End-to-Cloud Collaborative Battery Management Method and System Based on Embedded Fiber Optic Sensing

Abstract

This invention provides an end-to-cloud collaborative battery management method and system based on embedded fiber optic sensing. By integrating a distributed temperature self-sensing system at the battery end to sense the internal and external temperature distribution of individual battery cells, battery modeling and state estimation are performed in the battery management system, and SOC-OCV curve estimation is performed in the cloud to guide the correction and updating of the terminal model. This achieves multi-level organic integration of data from the intelligent battery end, terminal, and cloud, which not only makes the model more accurate and has a wider range of adaptability, but also ensures the richness of state estimation terms. Compared with the prior art, it significantly improves the accuracy and efficiency of battery electro-thermal management.

Description

Technical Field

[0001] This invention belongs to the field of battery management system technology, specifically relating to an end-to-cloud collaborative battery management method and system based on embedded fiber optic sensing. Background Technology

[0002] In practical applications of lithium-ion batteries, real-time and accurate monitoring and management are crucial for ensuring the safe and reliable operation of electrical equipment. Currently, battery management generally relies on pre-installed programs on the terminal to analyze basic signals collected by sampling circuits to monitor the battery's operating status. However, a battery system is a nonlinear system with strong time-varying and temperature-dependent characteristics, which makes accurate monitoring of key electrothermal behaviors of the battery often difficult. In traditional battery management system frameworks, the available monitoring parameters are limited to current, voltage, and surface temperature. These systems focus more on designing complex algorithms to improve management efficiency, but the inability to obtain more measurement data to intuitively infer internal battery information limits the true effectiveness of battery management. Recent battery management technologies that utilize intelligent embedded sensors have achieved some improvements compared to traditional battery management systems, but the applied battery models still have significant room for improvement, and the coordination and matching with the terminal system are not yet perfect. Furthermore, system architectures integrating advanced sensing technologies have a wider and richer amount of data compared to traditional architectures. Those skilled in the art lack sufficient understanding and solutions on how to utilize cloud systems and digital twin technology to further improve the construction level of battery management systems. Summary of the Invention

[0003] In view of this, and to address the technical problems existing in this field, the present invention provides an end-to-cloud collaborative battery management method based on embedded fiber optic sensing, specifically including the following steps:

[0004] Step 1: For the specific type of individual battery physical entity in the battery system to be monitored, a distributed temperature self-sensing system suitable for smart battery cells is constructed by integrating an embedded distributed fiber optic sensor system. The sensing data collected by the distributed temperature self-sensing system is then acquired by the terminal battery management system and uploaded to the cloud system. The cloud system stores specific cycle charge-discharge experimental data of the same type of battery cells in the experimental environment, as well as the historical operating data of the controlled battery.

[0005] Step 2: Build an equivalent circuit model and a heat collection model of the physical entity of a single battery on the terminal battery management system, and collect battery current and terminal voltage data in real time; perform parameter identification on the equivalent circuit model using the least squares method; estimate the battery's state of charge (SOC) based on the extended Kalman filter (EKF) and the identified equivalent circuit model; input the SOC estimation result into the SOC-OCV relationship sent by the cloud system to obtain the open-circuit voltage (OCV) value; use the obtained OCV value to perform parameter identification on the heat collection model; estimate the battery's heat generation rate based on the extended Kalman filter (EKF) and the identified heat collection model.

[0006] Step 3: Establish a Long Short-Term Memory Network (LSTMN) in the cloud system to predict the SOC-OCV relationship corresponding to different temperatures and charge / discharge rate characteristics online. The training of the LTMN specifically utilizes experimental data obtained from battery testing experiments, with historical battery temperature distribution and charge / discharge rate characteristic data as inputs, and OCV and the corresponding SOC standard segment as outputs. The final SOC-OCV relationship curve is obtained by polynomial fitting and sent to the terminal battery management system for real-time correction and updating of the model parameters of the model established on the terminal battery management system.

[0007] Step 4: The cloud system uses continuously collected test data and historical operating data of each battery cell to periodically train, adjust and update the LTSMN.

