CN115294745A - Lithium battery thermal runaway layering early warning method based on neural network and data difference - Google Patents
Lithium battery thermal runaway layering early warning method based on neural network and data difference Download PDFInfo
- Publication number
- CN115294745A CN115294745A CN202210562350.1A CN202210562350A CN115294745A CN 115294745 A CN115294745 A CN 115294745A CN 202210562350 A CN202210562350 A CN 202210562350A CN 115294745 A CN115294745 A CN 115294745A
- Authority
- CN
- China
- Prior art keywords
- sampling
- neural network
- signal
- precision
- early warning
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
- G08B29/186—Fuzzy logic; neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a lithium battery thermal runaway layered early warning method based on a neural network and data difference, belongs to the technical field of battery fire fighting, and aims to improve the prediction prevention effect while reducing prediction lag through correcting low-fidelity data and difference prediction by the neural network, thereby having better popularization value.
Description
Technical Field
The invention relates to the technical field of battery fire fighting, in particular to a lithium battery thermal runaway layered early warning method based on a neural network and data difference.
Background
The early warning of the thermal runaway of the new energy battery is an important defense line for the safety of new energy battery driving equipment, and is an effective way for reducing life and property losses caused by fire. In the process of firing a new energy battery, chemical reaction still occurs inside the battery, possibly resulting in a domino effect, and the traditional early warning difficulty is high; the smoke sensor can be used for effectively carrying out early warning on thermal runaway of the lithium battery and taking measures to prevent fire. The prediction of thermal runaway in the prior art usually has great hysteresis, and the prediction and prevention effect on the thermal runaway is poor.
Disclosure of Invention
In order to solve the problems in the prior art, the application provides a lithium battery thermal runaway layering early warning method based on a neural network and data difference, and aims to reduce prediction lag and improve prediction prevention effect.
In order to realize the purpose, the invention adopts the following technical scheme:
a lithium battery thermal runaway layering early warning method based on a neural network and data difference at least comprises the following steps: the signal sampling device can acquire an induction signal representing the thermal runaway of the battery and comprises two sampling modes of low sampling frequency, high sampling precision and high sampling frequency and low sampling precision;
the central processing unit device can perform neural network processing according to the induction signal representing the thermal runaway of the battery, predict and obtain a future sampling value, perform differential processing on the predicted future sampling value, determine a risk grade according to the magnitude of the differential value, and output an execution signal related to the risk grade; and
the alarm device can receive the execution signal and respond to the execution signal to give an alarm prompt;
the early warning method at least comprises the following steps:
s1, signal acquisition is carried out by using a signal sampling device;
s2, the central processing unit device determines a risk level according to the induction signal acquired by the signal acquisition device and adjusts a sampling mode according to the risk level;
and S3, when the risk level meets the preset level requirement, outputting an execution signal related to the risk level by the central processing unit, and giving an alarm prompt by using the alarm device.
Preferably, in step S1, a low sampling frequency and high sampling precision mode is used for signal acquisition;
the step S2 specifically comprises the steps that after sampling values are obtained from a signal sampling device, a neural network is used for predicting future sampling values with equal time intervals for several times, then differential calculation is carried out on the predicted sampling values for several times, when the differential value is higher than a set first threshold value, the risk level is determined to be in a second level, the sampling mode of the sampling device is adjusted to be a high-sampling-frequency low-sampling-precision mode, otherwise, the risk level is still in the first level, and the signal sampling device still adopts the low-sampling-frequency high-sampling-precision mode to carry out signal acquisition; after entering a high sampling frequency and low sampling precision mode, carrying out neural network fitting on the collected low-precision sequence, carrying out precision improvement processing, taking the current data after the precision improvement processing and the previous high-precision data as the input of neural network subsequent sequence prediction, predicting a sampling value sequence at a certain time interval in the future, carrying out differential calculation, and determining that the risk level is three when the differential value is higher than a second threshold value;
and S3, specifically, when the central processing unit determines that the risk level is three-level, the central processing unit outputs an execution signal, and an alarm device is used for giving an alarm prompt.
