Battery state evaluation method of intelligent lithium ion battery and intelligent lithium ion battery

Abstract

The invention relates to a battery state evaluation method of an intelligent lithium ion battery and the intelligent lithium ion battery. The method comprises the following steps: collecting current sensing signals of a plurality of sensors and battery data of a lithium ion battery, and adjusting each dimension battery model based on the battery data to obtain each target battery model corresponding to the lithium ion battery; simulating the operation process of the lithium ion battery through each target battery model on the basis of each current sensing signal to obtain simulation operation data of each target battery model, and identifying a sub-battery state corresponding to each target battery model on the basis of the simulation operation data of each target battery model; and based on the sub-battery state corresponding to each target battery model, identifying the target battery state of the lithium ion battery through a fusion algorithm. By adopting the method, the battery state evaluation accuracy of the lithium ion battery can be effectively improved.

Description

Technical Field

[0001] This application relates to the field of lithium-ion battery technology, and in particular to a method for assessing the state of a smart lithium-ion battery and a smart lithium-ion battery. Background Technology

[0002] As the application of lithium-ion batteries expands, the requirements for their safety and lifespan are also increasing. During use, batteries may encounter problems such as overcharging, over-discharging, overheating, and internal short circuits. Existing protection measures often fail to respond quickly enough or are not intelligent enough, and cannot effectively prevent battery damage or thermal runaway. Furthermore, the battery's state of charge, state of power, state of energy, and aging state exhibit strong nonlinear mapping relationships with voltage, current, and temperature. Therefore, accurate assessment and analysis of battery status is a current research focus.

[0003] Traditional battery status assessment methods rely on battery management algorithms to analyze and calculate the battery status of lithium-ion batteries. However, existing battery management algorithms are not accurate or intelligent enough to accurately assess battery status, resulting in low accuracy in assessing the battery status of lithium-ion batteries. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for assessing the state of a smart lithium-ion battery, addressing the aforementioned technical problems.

[0005] In a first aspect, this application provides a method for evaluating the state of a smart lithium-ion battery, including:

[0006] Collect current sensing signals from multiple sensors and battery data from lithium-ion batteries, and adjust the battery models in each dimension based on the battery data to obtain the target battery models corresponding to the lithium-ion batteries.

[0007] Based on the current sensing signals, the operation process of the lithium-ion battery is simulated through the target battery models to obtain the simulation operation data of the target battery models. Based on the simulation operation data of the target battery models, the sub-battery state corresponding to each target battery model is identified.

[0008] Based on the sub-battery state corresponding to each target battery model, the target battery state of the lithium-ion battery is identified through a fusion algorithm.

[0009] Optionally, adjusting the battery model across various dimensions based on the battery data to obtain the target battery models corresponding to the lithium-ion battery includes:

[0010] Based on the battery data, identify the various battery parameters of the lithium-ion battery;

[0011] Query the parameter requirements of each dimension battery model for lithium-ion batteries, and based on the parameter requirements of each dimension battery model for lithium-ion batteries, filter the target battery parameters required by each dimension battery model from the battery parameters of the lithium-ion batteries.

[0012] Based on the target battery parameters required by each dimension battery model, the model update process is performed on each dimension battery model to obtain the target battery models corresponding to the lithium-ion battery.

[0013] Optionally, the step of simulating the operation of the lithium-ion battery based on each of the current sensing signals and using each of the target battery models to obtain simulation operation data for each of the target battery models includes:

[0014] Identify the target battery model corresponding to each current sensing signal, and for each target battery model, input the current sensing signal corresponding to the target battery model into the target battery model to simulate the operation process of the lithium-ion battery and obtain the operation log information of the target battery model;

[0015] Based on the operation log information, the battery state data change information of the lithium-ion battery is extracted, and the battery state data change information of the lithium-ion battery is used as the simulation operation data of the target battery model.

[0016] Optionally, identifying the sub-cell state corresponding to each target battery model based on the simulation running data of each target battery model includes:

[0017] Based on the battery state data change information of the lithium-ion battery simulated by each target battery model, identify each battery state parameter and the battery state type simulated by each target battery model.

[0018] Based on the battery state parameters simulated by each target battery model, the sub-battery state of each target battery model is identified by the battery state evaluation algorithm corresponding to the battery state type simulated by each target battery model.

[0019] The sub-cell states of each cell state type simulated by each target cell model are taken as the sub-cell states corresponding to each target cell model.

[0020] Optionally, the step of identifying the target battery state of the lithium-ion battery based on the sub-battery state corresponding to each target battery model through a fusion algorithm includes:

[0021] Based on the battery state type corresponding to each of the sub-battery states, the battery state weight value of each sub-battery state is adapted.

[0022] The target battery state of the lithium-ion battery is calculated by using a fusion algorithm to combine the battery state state of each sub-battery and the battery state weight value of each sub-battery state.

[0023] Optionally, the method further includes:

[0024] Based on the current sensing signals of each sensor, the current thermal runaway cause and current thermal runaway information of the lithium-ion battery are identified through a thermal runaway analysis strategy.

[0025] Based on the current cause of thermal runaway of the lithium-ion battery and the current thermal runaway information of the lithium-ion battery, a thermal runaway early warning information for the lithium-ion battery is generated.

