Method and device for establishing failure probability prediction model, equipment and storage medium

Abstract

The application discloses a fault probability prediction model establishment method and device, equipment and a storage medium, and the method comprises the steps of acquiring the transmitting power and the reflected power of a high power amplifier unit at the same time; calculating the decibel difference value of the transmitting power and the reflected power; establishing a fault probability solving model; and obtaining the fault probability prediction model according to the fitting function of the fault probability prediction model. The application can improve the overall performance of the high power amplifier, and optimize the operation efficiency of the measurement operation and control equipment.

Description

Technical Field

[0001] This invention belongs to the field of health management technology for aerospace telemetry, tracking and control equipment, and particularly relates to a method, device, equipment and storage medium for establishing a fault probability prediction model. Background Technology

[0002] With the vigorous development of the space industry, various low-, medium-, and high-altitude satellites have been launched one after another. In order to organize the orderly operation of these satellites, the space telemetry, tracking, and command (TT&C) equipment needs to be rationally scheduled and planned. The space TT&C equipment has a complex structure, mainly consisting of a launch subsystem, a high-frequency receiving subsystem, a satellite feeder subsystem, a multi-functional baseband subsystem, a data interaction subsystem, a time and frequency subsystem, and a test and calibration subsystem. Each subsystem is composed of multiple components. As one of the important components of the launch subsystem, the high-frequency power amplifier's gain will affect the performance of the launch subsystem, and thus the operational effectiveness of the entire space TT&C equipment.

[0003] The high-power amplifier (HPA) consists of a pre-stage monitoring unit and a final-stage power amplifier unit. The health status of these unit modules determines the overall performance of the HPA. Typically, as the equipment ages, these unit modules will exhibit various forms of damage. Currently, the determination of whether to replace damaged unit modules relies mainly on manual experience, lacking definitive assessment criteria. Failure to predict the health status of unit modules and replace damaged ones in a timely manner during equipment operation will reduce the equipment's launch performance and affect the effectiveness of aerospace telemetry and control equipment. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies by providing a method, apparatus, device, and storage medium for establishing a fault probability prediction model. This model can calculate the decibel difference between the transmit power and reflective power of a high-power amplifier unit at the same time, then substitute the decibel difference into the fault probability solution model to obtain the fault probability of the high-power amplifier unit, and finally obtain the fault probability of a specified power amplifier unit at the predicted time through the fault probability prediction model. Based on the fault probability value, severely damaged units can be replaced in a timely manner, thereby improving the overall performance of the high-power amplifier and optimizing the operating efficiency of measurement and control equipment.

[0005] The objective of this invention is achieved through the following technical solution:

[0006] A method for establishing a failure probability prediction model, the method being used to establish a failure probability prediction model for high power amplifier units in aerospace telemetry and control equipment, the method comprising:

[0007] Obtain the transmit power and reflect power of the high power amplifier unit at the same moment;

[0008] Calculate the difference in decibels between the transmitted power and the reflected power;

[0009] Establish a fault probability solution model, which includes:

[0010]

[0011] Where 'a' is the preset threshold for health status, that is, the equipment is in a healthy state when VSWR>adB;

[0012] The failure probability of a unit module within a preset time range is calculated based on the failure probability solution model. The fitting function is obtained by using the least squares method to obtain the failure probability prediction model.

[0013] Furthermore, the calculation of the decibel difference between the transmitted power and the reflected power specifically includes:

[0014] The ratio of the transmitted power to the reflected power is calculated by substituting the result into a base-10 logarithm, and then multiplied by the amplification factor of 10 to obtain the decibel difference between the transmitted power and the reflected power, VSWR.

[0015] VSWR=10×lg(P OUT / P REF )

[0016] Among them, P OUT P represents the transmit power of the high-power amplifier unit at the same moment. REF This indicates the reflected power of the high-power amplifier unit at the same moment.

[0017] Furthermore, the step of obtaining the fitting function using the least squares method specifically includes:

[0018] Set the expression for the fitting function;

[0019] Construct the loss function expression;

[0020] Calculate the parameters of the fitted function.

