Energy storage system health assessment and optimization method and system based on data analysis

Abstract

The invention relates to the technical field of energy storage measurement and evaluation, and provides an energy storage system health evaluation and optimization method and system based on data analysis. Historical data and working condition data collected by an industrial sensor are obtained through an intelligent sensor and preprocessed to generate first data, a concentration diffusion model of lithium ions and a heat conduction model of an energy storage system are constructed, and coupling characteristic tensor and stress distribution are jointly generated; training a neural network based on a multi-head attention mechanism on historical data, and determining battery parameters and statistical distribution representing battery health through the neural network; and finally, generating a health report and a control instruction to control the operation of the energy storage system. The coupling feature tensor is generated based on the ion concentration diffusion model and the heat conduction model, the internal state which cannot be directly measured is converted into quantifiable features, material-level damage diagnosis and early warning are achieved, the accuracy of pre-diagnosis of the energy storage system is improved, and the efficiency of health management of the energy storage system is enhanced.

Description

Technical Field

[0001] This application relates to the field of energy storage measurement and evaluation technology, and more specifically, to a method and system for health assessment and optimization of energy storage systems based on data analysis. Background Art

[0002] With the increasing proportion of intermittent energy sources such as wind and solar power, the demand for energy storage systems from the power grid has surged. In high-intensity application scenarios such as grid frequency regulation and renewable energy consumption, traditional methods struggle to accurately quantify internal material-level damage within batteries, such as electrode lithium plating and particle cracking. Furthermore, static control strategies cannot balance the conflict between grid response benefits and battery life loss, leading to a severe challenge of both safety risks and declining economic benefits for the system. Therefore, existing technologies suffer from the problem of invisible battery material-level damage leading to misjudgments of health, resulting in low accuracy in the pre-diagnosis and health management of energy storage systems. Summary of the Invention

[0003] This application provides a data analysis-based method and system for health assessment and optimization of energy storage systems, which can at least partially solve the problem of low accuracy in pre-diagnosis and health management of energy storage systems.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] According to one aspect of this application, a data analysis-based method for health assessment and optimization of an energy storage system is provided, comprising: acquiring historical data and operating condition data collected by industrial sensors through intelligent sensors, and preprocessing the historical data and the operating condition data to generate first data; constructing a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system based on the first data, and combining the concentration diffusion model and the thermal conduction model to generate a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system; training a neural network based on a multi-head attention mechanism through the historical data, and inputting the coupled feature tensor into the neural network to determine battery parameters and statistical distribution characterizing battery health; generating a health report of the energy storage system based on the stress distribution, the battery parameters, and the statistical distribution, and generating control commands based on the health report to control the operation of the energy storage system; and updating the health report of the energy storage system during the execution of the control commands.

[0006] In this application, based on the aforementioned scheme, the step of preprocessing the historical data and the operating condition data to generate the first data includes: aligning the historical data and operating condition data from different sampling rates using timestamps to generate the second data; performing adaptive filtering on the current signal in the second data; and performing information enhancement on the temperature data in the second data to generate the first data.

[0007] In this application, based on the aforementioned scheme, the step of constructing a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system based on the first data, and combining the concentration diffusion model and the thermal conduction model to generate a coupled characteristic tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system, includes: constructing a lithium-ion concentration diffusion model in the energy storage system based on the lithium-ion concentration and the real-time diffusion coefficient of the energy storage material in the first data; constructing a thermal conduction model of the energy storage system based on the reaction data and the material data of the energy storage material in the first data; combining the concentration diffusion model and the thermal conduction model to generate a coupled characteristic tensor characterizing the relationship between the material volume and electrolyte concentration of the energy storage system; and performing finite element method decomposition on the coupled characteristic tensor to obtain a four-dimensional stress distribution.

[0008] In this application, based on the aforementioned scheme, the step of training a neural network based on a multi-head attention mechanism using the historical data, and inputting the coupled feature tensor into the neural network to determine the battery parameters and statistical distribution characterizing battery health includes: training a neural network based on a multi-head attention mechanism based on the historical data; inputting the coupled feature tensor into the neural network to obtain output features, and calculating the partial derivatives of the output features of the neural network with respect to the input features; determining the battery parameters characterizing battery health based on the output features and the partial derivatives; and performing K forward propagations on the coupled feature tensor in the neural network to generate the statistical distribution of the battery parameters.

[0009] In this application, based on the aforementioned scheme, the step of generating a health report for the energy storage system based on the stress distribution, battery parameters, and statistical distribution, and generating control commands based on the health report to control the operation of the energy storage system, includes: generating a health report for the energy storage system based on the stress distribution, battery parameters, and statistical distribution; extracting risk tags from the health report; mapping the risk tags to a preset control strategy library to obtain control commands corresponding to the risk tags; and controlling the operation of the energy storage system through the control commands.