[0026] Secondly, this application also provides a battery state assessment system for a smart lithium-ion battery, which includes a sensor module, a data transmission module, and a control processing module, wherein:

[0027] The sensor module is connected to the data transmission module, and the data transmission module is connected to the control processing module;

[0028] The sensor module includes multiple sensor types for detecting various sensing signals from the lithium-ion battery and transmitting each sensing signal to the data transmission module.

[0029] The data transmission module includes a wireless communication module or a wired communication module, used to transmit each of the sensor signals to the control processing module;

[0030] The control and processing module is used to collect current sensing signals from multiple sensors and battery data from the lithium-ion battery, and adjust the battery models of each dimension based on the battery data to obtain target battery models corresponding to the lithium-ion battery; based on the current sensing signals, simulate the operation process of the lithium-ion battery through each target battery model to obtain simulation operation data of each target battery model, and identify the sub-battery state corresponding to each target battery model based on the simulation operation data of each target battery model; based on the sub-battery state corresponding to each target battery model, identify the target battery state of the lithium-ion battery through a fusion algorithm.

[0031] Thirdly, this application also provides a battery state assessment device for a smart lithium-ion battery, comprising:

[0032] The acquisition module is used to acquire the current sensing signals of multiple sensors and the battery data of the lithium-ion battery, and adjust the battery model in each dimension based on the battery data to obtain the target battery model corresponding to the lithium-ion battery.

[0033] The simulation module is used to simulate the operation process of the lithium-ion battery based on the current sensing signals and through the target battery models, to obtain the simulation operation data of the target battery models, and to identify the sub-battery state corresponding to each target battery model based on the simulation operation data of the target battery models.

[0034] The identification module is used to identify the target battery state of the lithium-ion battery based on the sub-battery state corresponding to each target battery model through a fusion algorithm.

[0035] Optionally, the acquisition module is specifically used for:

[0036] Based on the battery data, identify the various battery parameters of the lithium-ion battery;

[0037] Query the parameter requirements of each dimension battery model for lithium-ion batteries, and based on the parameter requirements of each dimension battery model for lithium-ion batteries, filter the target battery parameters required by each dimension battery model from the battery parameters of the lithium-ion batteries.

[0038] Based on the target battery parameters required by each dimension battery model, the model update process is performed on each dimension battery model to obtain the target battery models corresponding to the lithium-ion battery.

[0039] Optionally, the simulation module is specifically used for:

[0040] Identify the target battery model corresponding to each current sensing signal, and for each target battery model, input the current sensing signal corresponding to the target battery model into the target battery model to simulate the operation process of the lithium-ion battery and obtain the operation log information of the target battery model;

[0041] Based on the operation log information, the battery state data change information of the lithium-ion battery is extracted, and the battery state data change information of the lithium-ion battery is used as the simulation operation data of the target battery model.

[0042] Optionally, the simulation module is specifically used for:

[0043] Based on the battery state data change information of the lithium-ion battery simulated by each target battery model, identify each battery state parameter and the battery state type simulated by each target battery model.

[0044] Based on the battery state parameters simulated by each target battery model, the sub-battery state of each target battery model is identified by the battery state evaluation algorithm corresponding to the battery state type simulated by each target battery model.

[0045] The sub-cell states of each cell state type simulated by each target cell model are taken as the sub-cell states corresponding to each target cell model.

[0046] Optionally, the identification module is specifically used for:

[0047] Based on the battery state type corresponding to each of the sub-battery states, the battery state weight value of each sub-battery state is adapted.

[0048] The target battery state of the lithium-ion battery is calculated by using a fusion algorithm to combine the battery state state of each sub-battery and the battery state weight value of each sub-battery state.

[0049] Optionally, the device may also include:

[0050] The thermal runaway analysis module is used to identify the current thermal runaway cause and the current thermal runaway information of the lithium-ion battery based on the current sensing signals of each sensor and through a thermal runaway analysis strategy.

[0051] The early warning module is used to generate early warning information for thermal runaway of the lithium-ion battery based on the current cause of thermal runaway and the current thermal runaway information of the lithium-ion battery.

[0052] Fourthly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0053] Fifthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0054] Sixthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0055] The aforementioned method for assessing the state of a smart lithium-ion battery and the smart lithium-ion battery itself involve collecting current sensing signals from multiple sensors and battery data from the lithium-ion battery. Based on this battery data, the battery model is adjusted across various dimensions to obtain target battery models corresponding to the lithium-ion battery. Based on the current sensing signals, the operating process of the lithium-ion battery is simulated using each target battery model to obtain simulation operating data for each target battery model. Based on this simulation operating data, the sub-battery state corresponding to each target battery model is identified. Finally, based on the sub-battery states corresponding to each target battery model, a fusion algorithm is used to identify the target battery state of the lithium-ion battery. This scheme collects current sensing signals from multiple sensors and combines them with various battery models of the lithium-ion battery. The operating process of the lithium-ion battery is simulated according to the current sensing signals to obtain simulation operating data for each battery model. Then, the battery management algorithm is used to calculate the sub-battery state of the lithium-ion battery under each simulation strategy. This not only effectively avoids the low precision and accuracy problems of direct algorithm calculation of battery state information, but also improves the comprehensiveness of battery state identification from different sensing angles. Next, this scheme fuses the identified sub-battery states using a fusion algorithm to obtain the target battery state of the lithium-ion battery. This allows for multi-angle analysis of the lithium-ion battery state and the fusion calculation of the target battery state based on the combined analysis of various angles. This achieves the goal of classification simulation and state identification based on real-time acquired sensor signals, effectively improving the accuracy of lithium-ion battery state assessment. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a system architecture diagram of a battery state assessment system for a smart lithium-ion battery in one embodiment;

[0058] Figure 2 This is a flowchart illustrating a method for assessing the state of a smart lithium-ion battery in one embodiment.