[0021] Furthermore, the expression for setting the fitting function specifically includes:

[0022]

[0023] Where, x i Let θ be the i-th independent variable. i Let i be the i-th parameter.

[0024] Furthermore, the construction of the loss function expression specifically includes:

[0025]

[0026] Among them, y (j) This represents the actual value of the j-th group.

[0027] Furthermore, the parameters for calculating the fitting function specifically include:

[0028] For each of the loss function expressions, θ i Find the partial derivatives of (i = 0, 1, ..., n) and obtain θ by setting the derivatives to 0. i (i = 0, 1, ..., n);

[0029]

[0030] Where, x i Let θ be the i-th independent variable. i For the i-th parameter, y (j) This represents the actual value of the j-th group.

[0031] On the other hand, the present invention also provides a fault probability prediction model establishment device, the device comprising:

[0032] A power acquisition module acquires the transmit power and reflect power of the high power amplifier unit at the same time.

[0033] A difference calculation module calculates the difference in decibels between the transmitted power and the reflected power;

[0034] A fault probability solution model establishment module, wherein the fault probability solution model establishment module establishes a fault probability solution model, the fault probability solution model comprising:

[0035]

[0036] Where 'a' is the preset threshold for health status, that is, the equipment is in a healthy state when VSWR>adB;

[0037] The fault probability prediction model establishment module calculates the fault probability of the unit module within a preset time range based on the fault probability solution model, and obtains the fault probability prediction model by obtaining the fitting function using the least squares method.

[0038] On the other hand, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory stores a computer program, which is loaded and executed by the processor to implement any of the above-described methods for establishing a fault probability prediction model.

[0039] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program, which is loaded and executed by a processor to implement any of the above-described methods for establishing a fault probability prediction model.

[0040] The beneficial effects of this invention are as follows:

[0041] This invention first calculates the decibel difference between the transmitted power and the reflected power. Then, it inputs this decibel difference into a fault probability solution model to calculate the fault probability of the unit module. Subsequently, it inputs the calculation result into a fault probability prediction model and uses curve fitting to obtain a fault probability prediction curve. Finally, by viewing the fault probability prediction curve, the equipment administrator can obtain the fault probability of the unit module at a specified time and determine its health status. Based on the predicted fault probability value of the unit module, severely damaged unit modules can be replaced in a timely manner, thereby optimizing the overall performance of the high-power amplifier and improving the reliability of the measurement, operation, and control equipment. Attached Figure Description

[0042] Figure 1 This is a flowchart of the fault probability prediction model establishment method provided in the embodiments of the present invention;

[0043] Figure 2 This is a flowchart of the fault probability prediction process according to an embodiment of the present invention;

[0044] Figure 3 This is a structural block diagram of the fault probability prediction model establishment device provided in the embodiments of the present invention. Detailed Implementation

[0045] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0046] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0047] The high-power amplifier (HPA) consists of a pre-stage monitoring unit and a final-stage power amplifier unit. The health status of these unit modules determines the overall performance of the HPA. Typically, as the equipment ages, these unit modules will exhibit various forms of damage. Currently, the determination of whether to replace damaged unit modules relies mainly on manual experience, lacking definitive assessment criteria. Failure to predict the health status of unit modules and replace damaged ones in a timely manner during equipment operation will reduce the equipment's launch performance and affect the effectiveness of aerospace telemetry and control equipment.

[0048] To address the aforementioned technical problems, the following embodiments of the fault probability prediction model establishment method, apparatus, device, and storage medium of the present invention are proposed.

[0049] Example 1

[0050] This embodiment provides a method for establishing a failure probability prediction model for a high power amplifier unit in aerospace measurement, operation and control equipment.

[0051] Refer to Figure 1 , as Figure 1 is a flow block diagram of the method for establishing a failure probability prediction model provided by this embodiment. The method specifically includes the following steps:

[0052] Step 1: Obtain the transmit power and reflected power of the high power amplifier unit at the same time.

[0053] Step 2: Calculate the decibel difference between the transmit power and the reflected power.

