CN116923100B - Power battery pack repairing method and system - Google Patents
Power battery pack repairing method and system Download PDFInfo
- Publication number
- CN116923100B CN116923100B CN202311204127.0A CN202311204127A CN116923100B CN 116923100 B CN116923100 B CN 116923100B CN 202311204127 A CN202311204127 A CN 202311204127A CN 116923100 B CN116923100 B CN 116923100B
- Authority
- CN
- China
- Prior art keywords
- repair
- battery pack
- power battery
- parameters
- state parameters
- 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 31
- 230000008439 repair process Effects 0.000 claims abstract description 143
- 238000012549 training Methods 0.000 claims abstract description 102
- 230000002159 abnormal effect Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 38
- 238000012795 verification Methods 0.000 claims description 34
- 238000006243 chemical reaction Methods 0.000 claims description 27
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 239000011149 active material Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 210000001787 dendrite Anatomy 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
- B60L3/0023—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
- B60L3/0046—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train relating to electric energy storage systems, e.g. batteries or capacitors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4207—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells for several batteries or cells simultaneously or sequentially
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
- H01M2010/4271—Battery management systems including electronic circuits, e.g. control of current or voltage to keep battery in healthy state, cell balancing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M2220/00—Batteries for particular applications
- H01M2220/20—Batteries in motive systems, e.g. vehicle, ship, plane
Abstract
The invention provides a method and a system for repairing a power battery pack, wherein the method comprises the following steps: when detecting that a power battery pack in the vehicle runs, acquiring actual state parameters generated by the power battery pack in real time, and analyzing the actual state parameters to judge whether the power battery pack is in an abnormal state in real time; if the power battery pack is judged to be in an abnormal state in real time, acquiring theoretical state parameters corresponding to the power battery pack, and training a corresponding repair model according to the theoretical state parameters; and outputting corresponding repair parameters according to the actual state parameters through the repair model, and carrying out self-adaptive repair on the power battery pack through the repair parameters. The invention can enable the power battery pack to be in a stable working state continuously, and correspondingly improves the use experience of users.
Description
Technical Field
The invention relates to the technical field of new energy automobiles, in particular to a method and a system for repairing a power battery pack.
Background
Along with the progress of technology and the rapid development of productivity, the technology of new energy electric automobiles is mature, and is accepted by people gradually, so that the new energy electric automobiles are popularized in daily life of people, and the life of people is greatly facilitated.
The power battery pack is one of core parts of the new energy automobile and is used for providing electric energy for a driving motor in the automobile, so that the service performance and the service life of the power battery pack directly determine the endurance mileage and the driving stability of the new energy automobile.
In the existing power battery pack, various physical and chemical changes, such as dendrite growth, electrolyte decomposition, and active material falling off, occur in the inside of the power battery pack during use, so that problems of increased internal resistance, thermal runaway, and the like may occur. Based on this, in order to promote the performance and the stability in use of power battery package in prior art, most can carry out periodic inspection or change to power battery package, however, the cost of the mode of above-mentioned maintenance power battery package is higher, and efficiency is lower simultaneously, leads to having reduced user's use experience.
Disclosure of Invention
Based on the above, the invention aims to provide a method and a system for repairing a power battery pack, which are used for solving the problems of higher maintenance cost and lower efficiency of the power battery pack in the prior art.
The first aspect of the embodiment of the invention provides:
a method of repairing a power battery pack, wherein the method comprises:
when detecting that a power battery pack in a vehicle runs, acquiring actual state parameters generated by the power battery pack in real time, and analyzing the actual state parameters to judge whether the power battery pack is in an abnormal state in real time;
if the power battery pack is judged to be in the abnormal state in real time, acquiring theoretical state parameters corresponding to the power battery pack, and training a corresponding repair model according to the theoretical state parameters;
and outputting corresponding repair parameters according to the actual state parameters through the repair model, and carrying out self-adaptive repair on the power battery pack through the repair parameters.