[0010] In this application, based on the aforementioned scheme, updating the health report of the energy storage system during the execution of the control command includes: acquiring real-time data based on a preset time period during the execution of the control command; analyzing the real-time data; and updating the health report of the energy storage system based on the analysis results.

[0011] In this application, based on the aforementioned scheme, the method further includes: generating a failure strength function of the energy storage system based on stress distribution, temperature, and lithium-ion concentration; generating a lifetime probability of the energy storage system based on the failure strength function, and using the lifetime probability as one of the battery parameters.

[0012] According to one aspect of this application, a data analysis-based health assessment and optimization system for energy storage systems is provided, comprising: The acquisition unit is used to acquire historical data and operating condition data collected by industrial sensors through intelligent sensors, and to preprocess the historical data and the operating condition data to generate first data; The model unit is used to construct a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system based on the first data, and to generate a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system by combining the concentration diffusion model and the thermal conduction model. A distribution unit is used to train a neural network based on a multi-head attention mechanism using the historical data, and to input the coupled feature tensor into the neural network to determine the battery parameters and statistical distribution characterizing battery health. The control unit is used to generate a health report of the energy storage system based on the stress distribution, the battery parameters and statistical distribution, and to generate control commands based on the health report to control the operation of the energy storage system; An execution unit is used to update the health report of the energy storage system during the execution of the control commands.

[0013] According to one aspect of this application, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the data analysis-based energy storage system health assessment and optimization method as described in the above embodiments.

[0014] According to one aspect of this application, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the data analysis-based energy storage system health assessment and optimization method as described in the above embodiments.

[0015] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the data analysis-based energy storage system health assessment and optimization method provided in the various optional implementations described above.

[0016] This application's technical solution acquires historical data from intelligent sensors and operational data from industrial sensors, preprocesses the historical data and operational data to generate first data; based on the first data, it constructs a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system; combining the concentration diffusion model and the thermal conduction model, it generates a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system; it trains a neural network based on a multi-head attention mechanism using the historical data, inputs the coupled feature tensor into the neural network, and determines battery parameters and statistical distributions characterizing battery health; based on the stress distribution, battery parameters, and statistical distribution, it generates a health report for the energy storage system, and generates control commands based on the health report to control the operation of the energy storage system; during the execution of the control commands, it updates the health report of the energy storage system. By generating a coupled feature tensor based on the ion concentration diffusion model and the thermal conduction model, it transforms internal states that cannot be directly measured into quantifiable features, enabling material-level damage diagnosis and early warning, improving the accuracy of energy storage system pre-diagnosis, and enhancing the efficiency of energy storage system health management.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0019] Figure 1 The flowchart illustrating a data analysis-based energy storage system health assessment and optimization method in one embodiment of this application is shown.

[0020] Figure 2 The flowchart illustrating the determination of the coupling characteristic tensor and stress distribution in one embodiment of this application is shown schematically.

[0021] Figure 3 The illustration shows a schematic diagram of a data analysis-based energy storage system health assessment and optimization system in one embodiment of this application.

[0022] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0023] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0024] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0025] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0026] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0027] The implementation details of the technical solution of this application are described below: Figure 1 A flowchart illustrating a data analysis-based health assessment and optimization method for an energy storage system according to an embodiment of this application is shown. (Refer to...) Figure 1 As shown, the data analysis-based energy storage system health assessment and optimization method includes at least steps S110 to S150, which are detailed below: S110: Acquire historical data and operating condition data collected by industrial sensors through intelligent sensors, and preprocess the historical data and operating condition data to generate first data.

[0028] In this embodiment, a database covering the entire lifecycle of the energy storage system is integrated with a real-time deployed industrial sensor network. The database is used to obtain multi-dimensional historical data on battery operation in the energy storage system, while the industrial sensor network is used to obtain current operating condition data.

[0029] Specifically, the database, composed of historical data, includes electrical parameters such as voltage, current, and temperature at different stages. In addition, it may include degradation trajectories such as mechanical deformation and changes in internal resistance. Industrial sensor networks acquire in real-time electrical signal waveforms, three-dimensional temperature field distribution, and structural vibration states of the energy storage system during charging and discharging processes.

[0030] Optionally, after acquiring historical and operational data, a raw data pool is constructed to provide a basic information source covering the three dimensions of time, space, and state for subsequent physical feature extraction, ensuring that the health assessment of the energy storage system has sufficient physical driving basis.

[0031] Specifically, in one embodiment of this application, the historical data and the operating condition data are preprocessed to generate first data, including: Second data is generated by aligning the historical data and operating condition data from different sampling rates using timestamps; Adaptive filtering is applied to the current signal in the second data, and information enhancement is performed on the temperature data in the second data to generate the first data.

[0032] In this embodiment, a unified clock reference, namely a timestamp, is used to align the time tags of historical data and operating condition data, thereby solving the data misalignment problem caused by differences in sensor sampling frequencies.

