CN117349633B - Fault and life prediction method, device, equipment and medium of source-load integrated machine - Google Patents
Fault and life prediction method, device, equipment and medium of source-load integrated machine Download PDFInfo
- Publication number
- CN117349633B CN117349633B CN202311657449.0A CN202311657449A CN117349633B CN 117349633 B CN117349633 B CN 117349633B CN 202311657449 A CN202311657449 A CN 202311657449A CN 117349633 B CN117349633 B CN 117349633B
- Authority
- CN
- China
- Prior art keywords
- source
- integrated machine
- data set
- failure rate
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000003990 capacitor Substances 0.000 claims description 103
- 238000010606 normalization Methods 0.000 claims description 90
- 238000005070 sampling Methods 0.000 claims description 87
- 238000012545 processing Methods 0.000 claims description 44
- 239000011159 matrix material Substances 0.000 claims description 31
- 238000013461 design Methods 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 230000007704 transition Effects 0.000 claims description 16
- 230000001360 synchronised effect Effects 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 11
- 230000002457 bidirectional effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 230000007123 defense Effects 0.000 abstract description 9
- 239000004065 semiconductor Substances 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000002441 reversible effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000670 limiting effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention discloses a fault and life prediction method, device, equipment and medium of a source-carried integrated machine. The method and the device can predict the faults and the service life of the source-carrying all-in-one machine and meet the requirements of the national defense and military industry, aerospace, semiconductor and other fields with high reliability.
Description
Technical Field
The invention relates to the field of source-load integrated machines, in particular to a method, a device, equipment and a medium for predicting faults and service lives of source-load integrated machines.
Background
The source-carried integrated machine is widely applied to the testing of the fields of national defense and military industry, aerospace, semiconductors and the like, the existing source-carried integrated machine has the functions of simple fault monitoring and the like, when a certain component breaks down, the alarm can be given, but the impending fault and the residual life of a power supply cannot be predicted, the capability of autonomous guarantee and autonomous diagnosis is insufficient, and corresponding components can be replaced by maintenance staff after equipment breaks down, so that the existing source-carried integrated machine does not have the function of predicting the fault and the life, and cannot meet the requirements of the fields of national defense and military industry, aerospace, semiconductors and the like in high reliability.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a method, a device, equipment and a medium for predicting the faults and the service lives of source-carrying integrated machines, which can predict the faults and the service lives of the source-carrying integrated machines and meet the requirements of the high-reliability fields of national defense and military industry, aerospace, semiconductors and the like.
According to an embodiment of the first aspect of the invention, the method for predicting the failure and the service life of the source-load integrated machine comprises the following steps:
acquiring temperature sampling data of an electrolytic capacitor in the source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation, and calculating the service life of the electrolytic capacitor;
acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and then carrying out normalization processing to obtain a first normalization data set;
acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set;
Acquiring voltage and current sampling data of the source-load integrated machine, and then carrying out normalization processing to obtain a third normalization data set;
constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, and obtaining the probability of faults to occur to key components in the source-carrier all-in-one machine according to the optimal solution;
the expression of the hidden Markov model is as follows:
λ=(A,B,Π)，
λ is a hidden markov model, a is a state transition probability distribution matrix, B is an observation state probability matrix, and pi is an initial state distribution of failure rate of the component; the state transition probability distribution matrix is calculated by a first normalized data set, a second normalized data set and a third normalized data set, the observation state probability matrix is calculated by the first normalized data set, the second normalized data set and the third normalized data set, and the initial state distribution of the failure rate of the component is calculated by the second normalized data set;
and predicting the residual life of the source-load integrated machine according to the life of the electrolytic capacitor and the probability of faults to occur to key components in the source-load integrated machine.
The method for predicting the faults and the service lives of the source-loaded all-in-one machine has at least the following beneficial effects:
firstly, acquiring temperature sampling data of an electrolytic capacitor in a source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the service life of the electrolytic capacitor; then acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and performing normalization processing to obtain a first normalization data set; then, acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set; then acquiring voltage and current sampling data of the source-load integrated machine, and performing normalization processing to obtain a third normalization data set; and finally, constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, obtaining the probability of faults to occur to key components in the source-load all-in-one machine according to the optimal solution, and predicting the residual life of the source-load all-in-one machine according to the life of the electrolytic capacitor and the probability of faults to occur to the key components in the source-load all-in-one machine.
According to the method, firstly, the service life of an electrolytic capacitor and the work failure rate of key components are calculated, then, a hidden Markov model is built by combining temperature data, environment temperature data, voltage and current sampling data, historical data and power supply design parameters of all components in the source-carried integrated machine, and finally, the hidden Markov model is solved through a Viterbi algorithm, so that the fault probability and the residual service life of the key components in the source-carried integrated machine are obtained. The method can predict the faults and the service life of the source-carrying integrated machine and meet the requirements of the national defense and military industry, aerospace, semiconductors and other fields with high reliability.
According to some embodiments of the present invention, in the step of substituting the temperature sampling data of the electrolytic capacitor into the Arrhenius equation to calculate the lifetime of the electrolytic capacitor, the Arrhenius equation has the expression:
，
wherein L is the service life of the electrolytic capacitor when the ambient temperature is T, T 0 For rated highest use temperature of electrolytic capacitor, L 0 The rated life of the electrolytic capacitor at the rated highest service temperature is equal to the ambient temperature.
According to some embodiments of the invention, the temperature data of each component in the source-carrier integrated machine includes temperature sampling data, radiator temperature data and PCB board temperature data of each component in the source-carrier integrated machine.
According to some embodiments of the present invention, in the step of substituting the basic failure rate of the key component into the failure rate prediction model to calculate the operation failure rate of the key component, the failure rate prediction model has the expression:
=/>，
wherein λP is the failure rate of the operation of the component, λb is the basic failure rate of the component,for the correction coefficients, n is the number of correction coefficients for the component.