[0008] Furthermore, in step one, for the cylindrical battery as a physical entity, the integrated construction of the distributed temperature self-sensing system is achieved through the following steps: First, a hole is drilled in the center of the negative terminal of the battery cell in an inert gas environment, and its internal structure is sealed to protect it; then, the positive terminal is opened with a pipe cutter and sealed to prevent short circuits, while a distributed optical fiber is inserted into the battery from the negative terminal through the isolation layer; the resealed battery cell is connected to the terminal battery management system via electrical and optical communication, so that all battery cells and the terminal battery management system together constitute a distributed temperature self-sensing system capable of sensing the internal and surface temperatures of each cell.

[0009] Furthermore, in step two, the following equivalent circuit model containing two RC circuits is specifically established for each battery cell:

[0010]

[0011] V t (t)=V oc (t)+V p1 (t)+V p2 (t)+R0(t)I(t)

[0012] Where I is the battery load current, R1 and R2 are the polarization resistances of the two RC loops, C1 and C2 are the polarization capacitances of the two RC loops, R0 is the ohmic resistance, and V p1 and V p2 It is the voltage of two RC loops, V OC It is the open-circuit voltage, V t Where t is the terminal voltage and t is time;

[0013] The following discrete form is obtained after the Laplace transform:

[0014]

[0015] θ e =[k1 k2 k3 k4 k5] T

[0016]

[0017] in,

[0018]

[0019] Parameter matrix θ e The model parameters to be identified are obtained using the following least squares method:

[0020]

[0021] Where P(k) is the covariance matrix; K(k) is the gain matrix; e(k) is the estimation error; y is the output variable; and I is the identity matrix.

[0022] Furthermore, in step two, the following heat collection model is specifically established for each battery cell:

[0023]

[0024] Q(t)=I(t)(V oc (t)-V t (t))-λI(t)T a (t)

[0025] Among them, T c and T s These are the average values ​​of the center temperature and surface temperature of the battery cell, obtained through distributed optical fibers, respectively; C c R represents the heat capacity of the battery cell. c Indicates thermal resistance; Q is the heat generation rate, I(t) is the load current, and T is the load current. a It is T c and T s The average value, λI(t)T a(t) is the reversible entropic heat, where λ is the entropy coefficient;

[0026] The following discrete form is obtained after the Laplace transform:

[0027]

[0028] θ t =[1 α β γ] T

[0029]

[0030] Wherein, the parameter matrix θ t Let P(k) be the model parameters to be identified; K(k) be the covariance matrix; e(k) be the gain matrix; y be the estimation error; and I be the identity matrix.

[0031] Furthermore, in step three, the hidden state h of the neural unit in the LTMN at each time step t is specifically defined. t Data x from the same time step t Update, the hidden state of the previous time step h t-1 Input gate i t Input node g t Forgotten Gate f t Output gate o t and storage unit c t The updated formula is:

[0032]

[0033] In the formula, W and b are the layer weights and biases, respectively. fx and W fh These are the forgetting gates relative to x. t and h t-1 The two weight matrices, b f It is the bias term, σ is the sigmoid function; W ix and W ih These are the input gates relative to x t and h t-1 The two weight matrices, b i It is a bias term; W gx and W gh These are the activation functions of tanh relative to x. t and h t-1 The two weight matrices, b g It is a bias term; W ox and W oh These are the output gates relative to x. t and h t-1 The two weight matrices, b oIt is a bias term;

[0034] A dropout layer is introduced for model training. This layer randomly masks some hidden outputs, ensuring that these neurons do not affect forward propagation during training. The estimated standard open-circuit voltage matrix is ​​output based on the following formula:

[0035]

[0036] Among them, W out and b out These are the dropout layer weights and biases, and the output values ​​are... This corresponds to the OCV estimation result of the standard SOC array, with ReLU chosen as the activation function; for model training, the mean squared error (MSE) is used as the model loss.

[0037]

[0038] Where n is the number of training samples;

[0039] A well-trained LSTMN can output OCVs corresponding to the SOC list. output =[OCV1 OCV2 ... OCV] 10 ];

[0040] The SOC-OCV relationship is obtained by fitting the following polynomial:

[0041]

[0042] Where M is the highest coefficient of the polynomial, SOC j w represents the j-th power of SOC j For SOC j The coefficient;

[0043] The fitting error is characterized by the following formula:

[0044]

[0045] Where N is the number of samples; the final polynomial coefficients are obtained using the following formula:

[0046]

[0047] Accordingly, the present invention also provides an end-to-cloud collaborative battery management system based on embedded fiber optic sensing for performing the above-described method, which consists of a distributed temperature self-sensing system, a terminal battery management system and a cloud system;

[0048] Among them, the distributed temperature self-sensing system is used to obtain the internal and external temperature distribution of the battery physical entity;

[0049] The terminal battery management system is used to acquire battery cell temperature data and battery operation data collected by the distributed temperature self-sensing system. It performs multi-dimensional estimation of battery SOC and heat generation rate through the physical entity equivalent circuit model and heat collection model built on it, and uploads the collected raw data and the estimated battery state results to the cloud system.