[0033] For example, during the charging and discharging process of a battery in an energy storage system, the high-frequency acquired electrical signals and the low-frequency recorded temperature field are re-matched according to the actual time sequence of physical events, generating a strictly synchronized second data set. This ensures the accurate correspondence of the causal relationship between key events such as current surges and temperature rises in subsequent analyses, laying a time-series foundation for multiphysics coupling modeling.

[0034] In this embodiment, adaptive filtering technology is used to dynamically purify the current signal in the second data. Specifically, pulse interference during the charge-discharge switching phase and background noise during steady-state operation are first identified. Then, the filtering intensity parameter is adjusted in real time, and the current signal is filtered according to the real-time filtering intensity parameter. While maintaining the characteristics of rapid current change, the high-frequency oscillation and zero drift error introduced by the measuring device are effectively suppressed, and a smooth and physically realistic current signal is output as the first data to improve the numerical stability in the subsequent electrochemical model processing.

[0035] For the temperature data in the second set of data, this embodiment augments and enhances the temperature data collected by the temperature sensor based on the law of thermal conduction. Specifically, the temperature distribution in areas without sensors is deduced using the three-dimensional thermal diffusion equation. Combined with the material heat capacity parameters of the energy storage system and the layout of the cooling system, a virtual temperature field conforming to the principle of energy conservation is generated, thereby augmenting and enhancing the temperature data. This approach compensates for blind spots in hardware monitoring, transforming the data collected by limited industrial sensors into a complete spatial thermal state map.

[0036] The above process synchronously collects historical data and real-time operating parameters using industrial or smart sensors, aligns them with timestamps to resolve sampling rate discrepancies, and ensures the temporal consistency of the electrothermal multi-physics data. Current signal noise is eliminated through filtering, and physical information enhancement techniques complete the spatial distribution of the temperature field, generating high-fidelity primary data. The final output primary data contains high-confidence global temperature gradient information, providing complete input for thermal stress coupling analysis.

[0037] S120, Based on the first data, construct a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system, and combine the concentration diffusion model and the thermal conduction model to generate a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system.

[0038] like Figure 2 As shown, in one embodiment of this application, a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system are constructed based on the first data. By combining the concentration diffusion model and the thermal conduction model, a coupled characteristic tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system are generated, including: S210, Based on the lithium ion concentration and the real-time diffusion coefficient of the energy storage material in the first data, construct a lithium ion concentration diffusion model in the energy storage system; S220, Based on the reaction data and material data of the energy storage material in the first data, construct a heat conduction model of the energy storage system; S230, By combining the concentration diffusion model and the heat conduction model, a coupled feature tensor characterizing the relationship between the material volume and electrolyte concentration of the energy storage system is generated; S240, the coupled feature tensor is decomposed using the finite element method to obtain a four-dimensional stress distribution.

[0039] In practical applications, the current passing through the battery generates Joule heat and reaction heat, which leads to an increase in temperature. The increase in temperature accelerates ion diffusion, but overheating can trigger side reactions. Therefore, the two are coupled bidirectionally through concentration diffusion and heat conduction.

[0040] Meanwhile, in practical applications, commercial sensors are generally larger than 100 micrometers in size, while the ion concentration gradient occurs within the micrometer-scale electrode pores. Furthermore, insertable sensors can disrupt the electrolyte sealing environment, triggering side reactions such as electrolyte decomposition. Even though microelectrodes allow for localized measurement, a laboratory attempt to implant a miniature ion concentration sensor into the electrolyte resulted in leakage due to sealing failure, leading to a 57% decrease in battery cycle life, and localized sensor heating caused the measured values ​​to deviate from the true values ​​by 38%. Therefore, it is difficult to directly measure ion concentration in practical applications. In this embodiment, data is acquired through sensor nodes deployed outside the energy storage system to construct coupled characteristic tensors and stress distributions to determine battery parameters and statistical distributions characterizing battery health, achieving comprehensive pre-diagnosis and health management of the energy storage system.

[0041] In one embodiment of this application, based on the lithium-ion concentration in the first data and the real-time diffusion coefficient of the energy storage material, a lithium-ion concentration diffusion model in the energy storage system is constructed as follows:

[0042] in, This indicates the lithium-ion concentration in the electrolyte of the energy storage system. t Indicates time, Indicates gradient operation; in, , representing the real-time diffusion coefficient of the energy storage material; specifically, This represents the real-time diffusion coefficient of the energy storage material as determined experimentally. Indicates the activation energy of the energy storage material. r The gas constant representing a unit energy conversion. T This indicates the real-time temperature monitored by the temperature sensor; in, j Represents local current density. f This represents the Faraday constant. In this embodiment, the lithium-ion concentration diffusion model reflects the effect of current on the electrolyte concentration distribution.

