CN117454087A - Multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for energy storage power station - Google Patents
Multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for energy storage power station Download PDFInfo
- Publication number
- CN117454087A CN117454087A CN202311438280.XA CN202311438280A CN117454087A CN 117454087 A CN117454087 A CN 117454087A CN 202311438280 A CN202311438280 A CN 202311438280A CN 117454087 A CN117454087 A CN 117454087A
- Authority
- CN
- China
- Prior art keywords
- thermal runaway
- stage
- lithium battery
- probability
- early
- 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 148
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 148
- 230000004927 fusion Effects 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004146 energy storage Methods 0.000 title claims abstract description 41
- 238000010586 diagram Methods 0.000 claims abstract description 31
- 239000000779 smoke Substances 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 238000005315 distribution function Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
The invention discloses a multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for an energy storage power station, wherein the method comprises the following steps: acquiring time sequence temperature data, preprocessing the time sequence temperature data, and converting the time sequence temperature data into a two-dimensional thermodynamic diagram; inputting the two-dimensional thermodynamic diagram into a trained lithium battery thermal runaway prediction model to obtain probabilities that the lithium battery is in different stages respectively, and determining a first decision and a first probability corresponding to the first decision; calculating a posterior probability by adopting a Bayesian formula according to the voltage data, the combustible gas data and the smoke data acquired in real time, carrying out primary fusion on the posterior probability by adopting a D-S demonstration theory to obtain a first fusion probability, and determining a second decision and a second probability corresponding to the second decision; and correlating the first probability with the second probability, and performing secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery at different stages respectively, and determining the state of the lithium battery, so that the charge and discharge conditions of the lithium battery can be detected very early and accurately in real time.
Description
Technical Field
The invention relates to the field of energy storage detection and early warning, in particular to a multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for an energy storage power station.
Background
In recent years, china has made a great breakthrough in the technical field of new energy power such as photovoltaic power, wind power and the like, and further promotes the development of novel energy storage. The energy storage power station can realize peak clipping and valley filling, and is an important means for improving the utilization rate of renewable energy sources and the stability of an electric power system. The lithium battery has high energy density, strong endurance and long cycle life, and is widely applied to novel energy storage power stations. The number of series-parallel batteries in the energy storage cabinet is large, and in the long-term charging and discharging use process, the difference between the monomers can be gradually increased, so that the safety risk of non-negligible overcharge and thermal runaway exists in the application of the transformer substation.
At present, most of existing detection methods for thermal runaway of lithium batteries detect and early warn according to single-class sensors, such as temperature sensors and gas sensors, and the obtained single-parameter characteristics are used for judging the conditions of the thermal runaway of the lithium batteries, so that the conditions of large error, incorrect judgment and the like are easy to occur, and the existing methods lack judgment for the extremely early stage of the thermal runaway of the lithium batteries, so that an early warning method which is high in fault tolerance and precision and can detect the thermal runaway of the lithium batteries extremely early is needed in the field so as to ensure safe operation of an energy storage power station.
Disclosure of Invention
The technical problems mentioned above are solved. The embodiment of the application aims to provide a multi-sensor data fusion-based method and device for predicting thermal runaway of a lithium battery of an energy storage power station, so as to solve the technical problems mentioned in the background art section.
In a first aspect, the invention provides a multi-sensor data fusion-based lithium battery thermal runaway prediction method for an energy storage power station, which comprises the following steps:
acquiring time sequence temperature data of temperature change along with time, which is acquired in an energy storage cabinet, preprocessing the time sequence temperature data to obtain processed time sequence temperature data, and converting the processed time sequence temperature data to obtain a two-dimensional thermodynamic diagram;
constructing and training a lithium battery thermal runaway prediction model to obtain a trained lithium battery thermal runaway prediction model, inputting a two-dimensional thermodynamic diagram into the trained lithium battery thermal runaway prediction model to obtain probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining a first decision and a first probability corresponding to the first decision according to the probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively;
According to the voltage data, the combustible gas data and the smoke data acquired in the experimental stage, calculating the prior probability and the conditional probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage under different conditions by adopting a Bayesian formula, acquiring the voltage data, the combustible gas data and the smoke data acquired in real time, combining the prior probability and the conditional probability to obtain the posterior probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage, and performing primary fusion on the posterior probability by adopting a D-S demonstration theory to obtain the first fusion probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early-middle stage, the thermal runaway early-middle stage and the thermal runaway later stage, and determining a second decision and the corresponding second probability according to the first fusion probability;
and correlating the first probability with the second probability, and performing secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining the state of the lithium battery according to the second fusion probabilities.
