Energy storage station battery safety early warning system based on big data

Abstract

The invention relates to the technical field of battery early warning, in particular to an energy storage station battery safety early warning system based on big data. The method comprises the following steps: acquiring a temperature signal, a stress signal, an electric signal and a gas concentration signal of a battery; according to whether the electric signal satisfies a first preset condition, determining whether to generate a time-delay early warning signal; according to whether the temperature signal and the stress signal meet a second preset condition, whether a moderate-time early warning signal is generated or not is judged; and judging whether a short-time early warning signal is generated or not according to whether the stress signal, the temperature signal, the electric signal and the gas concentration signal meet a third preset condition or not. According to the method, heat, force, gas, electricity and other signals are graded according to corresponding speeds in the battery thermal runaway process, and multi-stage safety early warning based on multi-source safety parameters is achieved. Multi-level safety early warning is divided into long-time failure early warning, medium-time fault diagnosis early warning and short-time thermal runaway early warning, and full coverage of battery life cycle failure prediction, fault diagnosis and thermal runaway early warning is achieved.

Description

Technical Field

[0001] The present invention relates to the field of battery early warning technology, and in particular to a battery safety early warning system for energy storage stations based on big data. Background Art

[0002] Energy storage power stations are built on the basis of a large number of batteries. Numerous battery modules are densely arranged in series or parallel. During operation, energy storage batteries may have electrical, thermal and other safety problems. Once a module has a problem, the heat generated by the module battery will cause fire, explosion and other safety accidents through heat transfer, thermal radiation and spraying of combustion materials.

[0003] Currently, most existing early warning solutions use battery pack temperature, insulation resistance, or other parameters to determine the safety status of energy storage systems. However, due to the slow response of temperature and resistance signals during battery thermal runaway, thermal runaway often already occurs by the time an anomaly is detected. Therefore, solutions that provide safety warnings by monitoring only a few parameters, such as battery temperature and resistance, cannot fully reflect the battery's safety status, making it difficult to effectively prevent safety accidents caused by battery thermal runaway. They also suffer from incomplete early warning signals and delayed safety warnings. Summary of the Invention

[0004] In view of this, the present invention provides a battery safety early warning system for energy storage stations based on big data to solve the problem of incomplete battery early warning for energy storage power stations in the prior art.

[0005] In a first aspect, the present invention provides a big data-based battery safety warning method for an energy storage station, the method comprising: obtaining operating data of the energy storage station battery, the operating data comprising a temperature signal, a stress signal, an electrical signal, and a gas concentration signal; determining whether to generate a long-term warning signal based on whether the electrical signal satisfies a first preset condition; determining whether to generate a medium-term warning signal based on whether the temperature signal and the stress signal satisfy a second preset condition; and determining whether to generate a short-term warning signal based on whether the stress signal, the temperature signal, the electrical signal, and the gas concentration signal satisfy a third preset condition.

[0006] This invention proposes grading multi-level warning signals, such as heat, force, gas, and electricity, according to their corresponding speeds during the battery thermal runaway process, achieving multi-level safety warnings based on multiple safety parameters. Furthermore, the multi-level safety warnings are divided into long-term failure warnings, medium-term fault diagnosis warnings, and short-term thermal runaway warnings, achieving full coverage of failure prediction, fault diagnosis, and thermal runaway warnings throughout the lifecycle of energy storage station batteries.

[0007] In an optional embodiment, the electrical signal includes current, voltage and electrochemical impedance spectrum, and whether to generate a long-term warning signal is determined based on whether the electrical signal meets a first preset condition, including: calculating the actual capacity of the battery, the remaining cycle life of the battery and the variance between the actual capacity of the battery and the remaining cycle life module based on the electrical signal; when the battery capacity decay determined based on the actual capacity of the battery is greater than a first threshold, generating a capacity decay warning; when the remaining cycle life of the battery is less than a second threshold, generating a cycle life warning; when the variance between the actual capacity of the battery and the remaining cycle life module is greater than a third threshold, generating a battery consistency warning, the capacity decay warning, cycle life warning and battery consistency warning constitute a long-term warning signal.

[0008] In the present invention, early warning of early failure and high-risk behavior of energy storage batteries is achieved by calculating the actual battery capacity, the remaining cycle life of the battery, and the variance between the actual battery capacity and the remaining cycle life of the battery based on electrical signals.