According to some embodiments of the invention, in the step of obtaining the voltage and current sampling data of the source-carried integrated machine, the voltage and current sampling data of the source-carried integrated machine includes power input voltage and current sampling data of the source-carried integrated machine and voltage and current sampling data of each stage of topology in the source-carried integrated machine.
According to some embodiments of the present invention, the input/output voltage and current sampling data of each stage of topology in the source-load integrated machine includes voltage and current sampling data of bridgeless PFC topology, voltage and current sampling data of bidirectional CLLC topology, and voltage and current sampling data of three-phase interleaved synchronous BUCK topology.
According to a second aspect of the present invention, a failure and life prediction apparatus for an on-board integrated machine includes:
the electrolytic capacitor life calculation unit is used for acquiring temperature sampling data of the electrolytic capacitor in the source-load all-in-one machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the life of the electrolytic capacitor;
The temperature data processing unit is used for acquiring temperature data and environmental temperature data of all components in the source-load all-in-one machine, and then carrying out normalization processing to obtain a first normalization data set;
the failure rate data processing unit is used for acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set;
the current-voltage data processing unit is used for acquiring voltage and current sampling data of the source-load all-in-one machine and then carrying out normalization processing to obtain a third normalization data set;
the fault probability calculation unit is used for constructing a hidden Markov model according to the first normalized data set, the second normalized data set and the third normalized data set, solving the constructed hidden Markov model through a Viterbi algorithm, and obtaining the fault probability of key components in the source-carrier all-in-one machine according to the optimal solution;
The expression of the hidden Markov model is as follows:
λ=(A,B,Π)，
λ is a hidden markov model, a is a state transition probability distribution matrix, B is an observation state probability matrix, and pi is an initial state distribution of failure rate of the component; the state transition probability distribution matrix is calculated by a first normalized data set, a second normalized data set and a third normalized data set, the observation state probability matrix is calculated by the first normalized data set, the second normalized data set and the third normalized data set, and the initial state distribution of the failure rate of the component is calculated by the second normalized data set;
and the residual life prediction unit is used for predicting the residual life of the source-load integrated machine according to the life of the electrolytic capacitor and the probability of faults to occur in key components in the source-load integrated machine.
The failure and service life prediction device of the source-loaded all-in-one machine according to the embodiment of the second aspect of the invention has at least the following beneficial effects:
firstly, acquiring temperature sampling data of an electrolytic capacitor in a source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the service life of the electrolytic capacitor; then acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and performing normalization processing to obtain a first normalization data set; then, acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set; then acquiring voltage and current sampling data of the source-load integrated machine, and performing normalization processing to obtain a third normalization data set; and finally, constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, obtaining the probability of faults to occur to key components in the source-load all-in-one machine according to the optimal solution, and predicting the residual life of the source-load all-in-one machine according to the life of the electrolytic capacitor and the probability of faults to occur to the key components in the source-load all-in-one machine.
According to the method, firstly, the service life of an electrolytic capacitor and the work failure rate of key components are calculated, then, a hidden Markov model is built by combining temperature data, environment temperature data, voltage and current sampling data, historical data and power supply design parameters of all components in the source-carried integrated machine, and finally, the hidden Markov model is solved through a Viterbi algorithm, so that the fault probability and the residual service life of the key components in the source-carried integrated machine are obtained. The method can predict the faults and the service life of the source-carrying integrated machine and meet the requirements of the national defense and military industry, aerospace, semiconductors and other fields with high reliability.
An electronic device according to an embodiment of the third aspect of the present invention includes a memory and a processor, where the memory stores a computer program or instructions, and the processor implements the method for predicting failure and lifetime of an on-source integrated machine described above when executing the computer program or instructions.
The electronic equipment according to the embodiment of the third aspect of the invention has at least the following beneficial effects:
firstly, acquiring temperature sampling data of an electrolytic capacitor in a source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the service life of the electrolytic capacitor; then acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and performing normalization processing to obtain a first normalization data set; then, acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set; then acquiring voltage and current sampling data of the source-load integrated machine, and performing normalization processing to obtain a third normalization data set; and finally, constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, obtaining the probability of faults to occur to key components in the source-load all-in-one machine according to the optimal solution, and predicting the residual life of the source-load all-in-one machine according to the life of the electrolytic capacitor and the probability of faults to occur to the key components in the source-load all-in-one machine.
According to the method, firstly, the service life of an electrolytic capacitor and the work failure rate of key components are calculated, then, a hidden Markov model is built by combining temperature data, environment temperature data, voltage and current sampling data, historical data and power supply design parameters of all components in the source-carried integrated machine, and finally, the hidden Markov model is solved through a Viterbi algorithm, so that the fault probability and the residual service life of the key components in the source-carried integrated machine are obtained. The method can predict the faults and the service life of the source-carrying integrated machine and meet the requirements of the national defense and military industry, aerospace, semiconductors and other fields with high reliability.
According to a fourth aspect of the present invention, the storage medium is a computer readable storage medium, and is used for computer readable storage, where the storage medium stores one or more programs, and the one or more programs may be executed by one or more processors, so as to implement the steps of the method for predicting failure and life of an on-source integrated machine.
The storage medium according to the embodiment of the fourth aspect of the present invention has at least the following advantageous effects:
firstly, acquiring temperature sampling data of an electrolytic capacitor in a source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the service life of the electrolytic capacitor; then acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and performing normalization processing to obtain a first normalization data set; then, acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set; then acquiring voltage and current sampling data of the source-load integrated machine, and performing normalization processing to obtain a third normalization data set; and finally, constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, obtaining the probability of faults to occur to key components in the source-load all-in-one machine according to the optimal solution, and predicting the residual life of the source-load all-in-one machine according to the life of the electrolytic capacitor and the probability of faults to occur to the key components in the source-load all-in-one machine.
According to the method, firstly, the service life of an electrolytic capacitor and the work failure rate of key components are calculated, then, a hidden Markov model is built by combining temperature data, environment temperature data, voltage and current sampling data, historical data and power supply design parameters of all components in the source-carried integrated machine, and finally, the hidden Markov model is solved through a Viterbi algorithm, so that the fault probability and the residual service life of the key components in the source-carried integrated machine are obtained. The method can predict the faults and the service life of the source-carrying integrated machine and meet the requirements of the national defense and military industry, aerospace, semiconductors and other fields with high reliability.
