Intelligent battery early warning system and method based on user side energy storage equipment

Abstract

The invention relates to the technical field of electric power, discloses an intelligent battery early warning system and method based on user side energy storage equipment, and realizes accurate prediction and early warning of battery performance by comprehensively monitoring real-time state parameters, environmental parameters and historical operation data of a battery and combining fault risk assessment, residual life prediction and fault trend analysis. By dynamically adjusting early warning conditions and adopting a multi-stage early warning mechanism, efficient and accurate battery health monitoring and fault prediction can be realized, the safety and reliability of the energy storage system are improved, and the service life of the battery is prolonged.

Description

Technical Field

[0001] The present invention relates to the field of power technology, and more particularly, to an intelligent battery warning system and method based on a user-side energy storage device. Background Art

[0002] With the rapid development of renewable energy technology, user-side energy storage devices are increasingly widely used in the household and commercial fields. As the core component of the energy storage system, the performance of the battery plays a crucial role in the efficiency and safety of the energy storage system. However, during long-term use, the battery will be affected by various factors, such as the number of charge and discharge cycles, environmental conditions, load fluctuations, etc. These factors may lead to the performance degradation of the battery and even failures, thus affecting the stability and safety of the energy storage system. Therefore, developing a technology that can monitor the battery state in real time and give intelligent warnings is of great significance for improving the reliability of the energy storage system and extending the service life of the battery.

[0003] Existing battery management systems mostly adopt a single state monitoring method based on parameters such as battery voltage, current, and temperature, and cannot comprehensively and accurately evaluate the health state and remaining life of the battery. In addition, the existing technology does not adequately consider environmental factors, resulting in poor accuracy and real-time performance of the warning system when dealing with complex working conditions.

[0004] Therefore, there is an urgent need for a more intelligent and comprehensive battery warning method to achieve accurate prediction and management of the battery. Summary of the Invention

[0005] In view of this, the present invention proposes an intelligent battery warning system and method based on a user-side energy storage device, aiming to automatically analyze the battery operation data, identify potential failure modes, and send out warning signals in advance when the battery performance deteriorates or is about to fail, so as to effectively avoid the shutdown of the energy storage system or safety accidents caused by battery failures.

[0006] The present invention proposes an intelligent battery warning method based on a user-side energy storage device, including:

[0007] Obtaining real-time battery state parameters, and calculating corresponding battery state warning values according to the real-time battery state parameters; the real-time battery state parameters include battery voltage, current, temperature, internal resistance, state of charge, and health state;

[0008] Obtaining real-time environmental parameters, and generating environmental impact prediction values according to the relationship between the real-time environmental parameters and the battery performance; the real-time environmental parameters include environmental temperature, humidity, vibration, and shock;

[0009] Obtain the historical operating parameters of the battery, and analyze the remaining life and failure risk assessment value based on the historical operating parameters, battery status warning value, and environmental impact prediction value; the historical operating parameters include the number of charge and discharge cycles, cycle life, and charge and discharge rate;

[0010] Judge whether a warning is needed according to the relationship between the remaining life, failure risk assessment value, and preset threshold; when the judgment result is that a warning is needed, generate a warning signal.

[0011] Preferably, the battery status warning value is non-linearly calculated from real-time battery status parameters, and its calculation formula is as follows:

[0012]

[0013] Among them, Sb represents the battery status warning value; the value range of i is 1-6, and P1-P6 correspond to the battery voltage V, current I, battery temperature Tb, internal resistance Rb, state of charge SOC, and state of health SOH in sequence; αi represents the weight factor; ηi represents the non-linear adjustment index; γ1 represents the correction factor.

[0014] Preferably, the environmental impact prediction value is obtained by multivariate regression calculation, and the calculation formula is as follows:

[0015]

[0016] Among them, Se represents the environmental impact prediction value; the value range of j is 1-4; Q1-Q4 represent the environmental temperature Ta, humidity H, vibration intensity Vb, and impact force Im respectively; βj represents the environmental parameter weight; γ2 represents the correction factor.

[0017] Preferably, the remaining life calculation is based on the exponential decay model and considers the environmental impact, and the calculation formula is as follows:

[0018]

[0019] Among them, RUL represents the remaining life; R0 represents the initial design life; C represents the number of charge and discharge cycles; L represents the cycle life; D represents the charge and discharge rate; λ1-λ4 represent the influence coefficients; γ3 represents the correction factor.

[0020] Preferably, the failure risk assessment value is calculated by the entropy weight comprehensive evaluation method, and its calculation formula is as follows:

[0021]

[0022] Among them, FR represents the failure risk assessment value; Xk represents the failure-related parameter; wk represents the entropy weight distribution coefficient; δ represents the smoothing parameter; γ4 represents the correction factor.

[0023] Preferably, the fault-related parameters include at least three of battery anomaly data, environmental anomaly data, battery gas composition, acoustic emission, impedance spectrum, magnetic field strength, and deformation.

[0024] Preferably, the battery anomaly data includes sudden change in internal resistance and abnormal temperature; the environmental anomaly data includes vibration and shock.

[0025] Preferably, a fault trend index is calculated based on the time series change rate of the fault risk assessment value, and its calculation formula is as follows:

[0026]

[0027] where FT represents the fault trend index; τ1 and τ2 represent weight coefficients; represents the fault risk change rate; represents the fault acceleration; T represents the observation time window.

[0028] Preferably, a dynamic correction factor is calculated according to the fault trend index, and the remaining life calculation is optimized:

[0029]

[0030] RUL′ = RUL - Δγ;

[0031] where Δγ represents the dynamic correction factor; ω1, ω2, and ω3 represent adjustment parameters; Tw represents the prediction time window; RUL′ represents the corrected remaining life.

[0032] Preferably, the early warning determination is calculated based on the remaining life, the fault risk assessment value, and a set threshold, and the calculation formula is as follows:

[0033]

[0034] where Pw represents the early warning trigger probability; σ1, σ2, and σ3 represent adjustment coefficients; θRUL, θFR, and θFT represent the thresholds corresponding to the remaining life, the fault risk assessment value, and the fault trend index, respectively.

[0035] Preferably, when the early warning trigger probability exceeds the early warning threshold, hierarchical early warning is executed, where:

[0036] When θP ≤ Pw < 1.2, it is determined as a mild anomaly, and the hierarchical early warning result is a first-level early warning;

[0037] When 1.2θP ≤ Pw < 1.5, it is determined as a moderate anomaly, and the hierarchical early warning result is a second-level early warning;

[0038] When Pw ≥ 1.5θP, it is determined as a severe anomaly, and the hierarchical early warning result is a third-level early warning;

[0039] Among them, θP represents the warning threshold.

[0040] The present invention also provides an intelligent battery warning system based on user-side energy storage devices, which is used to implement the above-mentioned intelligent battery warning method based on user-side energy storage devices.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0042] The intelligent battery warning method based on user-side energy storage devices provided by the present invention can comprehensively evaluate the health status, remaining life and failure risk of the battery by real-time monitoring of multi-dimensional parameters (including battery status, environmental conditions and operation data), combined with advanced data processing algorithms. The method has the following beneficial effects:

[0043] Multi-dimensional data fusion: By combining multi-dimensional information such as battery status parameters, environmental factors, and historical operation data, the health status of the battery can be comprehensively analyzed, avoiding misjudgment caused by a single parameter.

[0044] Dynamic warning mechanism: By introducing comprehensive evaluation means such as the fault trend index (FT) and the fault risk assessment value (FR), the warning trigger conditions of the battery can be dynamically adjusted, and the possible faults of the battery can be predicted in real time, reducing the system downtime.

[0045] High-precision remaining life prediction: By combining environmental impact, charge and discharge mode and multi-level correction model, the remaining life of the battery can be accurately predicted, and an intelligent warning signal can be generated based on the corrected remaining life, further improving the safety and reliability of the system.

[0046] Multi-level warning classification: By setting a multi-level warning classification mechanism, the present invention can flexibly respond to different fault risks, providing three warning levels: mild, moderate and severe, to help users take appropriate measures in time.

[0047] Strong adaptability: The method can be adaptively adjusted according to different battery types and usage scenarios, has a wide application prospect, and can meet the needs of various user-side energy storage devices. Description of the Drawings

[0048] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0049] Figure 1 It is a flowchart of the intelligent battery warning method based on user-side energy storage devices of the present invention. Detailed Embodiments

[0050] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0051] Referring to Figure 1 , this embodiment provides an intelligent battery warning method based on a user-side energy storage device, including:

[0052] Obtain real-time battery state parameters, and calculate corresponding battery state warning values according to the real-time battery state parameters; the real-time battery state parameters include battery voltage, current, temperature, internal resistance, state of charge, and health state;

[0053] Obtain real-time environmental parameters, and generate environmental impact prediction values according to the relationship between the real-time environmental parameters and battery performance; the real-time environmental parameters include environmental temperature, humidity, vibration, and shock;

[0054] Obtain the historical operation parameters of the battery, and analyze the remaining life and failure risk assessment values according to the historical operation parameters, battery state warning values, and environmental impact prediction values; the historical operation parameters include the number of charge and discharge cycles, cycle life, and charge and discharge rate;

[0055] Judge whether a warning needs to be issued according to the relationship between the remaining life, failure risk assessment value, and a preset threshold; when the judgment result is that a warning needs to be issued, generate a warning signal.

[0056] It can be seen that this embodiment proposes an innovative intelligent battery warning method, which is based on a user-side energy storage device, and its main steps include:

[0057] First, obtain real-time battery state parameters, and then calculate corresponding battery state warning values according to these real-time battery state parameters; these real-time battery state parameters specifically include key indicators such as battery voltage, current, temperature, internal resistance, state of charge, and health state;

[0058] Secondly, obtain real-time environmental parameters, and further generate environmental impact prediction values based on the relationship between these real-time environmental parameters and battery performance; these real-time environmental parameters cover factors such as environmental temperature, humidity, vibration, and shock;

[0059] Next, obtain the historical operating parameters of the battery, and conduct a comprehensive analysis using these historical operating parameters, the battery status warning value, and the predicted environmental impact value, so as to evaluate the remaining life of the battery and the fault risk assessment value; the historical operating parameters mainly include the number of charge and discharge cycles, cycle life, charge and discharge rate, etc.;

[0060] Finally, determine whether it is necessary to issue a warning signal based on the mutual relationship among the remaining life of the battery, the fault risk assessment value, and the preset threshold; if the judgment result indicates that a warning is required, a corresponding warning signal will be generated.

[0061] It can be understood that the intelligent battery warning method of this embodiment not only takes into account the real-time status parameters of the battery itself, but also fully combines the real-time environmental parameters and the historical operating parameters of the battery, so as to achieve a comprehensive assessment of the remaining life and fault risk of the battery. The application of this method can greatly improve the safety and reliability of the user-side energy storage equipment, and effectively avoid various problems caused by battery failures. At the same time, through real-time warning, users can timely understand the status of the battery, and thus take corresponding measures to ensure the normal operation of the equipment. Therefore, the intelligent battery warning method of this embodiment has broad application prospects and important practical value.

[0062] In some embodiments of the present application, the battery status warning value is non-linearly calculated from the real-time battery status parameters, and its calculation formula is as follows:

[0063]

[0064] Among them, Sb represents the battery status warning value; the value range of i is 1-6, and P1-P6 correspond to the battery voltage V, current I, battery temperature Tb, internal resistance Rb, state of charge SOC, and state of health SOH in sequence; αi represents the weight factor; ηi represents the non-linear adjustment index; γ1 represents the correction factor.

[0065] It can be seen that the battery status warning value of this embodiment is obtained through a non-linear calculation method of real-time battery status parameters, and its specific calculation formula is as follows:

[0066]

[0067] In this formula, Sb represents the battery status warning value; the value range of the variable i is from 1 to 6, where P1 to P6 respectively represent six key parameters of the battery, including the battery voltage V, current I, battery temperature Tb, internal resistance Rb, state of charge SOC, and state of health SOH; αi is the corresponding weight factor; ηi is the exponent used to adjust the non-linear relationship; and γ1 is a factor used for correction.

[0068] It can be understood that in this embodiment, by introducing a non-linear calculation method, the complex relationship between battery state parameters can be more accurately reflected, thereby improving the accuracy and reliability of early warning. In addition, the introduction of the weight factor αi quantifies the contribution degree of different parameters in the early warning calculation, further enhancing the flexibility and adaptability of the early warning system. The non-linear adjustment index ηi helps to capture the small changes in battery state parameters and improve the sensitivity of the early warning system. The addition of the correction factor γ1 can make necessary adjustments to the calculation results to ensure the accuracy and reliability of the early warning results. This early warning method that comprehensively considers multiple factors and performs non-linear calculations provides a strong guarantee for the safe operation of user-side energy storage devices.

[0069] In some embodiments of the present application, the environmental impact prediction value is obtained through multivariate regression calculation, and the calculation formula is as follows:

[0070]

[0071] Wherein, Se represents the environmental impact prediction value; the value range of j is 1-4; Q1-Q4 respectively represent the environmental temperature Ta, humidity H, vibration intensity Vb, and impact force Im; βj represents the environmental parameter weight; γ2 represents the correction factor.

[0072] It can be seen that this embodiment adopts the method of multivariate regression analysis to calculate the environmental impact prediction value. Through a series of mathematical calculations, this method can effectively predict the impact that environmental factors may have on a specific situation or device.

[0073] In the above formula, Se represents the environmental impact prediction value, which is the core index we are concerned about. The value range of the variable j is from 1 to 4, covering the four main environmental parameters we are concerned about. Specifically, Q1 to Q4 respectively represent the four environmental factors of environmental temperature Ta, humidity H, vibration intensity Vb, and impact force Im. Each environmental factor corresponds to a weight βj, and this weight value reflects the contribution degree of this environmental factor to the overall environmental impact prediction value. And γ2 is a correction factor, which is used to adjust and optimize the final prediction result to ensure the accuracy and reliability of the prediction value.

[0074] It can be understood that in this embodiment, by using the method of multivariable regression analysis to calculate the predicted value of environmental impact, not only the comprehensive impact of multiple environmental factors on battery performance is considered, but also the contribution degree of different environmental factors in the prediction is quantified by introducing the weight βj. The application of this method makes the prediction of environmental impact more accurate, helps to detect and address potential environmental risks in advance, and further ensures the safe operation of the energy storage device on the user side. In addition, the addition of the correction factor γ2 can make necessary adjustments and optimizations to the prediction results to ensure the accuracy and reliability of the prediction results. To sum up, the intelligent battery warning method of this embodiment comprehensively considers the real-time state parameters of the battery, real-time environmental parameters, and historical operation parameters, and through the introduction of non-linear calculation methods and multivariable regression analysis, realizes a comprehensive and accurate assessment of the remaining life and failure risk of the battery, and has broad application prospects and important practical value.

[0075] In some embodiments of the present application, the remaining life calculation is based on an exponential decay model and considers environmental impact, and the calculation formula is as follows:

[0076]

[0077] Where RUL represents the remaining life; R0 represents the initial design life; C represents the number of charge and discharge cycles; L represents the cycle life; D represents the charge and discharge rate; λ1-λ4 represent influence coefficients; γ3 represents a correction factor.

[0078] It can be seen that this embodiment adopts a remaining life calculation method based on an exponential decay model and fully considers the influence of environmental factors during the calculation process. In the above formula, RUL represents the remaining life of the device or battery, R0 represents its initial design life, C represents the number of charge and discharge cycles, L represents the cycle life, D represents the charge and discharge rate, and λ1 to λ4 represent different influence coefficients, which reflect the influence degree of different environmental factors on the device life. In addition, γ3 is a correction factor used to fine-tune the calculation results to ensure the accuracy of the calculation.

[0079] It is understandable that in this embodiment, by adopting the remaining life calculation method based on the exponential decay model and combining the influence of environmental factors, the accurate prediction of the remaining life of the battery is achieved. This method not only considers the physical characteristics of the battery itself, such as the number of charge and discharge cycles, cycle life, and charge and discharge rate, but also fully combines environmental factors, such as temperature, humidity, vibration, and shock, etc., which may have potential impacts on the battery life. The introduction of the influence coefficients λ1 to λ4 enables the quantification of the specific impacts of different environmental factors on the battery life, thereby improving the accuracy of the prediction. The addition of the correction factor γ3 can make necessary adjustments and optimizations to the prediction results to ensure the reliability and practicality of the prediction results. This remaining life prediction method that comprehensively considers multiple factors and performs accurate calculations provides strong support for the safe operation of user-side energy storage devices, helps users promptly understand the remaining life of the battery, and thus take corresponding maintenance or replacement measures to avoid various problems caused by the exhaustion of the battery life. Therefore, the intelligent battery warning method and its remaining life prediction method in this embodiment have broad application prospects and important practical values, and are of great significance for improving the safety and reliability of user-side energy storage devices.

[0080] In some embodiments of the present application, the failure risk assessment value is calculated by the entropy weight comprehensive evaluation method, and its calculation formula is as follows:

[0081]

[0082] Wherein, FR represents the failure risk assessment value; Xk represents the failure-related parameters; wk represents the entropy weight distribution coefficient; δ represents the smoothing parameter; γ4 represents the correction factor.

[0083] It can be seen that in this embodiment, the entropy weight comprehensive evaluation method is adopted to calculate the failure risk assessment value. This method can effectively comprehensively consider various failure-related parameters to obtain a comprehensive evaluation result. In this formula, FR represents the failure risk assessment value, which is a key indicator used to measure the degree of failure risk that the system or device may encounter during operation. Xk represents the various parameters related to the failure, and these parameters can be various, including but not limited to temperature, pressure, vibration, etc., which are all key factors affecting the operation stability of the device. wk represents the entropy weight distribution coefficient, which is used to represent the importance weight of each failure-related parameter in the overall evaluation. Through the entropy weight method, these weights can be scientifically allocated to ensure the accuracy of the evaluation result. δ represents the smoothing parameter, which is used to handle possible data anomalies or extreme values to ensure the smooth progress of the evaluation process. Finally, γ4 represents the correction factor, which is used to fine-tune the evaluation result to adapt to specific application scenarios or conditions to ensure the applicability and accuracy of the evaluation result.

[0084] It can be understood that in this embodiment, by introducing the entropy weight comprehensive evaluation method to calculate the fault risk evaluation value, a comprehensive and scientific evaluation of the fault risk of the system or equipment is achieved. This method not only considers a variety of fault-related parameters, but also reasonably assigns the importance weights of each parameter through the entropy weight method, making the evaluation results more accurate and reliable. At the same time, the introduction of the smoothing parameter δ effectively handles the problems of data anomalies or extreme values, ensuring the stability and reliability of the evaluation process. The addition of the correction factor γ4 can make necessary adjustments and optimizations to the evaluation results to adapt to different application scenarios or conditions, further improving the practicality and accuracy of the evaluation results. This fault risk evaluation method that comprehensively considers multiple factors and conducts precise evaluation provides a strong guarantee for the safe operation of the user-side energy storage equipment, helps users detect and handle potential fault risks in a timely manner, thereby ensuring the stable operation of the system and extending the service life of the equipment. Therefore, the intelligent battery warning method and its fault risk evaluation method in this embodiment also have broad application prospects and important practical values.

[0085] In some embodiments of the present application, the fault-related parameters include at least three of battery abnormal data, environmental abnormal data, battery gas composition, acoustic emission, impedance spectrum, magnetic field strength, and deformation.

[0086] It can be understood that the fault-related parameters involved in this embodiment are not limited to any one or several of battery abnormal data, environmental abnormal data, battery gas composition, acoustic emission, impedance spectrum, magnetic field strength, and deformation, but cover at least three of these parameters. The comprehensive consideration of these parameters can more comprehensively evaluate the health status of the battery system, thereby detecting potential fault risks at an early stage and ensuring the safe and stable operation of the battery system.

[0087] In some embodiments of the present application, the battery abnormal data includes internal resistance mutation and temperature anomaly; the environmental abnormal data includes vibration and shock.

[0088] It can be understood that the battery abnormal data and environmental abnormal data mentioned in this embodiment are important components in the fault risk evaluation. Internal resistance mutation and temperature anomaly, as two key indicators of battery abnormal data, can directly reflect the changes in the internal state of the battery. Internal resistance mutation may mean damage to the internal structure of the battery or deterioration of the electrolyte, while temperature anomaly may be caused by overheating or overcooling of the battery, which may indicate that the battery is about to fail. Vibration and shock in the environmental abnormal data cannot be ignored either. It may damage the physical structure of the battery, accelerate the aging process of the battery, and thus increase the risk of failure. By comprehensively considering these fault-related parameters, the intelligent battery warning system in this embodiment can more accurately evaluate the health status of the battery system, provide timely warning information to users, and ensure the safe and stable operation of the battery system.

[0089] In some embodiments of the present application, a fault trend index is calculated based on the time series change rate of the fault risk assessment value, and its calculation formula is as follows:

[0090]

[0091] Wherein, FT represents the fault trend index; τ1 and τ2 represent weight coefficients; represents the fault risk change rate; represents the fault acceleration; T represents the observation time window.

[0092] It can be seen that this embodiment adopts a method of calculating the fault trend index based on the time series change rate of the fault risk assessment value. In this formula, FT represents the fault trend index, which is a key indicator used to predict and evaluate the potential fault risk of equipment or systems. τ1 and τ2 represent weight coefficients, and the role of these two coefficients is to adjust the relative importance of the fault risk change rate and the fault acceleration according to different application scenarios and requirements. Among them, represents the fault risk change rate, which reflects the rate of change of the fault risk over time within the observation time window T. And represents the fault acceleration, which describes the acceleration of the change rate of the fault risk over time, that is, the change trend of the change rate. T represents the observation time window, and the length of this time window can be adjusted according to actual situations to meet different monitoring requirements and accuracy requirements.

[0093] It can be understood that in this embodiment, by introducing the fault trend index FT, the dynamic prediction and evaluation of the potential fault risk of the device or system are realized. The fault trend index FT not only considers the fault risk change rate, that is, the rate at which the fault risk changes over time, but also introduces the concept of fault acceleration, which describes the acceleration of the fault risk change rate over time. The comprehensive consideration of these two indicators makes the prediction of the fault risk more comprehensive and accurate. At the same time, the introduction of the weight coefficients τ1 and τ2 allows the relative importance of the fault risk change rate and the fault acceleration to be adjusted according to different application scenarios and requirements, thereby improving the flexibility and adaptability of the prediction results. The setting of the observation time window T provides the possibility for users to adjust the monitoring accuracy and frequency according to actual needs, further enhancing the practicality and flexibility of this method. Through this fault trend evaluation method that comprehensively considers multiple factors and conducts dynamic prediction, the safe operation of the user-side energy storage device is more powerfully guaranteed. Users can more timely understand the potential fault risks of the device or system, and thus take corresponding preventive measures to avoid the occurrence of faults, ensure the stable operation of the system, and extend the service life of the device. Therefore, the intelligent battery warning method and its fault trend evaluation method in this embodiment also demonstrate broad application prospects and important practical values.

[0094] In some embodiments of the present application, a dynamic correction factor is calculated according to the fault trend index, and the remaining life calculation is optimized:

[0095]

[0096] RUL′ = RUL - Δγ;

[0097] where, Δγ represents the dynamic correction factor; ω1, ω2, ω3 represent adjustment parameters; Tw represents the prediction time window; and RUL′ represents the corrected remaining life.

[0098] It can be seen that this embodiment adopts an innovative method, that is, a dynamic correction factor is calculated according to the fault trend index, and the calculation process of the remaining life is further optimized. First, a series of calculation steps are used to determine the fault trend index, which is crucial because it directly affects the accuracy of the dynamic correction factor; then, these fault trend indexes are used to dynamically calculate a correction factor, which will be used to adjust and optimize the calculation of the remaining life. In this process, Δγ represents the calculated dynamic correction factor; ω1, ω2, ω3 represent the adjustment parameters, which can be adjusted accordingly according to different application scenarios and requirements; Tw represents the prediction time window, which defines the time range for predicting the remaining life; and RUL′ represents the remaining life after being adjusted by the dynamic correction factor, which is more accurate and reliable than the original remaining life calculation result.

[0099] It can be understood that in this embodiment, by introducing the dynamic correction factor Δγ, a more accurate calculation and prediction of the remaining battery life are achieved. In traditional remaining life calculation methods, the development of the fault trend is often ignored, and the prediction is only based on the current operating state, which may lead to inaccurate prediction results. However, in this embodiment, by comprehensively considering the fault trend index, the dynamic correction factor is calculated and applied to the calculation of the remaining life, so as to more accurately reflect the actual situation of the remaining battery life. The introduction of the adjustment parameters ω1, ω2, ω3 allows corresponding adjustments according to different battery types, working environments and user requirements, improving the flexibility and adaptability of the calculation results. The setting of the prediction time window Tw provides the possibility for users to adjust the prediction range according to actual needs, further enhancing the practicality and flexibility of this method. Through this remaining life calculation method that comprehensively considers multiple factors and performs dynamic correction, users can more accurately understand the remaining battery life, so as to take corresponding measures in advance to avoid system downtime or damage caused by battery failure, ensuring the stable operation of the system and extending the service life of the battery. Therefore, the intelligent battery warning method and its remaining life calculation method in this embodiment not only improve the accuracy of prediction, but also show broad application prospects and important practical values.

[0100] In some embodiments of the present application, the warning determination is calculated based on the remaining life, the fault risk assessment value and the set threshold, and the calculation formula is as follows:

[0101]

[0102] Wherein, Pw represents the warning trigger probability; σ1, σ2, σ3 represent adjustment coefficients; θRUL, θFR and θFT respectively represent the thresholds corresponding to the remaining life, the fault risk assessment value and the fault trend index.

[0103] It can be seen that in this embodiment, the warning determination is calculated based on the remaining life, the fault risk assessment value and the set threshold. Among them, Pw represents the warning trigger probability; σ1, σ2, σ3 represent adjustment coefficients; θRUL, θFR and θFT respectively represent the thresholds corresponding to the remaining life, the fault risk assessment value and the fault trend index. In some specific embodiments, the calculation and setting of these parameters are based on the comprehensive analysis of historical data and real-time monitoring information to ensure the accuracy and timeliness of the warning system.

[0104] It can be understood that in this embodiment, by comprehensively considering multiple factors such as the remaining life, the fault risk assessment value, and the fault trend index, a more comprehensive and accurate early warning determination of the battery fault risk is achieved. The early warning trigger probability Pw is a key output index, which reflects the likelihood of the battery failing. The calculation of this index not only considers the remaining life θRUL, that is, the expected time length for which the battery can still operate normally, but also introduces two important parameters, the fault risk assessment value θFR and the fault trend index θFT. The fault risk assessment value θFR reflects the magnitude of the current battery fault risk, while the fault trend index θFT describes the development trend of the fault risk over time. The comprehensive consideration of these three indicators makes the early warning determination more comprehensive and accurate. At the same time, the introduction of the adjustment coefficients σ1, σ2, and σ3 allows the relative importance of these three parameters to be adjusted according to different application scenarios and requirements, thereby improving the flexibility and adaptability of the early warning results. Through this method of comprehensively considering multiple factors and making dynamic early warning determinations, users can more accurately understand the battery fault risk situation, thereby taking corresponding preventive measures in advance to avoid system downtime or damage caused by battery failures, ensuring the stable operation of the system and extending the service life of the battery. Therefore, the intelligent battery early warning method and its early warning determination basis in this embodiment not only improve the accuracy of the early warning, but also demonstrate broad application prospects and important practical value.

[0105] In some embodiments of the present application, when the early warning trigger probability exceeds the early warning threshold, a hierarchical early warning is executed, where:

[0106] When θP ≤ Pw < 1.2, it is determined as a mild abnormality, and the hierarchical early warning result is a first-level early warning;

[0107] When 1.2θP ≤ Pw < 1.5, it is determined as a moderate abnormality, and the hierarchical early warning result is a second-level early warning;

[0108] When Pw ≥ 1.5θP, it is determined as a severe abnormality, and the hierarchical early warning result is a third-level early warning;

[0109] Where θP represents the early warning threshold.

[0110] It can be understood that in this embodiment, when the probability of the early warning trigger exceeds the set early warning threshold, the system will execute a hierarchical early warning mechanism. Specifically:

[0111] If the early warning probability Pw is less than or equal to the early warning threshold θP multiplied by 1.2, that is, θP ≤ Pw < 1.2, then the system will determine the current situation as a mild abnormality and set the result of the hierarchical early warning as a first-level early warning;

[0112] If the warning probability Pw is between 1.2 times the warning threshold θP and 1.5 times the warning threshold θP, that is, 1.2θP ≤ Pw < 1.5θP, then the system will determine the current situation as moderately abnormal and set the result of the hierarchical warning as a secondary warning;

[0113] If the warning probability Pw is greater than or equal to 1.5 times the warning threshold θP, that is, Pw ≥ 1.5θP, then the system will determine the current situation as severely abnormal and set the result of the hierarchical warning as a tertiary warning;

[0114] Here, θP represents the warning threshold, which is a key parameter for the system to judge the degree of abnormality.

[0115] It can be understood that in this embodiment, by setting warning thresholds at different levels, hierarchical management and response to the battery failure risk are achieved. This hierarchical warning mechanism not only improves the pertinence and effectiveness of the warning system but also provides more explicit guidance on response measures for users. In the case of a primary warning for mild abnormality, users can take some routine monitoring and maintenance measures to ensure the normal operation of the battery; in the case of a secondary warning for moderate abnormality, users need to strengthen the monitoring and maintenance of the battery and may also need to conduct some additional inspections and tests to prevent the failure from deteriorating further; in the case of a tertiary warning for severe abnormality, users need to immediately take corresponding emergency measures, such as shutting down for maintenance or replacing the battery, to avoid serious damage to the system or safety accidents caused by battery failure. Through this hierarchical warning mechanism, users can take corresponding response measures based on warning information at different levels, thereby more effectively managing and controlling the battery failure risk, ensuring the stable operation of the system, and extending the service life of the battery. Therefore, the intelligent battery warning method and its hierarchical warning mechanism in this embodiment not only improve the accuracy and pertinence of the warning but also provide more explicit and effective guidance on response measures for users, showing broad application prospects and important practical value.

[0116] This embodiment also proposes an intelligent battery warning system based on the user-side energy storage device for implementing the above-mentioned intelligent battery warning method based on the user-side energy storage device.

[0117] It can be understood that the intelligent battery warning system in this embodiment is designed to efficiently and accurately execute the above warning method.

[0118] Preferably, the system integrates an advanced data acquisition module, which can monitor the key parameters of the battery in real time, such as voltage, current, temperature, etc., and input these data into the warning algorithm for processing. In addition, the system is also equipped with a powerful computing and analysis unit, which is responsible for executing complex warning determination logics, including the prediction of remaining life, the calculation of failure risk assessment values, and the analysis of failure trend indexes, etc. To ensure the timely transmission of warning information, the system also has high-speed communication capabilities and can push the warning results to users or relevant management systems in real time.

[0119] In specific implementation, the intelligent battery warning system will first collect the real-time monitoring data of the battery and analyze and process these data through the built-in algorithm model. Based on the processing results, the system will calculate the warning trigger probability Pw and determine the current warning level according to the preset hierarchical warning mechanism. Once the warning trigger probability exceeds the warning threshold, the system will immediately start the corresponding warning response process and convey the warning information to users in a variety of ways, such as audible and visual alarms, SMS notifications, email reminders, etc. Users can quickly take corresponding countermeasures according to the received warning information, thus effectively avoiding the potential risks and losses brought by battery failures.

[0120] Generally speaking, the intelligent battery warning system of this embodiment provides a powerful battery failure warning solution for users with its comprehensive warning determination basis, precise hierarchical warning mechanism, and efficient data processing capabilities. The application of this system will greatly improve the safety and reliability of user-side energy storage devices and provide strong guarantees for the stable operation of the power system and the long-life use of batteries.

[0121] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0122] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowcharts and / or block diagrams can also be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate for implementing in the process Figure 1one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks

[0123] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions in the process Figure 1 one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific implementation manners of the present invention, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. An intelligent battery early warning method based on user-side energy storage equipment, characterized in that: include: Acquire real-time battery status parameters, and calculate corresponding battery status warning values ​​according to the real-time battery status parameters; The real-time battery status parameters include battery voltage, current, temperature, internal resistance, state of charge and health status; Acquire real-time environmental parameters, and generate environmental impact prediction values ​​according to the relationship between the real-time environmental parameters and battery performance; the real-time environmental parameters include environmental temperature, humidity, vibration and impact; Obtaining historical operating parameters of the battery, and analyzing remaining life and failure risk assessment values ​​according to the historical operating parameters, battery status warning values, and environmental impact prediction values; The historical operating parameters include charge and discharge times, cycle life and charge and discharge rate; Determining whether an early warning is required based on the relationship between the remaining life, the failure risk assessment value and the preset threshold; When the judgment result is that an early warning is needed, an early warning signal is generated.

2. The intelligent battery early warning method based on the user-side energy storage device according to claim 1 is characterized in that: The battery status warning value is obtained by nonlinear calculation of the real-time battery status parameter, and its calculation formula is as follows: Among them, Sb represents the battery status warning value; the value range of i is 1-6, P1-P6 correspond to the battery voltage V, current I, battery temperature Tb, internal resistance Rb, state of charge SOC, and state of health SOH respectively; αi represents the weight factor; ηi represents the nonlinear adjustment index; γ1 represents the correction factor.

3. The intelligent battery early warning method based on the user-side energy storage device according to claim 2 is characterized in that: The environmental impact prediction value is obtained through multivariate regression calculation, and the calculation formula is as follows: Among them, Se represents the predicted value of environmental impact; the value range of j is 1-4; Q1-Q4 represent the ambient temperature Ta, humidity H, vibration intensity Vb, and impact force Im respectively; βj represents the environmental parameter weight; γ2 represents the correction factor.

4. The intelligent battery early warning method based on the user-side energy storage device according to claim 3 is characterized in that: The remaining life calculation is based on an exponential decay model and takes environmental impact into consideration. The calculation formula is as follows: Among them, RUL represents the remaining life; R0 represents the initial design life; C represents the number of charge and discharge times; L represents the cycle life; D represents the charge and discharge rate; λ1-λ4 represents the influence coefficient; γ3 represents the correction factor.

5. The intelligent battery early warning method based on the user-side energy storage device according to claim 4 is characterized in that: The fault risk assessment value is calculated by the entropy weight comprehensive assessment method, and its calculation formula is as follows: Among them, FR represents the fault risk assessment value; Xk represents the fault-related parameters; wk represents the entropy weight allocation coefficient; δ represents the smoothing parameter; γ4 represents the correction factor.

6. The intelligent battery early warning method based on the user-side energy storage device according to claim 5 is characterized in that: The fault trend index is calculated based on the time series change rate of the fault risk assessment value. The calculation formula is as follows: Among them, FT represents the fault trend index; τ1 and τ2 represent weight coefficients; represents the failure risk change rate; represents the fault acceleration; T represents the observation time window.

7. The intelligent battery early warning method based on the user-side energy storage device according to claim 6 is characterized in that: Calculate dynamic correction factors based on the failure trend index and optimize remaining life calculation: RUL′=RUL-Δγ; Among them, Δγ represents the dynamic correction factor; ω1, ω2, ω3 represent the adjustment parameters; Tw represents the prediction time window; RUL′ represents the corrected remaining life.

8. The intelligent battery early warning method based on the user-side energy storage device according to claim 7 is characterized in that: The early warning judgment is calculated based on the remaining life, fault risk assessment value and set threshold value. The calculation formula is as follows: Among them, Pw represents the warning trigger probability; σ1, σ2, σ3 represent the adjustment coefficients; θRUL, θFR and θFT represent the thresholds corresponding to the remaining life, failure risk assessment value and failure trend index, respectively.

9. The intelligent battery early warning method based on the user-side energy storage device according to claim 8 is characterized in that: When the warning trigger probability exceeds the warning threshold, a graded warning is executed, where: When θP≤Pw<1.2, it is judged as a slight abnormality, and the graded warning result is a level one warning; When 1.2θP≤Pw<1.5, it is judged as moderate abnormality, and the graded warning result is level 2 warning; When Pw≥1.5θP, it is judged as severe abnormality, and the graded warning result is level 3 warning; Among them, θP represents the warning threshold.

10. An intelligent battery early warning system based on user-side energy storage equipment, characterized in that: Used to implement the intelligent battery early warning method based on the user-side energy storage device as described in any one of claims 1-9.

Images