[0050] The cloud system is used to store and process data uploaded by the terminal battery management system, and uses historical battery temperature distribution and charge / discharge rate characteristic data, as well as test experimental data, to train an LTMN network. The trained LTMN network is then applied online to estimate the SOC-OCV relationship. The obtained SOC-OCV relationship is then sent to the terminal battery management system to correct and update the parameters of each model.

[0051] The end-to-cloud collaborative battery management method and system based on embedded fiber optic sensing provided by the present invention senses the internal and external temperature distribution of individual battery cells by integrating a distributed temperature self-sensing system at the battery end. Battery modeling and state estimation are performed in the battery management system, and SOC-OCV curve estimation is performed in the cloud to guide the correction and updating of the terminal model. This achieves multi-level organic integration of data from the intelligent battery end, terminal, and cloud, giving the model higher accuracy and wider adaptability, and ensuring the richness of state estimation terms. Compared with the prior art, this significantly improves the accuracy and efficiency of battery electro-thermal management. Attached Figure Description

[0052] Figure 1 This is an optional structural block diagram of the system provided by the present invention;

[0053] Figure 2 This is a flowchart of the model parameter identification and state estimation process of the present invention.

[0054] Figure 3 This is a flowchart illustrating the integrated construction process of the distributed temperature self-sensing system of the present invention.

[0055] Figure 4 This is an optional flowchart for conducting battery testing experiments based on an example of the present invention. Detailed Implementation

[0056] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] The end-to-cloud collaborative battery management method based on embedded fiber optic sensing provided by this invention, such as... Figure 1 , 2As shown, the specific steps include:

[0058] Step 1: For the specific type of individual battery physical entity in the battery system to be monitored, a distributed temperature self-sensing system suitable for smart battery cells is constructed by integrating an embedded distributed fiber optic sensor system. The sensing data collected by the distributed temperature self-sensing system is then acquired by the terminal battery management system and uploaded to the cloud system. The cloud system stores specific cycle charge-discharge experimental data of the same type of battery cells in the experimental environment, as well as the historical operating data of the controlled battery.

[0059] Step 2: Build an equivalent circuit model and a heat collection model of the physical entity of a single battery on the terminal battery management system, and collect battery current and terminal voltage data in real time; perform parameter identification on the equivalent circuit model using the least squares method; estimate the battery's state of charge (SOC) based on the extended Kalman filter (EKF) and the identified equivalent circuit model; input the SOC estimation result into the SOC-OCV relationship sent by the cloud system to obtain the open-circuit voltage (OCV) value; use the obtained OCV value to perform parameter identification on the heat collection model; estimate the battery's heat generation rate based on the extended Kalman filter (EKF) and the identified heat collection model.

[0060] Step 3: Establish a Long Short-Term Memory (LSTMN) network in the cloud system to predict the SOC-OCV relationship corresponding to different temperatures and charge / discharge rates online; the training of the LTMN specifically utilizes... Figure 4 The experimental data obtained from the battery test experiment shown takes the historical temperature distribution and charge / discharge rate characteristic data of the battery as input, and OCV and the corresponding SOC standard segment as output. The final SOC-OCV relationship curve is obtained by polynomial fitting and sent to the terminal battery management system for real-time correction and updating of the model parameters of the model established on the terminal battery management system.

[0061] Step 4: The cloud system uses continuously collected test data and historical operating data of each battery cell to periodically train, adjust and update the LTSMN.

[0062] In a preferred embodiment of the present invention, step one involves, for the cylindrical battery as a physical entity, sequentially performing the following steps: Figure 3The steps shown demonstrate the integrated construction of a distributed temperature self-sensing system: First, in an inert gas environment, drill a 0.9 mm diameter hole in the center of the negative terminal of the battery cell and seal it with Kapton tape to protect its internal structure; then, open the positive terminal with a tube cutter and seal it with Kapton tape to prevent short circuits, while simultaneously inserting distributed optical fibers from the negative terminal through the insulating layer into the battery; finally, establish an electrical and optical communication connection between the resealed battery cell and the terminal battery management system, so that all battery cells and the terminal battery management system together constitute a distributed temperature self-sensing system capable of sensing the internal and surface temperatures of each cell.

