An Electrochemical Energy Storage Thermal Abuse Early Warning Method Based on Reinforced Deep Learning

Abstract

The present invention discloses an early warning method for thermal abuse of electrochemical energy storage based on enhanced deep learning, which relates to the technical field of energy storage. The method includes obtaining the charge time series data, the device surface temperature time series data, and the external environment temperature time series data within the current period; using the above data as the input of the temperature prediction model to obtain the device surface predicted temperature time series data for the next period; determining the charge time series data for the next period based on the current charge data; establishing a device surface temperature curve that changes with the charge data based on the historical device surface temperature time series data and the device surface predicted temperature time series data during the current charge-discharge process, and the historical charge time series data and the charge time series data for the next period during the current charge-discharge process; determining whether there is a risk of thermal abuse based on this curve; and generating a warning message when there is a risk of thermal abuse. The method disclosed by the present invention can give an early warning before the thermal abuse occurs, avoiding unnecessary losses caused by thermal abuse.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage, and particularly relates to a method for predicting thermal abuse of electrochemical energy storage based on enhanced deep learning. Background Art

[0002] With the rapid development of renewable energy, the role of energy storage systems in power systems has become increasingly prominent. As one of the core components of energy storage systems, the safety and stability of electrochemical energy storage devices are directly related to the reliable operation of the entire system. However, during the energy storage process through electrochemical energy storage devices, various problems that may be encountered, especially thermal abuse, are one of the main factors threatening the safety of energy storage systems.

[0003] Thermal abuse is generally caused by external heat sources or excessive internal heat generation and poor heat dissipation. Thermal abuse will cause the internal temperature of electrochemical energy storage devices to rise sharply, which will in turn trigger out-of-control internal chemical reactions in the battery, generate a large amount of heat and may cause fires or explosions. Especially during the charge and discharge process, due to the heat generated by the internal reactions of electrochemical energy storage devices, it is easier to cause thermal abuse. At present, for thermal abuse during the charge and discharge process, it is mostly detected based on the surface temperature of electrochemical energy storage devices. Using such a method can generally only detect that thermal abuse has occurred in electrochemical energy storage devices after thermal abuse occurs, and cannot give early warnings before thermal abuse occurs, thus causing unnecessary losses.

[0004] Therefore, how to provide an effective solution to give early warnings before thermal abuse occurs has become an urgent problem to be solved in the prior art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for predicting thermal abuse of electrochemical energy storage based on enhanced deep learning to solve the above problems existing in the prior art.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for predicting thermal abuse of electrochemical energy storage based on enhanced deep learning, including:

[0008] Obtaining the charge-discharge sequence data, device surface temperature sequence data, and external environmental temperature sequence data of an electrochemical energy storage device during the current period;

[0009] Based on the charge-discharge state of the electrochemical energy storage device, determining a temperature prediction model corresponding to the charge-discharge state and based on enhanced deep learning, where the charge-discharge state is a charging state or a discharging state;

[0010] Using the charged time series data, the device surface temperature time series data, and the external environment temperature time series data as inputs to the temperature prediction model for calculation, the predicted device surface temperature time series data of the electrochemical energy storage device in the next time period is obtained;

[0011] Based on the current charge data of the electrochemical energy storage device, the charged time series data of the electrochemical energy storage device in the next time period is determined;

[0012] Based on the historical time series data of the device surface temperature and the predicted device surface temperature time series data of the electrochemical energy storage device during the current charge and discharge process, as well as the historical charged time series data of the electrochemical energy storage device during the current charge and discharge process and the charged time series data of the electrochemical energy storage device in the next time period, a device surface temperature curve of the electrochemical energy storage device varying with the charge data from the start of the current charge and discharge to the next time period is established;

[0013] Based on the device surface temperature curve, it is determined whether the electrochemical energy storage device has a thermal abuse risk;

[0014] When the electrochemical energy storage device has a thermal abuse risk, a warning message is generated.

[0015] Based on the above-disclosed content, the present invention obtains the charged time series data, the device surface temperature time series data, and the external environment temperature time series data of the electrochemical energy storage device during charging and discharging in the current time period; determines a temperature prediction model based on enhanced deep learning corresponding to the charge and discharge state based on the charge and discharge state of the electrochemical energy storage device; uses the charged time series data, the device surface temperature time series data, and the external environment temperature time series data as inputs to the temperature prediction model for calculation to obtain the predicted device surface temperature time series data of the electrochemical energy storage device in the next time period; determines the charged time series data of the electrochemical energy storage device in the next time period based on the current charge data of the electrochemical energy storage device; based on the historical time series data of the device surface temperature and the predicted device surface temperature time series data of the electrochemical energy storage device during the current charge and discharge process, as well as the historical charged time series data of the electrochemical energy storage device during the current charge and discharge process and the charged time series data of the electrochemical energy storage device in the next time period, establishes a device surface temperature curve of the electrochemical energy storage device varying with the charge data from the start of the current charge and discharge to the next time period; determines whether the electrochemical energy storage device has a thermal abuse risk based on the device surface temperature curve; when the electrochemical energy storage device has a thermal abuse risk, a warning message is generated. In this way, it is possible to predict whether the electrochemical energy storage device has a thermal abuse risk in the next time period and generate a warning message when there is a thermal abuse risk, so as to give an early warning before the occurrence of thermal abuse, so as to take corresponding measures in advance to prevent the occurrence of thermal abuse and avoid unnecessary losses caused by thermal abuse.