[0043] In one embodiment of this application, based on the reaction data and material data of the energy storage material in the first data, the heat conduction model of the energy storage system is constructed as follows:

[0044] in, This indicates the material density of the energy storage material. This indicates the specific heat capacity of the energy storage material. T Indicates real-time temperature. t Indicates time; k Indicates the thermal conductivity of the energy storage material; in, I This indicates the output current of the energy storage system. R This indicates the real-time resistance of the energy storage system; in, This represents the heat of side reactions in the energy storage system. This represents the reaction coefficient of the energy storage system. This indicates an overpotential. In this embodiment, the heat conduction model reflects the conduction process of heat generated by current and heat of reaction.

[0045] In one embodiment of this application, the concentration diffusion model reflects the influence of current on the electrolyte concentration distribution, and the heat conduction model reflects the conduction process of current-generated heat and reaction heat. The two models simulate the interaction between the internal electrochemical reaction and temperature field of the battery, providing key physical characteristics for subsequent health status assessment.

[0046] By combining the concentration diffusion model and the heat conduction model, and solving the system of equations formed by the two equations above, the local current density can be obtained. j Real-time lithium-ion concentration of electrolyte in energy storage system These technologies are adapted to the heat flow distribution and ion concentration field in the temperature control process of energy storage systems, respectively, to quantify the effect of high temperature on the ion diffusion rate, and to predict the hot spot locations inside the battery of the energy storage system, such as the battery electrode edge temperature rising by 5°C.

[0047] In practical applications, lithium ion embedding in electrode materials causes volume expansion, such as the 8% expansion rate of graphite anodes. Temperature changes also lead to thermal expansion and contraction of the material. The combined effect of these two factors generates mechanical stress, which may cause electrode particles to break. In this embodiment, the lithium ion concentration of the electrolyte in the energy storage system is used as the basis for this measurement. The internal stress distribution of the electrode is obtained by direct inference to capture the volume change caused by lithium ion insertion or extraction in the energy storage system, based on the lithium ion concentration. Generate a coupled characteristic tensor characterizing the relationship between material volume and electrolyte concentration in an energy storage system. F for:

[0048] in, This represents the material expansion coefficient of the energy storage system. Through the above process, the volume corresponding to the coupled characteristic tensor is driven by the lithium-ion concentration gradient; the higher the concentration, the stronger the expansion force. This is used to quantify the changes in mechanical stress during battery cycling and predict battery fatigue and aging caused by stress.

[0049] Finite element decomposition is performed on the coupled characteristic tensor, and the four-dimensional stress distribution is inverted using the stress balance equation to obtain the four-dimensional stress distribution as follows: By analyzing the four-dimensional stress distribution, high-stress target areas, such as electrode edges, can be located. Furthermore, the stress distribution can be used to predict particle cracks; for example, when the stress exceeds 50 MPa, the risk of cracking increases by 80%.

[0050] The above process quantifies electrode reaction kinetics based on an ion concentration diffusion model and analyzes the temperature gradient distribution using a heat conduction model. The finite element method decomposes the coupled characteristic tensor of the two fields into a four-dimensional stress field, revealing the spatiotemporal evolution of internal stress in the material during charging and discharging. Through multi-physics coupling modeling, the aging mechanism of the battery is comprehensively characterized from electrochemical, thermal, and mechanical dimensions, solving the problem that a single physics model cannot accurately describe the complex aging process. This enables the mapping from macroscopic operating parameters to microscopic material damage, such as locating the risk area of ​​electrode particle cracks, giving health assessment the ability to provide material-level failure early warning.

[0051] S130, a neural network based on a multi-head attention mechanism is trained using the historical data, and the coupled feature tensor is input into the neural network to determine the battery parameters and statistical distribution that characterize battery health.

[0052] In one embodiment of this application, a neural network based on a multi-head attention mechanism is trained using the historical data, and the coupled feature tensor is input into the neural network to determine battery parameters and statistical distributions characterizing battery health, including: Based on the historical data, a neural network based on a multi-head attention mechanism is trained; The coupled feature tensor is input into the neural network to obtain the output features, and the partial derivatives of the output features of the neural network with respect to the input features are calculated. Based on the output characteristics and the partial derivatives, determine the battery parameters characterizing battery health; Performing the coupled feature tensor in the neural network K The next forward propagation generates the statistical distribution of battery parameters.

[0053] In this embodiment, based on historical data, a neural network based on a multi-head attention mechanism is trained using a convolutional neural network; the coupled feature tensor is input into the neural network to obtain the output features, and the partial derivative of the output features of the neural network with respect to the input features is calculated. Based on the neural network and the partial derivatives, battery parameters characterizing battery health are determined. S for:

[0054] in, This refers to a neural network based on a multi-head self-attention mechanism. Indicates output features, This represents the regularization strength coefficient. i and N These represent the identifier and total number of input features, respectively. In this embodiment, the calculated battery parameters are used to characterize the difference between the current battery capacity and the initial capacity, thus reflecting the battery's health status.