Preferably, the preprocessing is performed on the time sequence temperature data to obtain processed time sequence temperature data, which specifically includes:
and normalizing the time sequence temperature data according to the following formula:
wherein, the time sequence temperature data is X= { X 1 ,x 2 ,...,x n }，i＝1,2,...,n；
Performing dimension reduction processing on the normalized time sequence temperature data to obtain processed time sequence temperature data, wherein the formula is as follows:
where the compression ratio k=n/l, l is the length of the processed time-series temperature data.
Preferably, the method for converting the processed time sequence temperature data into a two-dimensional thermodynamic diagram specifically includes:
converting the processed time sequence temperature data into a polar coordinate system by taking the processed time sequence temperature data as a polar angle and taking a timestamp as a radius, wherein the formula is as follows:
wherein,represents the point x' g Time stamp of->The number of all time points included in the processed time-series temperature data;
and constructing a gram matrix according to polar angles corresponding to every two time points to finish GASF coding, wherein the formula is as follows:
wherein phi is i Polar angle, phi, representing the ith point in time j The polar angle at the j-th time point is indicated.
Preferably, the lithium battery thermal runaway prediction model adopts a CNN convolutional neural network.
Preferably, the prior probability and the conditional probability that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively are calculated according to the voltage data, the combustible gas data and the smoke data acquired in the experimental stage by adopting a bayesian formula, the voltage data, the combustible gas data and the smoke data acquired in real time are acquired, and the posterior probability that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively is calculated by combining the prior probability and the conditional probability, and the posterior probability specifically comprises the following steps:
Let A 1 ,A 2 ,A 3 ,...,A o For one division of the sample space Ω, the following is satisfied:
A s ∪A t …∪A o ＝Ω；
P(A s )＞0(s＝1,2,…,o)；
then for any event B, and P (B) > 0, then result A appears for event B s The posterior probability of (2) is:
the sample space omega is four phases of thermal runaway, when one observation result of the collected voltage data, the combustible gas data and the smoke data is B, the prior probability P (A w ) And a conditional probability P (B|A) in the case where the observation result at this stage is B w ) A occurs under the condition that a known observation result acquired in real time is B through Bayesian posterior probability formula calculation w Posterior probability P (A) w |B)。
Preferably, the fusion process using the D-S demonstration theory is as follows:
assume that the recognition frame θ= { is normal, extremely early, medium, late } = { H 1 ,H 2 ,H 3 ,H 4 }；
For event C, there is evidence X 1 And Y 2 ，m 1 And m 2 Evidence X respectively 1 And Y 2 Corresponding basic probability distribution function, C p And D q As focal element, the fusion formula of the two evidences is:
wherein, K is a conflict coefficient,expressed as an empty set, the definition formula is as follows:
fusing multiple evidences pairwise to obtain a basic probability distribution function m (H) 1 ),m(H 2 ),m(H 3 ),m(H 4 )。
Preferably, the determining the first decision and the first probability corresponding to the first decision according to the probabilities that the lithium battery is in the normal working stage, the extremely early stage, the early and middle stage and the later stage of the thermal runaway respectively specifically comprises:
Determining the maximum value of probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage as a first probability, wherein the corresponding stage is a first decision;
determining a second decision and a second probability corresponding to the second decision according to the first fusion probability specifically comprises:
determining the maximum value in the first fusion probabilities of the lithium battery in the normal working phase, the thermal runaway extremely early phase, the thermal runaway early-middle phase and the thermal runaway later phase as a second probability, wherein the corresponding phase is a second decision;
determining the state of the lithium battery according to the second fusion probability, wherein the state comprises
And the lithium battery is in a state of being in a stage corresponding to the maximum value in the second fusion probability of the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively.
In a second aspect, the invention provides a multi-sensor data fusion-based lithium battery thermal runaway prediction device of an energy storage power station, comprising:
the data processing module is configured to acquire time sequence temperature data of temperature change along with time acquired in the energy storage cabinet, preprocess the time sequence temperature data to obtain processed time sequence temperature data, and convert the processed time sequence temperature data to obtain a two-dimensional thermodynamic diagram;
The first decision determining module is configured to construct and train a lithium battery thermal runaway prediction model to obtain a trained lithium battery thermal runaway prediction model, input a two-dimensional thermodynamic diagram into the trained lithium battery thermal runaway prediction model to obtain probabilities that the lithium battery is in a normal working stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determine a first decision and corresponding first probabilities according to the probabilities that the lithium battery is in the normal working stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively;
the second decision determining module is configured to calculate prior probabilities and conditional probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively under different conditions by adopting a Bayesian formula according to the voltage data, the combustible gas data and the smoke data acquired in real time, calculate posterior probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively by combining the prior probabilities and the conditional probabilities, and fuse the posterior probabilities once by adopting a D-S evidence theory to obtain first fusion probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early-early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively, and determine a second decision and corresponding second probabilities according to the first fusion probabilities;
The state prediction module is configured to correlate the first probability with the second probability, and perform secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determine the state of the lithium battery according to the second fusion probabilities.
In a third aspect, the present invention provides an electronic device comprising one or more processors; and storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as described in any of the implementations of the first aspect.
Compared with the prior art, the invention has the following beneficial effects:
(1) By processing the temperature data, the abnormal state of the lithium battery during operation can be detected very early, and the early warning can be sent very early in the early warning of the thermal runaway stage of the lithium battery at the first time.
(2) The invention integrates the advantages of each sensor for detecting the thermal runaway process of the lithium battery, such as the temperature can make more accurate judgment in the early stage of the thermal runaway of the lithium battery, and the gas sensor is more suitable for the characteristic identification in the middle and later stages of overcharging.
(3) The invention combines the information of a plurality of sensors, eliminates the limitation of a single sensor, and improves the accuracy, the robustness and the reliability of the sensing of the system.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is an exemplary device frame pattern to which an embodiment of the present application may be applied;
FIG. 2 is a schematic flow chart of a multi-sensor data fusion-based method for predicting thermal runaway of a lithium battery of an energy storage power station according to an embodiment of the present application;
FIG. 3 is a flow chart of a multi-sensor data fusion-based method for predicting thermal runaway of a lithium battery of an energy storage power station according to an embodiment of the present application;
FIG. 4 is a schematic flow chart of a D-S demonstration theory of a multi-sensor data fusion-based lithium battery thermal runaway prediction method of an energy storage power station in an embodiment of the application;
FIG. 5 is a schematic diagram of a multi-sensor data fusion-based thermal runaway prediction device for lithium batteries of an energy storage power station according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer device suitable for use in implementing the embodiments of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
FIG. 1 illustrates an exemplary device architecture 100 of an energy storage power station lithium battery thermal runaway prediction method based on multi-sensor data fusion or an energy storage power station lithium battery thermal runaway prediction device based on multi-sensor data fusion, to which embodiments of the present application may be applied.
As shown in fig. 1, the apparatus architecture 100 may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the first terminal device 101, the second terminal device 102, the third terminal device 103, to receive or send messages, etc. Various applications, such as a data processing class application, a file processing class application, and the like, may be installed on the terminal device one 101, the terminal device two 102, and the terminal device three 103.
The first terminal device 101, the second terminal device 102 and the third terminal device 103 may be hardware or software. When the first terminal device 101, the second terminal device 102, and the third terminal device 103 are hardware, they may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like. When the first terminal apparatus 101, the second terminal apparatus 102, and the third terminal apparatus 103 are software, they can be installed in the above-listed electronic apparatuses. Which may be implemented as multiple software or software modules (e.g., software or software modules for providing distributed services) or as a single software or software module. The present invention is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background data processing server that processes files or data uploaded by the terminal device one 101, the terminal device two 102, and the terminal device three 103. The background data processing server can process the acquired file or data to generate a processing result.
It should be noted that, the multi-sensor data fusion-based thermal runaway prediction method for the lithium battery of the energy storage power station provided by the embodiment of the application may be executed by the server 105, or may be executed by the first terminal device 101, the second terminal device 102 and the third terminal device 103, and correspondingly, the multi-sensor data fusion-based thermal runaway prediction device for the lithium battery of the energy storage power station may be set in the server 105, or may be set in the first terminal device 101, the second terminal device 102 and the third terminal device 103.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. In the case where the processed data does not need to be acquired from a remote location, the above-described apparatus architecture may not include a network, but only a server or terminal device.
Fig. 2 shows a method for predicting thermal runaway of a lithium battery of an energy storage power station based on multi-sensor data fusion, which comprises the following steps:
s1, acquiring time sequence temperature data of temperature change along with time, which is acquired in an energy storage cabinet, preprocessing the time sequence temperature data to obtain processed time sequence temperature data, and converting the processed time sequence temperature data to obtain a two-dimensional thermodynamic diagram.
In a specific embodiment, preprocessing the time sequence temperature data to obtain processed time sequence temperature data specifically includes:
and normalizing the time sequence temperature data according to the following formula:
wherein, the time sequence temperature data is X= { X 1 ,x 2 ,...,x n }，i＝1,2,...,n；
Performing dimension reduction processing on the normalized time sequence temperature data to obtain processed time sequence temperature data, wherein the formula is as follows:
where the compression ratio k=n/l, l is the length of the processed time-series temperature data.