Additional aspects and advantages of the invention 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 invention.
Drawings
The invention is further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a schematic circuit topology diagram of a source-load integrated machine according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for predicting failure and lifetime of an on-board integrated machine according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a method for predicting failure and lifetime of a source-loaded integrated machine according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating the operation of the sampling procedure according to an embodiment of the present invention;
fig. 5 is a diagram of an optimal path in the viterbi algorithm solution process according to an embodiment of the invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
In the description of the present invention, it should be understood that the direction or positional relationship indicated with respect to the description of the orientation, such as up, down, etc., is based on the direction or positional relationship shown in the drawings, is merely for convenience of describing the present invention and simplifying the description, and does not indicate or imply that the apparatus or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
In the description of the present invention, plural means two or more. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless explicitly defined otherwise, terms such as arrangement, installation, connection, etc. should be construed broadly and the specific meaning of the terms in the present invention can be reasonably determined by a person skilled in the art in combination with the specific contents of the technical scheme.
The invention relates to a fault and service life prediction method of a source-load integrated machine, and referring to fig. 1, a circuit topology structure of the source-load integrated machine is introduced first, the source-load integrated machine in the invention is a topology structure of a three-stage architecture, the first stage is a bridgeless PFC topology, the second stage is a bidirectional CLLC topology, and the third stage is a three-phase staggered synchronous BUCK topology.
Specifically, the first stage is a bridgeless PFC topology, AC_L and AC_N are respectively a live wire end and a zero wire end of a single-phase 220V power supply, the live wire end AC_L and the zero wire end AC_N are respectively connected to two arms of the bridgeless PFC through a common mode inductor L1, a differential mode inductor L2A and a differential mode inductor L2B, a MOS tube Q1 and a MOS tube Q2 are SiC-MOSFET, namely a fast switching tube, and the switching frequency is 100KHz; MOS tube Q3, MOS tube Q4 are ordinary MOS tube, slow switch tube promptly, switching frequency 50Hz. The capacitor C3 adopts a high-capacity electrolytic capacitor as a filter capacitor of PFC. PFC_v1 is alternating current voltage sampling, PFC_i1 is alternating current sampling, PFC_v2 is PFC bus voltage sampling, PFC_t1, PFC_t2, PFC_t3, PFC_t4 and PFC_t5 are alternating current input common-mode inductance L1 temperature sampling, PFC inductance L2 temperature sampling, PFC fast switching tube Q1 temperature sampling, PFC fast switching tube Q2 temperature sampling and PFC bus capacitor C3 temperature sampling respectively.
Specifically, the second stage is a bidirectional CLLC topology, the MOS transistors Q5-Q12 respectively form two full-bridge circuits, the two full-bridge circuits are connected through a high-frequency transformer, wherein the inductor L3 is a resonant inductor, the capacitor C4 and the capacitor C5 are resonant capacitors, and the capacitor C6 is a filter capacitor of the later stage of the CLLC. During forward operation, the MOS transistor Q5, the MOS transistor Q6, the MOS transistor Q7 and the MOS transistor Q8 are used as switching transistors, and PWM pulses of the MOS transistor Q9, the MOS transistor Q10, the MOS transistor Q11 and the MOS transistor Q12 are closed and used as rectifier diodes; during reverse operation, the MOS transistor Q9, the MOS transistor Q10, the MOS transistor Q11 and the MOS transistor Q12 are used as switching transistors, and PWM pulses of the MOS transistor Q5, the MOS transistor Q6, the MOS transistor Q7 and the MOS transistor Q8 are closed and used as rectifier diodes. When the forward and reverse directions work, the circuit works in the resonance soft switch working state, and the MOS tube is turned on at zero voltage and turned off at zero current. The bidirectional series resonant converter adopts a constant-frequency PWM control method, can realize decoupling of the voltage gain of the converter and the size and direction of transmission power, and realizes bidirectional voltage increasing and decreasing wide-range continuous regulation.
Specifically, the third stage is three-phase staggered synchronous BUCK topology, a first path of synchronous BUCK is formed by an MOS tube Q13, an MOS tube Q14 and an inductor L5A, a second path of synchronous BUCK is formed by an MOS tube Q15, an MOS tube Q16 and an inductor L5B, a third path of synchronous BUCK is formed by an MOS tube Q17, an MOS tube Q18 and an inductor L5C, a capacitor C7 is an output filter capacitor, 120 DEG phase shifting is performed between the three paths of synchronous BUCK, the three paths of synchronous BUCK work in a BUCK mode in the forward direction and work in a BOOST mode in the reverse direction, energy bidirectional flow is realized, and the staggered parallel topology circuit can reduce output voltage ripple, reduce the volume of each phase of inductor and improve the response speed of the circuit.
It should be noted that the above only describes a circuit topology structure of an existing source-load integrated machine, and the innovation point of the invention is not in the circuit topology of the source-load integrated machine, and the method of the invention is not limited to the source-load integrated machine with the circuit topology structure, and the source-load integrated machine with any circuit topology structure belongs to the application scope of the invention.
The specific method of the present invention is described in detail below:
referring to fig. 2 and 3, a fault and life prediction method of an on-source integrated machine includes the following steps:
s100, acquiring temperature sampling data of an electrolytic capacitor in the source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation, and calculating the service life of the electrolytic capacitor;
the temperature is an important factor affecting the life of the power supply, and the reaction speed of the main power element is doubled and the life is reduced by 50% every time the ambient temperature rises by 10 ℃. Iron loss and copper loss are the main causes of temperature rise caused by the operation of magnetic devices such as transformers and inductors, and the life is also affected because the coil is inevitably deteriorated, the insulating performance is lowered, and the capability of power supply impact is weakened due to the rise of the operating temperature of the magnetic devices. The service life of the electrolytic capacitor directly influences the service life of the source-carried integrated machine, and because other components in the source-carried integrated machine are relatively stable and the average service life is longer than that of the electrolytic capacitor, the service life of the electrolytic capacitor is calculated first, the basic service life of the source-carried integrated machine can be obtained through the service life of the electrolytic capacitor, and the residual service life of the source-carried integrated machine can be predicted by combining the failure rate of other components obtained through the hidden Markov model.
