CN114239373A - Particle swarm algorithm-based aerospace BDR module residual life prediction method - Google Patents

Particle swarm algorithm-based aerospace BDR module residual life prediction method Download PDF

Info

Publication number
CN114239373A
CN114239373A CN202111551123.0A CN202111551123A CN114239373A CN 114239373 A CN114239373 A CN 114239373A CN 202111551123 A CN202111551123 A CN 202111551123A CN 114239373 A CN114239373 A CN 114239373A
Authority
CN
China
Prior art keywords
aerospace
particle
particle swarm
module
bdr
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.)
Pending
Application number
CN202111551123.0A
Other languages
Chinese (zh)
Inventor
田前程
陈海涛
朱兼
丁帅
金超
黄洪钟
黄军
刘勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Institute of Space Power Sources
Original Assignee
Shanghai Institute of Space Power Sources
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Institute of Space Power Sources filed Critical Shanghai Institute of Space Power Sources
Priority to CN202111551123.0A priority Critical patent/CN114239373A/en
Publication of CN114239373A publication Critical patent/CN114239373A/en
Pending legal-status Critical Current

Links

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
    • G06F30/25—Design optimisation, verification or simulation using particle-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Testing Of Individual Semiconductor Devices (AREA)

Abstract

The invention discloses a particle swarm algorithm-based method for predicting the residual life of an aerospace BDR module, which comprises the following steps: s1, determining key components; s2, aiming at the key components, carrying out degradation mechanism analysis; s3, constructing a space BDR module degradation mechanism model; s4, calculating a residual life prediction root mean square error of the module, and taking the residual life prediction root mean square error as a fitness function of the particle swarm algorithm; s5, calculating a particle fitness value according to the fitness function of the particle swarm; s6, recording the optimal positions of the individuals and the population, updating the particle speed and the particle position, and determining the global optimal positions of the individuals and the population; and S7, judging whether the root mean square error reaches the minimum, if not, returning to the step S5, continuing iteration, and if the root mean square error reaches the minimum or the iteration number is equal to the maximum iteration number, ending the iteration. The method can predict the residual life of the aerospace BDR module, and the obtained residual life prediction method also provides method support for guiding the prediction of the residual life of other aerospace electronic products.