Preferably, the difference calculation used comprises forward difference, backward difference, end-of-fit derivation, or a combination thereof.
Compared with the prior art, the invention at least has the following beneficial effects:
1. the hierarchical control system enters different stages and dynamically adjusts the power consumption and the precision of the measurement system;
2. the neural network is used for predicting the data under the high sampling frequency after once correcting the data under the high sampling frequency and the data under the low sampling frequency, so that the data is fully utilized, the sampling signal-to-noise ratio is improved, and a theoretical basis is laid for a layering system taking a differential calculation result as a layering basis;
3. differential calculation is used as a layering control basis, so that a good prediction effect is achieved on rapid thermal runaway change of the lithium battery;
4. based on the fundamental contradiction that the indexes of sampling frequency and sampling precision can not be improved at the same time in the traditional data, the signal to noise ratio of the data is improved by using the simple neural network, the high-frequency noise of the signal is reduced, the contradiction between the sampling frequency and the sampling precision is relieved, and meanwhile, the difference calculation result for carrying out layered early warning is not excessively interfered by the high-frequency noise, so that the accuracy rate of using the difference as the layered index is greatly improved. In addition, two sensors may be used to sense data simultaneously, using two different frequencies for sampling, so that the predicted curve has the highest accuracy.
Drawings
The invention will be described in more detail hereinafter on the basis of embodiments and with reference to the accompanying drawings. Wherein:
FIG. 1 is a schematic diagram of the difference calculation after fitting of the neural network of the present invention;
FIG. 2 is a schematic of the initial sampling results of the present invention;
FIG. 3 is a schematic diagram of the fitting result of the neural network of the present invention with original sampling points retained;
FIG. 4 is a schematic diagram of the fitting result of the neural network without the original sampling point according to the present invention;
FIG. 5 is a schematic diagram of the fitting results of a neural network without a second optimization using the neural network according to the present invention;
FIG. 6 is a pre-and post-comparison graph of the fitting results of a neural network optimized for secondary use in accordance with the present invention;
FIG. 7 is a schematic diagram of a neural network architecture employed by the present invention;
in the drawings, like parts are provided with like reference numerals. The drawings are not to scale.
Detailed Description
The invention will be further explained with reference to the drawings.
The invention provides a lithium battery thermal runaway layered early warning method based on a neural network and data difference, which adopts an early warning system at least comprising the following steps:
the signal sampling device can acquire an induction signal representing the thermal runaway of the battery and comprises two sampling modes of low sampling frequency, high sampling precision and high sampling frequency and low sampling precision;
the central processing unit device can perform neural network processing according to the induction signal representing the thermal runaway of the battery, predict and obtain a future sampling value, perform differential processing on the predicted future sampling value, determine a risk grade according to the magnitude of the differential value, and output an execution signal related to the risk grade; and
the alarm device can receive the execution signal and respond to the execution signal to give an alarm prompt;
the early warning method at least comprises the following steps:
s1, signal acquisition is carried out by using a signal sampling device;
s2, the central processing unit device determines a risk level according to the induction signal acquired by the signal acquisition device and adjusts a sampling mode according to the risk level;
and S3, when the risk level meets the preset level requirement, outputting an execution signal related to the risk level by the central processing unit, and giving an alarm prompt by using the alarm device.
