CN113671401A - Lithium battery health state assessment method based on optimization algorithm and data driving - Google Patents
Lithium battery health state assessment method based on optimization algorithm and data driving Download PDFInfo
- Publication number
- CN113671401A CN113671401A CN202111007676.XA CN202111007676A CN113671401A CN 113671401 A CN113671401 A CN 113671401A CN 202111007676 A CN202111007676 A CN 202111007676A CN 113671401 A CN113671401 A CN 113671401A
- Authority
- CN
- China
- Prior art keywords
- real
- lithium battery
- pso
- battery
- 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.)
- Pending
Links
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 95
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 95
- 230000036541 health Effects 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims abstract description 16
- 239000002245 particle Substances 0.000 claims description 62
- 230000003862 health status Effects 0.000 claims description 32
- 238000012360 testing method Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000007599 discharging Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000007500 overflow downdraw method Methods 0.000 description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 229910001416 lithium ion Inorganic materials 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
- G01R31/005—Testing of electric installations on transport means
- G01R31/006—Testing of electric installations on transport means on road vehicles, e.g. automobiles or trucks
- G01R31/007—Testing of electric installations on transport means on road vehicles, e.g. automobiles or trucks using microprocessors or computers
-
- 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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/3644—Constructional arrangements
- G01R31/3648—Constructional arrangements comprising digital calculation means, e.g. for performing an algorithm
-
- 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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- 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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/386—Arrangements for measuring battery or accumulator variables using test-loads
-
- 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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Secondary Cells (AREA)
Abstract
The invention relates to a lithium battery health state evaluation method based on an optimization algorithm and data driving, which comprises the following steps: establishing an initial PSO-LSTM model; acquiring characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into the initial PSO-LSTM model as input variables, and performing iterative training by taking the health condition of the battery as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model with complete training; and inputting real-time data of the battery to be predicted into the target PSO-LSTM model to predict the health condition of the battery. The invention effectively combines the strong optimizing capability of the PSO algorithm and the predicting capability of the variable length sequence of the LSTM algorithm, provides a more effective method for the health state evaluation of the lithium battery, and can rapidly and accurately predict the health condition of the lithium battery.
Description
Technical Field
The invention relates to the technical field of battery monitoring, in particular to a lithium battery health state evaluation method based on an optimization algorithm and data driving.
Background
With the rapid development of the new energy automobile industry, batteries of electric automobiles are also vigorously developed. Because the lithium battery has the characteristics of low cost, long service life, high energy and the like, the lithium battery is widely used for providing power for the electric automobile. However, the health state of the lithium battery is always changed in the using process, the internal chemical reaction mechanism is complex, and a plurality of factors causing the performance attenuation of the lithium battery influence the using performance of the lithium battery, so that the evaluation of the health state of the lithium battery is very important.
Currently, there are three main types of methods for evaluating the health status of a battery: physical models, data-driven and fusion methods.
The method based on the physical model comprises methods such as an electrochemical model, an equivalent circuit model and an empirical model, but the method has the disadvantages of more parameters to be considered, great environmental influence and difficult modeling. The data-driven method comprises a neural network, support vector regression, Gaussian process regression and the like, but the neural network model is complex, needs a large amount of data for training and has a large calculation amount. The fusion method is characterized in that a plurality of methods are fused together, advantages and disadvantages are brought into play, the advantages of each method are exerted, and the fusion method is accepted and used by a plurality of scholars, but the current research success is less.
Disclosure of Invention
In view of the above, it is necessary to provide a lithium battery health state assessment method based on an optimization algorithm and data driving, so as to solve the problems in the prior art that the physical model method is difficult to model and the data driving method has a large calculation amount.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides an optimization algorithm and data-driven lithium battery health status assessment method, including:
establishing an initial PSO-LSTM model;
acquiring characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into an initial PSO-LSTM model as input variables, and performing iterative training by taking the health condition of the battery as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model with complete training;
and inputting the real-time data of the battery to be predicted into the target PSO-LSTM model to predict the health condition of the battery.
Preferably, establishing an initial PSO-LSTM model comprises:
generating LSTM network models of different network parameters;
and optimizing LSTM network models of different network parameters according to a PSO algorithm, and searching for the optimal network parameters.
Preferably, the PSO algorithm comprises:
initializing the speed and position of each particle in the particle swarm;
calculating the historical optimal position of the particle swarm population;
updating the speed and position of each particle in the population of particles;
updating particles at the historical best position in the particle swarm;
and mapping the position information of the particles with the historical optimal positions in the particle swarm to the LSTM network model, and optimizing the parameters of the LSTM network model.
Preferably, the formula for updating the velocity and position of each particle in the particle swarm is specifically:
the velocity update formula is:
vi＝vi+c1×r1×(pbesti-xi)+c2×r2×(gbesti-xi)，
the location update formula is:
xi＝xi+vi，
in the formula: c. C1，c2Is a learning factor, r1，r2Is [0,1 ]]Random number between, pbestiIs the historical best position of the particle, gbestiIs the historical best position of the population.
Preferably, the characteristic parameters characterizing the performance of the lithium battery include real-time discharge voltage, real-time discharge current, real-time load voltage and real-time load current of the lithium battery, the characteristic parameter data characterizing the performance of the battery are divided into a data training set and a data testing set, and the data training set and the data testing set respectively include a real-time discharge voltage data set, a real-time discharge current data set, a real-time load voltage data set and a real-time load current data set.
Preferably, when the real-time discharge voltage data set is the external load of the battery, the real-time voltage data sets at two ends of the load, when the real-time discharge current data set is the external load of the battery, the real-time current data sets at two ends of the load, when the real-time load voltage data set is the external load of the battery, the real-time voltage data sets at two ends of the battery, and when the real-time load current data sets are the external load of the battery, the real-time current data sets at two ends of the battery.
Preferably, the optimizing of the transition LSTM network model by using the particle swarm optimization algorithm and the judging whether the optimized model reaches the preset prediction precision or the preset iteration number specifically include:
calculating the root mean square error of the prediction result:
calculate the mean absolute percentage error of the prediction:
calculating the fitness of the particle swarm algorithm:
wherein n is the total amount of the samples,
is a sample prediction value, yiFor the real value of the sample,
is the sample average.
In a second aspect, the present invention further provides a lithium battery health status prediction apparatus, including:
the modeling module is used for establishing an initial PSO-LSTM model;
the training module is used for acquiring characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into the initial PSO-LSTM model as input variables, and performing iterative training by taking the health condition of the battery as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model which is completely trained;
and the prediction module is used for inputting the real-time data of the battery to be predicted into the target PSO-LSTM model and predicting the health condition of the battery.
In a third aspect, the present invention also provides an electronic device comprising a memory and a processor, wherein,
a memory for storing a program;
and the processor is coupled with the memory and is used for executing the program stored in the memory so as to realize the steps in the lithium battery health state evaluation method based on the optimization algorithm and the data driving in any one of the above implementation modes.
In a fourth aspect, the present invention further provides a computer-readable storage medium, configured to store a computer-readable program or instruction, where the program or instruction, when executed by a processor, can implement the steps in the optimization algorithm and data-driven lithium battery health status evaluation method in any one of the above-described implementation manners.
The beneficial effects of adopting the above embodiment are: the lithium battery health state assessment method based on the optimization algorithm and the data driving combines the PSO algorithm and the LSTM algorithm, effectively combines the strong optimizing capability of the PSO algorithm and the predicting capability of the variable length sequence of the LSTM algorithm, provides a more effective method for lithium battery health state assessment, and can rapidly and accurately predict the health state of the lithium battery.
Drawings
Fig. 1 is a schematic view of a scenario of a lithium battery health status prediction apparatus according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of an embodiment of a lithium battery health state evaluation method based on an optimization algorithm and data driving according to the present invention;
FIG. 3 is a schematic flow chart illustrating PSO algorithm optimization according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a lithium battery health status prediction apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a lithium battery health state prediction device according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention provides a lithium battery health state evaluation method based on an optimization algorithm and data driving, which is respectively explained below.
Fig. 1 is a schematic view of a scenario of a lithium battery health status prediction apparatus according to an embodiment of the present invention, and the system may include a server 100, where the lithium battery health status prediction apparatus, such as the server in fig. 1, is integrated in the server 100.
In the embodiment of the present application, the server 100 is mainly used for:
establishing an initial PSO-LSTM model; acquiring characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into an initial PSO-LSTM model as input variables, and performing iterative training by taking the health condition of the battery as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model with complete training; and inputting the real-time data of the battery to be predicted into the target PSO-LSTM model to predict the health condition of the battery.
In this embodiment, the server 100 may be an independent server, or may be a server network or a server cluster composed of servers, for example, the server 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing).
It is to be understood that the terminal 200 used in the embodiments of the present application may be a device that includes both receiving and transmitting hardware, i.e., a device having receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display. The specific terminal 200 may be a desktop, a laptop, a web server, a Personal Digital Assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, and the like, and the type of the terminal 200 is not limited in this embodiment.
Those skilled in the art can understand that the application environment shown in fig. 1 is only one application scenario related to the present embodiment, and does not constitute a limitation on the application scenario of the present embodiment, and that other application environments may further include more or fewer terminals than those shown in fig. 1, for example, only 2 terminals are shown in fig. 1, and it can be understood that the lithium battery health status prediction apparatus may further include one or more other terminals, which is not limited herein.
In addition, referring to fig. 1, the lithium battery health predicting apparatus may further include a memory 300 for storing data, such as a real-time discharge voltage data set, a real-time discharge current data set, a real-time load voltage data set, a real-time load current data set, and the like.
It should be noted that the scenario diagram of the lithium battery health status prediction apparatus shown in fig. 1 is only an example, and the lithium battery health status prediction apparatus and the scenario described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not limit the technical solution provided in the embodiment of the present application.
Referring to fig. 2, fig. 2 is a schematic flow chart of an embodiment of a lithium battery health state evaluation method based on an optimization algorithm and data driving according to the present invention, and the lithium battery health state evaluation method based on an optimization algorithm and data driving according to the present invention includes:
s201, establishing an initial PSO-LSTM model;
s202, obtaining characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into an initial PSO-LSTM model as input variables, and performing iterative training by taking the health condition of the battery as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model with complete training;
s203, inputting the real-time data of the battery to be predicted into the target PSO-LSTM model, and predicting the health condition of the battery.
In step S201, the PSO-LSTM model is a long-short term memory network model optimized based on a particle swarm optimization algorithm, the embodiment of the present invention optimizes the long-short term memory network model by the particle swarm optimization algorithm so as to meet the prediction requirement, and the manner of establishing the LSTM model may adopt thano, tenorflow, and Keras, which are commonly used methods in the prior art, and the model establishment process thereof is not described herein.
In step S202, the model specification and the like of the sensor are not particularly limited in this embodiment, and only the data of the real-time discharge voltage, the real-time discharge current, the real-time load voltage and the real-time load current of the lithium battery needs to be acquired in real time, and then the data is input into the initial PSO-LSTM model, and the PSO-LSTM model is iteratively optimized and stopped when the maximum number of times is reached or the prediction accuracy is met, where the PSO-LSTM model at this time is the target PSO-LSTM model which is completely trained.
In step S203, after the PSO-LSTM model is optimized, a target PSO-LSTM model with complete training is obtained, the model may be put into practical use, and real-time data of the battery to be predicted is input to the target PSO-LSTM model, so as to predict the health condition of the lithium battery.
Compared with the prior art, the optimization algorithm and data-driven lithium battery health state assessment method provided by the embodiment combines the PSO algorithm and the LSTM algorithm, effectively combines the strong optimizing capability of the PSO algorithm and the prediction capability of the variable length sequence of the LSTM algorithm, provides a more effective method for lithium battery health state assessment, and can rapidly and accurately predict the health state of the lithium battery.
In some embodiments of the invention, establishing an initial PSO-LSTM model comprises:
generating LSTM network models of different network parameters;
and optimizing LSTM network models of different network parameters according to a PSO algorithm, and searching for the optimal network parameters.
In the above embodiment, the number of PSO populations is set to 10, that is, the PSO-LSTM model can generate 10 LSTM networks with different parameters at a time, the discharge voltage, the discharge current, the load voltage, and the load current are used as model inputs, the battery SOH value is used as a model output, the fitting degree is used as a model evaluation standard, and the fitting degree reaching 95% is set as an iteration end condition. It is understood that the number of PSO populations may also be set to 15, 20, or other suitable values, and the invention is not further limited herein. The LSTM network with different parameters mainly has different network layer numbers and node numbers of each layer in the neural network, and along with the continuous change of the two super parameters, the error value obtained by prediction every time also continuously changes, and through continuous optimization, the model with the highest precision is found, and the globally optimal network parameters are found.
Referring to fig. 3, fig. 3 is a schematic flow chart of an embodiment of PSO algorithm optimization provided in the present invention, in some embodiments of the present invention, the PSO algorithm includes:
s301, initializing the speed and position of each particle in the particle swarm;
s302, calculating the historical optimal position of the particle swarm population;
s303, updating the speed and the position of each particle in the particle swarm;
s304, updating the particles at the historical optimal positions in the particle swarm;
s305, mapping the position information of the particles with the historical optimal positions in the particle swarm to an LSTM network model, and optimizing parameters of the LSTM network model.
In step S301, the initial speed and position information of each particle in the particle swarm during generation may be greatly different from the optimization requirement, and the speed and position of the particle swarm need to be initialized first, where the initialization method is the prior art and is not described herein again.
In step S302, the generated LSTM networks with 10 different parameters are optimized, and the historical optimal positions of all the particles in the optimization process are calculated and found, that is, the global extremum of all the particles in the particle swarm in the current optimization process, and the optimal network parameters can be found more quickly through the values.
In step S303, the velocities and positions of all particles are updated based on the global extremum calculated in step S302, and then the optimization process is performed again.
In step S304, the best position found by a single particle in the population in the optimization process is calculated, and the particle is an individual extremum in the current optimization process, and the value is favorable for optimizing the parameters of the LSTM network model.
In step S305, the position information of the particles at the historical best positions in the particle group in step S304 is mapped to the LSTM network model, the parameters of the LSTM network model are optimized, and then it is checked whether the optimized error satisfies the condition.
In the above embodiment, the PSO algorithm is an intelligent optimization algorithm, which is derived from research on simulating predation behavior of a bird swarm, and its core idea is: the optimal solution is found through cooperation and information sharing among individuals in the group. Each particle in the population has two attributes of a speed v _ i and a position x _ i, in an iteration process, each particle finds an optimal solution of the particle, shares an individual optimum with other particles, finds the optimal solution in the population as a global optimum, and finally updates the speed and the position of the particle according to the global optimum and the individual optimum. The number of network layers and the number of nodes of the LSTM neural network can be optimized through the PSO algorithm, the LSTM network is dynamically optimized and improved, the LSTM neural network has better nonlinear function prediction capability, the service life prediction of a lithium battery can be met, and the prediction result error is small and the prediction speed is high.
In some embodiments of the present invention, the formula for updating the velocity and position of each particle in the population of particles is specifically:
the velocity update formula is:
vi＝vi+c1×r1×(pbesti-xi)+c2×r2×(gbesti-xi)，
the location update formula is:
xi＝xi+vi，
in the formula：c1，c2Is a learning factor, r1，r2Is [0,1 ]]Random number between, pbestiIs the historical best position of the particle, gbestiIs the historical best position of the population.
In the above embodiment, the speed and the position of the particles in the particle swarm are updated through the speed updating formula and the position updating formula, so that the number of network layers and the number of nodes of the LSTM neural network are quickly found out, and a quick optimization effect is achieved.
In some embodiments of the present invention, the characteristic parameters characterizing the performance of the lithium battery include a real-time discharge voltage, a real-time discharge current, a real-time load voltage, and a real-time load current of the lithium battery, the characteristic parameter data characterizing the performance of the battery are divided into a data training set and a data testing set, and the data training set and the data testing set each include a real-time discharge voltage data set, a real-time discharge current data set, a real-time load voltage data set, and a real-time load current data set.
In the above embodiment, the collected characteristic parameters characterizing the performance of the lithium battery are the real-time discharge voltage, the real-time discharge current, the real-time load voltage, and the real-time load current of the lithium battery. It can be understood that there are many characteristic parameters capable of characterizing the performance of the lithium battery, but the embodiment of the invention can predict the health condition of the lithium battery only by the real-time discharge voltage, the real-time discharge current, the real-time load voltage and the real-time load current of the lithium battery.
In some embodiments of the present invention, when the real-time discharge voltage data set is a real-time voltage data set at two ends of a load when the battery is externally connected to the load, the real-time discharge current data set is a real-time current data set at two ends of the load when the battery is externally connected to the load, the real-time load voltage data set is a real-time voltage data set at two ends of the battery when the battery is externally connected to the load, and the real-time load current data set is a real-time current data set at two ends of the battery when the battery is externally connected to the load.
In the above embodiment, three experiments of charging, discharging, and impedance are performed on the battery at room temperature by collecting characteristic parameters of the nasapcae 5 battery, in the experimental data, each cycle process is a battery discharging process, the collected characteristic parameters characterizing the performance of the lithium battery are battery data in the discharging process, every 10 consecutive cycle times are used to predict the next cycle time, the total cycle number of the No. 5 battery is 168, the number of samples is 157, the first 87 samples are selected as a training set, and the last 70 samples are selected as a test set for performing the experiment. It is understood that other types of lithium batteries may be selected for the experiment, and the signals and the number of the batteries are not particularly limited in the embodiment of the present invention. The battery is a load, the load voltage and the load current are the voltage and the current acting on the battery, the battery is connected with a load, and the current and the voltage of the load are the discharge current and the discharge voltage of the battery.
In some embodiments of the present invention, optimizing the transition LSTM network model by using a particle swarm optimization algorithm and determining whether the optimized model reaches a preset prediction accuracy or a preset iteration number specifically includes:
calculating the root mean square error of the prediction result:
calculate the mean absolute percentage error of the prediction:
calculating the fitness of the particle swarm algorithm:
wherein n is the total amount of the samples,
is a sample prediction value, yiFor the real value of the sample,
is the sample average.
In the embodiment, the lithium battery health condition prediction result is evaluated through the evaluation index, the root mean square error RMSE is evaluated according to the lithium ion battery capacity, is the square root of the ratio of the square sum of the deviation of the observed value and the true value of the battery capacity to the observation frequency n, is used for measuring the deviation between the predicted value and the actual value of the lithium ion battery capacity, and can better reflect the abnormal value in prediction. The average absolute percentage error MAPE is a statistical index for measuring the prediction accuracy, is a percentage value, and generally, when the MAPE is less than 10, the prediction accuracy is higher. Fitness coefficient r2Is used to evaluate how well the predicted value of SOH fits the true value. And judging whether the two parameters of the network layer number and the node number of the current LSTM neural network can meet the conditions according to the calculation result, and if not, repeating the PSO algorithm optimization process.
In order to better implement the lithium battery health status assessment method based on the optimization algorithm and the data driving in the embodiment of the present invention, on the basis of the lithium battery health status assessment method based on the optimization algorithm and the data driving, correspondingly, please refer to fig. 4, where fig. 4 is a schematic structural diagram of an embodiment of a lithium battery health status prediction apparatus provided in the present invention, an embodiment of the present invention provides a lithium battery health status prediction apparatus 400, including:
the modeling module 401 is used for establishing an initial PSO-LSTM model;
the training module 402 is used for acquiring characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into the initial PSO-LSTM model as input variables, and performing iterative training by taking the battery residual capacity as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model which is trained completely;
and the prediction module 403 is configured to input real-time data of the battery to be predicted into the target PSO-LSTM model, so as to predict the health condition of the battery.
Here, it should be noted that: the lithium battery health condition prediction apparatus 400 provided in the foregoing embodiment may implement the technical solutions described in the foregoing method embodiments, and the specific implementation principles of the modules or units may refer to the corresponding contents in the foregoing method embodiments, and are not described herein again.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a lithium battery health status prediction device according to an embodiment of the present invention. Based on the lithium battery health state assessment method based on the optimization algorithm and data driving, the invention also correspondingly provides lithium battery health state prediction equipment which can be computing equipment such as a mobile terminal, a desktop computer, a notebook computer, a palm computer, a server and the like. The lithium battery health prediction apparatus includes a processor 510, a memory 520, and a display 530. Fig. 5 shows only some of the components of the electronic device, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
The storage 520 may be an internal storage unit of the lithium battery health status prediction apparatus in some embodiments, for example, a hard disk or a memory of the lithium battery health status prediction apparatus. The memory 520 may also be an external storage device of the lithium battery health status predicting device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are equipped on the lithium battery health status predicting device. Further, the memory 520 may also include both an internal storage unit of the lithium battery health prediction apparatus and an external storage apparatus. The memory 520 is used for storing application software installed in the lithium battery health status prediction apparatus and various data, such as program codes installed in the lithium battery health status prediction apparatus. The memory 520 may also be used to temporarily store data that has been output or is to be output. In an embodiment, the memory 520 stores a lithium battery health status prediction program 540, and the lithium battery health status prediction program 540 can be executed by the processor 510, so as to implement the lithium battery health status evaluation method based on an optimization algorithm and data driving according to the embodiments of the present application.
The processor 510 may be, in some embodiments, a Central Processing Unit (CPU), a microprocessor or other data Processing chip, and is configured to execute program codes stored in the memory 1020 or process data, such as performing an optimization algorithm and a data-driven lithium battery health status evaluation method.
The display 530 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, and the like in some embodiments. The display 530 is used to display information on the lithium battery health prediction apparatus and to display a visual user interface. The components 510 and 530 of the lithium battery health status prediction device communicate with each other through a system bus.
In one embodiment, the steps of the above method for estimating the state of health of a lithium battery based on an optimization algorithm and data driving are implemented when the processor 510 executes the lithium battery state of health predicting program 540 in the memory 520.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are also included in the scope of the present invention.
Claims (10)
1. A lithium battery health state assessment method based on optimization algorithm and data driving is characterized by comprising the following steps:
establishing an initial PSO-LSTM model;
acquiring characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into the initial PSO-LSTM model as input variables, and performing iterative training by taking the health condition of the battery as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model with complete training;
and inputting real-time data of the battery to be predicted into the target PSO-LSTM model to predict the health condition of the battery.
2. The optimization algorithm and data-driven based lithium battery state of health assessment method according to claim 1, wherein said establishing an initial PSO-LSTM model comprises:
generating LSTM network models of different network parameters;
and optimizing the LSTM network models of the different network parameters according to the PSO algorithm, and searching for the optimal network parameters.
3. The optimization algorithm and data-driven based lithium battery state of health assessment method according to claim 2, wherein the PSO algorithm comprises:
initializing the speed and position of each particle in the particle swarm;
calculating the historical optimal position of the particle swarm population;
updating the velocity and position of each particle in the population of particles;
updating particles at historical optimal positions in the particle swarm;
and mapping the position information of the particles with the historical optimal positions in the particle swarm to an LSTM network model, and optimizing parameters of the LSTM network model.
4. The optimization algorithm and data drive based lithium battery health status evaluation method according to claim 3, wherein the formula for updating the speed and position of each particle in the particle swarm is specifically as follows:
the velocity update formula is:
vi＝vi+c1×r1×(pbesti-xi)+c2×r2×(gbesti-xi)，
the location update formula is:
xi＝xi+vi，
in the formula: c. C1，c2Is a learning factor, r1，r2Is [0,1 ]]Random number between, pbestiIs the historical best position of the particle, gbestiIs the historical best position of the population.
5. The optimization algorithm and data drive based lithium battery health status assessment method according to claim 1, wherein the characteristic parameters characterizing the performance of the lithium battery comprise a real-time discharge voltage, a real-time discharge current, a real-time load voltage and a real-time load current of the lithium battery, the characteristic parameter data characterizing the performance of the battery are divided into a data training set and a data testing set, and the data training set and the data testing set respectively comprise a real-time discharge voltage data set, a real-time discharge current data set, a real-time load voltage data set and a real-time load current data set.