Description

Particle swarm algorithm-based aerospace BDR module residual life prediction method
Technical Field
The invention relates to the field of prediction of the residual life of aerospace electronic products, in particular to a method for predicting the residual life of an aerospace BDR module based on a particle swarm algorithm.
Background
The space BDR module is a key module in a power supply controller, belongs to one of space electronic products, and the residual service life of the space BDR module also determines the residual service life of a spacecraft. At present, the research on the aspect of predicting the residual life of the aerospace BDR module in China is less, the traditional statistical method cannot carry out accurate residual life prediction on the aerospace BDR module, a plurality of spacecrafts or a method for backing up the aerospace BDR module are used for improving the stability of the system, and the method relying on over-design of products not only increases the volume, the weight and the production cost, but also increases the complexity of system control.
Disclosure of Invention
In order to improve the research level of the prediction aspect of the residual life of aerospace electronic products in China, the invention provides a prediction method of the residual life of an aerospace BDR module based on a particle swarm algorithm.
The invention provides a particle swarm algorithm-based method for predicting the residual life of an aerospace BDR module, which is characterized by comprising the following steps of:
s1, analyzing historical data of the aerospace BDR module, and determining key components influencing the service life of the module;
s2, aiming at the key components, carrying out degradation mechanism analysis;
s3, constructing a degradation mechanism model of the aerospace BDR module based on degradation mechanism analysis;
s4, calculating the Root Mean Square Error (RMSE) of the residual life prediction of the aerospace BDR module, taking the RMSE as a fitness function of the particle swarm algorithm,
s5, calculating a particle fitness value according to the particle swarm fitness function;
s6, recording the optimal positions of the individuals and the population, updating the particle speed and the particle position, and determining the global optimal positions of the individuals and the population;
and S7, judging whether the root mean square error RMSE reaches the minimum, if not, returning to the step S5, continuing iteration, and if the root mean square error RMSE reaches the minimum or the iteration number is equal to the maximum iteration number, ending the iteration and finishing the residual life modeling of the aerospace BDR module.
Optionally, the step S1 specifically includes:
s11, collecting historical data of the aerospace BDR module, and analyzing the data of the aerospace BDR module;
and S12, comparing possible failure mechanisms, neglecting failure factors with smaller influence, and determining key components influencing the service life of the module.
Optionally, the step S2 specifically includes:
s21, taking the working time and the working temperature into consideration, and carrying out degradation mechanism analysis on the resistance by using an Arrhenius model, wherein the expression is as follows:
Figure BDA0003417619430000021
wherein Δ R, R is the resistance difference and resistance at time T, T is the temperature, B, C, D and F are constants;
s22, considering the working temperature, and carrying out degradation mechanism analysis on the capacitance by using an Arrhenius model, wherein the expression is as follows:
c＝A·exp(-E/kT)
wherein c is a capacitor, T is temperature, E is voltage at two ends of the capacitor, and A and k are constants;
s23, taking the inductance value as the fault characteristic parameter of the inductor, and carrying out degradation mechanism analysis on the inductor, wherein the expression is as follows:
L(t)＝L0-λt
wherein L (t) is the inductance value at time t, L0The nominal value of the inductance at the initial moment, and lambda is a degradation model parameter;
s24, indirectly using the conduction resistance as a fault characteristic parameter for reflecting the degradation degree of the power diode, and carrying out degradation mechanism analysis on the power diode, wherein the expression is as follows:
ΔRD＝a·[eb·t-1]
wherein, Δ RDthe on-resistance at time t, a and b are constants;
s25, not considering the failure of the packaging structure, only considering the failure of the chip structure, carrying out degradation mechanism analysis on the MOSFET, wherein the expression is as follows:
Figure BDA0003417619430000031
wherein, is Δ VthIs the gate-source voltage, C, at the very beginning of the device conductionoxIs an oxide layer capacitance, Δ QotAnd Δ QitRespectively representing the variation of the numbers of the oxide layer trapped charges and the interface state trapped charges.
Optionally, the step S3 specifically includes:
s31, establishing a damp and hot based degradation model, wherein the expression is as follows:
Figure BDA0003417619430000032
wherein L (H, T) represents the damp-heat aging life, b and c are undetermined model parameters, A is a constant, H is relative humidity, and T is absolute temperature;
s32, based on the degradation model, using a least square method to realize parameter identification and determine the parameters of the degradation model;
s33, considering that the data have errors, and removing abnormal values by using a RANSAC algorithm;