Specifically, firstly, acquiring several sampling data of PFC_T5, LLC_T3, LLC_T8 and BUCK_T4, wherein PFC_T5 is the temperature sampling of a capacitor C3, LLC_T3 is the temperature sampling of a capacitor C4, LLC_T8 is the temperature sampling of a capacitor C6, BUCK_T4 is the temperature sampling of a capacitor C7, the several capacitors are large-capacity electrolytic capacitors, and the service life of the electrolytic capacitors is calculated according to an Arrhenius equation, wherein the expression of the Arrhenius equation is as follows:
，
wherein L is the rated highest service temperature of the electrolytic capacitor when the ambient temperature is T, and L 0 The rated life of the electrolytic capacitor at the rated highest service temperature is equal to the ambient temperature.
When the working temperature of the electrolytic capacitor is at the rated highest working temperature (namely T0=T), the minimum service life of the electrolytic capacitor is calculated as L=L by the formula 0 I.e. equal to the rated life, for example 10000 hours, 10000/8760=1.14 years. When the working temperature of the electrolytic capacitor is lower than the maximum use temperature by 10 ℃, the service life of the electrolytic capacitor is calculated as L=L by the formula 0 ×2[T 0 -(T 0 -10℃)]/10℃=L 0 X 2, i.e. equal to 2 times the rated life, i.e. 20000 hours, so the life of the electrolytic capacitor at this time is approximately 20000/8760=2.28 years.
S200, acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and then carrying out normalization processing to obtain a first normalization data set;
The temperature data of each component in the source-load integrated machine in step S200 includes temperature sampling data, radiator temperature data and PCB board temperature data of each component in the source-load integrated machine.
The temperature sampling data of each component in the embodiment of the present invention includes several temperature sampling data, including pfc_t1, pfc_t2, pfc_t3, pfc_t4, llc_t1, llc_t2, llc_t4, llc_t5, llc_t6, llc_t7, buck_t1, buck_t2, and buck_t3, and the temperature sampling data, the radiator temperature data, the PCB board temperature data, and the ambient temperature data are normalized together.
S300, acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set;
the basic failure rate in step S300 refers to a basic failure rate of a component only considering temperature and electrical stress, and the expression of the failure rate prediction model is as follows:
=/>，
Wherein λP is the failure rate of the operation of the component, λb is the basic failure rate of the component,the correction coefficients are correction coefficients which affect the work failure rate of the component, and n is the number of the correction coefficients of the component.
It should be noted that, the basic failure rate and correction coefficient of the components and the specific failure rate prediction model can be obtained by consulting GJB/Z299C-2006 electronic equipment reliability prediction Manual, the correction coefficient refers to various correction factors affecting the operation failure rate of the components; the number of correction coefficients is the specific influence number of the component operation failure rate.
Exemplary, the following table 1 shows an exemplary table of operation failure rates of some components, and the operation failure rates of the MOS transistor, the electrolytic capacitor, the transformer, and the inductor are calculated according to the correction coefficients of the respective quality levels, the stress ratio, the working environment, and the like, and the basic failure rates thereof.
Table 1 working failure rate example table of part of components
It should be understood that the failure rates of the above MOS transistor, electrolytic capacitor, transformer, and inductor are only examples of the present invention, and the failure rates of other components can be calculated in the above manner.
The failure rate in step S300 refers to the probability of failure occurring in a unit time after a certain time when a component that has not failed is operated. The historical data of the source-load all-in-one machine is read out from a historical database, and the historical database refers to a database storing the data sampled before, failure rate analysis and other results. The power supply design parameters comprise an input voltage range, an output current range, an output power range, voltage withstand values of component selection, rated currents and the like.
It should be noted that, the key components of the source-load integrated machine refer to other components except the electrolytic capacitor, because the service life of the electrolytic capacitor can directly pass through an Arrhenius equation, the other components have better stability on one hand, the average service life is higher than that of the electrolytic capacitor, and on the other hand, no related calculation formula exists, the fault information can only be monitored through actual running conditions, and the fault information can be predicted through a related algorithm of machine learning. Therefore, the service life of the electrolytic capacitor is calculated firstly, the basic service life of the source-load integrated machine can be obtained through the service life of the electrolytic capacitor, and the residual service life of the source-load integrated machine can be predicted by combining the failure rate of other components obtained through the hidden Markov model.
S400, acquiring voltage and current sampling data of the source-load integrated machine, and then carrying out normalization processing to obtain a third normalization data set;
the voltage and current sampling data of the source-load integrated machine are obtained for monitoring the power state of the source-load integrated machine. The voltage and current sampling data of the source-carried integrated machine comprise power input voltage and current sampling data of the source-carried integrated machine and voltage and current sampling data of all levels of topologies in the source-carried integrated machine.
Specifically, the input and output voltage and current sampling data of each stage of topology in the source-load integrated machine comprise voltage and current sampling data of bridgeless PFC topology, voltage and current sampling data of bidirectional CLLC topology and voltage and current sampling data of three-phase staggered synchronous BUCK topology.
It should be noted that, in step S200, the temperature data and the ambient temperature data of each component, and in step S400, the voltage and current sampling data of the source-load integrated machine are both collected by the DSP, and referring to fig. 4, a specific workflow of a sampling program in the DSP is shown, where the first step is initialized, and the second step runs the sampling subroutine to collect relevant sampling data.
S500, constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, and obtaining the probability of faults to occur to key components in the source-carrier all-in-one machine according to the optimal solution.