The beneficial effects of the invention are as follows: the actual state parameters of the power battery pack are acquired in real time, so that the actual working state of the current power battery pack can be correspondingly acquired, further, whether the current power battery pack is in an abnormal state can be correspondingly judged, and if so, the current actual state parameters are in the abnormal state, based on the abnormal state, a corresponding repair model is further trained according to the acquired theoretical state parameters, and required repair parameters are further generated, so that the current actual state parameters are accurately repaired through the repair parameters, the power battery pack can be continuously in a stable working state on the premise that detection and replacement are not carried out, and the use experience of a user is correspondingly improved.
Further, the step of training a corresponding repair model according to the theoretical state parameter includes:
when the theoretical state parameters are obtained, carrying out forward maximum step length word segmentation on the theoretical state parameters so as to split the theoretical state parameters into a plurality of corresponding character strings, and carrying out serialization processing on the plurality of character strings through a preset DTW algorithm so as to generate a plurality of corresponding training codes;
and generating a corresponding training set and verification set according to a plurality of training codes based on a preset rule, and constructing the repair model according to the training set, the verification set and a preset neural network.
Further, the step of constructing the repair model according to the training set, the verification set and a preset neural network includes:
when the training set and the verification set are acquired, the training set and the verification set are respectively and sequentially input into a conversion layer, a processing layer and a learning layer of the preset neural network;
and sequentially adjusting parameters in the conversion layer, the processing layer and the learning layer through the training set, and sequentially verifying results output by the conversion layer, the processing layer and the learning layer through the verification set so as to correspondingly construct the repair model.
Further, the step of sequentially adjusting parameters in the conversion layer, the processing layer and the learning layer through the training set includes:
when the training set is acquired, inputting target training codes in the training set into a transducer encoder in the conversion layer so as to convert the target training codes into corresponding feature sequences;
inputting the characteristic sequence into an identification algorithm in the processing layer to correspondingly identify a plurality of characteristic values contained in the characteristic sequence;
and inputting a plurality of characteristic values into a learning network in the learning layer, and adjusting original network parameters in the learning network through the plurality of characteristic values.
Further, the step of adjusting the original network parameters in the learning network by the plurality of characteristic values includes:
performing full-disk scanning on the learning network to detect a plurality of learning nodes contained in the learning network and identify a first sequence among the plurality of learning nodes;
detecting a plurality of second sequences among the characteristic values, and establishing a mapping relation between the first sequences and the second sequences;
and replacing the original network parameters in each learning node with each characteristic value based on the mapping relation so as to complete training of the learning network.
Further, the step of outputting, by the repair model, the corresponding repair parameter according to the actual state parameter includes:
analyzing the actual state parameters through the repair model to detect repair grades corresponding to the power battery pack, wherein each repair grade corresponds to a repair coefficient;
and multiplying the actual state parameter and the repair coefficient to correspondingly calculate the repair parameter.
Further, the method further comprises:
when the repair parameters are obtained, accumulating the repair parameters and the actual state parameters to generate corresponding target state parameters, and controlling the power battery pack to work according to the target state parameters.
A second aspect of an embodiment of the present invention proposes:
a power battery pack repair system, wherein the system comprises:
the acquisition module is used for acquiring actual state parameters generated by the power battery pack in real time when detecting the running of the power battery pack in the vehicle, and analyzing the actual state parameters to judge whether the power battery pack is in an abnormal state in real time;
the training module is used for acquiring theoretical state parameters corresponding to the power battery pack if the power battery pack is judged to be in the abnormal state in real time, and training a corresponding repair model according to the theoretical state parameters;
and the repair module is used for outputting corresponding repair parameters according to the actual state parameters through the repair model, and carrying out self-adaptive repair on the power battery pack through the repair parameters.