and S34, fitting the data with the abnormal values removed again, and extrapolating the degradation model of the fitting result to the failure threshold value to obtain the failure time of the key component, thereby obtaining the predicted value of the residual service life of the key component.
Optionally, the step S4 specifically includes:
s41, calculating the Root Mean Square Error (RMSE) of the prediction of the residual service life of the aerospace BDR module according to the predicted value of the residual service life obtained in the step S3;
the root mean square error RMSE formula is as follows:
Figure BDA0003417619430000033
where n represents the number of predictions, x (i) represents the actual lifetime of the aerospace BDR module,
Figure BDA0003417619430000034
represents the predicted lifetime of an aerospace BDR module;
and S42, taking the root mean square error as a fitness function of the particle swarm algorithm.
Optionally, the step S5 specifically includes:
s51, determining the speed and the position of the current particle;
and S52, determining the particle fitness value according to the speed and the position of the particles.
Optionally, the step S6 specifically includes:
s61, recording the optimal position of each particle in each searching process:
Figure BDA0003417619430000041
wherein p isiAnd pgLocal and global optimal positions, respectively;
s62, velocity v of particleiAnd position xiThe updating mode is as follows:
Figure BDA0003417619430000042
Figure BDA0003417619430000043
n, w is an inertia factor, c1And c2For the acceleration constant, α is a constraint factor;
s63, the optimal solution of the optimal positions of all the particles can be used as the optimal position of the whole particle swarm:
Figure BDA0003417619430000044
wherein, giAnd GiThe optimal positions of individuals and populations respectively.
Optionally, the step S7 specifically includes:
s71, recording the Root Mean Square Error (RMSE) value in each iteration process;
s72, if the RMSE does not reach the minimum value, returning to the step S5, continuing iteration, updating the particle speed and the position, and continuing to find the global optimal position of the particle swarm;
and S73, if the RMSE reaches the minimum value or the maximum iteration number, finishing the particle swarm optimization and finishing the residual life modeling of the aerospace BDR module.
The technical scheme provided by the invention can have the following beneficial effects:
the invention provides a particle swarm algorithm-based method for predicting the residual life of an aerospace BDR module, which has obvious advantages, integrates a degradation mechanism model and a particle swarm algorithm, realizes the self-optimization of key parameters of the degradation model, and can accurately predict the residual life of the aerospace BDR module. In addition, the method of fusing the degradation mechanism model and the particle swarm optimization further solves the problems of difficult modeling and difficult parameter determination based on the traditional mechanism degradation method, improves the accuracy of the prediction of the residual life of the aerospace BDR module, and provides method support for guiding the prediction of the residual life of other aerospace electronic products by the obtained residual life prediction method.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention patent, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for predicting the remaining life of an aerospace BDR module based on a particle swarm algorithm in the embodiment of the invention.
Detailed Description
Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that, although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The embodiment of the invention provides a method for predicting the residual life of an aerospace BDR module based on a particle swarm algorithm, which integrates a degradation mechanism model and the particle swarm algorithm, realizes the self-optimization of key parameters of the degradation model, and can accurately predict the residual life of the aerospace BDR module.
The following describes the technical solutions of the embodiments of the present invention in detail with reference to the accompanying drawings.
Referring to fig. 1, the present embodiment provides a method for predicting remaining life of an aerospace BDR module by using a particle swarm algorithm, as shown in fig. 1, which includes:
s1, analyzing historical data of the aerospace BDR module, and determining key components influencing the service life of the module;
s11, collecting historical data of the aerospace BDR module, namely voltage, current, humidity and temperature data of components such as a resistor, a capacitor, an inductor, a power diode, an MOSFET and the like, and performing data analysis on the historical data;
s12, through analysis of historical data, sorting the influence of the fault mechanism, comparing the possible fault mechanisms, and neglecting the fault factors with smaller influence, thereby determining the key components influencing the service life of the module: resistors, capacitors, inductors, power diodes and MOSFETs;
s2, aiming at the key components, carrying out degradation mechanism analysis;
s21, considering the working time and the working temperature, and carrying out degradation mechanism analysis on the resistance by using an Arrhenius model, wherein the common expression is as follows:
Figure BDA0003417619430000061
wherein Δ R, R is the resistance difference and resistance at time T, T is the temperature, B, C, D and F are constants;
s22, considering the working temperature, and carrying out degradation mechanism analysis on the capacitance by using an Arrhenius model, wherein the common expression is as follows:
c＝A·exp(-E/kT)
wherein c is a capacitor, T is temperature, E is voltage at two ends of the capacitor, and A and k are constants;
s23, taking the inductance value as the fault characteristic parameter of the inductor, and carrying out degradation mechanism analysis on the inductor, wherein the common expression is as follows:
L(t)＝L0-λt
wherein L (t) is the inductance value at time t, L0The nominal value of the inductance at the initial moment, and lambda is a degradation model parameter;
s24, indirectly using the on-resistance as a fault characteristic parameter for reflecting the degradation degree of the power diode, and carrying out degradation mechanism analysis on the power diode, wherein the common expression is as follows:
ΔRD＝a·[eb·t-1]
wherein, Δ RDthe on-resistance at time t, a and b are constants;
s25, carrying out degradation mechanism analysis on the MOSFET without considering the failure of the packaging structure and only considering the failure of the chip structure, wherein the common expression is as follows:
Figure BDA0003417619430000071
wherein, is Δ VthWhen the device is initially conductingGate-source voltage (threshold voltage), CoxIs an oxide layer capacitance, Δ QotAnd Δ QitRespectively representing the variation of the numbers of the oxide layer trap charges and the interface state trap charges;
s3, constructing a degradation mechanism model of the aerospace BDR module based on degradation mechanism analysis;
s31, establishing a damp and hot based degradation model:
Figure BDA0003417619430000072
wherein L (H, T) represents the damp-heat aging life, b and c are undetermined model parameters, A is a constant, H is relative humidity, and T is absolute temperature;
s32, based on the degradation model, using a least square method to realize parameter identification and determine the parameters of the degradation model;
s33, considering that the data have errors, and removing abnormal values by using a RANSAC algorithm;
the RANSAC algorithm, Random Sample Consensus (Random Sample Consensus), is a fast algorithm for eliminating outliers that estimate camera pose, which estimates model parameters using the smallest subsample of observed data, and is particularly efficient when the data contains a large number of outliers, while normal values should account for at least 50% of the data set for good performance;
s34, fitting the data with the abnormal values removed again, and extrapolating the degradation model of the fitting result to a failure threshold value to obtain the failure time of the key component, so as to obtain the predicted value of the residual service life of the key component;
s4, calculating the Root Mean Square Error (RMSE) of the residual life prediction of the aerospace BDR module, taking the RMSE as a fitness function of the particle swarm algorithm,
s41, calculating the Root Mean Square Error (RMSE) of the prediction of the residual service life of the aerospace BDR module according to the predicted value of the residual service life obtained in the step S3;
the root mean square error RMSE formula is as follows:
Figure BDA0003417619430000073
where n represents the number of predictions, x (i) represents the actual lifetime of the aerospace BDR module,
Figure BDA0003417619430000074
represents the predicted lifetime of an aerospace BDR module;
s42, taking the root mean square error as a fitness function of the particle swarm algorithm;
s5, calculating a particle fitness value according to the particle swarm fitness function;
s51, determining the speed and the position of the current particle;
s52, determining a particle fitness value according to the speed and the position of the particle;
s6, recording the optimal positions of the individuals and the population, updating the particle speed and the particle position, and determining the global optimal positions of the individuals and the population;
s61, recording the optimal position of each particle in each searching process:
Figure BDA0003417619430000081
wherein p isiAnd pgLocal and global optimal positions, respectively.
S62, velocity v of particleiAnd position xiThe updating mode is as follows:
Figure BDA0003417619430000082
Figure BDA0003417619430000083
n, w is an inertia factor, c1And c2For the acceleration constant, α is a constraint factor.
S63, the optimal solution of the optimal positions of all the particles can be used as the optimal position of the whole particle swarm:
Figure BDA0003417619430000084
wherein, giAnd GiRespectively the optimal positions of individuals and populations;
and S7, judging whether the root mean square error RMSE reaches the minimum, if not, returning to the step S5, continuing iteration, and if the root mean square error RMSE reaches the minimum or the iteration number is equal to the maximum iteration number, ending the iteration and finishing the residual life modeling of the aerospace BDR module.
S71, recording the Root Mean Square Error (RMSE) value in each iteration process;
s72, if the root mean square error RMSE does not reach the minimum value, returning to the step S5, continuing iteration, updating the particle speed and the position, and continuing to search the global optimal position of the particle swarm;
and S73, if the root mean square error RMSE reaches the minimum value or the maximum iteration number, finishing particle swarm optimization and finishing the residual life modeling of the aerospace BDR module.
The above description is only an example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present invention are included in the protection scope of the present invention.