In a specific embodiment, the converting the processed time-series temperature data to obtain a two-dimensional thermodynamic diagram specifically includes:
converting the processed time sequence temperature data into a polar coordinate system by taking the processed time sequence temperature data as a polar angle and taking a timestamp as a radius, wherein the formula is as follows:
wherein,represents the point x' g Time stamp of->The number of all time points included in the processed time-series temperature data;
and constructing a gram matrix according to polar angles corresponding to every two time points to finish GASF coding, wherein the formula is as follows:
wherein phi is i Polar angle, phi, representing the ith point in time j The polar angle at the j-th time point is indicated.
Specifically, referring to fig. 3, the temperature characteristics are first extracted, the temperature change can react earlier to the thermal runaway condition of the lithium battery, and when the thermal runaway condition of the lithium battery occurs, the temperature changes in a monotonically increasing form with time. In the embodiment of the application, the surface temperature T of the center of the lithium battery is acquired by using a patch temperature sensor i And combine the acquisition time to form one-dimensional time sequence temperatureThe temperature data can be converted into a two-dimensional thermodynamic diagram by adopting the GASF theory, and the temperature change characteristics are amplified. The specific process comprises the following steps: corresponding sensors are arranged at proper positions in the energy storage cabinet, and environmental data in the energy storage cabinet are collected. Time-series temperature data x= { X of temperature to be acquired from a sensor with time 1 ,x 2 ,...,x n Normalized operation scaling the data range to [0,1 ]]. And then carrying out data smoothing on the normalized time sequence temperature data, reducing the sequence length, and shortening the time sequence temperature data with the length of n to processed time sequence temperature data X' with the length of l, wherein the dimension reduction with the compression ratio of k=n/l can be specifically set. Converting the processed time sequence temperature data into a polar coordinate system, namely taking the numerical value as an included angle cosine value phi, taking the timestamp as a radius r, keeping the time dependence through the r coordinate, keeping the numerical relation of the polar angle phi, calculating to generate a gram matrix after finishing the conversion, and finishing the mapping between the one-dimensional time sequence temperature data and the two-dimensional space through the steps to convert the one-dimensional time sequence temperature data into a two-dimensional thermodynamic diagram.
The conditions for the division of the lithium battery at different stages are set as shown in table 1.
Table 1 lithium battery thermal runaway stage division condition setting
S2, constructing and training a lithium battery thermal runaway prediction model to obtain a trained lithium battery thermal runaway prediction model, inputting a two-dimensional thermodynamic diagram into the trained lithium battery thermal runaway prediction model to obtain probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining a first decision and a first probability corresponding to the first decision according to the probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively.
In a specific embodiment, the lithium battery thermal runaway prediction model employs a CNN convolutional neural network.
In a specific embodiment, determining the first decision and the first probability corresponding to the first decision according to the probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively specifically includes:
and determining the maximum value of the probabilities of the lithium battery in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage as a first probability, wherein the corresponding stage is a first decision.
Specifically, deep learning is further combined to deeply excavate the features of the two-dimensional thermodynamic diagram, a lithium battery thermal runaway prediction model based on the CNN convolutional neural network is constructed, the two-dimensional thermodynamic diagram at different stages of temperature change is collected to serve as training data, the training data are input into the CNN convolutional neural network to conduct classified training, and the trained lithium battery thermal runaway prediction model is obtained. The two-dimensional thermodynamic diagram converted from the time sequence temperature data acquired in real time is input into a trained lithium battery thermal runaway prediction model, and the probability m of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage is output respectively a (H i ) The probability maximum is selected as the first probability and a first decision is made.
And S3, calculating prior probabilities and conditional probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively under different conditions by adopting a Bayesian formula according to the voltage data, the combustible gas data and the smoke data acquired in real time, obtaining posterior probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively by combining the prior probabilities and the conditional probabilities, fusing the posterior probabilities once by adopting a D-S theory to obtain first fusion probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early-stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively, and determining a second decision and a corresponding second probability according to the first fusion probabilities.
In a specific embodiment, according to voltage data, combustible gas data and smoke data acquired in an experimental stage, a bayesian formula is adopted to calculate prior probabilities and conditional probabilities that a lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively under different conditions, the voltage data, the combustible gas data and the smoke data acquired in real time are acquired, and posterior probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively are calculated by combining the prior probabilities and the conditional probabilities, the method specifically comprises the following steps:
let A 1 ,A 2 ,A 3 ,…,A o For one division of the sample space Ω, the following is satisfied:
A s ∪A t …∪A o ＝Ω；
P(A s )＞0(s＝1,2,…,o)；
then for any event B, and P (B) > 0, then result A appears for event B s The posterior probability of (2) is:
the sample space omega is four phases of thermal runaway, when one observation result of the collected voltage data, the combustible gas data and the smoke data is B, the prior probability P (A w ) And a conditional probability P (B|A) in the case where the observation result at this stage is B w ) A occurs under the condition that a known observation result acquired in real time is B through Bayesian posterior probability formula calculation w Posterior probability P (A) w |B)。
In a specific embodiment, determining the second decision and the corresponding second probability according to the first fusion probability specifically includes:
and determining the maximum value in the first fusion probabilities of the lithium battery in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage as a second probability, wherein the corresponding stage is a second decision.