The expression of the hidden Markov model is as follows:
λ=(A,B,Π)
the method comprises the steps that lambda is a hidden Markov model, A is a state transition probability distribution matrix, B is an observation state probability matrix, pi is initial state distribution of failure rate of the component, the state transition probability distribution matrix is calculated through a first normalized data set, a second normalized data set and a third normalized data set, the observation state probability matrix is calculated through the first normalized data set, the second normalized data set and the third normalized data set, and the initial state distribution of failure rate of the component is calculated through the second normalized data set.
The hidden markov model, that is, the HMM model (Hidden Markov Model), is widely used in the fields of language recognition, natural language processing, pattern recognition, and the like. According to the method, the failure rate of each key component of the power supply is analyzed, the failure rate of the power supply can be predicted after the power supply is processed by adopting a Viterbi algorithm through the thought of combining an Arrhenius equation and a hidden Markov model, and the residual life is predicted.
It should be noted that the prediction problem, also called the decoding problem, is that is, given the model λ= (a, B, pi) and the observed sequence o= { O 1 ,O 2 ,...,O T The most probable corresponding state sequence under the condition of a given observation sequence is calculated and the application is generalThe hidden Markov model is solved by the over Viterbi algorithm.
It should be noted that the viterbi algorithm is a method for solving the shortest path of the sequence based on dynamic programming. The algorithm needs to find the appropriate local state, and a recursive formula for the local state.
Assume that input: HMM model lambda= (A, B, pi), observed sequence O= { O 1 ,O 2 ,...,O T }。
1. Initializing a local state:
2. dynamic programming recurrence time t=2, 3,..local state at time T:
3. calculating delta of time Tmax T (i) I.e. the probability of the most likely hidden state sequence occurring. Calculating T maximum t (i) Namely the most probable hidden state at time T:
4. the backtracking starts with the local state ψ (i). For t=t-1, T-2,..1, then:
5. the most likely hidden state sequence I ∗ = { I1 ∗, I2 ∗,..it ∗ }.
The process of solving the hidden markov model by the viterbi algorithm in the present invention will be described in detail with specific examples,
firstly, a model lambda= (A, B, pi) of MOS-LLC_T6, MOS-LLC_T7 and electrolytic capacitor-LLC_T8 is assumed, the state set is Q, and the observation set is V.
Wherein, the observation set v= { normal, failure }; state set q= { normalized failure rate 1, normalized failure rate 2, normalized failure rate 3}.
The normalized failure rate 1 represents the failure rate read out from the historical database, the normalized failure rate 2 represents the working failure rate calculated according to the current running condition, and the normalized failure rate 3 represents the failure rate when the power supply is designed, wherein the failure rate when the power supply is designed is obtained according to GJB/Z299C-2006 electronic equipment reliability prediction Manual.
In the embodiment of the invention, the initial state distribution pi= (normalized failure rate 1:0.2, normalized failure rate 2:0.4, normalized failure rate 3:0.4) T 。
The state transition probability distribution matrix is shown in table 2 below:
TABLE 2 State transition probability distribution matrix
Thus, the state transition probability distribution matrix is expressed as:
the observation state probability matrix is shown in table 3 below:
TABLE 3 observation state probability matrix
Thus, the state transition probability distribution matrix is expressed as:
it should be noted that the above values are all calculated by referring to the GJB/Z299C-2006 "Manual for predicting reliability of electronic device", which is an example of the method, by adopting the method of step S100-step S400.
Referring to fig. 1, the failure rate is mainly the failure rate of the capacitor C6, that is, the failure rate parameter of the electrolytic capacitor-llc_t8, and the fault conditions of the MOS transistor Q9 and the MOS transistor Q10, that is, the MOS-llc_t6 and the MOS-llc_t7 are the previous link components of the electrolytic capacitor-llc_t8, which have strong correlation. The MOS-LLC_T6 and the MOS-LLC_T7 are the MOS of the upper arm and the lower arm, so that the parameters of the two MOS transistors can be considered to be the same.
The observation sequence o= { MOS-llc_t6, electrolytic capacitor-llc_t8, MOS-llc_t7}.
The Viterbi algorithm needs to obtain two local states corresponding to three hidden states at time 1, where the observed state is 1, i.e. the probability that the observed o1 is MOS-LLC_T6, ψ 1 (i) The previous state of the path with the highest probability at time 1 is thus:
δ1(1)= 1 b 1 (O 1 )=0.2×0.5=0.1
δ1(2)= 2 b 2 (O 1 )=0.4×0.4=0.16
δ1(3)= 3 b 3 (O 1 )=0.4×0.7=0.28
Ψ 1 (1)=Ψ 1 (2)=Ψ 1 (3)=0
wherein,probability of failure corresponding to time 1, pi 1 Is normalized failure rate 1, pi in initial state distribution 2 Is normalized failure rate 2 pi in initial state distribution 3 Normalized failure rate 3 within the initial state distribution, b1 is the 1 st value of the "normal" column of the observed state probability matrix, i.e., probability of normal/failure, O 1 Is MOS-LLC_T6, O 2 Is electrolytic capacitor-LLC_T8, O 3 Is MOS-llc_t7.
Then starting recursion of the respective two local states corresponding to the three hidden states at time 2, where the observed state is 2, i.e. the maximum probability of a path where state j is observed as MOS-llc_t6 at t=1 and state i is observed as MOS-llc_t7 at t=2, ψ 2 (i) The previous state of the path with the highest probability at time 2:
Ψ 2 (1)=3
Ψ 2 (2)=3
Ψ 2 (3)=3
the time in the present invention refers to the number of times the program is run, or the time set by the program, for example, 10ms for one cycle, time 1 indicates 10ms, and time 2 indicates 20ms.