Preferably, in step S1, a low sampling frequency and high sampling precision mode is used for signal acquisition;
the step S2 specifically comprises the steps that after sampling values are obtained from a signal sampling device, a primary neural network is used for predicting future sampling values with equal time intervals for several times, then differential calculation is carried out on the predicted sampling values for several times, when the differential value is higher than a set first threshold value, the risk grade is determined to be in a second grade, the sampling mode of the sampling device is adjusted to be a high-sampling-frequency low-sampling-precision mode, otherwise, the risk grade is still in the first grade, and the signal sampling device still adopts the low-sampling-frequency high-sampling-precision mode to carry out signal acquisition; after entering a high sampling frequency and low sampling precision mode, carrying out neural network fitting on the collected low-precision sequence, carrying out precision improvement processing, taking current data after the precision improvement processing and previous high-precision data as input of neural network subsequent sequence prediction, predicting a sampling value sequence at a certain time interval in the future, carrying out differential calculation, and determining that the risk level is three when the differential value is higher than a second threshold value;
and S3, when the central processing unit determines that the risk level is three, the central processing unit outputs an execution signal, and an alarm device is used for giving an alarm prompt.
Preferably, the difference calculation used comprises forward difference, backward difference, derivation of the end of the fitting function, or a combination thereof. Preferably, when signal sampling is performed, the signal sampling device can simultaneously adopt a low sampling frequency high sampling precision mode and a high sampling frequency low sampling precision mode to perform signal acquisition.
When data acquisition is performed on the new energy battery, data with different sampling frequencies and different sampling accuracies are sequentially acquired, and then difference calculation is performed through neural network fitting, as shown in fig. 1. Firstly, acquiring sampling data as shown in a diamond part of fig. 2, then performing neural network fitting on the sampling data (as shown in fig. 3), then performing difference to obtain a first section of fitting curve of fig. 4, performing difference operation (differential derivation here) on the tail end of the first section of fitting curve, judging that a decision should enter a risk level two at the moment, and starting a high sampling frequency low sampling precision mode; the obtained sampling points are as the dotted parts in fig. 2, a second section of fitting curve in fig. 4 can be obtained after fitting by using a neural network, differential operation (differential derivation here) is carried out on the tail end of the second section of fitting curve, the decision of the calculation result is judged to be risk level three, and an alarm is sounded.
Specifically, in one embodiment, directly using all the sampled data as input for neural network fitting can obtain the effect of globally fitting curve as shown in fig. 5, which is similar to the trend of the two curves in fig. 5.
In one embodiment, a quadratic fitting method is used, after neural network fitting is performed on data with high sampling frequency, data with corrected precision obtained by sampling again is used for replacing original low-precision data, and then a globally fitted curve is obtained, as shown in fig. 6, compared with the result of the globally fitted curve shown in fig. 5, the obtained curve is smoother at the moment, and the difference operation result is more stable and smoother.
Specifically, it should be noted that the neural network used is a DNN-deep neural network, and the specific framework is an input layer (1 x 50) + a fully-connected layer (50 x 50) + an output layer (50 x 1) (see fig. 7); if the time sequence stops before 0.5s, the risk level is first grade; the risk rating is secondary if the time series stops before 1.5s and after 0.5 s.
Preferably, when the DNN-deep neural network is used for fitting, a feed-forward network with multiple layers is provided, each layer comprises 30 to 50 neurons, and the architecture of each layer is different (for example, one layer has three input neurons, the other layer has only two input neurons, but only one output neuron), and the equal activation function is used for the output layers of the networks by using the ReLU activation function; further preferably, during training, the collected data points are divided into a training set and a verification set, for example, the training set accounts for 90% of the total data points, the verification set accounts for 10%, and then fitting adjustment is performed by using a secondary cost function and a dynamic learning rate; the learning rate is dynamically adjusted according to the fitting condition of the neural network, preferably according to the tolerance value. By adopting the setting mode, a more effective network can be provided, and the CPU time with different tolerances can be improved.