[0059] Figure 3 This is a schematic diagram of the battery structure of a smart lithium-ion battery in one embodiment;

[0060] Figure 4 This is a schematic diagram of the battery structure of a smart lithium-ion battery in another embodiment;

[0061] Figure 5 This is a schematic diagram of the battery state of charge assessment process in one embodiment;

[0062] Figure 6 This is a schematic diagram of the battery thermal runaway state assessment process in one embodiment;

[0063] Figure 7 This is a flowchart illustrating an example of battery state assessment for a smart lithium-ion battery in one embodiment.

[0064] Figure 8 This is a structural block diagram of a battery state assessment device for a smart lithium-ion battery in one embodiment.

[0065] Figure 9 This is an internal structural diagram of a computer device in one embodiment.

[0066] Figure Labels

[0067] 1- Soft-pack lithium-ion battery core, including lithium iron phosphate positive electrode, separator, graphite negative electrode, and electrolyte; 2- Built-in thin-film pressure sensor; 3- Positive electrode tab; 4- Negative electrode tab; 5- Soft-pack battery aluminum-plastic film encapsulation; 6- Wiring harness connecting the battery to the load; 7- External voltage sensor; 8- External load; 9- External current sensor; 10- Current sensor data transmission harness; 11- Voltage sensor data transmission harness; 12- Thin-film pressure sensor data transmission harness; 13- Control module; 14- Wireless communication; 15- Square-shell lithium-ion battery core, including nickel-cobalt-manganese ternary material positive electrode, separator, graphite negative electrode, and electrolyte; 16- Square-shell battery aluminum shell encapsulation; 17- Positive electrode post; 18- Negative electrode post; 19- Pressure sensor; 20- Small hole on the battery casing; 21- Pressure sensor data transmission harness; 22- CAN (Controller Area Network) communication harness between the control module and the upper-level control system. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0069] The battery state assessment method for smart lithium-ion batteries provided in this application embodiment can be applied to a battery state assessment system for smart lithium-ion batteries. This system includes a sensor module, a data transmission module, and a control processing module. The sensor module is connected to the data transmission module, which in turn is connected to the control processing module. The sensor module includes multiple sensors for collecting sensor information from the lithium-ion battery. The data transmission module transmits this sensor information to the control processing module wirelessly / wired. The control processing module can be a terminal, a server, or a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc. The terminal collects the current sensing signals from multiple sensors and, combined with various battery models of the lithium-ion battery, simulates the operation process of the lithium-ion battery according to the current sensing signals, obtaining simulation operation data for the battery model. Then, the battery management algorithm is used to calculate the sub-battery state of the lithium-ion battery under each simulation strategy. This not only effectively avoids the low precision and accuracy problems of direct algorithm calculation of battery state information, but also improves the comprehensiveness of battery state identification from different sensing angles. Next, this scheme fuses the identified sub-battery states using a fusion algorithm to obtain the target battery state of the lithium-ion battery. This allows for multi-angle analysis of the lithium-ion battery state and the fusion calculation of the target battery state based on the combined analysis of various angles. This achieves the goal of classification simulation and state identification based on real-time acquired sensor signals, effectively improving the accuracy of lithium-ion battery state assessment.

[0070] In one exemplary embodiment, such as Figure 2 As shown, a method for assessing the state of a smart lithium-ion battery is provided, which can be applied to applications such as... Figure 1 As shown, the control processing module is used as an example for illustration, including the following steps S201 to S203. Wherein:

[0071] Step S201: Collect the current sensing signals of multiple sensors and the battery data of the lithium-ion battery, and adjust the battery models of each dimension based on the battery data to obtain the target battery models corresponding to the lithium-ion battery.

[0072] In this embodiment, the terminal receives real-time sensor signals from various sensors transmitted by the data transmission module to obtain the current sensor signal of each sensor. These sensors are built-in sensors, including but not limited to voltage sensors, current sensors, temperature sensors, pressure sensors, strain sensors, air pressure sensors, positive and negative electrode potential sensors, and fiber optic sensors. Each sensor collects one sensor signal. Then, in response to the operator's battery data upload operation, the terminal obtains the battery data of the lithium-ion battery whose state needs to be identified. This battery data is the battery electrical data of the lithium-ion battery, specifically the electrical parameters corresponding to the battery's charging and discharging process. Examples of this battery electrical data include current transmission mode, current conversion rate, and current transmission loss. Then, the terminal uses the battery data to update the preset battery models in various dimensions, thereby obtaining target battery models capable of simulating the lithium-ion battery. These battery models include, but are not limited to, mechanical, electrochemical, and thermal battery models. The specific adjustment process will be explained in detail later. Among them, each target dimension battery is used to simulate the current operation process of the lithium-ion battery through the current sensing signal, thereby identifying the operating data of the lithium-ion battery.