Then recursively estimating two corresponding local states of the three hidden states at the moment 3, wherein the observed states are 1, ψ 3 (i) The previous state of the path with the highest probability at time 3:
Ψ 3 (1)=2
Ψ 3 (2)=2
Ψ 3 (3)=3
to sum up, the probability of the optimal path is represented by P, where the maximum probability is δ 3 (3) Whereby the end point of the optimal path is i 3 *，i 3 * =3。
Reverse direction finding i 2 *、i 1 *：
At t=2, i 2 *=Ψ 3 (i 3 *) =Ψ 3 (3) = 3；
At t=1, i 1 *=Ψ 2 (i 2 *) =Ψ 2 (3) = 3；
Then, an optimal path is obtained, and the optimal path diagram is shown in fig. 5, and the optimal path diagram can be known, i.e., an optimal state sequence i = (i) 1 *, i 2 *, i 3 * ) = (3, 3, 3), electrolytic capacitor-llc_t8 has a high probability of failure, and when the probability is greater than a threshold value, an alarm prompt for predicting failure will be given.
S600, predicting the residual life of the source-load integrated machine according to the life of the electrolytic capacitor and the probability of faults to occur in key components in the source-load integrated machine.
It should be noted that, because the average lifetime of the electrolytic capacitor in the source-load integrated machine is the lowest, the lifetime of the electrolytic capacitor directly affects the lifetime of the source-load integrated machine, but the failure probability of other key components except the electrolytic capacitor also affects the remaining lifetime of the source-load integrated machine, so the basic lifetime of the source-load integrated machine is obtained according to the lifetime of the electrolytic capacitor, and then the failure probability about to occur in the key components in the load integrated machine obtained in step S500 is used as a coefficient to obtain the prediction result of the remaining lifetime of the source-load integrated machine.
Firstly, acquiring temperature sampling data of an electrolytic capacitor in a source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the service life of the electrolytic capacitor; then acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and performing normalization processing to obtain a first normalization data set; then, acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set; then acquiring voltage and current sampling data of the source-load integrated machine, and performing normalization processing to obtain a third normalization data set; and finally, constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, obtaining the probability of faults to occur to key components in the source-load all-in-one machine according to the optimal solution, and predicting the residual life of the source-load all-in-one machine according to the life of the electrolytic capacitor and the probability of faults to occur to the key components in the source-load all-in-one machine.
According to the method, firstly, the service life of an electrolytic capacitor and the work failure rate of key components are calculated, then, a hidden Markov model is built by combining temperature data, environment temperature data, voltage and current sampling data, historical data and power supply design parameters of all components in the source-carried integrated machine, and finally, the hidden Markov model is solved through a Viterbi algorithm, so that the fault probability and the residual service life of the key components in the source-carried integrated machine are obtained. The method can predict the faults and the service life of the source-carrying integrated machine and meet the requirements of the national defense and military industry, aerospace, semiconductors and other fields with high reliability.
The invention also relates to a fault and service life prediction device of the source-load integrated machine, which comprises the following components:
the electrolytic capacitor life calculation unit is used for acquiring temperature sampling data of the electrolytic capacitor in the source-load all-in-one machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the life of the electrolytic capacitor;
the temperature data processing unit is used for acquiring temperature data and environmental temperature data of all components in the source-carried all-in-one machine, and then carrying out normalization processing to obtain a first normalization data set;
The failure rate data processing unit is used for acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set;
the current-voltage data processing unit is used for acquiring voltage and current sampling data of the source-load all-in-one machine and then carrying out normalization processing to obtain a third normalization data set;
the fault probability calculation unit is used for constructing a hidden Markov model according to the first normalized data set, the second normalized data set and the third normalized data set, solving the constructed hidden Markov model through a Viterbi algorithm, and obtaining the fault probability of key components in the source-carrier all-in-one machine according to the optimal solution;
the expression of the hidden Markov model is as follows:
λ=(A,B,Π)，
λ is a hidden markov model, a is a state transition probability distribution matrix, B is an observation state probability matrix, and pi is an initial state distribution of failure rate of the component; the state transition probability distribution matrix is calculated by a first normalized data set, a second normalized data set and a third normalized data set, the observation state probability matrix is calculated by the first normalized data set, the second normalized data set and the third normalized data set, and the initial state distribution of the failure rate of the component is calculated by the second normalized data set;
And the residual life prediction unit is used for predicting the residual life of the source-load integrated machine according to the life of the electrolytic capacitor and the probability of faults to occur in key components in the source-load integrated machine.
The failure and life prediction device of the source-load integrated machine in the embodiment of the present invention is used for executing the failure and life prediction method of the source-load integrated machine in the above embodiment, and the specific processing procedure is the same as the failure and life prediction method of the source-load integrated machine in the above embodiment, and will not be described in detail here.
The invention also relates to an electronic device comprising a memory and a processor, wherein the memory stores a computer program or instructions, and the processor executes the computer program or instructions to implement the fault and life prediction method of the source-load integrated machine of the above embodiment.
In implementation, each step of the above method may be implemented by an integrated logic circuit of hardware in a processor or a computer program or instructions in the form of software. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method. To avoid repetition, a detailed description is not provided herein.
It should be noted that the processor in the embodiments of the present application may be an integrated circuit chip with signal processing capability. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or by computer programs or instructions in the form of software. The processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, or discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
It will be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (programmableROM, PROM), an erasable programmable read-only memory (erasablePROM, EPROM), an electrically erasable programmable read-only memory (electricallyEPROM, EEPROM), or a flash memory, among others. The volatile memory may be Random Access Memory (RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic random access memory (dynamicRAM, DRAM), synchronous dynamic random access memory (synchronousDRAM, SDRAM), double data rate synchronous dynamic random access memory (doubledatarateSDRAM, DDRSDRAM), enhanced synchronous dynamic random access memory (enhancedSDRAM, ESDRAM), synchronous link dynamic random access memory (synchlinkDRAM, SLDRAM), and direct memory bus random access memory (directrambusRAM, DRRAM). It should be noted that the memory described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
The present invention also relates to a storage medium, which is a computer readable storage medium, and is used for computer readable storage, where the storage medium stores one or more programs, and the one or more programs may be executed by one or more processors, so as to implement the steps of the failure and life prediction method of the source-carrier integrated machine in the foregoing embodiment.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relation of association objects, and indicates that there may be three kinds of relations, for example, a and/or B, and may indicate that a alone exists, a and B together, and B alone exists. Wherein A, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of the following" and the like means any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent: a alone, b alone, c alone, a and b together, a and c together, b and c together, or a and b and c together, wherein a, b, c may be single or plural.