Preferably, when the DNN-deep neural network is adopted for fitting, a sampling algorithm based on a multi-fidelity neural network agent is adopted, two calculation models with low fidelity and high fidelity are set, when calculation is carried out, firstly, a group of large low-fidelity data and a group of small high-fidelity data are generated by using the two calculation models, and then two networks, namely NN (neural network) NN (neural network) NN) are constructed on different levels 1 And a second neural network NN 2 Wherein the first neural network NN 1 The correlation between the low-fidelity data and the high-fidelity data is learned, and additional high-fidelity data can be generated according to the correlation; NN in a first neural network 1 After generating additional high fidelity data, the second neural network NN 2 Utilizing the additional high fidelity data, both raw and newly generatedTraining is performed as a high fidelity metric instead, and then embedded into the classical Markov Chain (MC) sample training model framework to compute some desired number of statistics of interest. In this way, the accuracy of the neural network simulation can be improved. Wherein the computational model used comprises:
in the formula (I), the compound is shown in the specification,
the correlation between low fidelity data and high fidelity data is measured,
and
respectively representing approximations of a quantity Q (Y) obtained by low-fidelity and high-fidelity computational models, Q (Y) being the desired acquired high-fidelity data, with an arrow indicating the output of the test data through the responsive neural network, an angle i representing the sampled data point index, and Y I 、Y II Is meant to represent two disjoint sets taken from the set of sample points.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "bottom", "top", "front", "rear", "inner", "outer", "left", "right", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the present invention.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that features described in different dependent claims and herein may be combined in ways different from those described in the original claims. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.
Claims (5)
1. A lithium battery thermal runaway layering early warning method based on a neural network and data difference is characterized in that an adopted early warning system at least comprises the following steps:
the signal sampling device can acquire an induction signal representing battery thermal runaway, and comprises two sampling modes of low sampling frequency, high sampling precision and high sampling frequency and low sampling precision;
the central processing unit device can perform neural network processing according to the induction signal representing the thermal runaway of the battery, predict and obtain a future sampling value, perform differential processing on the predicted future sampling value, determine a risk grade according to the magnitude of the differential value, and output an execution signal related to the risk grade; and
the alarm device can receive the execution signal and respond to the execution signal to give an alarm prompt;
the early warning method at least comprises the following steps:
s1, signal acquisition is carried out by using a signal sampling device;
s2, the central processing unit device determines a risk level according to the induction signal acquired by the signal sampling device and adjusts a sampling mode according to the risk level;
and S3, when the risk level meets the preset level requirement, outputting an execution signal related to the risk level by the central processing unit, and giving an alarm prompt by using the alarm device.
2. The lithium battery thermal runaway layered early warning method based on the neural network and the data difference as claimed in claim 1, wherein in step S1, a low sampling frequency and high sampling precision mode is used for signal acquisition;
step S2 specifically comprises the steps that after sampling values are obtained from a signal sampling device, a primary neural network is used for predicting future sampling values with equal time intervals for several times, then differential calculation is carried out on the predicted sampling values for several times, when the differential value is higher than a set first threshold value, the risk grade is determined to be in a second grade, the sampling mode of the signal sampling device is adjusted to be a high-sampling-frequency low-sampling-precision mode, otherwise, the risk grade is still in the first grade, and the signal sampling device still adopts the low-sampling-frequency high-sampling-precision mode; after entering a high sampling frequency and low sampling precision mode, carrying out neural network fitting on the collected low-precision sequence, carrying out precision improvement processing, taking the current data after the precision improvement processing and the previous high-precision data as the input of neural network subsequent sequence prediction, predicting a sampling value sequence at a certain time interval in the future, carrying out differential calculation, and determining that the risk level is three when the differential value is higher than a second threshold value;
and S3, when the central processing unit determines that the risk level is three, the central processing unit outputs an execution signal, and an alarm device is used for giving an alarm prompt.
3. The lithium battery thermal runaway layered early warning method based on the neural network and the data difference as claimed in any one of claims 1 to 2, wherein the operation purpose of the difference calculation is to obtain a signal indicative of a future trend of the sampled value, which includes derivation of the end of the prediction curve or difference of the discrete data obtained, and a forward difference method, a backward difference method or other equivalent difference methods can be used.
4. The lithium battery thermal runaway layered early warning method based on the neural network and the data difference as claimed in claims 1-2, wherein the neural network used is constituted as a 1x50 input layer + a 50x50 first fully connected layer + a 50x50 second fully connected layer + a 50x1 output layer.