Specifically, the corresponding sensor is arranged to collect the voltage data u i Combustible gas data g i Smoke data s i According to experimental data, calculating prior probability and conditional probability values of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively under different conditions by using a Bayesian formula. And in the real-time environment monitoring process, the probability of being at a certain stage at present is obtained according to the prior probability and the conditional probability. The D-S demonstration is adopted to fuse the results of each sensor once to obtain m b (H i ) The probability maximum is selected and a second decision is made.
And S4, correlating the first probability with the second probability, and carrying out secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining the state of the lithium battery according to the second fusion probabilities.
In a specific example, the fusion process using the D-S demonstration theory is as follows:
assume that the recognition frame θ= { is normal, extremely early, medium, late } = { H 1 ,H 2 ,H 3 ,H 4 }；
For event C, there is evidence X 1 And Y 2 ，m 1 And m 2 Evidence X respectively 1 And Y 2 Corresponding basic probability distribution function, C p And D q As focal element, the fusion formula of the two evidences is:
wherein, K is a conflict coefficient,expressed as an empty set, the definition formula is as follows:
fusing multiple evidences pairwise to obtain a basic probability distribution function m (H) 1 ),m(H 2 ),m(H 3 ),m(H 4 )。
In a specific embodiment, determining the state of the lithium battery according to the second fusion probability specifically comprises
And the lithium battery is in a state of being in a stage corresponding to the maximum value in the second fusion probability of the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively.
Specifically, m is a (H i ) And m b (H i ) The association is carried out by adopting a D-S demonstration theory to carry out secondary fusion, and the probability m (H) of the current normal working of the lithium battery is respectively obtained 1 ) Probability m (H) of being in very early stage of thermal runaway 2 ) Probability m (H) of being in early and mid stages of thermal runaway 3 ) And probability m (H) of being in the late phase of thermal runaway 4 ) And finally, a decision is obtained according to the method, and the working condition of the lithium battery is judged. Referring to FIG. 4, in the D-S theory of demonstration, data collected by multiple sensors is taken as evidence, one sensor corresponds to one evidence source, and a plurality of evidence sources X exist i ，Y j ，…，Z k Etc. corresponding to the basic trust allocation function m 1 ，m 2 ，...，m l Where i, j, k, l=1, 2. The product of the two pieces of evidence is the degree of support for the event. Different evidence sources are fused according to the D-S demonstration theory, and a basic probability distribution function m (H) under the common evidence of multiple sensors is obtained 1 ),m(H 2 ),m(H 3 ),m(H 4 ) That is, representing branches at different stages of an eventAnd finally, making a final decision according to the decision rule. And selecting a stage corresponding to the maximum value in the second fusion probability as a final decision, wherein the final decision is the state of the lithium battery.
The above steps S1-S4 do not merely represent the order between steps, but rather are step notations.
With further reference to fig. 5, as an implementation of the method shown in the foregoing drawings, the present application provides an embodiment of a thermal runaway prediction device for a lithium battery of an energy storage power station based on multi-sensor data fusion, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various electronic devices.
The embodiment of the application provides an energy storage power station lithium cell thermal runaway prediction device based on multisensor data fusion, includes:
the data processing module 1 is configured to acquire time sequence temperature data of temperature change along with time acquired in the energy storage cabinet, preprocess the time sequence temperature data to obtain processed time sequence temperature data, and convert the processed time sequence temperature data to obtain a two-dimensional thermodynamic diagram;
the first decision determining module 2 is configured to construct and train a lithium battery thermal runaway prediction model to obtain a trained lithium battery thermal runaway prediction model, input a two-dimensional thermodynamic diagram into the trained lithium battery thermal runaway prediction model to obtain probabilities that the lithium battery is in a normal working stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determine a first decision and corresponding first probabilities according to the probabilities that the lithium battery is in the normal working stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively;
the second decision determining module 3 is configured to calculate prior probabilities and conditional probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively under different conditions by adopting a Bayesian formula according to the voltage data, the combustible gas data and the smoke data acquired in real time, calculate posterior probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively by combining the prior probabilities and the conditional probabilities, and fuse the posterior probabilities once by adopting a D-S argumentation theory to obtain first fusion probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early-stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively, and determine a second decision and corresponding second probabilities according to the first fusion probabilities;
The state prediction module 4 is configured to correlate the first probability with the second probability, and perform secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determine the state of the lithium battery according to the second fusion probabilities.