In embodiments of the present application, "indication" may include direct indication and indirect indication, as well as explicit indication and implicit indication. The information indicated by a certain information is referred to as information to be indicated, and in a specific implementation process, there may be various ways of indicating the information to be indicated, for example, but not limited to, directly indicating the information to be indicated, such as indicating the information to be indicated itself or an index of the information to be indicated. The information to be indicated can also be indicated indirectly by indicating other information, wherein the other information and the information to be indicated have an association relation. It is also possible to indicate only a part of the information to be indicated, while other parts of the information to be indicated are known or agreed in advance. For example, the indication of the specific information may also be achieved by means of a pre-agreed (e.g., protocol-specified) arrangement sequence of the respective information, thereby reducing the indication overhead to some extent.
In the embodiments of the present application, each term and english abbreviation are given as exemplary examples for convenience of description, and should not constitute any limitation to the present application. This application does not exclude the possibility of defining other terms in existing or future protocols that perform the same or similar functions.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application.
Claims (9)
1. The fault and service life prediction method of the source-load integrated machine is characterized by comprising the following steps of:
acquiring temperature sampling data of an electrolytic capacitor in the source-load integrated machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation, and calculating the service life of the electrolytic capacitor;
acquiring temperature data and environmental temperature data of each component in the source-load integrated machine, and then carrying out normalization processing to obtain a first normalization data set;
acquiring the basic failure rate of the key components in the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model, and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set;
Acquiring voltage and current sampling data of the source-load integrated machine, and then carrying out normalization processing to obtain a third normalization data set;
constructing a hidden Markov model according to the first normalization data set, the second normalization data set and the third normalization data set, solving the constructed hidden Markov model through a Viterbi algorithm, and obtaining the probability of faults to occur to key components in the source-carrier all-in-one machine according to the optimal solution;
the expression of the hidden Markov model is as follows:
λ=(A,B,Π)，
λ is a hidden markov model, a is a state transition probability distribution matrix, B is an observation state probability matrix, and pi is an initial state distribution of failure rate of the component; the state transition probability distribution matrix is calculated by a first normalized data set, a second normalized data set and a third normalized data set, the observation state probability matrix is calculated by the first normalized data set, the second normalized data set and the third normalized data set, and the initial state distribution of the failure rate of the component is calculated by the second normalized data set;
and predicting the residual life of the source-load integrated machine according to the life of the electrolytic capacitor and the probability of faults to occur to key components in the source-load integrated machine.
2. The method for predicting the failure and life of an on-source integrated machine according to claim 1, wherein in the step of substituting temperature sampling data of an electrolytic capacitor into an alry equation to calculate the life of the electrolytic capacitor, the alry equation has the expression:
，
wherein L is the service life of the electrolytic capacitor when the ambient temperature is T, T 0 For rated highest use temperature of electrolytic capacitor, L 0 The rated life of the electrolytic capacitor at the rated highest service temperature is equal to the ambient temperature.
3. The method for predicting failure and life of an on-board integrated machine according to claim 1, wherein the temperature data of each component in the on-board integrated machine includes temperature sampling data of each component in the on-board integrated machine, heat sink temperature data and PCB temperature data.
4. The method for predicting failure and life of an on-source integrated machine according to claim 1, wherein in the step of calculating the failure rate of the key component by substituting the basic failure rate of the key component into the failure rate prediction model, the failure rate prediction model has the expression:
=/>，
wherein λP is the failure rate of the operation of the component, λb is the basic failure rate of the component,for the correction coefficients, n is the number of correction coefficients for the component.
5. The method for predicting failure and life of an on-board integrated machine according to claim 1, wherein in the step of acquiring voltage and current sampling data of the on-board integrated machine, the voltage and current sampling data of the on-board integrated machine includes voltage and current sampling data of a power supply input voltage and current of the on-board integrated machine and voltage and current sampling data of each stage topology in the on-board integrated machine.
6. The method for predicting failure and life of an on-board integrated machine according to claim 5, wherein the input/output voltage and current sampling data of each stage of topology in the on-board integrated machine includes voltage and current sampling data of bridgeless PFC topology, voltage and current sampling data of bidirectional CLLC topology, and voltage and current sampling data of three-phase interleaved synchronous BUCK topology.
7. The utility model provides a trouble and life-span prediction device of source year all-in-one which characterized in that includes:
the electrolytic capacitor life calculation unit is used for acquiring temperature sampling data of the electrolytic capacitor in the source-load all-in-one machine, substituting the temperature sampling data of the electrolytic capacitor into an Arrhenius equation to calculate the life of the electrolytic capacitor;
the temperature data processing unit is used for acquiring temperature data and environmental temperature data of all components in the source-load all-in-one machine, and then carrying out normalization processing to obtain a first normalization data set;
The failure rate data processing unit is used for acquiring the basic failure rate of the key components of the source-load integrated machine, substituting the basic failure rate of the key components into a failure rate prediction model and calculating the working failure rate of the key components; acquiring historical data and power supply design parameters of the source-carried integrated machine, and carrying out normalization processing on the historical data, the work failure rate of key components and the power supply design parameters of the source-carried integrated machine to obtain a second normalization data set;
the current-voltage data processing unit is used for acquiring voltage and current sampling data of the source-load all-in-one machine and then carrying out normalization processing to obtain a third normalization data set;
the fault probability calculation unit is used for constructing a hidden Markov model according to the first normalized data set, the second normalized data set and the third normalized data set, solving the constructed hidden Markov model through a Viterbi algorithm, and obtaining the fault probability of key components in the source-carrier all-in-one machine according to the optimal solution;
the expression of the hidden Markov model is as follows:
λ=(A,B,Π)，
λ is a hidden markov model, a is a state transition probability distribution matrix, B is an observation state probability matrix, and pi is an initial state distribution of failure rate of the component; the state transition probability distribution matrix is calculated by a first normalized data set, a second normalized data set and a third normalized data set, the observation state probability matrix is calculated by the first normalized data set, the second normalized data set and the third normalized data set, and the initial state distribution of the failure rate of the component is calculated by the second normalized data set;
And the residual life prediction unit is used for predicting the residual life of the source-load integrated machine according to the life of the electrolytic capacitor and the probability of faults to occur in key components in the source-load integrated machine.