5. The lithium battery thermal runaway layered early warning method based on the neural network and the data difference as claimed in one of claims 1 to 4, characterized in that the neural network is provided with a feed forward network of a plurality of layers, each layer comprises 30 to 50 neurons, the architecture of each layer is different, and the collected data points are split into a training set and a verification set during training.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210562350.1A CN115294745B (en) | 2022-05-23 | 2022-05-23 | Lithium battery thermal runaway layered early warning method based on neural network and data difference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210562350.1A CN115294745B (en) | 2022-05-23 | 2022-05-23 | Lithium battery thermal runaway layered early warning method based on neural network and data difference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115294745A true CN115294745A (en) | 2022-11-04 |
| CN115294745B CN115294745B (en) | 2023-09-29 |
Family
ID=83821143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210562350.1A Active CN115294745B (en) | 2022-05-23 | 2022-05-23 | Lithium battery thermal runaway layered early warning method based on neural network and data difference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115294745B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005078673A1 (en) * | 2004-02-03 | 2005-08-25 | Sys Technologies, Inc. | Remote battery monitoring system having embedded telesensors |
| JP2007165040A (en) * | 2005-12-12 | 2007-06-28 | Matsushita Electric Ind Co Ltd | Maintenance control method of secondary battery |
| JP2009192311A (en) * | 2008-02-13 | 2009-08-27 | Nippon Telegr & Teleph Corp <Ntt> | Device for predicting generation of thunder, and method therefor, and program |
| US20140159915A1 (en) * | 2012-12-12 | 2014-06-12 | Electronics And Telecommunications Research Institute | Apparatus and method for comprehensively monitoring slopes based on wireless network |
| CN105740578A (en) * | 2016-03-08 | 2016-07-06 | 国网新疆电力公司检修公司 | Maximum entropy-spectrum method applied to disconnecting switch vibration monitoring |
| CN107133142A (en) * | 2017-04-18 | 2017-09-05 | 浙江大学 | A kind of monitoring data intellegent sampling method based on association analysis |
| CN209071574U (en) * | 2018-04-26 | 2019-07-05 | 桂林电子科技大学 | Battery thermal runaway spreads simulator |
| CN111308376A (en) * | 2020-02-24 | 2020-06-19 | 上海蔚来汽车有限公司 | Power battery insulation monitoring method, system and device |
| WO2021063136A1 (en) * | 2019-09-30 | 2021-04-08 | 江苏大学 | Data-driven high-precision integrated navigation data fusion method |
| CN112946522A (en) * | 2021-02-05 | 2021-06-11 | 四川大学 | On-line monitoring method for short-circuit fault in battery energy storage system caused by low-temperature working condition |
| WO2021155851A1 (en) * | 2020-02-07 | 2021-08-12 | 华为技术有限公司 | Neural network circuit and neural network system |
| CN113344024A (en) * | 2021-04-22 | 2021-09-03 | 华中科技大学 | Lithium ion battery thermal runaway grading early warning method and early warning system |
| CN114312322A (en) * | 2021-12-31 | 2022-04-12 | 中国第一汽车股份有限公司 | Vehicle detection method and device |
-
2022
- 2022-05-23 CN CN202210562350.1A patent/CN115294745B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005078673A1 (en) * | 2004-02-03 | 2005-08-25 | Sys Technologies, Inc. | Remote battery monitoring system having embedded telesensors |
| JP2007165040A (en) * | 2005-12-12 | 2007-06-28 | Matsushita Electric Ind Co Ltd | Maintenance control method of secondary battery |
| JP2009192311A (en) * | 2008-02-13 | 2009-08-27 | Nippon Telegr & Teleph Corp <Ntt> | Device for predicting generation of thunder, and method therefor, and program |
| US20140159915A1 (en) * | 2012-12-12 | 2014-06-12 | Electronics And Telecommunications Research Institute | Apparatus and method for comprehensively monitoring slopes based on wireless network |
| CN105740578A (en) * | 2016-03-08 | 2016-07-06 | 国网新疆电力公司检修公司 | Maximum entropy-spectrum method applied to disconnecting switch vibration monitoring |