Further, the training module is specifically configured to:
when the theoretical state parameters are obtained, carrying out forward maximum step length word segmentation on the theoretical state parameters so as to split the theoretical state parameters into a plurality of corresponding character strings, and carrying out serialization processing on the plurality of character strings through a preset DTW algorithm so as to generate a plurality of corresponding training codes;
and generating a corresponding training set and verification set according to a plurality of training codes based on a preset rule, and constructing the repair model according to the training set, the verification set and a preset neural network.
Further, the training module is specifically configured to:
when the training set and the verification set are acquired, the training set and the verification set are respectively and sequentially input into a conversion layer, a processing layer and a learning layer of the preset neural network;
and sequentially adjusting parameters in the conversion layer, the processing layer and the learning layer through the training set, and sequentially verifying results output by the conversion layer, the processing layer and the learning layer through the verification set so as to correspondingly construct the repair model.
Further, the training module is specifically configured to:
when the training set is acquired, inputting target training codes in the training set into a transducer encoder in the conversion layer so as to convert the target training codes into corresponding feature sequences;
inputting the characteristic sequence into an identification algorithm in the processing layer to correspondingly identify a plurality of characteristic values contained in the characteristic sequence;
and inputting a plurality of characteristic values into a learning network in the learning layer, and adjusting original network parameters in the learning network through the plurality of characteristic values.
Further, the training module is specifically configured to:
performing full-disk scanning on the learning network to detect a plurality of learning nodes contained in the learning network and identify a first sequence among the plurality of learning nodes;
detecting a plurality of second sequences among the characteristic values, and establishing a mapping relation between the first sequences and the second sequences;
and replacing the original network parameters in each learning node with each characteristic value based on the mapping relation so as to complete training of the learning network.
Further, the repair module is specifically configured to:
analyzing the actual state parameters through the repair model to detect repair grades corresponding to the power battery pack, wherein each repair grade corresponds to a repair coefficient;
and multiplying the actual state parameter and the repair coefficient to correspondingly calculate the repair parameter.
Further, the power battery pack repair system further comprises a control module, wherein the control module is specifically configured to:
when the repair parameters are obtained, accumulating the repair parameters and the actual state parameters to generate corresponding target state parameters, and controlling the power battery pack to work according to the target state parameters.
A third aspect of an embodiment of the present invention proposes:
a computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the power battery pack repair method as described above when the computer program is executed by the processor.
A fourth aspect of the embodiment of the present invention proposes:
a readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements the power battery pack repair method as described above.
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
Fig. 1 is a flowchart of a power battery pack repairing method according to a first embodiment of the present invention;
fig. 2 is a block diagram of a power battery pack repair system according to a sixth embodiment of the present invention.
The invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, a power battery pack repairing method according to a first embodiment of the present invention is shown, and the power battery pack repairing method according to the present embodiment can enable a power battery pack to be continuously in a stable working state without detection or replacement, thereby correspondingly improving the use experience of a user.
Specifically, the method for repairing the power battery pack provided by the embodiment specifically includes the following steps:
step S10, when detecting that a power battery pack in a vehicle runs, acquiring actual state parameters generated by the power battery pack in real time, and analyzing the actual state parameters to judge whether the power battery pack is in an abnormal state in real time;
step S20, if the power battery pack is judged to be in the abnormal state in real time, acquiring theoretical state parameters corresponding to the power battery pack, and training a corresponding repair model according to the theoretical state parameters;
and step S30, outputting corresponding repair parameters according to the actual state parameters through the repair model, and carrying out self-adaptive repair on the power battery pack through the repair parameters.
In particular, in this embodiment, it should be noted first that the method for repairing a power battery pack can be applied to power battery packs of different types, and is used for repairing operation parameters of the power battery pack in real time, so that the power battery pack can be continuously in a stable and efficient working state. Based on the above, in the process of the actual running of the power battery pack, the actual state parameters of the current power battery pack need to be acquired in real time, and meanwhile, corresponding analysis processing is performed, so that whether the current power battery pack is in an abnormal state or not can be judged in real time according to analysis results. Specifically, if not, no repair processing is needed, and if so, further acquiring theoretical state parameters of the current power battery pack when leaving the factory, and further training a corresponding repair model according to the theoretical state parameters.