[0055] In the trained neural network The middle retains a random deactivation layer, and performs operations on the input features corresponding to the same coupled feature tensor. K The first forward propagation (e.g., K=100) determines the statistical distribution of the battery parameters. Specifically, the statistical distribution includes the first statistical parameter. for:

[0056] in, Indicates the first k Battery parameters generated by the second forward propagation k Indicates the number of forward propagations. K This indicates the total number of forward propagations.

[0057] Then, based on the calculated first statistical parameter, the second statistical parameter belonging to the statistical distribution is determined. for:

[0058] Then, the statistical distribution corresponding to the battery parameters is determined based on the first statistical parameter and the second statistical parameter. for:

[0059] After calculating the statistical distribution, if the confidence interval corresponding to the statistical distribution is narrow, it means that the neural network is performing stably on battery data; if the confidence interval is wide, it means that the neural network has encountered unknown operating conditions, and an early warning is triggered to switch the energy storage system back to a safe mode, such as derating operation, or to trigger manual inspection when the interval boundary reaches the threshold.

[0060] In addition, in the embodiments of this application, a failure strength function of the energy storage system is generated based on stress distribution, temperature, and lithium ion concentration. for:

[0061] in, These represent the function factors obtained by training based on historical data; in, , indicating temperature T Non-uniformity, x, y Represents the two-dimensional physical coordinates of the battery hardware in the energy storage system; in, Indicates battery hardware in t In three-dimensional coordinates at all times Stress distribution on This indicates the lithium-ion concentration in the electrolyte of the energy storage system.

[0062] In this embodiment, the failure strength function This is used to correlate the physical state of an energy storage system with the failure risk of its batteries. After determining the failure intensity function, it predicts the time-related failure risk of the energy storage system based on the failure intensity function. Probability of internal failure within service life for:

[0063] in, This represents the time integral variable.

[0064] The lifespan probability of the energy storage system is obtained by constructing a failure intensity function based on stress distribution, temperature gradient, and ion concentration change rate. This lifespan probability is then used as one of the battery parameters to dynamically quantify the material damage accumulation rate and update the lifespan probability distribution in real time.

[0065] The above process employs a multi-head attention neural network to uncover the correlation between coupled features and aging modes, constraining the model to conform to electrochemical laws through output feature partial derivatives; and generates probability distributions of battery parameters through forward propagation to quantify uncertainty assessment. By integrating physical mechanisms with data-driven approaches, it directly reflects the degree of battery aging and risk level.

[0066] S140, based on the stress distribution, the battery parameters, and the statistical distribution, generate a health report for the energy storage system, and generate control commands based on the health report to control the operation of the energy storage system.

[0067] In one embodiment of this application, a health report of the energy storage system is generated based on the stress distribution, the battery parameters, and the statistical distribution, and control commands are generated based on the health report to control the operation of the energy storage system, including: Based on the stress distribution, the battery parameters, and the statistical distribution, a health report for the energy storage system is generated; Risk tags are extracted from the health report, and the risk tags are mapped to a preset control strategy library to obtain the control instructions corresponding to the risk tags. The operation of the energy storage system is controlled by control commands.

[0068] Based on the stress distribution, battery parameters, and statistical distribution output from the above steps, a structured health report is automatically generated. Specifically, the health report may include areas where electrode stress exceeds limits, statistical layer life prediction, and economic indicators, such as a failure probability greater than 30% after 180 days. In addition, it may include residual value assessment, forming a quantitative analysis that includes safety level, life stage, and maintenance recommendations.

[0069] Risk tags are extracted from the health report and mapped to a preset control strategy library to obtain corresponding control strategies, thereby generating control instructions corresponding to the risk tags. Specifically, risk tags in the health report are directly mapped to the control strategy library. For example, if the width of the statistical distribution is greater than 0.15, it is a high-risk scenario, and a derating instruction is generated to compress the maximum charge and discharge current to 50% of the safety threshold, while simultaneously increasing the liquid cooling flow rate by 200% to combat local hot spots. If the battery parameter is less than 0.7, it is an end-of-life scenario, triggering a long-life mode, reducing the cutoff voltage by 0.1V and shutting down the cooling fan in the high-stress area to delay structural failure.

[0070] Control commands are compiled into hardware-executable signals and sent to the energy storage system. Specifically, at the power control layer, current switching is achieved through switching timing adjustments to ensure precise matching of actions with optimization strategies; at the thermal management execution layer, the liquid cooling system is zoned and controlled according to stress distribution, and the air-cooled system is started and stopped based on a mechanical vibration model; at the safety monitoring layer, the rate of change of ion concentration is continuously monitored through an embedded electrochemical solver, and power-off protection is executed when limits are exceeded.

[0071] S150, during the execution of the control command, update the health report of the energy storage system.

[0072] In one embodiment of this application, updating the health report of the energy storage system during the execution of the control command includes: During the execution of the control commands, real-time data is acquired based on a preset time period; The real-time data is analyzed, and the health report of the energy storage system is updated based on the analysis results.