[0063] In a preferred embodiment of the present invention, step two specifically establishes the following equivalent circuit model for a single battery cell, which includes two RC circuits:

[0064]

[0065] V t (t)=V oc (t)+V p1 (t)+V p2 (t)+R0(t)I(t)

[0066] Where I is the battery load current, R1 and R2 are the polarization resistances of the two RC loops, C1 and C2 are the polarization capacitances of the two RC loops, R0 is the ohmic resistance, and V p1 and V p2 It is the voltage of two RC loops, V OC It is the open-circuit voltage, V t Where t is the terminal voltage and t is time;

[0067] The following discrete form is obtained after the Laplace transform:

[0068]

[0069] θ e =[k1 k2 k3 k4 k5] T

[0070]

[0071] in,

[0072]

[0073] Parameter matrix θ e The model parameters to be identified are obtained using the following least squares method:

[0074]

[0075] Where P(k) is the covariance matrix; K(k) is the gain matrix; e(k) is the estimation error; y is the output variable; and I is the identity matrix.

[0076] In a preferred embodiment of the present invention, step two specifically establishes a heat collection model for the battery cell in the following form:

[0077]

[0078] Q(t)=I(t)(V oc (t)-V t (t))-λI(t)T a (t)

[0079] Among them, T c and T s These are the average values ​​of the center temperature and surface temperature of the battery cell, obtained through distributed optical fibers, respectively; C c R represents the heat capacity of the battery cell. c Indicates thermal resistance; Q is the heat generation rate, I(t) is the load current, and T is the load current. a It is T c and T s The average value, λI(t)T a (t) is the reversible entropic heat, where λ is the entropy coefficient;

[0080] The following discrete form is obtained after the Laplace transform:

[0081]

[0082] θ t =[1αβγ] T

[0083]

[0084] Wherein, the parameter matrix θ t Let P(k) be the model parameters to be identified; K(k) be the covariance matrix; e(k) be the gain matrix; y be the estimation error; and I be the identity matrix.

[0085] Using the equivalent circuit model, the Extended Kalman Filter (EKF) algorithm can be performed to estimate the battery's State of Charge (SOC).

[0086]

[0087] In a preferred embodiment of the present invention, step three specifically defines the hidden state h of the neural unit in the LTMN at each time step t. t Data x from the same time step t Update, the hidden state of the previous time step h t-1Input gate i t Input node g t Forgotten Gate f t Output gate o t and storage unit c t The updated formula is:

[0088]

[0089] In the formula, W and b are the layer weights and biases, respectively. fx and W fh These are the forgetting gates relative to x. t and h t-1 The two weight matrices, b f It is the bias term, σ is the sigmoid function; W ix and W ih These are the input gates relative to x t and h t-1 The two weight matrices, b i It is a bias term; W gx and W gh These are the activation functions of tanh relative to x. t and h t-1 The two weight matrices, b g It is a bias term; W ox and W oh These are the output gates relative to x. t and h t-1 The two weight matrices, b o It is a bias term;

[0090] A dropout layer is introduced for model training. This layer randomly masks some hidden outputs, ensuring that these neurons do not affect forward propagation during training. The estimated standard open-circuit voltage matrix is ​​output based on the following formula:

[0091]

[0092] Among them, W out and b out These are the dropout layer weights and biases, and the output values ​​are... This corresponds to the OCV estimation result of the standard SOC array, with ReLU chosen as the activation function; for model training, the mean squared error (MSE) is used as the model loss.

[0093]

[0094] Where n is the number of training samples;

[0095] A well-trained LSTMN can output OCVs corresponding to the SOC list. output=[OCV1 OCV2 ... OCV] 10 ];

[0096] The SOC-OCV relationship was obtained by fitting the following polynomial:

[0097]

[0098] Where M is the highest coefficient of the polynomial, and in this embodiment, M = 6, SOC j w represents the j-th power of SOC j For SOC j The coefficient;

[0099] The fitting error is characterized by the following formula:

[0100]

[0101] Where N is the number of samples, and in this embodiment, N = 10; the final polynomial coefficients are obtained by the following formula:

[0102]

[0103] Accordingly, the present invention also provides an end-to-cloud collaborative battery management system based on embedded fiber optic sensing for performing the above-described method, which consists of a distributed temperature self-sensing system, a terminal battery management system and a cloud system;

[0104] Among them, the distributed temperature self-sensing system is used to obtain the internal and external temperature distribution of the battery physical entity;

[0105] The terminal battery management system is used to acquire battery cell temperature data and battery operation data collected by the distributed temperature self-sensing system. It performs multi-dimensional estimation of battery SOC and heat generation rate through the physical entity equivalent circuit model and heat collection model built on it, and uploads the collected raw data and the estimated battery state results to the cloud system.

