Remote monitoring and management platform and method for energy storage device based on Internet of Things

Abstract

The present invention discloses a remote monitoring and management platform and method for energy storage devices based on the Internet of Things, and relates to the field of thermal runaway management technology. The method includes: obtaining the initial thermal runaway influence coefficient of the target energy storage device; performing dynamic operation monitoring to obtain a target operation characteristic parameter set; obtaining a predicted operation characteristic parameter set according to a predetermined time, and combining the target historical heat dissipation record to obtain a predicted thermal runaway influence coefficient; judging whether the target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold; if not, activating a remote control plan to manage the target energy storage device. The present invention solves the technical problems in the prior art that the traditional monitoring and management of energy storage devices has hysteresis and the reliability of risk control is low, and achieves the technical effect of reducing the risk of thermal runaway of energy storage devices and improving the reliability of risk control through thermal runaway risk prediction and remote control.

Description

Technical Field

[0001] This invention relates to the field of thermal runaway management technology, and more specifically to a remote monitoring and management platform and method for energy storage devices based on the Internet of Things. Background Technology

[0002] With the rapid development of the new energy and renewable energy industry, energy storage devices, as surplus electricity storage facilities, are widely used in smart factories, digital workshops, industrial and commercial parks, and other scenarios. However, the batteries and equipment in energy storage devices have high energy density and are flammable. In the event of a malfunction or fire, serious casualties and property damage may occur. Therefore, monitoring and management of energy storage devices are necessary to ensure their safe operation. However, existing technologies mostly rely on threshold monitoring for risk management of energy storage devices, which has a certain lag, resulting in low safety and reliability of supervision. Summary of the Invention

[0003] This application provides an IoT-based remote monitoring and management platform and method for energy storage devices, which addresses the technical problems of lagging monitoring and management and low reliability of risk control in existing energy storage device monitoring and management technologies.

[0004] The first aspect of this application provides a remote monitoring and management method for energy storage devices based on the Internet of Things (IoT). The method includes: acquiring a target energy storage device, wherein the target energy storage device is an energy storage device that meets predetermined constraints; obtaining an initial thermal runaway influence coefficient of the target energy storage device under a target remaining lifetime by combining historical remote monitoring data of energy storage devices; reading predetermined operating characteristics and dynamically monitoring the target energy storage device based on the predetermined operating characteristics to obtain a target operating characteristic parameter set; reading a predetermined time and obtaining a predicted operating characteristic parameter set of the energy storage device at the predetermined time by combining the target operating characteristic parameter set; acquiring a target historical heat dissipation record, wherein the target historical heat dissipation record refers to the operating record of the target radiator during the historical operation of the target energy storage device; inputting the predicted operating characteristic parameter set and the target historical heat dissipation record into a thermal runaway influence coefficient prediction model to obtain a predicted thermal runaway influence coefficient; determining whether the target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold; if not, activating a remote control plan and managing the target energy storage device according to the remote control plan.

[0005] A second aspect of this application provides an IoT-based remote monitoring and management platform for energy storage devices. The platform includes: a target energy storage device acquisition module, used to acquire target energy storage devices that meet predetermined constraints; an initial thermal runaway impact analysis module, used to obtain the initial thermal runaway impact coefficient of the target energy storage device under the target remaining lifetime by combining historical remote monitoring data of energy storage devices; a dynamic operation monitoring module, used to read predetermined operation characteristics and perform dynamic operation monitoring of the target energy storage device based on the predetermined operation characteristics to obtain a target operation characteristic parameter set; and an operation characteristic parameter prediction module, used to read a predetermined time and combine the target operation characteristic parameter set to obtain a prediction of the energy storage device at that predetermined time. The system includes: a set of operating characteristic parameters; a target historical heat dissipation record acquisition module, which acquires the target historical heat dissipation record, referring to the operating record of the target radiator during the historical operation of the target energy storage device; a thermal runaway influence coefficient prediction module, which inputs the predicted operating characteristic parameter set and the target historical heat dissipation record into the thermal runaway influence coefficient prediction model to obtain the predicted thermal runaway influence coefficient; a target coefficient determination module, which determines whether the target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold; and an energy storage device management module, which activates a remote control plan and manages the target energy storage device according to the remote control plan if the target coefficient is not within the predetermined coefficient threshold.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] This application provides an IoT-based remote monitoring and management platform for energy storage devices, relating to the field of thermal runaway management technology. It acquires a set of target operating characteristic parameters and makes predictions based on predetermined times to obtain a predicted set of operating characteristic parameters. By analyzing the target's historical heat dissipation records, a predicted thermal runaway impact coefficient is obtained. The platform then determines whether the target coefficient obtained by multiplying the initial thermal runaway impact coefficient by the predicted thermal runaway impact coefficient is within a predetermined threshold. If not, a remote control plan is activated to manage the target energy storage device. This solves the technical problems of lag and low reliability of risk control in traditional energy storage device monitoring and management. It achieves the technical effect of reducing the risk of thermal runaway in energy storage devices and improving the reliability of risk control through thermal runaway risk prediction and remote control. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 A schematic diagram of the process for a remote monitoring and management method for an energy storage device based on the Internet of Things, provided in an embodiment of this application;

[0010] Figure 2 A flowchart illustrating the prediction of the set of operating characteristic parameters in the IoT-based remote monitoring and management method for energy storage devices provided in this application embodiment;

[0011] Figure 3 A schematic diagram of the process for obtaining the predicted thermal runaway influence coefficient in the IoT-based remote monitoring and management method for energy storage devices provided in this application embodiment;

[0012] Figure 4 A schematic diagram of the structure of the IoT-based remote monitoring and management platform for energy storage devices provided in this application embodiment.

[0013] Explanation of reference numerals in the attached figures: Target energy storage device acquisition module 11, Initial thermal runaway impact analysis module 12, Dynamic operation monitoring module 13, Operation characteristic parameter prediction module 14, Target historical heat dissipation record acquisition module 15, Thermal runaway impact coefficient prediction module 16, Target coefficient determination module 17, Energy storage device management module 18. Detailed Implementation

[0014] This application provides a remote monitoring and management method for energy storage devices based on the Internet of Things, which addresses the technical problems of lagging monitoring and management and low reliability of risk control in existing energy storage device monitoring and management technologies.

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0016] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0017] Example 1

[0018] like Figure 1 As shown, this application provides a method for remote monitoring and management of energy storage devices based on the Internet of Things, the method comprising:

[0019] P10: Obtain the target energy storage device, wherein the target energy storage device is an energy storage device that meets predetermined conditions and constraints;

[0020] The predetermined condition constraint means that the energy storage device has no mechanical damage or manufacturing defects, and is still within its predetermined lifespan.

[0021] Optionally, target energy storage devices can be selected based on predetermined constraints, wherein the predetermined constraints mean that the selected energy storage device must be free from mechanical damage and manufacturing defects, and must still be within its predetermined lifespan.

[0022] Specifically, firstly, the target energy storage device must be free from mechanical damage, such as cracked casing, loose connections, or displaced internal components. These issues could affect the normal operation of the energy storage device and even lead to safety accidents. In particular, short circuits are unacceptable, as they can easily cause thermal runaway, posing a serious risk to energy storage. Remote monitoring and management cannot address this risk; therefore, it is necessary to check relevant records or conduct on-site inspections to confirm the presence of mechanical damage to the energy storage device.

[0023] Secondly, the target energy storage device must be free of manufacturing defects. Manufacturing defects arise during the production process, such as uneven material distribution, process problems, or design errors, which can lead to unstable performance or premature failure of the energy storage device. Therefore, it is necessary to ensure that the target energy storage device is free of manufacturing defects by reviewing production records and quality inspection reports.

[0024] Finally, the target energy storage device must still be within its predetermined lifespan. The predetermined lifespan refers to the minimum service life of the energy storage device as assessed at the time of manufacture, and is typically related to factors such as its design, materials, and operating environment. Whether it is still within the predetermined lifespan can be determined based on information such as the energy storage device's manufacturing date and usage duration. Energy storage devices that have exceeded their lifespan are not selected as monitoring and management targets because their performance may have degraded and safety risks may have increased.

[0025] By using the predetermined constraints for screening, it is possible to ensure that the selected target energy storage device has high safety and reliability, providing a good foundation for subsequent remote monitoring and management.

[0026] P20: The initial thermal runaway influence coefficient of the target energy storage device under the target remaining lifetime is obtained by combining historical remote monitoring data of energy storage devices;

[0027] Furthermore, step P20 in this embodiment of the application also includes:

[0028] P21: Extract the first historical data from the remote monitoring data of the historical energy storage device. The first historical data refers to the data on whether the first energy storage device is thermally runaway under the target remaining lifespan.

[0029] P22: Calculate the historical thermal runaway ratio based on the first historical data, and use the historical thermal runaway ratio as the initial thermal runaway influence coefficient.

[0030] It should be understood that data collection from the historical energy storage device remote monitoring database includes collecting the performance, environmental parameters, charge and discharge records, and thermal runaway event records of the energy storage devices at different remaining life stages, thus obtaining historical energy storage device remote monitoring data.

[0031] Furthermore, from the remote monitoring data of the historical energy storage devices, thermal runaway data related to the first energy storage device under the target remaining lifespan is selected as the first historical data. The first energy storage device is a sample energy storage device with the same model, specifications, usage environment, and operating conditions as the target energy storage device. Therefore, the first historical data includes thermal runaway records of the target energy storage device under a specific remaining lifespan, i.e., records of whether a thermal runaway event has occurred.

[0032] Furthermore, based on the first historical data, the historical thermal runaway ratio is calculated. For example, firstly, the number of energy storage devices that experienced thermal runaway and the total number of energy storage devices are counted from the first historical data, and the ratio of the number of energy storage devices that experienced thermal runaway to the total number of energy storage devices is calculated to obtain the historical thermal runaway ratio. This historical thermal runaway ratio is used as the initial thermal runaway influence coefficient, which reflects the probability of the target energy storage device experiencing thermal runaway under similar conditions within its target remaining lifetime.

[0033] P30: Read the predetermined operating characteristics and perform dynamic operation monitoring on the target energy storage device based on the predetermined operating characteristics to obtain the target operating characteristic parameter set;

[0034] The predetermined operating characteristics include charging current, charging voltage, charging duration, charging and discharging frequency, internal pressure, internal resistance, ambient temperature, and ambient humidity.

[0035] Optionally, predetermined operating characteristics are read. These predetermined operating characteristics are key parameters pre-set for monitoring the operating status of the energy storage device. In this step, these characteristics include charging current, charging voltage, charging duration, charge / discharge frequency, internal pressure, internal resistance, ambient temperature, and ambient humidity. The selection of these predetermined operating characteristics is based on their impact on the performance of the energy storage device and the risk of thermal runaway. For example, charging current and voltage directly affect the battery's charging speed and efficiency, charge / discharge frequency reflects the battery's usage frequency, internal pressure and internal resistance reflect the battery's internal health status, and ambient temperature and humidity affect the battery's operating environment and heat dissipation conditions.

[0036] Furthermore, the target energy storage device is dynamically monitored based on the predetermined operating characteristics. Dynamic operation monitoring involves collecting various operating characteristic parameters of the target energy storage device in real time or periodically during operation, including real-time charging current, charging voltage, charging duration, charging and discharging frequency, internal pressure, internal resistance, ambient temperature, and ambient humidity, thereby forming a target operating characteristic parameter set to provide a basis for subsequent analysis and evaluation.

[0037] P40: Read the predetermined time and combine it with the target operating characteristic parameter set to obtain the predicted operating characteristic parameter set of the energy storage device at the predetermined time;

[0038] Furthermore, such as Figure 2 As shown, step P40 in this embodiment further includes:

[0039] P41: Extract the first target runtime sequence from the target runtime feature parameter set;

[0040] P42: Generate the first linear curve based on the first scatter plot of the first target runtime sequence;

[0041] P43: Input the predetermined time into the first fitting polynomial of the first spline curve to obtain the first target prediction parameters;

[0042] P44: Construct the prediction operation feature parameter set based on the first target prediction parameters.

[0043] It should be understood that reading the predetermined time, which is a future point in time, is used to predict the operating state of the energy storage device at that time. Combined with the previously collected target operating characteristic parameter set, the operation prediction at the predetermined time is performed to obtain the predicted operating characteristic parameter set.

[0044] Specifically, time-series data related to any specific operational characteristic, such as charging current time series and charging voltage time series, are extracted from the target operational characteristic parameter set and used as the first target operational sequence. The first target operational sequence reflects the change of the operational characteristic over time. Furthermore, a first scatter plot is plotted based on the first target operational sequence data to visually display the distribution of data points. Then, using spline curve fitting technology, a smooth first spline curve is generated by connecting the scatter points in the first scatter plot. This first spline curve can effectively reflect the overall trend and local changes of the data.

[0045] Furthermore, after generating the first spline curve, the mathematical expression of the first spline curve, namely the first fitting polynomial, is obtained by fitting. The predetermined time is then substituted into the first fitting polynomial as the input value to calculate the prediction parameter value corresponding to that time, namely the prediction value of the target energy storage device for a specific operating characteristic at the predetermined time.

[0046] Furthermore, based on the acquisition method of the first target prediction parameter, the predicted values ​​of different operating characteristics are obtained and combined to form a complete set of predicted operating characteristic parameters. The set of predicted operating characteristic parameters contains the predicted values ​​of the target energy storage device for each operating characteristic at a predetermined time, which can be used for subsequent performance evaluation, risk prediction and other analysis work.

[0047] Furthermore, step P42 in this embodiment of the application also includes:

[0048] P42-1: Randomly extract the first scatter sample group from the first scatter plot;

[0049] P42-2: The first curve generated based on the first scatter sample group is tested according to the first scatter test group to obtain the first inside-outside point ratio. The first scatter test group refers to the combination of scatter points after removing the first scatter sample group from the first scatter plot.

[0050] P42-3: When the ratio of the first inner and outer points reaches a predetermined ratio threshold, the first curve at that time is taken as the first spline curve.

[0051] In one possible embodiment of this application, a portion of scattered points are randomly extracted from the first scatter plot as a first scatter sample group, and the remaining scattered points after removing the first scatter sample group from the first scatter plot are used as a first scatter test group. Further, a first curve is generated based on the first scatter sample group, and the first scatter test group is used to test the first curve to determine whether the first curve can fit the overall data points well. This can be determined by calculating the first inside-outside point ratio, which is the ratio of the number of points inside the first curve to the number of points outside the first curve. This ratio reflects the degree of fit of the curve to the data; the larger the ratio, the better the fit.

[0052] Furthermore, it is determined whether the ratio of the first inside-outside points meets a predetermined ratio threshold. This predetermined ratio threshold can be set by professionals according to actual needs. When the ratio of the first inside-outside points reaches the predetermined ratio threshold, it indicates that the first curve fits the data well and can be used as the final first sample curve. If the ratio of the first inside-outside points does not reach the predetermined ratio threshold, the number of sample points needs to be increased for refitting to improve the accuracy of the fit.

[0053] Furthermore, step P42-2 in the embodiments of this application also includes:

[0054] P42-21: Extract the first scatter point from the first scatter test group;

[0055] P42-22: Obtain the first distance, which refers to the distance from the first scatter point to the first curve;

[0056] P42-23: Determine whether the first distance is within a predetermined distance threshold;

[0057] P42-24: If it is in the set, add the first scatter point to the inner point set; if it is not in the set, add the first scatter point to the outer point set.

[0058] P42-25: The first ratio of the inner and outer points is calculated based on the inner point set and the outer point set.

[0059] Specifically, randomly extract any scatter point from the first scatter point test group as the first scatter point, and calculate the vertical distance from the first scatter point to the first curve as the first distance. Further, determine whether the first distance is within a predetermined distance threshold range. The predetermined distance threshold can be used to distinguish the categories of scatter points and can be set by professionals according to actual needs. If the first distance is within the predetermined distance threshold range, it indicates that the first scatter point is close to the first curve, and then add the first scatter point to the inlier set; otherwise, add the first scatter point to the outlier set. By analogy, classify all the scatter points in the first scatter point test group. Finally, calculate the ratio of inliers to outliers based on the number of scatter points in the inlier set and the outlier set to obtain the first inlier-outlier ratio for evaluating the curve fitting degree.

[0060] P50: Obtain the target historical heat dissipation record, where the target historical heat dissipation record refers to the operation record of the target radiator during the historical operation of the target energy storage device;

[0061] It should be understood that by accessing the database, collect the target historical heat dissipation record, where the target historical heat dissipation record refers to the operation record of the target radiator during the historical operation. Among them, the target radiator refers to the heat dissipation device supporting the target energy storage device, which is used to dissipate the heat generated by the energy storage device into the surrounding environment to maintain the normal working temperature of the energy storage device. And the target historical heat dissipation record includes the start time, stop time, heat dissipation efficiency, heat dissipation amount, temperature change trend, etc. of the target radiator, which can reflect the performance of the target radiator under different working conditions.

[0062] P60: Input the predicted operation characteristic parameter set and the target historical heat dissipation record into the thermal runaway influence coefficient prediction model to obtain the predicted thermal runaway influence coefficient;

[0063] Further, as Figure 3 shown, step P60 of the embodiment of the present application further includes:

[0064] P61: Extract the target historical heat dissipation efficiency time series from the target historical heat dissipation record;

[0065] P62: Obtain the predicted heat dissipation efficiency at the predetermined moment according to the target historical heat dissipation efficiency time series;

[0066] P63: Analyze the predicted operation characteristic parameter set and the predicted heat dissipation efficiency through the thermal runaway influence coefficient prediction model to obtain the predicted thermal runaway influence coefficient;

[0067] P64: Among them, the thermal runaway influence coefficient prediction model is an intelligent model trained based on the neural network principle.

[0068] Optionally, the predicted operational characteristic parameter set and the target historical heat dissipation record are input into the thermal runaway influence coefficient prediction model to predict the thermal runaway influence and obtain the predicted thermal runaway influence coefficient. Specifically, the target historical heat dissipation efficiency time series is extracted from the target historical heat dissipation record, that is, the time series number of the heat dissipation efficiency of the target radiator. Further, based on the target historical heat dissipation efficiency time series, heat dissipation efficiency change prediction is performed through time series analysis to obtain the predicted heat dissipation efficiency at a predetermined time.

[0069] Furthermore, the thermal runaway impact coefficient prediction model is trained based on neural network principles. First, a large amount of data related to thermal runaway is collected, including equipment operating characteristic parameters and heat dissipation records, as the training and validation sets for the model. Based on neural network principles, a thermal runaway impact coefficient prediction model is constructed. Then, the training set is used to perform supervised training on the thermal runaway impact coefficient prediction model. The network architecture of the model is adjusted based on the error between the output data and the actual thermal runaway impact coefficient. The model is then validated using the validation set until the thermal runaway impact coefficient prediction model converges and meets the preset accuracy requirements, thus completing the training of the thermal runaway impact coefficient prediction model.

[0070] Furthermore, the predicted operating characteristic parameter set and the predicted heat dissipation efficiency are input into the thermal runaway impact coefficient prediction model to predict the runaway impact and obtain the predicted thermal runaway impact coefficient. The predicted thermal runaway impact coefficient can be used to evaluate the equipment safety level at a predetermined time.

[0071] P70: Determine whether the target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold;

[0072] P80: If not, activate the remote control plan and manage the target energy storage device according to the remote control plan.

[0073] It should be understood that the initial thermal runaway impact coefficient is multiplied by the predicted thermal runaway impact coefficient to obtain a target coefficient. The target coefficient represents the overall assessment of the current thermal runaway risk. It is then determined whether the target coefficient is at a predetermined coefficient threshold. The predetermined coefficient threshold can usually be set based on the safety protection level and historical data to determine whether the thermal runaway risk has reached a level that requires intervention.

[0074] Furthermore, if the target coefficient is not within the predetermined threshold range, it means that the thermal runaway risk of the target energy storage device may be high, requiring immediate intervention. Therefore, a remote control plan is activated. This plan includes a series of predefined emergency response measures and plans, which can be used to remotely manage and control the target energy storage device when the thermal runaway risk is high. The target energy storage device is managed according to the remote control plan, for example, by reducing the charging and discharging rate of the energy storage device, adjusting the operating environment temperature, activating the cooling system, and cutting off the power supply, to reduce the thermal runaway risk and protect the safety of equipment and personnel.

[0075] In summary, the embodiments of this application have at least the following technical effects:

[0076] This application obtains a set of target operating characteristic parameters and makes predictions based on predetermined times to obtain a set of predicted operating characteristic parameters. It then analyzes the target's historical heat dissipation records to obtain a predicted thermal runaway influence coefficient. Finally, it determines whether the target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold. If not, it activates a remote control plan to manage the target energy storage device.

[0077] The technology has achieved the goal of reducing the risk of thermal runaway in energy storage devices and improving the reliability of risk management through thermal runaway risk prediction and remote control.

[0078] Example 2

[0079] Based on the same inventive concept as the IoT-based remote monitoring and management method for energy storage devices in the foregoing embodiments, such as Figure 4 As shown, this application provides a remote monitoring and management platform for energy storage devices based on the Internet of Things (IoT). The method and platform embodiments in this application are based on the same inventive concept. The platform includes:

[0080] The target energy storage device acquisition module 11 is used to acquire a target energy storage device, wherein the target energy storage device is an energy storage device that meets predetermined conditions and constraints.

[0081] Initial thermal runaway impact analysis module 12, which is used to combine historical remote monitoring data of energy storage devices to obtain the initial thermal runaway impact coefficient of the target energy storage device under the target remaining lifetime;

[0082] The dynamic operation monitoring module 13 is used to read predetermined operation characteristics and perform dynamic operation monitoring on the target energy storage device based on the predetermined operation characteristics to obtain a target operation characteristic parameter set;

[0083] The operating characteristic parameter prediction module 14 is used to read a predetermined time and combine it with the target operating characteristic parameter set to obtain the predicted operating characteristic parameter set of the energy storage device at the predetermined time.

[0084] The target historical heat dissipation record acquisition module 15 is used to acquire the target historical heat dissipation record, which refers to the operation record of the target radiator during the historical operation of the target energy storage device.

[0085] Thermal runaway influence coefficient prediction module 16, the thermal runaway influence coefficient prediction module 16 is used to input the predicted operating characteristic parameter set and the target historical heat dissipation record into the thermal runaway influence coefficient prediction model to obtain the predicted thermal runaway influence coefficient;

[0086] The target coefficient determination module 17 is used to determine whether the target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold.

[0087] The energy storage device management module 18 is used to activate the remote control plan if the target coefficient is not at a predetermined coefficient threshold, and to manage the target energy storage device according to the remote control plan.

[0088] Furthermore, the initial thermal runaway impact analysis module 12 is also used to perform the following steps:

[0089] Extract the first historical data from the remote monitoring data of the historical energy storage device. The first historical data refers to the data on whether the first energy storage device has thermal runaway under the target remaining lifespan.

[0090] The historical thermal runaway ratio is calculated based on the first historical data, and the historical thermal runaway ratio is used as the initial thermal runaway influence coefficient.

[0091] Furthermore, the running feature parameter prediction module 14 is also used to perform the following steps:

[0092] Extract the first target runtime sequence from the target runtime feature parameter set;

[0093] The first curve is generated based on the first scatter plot of the first target runtime sequence.

[0094] The predetermined time is input into the first fitting polynomial of the first spline curve to obtain the first target prediction parameters;

[0095] The prediction operation feature parameter set is constructed based on the first target prediction parameters.

[0096] Furthermore, the running feature parameter prediction module 14 is also used to perform the following steps:

[0097] Randomly extract the first scatter sample group from the first scatter plot;

[0098] The first curve generated based on the first scatter sample group is tested according to the first scatter test group to obtain the first inside-outside point ratio. The first scatter test group refers to the combination of scatter points after removing the first scatter sample group from the first scatter plot.

[0099] When the ratio of the first inner and outer points reaches a predetermined ratio threshold, the first curve at that time is taken as the first spline curve.

[0100] Furthermore, the running feature parameter prediction module 14 is also used to perform the following steps:

[0101] Extract the first scatter point from the first scatter test group;

[0102] Obtain the first distance, which refers to the distance from the first scatter point to the first curve;

[0103] Determine whether the first distance is within a predetermined distance threshold;

[0104] If it is in the set, add the first scatter point to the inner point set; if it is not in the set, add the first scatter point to the outer point set.

[0105] The first ratio of interior to exterior points is calculated based on the interior point set and the exterior point set.

[0106] Furthermore, the thermal runaway influence coefficient prediction module 16 is also used to perform the following steps:

[0107] Extract the target historical heat dissipation efficiency time series from the target historical heat dissipation record;

[0108] The predicted heat dissipation efficiency at the predetermined time is obtained based on the target historical heat dissipation efficiency time series.

[0109] The predicted thermal runaway influence coefficient is obtained by analyzing the predicted operating characteristic parameter set and the predicted heat dissipation efficiency through the predicted thermal runaway influence coefficient prediction model.

[0110] The thermal runaway influence coefficient prediction model is an intelligent model trained based on neural network principles.

[0111] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0112] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0113] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A remote monitoring and management method for energy storage devices based on the Internet of Things, characterized in that: The method comprises: Acquire a target energy storage device, where the target energy storage device is an energy storage device that meets a predetermined condition constraint; Combining historical energy storage device remote monitoring data to obtain an initial thermal runaway influence coefficient of the target energy storage device under a target remaining life; Reading a predetermined operating characteristic, and dynamically monitoring the target energy storage device based on the predetermined operating characteristic to obtain a target operating characteristic parameter set; Reading the predetermined time, and obtaining a predicted operating characteristic parameter set of the energy storage device at the predetermined time in combination with the target operating characteristic parameter set; Acquire a target historical heat dissipation record, wherein the target historical heat dissipation record refers to an operation record of a target radiator during a historical operation of the target energy storage device; Inputting the predicted operation characteristic parameter set and the target historical heat dissipation record into a thermal runaway influence coefficient prediction model to obtain a predicted thermal runaway influence coefficient; determining whether a target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold; If not, activating the remote control plan, and managing the target energy storage device according to the remote control plan; Wherein, obtaining the predicted operation characteristic parameter set of the energy storage device at the predetermined time in combination with the target operation characteristic parameter set includes: Extracting the first target operation timing in the target operation characteristic parameter set; generating a first spline curve according to a first scatter plot of the first target running time sequence; Inputting the predetermined time into a first fitting polynomial of the first spline curve to obtain a first target prediction parameter; The prediction operation feature parameter set is formed based on the first target prediction parameter.

2. The remote monitoring and management method for energy storage device according to claim 1, characterized in that: The predetermined condition constraint means that the energy storage device has no mechanical damage, no manufacturing defects, and is still within the predetermined life span.

3. The remote monitoring and management method for energy storage device according to claim 1, characterized in that: The initial thermal runaway influence coefficient of the target energy storage device under the target remaining life is obtained by combining the historical energy storage device remote monitoring data, including: Extracting first historical data from the historical energy storage device remote monitoring data, wherein the first historical data refers to data on whether the first energy storage device has thermal runaway at the target remaining life, and the data on whether the thermal runaway has occurred at the target remaining life is a record of whether a thermal runaway event has occurred at the first energy storage device; A historical thermal runaway ratio is calculated based on the first historical data, and the historical thermal runaway ratio is used as the initial thermal runaway influence coefficient.

4. The remote monitoring and management method for energy storage device according to claim 1, characterized in that: The predetermined operating characteristics include charging current, charging voltage, charging time, charging and discharging frequency, internal pressure, internal resistance, ambient temperature and ambient humidity.

5. The remote monitoring and management method for energy storage device according to claim 1, characterized in that: Generating a first spline curve according to a first scatter plot of the first target running time sequence includes: Randomly extract a first scatter point sample group from the first scatter point graph; Testing a first curve generated based on the first scatter point sample group according to a first scatter point test group to obtain a first inner and outer point ratio, wherein the first scatter point test group refers to a scatter point combination after the first scatter point sample group in the first scatter point graph is eliminated; When the first inner and outer point ratio reaches a predetermined ratio threshold, the first curve at that time is used as the first spline curve.

6. The method for remote monitoring and management of energy storage device according to claim 5, characterized in that: Testing a first curve generated based on the first scattered point sample group according to the first scattered point test group to obtain a first inner and outer point ratio, including: Extracting a first scattered point in the first scattered point inspection group; Acquire a first distance, where the first distance refers to a distance from the first scattered point to the first curve; determining whether the first distance is within a predetermined distance threshold; If it is, add the first scattered point to the inner point set; if it is not, add the first scattered point to the outer point set; The first inner and outer point ratio is calculated based on the inner point set and the outer point set.

7. The remote monitoring and management method for energy storage device according to claim 1, characterized in that: Inputting the predicted operation characteristic parameter set and the target historical heat dissipation record into a thermal runaway influence coefficient prediction model to obtain a predicted thermal runaway influence coefficient, including: Extracting a target historical heat dissipation efficiency time series from the target historical heat dissipation record; Acquire the predicted heat dissipation efficiency at the predetermined time according to the target historical heat dissipation efficiency time series; The predicted operation characteristic parameter set and the predicted heat dissipation efficiency are analyzed by the thermal runaway influence coefficient prediction model to obtain the predicted thermal runaway influence coefficient; Among them, the thermal runaway influence coefficient prediction model is an intelligent model trained based on the neural network principle.

8. The remote monitoring and management platform for energy storage devices based on the Internet of Things is characterized by: The platform includes: A target energy storage device acquisition module, the target energy storage device acquisition module is used to acquire a target energy storage device, the target energy storage device is an energy storage device that meets a predetermined condition constraint; An initial thermal runaway impact analysis module, the initial thermal runaway impact analysis module is used to obtain an initial thermal runaway impact coefficient of the target energy storage device under a target remaining life in combination with historical energy storage device remote monitoring data; A dynamic operation monitoring module, the dynamic operation monitoring module is used to read a predetermined operation characteristic, and perform dynamic operation monitoring on the target energy storage device based on the predetermined operation characteristic to obtain a target operation characteristic parameter set; An operation characteristic parameter prediction module, the operation characteristic parameter prediction module is used to read the predetermined time, and obtain a predicted operation characteristic parameter set of the energy storage device at the predetermined time in combination with the target operation characteristic parameter set; A target historical heat dissipation record acquisition module, the target historical heat dissipation record acquisition module is used to acquire a target historical heat dissipation record, the target historical heat dissipation record refers to an operation record of a target radiator during a historical operation of the target energy storage device; A thermal runaway influence coefficient prediction module, wherein the thermal runaway influence coefficient prediction module is used to input the predicted operation characteristic parameter set and the target historical heat dissipation record into a thermal runaway influence coefficient prediction model to obtain a predicted thermal runaway influence coefficient; a target coefficient determination module, the target coefficient determination module being used to determine whether a target coefficient obtained by multiplying the initial thermal runaway influence coefficient and the predicted thermal runaway influence coefficient is within a predetermined coefficient threshold; An energy storage device management module, the energy storage device management module is used to activate the remote control plan if the target coefficient is not within the predetermined coefficient threshold, and manage the target energy storage device according to the remote control plan; Wherein, the operation characteristic parameter prediction module is also used for: Extracting the first target operation timing in the target operation characteristic parameter set; generating a first spline curve according to a first scatter plot of the first target running time sequence; Inputting the predetermined time into a first fitting polynomial of the first spline curve to obtain a first target prediction parameter; The prediction operation feature parameter set is formed based on the first target prediction parameter.

Images