6. The optimization algorithm and data drive based lithium battery health status assessment method according to claim 5, wherein the real-time discharge voltage data set is a real-time voltage data set at two ends of a load when the battery is externally connected with the load, the real-time discharge current data set is a real-time current data set at two ends of the load when the battery is externally connected with the load, the real-time load voltage data set is a real-time voltage data set at two ends of the battery when the battery is externally connected with the load, and the real-time load current data set is a real-time current data set at two ends of the battery when the battery is externally connected with the load.
7. The optimization algorithm and data-driven lithium battery health state assessment method according to claim 6, wherein the optimizing the transition LSTM network model by using the particle swarm optimization algorithm and determining whether the optimized model reaches a preset prediction precision or a preset iteration number specifically comprises:
calculating the root mean square error of the prediction result:
calculate the mean absolute percentage error of the prediction:
calculating the fitness of the particle swarm algorithm:
wherein n is the total amount of the samples,
is a sample prediction value, yiFor the real value of the sample,
is the sample average.
8. A lithium battery state of health prediction apparatus, comprising:
the modeling module is used for establishing an initial PSO-LSTM model;
the training module is used for acquiring characteristic parameters representing the performance of the lithium battery, inputting the characteristic parameters into the initial PSO-LSTM model as input variables, and performing iterative training by taking the battery residual capacity as the output of the initial PSO-LSTM model to obtain a target PSO-LSTM model which is trained completely;
and the prediction module is used for inputting the real-time data of the battery to be predicted into the target PSO-LSTM model and predicting the health condition of the battery.
9. An electronic device comprising a memory and a processor, wherein,
the memory is used for storing programs;
the processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps of the optimization algorithm and data-driven lithium battery health status evaluation method according to any one of claims 1 to 7.
10. A computer-readable storage medium for storing a computer-readable program or instructions, which when executed by a processor, can implement the steps of the optimization algorithm and data-driven lithium battery health status assessment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111007676.XA CN113671401A (en) | 2021-08-30 | 2021-08-30 | Lithium battery health state assessment method based on optimization algorithm and data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111007676.XA CN113671401A (en) | 2021-08-30 | 2021-08-30 | Lithium battery health state assessment method based on optimization algorithm and data driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113671401A true CN113671401A (en) | 2021-11-19 |
Family
ID=78547434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111007676.XA Pending CN113671401A (en) | 2021-08-30 | 2021-08-30 | Lithium battery health state assessment method based on optimization algorithm and data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113671401A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113030764A (en) * | 2021-03-04 | 2021-06-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN114545280A (en) * | 2022-02-24 | 2022-05-27 | 苏州市职业大学 | New energy automobile lithium battery life prediction method based on optimization algorithm |
| CN115219906A (en) * | 2022-06-27 | 2022-10-21 | 武汉理工大学 | Multi-model fusion battery state of charge prediction method and system based on GA-PSO optimization |
| CN116125279A (en) * | 2022-11-16 | 2023-05-16 | 广东电网有限责任公司 | Method, device, equipment and storage medium for determining battery health state |
| CN116400227A (en) * | 2023-06-08 | 2023-07-07 | 长安大学 | SOH prediction method, system, equipment and medium for power battery of electric automobile |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180143257A1 (en) * | 2016-11-21 | 2018-05-24 | Battelle Energy Alliance, Llc | Systems and methods for estimation and prediction of battery health and performance |
| CN111044928A (en) * | 2019-12-31 | 2020-04-21 | 福州大学 | Lithium battery health state estimation method |
| CN113030764A (en) * | 2021-03-04 | 2021-06-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN113156325A (en) * | 2021-03-18 | 2021-07-23 | 吉林大学 | Method for estimating state of health of battery |
| CN113253116A (en) * | 2021-05-18 | 2021-08-13 | 齐鲁工业大学 | Lithium ion battery state of charge estimation method and storage medium |