[0009] In an optional embodiment, the temperature signal includes the internal temperature of the battery, and the stress signal includes the internal pressure of the battery. Whether to generate a medium-time warning signal is determined based on whether the temperature signal and the stress signal meet a second preset condition, including: when the internal temperature of the battery is greater than a fourth threshold, generating a warning that the internal temperature of the battery is too high; when the internal pressure of the battery is greater than a fifth threshold, generating a warning that the internal pressure of the battery is too high. The warning that the internal temperature of the battery is too high and the warning that the internal pressure of the battery is too high constitute a medium-time warning signal.

[0010] In the present invention, early warning of a fault is achieved by early warning of the internal temperature and internal pressure of the battery.

[0011] In an optional embodiment, the temperature signal includes the internal temperature of the battery, the stress signal includes the external pressure of the battery, and the electrical signal includes the internal voltage of the battery. Whether to generate a short-time warning signal is determined based on whether the stress signal, the temperature signal, the electrical signal and the gas concentration signal meet a third preset condition, including: when the internal temperature of the battery is greater than a fourth threshold, generating a warning that the internal temperature of the battery is too high; when the external pressure of the battery is greater than a sixth threshold, generating a warning that the external pressure of the battery is too high; when the internal voltage of the battery is greater than a seventh threshold, generating a warning that the internal voltage of the battery is too high; when the gas concentration signal is greater than an eighth threshold, generating a warning that the internal gas concentration of the battery is too high. The warning that the internal temperature of the battery is too high, the warning that the external pressure of the battery is too high, the warning that the internal voltage of the battery is too high and the warning that the internal gas concentration of the battery are too high constitute a short-time warning signal.

[0012] In an optional embodiment, the method also includes: performing feature extraction, feature selection, and feature conversion on the operating data to obtain processed features; using the processed features to train a time series data prediction model; using the trained time series data prediction model to train the battery's future operating data; and issuing a safety warning based on the battery's future operating data.

[0013] In the present invention, further early warning can be performed by predicting the future operating data of the battery.

[0014] In an optional implementation, obtaining the operating data of the battery includes: obtaining the operating data of the battery during the operation of the battery; and saving the obtained operating data at different moments in a battery state evolution database.

[0015] In the present invention, a battery state evolution database is used to store operating data, providing a data basis for subsequent data analysis.

[0016] In a second aspect, the present invention provides a battery safety warning system for an energy storage station based on big data. The system includes: a data transmission layer for obtaining operating data of the energy storage station battery, the operating data including temperature signals, stress signals, electrical signals and gas concentration signals; a data storage layer for storing operating data based on a battery state evolution database; a data analysis layer for determining whether to generate a long-term warning signal based on whether the electrical signal meets a first preset condition; determining whether to generate a medium-term warning signal based on whether the temperature signal and the stress signal meet a second preset condition; determining whether to generate a short-term warning signal based on whether the stress signal, temperature signal, electrical signal and gas concentration signal meet a third preset condition; and an application layer for providing hierarchical warning services based on interactive technology.

[0017] In a third aspect, the present invention provides a battery safety warning device for an energy storage station based on big data, the device comprising: a data acquisition module for acquiring operating data of the energy storage station battery, the operating data comprising temperature signals, stress signals, electrical signals and gas concentration signals; a long-time warning module for determining whether to generate a long-time warning signal based on whether the electrical signal satisfies a first preset condition; a medium-time warning module for determining whether to generate a medium-time warning signal based on whether the temperature signal and the stress signal meet a second preset condition; and a short-time warning module for determining whether to generate a short-time warning signal based on whether the stress signal, temperature signal, electrical signal and gas concentration signal meet a third preset condition.

[0018] In a fourth aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the big data-based energy storage station battery safety early warning method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0019] In a fifth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the big data-based energy storage station battery safety early warning method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0020] In a sixth aspect, the present invention provides a computer program product comprising computer instructions, the computer instructions being used to enable a computer to execute the energy storage station battery safety early warning method based on big data according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 1 is a flow chart of a battery safety early warning method for an energy storage station based on big data according to an embodiment of the present invention;

[0023] Figure 2 is a schematic diagram of operation data collection and transmission according to an embodiment of the present invention;

[0024] Figure 3 This is a structural block diagram of a battery safety early warning system for energy storage stations based on big data according to an embodiment of the present invention;

[0025] Figure 4 is a schematic diagram of the early warning process of the security early warning model according to an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of model construction according to an embodiment of the present invention;

[0027] Figure 6 1 is a structural block diagram of a battery safety early warning device for an energy storage station based on big data according to an embodiment of the present invention;

[0028] Figure 7 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0030] According to an embodiment of the present invention, an embodiment of a battery safety early warning method for an energy storage station based on big data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] In this embodiment, a battery safety early warning method for energy storage stations based on big data is provided, which can be used for electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1 FIG. 1 is a flow chart of a battery safety early warning method for an energy storage station based on big data according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0032] Step S101: Acquire operating data of the energy storage station battery. The operating data includes temperature signals, stress signals, electrical signals, and gas concentration signals. Specifically, the battery may be an energy storage battery deployed in an energy storage power station. Various sensors deployed in the energy storage power station, such as temperature sensors and gas sensors, may also be used to collect battery operating data. The acquired temperature signals include the battery surface temperature detected by thermocouples, the battery core temperature detected by built-in temperature sensors, and the ambient temperature near the battery detected by temperature and humidity sensors. Electrical signals include the battery current detected by current sensors, the battery voltage detected by voltage sensors, and the battery electrochemical impedance spectrum detected by an electrochemical workstation. Stress signals include battery surface stress or pressure signals detected by strain and pressure sensors, as well as battery internal stress or pressure signals detected by built-in strain and pressure sensors. Gas concentration signals include the concentrations of gases such as CO, H2, and CO2 detected by gas sensors such as gas chromatographs.

[0033] In an optional embodiment, obtaining the operating data of the battery includes: obtaining the operating data of the battery during the operation of the battery; and saving the obtained operating data at different times to a battery state evolution database. Specifically, the battery state evolution database is designed to store and manage a database architecture for system data with historical traceability or state changes. It can not only save the current state of the data, but also record all historical states and changes of the data. In this embodiment, the battery state evolution database uses the TDengine database as the storage of the battery state. TDengine is an open source, high-performance, distributed time series database that can easily process time series data in energy systems. At the same time, for this database, the hyper engine is used as the storage engine of the TDengine database to achieve compression and query of large amounts of data.

[0034] Before storing the acquired operational data in the battery state evolution database, the data is pre-processed through cleaning, synchronization, and format conversion. This includes removing raw data containing noise and erroneous values, removing duplicate data, and filling missing values using mean-filling methods. When the acquired operational data is from batteries in energy storage power stations, the data stored in the battery state evolution database includes real-time and historical data such as temperature, current, voltage, and gas changes for batteries in different operating scenarios and models.

[0035] Step S102: determining whether to generate a long-term warning signal based on whether the electrical signal meets a first preset condition.

[0036] Step S103 : determining whether to generate a medium-term warning signal based on whether the temperature signal and the stress signal meet a second preset condition.

[0037] Step S104 , determining whether to generate a short-time warning signal based on whether the stress signal, the temperature signal, the electrical signal, and the gas concentration signal meet a third preset condition.

[0038] Specifically, this embodiment, when providing battery warnings based on battery operating data, implements three levels of warnings: long-term warning, medium-term warning, and short-term warning by monitoring changes in the battery's operating status. First, during normal battery operation, conditions such as overcharge and over-discharge are unavoidable. During these times, the battery temperature remains within the normal range, but the electrical signal may be the first to show an abnormality. Therefore, this embodiment first monitors the electrical signal. If an abnormality is detected, a long-term warning signal is generated. This long-term warning signal is used to monitor for early battery failure and high-risk behavior, with a lead time of at least 40 days.

[0039] As the battery continues to operate, the battery temperature continues to rise, and the SEI (Solid Electrolyte Interphase), electrode materials, and electrolyte will decompose inside the battery. This process will release a large amount of heat and be accompanied by the generation of gases. At this time, the battery temperature may become abnormal and the battery pressure will continue to increase. Therefore, the temperature signal and stress signal can be further monitored to achieve medium-term warning. In this implementation, the warning time is greater than or equal to 10 days.

[0040] As the battery pressure continues to increase, when the safety valve (also called the pressure relief valve) inside the battery is opened, a large amount of gas inside the battery will overflow. At the same time, the stress signal, temperature signal, electrical signal and gas concentration signal of the battery will also change dramatically. Therefore, the stress signal, temperature signal, electrical signal and gas concentration signal can be further monitored to achieve short-term warning. The time of the short-term warning is greater than or equal to 2 hours. In addition, for the generated long-term warning signal, medium-term warning signal and short-term warning signal, the signal response speed changes from slow to fast, that is, the response speed for the short-term warning signal is the fastest.

[0041] The big data-based battery safety early warning method for energy storage stations provided by the present invention proposes grading multi-level early warning signals, such as heat, force, gas, and electricity, according to their corresponding speeds during the battery thermal runaway process. This implements multi-level safety early warnings based on multiple safety parameters. Furthermore, the multi-level safety early warnings are divided into long-term failure warnings, medium-term fault diagnosis warnings, and short-term thermal runaway warnings, achieving comprehensive coverage of failure prediction, fault diagnosis, and thermal runaway early warnings throughout the lifecycle of energy storage station batteries.

[0042] In this embodiment, a battery safety early warning method for an energy storage station based on big data is provided, which includes the following steps:

[0043] Step S201: Obtain the operating data of the energy storage station battery. The operating data includes temperature signals, stress signals, electrical signals, and gas concentration signals. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0044] Step S202: determining whether to generate a long-term warning signal based on whether the electrical signal satisfies a first preset condition.

[0045] Specifically, the above step S202 includes:

[0046] Step S2021 calculates the actual battery capacity, the remaining battery cycle life, and the inter-module variance between the actual battery capacity and the remaining battery cycle life based on the electrical signal. Specifically, the actual battery capacity can be calculated using the current in the electrical signal or the voltage. When current is used for calculation, the ampere-hour integration method can be used to calculate the actual battery capacity by integrating the current over time during the battery's charge and discharge process. When voltage is used for calculation, a calibration curve between the battery and capacity can be established based on the corresponding relationship between the battery's open-circuit voltage and the battery capacity. When the battery voltage is determined, the corresponding capacity value is determined.

[0047] For the remaining cycle life of the battery, the historical charge and discharge data of the battery can be analyzed through empirical models such as the exponential decay model, and the relationship between the battery capacity decay and the number of cycles can be established. Then, the remaining cycle life can be predicted based on the current capacity of the battery and the empirical model. When the predicted battery capacity drops to the specified end-of-life capacity (such as 80% of the initial capacity), the corresponding number of cycles is the remaining cycle life. In addition, the electrochemical impedance spectroscopy method can also be used to determine the remaining cycle life. As the number of battery cycles increases, the impedance of the battery will gradually increase. By establishing a relationship model between impedance and cycle life, the remaining cycle life can be estimated based on the currently measured battery impedance.

[0048] For the variance between the actual battery capacity and the remaining cycle life module, we can first obtain the actual capacity data and remaining cycle life of multiple batteries, then calculate the average value of the two respectively, and then calculate the sum of squared deviations based on the average values, and finally calculate the variance based on the sum of squared deviations.

[0049] Step S2022: When the battery capacity decay determined based on the actual battery capacity is greater than a first threshold, a capacity decay warning is generated.

[0050] Step S2023: When the remaining cycle life of the battery is less than a second threshold, a cycle life warning is generated.

[0051] Step S2024: When the variance between the actual battery capacity and the remaining cycle life module is greater than a third threshold, a battery consistency warning is generated. The capacity attenuation warning, cycle life warning, and battery consistency warning constitute a long-term warning signal.

[0052] Specifically, the calculated battery capacity decay, remaining cycle life, and the variance between the actual battery capacity and the remaining cycle life module are compared with the corresponding thresholds, and a determination is made based on the comparison results whether to generate a long-term warning signal. The first threshold, the second threshold, and the third threshold can be determined based on actual conditions. For example, when the battery capacity decay reaches 20%, a capacity decay warning is generated; when the remaining cycle life of the battery reaches 80%, a cycle life warning is generated; and when the variance between the actual battery capacity and the remaining cycle life module exceeds 10%, a battery consistency warning is generated. When any of these warnings is generated, it indicates that the battery is abnormal and a long-term warning signal is generated. For example, when the battery capacity decay reaches 20%, a long-term warning signal corresponding to the capacity decay warning is generated.

[0053] Step S203 : determining whether to generate a medium-term warning signal based on whether the temperature signal and the stress signal meet a second preset condition.

[0054] Specifically, the above step S203 includes:

[0055] Step S2031: When the internal temperature of the battery is greater than a fourth threshold, a warning of excessive internal temperature of the battery is generated.

[0056] Step S2032: When the internal pressure of the battery is greater than the fifth threshold, a warning signal indicating that the internal pressure of the battery is too high is generated. The warning signal indicating that the internal temperature of the battery is too high and the internal pressure of the battery are too high constitute a medium-time warning signal.

[0057] The fourth and fifth thresholds can be determined based on actual conditions. For example, when the battery internal pressure reaches 2.0 bar, a high battery internal pressure warning is generated; when the battery internal temperature reaches 50°C, a high battery internal temperature warning is generated.

[0058] Step S204 , determining whether to generate a short-time warning signal based on whether the stress signal, the temperature signal, the electrical signal, and the gas concentration signal meet a third preset condition.

[0059] Specifically, the above step S204 includes:

[0060] Step S2041: When the internal temperature of the battery is greater than a fourth threshold, a warning of excessive internal temperature of the battery is generated.

[0061] Step S2042: When the battery external pressure is greater than a sixth threshold, a battery external pressure excessively high warning is generated.

[0062] Step S2043: When the internal voltage of the battery is greater than the seventh threshold, a warning of excessive internal voltage of the battery is generated.

[0063] Step S2044: When the gas concentration signal is greater than the eighth threshold, a battery internal gas concentration warning is generated. The battery internal temperature too high warning, the battery external pressure too high warning, the battery internal voltage too high warning and the battery internal gas concentration warning constitute a short-term warning signal.

[0064] Similar to the above thresholds, the thresholds here can also be set according to actual conditions. For example, when the external pressure of the battery reaches 5.0 bar, a high external pressure warning is generated; when the internal temperature of the battery reaches 50°C, a high internal temperature warning is generated; when the internal voltage of the battery exceeds 4.5V, a short circuit warning is generated; when the oxygen or hydrogen concentration inside the battery exceeds 0.5%, a gas concentration warning is generated.

[0065] In this embodiment, a battery safety early warning method for an energy storage station based on big data is provided, which includes the following steps:

[0066] Step S301: Obtain the operating data of the energy storage station battery. The operating data includes temperature signals, stress signals, electrical signals and gas concentration signals. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0067] Step S302: Determine whether to generate a long-term warning signal based on whether the electrical signal meets the first preset condition; see Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0068] Step S303: Determine whether to generate a timely warning signal based on whether the temperature signal and the stress signal meet the second preset condition; see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0069] Step S304: Determine whether to generate a short-term warning signal based on whether the stress signal, temperature signal, electrical signal, and gas concentration signal meet a third preset condition. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0070] Step S305: perform feature extraction, feature selection, and feature conversion on the operating data to obtain processed features; use the processed features to train a time series data prediction model; use the trained time series data prediction model to train the battery's future operating data; and issue a safety warning based on the battery's future operating data.

[0071] Specifically, in addition to using real-time collected operating data to provide early warning for the battery, the future operating data of the battery can also be further predicted to achieve further early warning. Among them, since the operating data of the battery is time series data, this embodiment trains a time series data prediction model to predict the future operating data of the battery. During model training, the historical operating data of the battery stored in the battery state evolution database is obtained, and then the historical operating data is subjected to feature extraction, feature selection and feature conversion processing. Feature extraction specifically extracts features such as battery internal pressure, battery voltage, battery current, battery internal gas concentration, battery temperature, etc. from the historical operating data; then, through feature selection (such as using a filter method), features that contribute to model performance are selected through statistics (such as correlation coefficient, variance, mutual information, etc.) to reduce redundant features. Feature conversion is mainly carried out by processing such as standardization and normalization.

[0072] After the processed features are used to train the time series data prediction model, model evaluation and model testing can be further performed to improve model performance. The model evaluation and model testing process can be implemented with reference to relevant technologies and will not be described in detail here. For the final model, the current operating data of the battery can be input into the model to predict the future operating data of the battery, and then the predicted future data can be used for early warning. Among them, the process of early warning for future data can refer to the process from step S302 to step S304 above. By using future data for early warning, the early warning can be made more advanced, which facilitates the implementation of relevant measures for protection.

[0073] For the time series data prediction model, this embodiment uses the ARIMA model. The core of this model is the three parameters p, d, and q, which correspond to the autoregressive order, the number of differencing steps, and the sliding average order, respectively. The present invention uses the autocorrelation function (ACF) to determine the order q, and the partial autocorrelation function (PACF) to determine the order p.

[0074] The ACF formula is: Where: X t is the t-th observation in the time series, δ is the mean of the time series, k is the number of lags, which represents the gap between the current moment and the past time, and T is the length of the time series.

[0075] The PACF formula is: PACF(k)=corr(X t ,X t-k |X t-1 ,X t-2 ,...,X t-(k-1) ), where: X t is the observed value at the current moment, X t-k is the observed value at time lag k, X t-1,X t-2 ,...,X t-(k-1) is the intermediate observation between t and tk.

[0076] This embodiment also provides a big data-based energy storage station battery safety early warning system, which includes:

[0077] The data transmission layer is used to obtain the operating data of the energy storage station battery, including temperature signals, stress signals, electrical signals and gas concentration signals;

[0078] Data storage layer, used to store operating data based on the battery state evolution database;

[0079] The data analysis layer is used to determine whether to generate a long-term warning signal based on whether the electrical signal meets the first preset condition; to determine whether to generate a medium-term warning signal based on whether the temperature signal and stress signal meet the second preset condition; and to determine whether to generate a short-term warning signal based on whether the stress signal, temperature signal, electrical signal and gas concentration signal meet the third preset condition.

[0080] The application layer is used to provide graded warning services based on interactive technology.

[0081] Among them, the data transmission layer is used to receive the operating data collected by various sensors, such as Figure 2 As shown in the figure, the operation data collected by various sensors (such as temperature sensors, gas concentration sensors, electrical signal sensors and stress sensors) are transmitted to the big data platform (i.e., the energy storage station battery safety warning system based on big data) using the message queue model. After receiving the operation data, the data transmission layer in the system saves it to the data storage layer. Figure 3 As shown in Figure 1, the data storage layer includes a battery state evolution database, which is used to store long-term operation data of energy storage station batteries and static data required for analysis. This data storage layer includes the TDengine time series database and the MySQL database.

[0082] The data analysis layer includes a safety warning model, which performs multi-dimensional analysis on various battery characterization parameters and outputs multi-level warning signals. Specifically, the data analysis layer includes a data call / operation module, a safety warning model module, a multi-dimensional intelligent statistical analysis module, a real-time calculation engine module, an offline calculation engine module, and a chart generation engine module. Among them, the data call / operation module is used to call relevant data from the data storage layer, the real-time calculation engine module and the offline calculation engine module are used to perform pre-warning calculations on the called data, such as calculating the actual battery capacity, the remaining battery cycle life, etc.; the safety warning model module is used to use the above-mentioned warning methods for various types of signals to issue warnings; the chart generation engine module is used to generate charts for the warning results; the multi-dimensional intelligent statistical analysis is used to perform statistical analysis on the called data, such as calculating the mean, standard deviation, etc., and the results are generated into corresponding charts through the chart generation engine.

[0083] The application layer includes a battery management service module, a hierarchical warning service module, a user management service module, an energy storage station service module, and other service modules. The battery management service module manages the entire battery lifecycle. For example, it develops and implements battery charging and discharging strategies to ensure safe and efficient operation. The hierarchical warning service module outputs different types of alerts based on different warning signals to facilitate operations and maintenance personnel. The user management service module handles user-related matters, including user registration, login, and permission management. It sets different user roles (such as administrator and ordinary user) and assigns corresponding permissions, while also managing user information and password resets. The energy storage station service manages and schedules energy storage stations. For example, it optimizes energy storage station charging and discharging plans and coordinates interactions between energy storage stations and the power grid or other energy systems to improve overall operational efficiency and stability. Other service modules provide supplementary or expanded functional services, such as integration with external systems (such as energy trading platforms and other energy management systems) or customized services tailored to specific application scenarios and user needs. The various services provided in the application layer can be displayed on a large screen or in the management backend using user visualization and interaction technology.

[0084] Among them, the specific warning process of the security warning model can be referred to as follows Figure 4The process shown is implemented. First, during the normal operation of the battery, it is difficult to avoid conditions such as overcharging and discharging. At this time, the battery temperature is still within the normal threshold range, and the electrical signal will be the first to show abnormalities. The safety warning model performs real-time analysis of the internal electrical signals of the battery. The electrical signals include parameters such as battery current and voltage. After calculation, the actual battery capacity, the remaining battery cycle life, and the variance between the actual battery capacity and the remaining battery cycle life module are obtained. When each value exceeds the set threshold, it means that the battery is abnormal and a long-term warning signal is issued, thereby realizing early failure and high-risk behavior of the energy storage battery, and the prediction lead time is greater than or equal to 40 days. When the battery capacity decay reaches 20%, the platform system will issue a capacity decay warning; when the battery remaining cycle life reaches 80%, the platform system will issue a cycle life warning; when the battery remaining cycle life and the variance between the actual battery capacity and the remaining battery cycle life module exceed 10%, the platform system will issue a battery consistency warning. The relevant parameters of this warning are shown in Table 1:

[0085] Table 1

[0086]

[0087] As the temperature continues to rise, SEI, electrode materials, and electrolytes will decompose inside the battery. This process will release a large amount of heat and be accompanied by the generation of gas. At this time, the battery temperature becomes abnormal and the internal pressure of the battery continues to increase. When abnormalities in battery temperature and pressure are detected, a medium-term warning signal is generated to achieve a medium-term fault warning time of greater than or equal to 10 days. Specifically, when the internal pressure of the battery reaches 2.0 bar, the system platform will issue a warning that the internal pressure of the battery is too high; when the internal temperature of the battery reaches 50°C, the system platform will issue a warning that the internal temperature of the battery is too high. The relevant parameters of this warning are shown in Table 2:

[0088] Table 2

[0089]

[0090] When the safety valve is opened, a large amount of gas inside the battery will overflow, and the pressure signal outside the battery will also change dramatically. At this time, the safety warning model receives real-time gas concentration signals, battery temperature signals, battery voltage signals and battery external pressure signals, and compares each parameter with its own safety threshold. When it exceeds the safety threshold, a short-term warning signal is issued, and the short-term safety warning time is greater than or equal to 2 hours. Specifically, when the external pressure of the battery reaches 5.0 bar, the system platform will issue a warning that the external pressure of the battery is too high; when the internal temperature of the battery reaches 50°C, the system platform will issue a warning that the internal temperature of the battery is too high; when the internal voltage of the battery exceeds 4.5V, the system platform will issue a warning that the battery is short-circuited; when the concentration of oxygen or hydrogen inside the battery exceeds 0.5%, the system platform will issue a warning that the gas concentration inside the battery is too high. The relevant parameters of this warning are shown in Table 3:

[0091] Table 3

[0092]

[0093]

[0094] In an optional implementation, the acquired operating data can also be used to train a time series data prediction model to predict future data for further early warning. Figure 5 As shown, the process specifically includes data collection and access, data cleaning, feature engineering (including feature extraction, feature selection, and feature conversion), data partitioning (such as dividing into training and test sets), model selection (such as the ARIMA model), model training, model evaluation, model testing, and model deployment (such as deploying the model in a big data-based energy storage station battery safety early warning system). The deployed model can then predict future operating data based on current operating data and issue early warnings based on the predicted future data.

[0095] This embodiment also provides a big data-based energy storage station battery safety warning device, which is used to implement the above-mentioned embodiments and preferred implementations. Details that have already been described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0096] This embodiment provides a battery safety early warning device for energy storage stations based on big data, such as Figure 6 Shown, including:

[0097] Data acquisition module 61, used to obtain operating data of the energy storage station battery, the operating data including temperature signals, stress signals, electrical signals and gas concentration signals;

[0098] The long-term warning module 62 is used to determine whether to generate a long-term warning signal according to whether the electrical signal meets a first preset condition;

[0099] A medium-time warning module 63 is configured to determine whether to generate a medium-time warning signal based on whether the temperature signal and the stress signal meet a second preset condition;

[0100] The short-time warning module 64 is configured to determine whether to generate a short-time warning signal based on whether the stress signal, the temperature signal, the electrical signal, and the gas concentration signal satisfy a third preset condition.

[0101] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.

[0102] The embodiment of the present invention also provides a computer device having the above Figure 6 The big data-based energy storage station battery safety early warning device shown.

[0103] See also Figure 7 , Figure 7 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0104] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0105] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0106] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created based on the use of a computer device for displaying a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0107] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0108] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0109] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0110] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0111] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A battery safety early warning method for energy storage stations based on big data, characterized in that: The method comprises: Acquiring operating data of the energy storage station battery, wherein the operating data includes temperature signals, stress signals, electrical signals, and gas concentration signals; determining whether to generate a long-term warning signal based on whether the electrical signal meets a first preset condition; determining whether to generate a timely warning signal based on whether the temperature signal and the stress signal meet a second preset condition; Whether to generate a short-time warning signal is determined according to whether the stress signal, the temperature signal, the electrical signal, and the gas concentration signal meet a third preset condition.

2. The method according to claim 1, characterized in that The electrical signal includes current, voltage, and electrochemical impedance spectroscopy, and determining whether to generate a long-term warning signal based on whether the electrical signal meets a first preset condition includes: Calculating the actual capacity of the battery, the remaining cycle life of the battery, and the variance between the actual capacity of the battery and the remaining cycle life of the battery according to the electrical signal; When the battery capacity decay determined based on the actual battery capacity is greater than a first threshold, generating a capacity decay warning; When the remaining cycle life of the battery is less than a second threshold, generating a cycle life warning; When the variance between the actual battery capacity and the remaining cycle life module of the battery is greater than a third threshold, a battery consistency warning is generated. The capacity attenuation warning, cycle life warning and battery consistency warning constitute a long-term warning signal.

3. The method according to claim 1, characterized in that The temperature signal includes the internal temperature of the battery, the stress signal includes the internal pressure of the battery, and determining whether to generate a timely warning signal based on whether the temperature signal and the stress signal meet a second preset condition includes: When the internal temperature of the battery is greater than a fourth threshold, generating a battery internal temperature over-high warning; When the battery internal pressure is greater than a fifth threshold, a battery internal pressure too high warning is generated, and the battery internal temperature too high warning and the battery internal pressure too high warning constitute a timely warning signal.

4. The method according to claim 1, wherein The temperature signal includes the internal temperature of the battery, the stress signal includes the external pressure of the battery, and the electrical signal includes the internal voltage of the battery. Determining whether to generate a short-time warning signal based on whether the stress signal, the temperature signal, the electrical signal, and the gas concentration signal meet a third preset condition includes: When the internal temperature of the battery is greater than a fourth threshold, generating a battery internal temperature over-high warning; When the battery external pressure is greater than a sixth threshold, generating a battery external pressure excessively high warning; When the battery internal voltage is greater than a seventh threshold, generating a battery internal voltage over-high warning; When the gas concentration signal is greater than the eighth threshold, a battery internal gas concentration warning is generated. The battery internal temperature too high warning, the battery external pressure too high warning, the battery internal voltage too high warning and the battery internal gas concentration warning constitute a short-term warning signal.

5. The method according to claim 1, wherein The method further comprises: Performing feature extraction, feature selection, and feature conversion on the operating data to obtain processed features; Use the processed features to train the time series data prediction model; Use the trained time series data prediction model to train the battery's future operating data; Provide safety warnings based on future battery operating data.

6. The method according to claim 1, characterized in that Obtain battery operating data, including: Acquire battery operation data during battery operation; The acquired operating data at different times are saved in the battery state evolution database.

7. A battery safety early warning system for energy storage stations based on big data, characterized in that: The system comprises: The data transmission layer is used to obtain the operating data of the energy storage station battery, and the operating data includes temperature signals, stress signals, electrical signals and gas concentration signals; A data storage layer, configured to store the operating data based on a battery state evolution database; The data analysis layer is configured to determine whether to generate a long-term warning signal based on whether the electrical signal satisfies a first preset condition; determine whether to generate a medium-term warning signal based on whether the temperature signal and the stress signal satisfy a second preset condition; and determine whether to generate a short-term warning signal based on whether the stress signal, the temperature signal, the electrical signal, and the gas concentration signal satisfy a third preset condition; The application layer is used to provide graded warning services based on interactive technology.

8. A battery safety early warning device for energy storage stations based on big data, characterized in that: The device comprises: A data acquisition module is used to acquire operating data of the energy storage station battery, wherein the operating data includes temperature signals, stress signals, electrical signals and gas concentration signals; a long-term warning module, configured to determine whether to generate a long-term warning signal based on whether the electrical signal satisfies a first preset condition; a mid-time warning module, configured to determine whether to generate a mid-time warning signal based on whether the temperature signal and the stress signal meet a second preset condition; The short-time warning module is used to determine whether to generate a short-time warning signal according to whether the stress signal, temperature signal, electrical signal and gas concentration signal meet a third preset condition.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the big data-based energy storage station battery safety early warning method according to any one of claims 1 to 6 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the energy storage station battery safety early warning method based on big data according to any one of claims 1 to 6.

Images