[0073] In this embodiment, while executing optimized control commands, the real-time operating status of the energy storage unit is automatically captured according to a preset time period to obtain real-time data, which may include core parameters such as electrical response, temperature distribution, and mechanical vibration. This time-period acquisition mechanism takes into account both the monitoring needs of high-frequency key indicators (such as sudden current changes) and low-frequency slow variables (such as aging accumulation), ensuring that a continuous data stream reflecting the true state of the battery is continuously acquired during the dynamic adjustment of the charging and discharging strategy. By synchronously recording control actions and changes in physical state, timely basis is provided for iterative updates of the health status.

[0074] Based on the newly added real-time data stream, multi-dimensional fusion analysis is triggered. First, it identifies abnormal trend characteristics by correlating with the historical degradation pattern library. Then, it combines physical models to deduce the progress of material-level damage. Finally, it integrates lifetime prediction algorithms to update the health status assessment. Each update not only corrects quantitative indicators such as capacity decay rate, but also reveals hidden risks such as electrode stress concentration and accelerated interface side reactions, ensuring that the health report continuously approximates the actual degradation state. This closed-loop process ensures that operation and maintenance decisions are always adapted to the latest battery operating conditions, forming a self-evolving protection system of monitoring-evaluation-optimization, thereby achieving fault prediction and health management of the energy storage system.

[0075] In this embodiment, health reports and control commands form a dynamic closed loop. During short-term control, the output of high-degradation cells is actively suppressed during grid frequency regulation, increasing cluster revenue by 12%. During long-term control, spare parts resources are pre-scheduled based on battery lifespan distribution, reducing downtime by 18%. In terms of safety, stress-temperature coupling coefficient early warning is used to prevent the risk of dendrite growth seven times. Ultimately, this achieves a combined benefit of a 1.4-fold increase in lifespan and an 18% reduction in cost per kilowatt-hour, thereby realizing the pre-diagnosis and health management of the energy storage system.

[0076] The above process maps the risk labels in the health report to the control strategy library, generates optimized instructions for current, voltage, or temperature, periodically acquires real-time data during execution, and updates the health status through online analysis, forming a closed loop of assessment, control, and calibration, extending battery life by 53% and reducing the probability of dangerous events.

[0077] This application's technical solution acquires historical data from intelligent sensors and operational data from industrial sensors, preprocesses the historical data and operational data to generate first data; based on the first data, it constructs a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system; combining the concentration diffusion model and the thermal conduction model, it generates a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system; it trains a neural network based on a multi-head attention mechanism using the historical data, inputs the coupled feature tensor into the neural network, and determines battery parameters and statistical distributions characterizing battery health; based on the stress distribution, battery parameters, and statistical distribution, it generates a health report for the energy storage system, and generates control commands based on the health report to control the operation of the energy storage system; during the execution of the control commands, it updates the health report of the energy storage system. By generating a coupled feature tensor based on the ion concentration diffusion model and the thermal conduction model, it transforms internal states that cannot be directly measured into quantifiable features, enabling material-level damage diagnosis and early warning, improving the accuracy of energy storage system pre-diagnosis, and enhancing the efficiency of energy storage system health management.

[0078] The following describes system embodiments of this application, which can be used to execute the data analysis-based energy storage system health assessment and optimization method in the above embodiments of this application. It is understood that the data analysis-based energy storage system health assessment and optimization system can be a computer program (including program code) running on a computer device; for example, the data analysis-based energy storage system health assessment and optimization system is an application software. This data analysis-based energy storage system health assessment and optimization system can be used to execute the corresponding steps in the method provided in the embodiments of this application. For details not disclosed in the system embodiments of this application, please refer to the above embodiments of the data analysis-based energy storage system health assessment and optimization method of this application.

[0079] Figure 3 A block diagram of a data analysis-based energy storage system health assessment and optimization system according to an embodiment of this application is shown.

[0080] Reference Figure 3 As shown, a data analysis-based energy storage system health assessment and optimization system according to an embodiment of this application includes: The acquisition unit 310 is used to acquire historical data and operating condition data collected by industrial sensors through intelligent sensors, and to preprocess the historical data and the operating condition data to generate first data. Model unit 320 is used to construct a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system based on the first data, and to generate a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system by combining the concentration diffusion model and the thermal conduction model. Distribution unit 330 is used to train a neural network based on a multi-head attention mechanism using the historical data, input the coupled feature tensor into the neural network, and determine the battery parameters and statistical distribution characterizing battery health; Control unit 340 is used to generate a health report of the energy storage system based on the stress distribution, the battery parameters and statistical distribution, and to generate control commands based on the health report to control the operation of the energy storage system; The execution unit 350 is used to update the health report of the energy storage system during the execution of the control commands.

[0081] In this application, based on the aforementioned scheme, the step of preprocessing the historical data and the operating condition data to generate the first data includes: aligning the historical data and operating condition data from different sampling rates using timestamps to generate the second data; performing adaptive filtering on the current signal in the second data; and performing information enhancement on the temperature data in the second data to generate the first data.

[0082] In this application, based on the aforementioned scheme, the step of constructing a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system based on the first data, and combining the concentration diffusion model and the thermal conduction model to generate a coupled characteristic tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system, includes: constructing a lithium-ion concentration diffusion model in the energy storage system based on the lithium-ion concentration and the real-time diffusion coefficient of the energy storage material in the first data; constructing a thermal conduction model of the energy storage system based on the reaction data and the material data of the energy storage material in the first data; combining the concentration diffusion model and the thermal conduction model to generate a coupled characteristic tensor characterizing the relationship between the material volume and electrolyte concentration of the energy storage system; and performing finite element method decomposition on the coupled characteristic tensor to obtain a four-dimensional stress distribution.

[0083] In this application, based on the aforementioned scheme, the step of training a neural network based on a multi-head attention mechanism using the historical data, and inputting the coupled feature tensor into the neural network to determine the battery parameters and statistical distribution characterizing battery health includes: training a neural network based on a multi-head attention mechanism based on the historical data; inputting the coupled feature tensor into the neural network to obtain output features, and calculating the partial derivatives of the output features of the neural network with respect to the input features; determining the battery parameters characterizing battery health based on the output features and the partial derivatives; and performing K forward propagations on the coupled feature tensor in the neural network to generate the statistical distribution of the battery parameters.

[0084] In this application, based on the aforementioned scheme, the step of generating a health report for the energy storage system based on the stress distribution, battery parameters, and statistical distribution, and generating control commands based on the health report to control the operation of the energy storage system, includes: generating a health report for the energy storage system based on the stress distribution, battery parameters, and statistical distribution; extracting risk tags from the health report; mapping the risk tags to a preset control strategy library to obtain control commands corresponding to the risk tags; and controlling the operation of the energy storage system through the control commands.

[0085] In this application, based on the aforementioned scheme, updating the health report of the energy storage system during the execution of the control command includes: acquiring real-time data based on a preset time period during the execution of the control command; analyzing the real-time data; and updating the health report of the energy storage system based on the analysis results.

[0086] In this application, based on the aforementioned scheme, the method further includes: generating a failure strength function of the energy storage system based on stress distribution, temperature, and lithium-ion concentration; generating a lifetime probability of the energy storage system based on the failure strength function, and using the lifetime probability as one of the battery parameters.

[0087] This application's technical solution acquires historical data from intelligent sensors and operational data from industrial sensors, preprocesses the historical data and operational data to generate first data; based on the first data, it constructs a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system; combining the concentration diffusion model and the thermal conduction model, it generates a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system; it trains a neural network based on a multi-head attention mechanism using the historical data, inputs the coupled feature tensor into the neural network, and determines battery parameters and statistical distributions characterizing battery health; based on the stress distribution, battery parameters, and statistical distribution, it generates a health report for the energy storage system, and generates control commands based on the health report to control the operation of the energy storage system; during the execution of the control commands, it updates the health report of the energy storage system. By generating a coupled feature tensor based on the ion concentration diffusion model and the thermal conduction model, it transforms internal states that cannot be directly measured into quantifiable features, enabling material-level damage diagnosis and early warning, improving the accuracy of energy storage system pre-diagnosis, and enhancing the efficiency of energy storage system health management.

[0088] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0089] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not impose any limitations on the function and scope of use of the embodiments of this application.

[0090] In this embodiment, the computer system includes a central processing unit 401, which can perform various appropriate actions and processes based on a program stored in the read-only memory 402 or a program loaded from the storage section 408 into the random access memory 403, such as executing the data analysis-based energy storage system health assessment and optimization method described in the above embodiment. The random access memory 403 also stores various programs and data required for system operation. The central processing unit 401, the read-only memory 402, and the random access memory 403 are interconnected via a bus 404. An input / output interface 405 is also connected to the bus 404.

[0091] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 410 as needed so that computer programs read from it can be installed into the storage section 408 as needed.

[0092] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit 401, it performs various functions defined in the system of this application.

[0093] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0095] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0096] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0097] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the data analysis-based energy storage system health assessment and optimization method described in the above embodiments.

[0098] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0099] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0100] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0101] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data analysis-based method for health assessment and optimization of energy storage systems, characterized in that, include: The system acquires historical data and operating condition data collected by industrial sensors through intelligent sensors, and preprocesses the historical data and operating condition data to generate the first data. Based on the first data, a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system are constructed. By combining the concentration diffusion model and the thermal conduction model, a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system are generated. By training a neural network based on a multi-head attention mechanism using the historical data, and inputting the coupled feature tensor into the neural network, battery parameters and statistical distributions characterizing battery health are determined. Based on the stress distribution, battery parameters, and statistical distribution, a health report of the energy storage system is generated, and control commands are generated based on the health report to control the operation of the energy storage system. During the execution of the control commands, the health report of the energy storage system is updated.