Claims (8)

1. A particle swarm algorithm-based method for predicting the residual life of an aerospace BDR module is characterized by comprising the following steps:
s1, analyzing historical data of the aerospace BDR module, and determining key components influencing the service life of the module;
s2, aiming at the key components, carrying out degradation mechanism analysis;
s3, constructing a degradation mechanism model of the aerospace BDR module based on degradation mechanism analysis;
s4, calculating the Root Mean Square Error (RMSE) of the residual life prediction of the aerospace BDR module, taking the RMSE as a fitness function of the particle swarm algorithm,
s5, calculating a particle fitness value according to the particle swarm fitness function;
s6, recording the optimal positions of the individuals and the population, updating the particle speed and the particle position, and determining the global optimal positions of the individuals and the population;
and S7, judging whether the root mean square error RMSE reaches the minimum, if not, returning to the step S5, continuing iteration, and if the root mean square error RMSE reaches the minimum or the iteration number is equal to the maximum iteration number, ending the iteration and finishing the residual life modeling of the aerospace BDR module.
2. The particle swarm optimization-based method for predicting the remaining life of the aerospace BDR module as claimed in claim 1, wherein the step S1 specifically comprises:
s11, collecting historical data of the aerospace BDR module, and analyzing the data of the aerospace BDR module;
and S12, comparing possible failure mechanisms, neglecting failure factors with smaller influence, and determining key components influencing the service life of the module.
3. The particle swarm optimization-based method for predicting the remaining life of the aerospace BDR module as claimed in claim 1, wherein the step S2 specifically comprises:
s21, taking the working time and the working temperature into consideration, and carrying out degradation mechanism analysis on the resistance by using an Arrhenius model, wherein the expression is as follows:
Figure FDA0003417619420000011
wherein Δ R, R is the resistance difference and resistance at time T, T is the temperature, B, C, D and F are constants;
s22, considering the working temperature, and carrying out degradation mechanism analysis on the capacitance by using an Arrhenius model, wherein the expression is as follows:
c＝A·exp(-E/kT)
wherein c is a capacitor, T is temperature, E is voltage at two ends of the capacitor, and A and k are constants;
s23, taking the inductance value as the fault characteristic parameter of the inductor, and carrying out degradation mechanism analysis on the inductor, wherein the expression is as follows:
L(t)＝L0-λt
wherein L (t) is the inductance value at time t, L0The nominal value of the inductance at the initial moment, and lambda is a degradation model parameter;
s24, indirectly using the conduction resistance as a fault characteristic parameter for reflecting the degradation degree of the power diode, and carrying out degradation mechanism analysis on the power diode, wherein the expression is as follows:
ΔRD＝a·[eb·t-1]
wherein, Δ RDthe on-resistance at time t, a and b are constants;
s25, not considering the failure of the packaging structure, only considering the failure of the chip structure, carrying out degradation mechanism analysis on the MOSFET, wherein the expression is as follows:
Figure FDA0003417619420000021
wherein, is Δ VthIs the gate-source voltage, C, at the very beginning of the device conductionoxIs an oxide layer capacitance, Δ QotAnd Δ QitRespectively representing the variation of the numbers of the oxide layer trapped charges and the interface state trapped charges.
4. The particle swarm optimization-based method for predicting the remaining life of the aerospace BDR module as claimed in claim 1, wherein the step S3 specifically comprises:
s31, establishing a damp and hot based degradation model, wherein the expression is as follows:
Figure FDA0003417619420000031
wherein L (H, T) represents the damp-heat aging life, b and c are undetermined model parameters, A is a constant, H is relative humidity, and T is absolute temperature;
s32, based on the degradation model, using a least square method to realize parameter identification and determine the parameters of the degradation model;
s33, considering that the data have errors, and removing abnormal values by using a RANSAC algorithm;
and S34, fitting the data with the abnormal values removed again, and extrapolating the degradation model of the fitting result to the failure threshold value to obtain the failure time of the key component, thereby obtaining the predicted value of the residual service life of the key component.
5. The particle swarm optimization-based method for predicting the remaining life of the aerospace BDR module as claimed in claim 1, wherein the step S4 specifically comprises:
s41, calculating the Root Mean Square Error (RMSE) of the prediction of the residual service life of the aerospace BDR module according to the predicted value of the residual service life obtained in the step S3;
the root mean square error RMSE formula is as follows:
Figure FDA0003417619420000032
where n represents the number of predictions, x (i) represents the actual lifetime of the aerospace BDR module,
Figure FDA0003417619420000033
represents the predicted lifetime of an aerospace BDR module;
and S42, taking the root mean square error as a fitness function of the particle swarm algorithm.
6. The particle swarm optimization-based method for predicting the remaining life of the aerospace BDR module as claimed in claim 1, wherein the step S5 specifically comprises:
s51, determining the speed and the position of the current particle;
and S52, determining the particle fitness value according to the speed and the position of the particles.
7. The particle swarm optimization-based method for predicting the remaining life of the aerospace BDR module as claimed in claim 1, wherein the step S6 specifically comprises:
s61, recording the optimal position of each particle in each searching process:
Figure FDA0003417619420000041
wherein p isiAnd pgLocal and global optimal positions, respectively;
s62, velocity v of particleiAnd position xiThe updating mode is as follows:
Figure FDA0003417619420000042
Figure FDA0003417619420000043
n, w is an inertia factor, c1And c2For the acceleration constant, α is a constraint factor;
s63, the optimal solution of the optimal positions of all the particles can be used as the optimal position of the whole particle swarm:
Figure FDA0003417619420000044
wherein, giAnd GiThe optimal positions of individuals and populations respectively.
8. The particle swarm optimization-based method for predicting the remaining life of the aerospace BDR module as claimed in claim 1, wherein the step S7 specifically comprises:
s71, recording the Root Mean Square Error (RMSE) value in each iteration process;
s72, if the RMSE does not reach the minimum value, returning to the step S5, continuing iteration, updating the particle speed and the position, and continuing to find the global optimal position of the particle swarm;
and S73, if the RMSE reaches the minimum value or the maximum iteration number, finishing the particle swarm optimization and finishing the residual life modeling of the aerospace BDR module.
CN202111551123.0A 2021-12-17 2021-12-17 Particle swarm algorithm-based aerospace BDR module residual life prediction method Pending CN114239373A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111551123.0A CN114239373A (en) 2021-12-17 2021-12-17 Particle swarm algorithm-based aerospace BDR module residual life prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111551123.0A CN114239373A (en) 2021-12-17 2021-12-17 Particle swarm algorithm-based aerospace BDR module residual life prediction method