Further, the actual state parameters are input into the current repair model in real time so as to further output required repair parameters, and based on the current repair parameters and the current actual state parameters, the current actual state parameters can be subjected to self-adaptive adjustment so as to correspondingly complete self-adaptive repair, so that the power battery pack can be in a stable working state, and the use experience of a user is improved.
Second embodiment
Specifically, in this embodiment, it should be noted that the step of training the corresponding repair model according to the theoretical state parameter includes:
when the theoretical state parameters are obtained, carrying out forward maximum step length word segmentation on the theoretical state parameters so as to split the theoretical state parameters into a plurality of corresponding character strings, and carrying out serialization processing on the plurality of character strings through a preset DTW algorithm so as to generate a plurality of corresponding training codes;
and generating a corresponding training set and verification set according to a plurality of training codes based on a preset rule, and constructing the repair model according to the training set, the verification set and a preset neural network.
Specifically, in this embodiment, it should be noted that, after the theoretical state parameter is obtained, in order to facilitate subsequent training, forward maximum step word segmentation needs to be further performed on the current theoretical state parameter, specifically, for example, the obtained theoretical state parameter is "rated voltage is 160V", and after the forward maximum step word segmentation is performed, the formed character string is "rated/electric/voltage/1/6/0/V", based on this, the current character string may be further processed in a serialization manner by using an existing DTW algorithm, so as to correspondingly generate a required training code, and specifically, the training code may be identified by a preset neural network, so as to facilitate subsequent processing.
Further, all the current training codes are randomly split into corresponding training sets and verification sets according to the ratio of 7:3, based on the training sets, the verification sets and the preset neural network are used for constructing the repair model, and the neural network is preferably set as a CNN neural network so as to facilitate subsequent processing.
Specifically, in this embodiment, it should be further noted that the step of constructing the repair model according to the training set, the verification set, and a preset neural network includes:
when the training set and the verification set are acquired, the training set and the verification set are respectively and sequentially input into a conversion layer, a processing layer and a learning layer of the preset neural network;
and sequentially adjusting parameters in the conversion layer, the processing layer and the learning layer through the training set, and sequentially verifying results output by the conversion layer, the processing layer and the learning layer through the verification set so as to correspondingly construct the repair model.
Specifically, in this embodiment, after the required training set and the verification set are obtained through the steps respectively, at this time, the training set needs to be input into the conversion layer, the result output by the conversion layer is further input into the processing layer, the result output by the processing layer is further input into the learning layer, so as to finally complete training of the learning layer, and similarly, the verification set is input into the conversion layer, the processing layer and the learning layer in the same manner, so as to complete corresponding verification, and after the verification result is qualified, the repair model is generated.
Third embodiment
In this embodiment, the step of sequentially adjusting parameters in the conversion layer, the processing layer, and the learning layer through the training set includes:
when the training set is acquired, inputting target training codes in the training set into a transducer encoder in the conversion layer so as to convert the target training codes into corresponding feature sequences;
inputting the characteristic sequence into an identification algorithm in the processing layer to correspondingly identify a plurality of characteristic values contained in the characteristic sequence;
and inputting a plurality of characteristic values into a learning network in the learning layer, and adjusting original network parameters in the learning network through the plurality of characteristic values.
In addition, in this embodiment, specifically, in order to effectively complete training on the neural network, the target training codes included in the training set are first input into the transform encoder in the conversion layer, so as to correspondingly convert the current target training codes into corresponding feature sequences. Specifically, the feature sequence is a sequence that can be recognized by the processing layer described above.