[0106] The cloud system is used to store and process data uploaded by the terminal battery management system, and uses historical battery temperature distribution and charge / discharge rate characteristic data, as well as test experimental data, to train an LTMN network. The trained LTMN network is then applied online to estimate the SOC-OCV relationship. The obtained SOC-OCV relationship is then sent to the terminal battery management system to correct and update the parameters of each model.

[0107] In practical implementation, the terminal battery management system can be manufactured using, but is not limited to, hardware unit modules, display modules, communication modules, and related wiring harnesses and structural components (covers, brackets, bolts, etc.). Its operating model and corresponding SOC and battery heat generation rate estimation algorithms can be developed and implemented based on a battery management system developed for a charge / discharge machine or embedded system. The cloud system may include, but is not limited to, data transmission modules, cloud computing modules, and data storage modules. Data interaction between the distributed temperature self-sensing system and the terminal battery management system can be achieved through, but is not limited to, a control area network. Data interaction between the terminal battery management system and the cloud system can be achieved through wireless communication technologies, including but not limited to ZigBee, Wi-Fi, and 3G / 4G / 5G.

[0108] It should be understood that the sequence number of each step in the embodiments of the present invention does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0109] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An end-to-cloud collaborative battery management method based on embedded fiber optic sensing, characterized in that: Specifically, the following steps are included: Step 1: For the specific type of single cell physical entity in the battery system to be monitored, a distributed temperature self-sensing system suitable for smart battery cells is built by integrating an embedded distributed fiber optic sensor system. The sensing data collected by the distributed temperature self-sensing system is then obtained by the terminal battery management system and uploaded to the cloud system. The cloud system stores specific cycle charge-discharge test data of the same type of battery cells in the experimental environment, as well as historical operating data of the controlled batteries; Step 2: Build an equivalent circuit model and a heat collection model of the physical entity of a single battery on the terminal battery management system, and collect battery current and terminal voltage data in real time; identify the parameters of the equivalent circuit model based on the least squares method. Battery state of charge (SOC) is estimated based on the extended Kalman filter (EKF) and the identified equivalent circuit model; the SOC estimation result is input into the SOC-OCV relationship sent by the cloud system to obtain the open-circuit voltage (OCV) value; the obtained OCV value is used to identify the parameters of the heat collector model. The battery heat generation rate is estimated based on the extended Kalman filter (EKF) and the identified heat collection model. Step 3: Establish a Long Short-Term Memory Network (LSTMN) in the cloud system to predict the SOC-OCV relationship corresponding to different temperatures and charge / discharge rate characteristics online. The training of the LTMN specifically utilizes experimental data obtained from battery testing experiments, with historical battery temperature distribution and charge / discharge rate characteristic data as inputs, and OCV and the corresponding SOC standard segment as outputs. The final SOC-OCV relationship curve is obtained by polynomial fitting and sent to the terminal battery management system for real-time correction and updating of the model parameters of the model established on the terminal battery management system. Step 4: The cloud system uses continuously collected test data and historical operating data of each battery cell to periodically train, adjust and update the LTSMN.

2. The method as described in claim 1, characterized in that: In Step 1, for the cylindrical battery as a physical entity, the integrated construction of the distributed temperature self-sensing system is achieved through the following steps: First, a hole is drilled in the center of the negative terminal of the battery cell in an inert gas environment, and its internal structure is sealed to protect it; then, the positive terminal is opened with a tube cutter and sealed to prevent short circuits, while a distributed optical fiber is inserted into the battery from the negative terminal through the insulation layer; the resealed battery cell is connected to the terminal battery management system via electrical and optical communication, so that all battery cells and the terminal battery management system together constitute a distributed temperature self-sensing system capable of sensing the internal and surface temperatures of each cell.