[0016] In a possible design, performing operations with the charged time-series data, the device surface temperature time-series data, and the external environmental temperature time-series data as inputs to the temperature prediction model to obtain the predicted device surface temperature time-series data of the electrochemical energy storage device for the next time period includes:

[0017] Combining the charged time-series data, the device surface temperature time-series data, and the external environmental temperature time-series data after standardization processing to obtain a vector matrix, where each row in the vector matrix corresponds to data of one dimension;

[0018] Performing operations with the vector matrix as the input to the temperature prediction model to obtain the predicted device surface temperature time-series data of the electrochemical energy storage device for the next time period.

[0019] In a possible design, determining the charged time-series data of the electrochemical energy storage device for the next time period based on the current charge data of the electrochemical energy storage device includes:

[0020] Estimating the charged time-series data of the electrochemical energy storage device for the next time period based on the current charge data of the electrochemical energy storage device and at least the most recent charge and discharge records of the electrochemical energy storage device.

[0021] In a possible design, establishing the device surface temperature curve that changes with the charge data of the electrochemical energy storage device from the start of this charge and discharge process to the next time period based on the historical device surface temperature time-series data and the predicted device surface temperature time-series data of the electrochemical energy storage device during this charge and discharge process, and the historical charged time-series data and the charged time-series data of the electrochemical energy storage device for the next time period includes:

[0022] Determining the device surface temperature time-series data of the electrochemical energy storage device from the start of this charge and discharge process to the next time period based on the historical device surface temperature time-series data and the predicted device surface temperature time-series data of the electrochemical energy storage device during this charge and discharge process;

[0023] Determining the charged time-series data of the electrochemical energy storage device from the start of this charge and discharge process to the next time period based on the historical charged time-series data and the charged time-series data of the electrochemical energy storage device for the next time period during this charge and discharge process;

[0024] Establishing the device surface temperature curve that changes with the charge data of the electrochemical energy storage device from the start of this charge and discharge process to the next time period based on the device surface temperature time-series data of the electrochemical energy storage device from the start of this charge and discharge process to the next time period and the charged time-series data of the electrochemical energy storage device from the start of this charge and discharge process to the next time period.

[0025] In a possible design, determining whether there is a thermal abuse risk for the electrochemical energy storage device based on the device surface temperature curve includes:

[0026] Comparing the device surface temperature curve with the device historical surface temperature curve of the electrochemical energy storage device or the same model energy storage device of the electrochemical energy storage device when there is no thermal abuse risk, to determine whether there is a thermal abuse risk for the electrochemical energy storage device.

[0027] In a possible design, comparing the device surface temperature curve with the device historical surface temperature curve of the electrochemical energy storage device or the same model energy storage device of the electrochemical energy storage device when there is no thermal abuse risk includes:

[0028] Comparing the device surface temperature curve with the device historical surface temperature curve of the electrochemical energy storage device or the same model energy storage device that is similar to the initial curve and has no thermal abuse risk.

[0029] In a possible design, the electrochemical energy storage device is a lithium-ion battery or a sodium-sulfur battery.

[0030] In a second aspect, the present invention provides an electrochemical energy storage thermal abuse early warning device based on enhanced deep learning, including:

[0031] An acquisition unit, configured to acquire charge-discharge time series data, device surface temperature time series data, and external environment temperature time series data of the electrochemical energy storage device during the current period;

[0032] A first determination unit, configured to determine a temperature prediction model corresponding to the charge-discharge state and based on enhanced deep learning based on the charge-discharge state of the electrochemical energy storage device, where the charge-discharge state is a charging state or a discharging state;

[0033] A calculation unit, configured to use the charge-discharge time series data, the device surface temperature time series data, and the external environment temperature time series data as inputs of the temperature prediction model for calculation, to obtain device surface predicted temperature time series data of the electrochemical energy storage device in the next period;

[0034] A second determination unit, configured to determine the charge-discharge time series data of the electrochemical energy storage device in the next period based on the current charge data of the electrochemical energy storage device;

[0035] A building unit is configured to establish a device surface temperature curve of the electrochemical energy storage device varying with the charge data from the start of the current charge-discharge process to the next time period based on the historical time-series data of the device surface temperature and the predicted time-series data of the device surface temperature during the current charge-discharge process of the electrochemical energy storage device, as well as the historical charge time-series data of the electrochemical energy storage device during the current charge-discharge process and the charge time-series data of the electrochemical energy storage device in the next time period.