[0054] Specifically, the ratio of transmit power to reflected power is substituted into the base-10 logarithm, and then multiplied by an amplification factor of 10 to obtain the decibel difference VSWR between transmit power and reflected power.

[0055] VSWR=10×log(P OUT / P REF )

[0056] In the above formula, P OUT is the transmit power of the high power amplifier unit at the same time, P REF is the reflected power of the high power amplifier unit at the same time.

[0057] Step 3: Establish a failure probability solving model, where the failure probability solving model includes:

[0058]

[0059] where a is the preset threshold for the healthy state, that is, when VSWR > a dB, the equipment is in a healthy state. By comparing and analyzing the relationship between the health status of aerospace measurement, operation and control equipment and the decibel difference, it can be known that

[0060] when VSWR < 6 dB, the equipment is in an abnormal state; when 6 dB < VSWR < 8 dB, the equipment is in a sub-healthy state; when VSWR > 8 dB, the equipment is in a healthy state. It can be deduced from the above health status judgment conditions that the preset threshold for the equipment to be in a healthy state is 8 dB; substituting the decibel difference of the ratio of transmit power to reflected power into the failure probability solving model to obtain the failure probability of the unit module. The expression of the failure probability solving model is as follows:

[0061]

[0062] Step 4: Calculate the failure probability of the unit module within a preset time range in the past based on the failure probability solution model, and obtain the fitting function by using the least squares method to obtain the failure probability prediction model.

[0063] The fitting function expression is a fault probability prediction model, and its derivation steps are shown below:

[0064] Set the fitting function expression:

[0065]

[0066] Where, x i Let θ be the i-th independent variable. i Let i be the i-th parameter.

[0067] Constructing the loss function expression

[0068]

[0069]

[0070] Among them, y (j) This represents the actual value of the j-th group.

[0071] Calculate the fitting function parameters θ i (i = 0, 1, ..., n)

[0072] For each of the loss function expressions, θ i Find the partial derivatives of (i = 0, 1, ..., n) and obtain θ by setting the derivatives to 0. i (i = 0, 1, ..., n).

[0073]

[0074] Where, x i Let θ be the i-th independent variable. i For the i-th parameter, y (j) This represents the actual value of the j-th group.

[0075] Based on the aforementioned method for establishing a fault probability prediction model, this embodiment also provides a complete process for performing fault probability prediction. (Refer to...) Figure 2 ,like Figure 2 The diagram shown is a flowchart of the fault probability prediction process in this embodiment. The fault probability prediction process specifically includes the following steps:

[0076] Step S01: Input the transmit power and reflect power of the high power amplifier unit at the same time.

[0077] In this embodiment, the high power amplifier unit in the equipment has a transmission power of 48W and a reflection power of 18W at a certain moment within the data acquisition start and end time range (2022-10-01 00:00:00~2022-11-20 23:59:59).

[0078] Step S02: Calculate the difference in decibels between the transmit power and the reflected power of the high power amplifier unit.

[0079] Substituting the transmit power and reflect power values ​​at that moment into the decibel difference formula, the VSWR is:

[0080] VSWR = 10 × log(P) OUT / P REF = 10 × log(48 / 18) = 4.26

[0081] Step S03: Calculate the failure probability using the failure probability solution model.

[0082] From step S02, we know that VSWR = 4.26, and VSWR < 6dB, therefore this unit module is in an abnormal state; substituting the decibel difference of this unit module into the fault probability solution model, we obtain the fault probability, then P 故障 for:

[0083]

[0084] Step S04: Obtain the fitting function for the fault probability prediction model.

[0085] Based on the failure probability solution model of the unit module, the failure probability of the unit module within the time range of 2022-11-21 00:00:00 to 2022-11-30 23:59:59 is obtained. The fitting function is assumed to be h. θ Given (x0, x1) = θ0x0 + θ1x1, the expression for the fitting function can be derived using the least squares method. Therefore, the expression for the fault probability prediction model is:

[0086] h θ (x0,x1)=(9.5491E-6)*x1+32.7382*1.0000

[0087] Step S05: Calculate the failure probability of the high power amplifier unit at a specified time.

[0088] According to the failure probability prediction model, the failure probability of 2022-11-30 12:00:00 is 81.82%.