Further, the current feature sequence is further input into a feature recognition algorithm in the processing layer to correspondingly recognize a plurality of feature values contained in the current feature sequence, preferably, the feature recognition algorithm may be set as a HOG (Histogram Oriented Gradient direction gradient histogram) feature recognition algorithm, further, the acquired plurality of feature values are input into a learning network in the learning layer, and based on this, the original network parameters in the current learning network can be finally adjusted through the plurality of feature values.
In addition, in this embodiment, it should be further noted that the step of adjusting the original network parameters in the learning network through the plurality of feature values includes:
performing full-disk scanning on the learning network to detect a plurality of learning nodes contained in the learning network and identify a first sequence among the plurality of learning nodes;
detecting a plurality of second sequences among the characteristic values, and establishing a mapping relation between the first sequences and the second sequences;
and replacing the original network parameters in each learning node with each characteristic value based on the mapping relation so as to complete training of the learning network.
In addition, in this embodiment, it should also be noted that, after a plurality of feature values are obtained in the foregoing manner, in order to be able to effectively train the foregoing learning network, at this time, a full scan needs to be performed on the current learning network, so that all a plurality of learning nodes included in the current learning network can be correspondingly detected, where it should be noted that each learning node is unique, and an original network parameter is set in each learning node, based on this, the current plurality of learning nodes may be ordered correspondingly to generate a required first sequence. Correspondingly, each characteristic value is unique, and similarly, the current plurality of second characteristic values can be sequenced to generate corresponding second sequences, and based on the second sequences, the mapping relation between the current first sequences and the second sequences can be further established according to the sequence numbers of the current first sequences and the second sequences. On the basis, the original network parameters in each current learning node are replaced by the characteristic values according to the current mapping relation, so that training of the learning network can be effectively completed.
Fourth embodiment
In this embodiment, it should be noted that the step of outputting, by the repair model, the corresponding repair parameter according to the actual state parameter includes:
analyzing the actual state parameters through the repair model to detect repair grades corresponding to the power battery pack, wherein each repair grade corresponds to a repair coefficient;
and multiplying the actual state parameter and the repair coefficient to correspondingly calculate the repair parameter.
In this embodiment, it should be noted that, after the complete repair model is trained through the above steps, the actual state parameters are immediately input into the current repair model at this time to perform corresponding analysis processing, so that the repair grade corresponding to the power battery pack in the current vehicle can be detected, and specifically, each repair grade corresponds to a repair coefficient. Furthermore, the repair parameters can be correspondingly calculated by multiplying the actual state parameters by the current repair coefficients.
Fifth embodiment
In this embodiment, it should be noted that, the method further includes:
when the repair parameters are obtained, accumulating the repair parameters and the actual state parameters to generate corresponding target state parameters, and controlling the power battery pack to work according to the target state parameters.
In this embodiment, it should be noted that, after the required repair parameters are calculated through the above steps, the current repair parameters are correspondingly accumulated into the actual state parameters at this time, so as to correspondingly calculate the required target state parameters.
Further, the current target state parameters are input into the whole vehicle controller, so that the power battery pack is further controlled to work according to the current target state parameters through the whole vehicle controller, the abnormality of the power battery pack can be automatically repaired, the power battery pack can be continuously in a stable and efficient working state, and the use experience of a user is correspondingly improved.
Referring to fig. 2, a sixth embodiment of the present invention provides:
a power battery pack repair system, wherein the system comprises:
the acquisition module is used for acquiring actual state parameters generated by the power battery pack in real time when detecting the running of the power battery pack in the vehicle, and analyzing the actual state parameters to judge whether the power battery pack is in an abnormal state in real time;
the training module is used for acquiring theoretical state parameters corresponding to the power battery pack if the power battery pack is judged to be in the abnormal state in real time, and training a corresponding repair model according to the theoretical state parameters;
and the repair module is used for outputting corresponding repair parameters according to the actual state parameters through the repair model, and carrying out self-adaptive repair on the power battery pack through the repair parameters.
In the above power battery pack repair system, the training module is specifically configured to:
when the theoretical state parameters are obtained, carrying out forward maximum step length word segmentation on the theoretical state parameters so as to split the theoretical state parameters into a plurality of corresponding character strings, and carrying out serialization processing on the plurality of character strings through a preset DTW algorithm so as to generate a plurality of corresponding training codes;
and generating a corresponding training set and verification set according to a plurality of training codes based on a preset rule, and constructing the repair model according to the training set, the verification set and a preset neural network.
In the above power battery pack repair system, the training module is further specifically configured to:
when the training set and the verification set are acquired, the training set and the verification set are respectively and sequentially input into a conversion layer, a processing layer and a learning layer of the preset neural network;
and sequentially adjusting parameters in the conversion layer, the processing layer and the learning layer through the training set, and sequentially verifying results output by the conversion layer, the processing layer and the learning layer through the verification set so as to correspondingly construct the repair model.
In the above power battery pack repair system, the training module is further specifically configured to:
when the training set is acquired, inputting target training codes in the training set into a transducer encoder in the conversion layer so as to convert the target training codes into corresponding feature sequences;
inputting the characteristic sequence into an identification algorithm in the processing layer to correspondingly identify a plurality of characteristic values contained in the characteristic sequence;
and inputting a plurality of characteristic values into a learning network in the learning layer, and adjusting original network parameters in the learning network through the plurality of characteristic values.
In the above power battery pack repair system, the training module is further specifically configured to:
performing full-disk scanning on the learning network to detect a plurality of learning nodes contained in the learning network and identify a first sequence among the plurality of learning nodes;
detecting a plurality of second sequences among the characteristic values, and establishing a mapping relation between the first sequences and the second sequences;
and replacing the original network parameters in each learning node with each characteristic value based on the mapping relation so as to complete training of the learning network.
In the above power battery pack repair system, the repair module is specifically configured to:
analyzing the actual state parameters through the repair model to detect repair grades corresponding to the power battery pack, wherein each repair grade corresponds to a repair coefficient;
and multiplying the actual state parameter and the repair coefficient to correspondingly calculate the repair parameter.
Among them, in the above-mentioned power battery package repair system, power battery package repair system still includes control module, control module specifically is used for:
when the repair parameters are obtained, accumulating the repair parameters and the actual state parameters to generate corresponding target state parameters, and controlling the power battery pack to work according to the target state parameters.
A seventh embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the power battery pack repair method provided in the above embodiment when executing the computer program.
An eighth embodiment of the present invention provides a readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements the power battery pack repair method provided by the above embodiment.
In summary, the method and the system for repairing the power battery pack provided by the embodiment of the invention can enable the power battery pack to be in a stable working state continuously on the premise of not detecting and replacing, and correspondingly improve the use experience of users.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (6)
1. A method of repairing a power battery pack, the method comprising:
when detecting that a power battery pack in a vehicle runs, acquiring actual state parameters generated by the power battery pack in real time, and analyzing the actual state parameters to judge whether the power battery pack is in an abnormal state in real time;
if the power battery pack is judged to be in the abnormal state in real time, acquiring theoretical state parameters corresponding to the power battery pack, and training a corresponding repair model according to the theoretical state parameters;
outputting corresponding repair parameters according to the actual state parameters through the repair model, and carrying out self-adaptive repair on the power battery pack through the repair parameters;
the step of training a corresponding repair model according to the theoretical state parameters comprises the following steps:
when the theoretical state parameters are obtained, carrying out forward maximum step length word segmentation on the theoretical state parameters so as to split the theoretical state parameters into a plurality of corresponding character strings, and carrying out serialization processing on the plurality of character strings through a preset DTW algorithm so as to generate a plurality of corresponding training codes;
generating a corresponding training set and verification set according to a plurality of training codes based on a preset rule, and constructing the repair model according to the training set, the verification set and a preset neural network;
the step of constructing the repair model according to the training set, the verification set and a preset neural network comprises the following steps:
when the training set and the verification set are acquired, the training set and the verification set are respectively and sequentially input into a conversion layer, a processing layer and a learning layer of the preset neural network;
sequentially adjusting parameters in the conversion layer, the processing layer and the learning layer through the training set, and sequentially verifying results output by the conversion layer, the processing layer and the learning layer through the verification set to correspondingly construct the repair model;
the step of sequentially adjusting parameters in the conversion layer, the processing layer and the learning layer through the training set comprises the following steps:
when the training set is acquired, inputting target training codes in the training set into a transducer encoder in the conversion layer so as to convert the target training codes into corresponding feature sequences;
inputting the characteristic sequence into an identification algorithm in the processing layer to correspondingly identify a plurality of characteristic values contained in the characteristic sequence;
inputting a plurality of characteristic values into a learning network in the learning layer, and adjusting original network parameters in the learning network through the characteristic values;
the step of adjusting the original network parameters in the learning network by the plurality of characteristic values comprises the following steps:
performing full-disk scanning on the learning network to detect a plurality of learning nodes contained in the learning network and identify a first sequence among the plurality of learning nodes;
detecting a plurality of second sequences among the characteristic values, and establishing a mapping relation between the first sequences and the second sequences;
and replacing the original network parameters in each learning node with each characteristic value based on the mapping relation so as to complete training of the learning network.
2. The power cell pack repair method according to claim 1, wherein: the step of outputting corresponding repair parameters according to the actual state parameters through the repair model comprises the following steps:
analyzing the actual state parameters through the repair model to detect repair grades corresponding to the power battery pack, wherein each repair grade corresponds to a repair coefficient;
and multiplying the actual state parameter and the repair coefficient to correspondingly calculate the repair parameter.
3. The power cell pack repair method according to claim 2, wherein: the method further comprises the steps of:
when the repair parameters are obtained, accumulating the repair parameters and the actual state parameters to generate corresponding target state parameters, and controlling the power battery pack to work according to the target state parameters.
4. A power battery pack repair system for implementing the power battery pack repair method according to any one of claims 1 to 3, the system comprising:
the acquisition module is used for acquiring actual state parameters generated by the power battery pack in real time when detecting the running of the power battery pack in the vehicle, and analyzing the actual state parameters to judge whether the power battery pack is in an abnormal state in real time;
the training module is used for judging that the power battery pack is in the abnormal state in real time, acquiring theoretical state parameters corresponding to the power battery pack, and training a corresponding repair model according to the theoretical state parameters;
and the repair module is used for outputting corresponding repair parameters according to the actual state parameters through the repair model, and carrying out self-adaptive repair on the power battery pack through the repair parameters.
5. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the power cell pack repair method of any one of claims 1 to 3 when the computer program is executed.
6. A readable storage medium having stored thereon a computer program, which when executed by a processor, implements the power battery pack repair method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311204127.0A CN116923100B (en) | 2023-09-19 | 2023-09-19 | Power battery pack repairing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311204127.0A CN116923100B (en) | 2023-09-19 | 2023-09-19 | Power battery pack repairing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116923100A CN116923100A (en) | 2023-10-24 |