3. The method as described in claim 1, characterized in that: In step two, the following equivalent circuit model containing two RC circuits is specifically established for each battery cell: V t (t)=V oc (t)+V p1 (t)+V p2 (t)+R0(t)I(t) Where I(t) is the battery load current, R1 and R2 are the polarization resistances of the two RC loops, C1 and C2 are the polarization capacitances of the two RC loops, R0 is the ohmic resistance, and V p1 and V p2 It is the voltage of two RC loops, V OC It is the open-circuit voltage, V t Where t is the terminal voltage and t is time; The following discrete form is obtained after the Laplace transform: θ e =[k1 k2 k3 k4 k5] T in, Parameter matrix θ e The model parameters to be identified are obtained using the following least squares method: Where P(k) is the covariance matrix; K(k) is the gain matrix; e(k) is the estimation error; y is the output variable; and I is the identity matrix.

4. The method as described in claim 1, characterized in that: In step two, the following heat collection model is specifically established for each battery cell: Q(t)=I(t)(V oc (t)-V t (t))-λI(t)T a (t) Among them, T c and T s These are the average values ​​of the center temperature and surface temperature of the battery cell, obtained through distributed optical fibers, respectively; C c R represents the heat capacity of the battery cell. c Indicates thermal resistance; Q is the heat generation rate, I(t) is the load current, and T is the load current. a It is T c and T s The average value, λI(t)T a (t) is the reversible entropic heat, where λ is the entropy coefficient; The following discrete form is obtained after the Laplace transform: i t =[1a bg] T Wherein, the parameter matrix θ t Let P(k) be the model parameters to be identified; K(k) be the covariance matrix; e(k) be the gain matrix; y be the estimation error; and I be the identity matrix.

5. The method as described in claim 1, characterized in that: Step 3 specifically defines the hidden state h of the neural unit in the LTMN at each time step t. t Data x from the same time step t Update, the hidden state of the previous time step h t-1 Input gate i t Input node g t Forgotten Gate f t Output gate o t and storage unit c t The updated formula is: In the formula, W and b are the layer weights and biases, respectively. fx and W fh These are the forgetting gates relative to x. t and h t-1 The two weight matrices, b f It is the bias term, σ is the sigmoid function; W ix and W ih These are the input gates relative to x t and h t-1 The two weight matrices, b i It is a bias term; W gx and W gh These are the activation functions of tanh relative to x. t and h t-1 The two weight matrices, b g It is a bias term; W ox and W oh These are the output gates relative to x. t and h t-1 The two weight matrices, b o It is a bias term; A dropout layer is introduced for model training. The dropout layer randomly masks some of the hidden outputs, so that these neurons do not affect the forward propagation during training. The estimated result of the standard open-circuit voltage matrix is ​​output based on the following formula: Among them, W out and b out These are the dropout layer weights and biases, and the output values ​​are... This corresponds to the OCV estimation result of the standard SOC array, with ReLU chosen as the activation function; for model training, the mean squared error (MSE) is used as the model loss. Where n is the number of training samples; A well-trained LSTMN can output OCVs corresponding to the SOC list. output =[OCV1 OCV2...OCV 10 ]; The SOC-OCV relationship was obtained by fitting the following polynomial: Where M is the highest coefficient of the polynomial, SOC j w represents the j-th power of SOC j For SOC j The coefficient; The fitting error is characterized by the following formula: Where N is the number of samples; the final polynomial coefficients are obtained using the following formula:

6. An end-to-cloud collaborative battery management system based on embedded fiber optic sensing for performing the method according to any one of claims 1-5, characterized in that: It consists of a distributed temperature self-sensing system, a terminal battery management system, and a cloud system; Among them, the distributed temperature self-sensing system is used to obtain the internal and external temperature distribution of the battery physical entity; The terminal battery management system is used to acquire battery cell temperature data and battery operation data collected by the distributed temperature self-sensing system. It performs multi-dimensional estimation of battery SOC and heat generation rate through the physical entity equivalent circuit model and heat collection model built on it, and uploads the collected raw data and the estimated battery state results to the cloud system. The cloud system is used to store and process data uploaded by the terminal battery management system, and uses historical battery temperature distribution and charge / discharge rate characteristic data, as well as test experimental data, to train an LTMN network. The trained LTMN network is then applied online to estimate the SOC-OCV relationship. The obtained SOC-OCV relationship is then sent to the terminal battery management system to correct and update the parameters of each model.

Images