-
2021
- 2021-08-30 CN CN202111007676.XA patent/CN113671401A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180143257A1 (en) * | 2016-11-21 | 2018-05-24 | Battelle Energy Alliance, Llc | Systems and methods for estimation and prediction of battery health and performance |
| CN111044928A (en) * | 2019-12-31 | 2020-04-21 | 福州大学 | Lithium battery health state estimation method |
| CN113030764A (en) * | 2021-03-04 | 2021-06-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN113156325A (en) * | 2021-03-18 | 2021-07-23 | 吉林大学 | Method for estimating state of health of battery |
| CN113253116A (en) * | 2021-05-18 | 2021-08-13 | 齐鲁工业大学 | Lithium ion battery state of charge estimation method and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113030764A (en) * | 2021-03-04 | 2021-06-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN113030764B (en) * | 2021-03-04 | 2022-01-25 | 武汉大学 | Battery pack health state estimation method and system |
| CN114545280A (en) * | 2022-02-24 | 2022-05-27 | 苏州市职业大学 | New energy automobile lithium battery life prediction method based on optimization algorithm |
| CN114545280B (en) * | 2022-02-24 | 2022-11-15 | 苏州市职业大学 | New energy automobile lithium battery life prediction method based on optimization algorithm |
| CN115219906A (en) * | 2022-06-27 | 2022-10-21 | 武汉理工大学 | Multi-model fusion battery state of charge prediction method and system based on GA-PSO optimization |
| CN116125279A (en) * | 2022-11-16 | 2023-05-16 | 广东电网有限责任公司 | Method, device, equipment and storage medium for determining battery health state |
| CN116400227A (en) * | 2023-06-08 | 2023-07-07 | 长安大学 | SOH prediction method, system, equipment and medium for power battery of electric automobile |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113671401A (en) | Lithium battery health state assessment method based on optimization algorithm and data driving | |
| CN113589189B (en) | Lithium battery health condition prediction method and device based on charging and discharging data characteristics | |
| CN113671381A (en) | Lithium ion power battery estimation method based on time convolution network | |
| US20220130495A1 (en) | Method and Device for Determining Correlation Between Drug and Target, and Electronic Device | |
| CN112000893A (en) | Resident area prediction method, resident area prediction device, resident area prediction equipment and storage medium | |
| CN114781273A (en) | SOA-LSTM-based battery residual life prediction method and device | |
| Doppa et al. | Autonomous design space exploration of computing systems for sustainability: Opportunities and challenges | |
| Ma et al. | State of health prediction of lithium-ion batteries under early partial data based on IWOA-BiLSTM with single feature | |
| CN116500449A (en) | Cell temperature prediction method and device, storage medium and electronic equipment | |
| CN116125279A (en) | Method, device, equipment and storage medium for determining battery health state | |
| CN116050250A (en) | Power grid digital twin model modeling method and device based on hybrid driving model | |
| CN117892667B (en) | Method for setting arithmetic unit chip, computing subsystem and intelligent computing platform | |
| CN118259923A (en) | Micro-service self-adaptive deployment method and device, computer equipment and storage medium | |
| CN117031292A (en) | Battery health state prediction method, device, computer equipment and storage medium | |
| Zhang et al. | A model-data-fusion method for real-time continuous remaining useful life prediction of lithium batteries | |
| CN113933718B (en) | Retired battery capacity sorting method, retired battery capacity sorting device, retired battery capacity sorting equipment and storage medium | |
| KR20210016828A (en) | Battery management apparatus, battery management metohd and battery pack | |
| CN117092510A (en) | Battery operation simulation method, device and system | |
| CN113344435B (en) | Platform power supply state evaluation device, electronic equipment and storage medium | |
| CN115951236A (en) | Lithium battery state monitoring method, system, device and storage medium | |
| CN116224126A (en) | Method and system for estimating health state of lithium ion battery of electric automobile | |
| CN115438588A (en) | Temperature prediction method, system, equipment and storage medium of lithium battery | |
| CN114565172A (en) | Method for building battery residual life prediction model and predicting battery residual life | |
| CN115760074A (en) | Power equipment operation and maintenance method and device, computer equipment and storage medium | |
| CN112632846A (en) | Power transmission section limit probability evaluation method of power system and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211119 |