| CN116923100B true CN116923100B (en) | 2024-01-26 |
Family
ID=88390111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311204127.0A Active CN116923100B (en) | 2023-09-19 | 2023-09-19 | Power battery pack repairing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116923100B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111856299A (en) * | 2020-07-29 | 2020-10-30 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining power supply state |
| KR20230043466A (en) * | 2021-09-24 | 2023-03-31 | 세종대학교산학협력단 | A System and Method for Batteries State of Health Estimation using Multiple channel charging profile |
| CN116014850A (en) * | 2023-01-09 | 2023-04-25 | 中国华电科工集团有限公司 | Energy storage battery control optimization method and device and electronic equipment |
| CN116184247A (en) * | 2023-02-28 | 2023-05-30 | 合肥国轩高科动力能源有限公司 | Method, device, equipment and medium for detecting abnormal vehicle battery |
| CN116243196A (en) * | 2023-02-03 | 2023-06-09 | 岚图汽车科技有限公司 | Power battery health state evaluation method, device, equipment and storage medium |
| CN116470190A (en) * | 2023-06-19 | 2023-07-21 | 江西五十铃汽车有限公司 | Power battery pack heating method, system, computer and readable storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11691518B2 (en) * | 2017-07-21 | 2023-07-04 | Quantumscape Battery, Inc. | Predictive model for estimating battery states |
| US20210049480A1 (en) * | 2019-08-12 | 2021-02-18 | Micron Technology, Inc. | Predictive maintenance of automotive battery |
-
2023
- 2023-09-19 CN CN202311204127.0A patent/CN116923100B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111856299A (en) * | 2020-07-29 | 2020-10-30 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining power supply state |
| KR20230043466A (en) * | 2021-09-24 | 2023-03-31 | 세종대학교산학협력단 | A System and Method for Batteries State of Health Estimation using Multiple channel charging profile |
| CN116014850A (en) * | 2023-01-09 | 2023-04-25 | 中国华电科工集团有限公司 | Energy storage battery control optimization method and device and electronic equipment |
| CN116243196A (en) * | 2023-02-03 | 2023-06-09 | 岚图汽车科技有限公司 | Power battery health state evaluation method, device, equipment and storage medium |
| CN116184247A (en) * | 2023-02-28 | 2023-05-30 | 合肥国轩高科动力能源有限公司 | Method, device, equipment and medium for detecting abnormal vehicle battery |
| CN116470190A (en) * | 2023-06-19 | 2023-07-21 | 江西五十铃汽车有限公司 | Power battery pack heating method, system, computer and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116923100A (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190670B (en) | Charging pile fault prediction method based on extensible hoisting tree | |
| Li et al. | A model-data-hybrid-driven diagnosis method for open-switch faults in power converters | |
| CN109324291B (en) | Prediction method for predicting service life of proton exchange membrane fuel cell | |
| CN116853073B (en) | New energy electric automobile energy management method and system | |
| CN110619321B (en) | Charging pile technical condition diagnosis method and system based on deep neural network | |
| CN113159077A (en) | Three-phase inverter fault identification method based on hybrid convolutional neural network | |
| CN111191824B (en) | Power battery capacity attenuation prediction method and system | |
| CN112881915A (en) | Fault identification method and device for lithium battery and computer readable storage medium | |
| CN116794543A (en) | Lithium battery performance prediction method based on GBLS boost multitask learning model | |
| CN116776747B (en) | IGBT module service life calculation method and system | |
| CN116470190B (en) | Power battery pack heating method, system, computer and readable storage medium | |
| CN109921462B (en) | New energy consumption capability assessment method and system based on LSTM | |
| CN116923100B (en) | Power battery pack repairing method and system | |
| CN115878992A (en) | Monitoring method and monitoring system for comprehensive pipe rack power supply system | |
| CN111597182A (en) | Convolutional neural network-based fault anomaly identification method for oil pumping unit driving motor | |
| CN111751729A (en) | Method for determining the state of a rechargeable battery of a vehicle | |
| CN116338454A (en) | New energy automobile electrical property detection method and device | |
| CN114398989A (en) | Integrated universal electric chassis multi-target cooperative fault diagnosis method and system | |
| CN114839960A (en) | Method and system for detecting vehicle fault based on artificial intelligence algorithm | |
| CN116945907B (en) | New energy electric automobile mileage calculation method and system | |
| CN114115199A (en) | Monitoring and fault diagnosis system for new energy sanitation vehicle | |
| CN117117374A (en) | Method and system for recovering power battery pack | |
| CN117254746B (en) | Driving motor temperature control method and system | |
| CN117040351B (en) | Driving motor control method and system | |
| CN117533137A (en) | Fault early warning method and system for electric drive system |
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 |