Referring now to fig. 6, there is illustrated a schematic diagram of a computer apparatus 600 suitable for use in implementing an electronic device (e.g., a server or terminal device as illustrated in fig. 1) of an embodiment of the present application. The electronic device shown in fig. 6 is only an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present application.
As shown in fig. 6, the computer apparatus 600 includes a Central Processing Unit (CPU) 601 and a Graphics Processor (GPU) 602, which can perform various appropriate actions and processes according to programs stored in a Read Only Memory (ROM) 603 or programs loaded from a storage section 609 into a Random Access Memory (RAM) 604. In the RAM 604, various programs and data required for the operation of the apparatus 600 are also stored. The CPU 601, GPU602, ROM 603, and RAM 604 are connected to each other through a bus 605. An input/output (I/O) interface 606 is also connected to the bus 605.
The following components are connected to the I/O interface 606: an input portion 607 including a keyboard, a mouse, and the like; an output portion 608 including a speaker, such as a Liquid Crystal Display (LCD), etc.; a storage portion 609 including a hard disk and the like; and a communication section 610 including a network interface card such as a LAN card, a modem, or the like. The communication section 610 performs communication processing via a network such as the internet. The drive 611 may also be connected to the I/O interface 606 as needed. A removable medium 612 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 611 as necessary, so that a computer program read out therefrom is mounted into the storage section 609 as necessary.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 610, and/or installed from the removable medium 612. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 601 and a Graphics Processor (GPU) 602.
It should be noted that the computer readable medium described in the present application may be a computer readable signal medium or a computer readable medium, or any combination of the two. The computer readable medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor apparatus, device, or means, or a combination of any of the foregoing. More specific examples of the computer-readable medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution apparatus, device, or apparatus. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may be any computer readable medium that is not a computer readable medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution apparatus, device, or apparatus. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present application may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments described in the present application may be implemented by software, or may be implemented by hardware. The described modules may also be provided in a processor.
As another aspect, the present application also provides a computer-readable medium that may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring time sequence temperature data of temperature change along with time, which is acquired in an energy storage cabinet, preprocessing the time sequence temperature data to obtain processed time sequence temperature data, and converting the processed time sequence temperature data to obtain a two-dimensional thermodynamic diagram; constructing and training a lithium battery thermal runaway prediction model to obtain a trained lithium battery thermal runaway prediction model, inputting a two-dimensional thermodynamic diagram into the trained lithium battery thermal runaway prediction model to obtain probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining a first decision and a first probability corresponding to the first decision according to the probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively; according to the voltage data, the combustible gas data and the smoke data acquired in the experimental stage, calculating the prior probability and the conditional probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage under different conditions by adopting a Bayesian formula, acquiring the voltage data, the combustible gas data and the smoke data acquired in real time, combining the prior probability and the conditional probability to obtain the posterior probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage, and performing primary fusion on the posterior probability by adopting a D-S demonstration theory to obtain the first fusion probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early-middle stage, the thermal runaway early-middle stage and the thermal runaway later stage, and determining a second decision and the corresponding second probability according to the first fusion probability; and correlating the first probability with the second probability, and performing secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining the state of the lithium battery according to the second fusion probabilities.
The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the invention referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or equivalents thereof is possible without departing from the spirit of the invention. Such as the above-described features and technical features having similar functions (but not limited to) disclosed in the present application are replaced with each other.
Claims (10)
1. The multi-sensor data fusion-based lithium battery thermal runaway prediction method for the energy storage power station is characterized by comprising the following steps of:
acquiring time sequence temperature data of temperature change along with time, which is acquired in an energy storage cabinet, preprocessing the time sequence temperature data to obtain processed time sequence temperature data, and converting the processed time sequence temperature data to obtain a two-dimensional thermodynamic diagram;
constructing and training a lithium battery thermal runaway prediction model to obtain a trained lithium battery thermal runaway prediction model, inputting the two-dimensional thermodynamic diagram into the trained lithium battery thermal runaway prediction model to obtain probabilities that a lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining a first decision and a first probability corresponding to the first decision according to the probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively;
According to the voltage data, the combustible gas data and the smoke data acquired in the experimental stage, adopting a Bayesian formula to calculate the prior probability and the conditional probability that the lithium battery is respectively in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage under different conditions, acquiring the voltage data, the combustible gas data and the smoke data acquired in real time, combining the prior probability and the conditional probability to obtain the posterior probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early-middle stage, the thermal runaway early-middle stage and the thermal runaway later stage, fusing the posterior probability once by adopting a D-S theory to obtain the first fusing probability that the lithium battery is respectively in the normal working stage, the thermal runaway extremely early-middle stage, the thermal runaway early-middle stage and the thermal runaway later stage, and determining a second decision and the corresponding second probability according to the first fusing probability;
and correlating the first probability with the second probability, and performing secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determining the state of the lithium battery according to the second fusion probabilities.
2. The multi-sensor data fusion-based lithium battery thermal runaway prediction method for the energy storage power station, according to claim 1, is characterized in that the time-series temperature data is preprocessed to obtain processed time-series temperature data, and specifically comprises the following steps:
and normalizing the time sequence temperature data, wherein the formula is as follows:
wherein, the time sequence temperature data is X= { X 1 ,x 2 ,...,x n }，i＝1,2,...,n；
Performing dimension reduction processing on the normalized time sequence temperature data to obtain the processed time sequence temperature data, wherein the formula is as follows:
wherein the compression ratio k=n/l, l is the length of the processed time-series temperature data.
3. The multi-sensor data fusion-based lithium battery thermal runaway prediction method for the energy storage power station, according to claim 2, is characterized in that the converting the processed time-series temperature data into a two-dimensional thermodynamic diagram, and specifically comprises:
and converting the processed time sequence temperature data into a polar coordinate system by taking the processed time sequence temperature data as a polar angle and taking a timestamp as a radius, wherein the formula is as follows:
wherein,represents the point x' g Time stamp of->The number of all time points included in the processed time sequence temperature data;
And constructing a gram matrix according to polar angles corresponding to every two time points to finish GASF coding, wherein the formula is as follows:
wherein phi is i Polar angle, phi, representing the ith point in time j The polar angle at the j-th time point is indicated.
4. The multi-sensor data fusion-based lithium battery thermal runaway prediction method for the energy storage power station, which is characterized in that a CNN convolutional neural network is adopted in the lithium battery thermal runaway prediction model.
5. The multi-sensor data fusion-based prediction method for thermal runaway of the lithium battery of the energy storage power station according to claim 1, wherein the prior probability and the conditional probability that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively under different conditions are calculated by adopting a Bayesian formula according to the voltage data, the combustible gas data and the smoke data acquired in real time, and the posterior probability that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively are obtained by combining the prior probability and the conditional probability, and the method specifically comprises the following steps:
Let A 1 ,A 2 ,A 3 ,...,A o For one division of the sample space Ω, the following is satisfied:
A s ∪A t …∪A o ＝Ω；
P(A s )＞0(s＝1,2,…,o)；
then for any event B, and P (B) > 0, then result A appears for event B s The posterior probability of (2) is:
the sample space omega is four phases of thermal runaway, when one observation result of the collected voltage data, the combustible gas data and the smoke data is B, the prior probability P (A w ) And a conditional probability P (B|A) in the case where the observation result at this stage is B w ) A occurs under the condition that a known observation result acquired in real time is B through Bayesian posterior probability formula calculation w Posterior probability P (A) w |B)。
6. The multi-sensor data fusion-based lithium battery thermal runaway prediction method for the energy storage power station, according to claim 1, is characterized in that the fusion process by adopting the D-S demonstration theory is as follows:
assume that the recognition frame θ= { is normal, extremely early, medium, late } = { H 1 ,H 2 ,H 3 ,H 4 }；
For event C, there is evidence X 1 And Y 2 ，m 1 And m 2 Evidence X respectively 1 And Y 2 Corresponding basic probability distribution function, C p And D q As focal element, the fusion formula of the two evidences is:
wherein, K is a conflict coefficient,expressed as an empty set, the definition formula is as follows:
fusing multiple evidences pairwise to obtain a basic probability distribution function m (H) 1 ),m(H 2 ),m(H 3 ),m(H 4 )。
7. The multi-sensor data fusion-based prediction method for thermal runaway of a lithium battery of an energy storage power station according to claim 1, wherein the determining the first decision and the first probability corresponding to the first decision according to the probabilities that the lithium battery is in a normal working phase, a very early phase of thermal runaway, a very middle phase of thermal runaway, and a later phase of thermal runaway respectively specifically comprises:
determining the maximum value of probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage as the first probability, wherein the corresponding stage is the first decision;
the determining the second decision and the corresponding second probability according to the first fusion probability specifically includes:
determining the maximum value in the first fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage as the second probability, wherein the corresponding stage is the second decision;
the determining the state of the lithium battery according to the second fusion probability specifically comprises
And respectively setting the phases corresponding to the maximum value in the second fusion probability of the normal working phase, the thermal runaway extremely early phase, the thermal runaway early-middle phase and the thermal runaway later phase of the lithium battery as the states of the lithium battery.