[0089] Example 2

[0090] Reference Figure 3 ,like Figure 3The diagram shown is a structural block diagram of the fault probability prediction model establishment device provided in this embodiment. The device specifically includes the following structures:

[0091] A power acquisition module acquires the transmit power and reflect power of the high power amplifier unit at the same time.

[0092] A difference calculation module calculates the difference in decibels between the transmitted power and the reflected power;

[0093] A fault probability solution model establishment module, wherein the fault probability solution model establishment module establishes a fault probability solution model, the fault probability solution model comprising:

[0094]

[0095] Where 'a' is the preset threshold for health status, that is, the equipment is in a healthy state when VSWR>adB;

[0096] The fault probability prediction model establishment module calculates the fault probability of the unit module within a preset time range based on the fault probability solution model, and obtains the fault probability prediction model by obtaining the fitting function using the least squares method.

[0097] Example 3

[0098] This preferred embodiment provides a computer device that can implement the steps in any embodiment of the fault probability prediction model establishment method provided in this application. Therefore, it can achieve the beneficial effects of the fault probability prediction model establishment method provided in this application. For details, please refer to the previous embodiments, which will not be repeated here.

[0099] Example 4

[0100] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. Therefore, embodiments of the present invention provide a storage medium storing multiple instructions that can be loaded by a processor to execute the steps of any embodiment of the fault probability prediction model establishment method provided by the present invention.

[0101] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0102] Since the instructions stored in the storage medium can execute the steps in any of the fault probability prediction model establishment method embodiments provided by the present invention, the beneficial effects that any of the fault probability prediction model establishment methods provided by the present invention can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for establishing a fault probability prediction model, characterized in that, The method is used to establish a fault probability prediction model for high-power amplifier units in aerospace telemetry and control equipment. The method includes: Obtain the transmit power and reflect power of the high power amplifier unit at the same moment; Calculate the difference in decibels between the transmitted power and the reflected power; Establish a fault probability solution model, which includes: Where 'a' is a preset threshold for health status, i.e., when... The equipment is in a healthy state at this time; The failure probability of a unit module within a preset time range in the past is calculated based on the failure probability solution model. The fitting function is obtained by using the least squares method to obtain the failure probability prediction model. The calculation of the difference in decibels between the transmitted power and the reflected power specifically includes: The difference in decibels between the transmitted power and the reflected power is obtained by comparing the transmitted power and the reflected power, substituting the ratio into a base-10 logarithm, and then multiplying by the amplification factor of 10. : in, This indicates the transmit power of the high-power amplifier unit at the same moment. This indicates the reflected power of the high-power amplifier unit at the same moment; The specific steps of obtaining the fitting function using the least squares method include: Set the expression for the fitting function; Construct the loss function expression; Calculate the parameters of the fitted function; The expression for setting the fitting function specifically includes: in, For the first One independent variable, For the first One parameter; The specific expressions for constructing the loss function include: in, For the first Group actual value; The parameters for calculating the fitting function specifically include: For the loss function expression respectively Find the partial derivatives, and then obtain them by setting the derivatives to zero. ; ， in, For the first One independent variable, For the first One parameter, For the first Group actual value.

2. A fault probability prediction model establishment device, applied to the fault probability prediction model establishment method as described in claim 1, characterized in that, The device includes: A power acquisition module acquires the transmit power and reflect power of the high power amplifier unit at the same time. A difference calculation module calculates the difference in decibels between the transmitted power and the reflected power; A fault probability solution model establishment module, wherein the fault probability solution model establishment module establishes a fault probability solution model, the fault probability solution model comprising: Where 'a' is a preset threshold for health status, i.e., when... The equipment is in a healthy state at this time; The fault probability prediction model establishment module calculates the fault probability of the unit module within a preset time range based on the fault probability solution model, and obtains the fault probability prediction model by obtaining the fitting function using the least squares method.

3. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, which is loaded and executed by the processor to implement the fault probability prediction model establishment method as described in claim 1.

4. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which is loaded and executed by a processor to implement the fault probability prediction model establishment method as described in claim 1.

Images