CN109800485A - Power battery module light weight method, equipment and maximum stress value calculating method - Google Patents
Power battery module light weight method, equipment and maximum stress value calculating method Download PDFInfo
- Publication number
- CN109800485A CN109800485A CN201811653720.2A CN201811653720A CN109800485A CN 109800485 A CN109800485 A CN 109800485A CN 201811653720 A CN201811653720 A CN 201811653720A CN 109800485 A CN109800485 A CN 109800485A
- Authority
- CN
- China
- Prior art keywords
- power battery
- neural network
- battery module
- maximum stress
- stress value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000013461 design Methods 0.000 claims abstract description 72
- 238000013528 artificial neural network Methods 0.000 claims abstract description 54
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 230000002068 genetic effect Effects 0.000 claims abstract description 9
- 238000003062 neural network model Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000009395 breeding Methods 0.000 claims description 6
- 230000001488 breeding effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 239000013585 weight reducing agent Substances 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000003014 reinforcing effect Effects 0.000 claims 2
- 238000007796 conventional method Methods 0.000 abstract 1
- 239000003351 stiffener Substances 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Landscapes
- Battery Mounting, Suspending (AREA)
Abstract
The invention discloses a kind of power battery pack light weight methods neural network based, comprising the following steps: determines the first restriction range of design variable and the second restriction range of maximum stress value；Variable sample set is obtained, includes several design variable combinations for meeting the first restriction range in variable sample set, design variable combination includes multiple design variables relevant to the stress value of power battery module；Design variable, which is calculated, according to neural network approximate model combines corresponding maximum stress value and battery modules weight；Using battery modules weight as target, the combination of optimal design variable is calculated according to genetic algorithm.The present invention takes the method for solving that artificial neural network and genetic algorithms combine, and avoids the problem of conventional method is easily trapped into locally optimal solution, and can quickly calculate power battery pack maximum stress value.The invention also discloses a kind of power battery module maximum stress value calculating methods neural network based.
Description
Technical Field
The invention relates to design and calculation of a power battery module, in particular to calculation of a maximum stress value of the power battery module and determination of design variables in the power battery module.
Background
The power battery module is used as an important component of a new energy vehicle, the weight of the power battery module is reduced, the mechanical property of the material is fully utilized, and the improvement of the energy density of the module is the aim of research.
At present, the strength of the lightweight power module is mostly verified by a physical model or computer simulation, and each model is gradually verified by adopting an exhaustion method, so that the power battery module model with light weight and strength meeting the requirements is selected. The method for carrying out light weight by an exhaustion method possibly falls into the problem of local optimal solution, a model with strength meeting requirements and the smallest weight is difficult to find, and the method has the problems of time consumption and labor consumption, so that the research and development speed is greatly reduced.
In order to solve the problem, the invention introduces a neural network model, utilizes the strong nonlinear fitting capability of the neural network to save the time for lightening the power battery module, improves the capability of searching a global optimal module model and improves the development efficiency.
Disclosure of Invention
The invention aims to provide a power battery module design method and a maximum stress value calculation method, which utilize strong nonlinear fitting capability of a neural network to quickly calculate the maximum stress value of a power battery pack, so that a power battery module with proper stress and the lightest weight can be quickly selected, and the time for lightening the power battery module is saved.
Another object of the present invention is to provide an electronic device and a computer-readable storage medium corresponding to the power battery module design method and the maximum stress value calculation method.
In order to achieve the purpose, the invention discloses a method for calculating the maximum stress value of a power battery module based on a neural network, which comprises the following steps of: obtaining a trained neural network approximate model, inputting a design variable combination into the trained neural network approximate model to obtain a maximum stress value, wherein the design variable combination comprises a plurality of design variables related to the stress value of the power battery module; the method for obtaining the trained neural network approximate model comprises the following steps of: (1) determining the design variable combination; (2) establishing a neural network model with the maximum stress value of the power battery pack and the weight of the power battery pack as output values and the design variable combination as input values to obtain a database of the power battery module, wherein the database comprises a plurality of design variable combinations, the corresponding weight of the power battery pack and the maximum stress value of the power battery module under a plurality of working conditions; (3) and importing the data in the database into the neural network model by adopting an error back propagation learning algorithm, combining design variables as input variables, and training the neural network model by taking the corresponding weight of the power battery pack and the maximum stress value as output values to obtain a trained neural network approximate model.
The method utilizes strong nonlinear fitting capability of the neural network to quickly calculate the maximum stress value of the power battery pack, and is different from the method obtained by solving with finite element analysis software (such as ANSYS) in the prior art, so that the finite element analysis software needs to be repeatedly called when the lightweight design is carried out.
Preferably, the design variable combination is the thickness of each portion of the power battery pack housing.
Specifically, the design variable combination includes module curb plate thickness, end plate thickness, the first strengthening rib thickness of end plate, end plate second strengthening rib thickness.
Preferably, in the step (2), the step of obtaining the database of the power battery module includes: determining a first constraint range of design variables and a second constraint range of maximum stress values; obtaining a learning sample set, wherein the learning sample set comprises a plurality of design variable combinations conforming to a first constraint range; establishing a power battery module finite element model, calculating the sample set one by using finite element analysis software to obtain stress values and power battery pack weight under multiple working conditions, counting the maximum stress value, and recording each design variable combination and the corresponding maximum stress value and power battery pack weight to obtain the database.
Preferably, the neural network model includes an input layer, one or more hidden layers and an output layer, the number of nodes in the input layer is m, the number of nodes in the output layer is n, m is the number of input variables, m is the number of output values, a theoretical hidden layer node number L is calculated according to the number of nodes in the input layer being m and the number of nodes in the output layer being n, each integer from L-t1 to L + t2 is subjected to a numerical test to select one of the integers as an actual node number I of the hidden layer, and t1 and t2 are preset values.
Wherein,wherein a, b, c, d, e and f are all preset constants.
Preferably, when the error back propagation learning algorithm is adopted to introduce the data in the database into the neural network model, the iteration times of the algorithm are controlled by a mean square error function, and when an expected mean square error is met, the neural network model terminates iteration to obtain a trained neural network approximate model.
The invention also discloses a power battery pack lightweight method based on the neural network, which comprises the following steps: determining a first constraint range of design variables and a second constraint range of maximum stress values; obtaining a variable sample set, wherein the variable sample set comprises a plurality of design variable combinations which accord with a first constraint range, and the design variable combinations comprise a plurality of design variables related to stress values of the power battery module; calculating the maximum stress value and the weight of the battery module corresponding to the design variable combination according to the calculation method of the maximum stress value of the power battery module based on the neural network; and calculating to obtain the optimal design variable combination which accords with the first constraint range and the second constraint range according to a genetic algorithm by taking the weight of the battery module as a target.
The method is different from the defect that the traditional optimization method needs objective function gradient information, adopts a solving method combining a neural network and a genetic algorithm, fully utilizes the global mapping capability of the neural network, avoids the problem that the traditional method is easy to fall into a local optimal solution, uses strong nonlinear fitting capability of the neural network, quickly calculates the maximum stress value of the power battery pack, can quickly select the power battery module with proper stress and the lightest weight, and saves the time for lightening the power battery module.
Preferably, the step of calculating and obtaining the optimal design variable combination conforming to the first constraint range and the second constraint range according to the genetic algorithm with the weight of the battery module as the target comprises: performing group initialization on the variable sample set to generate a preset number of first generation groups, calculating a maximum stress value and battery module weight corresponding to the first generation groups according to the maximum stress value calculation method of the power battery module based on the neural network, and counting group fitness values; performing offspring breeding on the u generation population from the first generation population to generate a u +1 generation population, calculating the maximum stress value and the weight of the battery module corresponding to the first generation population according to the maximum stress value calculation method of the power battery module based on the neural network, and counting population fitness values until the population fitness value corresponding to the u +1 generation population and the population fitness corresponding to the u belt population are less than a preset value, and terminating population breeding; performing code conversion on the individual with the maximum group fitness value in the last generation group to obtain the optimal design variable combination; the group fitness value corresponds to the weight of the minimum battery module in the group, and the individual with the maximum group fitness value is the individual with the minimum weight of the battery module.
The invention also discloses an electronic device, comprising one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the programs comprising instructions for performing the neural network-based power cell module maximum stress value calculation method as described above.
Of course, the program may also be used to perform the neural network-based power battery pack weight reduction method as described above.
The invention also discloses a computer readable storage medium comprising a computer program for use in conjunction with an electronic device having a memory, the computer program being executable by a processor for performing the method for calculating a maximum stress value of a neural network based power battery module or the method for lightening a neural network based power battery module as described above.
Drawings
Fig. 1 is a schematic structural view of a power battery pack case.
Fig. 2 is a schematic structural diagram of the neural network model according to the present invention.
FIG. 3 is a flow chart of the neural network-based power battery pack weight reduction method of the present invention.
FIG. 4 is a flow chart of a method for obtaining a trained neural network approximation model according to the present invention.
Detailed Description
In order to explain technical contents, structural features, and objects and effects of the present invention in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 3, the invention discloses a power battery pack weight reduction method 10 based on a neural network, comprising the following steps: (11) determining a first constraint range of design variables and a second constraint range of maximum stress values; (12) obtaining a variable sample set, wherein the variable sample set comprises a plurality of design variable combinations meeting a first constraint range, and the design variable combinations comprise a plurality of design variables related to the stress value of the power battery pack; (13) calculating the maximum stress value and the weight of the battery module corresponding to the design variable combination according to a maximum stress value calculation method of the power battery module based on a neural network; (14) and calculating to obtain an optimal design variable combination which accords with a first constraint range and a second constraint range according to a genetic algorithm by taking the weight of the battery module as a target, wherein each design variable in the design variable combination accords with the first constraint range, and the corresponding maximum stress value accords with the design variable combination of the second constraint range.
Wherein the design variable is the thickness of each portion of the power battery pack case 100. Referring to fig. 1, the design variable set includes the thickness of the module side plate 101, the thickness of the end plate 102, the thickness of the end plate first stiffener 103, and the thickness of the end plate second stiffener 104.
Referring to fig. 3, the step (13) specifically includes: (31) obtaining a trained neural network approximate model, (32) inputting a design variable combination into the trained neural network approximate model to obtain a maximum stress value, wherein the design variable combination comprises a plurality of design variables related to the stress value of the power battery module. Specifically, referring to fig. 4, "obtaining a trained neural network approximation model" includes the following steps: (311) determining a design variable combination; (312) establishing a neural network model taking the maximum stress value of the power battery pack and the weight of the power battery pack as output values, and taking the design variable combination as an input value, (313) obtaining a database of the power battery module, wherein the database comprises the design variable combination, the corresponding weight of the power battery pack and the maximum stress value of the power battery module under a plurality of working conditions; (314) and importing the data in the database into the neural network model by adopting an error back propagation learning algorithm, combining design variables as a plurality of input variables, and training the neural network model by taking the corresponding weight of the power battery pack and the maximum stress value as output values, thereby obtaining a trained neural network model, namely a neural network approximate model. When the data in the database is imported into the neural network model by adopting an error back propagation learning algorithm, the iteration times of the algorithm are controlled by a mean square error function, and when the expected mean square error is met, the neural network model terminates iteration to obtain a trained neural network approximate model.
In the step (313), the step of obtaining the database of the power battery module comprises: the learning sample set is obtained, a power battery module finite element model is established, the sample set is calculated one by using finite element analysis software to obtain stress values and power battery pack weight under multiple working conditions, the maximum stress value is counted, and each design variable combination and the corresponding maximum stress value and power battery pack weight are recorded to obtain the database. In this embodiment, the finite element analysis software is ANSYS software. Of course, finite element analysis can be performed by other methods to obtain the stress value, and the calculation of the specific stress value belongs to the prior art and is not described in detail herein.
Referring to fig. 2, the neural network model includes an input layer 201, one or more hidden layers 202 and an output layer 203, where the number of nodes in the input layer is m, the number of nodes in the output layer is n, m is the number of input variables, m is the number of output values, a theoretical hidden layer node number L is calculated according to the number of nodes in the input layer is m and the number of nodes in the output layer is n, a numerical test is performed on each integer from L-t1 to L + t2 to select one of the integers as an actual node number I of the hidden layer, and t1 and t2 are preset values.
Preferably, the first and second substrates are selected from the group consisting of,wherein a, b, c, d, e and f are all preset constants. In particular, the amount of the solvent to be used,
in this embodiment, m is 4, n is 2, and L is 5, so an empirical formula and addition/subtraction are combined, and numerical tests are performed on the number of neurons in the hidden layer at 4, 5, 6, and 7, for example, 5 is selected as a reasonable parameter for the actual node number I of the hidden layer.
The step (14) of calculating the optimal design variable combination according to the genetic algorithm with the weight of the battery module as the target comprises the following steps: performing group initialization on the variable sample set to generate a preset number of first generation groups, calculating a maximum stress value and battery module weight corresponding to the first generation groups according to the maximum stress value calculation method of the power battery module based on the neural network, and counting group fitness values; performing offspring breeding on the u generation population from the first generation population to generate a u +1 generation population, calculating the maximum stress value and the weight of the battery module corresponding to the first generation population according to the maximum stress value calculation method of the power battery module based on the neural network, and counting population fitness values until the population fitness value corresponding to the u +1 generation population and the population fitness corresponding to the u belt population are less than a preset value, and terminating population breeding; performing code conversion on the individual with the maximum group fitness value in the last generation group to obtain the optimal design variable combination; the group fitness value corresponds to the weight of the minimum battery module in the group, and the individual with the maximum group fitness value is the individual with the minimum weight of the battery module. u ∈ 1, 2, 3, 4, 5 …, and the like are integers equal to or greater than 1.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the scope of the present invention, therefore, the present invention is not limited by the appended claims.
Claims (11)
1. A method for calculating the maximum stress value of a power battery module based on a neural network is characterized by comprising the following steps: the method comprises the following steps: obtaining a trained neural network approximate model, inputting a design variable combination into the trained neural network approximate model to obtain a maximum stress value, wherein the design variable combination comprises a plurality of design variables related to the stress value of the power battery module; wherein,
the method for obtaining the trained neural network approximate model comprises the following steps:
(1) determining the design variable combination;
(2) establishing a neural network model with the maximum stress value of the power battery pack and the weight of the power battery pack as output values and the design variable combination as input values to obtain a database of the power battery module, wherein the database comprises a plurality of design variable combinations, the corresponding weight of the power battery pack and the maximum stress value of the power battery module under a plurality of working conditions;
(3) and importing the data in the database into the neural network model by adopting an error back propagation learning algorithm, combining design variables as input variables, and training the neural network model by taking the corresponding weight of the power battery pack and the maximum stress value as output values to obtain a trained neural network approximate model.
2. The method for calculating the maximum stress value of the power battery module based on the neural network as claimed in claim 1, wherein: the design variable combination is the thickness of each portion of the power battery pack housing.
3. The method for calculating the maximum stress value of the power battery module based on the neural network as claimed in claim 2, wherein: the design variable combination comprises the thickness of a module side plate, the thickness of an end plate, the thickness of a first reinforcing rib of the end plate and the thickness of a second reinforcing rib of the end plate.
4. The method for calculating the maximum stress value of the power battery module based on the neural network as claimed in claim 1, wherein: in the step (2), the step of obtaining the database of the power battery module includes:
determining a first constraint range of design variables and a second constraint range of maximum stress values;
obtaining a learning sample set, wherein the learning sample set comprises a plurality of design variable combinations conforming to a first constraint range;
establishing a power battery module finite element model, calculating the sample set one by using finite element analysis software to obtain stress values and power battery pack weight under multiple working conditions, counting the maximum stress value, and recording each design variable combination and the corresponding maximum stress value and power battery pack weight to obtain the database.
5. The method for calculating the maximum stress value of the power battery module based on the neural network as claimed in claim 1, wherein: the neural network model comprises an input layer, one or more hidden layers and an output layer, wherein the number of nodes of the input layer is m, the number of nodes of the output layer is n, m is the number of input variables, m is the number of output values, the number L of the theoretical hidden layers is calculated according to the number of the nodes of the input layer which is m and the number of the nodes of the output layer which is n, each integer from L-t1 to L + t2 is subjected to numerical test to select one of the integers as the actual number I of the nodes of the hidden layers, and t1 and t2 are preset values.
6. The method for calculating the maximum stress value of the power battery module based on the neural network as claimed in claim 5, wherein:wherein a, b, c, d, e and f are all preset constants.
7. The method for calculating the maximum stress value of the power battery module based on the neural network as claimed in claim 1, wherein: and when the error back propagation learning algorithm is adopted to lead the data in the database into the neural network model, the iteration times of the algorithm are controlled through a mean square error function, and when the expected mean square error is met, the neural network model stops iteration to obtain a trained neural network approximate model.
8. A power battery pack lightweight method based on a neural network is characterized by comprising the following steps: the method comprises the following steps:
determining a first constraint range of design variables and a second constraint range of maximum stress values;
obtaining a variable sample set, wherein the variable sample set comprises a plurality of design variable combinations which accord with a first constraint range, and the design variable combinations comprise a plurality of design variables related to stress values of the power battery module;
calculating the maximum stress value and the battery module weight corresponding to the design variable combination according to the calculation method of the maximum stress value of the neural network-based power battery module according to any one of claims 1 to 7;
and calculating to obtain the optimal design variable combination which accords with the first constraint range and the second constraint range according to a genetic algorithm by taking the weight of the battery module as a target.
9. The neural network-based power battery pack weight reduction method according to claim 8, characterized in that: the method comprises the following steps of calculating and obtaining the optimal design variable combination which accords with a first constraint range and a second constraint range according to a genetic algorithm by taking the weight of the battery module as a target:
performing group initialization on the variable sample set to generate a preset number of first generation groups, calculating a maximum stress value and battery module weight corresponding to the first generation groups according to the maximum stress value calculation method of the power battery module based on the neural network, and counting group fitness values;
performing offspring breeding on a u generation population from the first generation population to generate a u +1 generation population, calculating a maximum stress value and battery module weight corresponding to the first generation population according to the maximum stress value calculation method of the power battery module based on the neural network, and counting population fitness values until the population fitness value corresponding to the u +1 generation population and the population fitness corresponding to the u belt population are less than a preset value, terminating population breeding, wherein u is an integer greater than or equal to 1;
performing code conversion on the individual with the maximum group fitness value in the last generation group to obtain the optimal design variable combination;
the group fitness value corresponds to the weight of the minimum battery module in the group, and the individual with the maximum group fitness value is the individual with the minimum weight of the battery module.
10. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the programs comprising instructions for performing the neural network-based power cell module maximum stress value calculation method of any one of claims 1-7.
11. A computer readable storage medium comprising a computer program for use in conjunction with an electronic device having a memory, characterized in that: the computer program is executable by a processor to perform the method for calculating the maximum stress value of a neural network-based power battery module according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811653720.2A CN109800485A (en) | 2018-12-29 | 2018-12-29 | Power battery module light weight method, equipment and maximum stress value calculating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811653720.2A CN109800485A (en) | 2018-12-29 | 2018-12-29 | Power battery module light weight method, equipment and maximum stress value calculating method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109800485A true CN109800485A (en) | 2019-05-24 |
Family
ID=66558372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811653720.2A Pending CN109800485A (en) | 2018-12-29 | 2018-12-29 | Power battery module light weight method, equipment and maximum stress value calculating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109800485A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521456A (en) * | 2011-12-15 | 2012-06-27 | 河海大学常州校区 | Optimal design method of arched girder based on neural network and genetic algorithm |
| CN105574300A (en) * | 2016-02-24 | 2016-05-11 | 武汉理工大学 | Optimum design method for steel rail weld seam finish-milling machine tool beam body based on BP neural network and genetic algorithm |
| CN106202731A (en) * | 2016-07-12 | 2016-12-07 | 南京理工大学 | Bridge crane multi-flexibl e dynamics structural optimization method |
| CN106919767A (en) * | 2017-03-09 | 2017-07-04 | 江铃汽车股份有限公司 | Automobile body-in-white lightweight analysis method |
| CN106934087A (en) * | 2015-12-31 | 2017-07-07 | 上海汽轮机厂有限公司 | The Optimization Design of the root of blade of turbomachinery and the molded line of rotor groove |
-
2018
- 2018-12-29 CN CN201811653720.2A patent/CN109800485A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521456A (en) * | 2011-12-15 | 2012-06-27 | 河海大学常州校区 | Optimal design method of arched girder based on neural network and genetic algorithm |
| CN106934087A (en) * | 2015-12-31 | 2017-07-07 | 上海汽轮机厂有限公司 | The Optimization Design of the root of blade of turbomachinery and the molded line of rotor groove |
| CN105574300A (en) * | 2016-02-24 | 2016-05-11 | 武汉理工大学 | Optimum design method for steel rail weld seam finish-milling machine tool beam body based on BP neural network and genetic algorithm |
| CN106202731A (en) * | 2016-07-12 | 2016-12-07 | 南京理工大学 | Bridge crane multi-flexibl e dynamics structural optimization method |
| CN106919767A (en) * | 2017-03-09 | 2017-07-04 | 江铃汽车股份有限公司 | Automobile body-in-white lightweight analysis method |
Non-Patent Citations (1)
| Title |
|---|
| 钟诗胜 等: "《中国核科学技术发展进展报告 第5卷：中国核学会2017年学术年会论文集 第10册 核测试与分析 核安全》", 北京：国防工业出版社, pages: 101 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860982A (en) | Wind power plant short-term wind power prediction method based on VMD-FCM-GRU | |
| CN110427654B (en) | Landslide prediction model construction method and system based on sensitive state | |
| CN110909926A (en) | TCN-LSTM-based solar photovoltaic power generation prediction method | |
| CN109978283B (en) | Photovoltaic power generation power prediction method based on branch evolution neural network | |
| CN111027732B (en) | Method and system for generating multi-wind power plant output scene | |
| CN113064093A (en) | Energy storage battery state of charge and state of health joint estimation method and system | |
| Zhang et al. | Wind speed prediction research considering wind speed ramp and residual distribution | |
| CN111144644B (en) | Short-term wind speed prediction method based on variation variance Gaussian process regression | |
| CN111931983B (en) | Precipitation prediction method and system | |
| CN110991721A (en) | Short-term wind speed prediction method based on improved empirical mode decomposition and support vector machine | |
| CN112884236B (en) | Short-term load prediction method and system based on VDM decomposition and LSTM improvement | |
| CN116644970A (en) | Photovoltaic power prediction method based on VMD decomposition and lamination deep learning | |
| CN114418180B (en) | Ultra-short-term prediction method and device for wind power and storage medium | |
| CN114462718A (en) | CNN-GRU wind power prediction method based on time sliding window | |
| CN114139783A (en) | Wind power short-term power prediction method and device based on nonlinear weighted combination | |
| CN116599050A (en) | Photovoltaic prediction method and related device based on self-attention mechanism | |
| CN116777039A (en) | Double-layer neural network wind speed prediction method based on training set segmentation and error correction | |
| CN110611334A (en) | Copula-garch model-based multi-wind-farm output correlation method | |
| CN113673788A (en) | Photovoltaic power generation power prediction method based on decomposition error correction and deep learning | |
| CN117217591A (en) | Method and system for predicting photovoltaic power generation power | |
| CN110532057B (en) | Method for predicting resource usage amount of container | |
| CN109459609B (en) | Distributed power supply frequency detection method based on artificial neural network | |
| CN109800485A (en) | Power battery module light weight method, equipment and maximum stress value calculating method | |
| CN115545164A (en) | Photovoltaic power generation power prediction method, system, equipment and medium | |
| CN116011071A (en) | Method and system for analyzing structural reliability of air building machine based on active learning |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220210 Address after: 215500 No. 68, Xin'anjiang Road, Southeast street, Changshu, Suzhou, Jiangsu Applicant after: Jiangsu Zenergy Battery Technologies Co.,ltd Address before: 210000 249 Lantian Road, Airport Economic Development Zone, Jiangning District, Nanjing City, Jiangsu Province Applicant before: JIANGSU TAFEL NEW ENERGY TECHNOLOGY Co.,Ltd. Applicant before: DONGGUAN TAFEL NEW ENERGY TECHNOLOGY Co.,Ltd. Applicant before: SHENZHEN TAFEL NEW ENERGY TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |
|
| RJ01 | Rejection of invention patent application after publication |