2. The data analysis-based health assessment and optimization method for energy storage systems according to claim 1, characterized in that, The historical data and the operating condition data are preprocessed to generate first data, including: Second data is generated by aligning the historical data and operating condition data from different sampling rates using timestamps; Adaptive filtering is applied to the current signal in the second data, and information enhancement is performed on the temperature data in the second data to generate the first data.

3. The data analysis-based health assessment and optimization method for energy storage systems according to claim 1, characterized in that, Based on the first data, a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system are constructed. By combining the concentration diffusion model and the thermal conduction model, a coupled characteristic tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system are generated, including: Based on the lithium ion concentration and the real-time diffusion coefficient of the energy storage material in the first data, a lithium ion concentration diffusion model in the energy storage system is constructed. Based on the reaction data and material data of the energy storage material in the first data, a heat conduction model of the energy storage system is constructed. By combining the concentration diffusion model and the heat conduction model, a coupled feature tensor characterizing the relationship between material volume and electrolyte concentration in the energy storage system is generated; The coupled feature tensor is decomposed using the finite element method to obtain a four-dimensional stress distribution.

4. The data analysis-based health assessment and optimization method for energy storage systems according to claim 1, characterized in that, By training a multi-head attention-based neural network using the historical data, and inputting the coupled feature tensor into the neural network, battery parameters and statistical distributions characterizing battery health are determined, including: Based on the historical data, a neural network based on a multi-head attention mechanism is trained; The coupled feature tensor is input into the neural network to obtain the output features, and the partial derivatives of the output features of the neural network with respect to the input features are calculated. Based on the output characteristics and the partial derivatives, determine the battery parameters characterizing battery health; Performing the coupled feature tensor in the neural network K The next forward propagation generates the statistical distribution of battery parameters.

5. The data analysis-based health assessment and optimization method for energy storage systems according to claim 4, characterized in that, Also includes: Based on stress distribution, temperature, and lithium-ion concentration, a failure strength function for the energy storage system is generated. Based on the failure intensity function, the lifetime probability of the energy storage system is generated, and the lifetime probability is used as one of the battery parameters.

6. The data analysis-based health assessment and optimization method for energy storage systems according to claim 1, characterized in that, Based on the stress distribution, battery parameters, and statistical distribution, a health report for the energy storage system is generated, and control commands are generated based on the health report to control the operation of the energy storage system, including: Based on the stress distribution, the battery parameters, and the statistical distribution, a health report for the energy storage system is generated; Risk tags are extracted from the health report, and the risk tags are mapped to a preset control strategy library to obtain the control instructions corresponding to the risk tags. The operation of the energy storage system is controlled by control commands.

7. The data analysis-based health assessment and optimization method for energy storage systems according to claim 1, characterized in that, During the execution of the control commands, the health report of the energy storage system is updated, including: During the execution of the control commands, real-time data is acquired based on a preset time period; The real-time data is analyzed, and the health report of the energy storage system is updated based on the analysis results.

8. A data analysis-based health assessment and optimization system for energy storage systems, characterized in that, include: The acquisition unit is used to acquire historical data and operating condition data collected by industrial sensors through intelligent sensors, and to preprocess the historical data and the operating condition data to generate first data; The model unit is used to construct a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system based on the first data, and to generate a coupled feature tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system by combining the concentration diffusion model and the thermal conduction model. A distribution unit is used to train a neural network based on a multi-head attention mechanism using the historical data, and to input the coupled feature tensor into the neural network to determine the battery parameters and statistical distribution that characterize battery health. The control unit is used to generate a health report of the energy storage system based on the stress distribution, the battery parameters and statistical distribution, and to generate control commands based on the health report to control the operation of the energy storage system; An execution unit is used to update the health report of the energy storage system during the execution of the control commands.

9. The data analysis-based energy storage system health assessment and optimization system according to claim 8, characterized in that, The historical data and the operating condition data are preprocessed to generate first data, including: Second data is generated by aligning the historical data and operating condition data from different sampling rates using timestamps; Adaptive filtering is applied to the current signal in the second data, and information enhancement is performed on the temperature data in the second data to generate the first data.

10. The data analysis-based energy storage system health assessment and optimization system according to claim 8, characterized in that, Based on the first data, a lithium-ion concentration diffusion model and a thermal conduction model of the energy storage system are constructed. By combining the concentration diffusion model and the thermal conduction model, a coupled characteristic tensor and stress distribution characterizing the relationship between the material volume and electrolyte concentration of the energy storage system are generated, including: Based on the lithium ion concentration and the real-time diffusion coefficient of the energy storage material in the first data, a lithium ion concentration diffusion model in the energy storage system is constructed. Based on the reaction data and material data of the energy storage material in the first data, a heat conduction model of the energy storage system is constructed. By combining the concentration diffusion model and the heat conduction model, a coupled feature tensor characterizing the relationship between material volume and electrolyte concentration in the energy storage system is generated; The coupled feature tensor is decomposed using the finite element method to obtain a four-dimensional stress distribution.

Images