[0073] Among them, the lithium-ion battery is a smart lithium-ion battery, such as... Figure 3 As shown, this intelligent lithium-ion battery is based on external voltage sensing, external current sensing, external temperature sensing, and a built-in thin-film pressure sensing. Its positive electrode material is lithium iron phosphate, and its negative electrode material is graphite. It is encapsulated in an aluminum-plastic film and has a rated capacity of 1Ah. The battery exterior includes voltage and current sensors, which are connected to a load via a load connection line. The current and voltage sensors are connected to an external control module via a data acquisition harness. A thin-film pressure sensor is built into the aluminum-plastic film and outside the battery core. This built-in pressure sensor transmits data to the external control module via two copper wires. At the battery's thermo-sealed location, tab adhesive ensures the battery's airtightness. The external control module receives and stores voltage, current, and pressure data, then performs battery state estimation based on an algorithm, and finally communicates wirelessly with the upper-level management control module via Bluetooth.

[0074] In another embodiment, such as Figure 4As shown, this intelligent lithium-ion battery is based on an external voltage sensor, an external current sensor, and a pressure sensor connected to the internal gas domain. Its positive electrode material is a nickel-cobalt-manganese ternary material, and its negative electrode material is graphite. It is encapsulated in an aluminum square casing and has a rated capacity of 100Ah. The battery exterior includes voltage and current sensors; the battery exterior is connected to a load via a load connection line; the current and voltage sensors are connected to an external control module via a data acquisition harness; the battery is equipped with a pressure sensor, which connects to the internal gas domain through a small hole at the top of the battery. The edge of the pressure sensor is welded to ensure the battery's airtightness; therefore, the pressure-sensitive module of the pressure sensor is built into the internal gas atmosphere of the battery. The pressure sensor transmits data to the external control module via a data sampling line; the external control module receives and stores voltage, current, and gas pressure data, then performs battery state estimation based on an algorithm, and finally communicates with the upper-level management control module via CAN communication.

[0075] Step S202: Based on each current sensor signal, simulate the operation process of the lithium-ion battery through each target battery model to obtain the simulation operation data of each target battery model, and identify the sub-battery state corresponding to each target battery model based on the simulation operation data of each target battery model.

[0076] In this embodiment, the terminal identifies the current sensor signals corresponding to each target battery model, and then simulates the operation of a lithium-ion battery through each target battery model based on these current sensor signals, obtaining simulation operation data for each target battery model. This simulation operation data is mainly used to characterize the operation data of the lithium-ion battery. Then, based on the simulation operation data of each target battery model, the terminal identifies the sub-battery state corresponding to each target battery model. The sub-battery state is identified by the terminal combining the simulation operation data with different battery state type evaluation algorithms to perform state evaluation processing, thereby evaluating the sub-battery state of each battery state type. The battery state types of each sub-battery state include, but are not limited to, battery state of charge, state of energy, state of power, health, safety, and charge / discharge states. Different battery state assessment algorithms include, but are not limited to, battery state-of-charge estimation algorithms based on ampere-hour integration, open-circuit voltage / mechanical pressure mapping, Kalman filtering, or artificial intelligence mapping; energy state estimation algorithms based on battery model time-series simulation, table lookup, mapping, or artificial intelligence-driven algorithms; power state estimation algorithms based on battery model instantaneous simulation, table lookup, or artificial intelligence-driven algorithms; health state estimation algorithms based on dual-tank algorithms, two-point methods, table lookup, mapping, or artificial intelligence-driven algorithms; safety state estimation algorithms based on anomaly threshold methods, data-driven, or artificial intelligence-driven algorithms; and charge / discharge state estimation algorithms based on logical judgment. The specific identification process will be explained in detail later.

[0077] Step S203: Based on the sub-battery state corresponding to each target battery model, the target battery state of the lithium-ion battery is identified through a fusion algorithm.

[0078] In this embodiment, the terminal identifies the target battery state of the lithium-ion battery based on the sub-battery state corresponding to each target battery model using a fusion algorithm. Each sub-battery state corresponds to a battery state weight value. The terminal performs a weighted summation process using this battery state weight value and each sub-battery state through the fusion algorithm to obtain the target battery state of the lithium-ion battery. The calculation formula for this fusion algorithm is as follows:

[0079] SOC = a1SOC1 + a2SOC2 + ... + anSOCn

[0080] In the above formula, SOC is the target battery state, SOC1, SOC2, ..., SOCn are the sub-battery states, n is the virtual number of each sub-battery state, and a1, a2, ..., an are the battery state weight values ​​corresponding to each sub-battery state.

[0081] Based on the above scheme, by collecting current sensing signals from multiple sensors and combining them with various battery models of lithium-ion batteries, the operation process of the lithium-ion battery is simulated according to the current sensing signals to obtain the simulation operation data of the battery model. Then, the battery management algorithm is used to calculate the sub-battery state of the lithium-ion battery under each simulation strategy. This not only effectively avoids the low precision and low accuracy problems of direct algorithm calculation of battery state information, but also improves the comprehensiveness of battery state identification from different sensing angles. Then, this scheme fuses the identified sub-battery states through a fusion algorithm to obtain the target battery state of the lithium-ion battery. This allows for the analysis of the battery state of lithium-ion batteries from multiple perspectives, and also allows for the fusion calculation of the target battery state by combining the battery states analyzed from various perspectives. This achieves the goal of classification simulation and classification state identification based on real-time acquired current sensing signals, thereby effectively improving the accuracy of lithium-ion battery state assessment.

[0082] Optionally, based on battery data, adjust the battery models of each dimension to obtain the target battery models corresponding to the lithium-ion battery. This includes: identifying the battery parameters of the lithium-ion battery based on the battery data; querying the parameter requirements of each dimension battery model for the lithium-ion battery, and based on the parameter requirements of each dimension battery model for the lithium-ion battery, filtering the target battery parameters required by each dimension battery model from the battery parameters of the lithium-ion battery; and updating each dimension battery model based on the target battery parameters required by each dimension battery model to obtain the target battery models corresponding to the lithium-ion battery.

[0083] In this embodiment, the terminal identifies various battery parameters of the lithium-ion battery based on battery data. Then, the terminal queries the parameter requirements of each dimension of the battery model for the lithium-ion battery. Different dimension battery models simulate battery operation differently; therefore, the model parameters in different dimension battery models correspond to one or more battery parameters among the various battery parameters required by the lithium-ion battery. These battery parameters include, but are not limited to, the specification parameters of the lithium-ion battery and the electrical parameter values ​​for various electrical characteristic types. The electrical characteristic types include, but are not limited to, current transmission method type, current conversion rate type, current transmission loss type, and current fluctuation range type. The terminal identifies the various battery parameters of the lithium-ion battery by first extracting the specification data from the battery data and using the identifier data of each specification parameter in the specification data as the specification parameters. Then, the terminal uses the data parameter conversion program corresponding to the COMSOL Multiphysics software to convert the sub-battery data marked with electrical characteristic types in the battery data into electrical parameter values ​​for each electrical characteristic type.

[0084] Then, based on the parameter requirements of each dimension battery model for lithium-ion batteries, the terminal identifies the required battery parameters for each dimension battery model. Next, the terminal filters the target battery parameters required by each dimension battery model from among the lithium-ion battery parameters. Finally, based on the target battery parameters required by each dimension battery model, the terminal performs model update processing on each dimension battery model to obtain the target battery models corresponding to the lithium-ion batteries.

[0085] Based on the above scheme, by combining the battery data of each lithium-ion battery, the battery parameters of the lithium-ion battery characteristics are identified. Then, the terminal updates and adjusts the battery model of each dimension according to the battery parameter requirements of each dimension battery model, thereby obtaining a target battery model that can simulate the lithium-ion battery and improving the simulation accuracy of the target battery model.

[0086] Optionally, based on each current sensor signal, the operation process of a lithium-ion battery is simulated using each target battery model to obtain simulation operation data for each target battery model. This includes: identifying the target battery model corresponding to each current sensor signal, and for each target battery model, inputting the current sensor signal corresponding to the target battery model into the target battery model to simulate the operation process of the lithium-ion battery and obtain the operation log information of the target battery model; based on the operation log information, extracting the battery state data change information of the lithium-ion battery, and using the battery state data change information of the lithium-ion battery as the simulation operation data of the target battery model.

[0087] In this embodiment, the terminal identifies the target battery model corresponding to each current sensor signal, and for each target battery model, inputs the current sensor signal corresponding to the target battery model to simulate the operation process of a lithium-ion battery, thereby obtaining the operation log information of the target battery model. Each current sensor signal can be used in the simulation process of one or more target battery models, and each target battery model can filter one or more current sensor signals for use in the battery operation simulation process.

[0088] Then, based on the operation log information, the terminal extracts the battery state data change information of the lithium-ion battery and uses this information as the simulation operation data for the target battery model. This battery state data change information refers to the distribution information of changes in operation data associated with the battery's operating state. This operation data includes, but is not limited to, temperature data, pressure data, current data, voltage data, and air pressure data.

[0089] Based on the above scheme, the operation process of the target battery model is simulated from different angles and directions using multi-dimensional battery models, thereby obtaining battery state data change information of battery models of different dimensions, improving the accuracy and comprehensiveness of battery state identification.

[0090] Optionally, based on the simulation data of each target battery model, the sub-battery state corresponding to each target battery model is identified, including: based on the battery state data change information of the lithium-ion battery simulated by each target battery model, identifying each battery state parameter and the battery state type of each target battery model; based on each battery state parameter of each target battery model, using the battery state evaluation algorithm corresponding to the battery state type of each target battery model, identifying the sub-battery state of the battery state type of each target battery model; and using the sub-battery state of each battery state type of each target battery model as the sub-battery state corresponding to each target battery model.

[0091] In this embodiment, the terminal identifies the battery state parameters and battery state type simulated by each target battery model based on the battery state data change information of the simulated lithium-ion battery for each target battery model. The battery state parameters are input parameters used to estimate the states of different sub-cells of the lithium-ion battery. For example, the battery state of charge (SOC) estimation algorithm is based on the relationship between open-circuit voltage and SOC, with the voltage parameter of the lithium-ion battery as the input parameter; the ampere-hour integral method is based on the relationship between current and SOC, with the current parameter of the lithium-ion battery as the input parameter; and the SOC estimation algorithm is based on the relationship between pressure signal and SOC, with the pressure parameter of the lithium-ion battery as the input parameter.

[0092] Then, based on the battery state parameters simulated by each target battery model, the terminal identifies the sub-battery state of each target battery model's simulated battery state type using a battery state evaluation algorithm corresponding to the battery state type simulated by each target battery model. For example... Figure 5 As shown, a battery state of charge (SOC) estimation algorithm based on multiple signals including voltage, current, and pressure is demonstrated. The process is as follows: First, the terminal performs model simulation based on the voltage sensing sampling results. Then, based on the relationship between open-circuit voltage and SOC, the voltage-based SOC estimation result SOC1 is calculated. Next, based on the current sensing sampling results, the terminal performs model simulation and uses the ampere-hour integration method to calculate the current-based SOC estimation result SOC2. Finally, based on the built-in thin-film pressure sensing sampling results, the terminal performs model simulation and uses the pressure signal and SOC relationship to calculate the pressure-based SOC estimation result SOC3.

[0093] Finally, the terminal takes the sub-battery states of each battery state type simulated by each target battery model as the sub-battery states corresponding to each target battery model.

[0094] Based on the above scheme, by calculating the state of sub-battery states of different battery state types using simulation results from battery models of different dimensions, the accuracy of the obtained sub-battery states and the identification efficiency of each sub-battery state are improved.

[0095] Optionally, based on the sub-battery state corresponding to each target battery model, the target battery state of the lithium-ion battery is identified through a fusion algorithm, including: adapting the battery state weight value of each sub-battery state to the battery state type corresponding to each sub-battery state; and calculating the target battery state of the lithium-ion battery by using each sub-battery state and the battery state weight value of each sub-battery state through a fusion algorithm.

[0096] In this embodiment, the terminal adapts the battery state weight value for each sub-battery state based on the battery state type corresponding to each sub-battery state. This adaptation method involves the terminal pre-setting a correspondence between each battery state type and its weight value. Using this correspondence, the terminal uses the weight value corresponding to each battery state type as the battery state weight value for each sub-battery state of that battery state type. Then, the summary sheet combines each sub-battery state and its battery state weight value using a fusion algorithm to calculate the target battery state of the lithium-ion battery.

[0097] Based on the above scheme, the fusion algorithm designed in this scheme is used to fuse the sub-battery states of battery state types, thereby improving the accuracy of the target battery filling.

[0098] Optionally, the method further includes: based on the current sensing signals of each sensor, identifying the current thermal runaway cause and current thermal runaway information of the lithium-ion battery through a thermal runaway analysis strategy; and generating thermal runaway early warning information for the lithium-ion battery based on the current thermal runaway cause and current thermal runaway information of the lithium-ion battery.

[0099] In this embodiment, the terminal identifies the current thermal runaway cause and information of the lithium-ion battery based on the current sensing signals from each sensor using a thermal runaway analysis strategy. This thermal runaway identification strategy includes sub-judgment strategies for each current sensing signal. These sub-judgment strategies include a threshold value for each current sensing signal's change value. When the change value of a current sensing signal exceeds this threshold, the terminal identifies the sensing signal type corresponding to that current sensing signal as the current thermal runaway cause and uses that current sensing signal as the current thermal runaway information of the lithium-ion battery.

[0100] Then, based on the current cause of thermal runaway and the current thermal runaway information of the lithium-ion battery, the terminal identifies the corresponding warning content through a warning database, and uses this warning content as the thermal runaway warning information for the lithium-ion battery. The warning database includes the correspondence between each warning content, its corresponding cause of thermal runaway, and the thermal runaway information. The terminal generates the thermal runaway warning information for the lithium-ion battery by querying these correspondences.

[0101] like Figure 6As shown, taking the current voltage signal and the current air pressure signal as examples, the terminal determines whether the voltage drop of the current lithium-ion battery is greater than the voltage variable threshold based on the current voltage signal; then, the terminal determines whether the air pressure rise of the current lithium-ion battery is greater than the air pressure variable threshold based on the current air pressure signal; then, the terminal performs an "OR" logic judgment on the two judgment results. When either method results in a thermal runaway warning, the terminal determines that the lithium-ion battery has a thermal runaway risk, queries the warning database, identifies the warning content corresponding to the above judgment results, and uses the warning signal corresponding to the warning content as the thermal runaway warning signal.

[0102] Based on the above scheme, by combining the current sensor signals to judge the thermal runaway of lithium-ion batteries, and by using a threshold judgment method, the thermal runaway risk of the lithium-ion battery can be efficiently identified, thereby improving the accuracy and efficiency of thermal runaway warning for lithium-ion batteries.

[0103] In another exemplary embodiment, such as Figure 1 As shown, a smart lithium-ion battery state assessment system is provided. The system comprises a sensor module 110, a data transmission module 120, and a control processing module 130. The sensor module 110 includes multiple sensor types for detecting various sensing signals of the lithium-ion battery and transmitting these signals to the data transmission module 120. The data transmission module 120 includes a wireless communication module or a wired communication module for transmitting the sensing signals to the control processing module 130. The control processing module 130 collects the current sensing signals from multiple sensors and the battery data of the lithium-ion battery. Based on the battery data, it adjusts the battery models of various dimensions to obtain target battery models corresponding to the lithium-ion battery. Based on the current sensing signals, it simulates the operation of the lithium-ion battery using each target battery model to obtain simulation operation data for each target battery model. Based on the simulation operation data of each target battery model, it identifies the sub-battery state corresponding to each target battery model. Based on the sub-battery state corresponding to each target battery model, it identifies the target battery state of the lithium-ion battery through a fusion algorithm.

[0104] This application also provides an example of cable structure optimization design, as shown in Figure 7. The specific processing steps include the following:

[0105] Step S701: Collect the current sensing signals of multiple sensors and the battery data of the lithium-ion battery.