Publications (1)

Publication Number Publication Date
CN114239373A true CN114239373A (en) 2022-03-25

Family

ID=80758278

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111551123.0A Pending CN114239373A (en) 2021-12-17 2021-12-17 Particle swarm algorithm-based aerospace BDR module residual life prediction method

Country Status (1)

Country Link
CN (1) CN114239373A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542155A (en) * 2011-12-05 2012-07-04 北京航空航天大学 Particle filter residual life forecasting method based on accelerated degradation data
CN107228926A (en) * 2017-06-09 2017-10-03 电子科技大学 The explosive logic network analysis method for reliability assessed based on accelerated aging
CN109446661A (en) * 2018-10-31 2019-03-08 河北工业大学 A kind of method for predicting residual useful life considering lithium battery degradation characteristics
CN109993270A (en) * 2019-03-27 2019-07-09 东北大学 Lithium ion battery residual life prediction technique based on grey wolf pack optimization LSTM network
CN110007240A (en) * 2019-04-26 2019-07-12 贵州大学 A kind of lithium ion battery residual life prediction technique
CN111985163A (en) * 2020-08-31 2020-11-24 北京航天测控技术有限公司 Rubidium clock life prediction method and device
CN113281671A (en) * 2021-06-28 2021-08-20 长安大学 Lithium ion battery remaining service life prediction method and system based on IGS-SVM
CN114297926A (en) * 2021-12-28 2022-04-08 上海空间电源研究所 Aerospace BDR module life quantification method based on heterogeneous information fusion

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542155A (en) * 2011-12-05 2012-07-04 北京航空航天大学 Particle filter residual life forecasting method based on accelerated degradation data
CN107228926A (en) * 2017-06-09 2017-10-03 电子科技大学 The explosive logic network analysis method for reliability assessed based on accelerated aging
CN109446661A (en) * 2018-10-31 2019-03-08 河北工业大学 A kind of method for predicting residual useful life considering lithium battery degradation characteristics
CN109993270A (en) * 2019-03-27 2019-07-09 东北大学 Lithium ion battery residual life prediction technique based on grey wolf pack optimization LSTM network
WO2020191801A1 (en) * 2019-03-27 2020-10-01 东北大学 Lithium ion battery remaining life prediction method based on wolf pack optimization lstm network
CN110007240A (en) * 2019-04-26 2019-07-12 贵州大学 A kind of lithium ion battery residual life prediction technique
CN111985163A (en) * 2020-08-31 2020-11-24 北京航天测控技术有限公司 Rubidium clock life prediction method and device
CN113281671A (en) * 2021-06-28 2021-08-20 长安大学 Lithium ion battery remaining service life prediction method and system based on IGS-SVM
CN114297926A (en) * 2021-12-28 2022-04-08 上海空间电源研究所 Aerospace BDR module life quantification method based on heterogeneous information fusion

Non-Patent Citations (8)