8. Energy storage power station lithium cell thermal runaway prediction device based on multisensor data fuses, characterized in that includes:
the data processing module is configured to acquire time sequence temperature data of temperature change along with time, which is acquired in the energy storage cabinet, pre-process the time sequence temperature data to obtain processed time sequence temperature data, and convert the processed time sequence temperature data to obtain a two-dimensional thermodynamic diagram;
the first decision determining module is configured to construct and train a lithium battery thermal runaway prediction model, obtain a trained lithium battery thermal runaway prediction model, input the two-dimensional thermodynamic diagram into the trained lithium battery thermal runaway prediction model, obtain probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determine a first decision and corresponding first probabilities according to the probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively;
the second decision determining module is configured to calculate prior probabilities and conditional probabilities that the lithium battery is in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively under different conditions by adopting a Bayesian formula according to the voltage data, the combustible gas data and the smoke data acquired in real time, calculate posterior probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively by combining the prior probabilities and the conditional probabilities, fuse the posterior probabilities once by adopting a D-S proof theory to obtain first fusion probabilities that the lithium battery is in the normal working stage, the thermal runaway extremely early-middle stage, the thermal runaway early-middle stage and the thermal runaway later stage respectively, and determine a second decision and corresponding second probabilities according to the first fusion probabilities;
The state prediction module is configured to correlate the first probability with the second probability, and perform secondary fusion by adopting a D-S demonstration theory to obtain second fusion probabilities of the lithium battery in a normal working stage, a thermal runaway extremely early stage, a thermal runaway early-middle stage and a thermal runaway later stage respectively, and determine the state of the lithium battery according to the second fusion probabilities.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311438280.XA CN117454087A (en) | 2023-11-01 | 2023-11-01 | Multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for energy storage power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311438280.XA CN117454087A (en) | 2023-11-01 | 2023-11-01 | Multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for energy storage power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117454087A true CN117454087A (en) | 2024-01-26 |
Family
ID=89596249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311438280.XA Pending CN117454087A (en) | 2023-11-01 | 2023-11-01 | Multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for energy storage power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117454087A (en) |
-
2023
- 2023-11-01 CN CN202311438280.XA patent/CN117454087A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115422696B (en) | Module digital twin model building method, system, terminal and medium | |
| CN116699297B (en) | Charging pile detection system and method thereof | |
| CN114722625B (en) | Method, system, terminal and medium for establishing monomer digital twin model of lithium battery | |
| CN116614177B (en) | Optical fiber state multidimensional parameter monitoring system | |
| CN115022187B (en) | Situation awareness method and device for electric-gas comprehensive energy system | |
| CN113310647A (en) | Method and device for detecting leakage of battery pack, electronic equipment and storage medium | |
| CN116572747B (en) | Battery fault detection method, device, computer equipment and storage medium | |
| CN117036732B (en) | Electromechanical equipment detection system, method and equipment based on fusion model | |
| Jiang et al. | Temperature prediction of battery energy storage plant based on EGA-BiLSTM | |
| Ma et al. | A novel health index for battery RUL degradation modeling and prognostics | |
| CN117454087A (en) | Multi-sensor data fusion-based lithium battery thermal runaway prediction method and device for energy storage power station | |
| CN116923188A (en) | Charging protection system of new energy vehicle | |
| CN116298902A (en) | Lithium battery aging prediction method and system based on multitask learning | |
| CN115267586A (en) | Lithium battery SOH evaluation method | |
| CN106816871B (en) | State similarity analysis method for power system | |
| Moura et al. | Better batteries through electrochemistry | |
| CN111319510A (en) | Method and device for predicting driving range of electric vehicle | |
| CN117040135B (en) | Power equipment power supply method, device, electronic equipment and computer readable medium | |
| CN117783886B (en) | Power battery abnormal state identification method and device, electronic equipment and storage medium | |
| Cao et al. | An early diagnosis method for overcharging thermal runaway of energy storage lithium batteries | |
| CN116256647B (en) | Online identification prediction method and system for fuel cell performance | |
| CN117081088B (en) | Power grid load dispatching control method and device, computer equipment and storage medium | |
| Li et al. | Retrieval-based Battery Degradation Prediction for Battery Energy Storage System Operations | |
| Lin et al. | Battery Health Prognosis Based on Sliding Window Sampling of Charging Curves and Independently Recurrent Neural Network | |
| Zhu et al. | Prediction Method of Ohmic Resistance and Charge Transfer Resistance for Lithium-Ion Batteries Based on CSA-SVR |
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 |