[0106] Step S702: Based on the battery data, identify the various battery parameters of the lithium-ion battery.

[0107] Step S703: Query the parameter requirements of each dimension battery model for lithium-ion batteries, and based on the parameter requirements of each dimension battery model for lithium-ion batteries, filter the target battery parameters required by each dimension battery model from the various battery parameters of lithium-ion batteries.

[0108] Step S704: Based on the target battery parameters required by each dimension battery model, perform model update processing on each dimension battery model to obtain the target battery models corresponding to the lithium-ion battery.

[0109] Step S705: Identify the target battery model corresponding to each current sensing signal, and for each target battery model, input the current sensing signal corresponding to the target battery model into the target battery model to simulate the operation process of the lithium-ion battery and obtain the operation log information of the target battery model.

[0110] Step S706: Based on the operation log information, extract the battery state data change information of the lithium-ion battery, and use the battery state data change information of the lithium-ion battery as the simulation operation data of the target battery model.

[0111] Step S707: Based on the battery state data change information of the lithium-ion battery simulated by each target battery model, identify the battery state parameters and battery state type of each target battery model.

[0112] Step S708: Based on the battery state parameters simulated by each target battery model, the sub-battery state of each target battery model is identified by the battery state evaluation algorithm corresponding to the battery state type simulated by each target battery model.

[0113] Step S709: Take the sub-battery states of each battery state type simulated by each target battery model as the sub-battery states corresponding to each target battery model.

[0114] Step S710: Based on the battery state type corresponding to each sub-battery state, adapt the battery state weight value for each sub-battery state.

[0115] Step S711: Calculate the target battery state of the lithium-ion battery by using a fusion algorithm to obtain the battery state state of each sub-battery and the battery state weight value of each sub-battery state.

[0116] Step S712: Based on the current sensing signals of each sensor, the current thermal runaway cause and current thermal runaway information of the lithium-ion battery are identified through a thermal runaway analysis strategy.

[0117] Step S713: Based on the current cause of thermal runaway of the lithium-ion battery and the current thermal runaway information of the lithium-ion battery, generate thermal runaway early warning information for the lithium-ion battery.

[0118] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0119] Based on the same inventive concept, this application also provides a battery state assessment device for a smart lithium-ion battery to implement the battery state assessment method for the smart lithium-ion battery described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the battery state assessment device for a smart lithium-ion battery provided below can be found in the limitations of the battery state assessment method for smart lithium-ion batteries described above, and will not be repeated here.

[0120] In one exemplary embodiment, such as Figure 8 As shown, a battery state assessment device for a smart lithium-ion battery is provided, comprising: a data acquisition module 810, a simulation module 820, and an identification module 830, wherein:

[0121] The acquisition module 810 is used to acquire the current sensing signals of multiple sensors and the battery data of the lithium-ion battery, and adjust the battery model of each dimension based on the battery data to obtain the target battery model corresponding to the lithium-ion battery.

[0122] The simulation module 820 is used to simulate the operation process of the lithium-ion battery based on the current sensing signals and through the target battery models, to obtain the simulation operation data of the target battery models, and to identify the sub-battery state corresponding to each target battery model based on the simulation operation data of the target battery models.

[0123] The identification module 830 is used to identify the target battery state of the lithium-ion battery based on the sub-battery state corresponding to each target battery model through a fusion algorithm.

[0124] Optionally, the acquisition module 810 is specifically used for:

[0125] Based on the battery data, identify the various battery parameters of the lithium-ion battery;

[0126] Query the parameter requirements of each dimension battery model for lithium-ion batteries, and based on the parameter requirements of each dimension battery model for lithium-ion batteries, filter the target battery parameters required by each dimension battery model from the battery parameters of the lithium-ion batteries.

[0127] Based on the target battery parameters required by each dimension battery model, the model update process is performed on each dimension battery model to obtain the target battery models corresponding to the lithium-ion battery.

[0128] Optionally, the simulation module 820 is specifically used for:

[0129] Identify the target battery model corresponding to each current sensing signal, and for each target battery model, input the current sensing signal corresponding to the target battery model into the target battery model to simulate the operation process of the lithium-ion battery and obtain the operation log information of the target battery model;

[0130] Based on the operation log information, the battery state data change information of the lithium-ion battery is extracted, and the battery state data change information of the lithium-ion battery is used as the simulation operation data of the target battery model.

[0131] Optionally, the simulation module 820 is specifically used for:

[0132] Based on the battery state data change information of the lithium-ion battery simulated by each target battery model, identify each battery state parameter and the battery state type simulated by each target battery model.

[0133] Based on the battery state parameters simulated by each target battery model, the sub-battery state of each target battery model is identified by the battery state evaluation algorithm corresponding to the battery state type simulated by each target battery model.

[0134] The sub-cell states of each cell state type simulated by each target cell model are taken as the sub-cell states corresponding to each target cell model.

[0135] Optionally, the identification module 830 is specifically used for:

[0136] Based on the battery state type corresponding to each of the sub-battery states, the battery state weight value of each sub-battery state is adapted.

[0137] The target battery state of the lithium-ion battery is calculated by using a fusion algorithm to combine the battery state state of each sub-battery and the battery state weight value of each sub-battery state.

[0138] Optionally, the device may also include:

[0139] The thermal runaway analysis module is used to identify the current thermal runaway cause and the current thermal runaway information of the lithium-ion battery based on the current sensing signals of each sensor and through a thermal runaway analysis strategy.