| CN107133142A (en) * | 2017-04-18 | 2017-09-05 | 浙江大学 | A kind of monitoring data intellegent sampling method based on association analysis |
| CN209071574U (en) * | 2018-04-26 | 2019-07-05 | 桂林电子科技大学 | Battery thermal runaway spreads simulator |
| WO2021063136A1 (en) * | 2019-09-30 | 2021-04-08 | 江苏大学 | Data-driven high-precision integrated navigation data fusion method |
| WO2021155851A1 (en) * | 2020-02-07 | 2021-08-12 | 华为技术有限公司 | Neural network circuit and neural network system |
| CN113255875A (en) * | 2020-02-07 | 2021-08-13 | 华为技术有限公司 | Neural network circuit and neural network system |
| CN111308376A (en) * | 2020-02-24 | 2020-06-19 | 上海蔚来汽车有限公司 | Power battery insulation monitoring method, system and device |
| CN112946522A (en) * | 2021-02-05 | 2021-06-11 | 四川大学 | On-line monitoring method for short-circuit fault in battery energy storage system caused by low-temperature working condition |
| CN113344024A (en) * | 2021-04-22 | 2021-09-03 | 华中科技大学 | Lithium ion battery thermal runaway grading early warning method and early warning system |
| CN114312322A (en) * | 2021-12-31 | 2022-04-12 | 中国第一汽车股份有限公司 | Vehicle detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115294745B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107436409B (en) | Intelligent SOC prediction device for power battery of electric automobile | |
| CN109818349B (en) | Power grid robust state prediction method based on multidimensional state matrix sliding matching | |
| CN116467667B (en) | Power failure monitoring and early warning method and system based on data fusion | |
| CN112434848A (en) | Nonlinear weighted combination wind power prediction method based on deep belief network | |
| CN113554200B (en) | Method, system and equipment for predicting voltage inconsistency of power battery | |
| CN112464996A (en) | Intelligent power grid intrusion detection method based on LSTM-XGboost | |
| CN110516813A (en) | A method of batteries of electric automobile RDR prediction is carried out based on big data machine learning | |
| CN114189047B (en) | False data detection and correction method for active power distribution network state estimation | |
| CN117408164A (en) | Intelligent wind speed prediction method and system for energy storage auxiliary black start | |
| CN108538301B (en) | Intelligent digital musical instrument based on neural network audio technology | |
| CN115113054A (en) | Echelon battery safety assessment method and device and electronic equipment | |
| CN113538037B (en) | Method, system, equipment and storage medium for monitoring charging event of battery car | |
| CN115294745A (en) | Lithium battery thermal runaway layering early warning method based on neural network and data difference | |
| CN114707692A (en) | Wetland effluent ammonia nitrogen concentration prediction method and system based on hybrid neural network | |
| CN107301266B (en) | LOC estimation method and system for lithium iron phosphate battery | |
| CN116503029A (en) | Module data cooperative processing method and system for automatic driving | |
| CN111626324A (en) | Seabed observation network data heterogeneous analysis integration method based on edge calculation | |
| CN114280490B (en) | Lithium ion battery state of charge estimation method and system | |
| CN113033695B (en) | Method for predicting faults of electronic device | |
| CN116400224A (en) | Battery remaining service life prediction method based on working temperature correction | |
| CN115718883A (en) | Thermal early warning method and device for battery energy storage system | |
| CN110794676A (en) | CSTR process nonlinear control method based on Hammerstein-Wiener model | |
| CN114757548A (en) | Wind power energy storage equipment adjusting performance evaluation method adopting scene construction | |
| CN113890633B (en) | Underwater acoustic communication system self-adaptive selection method based on deep neural network | |
| CN115639481A (en) | Battery data preprocessing system and method based on big data prediction SOC |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |