A Method for Medium- and Long-Term Failure Prediction and Early Fault Warning of a Battery Pack

Abstract

The present invention discloses a method for long-term failure prediction and early fault warning of a battery pack, which relates to the technical field of data prediction and includes the following steps: S1, obtaining key characteristic parameters of the battery pack in real time; S2, constructing a health state evaluation model of the battery pack; S3, analyzing the short-term dynamic changes and long-term degradation trends of the battery; S4, constructing a fault warning model, and the model sends out warning information when the battery shows abnormalities; S5, identifying and inferring fault modes; S6, formulating optimization strategies. The method for long-term failure prediction and early fault warning of the battery pack greatly improves the accuracy and timeliness of battery fault prediction through dynamic health state modeling. Compared with the prior art, this method can quickly detect abnormal changes in the battery in the short term and accurately predict the remaining life of the battery through long-term decline analysis, significantly reducing the false alarm and missed alarm problems in the traditional method.

Description

Technical Field

[0001] The present invention relates to the technical field of data prediction, and particularly to a method for medium- and long-term failure prediction and early fault warning of a battery pack. Background Art

[0002] With the rapid development of energy storage technology, battery packs have been widely used in fields such as power systems, renewable energy storage, and electric vehicles. However, during long-term use, battery packs are affected by various factors, resulting in a gradual decline in their performance and even failures. To ensure the safe and reliable operation of battery packs, it is particularly important to timely predict their health status and issue fault warnings. Currently, the health management of battery packs mainly relies on traditional single-parameter monitoring methods, such as voltage, temperature, and internal resistance. However, single-parameter monitoring cannot fully reflect the complex operating characteristics of battery packs, especially when facing battery aging and potential faults, it cannot provide sufficient warning capabilities.

[0003] Existing battery health management systems usually adopt some basic evaluation models, such as simple threshold determination methods based on battery voltage and temperature, or regression analysis based on historical data. These methods may be able to detect obvious fault signs in the short term, but often lack a comprehensive evaluation and accurate prediction of the health status of the battery pack. Especially when facing non-linear degradation and battery aging in complex working environments, they cannot make efficient and timely responses. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a method for medium- and long-term failure prediction and early fault warning of a battery pack to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a method for medium- and long-term failure prediction and early fault warning of a battery pack, including the following steps:

[0007] [[ID=z5]]S1. Real-time obtain the key characteristic parameters of the battery pack;

[0008] S2. Based on the obtained key characteristic parameters, construct a health status evaluation model of the battery pack to monitor the health status of the battery pack in real time;

[0009] S3. Based on the key characteristic parameters input into the health status evaluation model and the output health status values, analyze the short-term dynamic changes and long-term degradation trends of the battery;

[0010] S4. Based on the obtained key characteristic parameters, construct a fault warning model, and the model issues a warning message when the battery shows abnormalities;

[0011] S5. Identify and infer failure modes based on early warning information;

[0012] S6. Develop optimization strategies based on the analysis results of short-term dynamic changes and long-term degradation trends.

[0013] To further optimize the technical solution, in step S1, the key characteristic parameters of the battery pack include current, internal resistance, temperature, number of charge and discharge cycles, and charging rate, which are used to characterize battery aging and performance degradation, and are obtained at high frequency through sensors.

[0014] To further optimize this technical solution, in step S2, in the health status assessment model of the battery pack:

[0015] Assume that the battery's state of health SOH at time t is , and is affected by the internal resistance of the battery ,temperature , charge and discharge times and charge and discharge rates The influence of factors;

[0016] The battery pack health status assessment model is as follows:

[0017] ;

[0018] in,

[0019] : Battery in time The health status value at the time of , ranging from 0 to 1, 0 means completely failed, 1 means completely healthy;

[0020] :time Internal resistance of the battery at all times;

[0021] : Reference internal resistance, which is the initial internal resistance of the battery;

[0022] :time Battery temperature at all times;

[0023] : reference temperature of the battery;

[0024] : Battery temperature fluctuation range;

[0025] :time The number of charge and discharge cycles of the battery at all times;

[0026] : The maximum designed cycle number of the battery;

[0027] : Time The charging and discharging current intensity at time

[0028] : The maximum charging and discharging current of the battery;

[0029] : is the weight coefficient, used to adjust the influence weight of each factor on the health state assessment.

[0030] Further optimizing the technical solution, in step S3, when analyzing the short-term dynamic changes and long-term degradation trends of the battery, it includes:

[0031] Short-term dynamic changes: Adopting time series analysis methods including moving average and exponential smoothing, focusing on capturing the rapid changes in the battery health state value, and timely identifying the sudden abnormalities or rapid degradation trends of the battery;

[0032] Long-term degradation trend: Fitting the slow-changing trends of the parameters of the battery charging and discharging cycle number, the maximum charging and discharging current of the battery, and the internal resistance value, and using methods of non-linear regression and Bayesian inference to predict the battery life cycle;

[0033] Analyzing the change range of the health state value in different time periods, the short-term fluctuations of the health state value indicate potential faults, and the long-term degradation trend provides a basis for formulating the battery replacement plan.

[0034] Further optimizing the technical solution, in the short-term dynamic changes:

[0035] The moving average takes the average value of the parameter values within a period of time, helps to smooth the data, removes sudden noise and interference, and the moving average is used to reflect the short-term trend of the battery state and find abnormal fluctuations;

[0036] Exponential smoothing gives higher weights to the most recent observations and is used to more sensitively capture the rapid changes in the battery state;

[0037] When the internal resistance of the battery suddenly becomes greater than the moving average value at a certain moment, a warning signal is sent out in a timely manner through short-term dynamic analysis, indicating possible faults or performance deterioration.

[0038] Further optimizing the technical solution, in the long-term degradation trend:

[0039] The degradation of the battery shows a non-linear trend. The experimental data is fitted through a non-linear regression model to capture the non-linear change law of the battery state;

[0040] The Bayesian method models the battery degradation process by introducing the combination of prior information and observed data, provides an estimate of the uncertainty of degradation, and obtains the prediction results of the battery health state in the long-term degradation analysis.

[0041] To further optimize this technical solution, in step S4, when constructing the fault warning model, let the set of battery key characteristic parameters be , where represents time at the th operating parameter, and the fault warning model outputs the fault risk factor . The fault warning model is as follows:

[0042] ;

[0043] Among them,

[0044] is the state change rate term;

[0045] is the abnormality index term;

[0046] is the trend prediction term;

[0047] is the weight coefficient used to adjust the influence of the three indicators on the final fault risk factor.

[0048] To further optimize this technical solution, in the fault warning model:

[0049] The state change rate term is calculated as follows:

[0050] ;

[0051] used to describe the change rate of the set of battery key characteristic parameters within time , and is used to capture rapidly changing abnormal behaviors;

[0052] is a set of battery key characteristic parameter sets before the model prediction time;

[0053] The abnormality index term is calculated as follows:

[0054] ;

[0055] Among them,

[0056] : the Reference values of key characteristic parameters, i.e., the mean or nominal value during normal operation;

[0057] : The standard deviation of the parameter, used to normalize the deviation magnitude;

[0058] : The number of parameters;

[0059] Trend prediction term The calculation formula is as follows:

[0060] ;

[0061] Among them,

[0062] : The length of the analysis time window;

[0063] : The state change rate at time .

[0064] To further optimize this technical solution, in step S5, when identifying and inferring the fault mode, first obtain a large amount of historical fault data, train based on the historical fault data, and establish a fault mode recognition system based on methods such as support vector machines, decision trees, and deep neural networks. Input the warning information into the fault mode recognition system, analyze the working state of the battery based on the abnormal key characteristic parameters in the warning information, and identify and infer different fault modes, including battery leakage, capacity attenuation, and short circuit.

[0065] To further optimize this technical solution, in step S6, the optimization strategies include adjusting the charge and discharge strategies of the battery, optimizing the temperature control system, and regularly performing status monitoring and calibration;

[0066] And automatically recommend the best maintenance cycle and replacement plan to reduce the risk of faults occurring.

[0067] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of a method for long-term failure prediction and early fault warning of a battery pack as described in the first aspect of the present invention are implemented.

[0068] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program instructions are executed by the processor, the steps of a method for long-term failure prediction and early fault warning of a battery pack as described in the first aspect of the present invention are implemented.

[0069] Compared with the prior art, the present invention provides a method for predicting long-term failure and early warning of faults in a battery pack, having the following beneficial effects:

[0070] The method for predicting long-term failure and early warning of faults in the battery pack greatly improves the accuracy and timeliness of battery fault prediction through dynamic health state modeling. Compared with the prior art, this method can quickly detect abnormal changes in the battery in the short term and accurately predict the remaining life of the battery through long-term degradation analysis, significantly reducing the false alarm and missed alarm problems in the traditional method. At the same time, based on various key characteristic parameters of the battery, this method can provide a scientific basis for the operation and maintenance of the battery pack, help achieve more accurate health monitoring and fault warning, effectively reduce the operation risk of the system, and improve the safety and reliability in the fields of energy storage and electric transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0072] Figure 1 It is a schematic flow chart of a method for predicting long-term failure and early warning of faults in a battery pack proposed by the present invention;

[0073] Figure 2 It is a schematic flow chart of a fault warning model in a method for predicting long-term failure and early warning of faults in a battery pack proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0074] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention with reference to the drawings in the specification.

[0075] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0076] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an independent or selectively exclusive embodiment with other embodiments. Embodiment

[0077] Reference Figures 1 to 2 , which is the first embodiment of the present invention. This embodiment provides a method for long-term failure prediction and early fault warning of a battery pack, including the following steps:

[0078] S1. Obtain the key characteristic parameters of the battery pack in real time.

[0079] In this embodiment, the key characteristic parameters of the battery pack include current, internal resistance, temperature, charge and discharge cycle times, and charging rate, which are used to characterize battery aging and performance degradation, and are obtained frequently through sensors.

[0080] In particular, the change in internal resistance is an early signal of battery aging. By monitoring the internal resistance, potential abnormalities can be identified before the battery pack fails. In addition, with the change of the battery working environment (such as external factors like temperature and humidity), these environmental variables also need to be recorded in real time and jointly analyzed with the battery characteristic parameters.

[0081] S2. Based on the obtained key characteristic parameters, construct a health state evaluation model of the battery pack to monitor the health state of the battery pack in real time.

[0082] In this embodiment, in the health state evaluation model of the battery pack:

[0083] Set the state of health (SOH) of the battery at time t to , and it is affected by the internal resistance of the battery, temperature , charge and discharge times , and charge and discharge rate ;

[0084] The health state evaluation model of the battery pack is as follows:

[0085] ;

[0086] Wherein,

[0087] : The health state value of the battery at time , ranging from 0 to 1, where 0 represents complete failure and 1 represents complete health;

[0088] : The internal resistance value of the battery at time ;

[0089] : The reference internal resistance value, which is the internal resistance value of the battery at the initial time;

[0090] : The temperature of the battery at time ;

[0091] : The reference temperature of the battery;

[0092] : The temperature fluctuation range of the battery;

[0093] : Time The number of charge-discharge cycles of the battery at a certain moment;

[0094] : The maximum designed cycle number of the battery;

[0095] : Time The charge-discharge current intensity at a certain moment;

[0096] : The maximum charge-discharge current of the battery;

[0097] : Is the weight coefficient, used to adjust the influence weight of each factor on the health state assessment.

[0098] In the model,

[0099] Internal resistance Influence on SOH: As the battery is used more, the internal resistance of the battery will gradually increase, which means that the energy conduction efficiency inside the battery decreases, affecting the output ability of the battery. The term in the formula reflects the influence of the internal resistance change on the health state. A larger internal resistance value means a decline in battery performance and a decrease in the SOH value.

[0100] Temperature Influence on SOH: The temperature of the battery directly affects its chemical reaction rate and lifespan. Excessive temperature will accelerate the degradation process of the battery. The term in the formula represents the deviation between the battery operating temperature and the reference temperature, reflecting the negative impact of temperature on battery health. The more the temperature deviates from the normal value, the lower the SOH value.

[0101] Charge-discharge times Influence on SOH: The number of charge-discharge cycles of the battery is one of the key factors determining the battery lifespan. Each charge-discharge will bring a certain amount of attenuation, resulting in a gradual decrease in battery capacity. The term in the formula represents the ratio of the battery charge-discharge cycle to the maximum designed cycle number, reflecting the usage frequency of the battery and its influence on the health state.

[0102] Charge-discharge current Influence on SOH: Excessive charge-discharge current will accelerate the aging process of the battery, resulting in a shortened battery lifespan. The The item represents the ratio of the charging current to the maximum charging current, reflecting the impact of the current on the state of health.

[0103] In practical applications, the weight coefficient needs to be adjusted according to the specific battery type, working environment, and usage scenario. Machine learning algorithms, such as regression analysis or Bayesian optimization, can be used to automatically adjust the weight coefficient so that the model can adapt to the health assessment requirements of different types of batteries.

[0104] S3. Based on the key characteristic parameters input by the state of health assessment model and the output state of health values, analyze the short-term dynamic changes and long-term degradation trends of the battery.

[0105] In this embodiment, when analyzing the short-term dynamic changes and long-term degradation trends of the battery, it includes:

[0106] Short-term dynamic changes: Adopt time series analysis methods including moving average and exponential smoothing to focus on capturing the rapid changes in the battery state of health values, and timely identify the sudden abnormalities or rapid degradation trends of the battery;

[0107] Long-term degradation trend: Fit the slow-changing trends of parameters such as the number of battery charge and discharge cycles, the maximum charge and discharge current of the battery, and the internal resistance value, and use methods of nonlinear regression and Bayesian inference to predict the battery life cycle;

[0108] Analyze the change amplitude of the state of health values in different time periods. The short-term fluctuations of the state of health values indicate potential failures, and the long-term degradation trend provides a basis for formulating a battery replacement plan.

[0109] Furthermore, in the short-term dynamic changes:

[0110] Moving average takes the mean value of parameter values over a period of time to help smooth the data, remove sudden noise and interference. Moving average is used to reflect the short-term trend of the battery state and detect abnormal fluctuations;

[0111] Exponential smoothing gives higher weights to the most recent observations and is used to more sensitively capture the rapid changes in the battery state;

[0112] When the internal resistance of the battery suddenly becomes greater than the moving average value at a certain moment, an early warning signal is sent out in a timely manner through short-term dynamic analysis, indicating possible failures or performance deterioration.

[0113] Furthermore, in the long-term degradation trend:

[0114] The degradation of the battery shows a non-linear trend. The experimental data is fitted by a non-linear regression model to capture the non-linear change law of the battery state;

[0115] The Bayesian method models the battery degradation process by introducing the combination of prior information and observed data, provides an estimate of the uncertainty of degradation, and obtains prediction results on the battery health state in long-term degradation analysis.

[0116] If the growth rate of the internal resistance and the change of the capacity degradation of the battery conform to the degradation law within a certain period of time, the remaining service life of the battery (such as the remaining number of charge and discharge cycles) can be predicted. Through long-term degradation analysis, the battery management system (BMS) can issue a prompt for battery replacement when the battery capacity drops to a certain critical value, avoiding continued use when the battery performance decays to an unacceptable level.

[0117] S4. Based on the obtained key characteristic parameters, construct a fault warning model, and the model issues a warning message when the battery shows an anomaly.

[0118] In this embodiment, when constructing the fault warning model, let the set of battery key characteristic parameters be , where represents time at the th operating parameter, and the fault warning model outputs a fault risk factor , and the fault warning model is as follows:

[0119] ;

[0120] Among them,

[0121] is the state change rate term;

[0122] is the abnormality index term;

[0123] is the trend prediction term;

[0124] is the weight coefficient used to adjust the influence of the three indicators on the final fault risk factor.

[0125] Furthermore, in the fault warning model:

[0126] The state change rate term is calculated as follows:

[0127] ;

[0128] used to describe the change rate of the set of battery key characteristic parameters within time , and is used to capture rapidly changing abnormal behaviors;

[0129] A set of key battery characteristic parameter sets before the model prediction time;

[0130] The state change rate term represents the rate of change vector of the parameter state, reflecting the severity of the operating state at the current moment.

[0131] Anomaly index term The calculation formula is as follows:

[0132] ;

[0133] Among them,

[0134] : The reference value of the th key characteristic parameter, that is, the mean or nominal value during normal operation;

[0135] : The standard deviation of the th parameter, used to normalize the deviation amplitude;

[0136] : The number of parameters.

[0137] The anomaly index term represents the deviation between the current state and the normal reference value (calculated based on Z-score), measuring the overall anomaly degree of the system.

[0138] Trend prediction term The calculation formula is as follows:

[0139] ;

[0140] Among them,

[0141] : The length of the analysis time window;

[0142] : The state change rate at time .

[0143] Represents the fluctuation trend of the state change within a past period of time , used to capture the potential risk of rapid deterioration.

[0144] Automatically calibrated through optimization algorithms (such as genetic algorithms or Bayesian optimization).

[0145] When this model is used, it includes:

[0146] Real-time monitoring and calculation: During operation, the parameter data of the battery (such as internal resistance, current, etc.) is collected through sensors and input into the model in the form of . At the same time, the reference value of each parameter is calculated according to historical data and standard deviation . The model captures rapid abnormal fluctuations through the state change rate term and evaluates the overall deviation degree of the state through the abnormality index .

[0147] Threshold warning: Set a risk threshold. When is greater than the risk threshold, a warning signal is triggered. To adapt to different environments and battery usage scenarios, the threshold can be dynamically adjusted according to the operating data. For example, increase the threshold tolerance in extreme temperature environments to avoid frequent false alarms.

[0148] Trend evaluation and intervention: The trend prediction term of the model is sensitive to the accumulation of historical fluctuations. Therefore, when does not exceed the threshold, potential fault trends can still be identified in advance by observing . When is higher than the preset value, the system can take preventive measures in advance (such as reducing the charge and discharge rate or improving the heat dissipation conditions).

[0149] Multi-parameter adaptability: By flexibly defining the input parameter set , the model can adapt to different types of battery systems (such as single cells or battery packs). The weights of the parameters can be optimized according to different application scenarios (such as electric vehicles or energy storage systems).

[0150] Self-learning and optimization: The fault warning model supports self-learning based on historical fault data. By continuously updating the reference values and weight coefficients, the system can improve the accuracy of the warning and reduce the false alarm rate.

[0151] In this embodiment, two models are actually applied. Considering the influence of temperature and internal resistance, the application scenarios are as follows:

[0152] System parameters: A set of lithium-ion battery packs with a capacity of 100 Ah.

[0153] Initial state of health (SOH): 100%.

[0154] Normal operating conditions:

[0155] Temperature range: 15 - 45 °C

[0156] Internal resistance range:

[0157] State of health warning value: 70%

[0158] Risk threshold of the fault risk factor: 0.75.

[0159] Based on the model, record and analyze the operating data:

[0160] Initial state (time point )

[0161] Temperature:

[0162] Internal resistance:

[0163] Health status:

[0164] Fault risk factor:

[0165] When in the initial state, the battery pack runs stably, all parameters are within the normal range, and there is no abnormal risk.

[0166] During operation (time point , record abnormal changes):

[0167] Temperature: (exceeding the normal range)

[0168] Internal resistance: (deviating from the normal range)

[0169] Health status: Calculated according to the health status assessment model, it is obtained that is 78%

[0170] Fault risk factor: Calculated according to the fault warning model, it is obtained that is 0.88

[0171] During operation, the temperature and internal resistance increase abnormally, the health status is close to the warning value, and the fault risk factor has exceeded the risk threshold.

[0172] Trigger the warning signal, indicating that the temperature and internal resistance increase abnormally, the health status drops sharply, and there is a high fault risk.

[0173] Give suggestions:

[0174] Short-term measures: Immediately reduce the battery operation load and check whether the cooling system is abnormal and causes the temperature to rise.

[0175] Long-term measures: Conduct in-depth maintenance on the battery pack and replace the aging single cells if necessary to avoid system failures.

[0176] S5. Based on the warning information, identify and infer the fault mode.

[0177] In this embodiment, when identifying and inferring fault modes, a large amount of historical fault data is first obtained and trained based on the historical fault data. Based on methods such as support vector machines, decision trees, and deep neural networks, a fault mode recognition system is established. The early warning information is input into the fault mode recognition system, and the working state of the battery is analyzed based on the abnormal key characteristic parameters in the early warning information to identify and infer different fault modes, including battery leakage, capacity attenuation, and short circuit.

[0178] Fault mode recognition not only helps improve the accuracy of fault prediction but also helps maintenance personnel take targeted intervention measures, thereby extending the service life of the storage battery.

[0179] S6. Based on the analysis results of short-term dynamic changes and long-term degradation trends, formulate an optimization strategy.

[0180] In this embodiment, the optimization strategy includes adjusting the charge and discharge strategy of the battery, optimizing the temperature control system, and regularly performing status monitoring and calibration;

[0181] And automatically recommend the best maintenance cycle and replacement plan to reduce the risk of faults.

[0182] Combined with the usage scenarios of the battery pack (such as electric vehicles, energy storage power stations, etc.), different maintenance and management strategies can be customized. For example, for the battery pack under high-load conditions, the heat dissipation design can be strengthened to reduce the impact of temperature on battery degradation; for the battery in a low-load environment, the charging strategy can be optimized to delay the degradation speed. Through precise health management and optimization measures, the usage efficiency and life of the battery can be greatly improved. Embodiment

[0183] This embodiment also provides a computer device applicable to a method for medium- and long-term failure prediction and early fault warning of a battery pack, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement a method for medium- and long-term failure prediction and early fault warning of a battery pack as proposed in the above embodiment.

[0184] This embodiment also provides a storage medium with a computer program stored thereon, and when the program is executed by a processor, it implements a method for medium- and long-term failure prediction and early fault warning of a battery pack as proposed in the above embodiment.

[0185] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0186] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0187] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0188] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing it in a suitable manner if necessary, and then storing it in a computer memory.

[0189] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well-known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0190] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for long-term failure prediction and early fault warning in a battery pack, characterized in that, Including the following steps: S1. Obtain the key characteristic parameters of the battery pack in real time; S2. Based on the obtained key characteristic parameters, construct a health state evaluation model for the battery pack to monitor the health state of the battery pack in real time; S3. Analyze the short-term dynamic changes and long-term degradation trends of the battery based on the key characteristic parameters input into the health state evaluation model and the output health state values; S4. Based on the obtained key characteristic parameters, construct a fault warning model, and the model issues a warning message when the battery shows an abnormality; When constructing a fault warning model, let the set of battery key characteristic parameters be , where represents time at the moment of the th operating parameter, and the fault warning model outputs a fault risk factor . The fault warning model is as follows: ； Among them, is the state change rate term; is an abnormality index item; is a trend prediction item; is the weight coefficient used to adjust the influence of three indicators on the final failure risk factor; S5. Based on the warning message, identify and infer the fault mode; S6. Based on the analysis results of the short-term dynamic changes and long-term degradation trends, formulate an optimization strategy.

2. The medium- and long-term failure prediction and early fault warning method for a battery pack according to claim 1, wherein, In the step S1, the key characteristic parameters of the battery pack include current, internal resistance, temperature, charge and discharge cycle times, and charging rate, which are used to characterize battery aging and performance degradation, and are obtained frequently through sensors.

3. A method for long-term failure prediction and early fault warning of a battery pack according to claim 1, characterized in that In the step S2, in the health state evaluation model of the battery pack: Set the state of health SOH of the storage battery at time t to be , and it is affected by the internal resistance of the battery , temperature , number of charge and discharge cycles as well as the charge and discharge rate ; The health state evaluation model of the battery pack is as follows: ； Among them, : The state of health value of the battery at time , with a range of 0 to 1, where 0 indicates complete failure and 1 indicates complete health; : Time Internal resistance value of the battery at that moment; : Reference internal resistance value, which is the internal resistance value of the battery at the initial time; : Time The temperature of the battery at that moment; : Reference temperature of the battery; : Temperature fluctuation range of the battery; : Time The number of charge and discharge cycles of the battery at a moment; : The maximum designed cycle number of the battery; : Time The charging and discharging current intensity at a moment; : Maximum charge and discharge current of the battery; : is the weight coefficient, which is used to adjust the influence weights of various factors on the health status assessment.

4. A method for long-term failure prediction and early fault warning of a battery pack according to claim 1, characterized in that, In the step S3, when analyzing the short-term dynamic changes and long-term degradation trends of the battery, it includes: Short-term dynamic changes: Adopt time series analysis methods including moving average and exponential smoothing to focus on capturing the rapid changes in the battery health state value, and timely identify the sudden abnormalities or rapid deterioration trends of the battery; Long-term degradation trend: Fit the slow-changing trends of parameters such as the charge and discharge cycle times of the battery, the maximum charge and discharge current of the battery, and the internal resistance value, and use methods of nonlinear regression and Bayesian inference to predict the battery life cycle; Analyze the change amplitude of the health state value in different time periods. The short-term fluctuations of the health state value indicate potential faults, and the long-term degradation trend provides a basis for formulating a battery replacement plan.

5. A method for medium- and long-term failure prediction and early fault warning of a battery pack according to claim 4, characterized in that, In the short-term dynamic changes: Moving average takes the mean value of parameter values over a period of time to help smooth the data, remove sudden noise and interference. Moving average is used to reflect the short-term trend of the battery state and discover abnormal fluctuations; Exponential smoothing gives higher weights to the most recent observations and is used to more sensitively capture the rapid changes in the battery state; When the internal resistance of the battery suddenly becomes greater than the moving average value at a certain moment, a warning signal is sent in a timely manner through short-term dynamic analysis to indicate possible faults or performance deterioration.

6. A method for long-term failure prediction and early fault warning of a battery pack according to claim 4, characterized in that, In the long-term degradation trend: The degradation of the battery shows a non-linear trend. Fit the experimental data through a non-linear regression model to capture the non-linear change law of the battery state; The Bayesian method models the battery degradation process by combining prior information and observed data, and provides an estimate of the uncertainty of degradation. In long-term degradation analysis, obtain the prediction results regarding the battery health state.

7. A method for long-term failure prediction and early fault warning of a battery pack according to claim 1, characterized in that, In the fault warning model: State change rate term The calculation formula is as follows: ； For describing time within the set of key battery characteristic parameters to capture abnormal behaviors with rapid changes A set of battery key characteristic parameter sets before the model prediction moment; Abnormality index item The calculation formula is as follows: ； Among them, : The reference value of the th key characteristic parameter, i.e., the mean value or nominal value during normal operation; : Standard deviation of the th parameter, used to normalize the deviation magnitude; : Number of parameters; Trend prediction item The calculation formula is as follows: ； Among them, : The length of the analysis time window; : At time of the rate of change of state.

8. A method for long-term failure prediction and early fault warning of a battery pack according to claim 1, characterized in that, In step S5, when identifying and inferring the failure mode, a large amount of historical failure data is first obtained and trained based on the historical failure data. Based on methods such as support vector machines, decision trees, and deep neural networks, a failure mode recognition system is established. The warning information is input into the failure mode recognition system, and the working state of the battery is analyzed based on the abnormal key characteristic parameters in the warning information to identify and infer different failure modes, including battery leakage, capacity attenuation, and short circuit.

9. A method for long-term failure prediction and early fault warning in a battery pack, according to claim 1, wherein In step S6, the optimization strategies include adjusting the charge and discharge strategies of the battery, optimizing the temperature control system, and regularly performing status monitoring and calibration; and automatically recommending the best maintenance cycle and replacement plan to reduce the risk of failure occurrence.

Images