[0140] The early warning module is used to generate early warning information for thermal runaway of the lithium-ion battery based on the current cause of thermal runaway and the current thermal runaway information of the lithium-ion battery.

[0141] The various modules in the aforementioned intelligent lithium-ion battery state assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0142] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media to run. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a battery state assessment method for a smart lithium-ion battery.

[0143] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0144] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0146] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0147] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0148] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0149] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for evaluating a state of a battery of an intelligent lithium-ion battery, characterized by, The method includes: Collect current sensing signals from multiple sensors and battery data from lithium-ion batteries, and adjust the battery models in each dimension based on the battery data to obtain the target battery models corresponding to the lithium-ion batteries. Based on the current sensing signals, the operation process of the lithium-ion battery is simulated through the target battery models to obtain the simulation operation data of the target battery models. Based on the simulation operation data of the target battery models, the sub-battery state corresponding to each target battery model is identified. Based on the sub-battery state corresponding to each target battery model, the target battery state of the lithium-ion battery is identified through a fusion algorithm.

2. The method of claim 1, wherein, The process of adjusting the battery model across various dimensions based on the battery data to obtain the target battery models corresponding to the lithium-ion battery includes: Based on the battery data, identify the various battery parameters of the lithium-ion battery; Query the parameter requirements of each dimension battery model for lithium-ion batteries, and based on the parameter requirements of each dimension battery model for lithium-ion batteries, filter the target battery parameters required by each dimension battery model from the battery parameters of the lithium-ion batteries. Based on the target battery parameters required by each dimension battery model, the model update process is performed on each dimension battery model to obtain the target battery models corresponding to the lithium-ion battery.

3. The method of claim 1, wherein, The process of simulating the operation of a lithium-ion battery based on the current sensing signals and using the target battery models to obtain simulation operation data for each target battery model includes: Identify the target battery model corresponding to each current sensing signal, and for each target battery model, input the current sensing signal corresponding to the target battery model into the target battery model to simulate the operation process of the lithium-ion battery and obtain the operation log information of the target battery model; Based on the operation log information, the battery state data change information of the lithium-ion battery is extracted, and the battery state data change information of the lithium-ion battery is used as the simulation operation data of the target battery model.

4. The method of claim 3, wherein, The process of identifying the sub-cell state corresponding to each target battery model based on the simulation data of each target battery model includes: Based on the battery state data change information of the lithium-ion battery simulated by each target battery model, identify each battery state parameter and the battery state type simulated by each target battery model. Based on the battery state parameters simulated by each target battery model, the sub-battery state of each target battery model is identified by the battery state evaluation algorithm corresponding to the battery state type simulated by each target battery model. The sub-cell states of each cell state type simulated by each target cell model are taken as the sub-cell states corresponding to each target cell model.

5. The method of claim 1, wherein, The process of identifying the target battery state of the lithium-ion battery based on the sub-battery state corresponding to each target battery model, through a fusion algorithm, includes: Based on the battery state type corresponding to each of the sub-battery states, the battery state weight value of each sub-battery state is adapted. The target battery state of the lithium-ion battery is calculated by using a fusion algorithm to combine the battery state state of each sub-battery and the battery state weight value of each sub-battery state.

6. The method of claim 2, wherein, The method further includes: Based on the current sensing signals of each sensor, the current thermal runaway cause and current thermal runaway information of the lithium-ion battery are identified through a thermal runaway analysis strategy. Based on the current cause of thermal runaway of the lithium-ion battery and the current thermal runaway information of the lithium-ion battery, a thermal runaway early warning information for the lithium-ion battery is generated.

7. A battery state evaluation system for intelligent lithium-ion batteries, characterized by The system includes a sensor module, a data transmission module, and a control processing module, wherein: The sensor module is connected to the data transmission module, and the data transmission module is connected to the control processing module; The sensor module includes multiple sensor types for detecting various sensing signals from the lithium-ion battery and transmitting each sensing signal to the data transmission module. The data transmission module includes a wireless communication module or a wired communication module, used to transmit each of the sensor signals to the control processing module; The control and processing module is used to collect current sensing signals from multiple sensors and battery data from the lithium-ion battery, and adjust the battery models of each dimension based on the battery data to obtain target battery models corresponding to the lithium-ion battery; based on the current sensing signals, simulate the operation process of the lithium-ion battery through each target battery model to obtain simulation operation data of each target battery model, and identify the sub-battery state corresponding to each target battery model based on the simulation operation data of each target battery model; based on the sub-battery state corresponding to each target battery model, identify the target battery state of the lithium-ion battery through a fusion algorithm.

8. A battery state evaluation device for an intelligent lithium-ion battery, characterized by The device includes: The acquisition module is used to acquire the current sensing signals of multiple sensors and the battery data of the lithium-ion battery, and adjust the battery model in each dimension based on the battery data to obtain the target battery model corresponding to the lithium-ion battery. The simulation module is used to simulate the operation process of the lithium-ion battery based on the current sensing signals and through the target battery models, to obtain the simulation operation data of the target battery models, and to identify the sub-battery state corresponding to each target battery model based on the simulation operation data of the target battery models. The identification module is used to identify the target battery state of the lithium-ion battery based on the sub-battery state corresponding to each target battery model through a fusion algorithm. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

11. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images