8. An electronic device comprising a memory storing a computer program or instructions and a processor that when executed implements the method of failure and life prediction of an on-board all-in-one machine of any one of claims 1 to 6.
9. A storage medium, which is a computer-readable storage medium, for computer-readable storage, characterized in that the storage medium stores one or more programs executable by one or more processors to implement the steps of the method for predicting failure and lifetime of an on-source integrated machine according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657449.0A CN117349633B (en) | 2023-12-06 | 2023-12-06 | Fault and life prediction method, device, equipment and medium of source-load integrated machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657449.0A CN117349633B (en) | 2023-12-06 | 2023-12-06 | Fault and life prediction method, device, equipment and medium of source-load integrated machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117349633A CN117349633A (en) | 2024-01-05 |
| CN117349633B true CN117349633B (en) | 2024-02-13 |
Family
ID=89357973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311657449.0A Active CN117349633B (en) | 2023-12-06 | 2023-12-06 | Fault and life prediction method, device, equipment and medium of source-load integrated machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117349633B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682208A (en) * | 2012-05-04 | 2012-09-19 | 电子科技大学 | Turbine disk probability failure physical life predicting method based on Bayes information update |
| CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
| CN110045211A (en) * | 2019-05-16 | 2019-07-23 | 集美大学 | A kind of unmanned ships and light boats fault diagnosis filter method |
| CN111597755A (en) * | 2020-04-30 | 2020-08-28 | 北京锐达芯集成电路设计有限责任公司 | Method for predicting remaining life of electronic device based on gated recursion unit neural network |
| CN113486950A (en) * | 2021-07-05 | 2021-10-08 | 华能国际电力股份有限公司上安电厂 | Intelligent pipe network water leakage detection method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10139311B2 (en) * | 2014-09-26 | 2018-11-27 | Palo Alto Research Center Incorporated | Computer-implemented method and system for machine tool damage assessment, prediction, and planning in manufacturing shop floor |
-
2023
- 2023-12-06 CN CN202311657449.0A patent/CN117349633B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682208A (en) * | 2012-05-04 | 2012-09-19 | 电子科技大学 | Turbine disk probability failure physical life predicting method based on Bayes information update |
| CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
| CN110045211A (en) * | 2019-05-16 | 2019-07-23 | 集美大学 | A kind of unmanned ships and light boats fault diagnosis filter method |
| CN111597755A (en) * | 2020-04-30 | 2020-08-28 | 北京锐达芯集成电路设计有限责任公司 | Method for predicting remaining life of electronic device based on gated recursion unit neural network |
| CN113486950A (en) * | 2021-07-05 | 2021-10-08 | 华能国际电力股份有限公司上安电厂 | Intelligent pipe network water leakage detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 面向广义数学形态颗粒特征的灰色马尔科夫剩余寿命预测方法;李洪儒 等;《振动工程学报》;第28卷(第02期);第316-323页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117349633A (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101019342B1 (en) | Online Failure Detection System of DC Output Filtering Capacitors in Power Converters | |
| WO2017114001A1 (en) | Predictive control-based open-circuit fault diagnosis method for matrix converter switch | |
| CN112798982B (en) | Model-based open-circuit fault diagnosis method and system for three-phase converter power tube | |
| US20130015786A1 (en) | Switching power supply circuit | |
| CN111999557B (en) | Method for evaluating service life of direct-current side electrolytic capacitor in power quality control device | |
| CN117349633B (en) | Fault and life prediction method, device, equipment and medium of source-load integrated machine | |
| Busquets-Monge et al. | Design optimization of a boost power factor correction converter using genetic algorithms | |
| Barwar et al. | Performance analysis and reliability estimation of five‐level rectifier | |
| Laadjal et al. | Online condition monitoring of electrolytic capacitors in DC-DC interleaved boost converters, adopting a model-free predictive controller | |
| Baburajan et al. | Effect of unipolar and bipolar SPWM on the lifetime of DC-link capacitors in single-phase voltage source inverters | |
| Wang et al. | Cost assessment of three power decoupling methods in a single-phase power converter with a reliability-oriented design procedure | |
| Manez et al. | Three-port series-resonant converter DC transformer with integrated magnetics for high efficiency operation | |
| CN115343656A (en) | Fault hypothesis-based open-circuit fault diagnosis method for switching tube in three-level rectifier | |
| Li et al. | Multi-objective Design of LC Filter for High-efficiency, High-power-density and High-performance Buck Converter | |
| CN116938023A (en) | Control method, device and equipment of ANPC (advanced personal computer) type three-level inverter | |
| Catelani et al. | Reliability analysis and electrical characterization of a Class-E resonant inverter | |
| Jiang et al. | Transient modeling and analysis of fractional-order resonant very high frequency boost converter | |
| Zhang et al. | JITL based Fault Detection of DAB DC-DC Converter with EPS Control | |
| Sung et al. | Dual side control of wireless power transfer with mutual inductance estimation | |
| Amaral et al. | A non-invasive technique for fault diagnosis of SMPS | |
| Buticchi et al. | DC–DC Converter and On‐board DC Microgrid Stability | |
| Radmehr et al. | Reliability assessment and thermal consideration of a step-down DC/DC converter | |
| Xia et al. | Condition monitoring for capacitors in modular multilevel converter based on high-frequency transient analysis | |
| CN114204819B (en) | Startup control method, startup control system, computer equipment and storage medium | |
| CN110045262A (en) | Switch driving circuit fault detection means and method, electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |