locations where failures occur, allowing technicians to make targeted measures. This solves the problem of multi-stage sealing systems, especially when their abstract mathematical models are under-defined and have no definite solution.

Description

Multi-stage mechanical seal system fault traceability methods, devices, equipment and storage media

Technical field

This application relates to the field of fluid sealing technology, and in particular to a multi-stage mechanical sealing system fault traceability method, device, equipment and storage medium.

Background technique

Mechanical seal is an end face dynamic sealing device. It is necessary to reduce or eliminate the friction and wear of the friction pair (formed by the two end faces in relative motion and the fluid medium) while maintaining low or no leakage to extend the life. For occasions with high pressure, multi-stage mechanical seals are usually designed to gradually reduce the pressure and reduce the working load of each stage.

In order to detect the working status of the mechanical seal, related technologies usually use supporting auxiliary systems to monitor the pressure, flow, etc. in the external pipeline of the mechanical seal.

However, when companies apply the supporting auxiliary system, due to limitations of monitoring conditions, the results obtained by the auxiliary system monitoring in the multi-stage mechanical seal system cannot accurately predict the internal working status of the mechanical seal, especially the leakage of the seals at all levels. Therefore, when there is an abnormality in the system operation, the cause and risk of the abnormality cannot be determined, which needs to be solved urgently.

Contents of the invention

This application provides a multi-stage mechanical seal system fault traceability method, device, electronic equipment and storage medium to solve the problem of multi-stage seal system, especially the abstract mathematical model that is under-defined when solving and has no definite solution. question.

The first embodiment of the present application provides a method for tracing faults in a multi-stage mechanical seal system, including the following steps: obtaining the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by sensors; combining the boundary pressure and the Multiple monitoring parameters are input into the pre-built system physical model for solution, and the empirical understanding of the fault events of the multi-stage mechanical seal system is introduced during the solution process to obtain the characteristic parameter values of the multi-stage mechanical seal system; The characteristic parameter values are matched with the fault event, and the fault source of the multi-stage mechanical seal system is traced based on the matching results.

Optionally, in one embodiment of the present application, before obtaining the boundary pressure of the multi-stage mechanical seal system and the multiple monitoring parameters collected by the sensor, the method further includes: establishing a chamber model of the multi-stage mechanical seal system. and component models; construct the system physical model based on the chamber model and the component model.

Optionally, in one embodiment of the present application, introducing empirical understanding of failure events of the multi-stage mechanical seal system includes: introducing possible failures of the multi-stage mechanical seal system in the form of a priori probability distribution experience of events.

Optionally, in one embodiment of the present application, the boundary pressure and the multiple monitoring parameters are input into a pre-built system physical model for solution, and the multi-stage mechanical seal is introduced during the solution process The empirical understanding of system failure events and obtaining the characteristic parameter values of the multi-stage mechanical seal system include: using maximum likelihood to calculate the physical model of the system to obtain the characteristic parameter values.

Optionally, in one embodiment of the present application, the maximum likelihood is used to calculate the system physical model to obtain the characteristic parameter values, including:

in, is the characteristic parameter value, ρ _b (x) is the prior probability distribution, f (x; z) is the system physical model, and y is the monitoring parameter.

The second embodiment of the present application provides a multi-stage mechanical seal system fault traceability device, including: an acquisition module, used to obtain the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by sensors; a calculation module, used to obtain The boundary pressure and the multiple monitoring parameters are input into the pre-built system physical model for solution, and the empirical understanding of the fault events of the multi-stage mechanical seal system is introduced during the solution process to obtain the multi-stage mechanical seal system. The characteristic parameter value; the traceability module is used to match the characteristic parameter value with the fault event, and perform fault traceability of the multi-stage mechanical seal system according to the matching result.

Optionally, in one embodiment of the present application, it also includes: a first modeling module, used to establish the chamber model and component model of the multi-stage mechanical seal system; a second modeling module, used according to the The chamber model and the component model construct the system physical model.

Optionally, in one embodiment of the present application, introducing empirical understanding of failure events of the multi-stage mechanical seal system includes: introducing possible failures of the multi-stage mechanical seal system in the form of a priori probability distribution experience of events.

Optionally, in one embodiment of the present application, the calculation module is specifically configured to use maximum likelihood to calculate the system physical model to obtain the characteristic parameter values.

Optionally, in one embodiment of the present application, the maximum likelihood is used to calculate the system physical model to obtain the characteristic parameter values, including:

in, is the characteristic parameter value, ρ _b (x) is the prior probability distribution, f (x; z) is the system physical model, and y is the monitoring parameter.

A third embodiment of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the program to execute The multi-stage mechanical seal system fault tracing method as described in the above embodiment.

The fourth embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and the program is executed by a processor to perform the multi-level mechanical seal system fault tracing method as described in the above embodiment.

Therefore, this application has at least the following beneficial effects:

This application uses a quantitative analysis solution based on probability, which outputs the analysis results in the form of maximum likelihood system status, determines the internal working status of the multi-stage seal, and identifies the location where the fault is most likely to occur, allowing technicians to make targeted actions. This solves the problem of multi-stage sealing systems, especially when their abstract mathematical models are under-defined and have no definite solution.

Additional aspects and advantages of the 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 application.

Description of the drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

Figure 1 is a flow chart of a multi-stage mechanical seal system fault traceability method provided according to an embodiment of the present application;

Figure 2 is a schematic structural diagram of a multi-stage mechanical seal system according to an embodiment of the present application;

Figure 3 is a schematic execution logic diagram of a multi-stage mechanical seal system fault tracing method provided according to an embodiment of the present application;

Figure 4 is an example diagram of a multi-stage mechanical seal system fault traceability device according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the application.

Explanation of reference signs: acquisition module - 100, calculation module - 200, traceability module - 300, memory - 501, processor - 502, communication interface - 503.

Detailed ways

The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application, but should not be construed as limiting the present application.

The following describes a multi-level mechanical seal system fault tracing method, device, electronic equipment and storage medium according to the embodiment of the present application with reference to the accompanying drawings. In response to the problems mentioned in the above background technology, this application provides a multi-stage mechanical seal system fault traceability method. In this method, the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by sensors are obtained; The boundary pressure and multiple monitoring parameters are input into the pre-built system physical model for solution, and the empirical understanding of multi-stage mechanical seal system failure events is introduced during the solution process to obtain the characteristic parameter values of the multi-stage mechanical seal system; the characteristic parameters are The value is matched with the fault event, and the fault source of the multi-stage mechanical seal system is traced based on the matching results. From this, the internal working status of the multi-stage seal can be judged, and the location where the fault is most likely to occur can be identified, allowing technicians to make targeted measures and solve the problem of multi-stage seal systems, especially the abstract mathematical model. When solving, problems such as under-definition and no definite solution appear.

Specifically, FIG. 1 is a flow chart of a multi-stage mechanical seal system fault tracing method provided according to an embodiment of the present application.

As shown in Figure 1, the multi-stage mechanical seal system fault traceability method includes the following steps:

In step S101, the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by the sensor are obtained.

Specifically, the applicable object of the embodiments of this application may be a multi-stage mechanical seal system abstracted as the following model, as shown in Figure 2:

1) Inside and at the boundary of the system are some chambers. A chamber contains a certain amount of medium and is considered to have a consistent pressure. Consider only the case where there is only one medium. Transfer of media occurs between chambers, and the transfer rate is measured by flow rate. The chamber is divided into two categories: internal and boundary. The pressure at the boundary is determined by the working 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 (commonly 2 to 3. The single-stage sealing situation is simple and there is no need to use this application). Multi-stage seals are connected in series, that is, the downstream chamber of the previous stage seal is the upstream chamber of the next stage seal. Each mechanical seal has a certain leakage rate (the leakage rate is also a kind of flow rate). The leakage rate is determined by the surrounding environment of the mechanical seal (including temperature, upstream pressure, and downstream pressure. In some cases, the effect of temperature can be ignored) and the mechanical seal. Determined by the characteristic parameters.

3) It contains several throttling tubes (some are also called "coils"). The flow rate of the throttle tube is determined by its surrounding environment (upstream pressure and downstream pressure. It has little relationship with temperature) and characteristic parameters.

4) Contains several sensors. The sensor monitors the value of a specific physical quantity to obtain monitoring results, which are provided to the analysis method through software and hardware facilities such as storage devices and databases. Monitoring results may undergo some preprocessing before being input into the algorithm.

At the same time, the above system includes multiple types of parameters. For convenience of description, the embodiments of this application define them as follows:

Category 1: Characteristic parameters. They are unknown parameters in the component models of mechanical seals and coils, which are quantifications of potential failures. They are not monitored and are the targets for the algorithm to judge;

Category 2: Boundary pressure. Pressure is the easiest quantity to monitor, so in the embodiments of this application, it is considered that the boundary pressure is always monitored, which is basically consistent with engineering practice;

The third category: monitored parameters among parameters other than the above two categories; wherein, in the embodiment of the present application, the monitored parameters may refer to other parameters other than boundary pressure and characteristic parameters in the multi-stage sealing system that can be passed through the sensor. Monitored parameters.

Category 4: Other parameters.

It can be understood that the task of the embodiment of the present application is to infer the characteristic parameters of the mechanical seal and coil, the chamber pressure, and the flow rate between chambers based on the monitoring results provided by the sensor.

Optionally, in one embodiment of the present application, a chamber model and component model of a multi-stage mechanical seal system are established; a system physical model is constructed based on the chamber model and component model, and the expression form of the system physical model is: Among them,/> is the calculation result of the monitoring parameters by the system physical model, x is the characteristic parameter, and z is the boundary pressure.

Specifically, the above component model is established through mechanical seals and coils to describe how their flow rates are calculated from the surrounding environment parameters and their own characteristic parameters (the first type of parameters). There are many different modeling methods for these models (especially those of mechanical seals).

Internal Chambers The chambers described above can be modeled to describe how their pressure is affected by the flow to the chambers they are connected to. This model is divided into two forms: compressible media and incompressible media:

(a) For incompressible media, the model can be simply expressed as "the net flow is 0";

(b) For compressible media, the rate of change of pressure is affected by the net flow rate and the characteristics of the medium.

What needs to be understood is that the system physical model is defined as a system that inputs all characteristic parameters (first type parameters) and boundary pressures (second type parameters), and outputs monitoring results of all non-boundary pressures (third type parameters). Predictive model. This model is obtained by solving the above component model and chamber model simultaneously.

In the embodiment of this application, for convenience of description, all characteristic parameters are denoted as (First type parameter), the boundary pressure is/> (the second type of parameters), the monitoring results except boundary pressure are (Third type parameter). For fault diagnosis requirements, x is defined so that it is 0 at the design point.

The physical model of the system is denoted as Indicates the model’s calculation results of the monitoring results.

In fact, from the first and second types of parameters, not only the third type of parameters can be solved, but also the fourth type of parameters can be solved. In the embodiment of the present application, the fourth type of parameter is not included in the output of the above mathematical expression.

In step S102, the boundary pressure and multiple monitoring parameters are input into the pre-built system physical model for solution, and the empirical understanding of multi-stage mechanical seal system failure events is introduced during the solution process to obtain the characteristic parameters of the multi-stage mechanical seal system. value.

It should be noted that depending on the model form and specific monitoring implementation, and based on the monitoring results provided by the sensor, it is speculated that the characteristic parameters of the mechanical seal and coil, chamber pressure, flow rate between chambers and other parameters may present different problems. nature. The classification of the nature of these problems should not be understood purely from an analytical perspective, but should consider their actual performance after being affected by numerical errors, model errors, etc. in calculations. Specific issues are classified as follows:

(a) Fixed solution problem. The system physical model can definitely solve all unknown quantities based on the monitoring results, and its analysis method will not be discussed below.

(b) Over-constraint problem. Mathematically, there is no solution to solving the system state based on monitoring results (the number of independent monitoring results is more than the number of independent characteristic parameters to be solved). In other words, the monitoring results may be conflicting. In this case, the system model should be changed (mainly increasing the number of characteristic parameters) or some monitoring results should be abandoned and transformed into other problem types. The analysis methods will not be discussed below.

(c) Under-constraint problem. Generally, there are multiple combinations of characteristic parameters that will produce the same monitoring results from the system physical model (the number of independent monitoring results is less than the number of independent characteristic parameters to be solved). This type of problem is the most common situation in practical applications. This is because the component model with more undetermined characteristic parameters can more accurately describe the possible fault variation range of the actual analysis object, 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 prevalence of this situation, an analytical method to solve such problems is urgently needed in engineering applications.

Optionally, in one embodiment of the present application, introducing empirical understanding of failure events of the multi-stage mechanical seal system includes: introducing empirical understanding of possible failure events of the multi-stage mechanical seal system in the form of a priori probability distribution.

In order to solve the under-constraint problem of the embodiments of the application, the embodiments of the application perform calculations based on the system physical model, prior probabilities and monitoring results, and display the results to the user in the form of solving a specific probability problem.

Specifically, embodiments of the present application use probabilistic methods to analyze under-constrained problems. First assume a prior probability distribution for Distribution adaptation monitoring results. Let the prior distribution probability density function of x be ρ _b (x). The prior distribution can be selected based on the understanding of the working mechanism, engineering practice experience, etc., and at the same time, its mathematical expression can be made as convenient as possible for calculation and analysis.

A specific prior probability distribution used in this application is as follows:

The prior probability model is taken Right now

Each of them Set with experience. This form of prior probability requires fewer artificial settings and is more convenient and stable in calculation.

Optionally, in one embodiment of the present application, the boundary pressure and multiple monitoring parameters are input into a pre-built system physical model for solution, and the empirical understanding of multi-stage mechanical seal system failure events is introduced during the solution process, and we obtain The characteristic parameter values of the multi-stage mechanical seal system include: using maximum likelihood to calculate the system physical model to obtain the characteristic parameter values.

The embodiments of the present application provide a quantitative analysis solution based on probability, and output the analysis results in the form of maximum likelihood system state.

The maximum likelihood system state, for given y and z, find the condition that satisfies the following formula

That is, the one with the greatest prior probability among all x whose output is consistent with the monitoring. in, is the characteristic parameter value, ρ _b () is the prior probability distribution, f (x; z) is the system physical model, and y is the monitoring parameter.

Then, by The fourth type of parameters is deduced and the complete system state is reconstructed (the complete system state is the set of parameters of the first to fourth types).

Specifically, s.t.f(x;z) in the maximum likelihood system state is not a conventional constraint form in optimization problems, and its calculation is inconvenient. To facilitate calculation, transformations are performed for specific problems, maximizing the prior probability and minimizing the residual between f(x;z) and y in the same calculation step.

The difference between the model output f (x; z) and the observation value y is regarded as obeying a probability distribution with a small variance, and is formally incorporated into the formula of maximum likelihood analysis. Therefore, in the embodiments of this application, The simplified form of maximum likelihood analysis under the prior probability distribution, that is, the algorithm output form is as follows:

The problem is transformed into

Adjustment to a sufficiently low level until the /> in the calculated result Small enough.

In step S103, the characteristic parameter value is matched with the fault event, and the fault source of the multi-stage mechanical seal system is traced based on the matching result.

Therefore, this application is based on reasonable probability assumptions to determine the internal working status of the multi-stage seal and identify the most likely location of the failure, so that technicians can make targeted measures. A targeted solution is provided for the situation where under the limited monitoring conditions commonly used in enterprises, the information obtained is not enough to accurately solve the state of the multi-level sealing system, resulting in an under-defined problem.

The fault traceability method of the multi-stage mechanical seal system will be described below through a specific embodiment with reference to the accompanying drawings. Figure 3 shows the execution logic of a specific multi-stage mechanical seal system fault tracing method in this application. As shown in Figure 3, the algorithm parameters are first configured according to the system model, where the system is the multi-stage sealing system shown in Figure 2. In the system in Figure 2, it is necessary to achieve dynamic sealing between the liquid medium with a pressure of p ₁ and the atmosphere with a pressure of p ₄ , so that the leakage rate is only q _L . Temperature changes are not taken into account. The medium is considered to be incompressible (liquids with not too high pressure usually appear to be almost incompressible, and the model is calculated as incompressible).

Among them, the chamber contains:

(a) Level one upstream. The pressure is p ₁ , which is the boundary;

(b) The secondary upstream, that is, the primary downstream, has a pressure of p ₂ , is inside, and is monitored;

(c) The third level upstream, that is, the second level downstream, has a pressure of p ₃ and is inside and monitored;

(d) The atmosphere, that is, the third level downstream, has a pressure of p ₄ and is the boundary;

(e) High-pressure leakage line (usually called this, but it is not actually a "leakage". These flows flow back through other treatment devices and have nothing to do with this application). The pressure is p ₅ and is the boundary.

The pressures mentioned in the examples of this application are all gauge pressures. The design value of p ₁ is 15.4MPa, and the actual fluctuation is very small; the atmosphere is fixed at p ₄ =0MPa; the pressure of the high-pressure leakage line is fixed at p ₅ =0.25MPa.

All monitoring results are averaged within 5 minutes and input into the algorithm (corresponding to the aforementioned preprocessing of monitoring results).

The system includes 3 seals and 4 throttling tubes. The design leakage rate of the seal is 5L/h, and the design flow rate of the coil is 375L/h.

According to the flow relationship, the flow rate identified in Figure 2 satisfies the following equation (i.e., the above-mentioned chamber model), as shown in the following formula:

q ₁ +q ₁₂ -q ₂ -q ₂₅ =0

q ₂ +q ₁₃ -q ₃ -q ₃₅ =0

definition

q _H =q ₂₅ +q ₃₅

Among all flows, only q _H is monitored.

It should be noted that, under the current technology, the most critical _qL for sealing performance is to monitor the sum of _qL of multiple multi-stage sealing systems in the same unit, and the monitoring results of each unit cannot be separated. In the embodiment of this application Considered unmonitored.

Use the following equations to describe the characteristics of the seal and throttle tube (i.e., the above component model):

q ₁ exp(s ₁ )=k _SEAL (p ₁ -p ₂ )+b _SEAL

q ₁ exp(s ₂ )=k _SEAL (p ₂ -p ₃ )+b _SEAL

q ₃ exp(s ₃ )=k _SEAL (p ₃ -p ₄ )+b _SEAL

q ₁₂ exp(s ₁₂ )=k _{THROTTLE_5MPA} (p ₁ -p ₂ )+b _{THROTTLE_5MPA}

q ₁₃ exp(s ₁₃ )=k _{THROTTLE_10MPA} (p ₁ -p ₃ )+b _{THROTTLE_10MPA}

q ₂₅ exp(s ₂₅ )=k _{THROTTLE_5MPA} (p ₂ -p ₅ )+b _{THROTTLE_5MPA}

q ₃₅ exp(s ₃₅ )=k _{THROTTLE_10MPA} (p ₃ -p ₅ )+b _{THROTTLE_10MPA}

The following parameters are calculated theoretically:

k _SEAL =3×(5L/h)/(5MPa)

b _SEAL =-2×5L/h

k _{THROTTLE_5MPA} =0.55×(375L/h)/(5MPa)

b _{THROTTLE_5MPA} =-0.45×375L/h

k _{THROTTLE_10MPA} =0.55×(375L/h)/(10MPa)

b _{THROTTLE_10MPA} =-0.45×375L/h

The remaining s ₁ , s ₂ , s ₃ , s ₁₂ , s ₁₃ , s ₂₅ , and s ₃₅ are the characteristic parameters that need to be determined, that is, the first type of parameters mentioned above. In the design state, they should all be 0. Define x=[x ₁ x ₂ …x ₇ ]=[s ₁ s ₂ s ₃ s ₁₂ s ₁₃ s ₂₅ s ₃₅ ].

The above second type of parameter corresponds to z=[z ₁ z ₂ z ₃ ]=[p ₁ p ₄ p ₅ ]. Among them, p ₁ has small fluctuations, and the other two components are fixed.

The above third type of parameter corresponds to y=[y ₁ y ₂ y ₃ ]=[p ₂ p ₃ q _H ].

After that, given the prior probability distribution:

Among them, select according to the design flow rate and/>

The maximum likelihood analysis method was as described previously.

For example, by averaging the monitoring results within a certain 5-minute interval, we obtain p ₁ =15.440MPa, p ₂ =10.060MPa, p ₃ =5.155MPa, and q _H =772.8L/h.

Input y=[10.060MPa 5.155MPa 772.80L/h], z=[15.440MPa 0.25MPa0MPa] into the algorithm.

Maximum likelihood analysis yields The reconstructed non-boundary monitoring result is/> Further deriving the unmonitorable quantity

According to a multi-stage mechanical seal system fault traceability method proposed in the example of this application, by obtaining the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by the sensor; inputting the boundary pressure and multiple monitoring parameters into the pre-built The system physical model is solved, and the empirical understanding of multi-stage mechanical seal system fault events is introduced in the solution process to obtain the characteristic parameter values of the multi-stage mechanical seal system; the characteristic parameter values are matched with the fault events, and the multi-stage mechanical seal system is calculated based on the matching results. Mechanical sealing system performs fault tracing. Thus, the internal working status of the multi-stage seal can be judged, and the location where the failure is most likely to occur can be identified, allowing technicians to make targeted measures.

Next, a multi-stage mechanical seal system fault tracing device proposed according to the embodiment of the present application will be described with reference to the accompanying drawings.

Figure 4 is a block diagram of a multi-stage mechanical seal system fault tracing device according to an embodiment of the present application.

As shown in FIG. 4 , the multi-level mechanical seal system fault tracing device 10 includes: an acquisition module 100 , a calculation module 200 and a traceability module 300 .

Among them, the acquisition module 100 is used to acquire the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by the sensor. The calculation module 200 is used to input the boundary pressure and multiple monitoring parameters into the pre-built physical model of the system for solving, and introduces the empirical understanding of the fault events of the multi-stage mechanical seal system during the solving process to obtain the characteristics of the multi-stage mechanical seal system. parameter value. The traceability module 300 is used to match characteristic parameter values with fault events, and perform fault traceability on the multi-stage mechanical seal system based on the matching results.

Optionally, in one embodiment of the present application, it also includes: a first modeling module for establishing a chamber model and a component model of a multi-stage mechanical seal system; a second modeling module for establishing a chamber model based on the chamber model and component models to build a physical model of the system.

Optionally, in one embodiment of the present application, introducing empirical understanding of failure events of the multi-stage mechanical seal system includes: introducing empirical understanding of possible failure events of the multi-stage mechanical seal system in the form of a priori probability distribution.

Optionally, in one embodiment of the present application, the calculation module 200 is specifically configured to calculate the system physical model using maximum likelihood to obtain characteristic parameter values.

Optionally, in one embodiment of the present application, maximum likelihood is used to calculate the system physical model to obtain characteristic parameter values, including:

in, is the characteristic parameter value, ρ _b (x) is the prior probability distribution, f (x; z) is the system physical model, and y is the monitoring parameter.

It should be noted that the foregoing explanation of the embodiment of a multi-stage mechanical seal system fault traceability method is also applicable to the multi-stage mechanical seal system fault traceability device of this embodiment, and will not be described again here.

According to a multi-stage mechanical seal system fault traceability device proposed in the example of this application, by obtaining the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by the sensor; inputting the boundary pressure and multiple monitoring parameters into the pre-built The system physical model is solved, and the empirical understanding of multi-stage mechanical seal system fault events is introduced in the solution process to obtain the characteristic parameter values of the multi-stage mechanical seal system; the characteristic parameter values are matched with the fault events, and the multi-stage mechanical seal system is calculated based on the matching results. Mechanical sealing system performs fault tracing. A probability-based quantitative analysis scheme that outputs analysis results in the form of maximum likelihood system states. From this, the internal working status of the multi-stage seal can be judged, and the location where the fault is most likely to occur can be identified, allowing technicians to make targeted measures. It solves the problem that the abstract mathematical model of the multi-stage mechanical seal system is under-defined and cannot have a definite solution when solving it.

FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include:

Memory 501, processor 502, and a computer program stored on memory 501 and executable on processor 502.

When the processor 502 executes the program, the multi-level mechanical seal system fault tracing method provided in the above embodiment is implemented.

Furthermore, electronic equipment also includes:

Communication interface 503 is used for communication between the memory 501 and the processor 502.

Memory 501 is used to store computer programs that can be run on processor 502.

The memory 501 may include 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 can be connected to each other through a bus and complete communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one thick line is used in Figure 5, but it does not mean that there is only one bus or one type of bus.

Optionally, in terms of specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on one chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through the internal interface.

The processor 502 may be a Central Processing Unit (CPU for short), an Application Specific Integrated Circuit (ASIC for short), or one or more processors configured to implement the embodiments of the present application. integrated circuit.

This embodiment also provides a computer-readable storage medium on which a computer program is stored, which is characterized in that when the program is executed by a processor, the above multi-level mechanical seal system fault tracing method is implemented.

In the description of this specification, reference to the terms "one embodiment," "some embodiments," "an example," "specific examples," or "some examples" or the like means that specific features are described in connection with the embodiment or example. , structures, materials or features are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the specific features, structures, materials or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, those skilled in the art may combine and combine different embodiments or examples and features of different embodiments or examples described in this specification unless they are inconsistent with each other.

In addition, the terms “first” and “second” are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Therefore, features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically limited.

Any process or method descriptions in flowcharts or otherwise described herein may be understood to represent modules, segments, or portions of code that include one or more executable instructions for implementing customized logical functions or steps of the process. , and the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed out of the order shown or discussed, including in a substantially simultaneous manner or in the reverse order, depending on the functionality involved, which shall It should be understood by those skilled in the technical field to which the embodiments of this application belong.

It should be understood that various parts of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if it is implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: discrete logic gate circuits with logic functions for implementing data signals; Logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

Those of ordinary skill in the art can understand that all or part of the steps involved in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. The program can be stored in a computer-readable storage medium. When executed, one of the steps of the method embodiment or a combination thereof is included.

Claims (6)

1. A multi-stage mechanical seal system fault traceability method, which is characterized by including the following steps: Obtain the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by the sensor; The boundary pressure and the multiple monitoring parameters are input into the pre-built system physical model for solution, and the empirical understanding of the fault events of the multi-stage mechanical seal system is introduced during the solution process to obtain the multi-stage mechanical seal system. characteristic parameter values; Match the characteristic parameter value with the fault event, and perform fault tracing on the multi-stage mechanical seal system based on the matching results; The introduction of empirical understanding of failure events of the multi-stage mechanical seal system includes: introducing empirical understanding of possible failure events of the multi-stage mechanical seal system in the form of a priori probability distribution; The boundary pressure and the multiple monitoring parameters are input into the pre-built system physical model for solution, and the empirical understanding of the multi-stage mechanical seal system failure events is introduced during the solution process to obtain the multi-stage mechanical seal system. The characteristic parameter values of the sealing system include: calculating the system physical model using maximum likelihood to obtain the characteristic parameter values; The maximum likelihood is used to calculate the system physical model to obtain the characteristic parameter values, including: in, is the characteristic parameter value, ρ _b (x) is the prior probability distribution, f (x; z) is the system physical model, and y is the monitoring parameter. 2. The method according to claim 1, characterized in that before obtaining the boundary pressure of the multi-stage mechanical seal system and the multiple monitoring parameters collected by the sensor, it further includes: Establish the chamber model and component model of the multi-stage mechanical seal system; The system physical model is constructed based on the chamber model and the component model. 3. A multi-stage mechanical seal system fault traceability device, which is characterized by including: The acquisition module is used to acquire the boundary pressure of the multi-stage mechanical seal system and multiple monitoring parameters collected by the sensor; The calculation module is used to input the boundary pressure and the multiple monitoring parameters into the pre-built system physical model for solving, and introduce the empirical understanding of the multi-stage mechanical sealing system failure event during the solving process to obtain the above-mentioned Characteristic parameter values of multi-stage mechanical sealing systems; A traceability module, used to match the characteristic parameter value with the fault event, and perform fault traceability of the multi-stage mechanical seal system according to the matching results; The calculation module includes: introducing empirical knowledge of possible failure events of the multi-stage mechanical seal system in the form of a priori probability distribution; The calculation module is specifically used to calculate the system physical model using maximum likelihood to obtain the characteristic parameter values; The maximum likelihood is used to calculate the system physical model to obtain the characteristic parameter values, including: in, is the characteristic parameter value, ρ _b (x) is the prior probability distribution, f (x; z) is the system physical model, and y is the monitoring parameter. 4. The device according to claim 3, further comprising: The first modeling module is used to establish the chamber model and component model of the multi-stage mechanical seal system; The second modeling module is used to build the system physical model according to the chamber model and the component model. 5. An electronic device, characterized in that it includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the claims as claimed in The multi-stage mechanical seal system fault traceability method described in any one of requirements 1-2. 6. A computer-readable storage medium with a computer program stored thereon, characterized in that the program is executed by a processor to implement the multi-stage mechanical seal system failure as claimed in any one of claims 1-2. Traceability method.