* Cited by examiner, † Cited by third party
Title
QIANCHENG TIAN 等: "Remaining Useful Life Prediction Method of Lithium-Ion Batteries Based on Relevance Vector Machine", FAFEE 2022: THE PROCEEDINGS OF THE 10TH FRONTIER ACADEMIC FORUM OF ELECTRICAL ENGINEERING (FAFEE2022), 24 August 2023 (2023-08-24), pages 1303 - 1313 *
QIANCHENG TIAN 等: "The particle swarm optimization multi-kernel relevance vector machine for remaining useful life prediction of lithium-ion batteries", 2022 IEEE 6TH ADVANCED INFORMATION TECHNOLOGY, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC ), 9 November 2022 (2022-11-09), pages 938 - 943 *
RAMI N. KHUSHABA 等: "Electromyogram (EMG) Based Fingers Movement Recognition Using Neighborhood Preserving Analysis with QR-Decomposition", 2011 SEVENTH INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS AND INFORMATION PROCESSING, 9 January 2012 (2012-01-09) *
于磊: "空间电源系统并网供电技术研究", 中国博士学位论文全文数据库 工程科技II辑, 15 June 2018 (2018-06-15), pages 031 - 33 *
何成;刘长春;武洋;: "基于改进粒子滤波算法的医疗锂电池PHM系统设计", 计算机测量与控制, no. 11, 25 November 2018 (2018-11-25), pages 69 - 73 *
刘子英;钱超;朱琛磊;: "基于IPSO-Elman的锂电池剩余寿命预测", 现代电子技术, no. 12, 15 June 2020 (2020-06-15), pages 108 - 113 *
张成龙;刘杰;李想;: "基于改进PSO-SVR的多轴承健康寿命协同预测", 机床与液压, no. 16, 28 August 2020 (2020-08-28), pages 212 - 216 *
秦琪;赵帅;陈绍炜;黄登山;: "基于粒子群优化粒子滤波的电容剩余寿命预测", 计算机工程与应用, no. 20, 8 February 2018 (2018-02-08), pages 242 - 246 *

Similar Documents

Publication Publication Date Title
EP3904894B1 (en) Training device, estimation device, training method, estimation method, training program, and estimation program
KR102634815B1 (en) Method and apparatus for estimating state of battery based on error correction
Krishnamoorthy et al. Machine learning based modeling of power electronic converters
CN107909179A (en) The prediction model construction method and vehicle energy management method of a kind of plug-in hybrid vehicle driving cycle
KR20170078387A (en) Method and apparatus for managing sensors
CN113687239B (en) TCPSO lithium ion battery parameter identification method for noise immunity
CN107392352B (en) Battery future temperature prediction method and system based on fusion extreme learning machine
Samie et al. Developing prognostic models using duality principles for DC-to-DC converters
CN113868953B (en) Multi-unit operation optimization method, device and system in industrial system and storage medium
CN113919545A (en) Photovoltaic power generation power prediction method and system with integration of multiple data models
CN113255584A (en) Fault diagnosis and monitoring system based on edge calculation
CN116205140A (en) IGBT residual service life prediction method based on LSTM-ARIMA
CN116467674A (en) Intelligent fault processing fusion updating system and method for power distribution network
Wang et al. A DRL-aided multi-layer stability model calibration platform considering multiple events
CN115146525A (en) System for estimating deterioration state of secondary battery, method for estimating deterioration state of secondary battery, and storage medium
CN114239373A (en) Particle swarm algorithm-based aerospace BDR module residual life prediction method
CN108512479B (en) Motor controller and method for calculating predicted value of motor torque
CN117744856A (en) Lithium battery remaining life prediction method, system, computer device and storage medium
CN115693916B (en) Intelligent online monitoring method and system for direct-current power supply of transformer substation
CN112465250A (en) Power load prediction method, power load prediction device, computer equipment and storage medium
CN112488295A (en) Method for optimizing storage life prediction of LSTM network relay by cross validation algorithm
Tameemi Fusion-based deterministic and stochastic parameters estimation for a lithium-polymer battery model
CN114896865B (en) Digital twinning-oriented self-adaptive evolutionary neural network health state online prediction method
CN115687950A (en) Power system load fluctuation analysis method and system
CN114116370B (en) Complex electronic system operation health state monitoring point optimization method

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