[0036] A third determination unit is configured to determine whether there is a thermal abuse risk of the electrochemical energy storage device based on the device surface temperature curve.

[0037] An early warning unit is configured to generate an early warning message when there is a thermal abuse risk of the electrochemical energy storage device.

[0038] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a transceiver that are communicatively connected in sequence. The memory is configured to store a computer program, the transceiver is configured to send and receive messages, and the processor is configured to read the computer program and execute the method for warning of thermal abuse of an electrochemical energy storage based on enhanced deep learning as described in the first aspect or any possible design of the first aspect.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are run on a computer, the method for warning of thermal abuse of an electrochemical energy storage based on enhanced deep learning as described in the first aspect or any possible design of the first aspect is executed.

[0040] In a fifth aspect, the present invention provides a computer program product containing instructions. When the instructions are run on a computer, the computer is caused to execute the method for warning of thermal abuse of an electrochemical energy storage based on enhanced deep learning as described in the first aspect or any possible design of the first aspect.

[0041] Advantageous effects:

[0042] The method for warning of thermal abuse of an electrochemical energy storage based on enhanced deep learning provided by the present invention can predict whether there is a thermal abuse risk of the electrochemical energy storage device in the next time period, and generate an early warning message when there is a thermal abuse risk, so as to achieve early warning before the occurrence of thermal abuse, so as to take corresponding measures in advance to prevent the occurrence of thermal abuse, avoid unnecessary losses caused by thermal abuse, and facilitate practical application and promotion. Description of the drawings

[0043] Figure 1 It is a flowchart of the method for warning of thermal abuse of an electrochemical energy storage based on enhanced deep learning provided by an embodiment of the present application.

[0044] Figure 2Schematic block diagram of the electro-chemical energy storage thermal abuse warning device based on enhanced deep learning provided by the embodiments of the present application;

[0045] Figure 3 Schematic block diagram of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the present invention in combination with the accompanying drawings and the descriptions of the embodiments or the prior art. Obviously, the following descriptions of the structures of the accompanying drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts. It should be noted here that the descriptions of these embodiment modes are used to help understand the present invention, but do not constitute a limitation to the present invention.

[0047] In order to give an early warning before the occurrence of thermal abuse, the embodiments of the present application provide an electro-chemical energy storage thermal abuse warning method based on enhanced deep learning. The electro-chemical energy storage thermal abuse warning method based on enhanced deep learning can give an early warning before the occurrence of thermal abuse, so as to collect corresponding measures in advance to prevent the occurrence of thermal abuse and avoid unnecessary losses caused by thermal abuse.

[0048] The electro-chemical energy storage thermal abuse warning method based on enhanced deep learning provided by the embodiments of the present application can be applied to the background terminal device or server for detecting and managing electro-chemical energy storage devices. It can be understood that the execution subject does not constitute a limitation to the embodiments of the present application.

[0049] The following will detail the electro-chemical energy storage thermal abuse warning method based on enhanced deep learning provided by the embodiments of the present application.

[0050] As Figure 1 shown, it is the flowchart of the electro-chemical energy storage thermal abuse warning method based on enhanced deep learning provided by the first aspect of the embodiments of the present application. The electro-chemical energy storage thermal abuse warning method based on enhanced deep learning can but is not limited to include the following steps S101-S107.

[0051] Step S101. Obtain the charge-discharge time series data, the device surface temperature time series data, and the external environment temperature time series data of the electro-chemical energy storage device in the current period.

[0052] Among them, the electro-chemical energy storage device can but is not limited to be a lithium-ion battery, a sodium-sulfur battery, etc., which are energy storage devices that convert electrical energy into chemical energy and then convert chemical energy into electrical energy when needed.

[0053] In the embodiments of the present application, the charge-time series data of the electrochemical energy storage device during charging and discharging can be collected by a battery management system (BMS). At the same time, temperature sensors can be set on the surface and around the electrochemical energy storage device, and the device surface temperature time series data and the external environment temperature time series data of the electrochemical energy storage device during the current period can be obtained through the temperature sensors.

[0054] Among them, the charge-time series data includes a plurality of state of charge (SOC) data and the time corresponding to each state of charge data. The device surface temperature time series data includes a plurality of device surface temperature data and the time corresponding to each device surface temperature data. The external environment temperature time series data includes a plurality of external environment temperature data and the time corresponding to each external environment temperature data. This time can refer to the time difference between the start of charging and discharging and the acquisition of the corresponding data.

[0055] The charge-time series data, the device surface temperature time series data, and the external environment temperature time series data of the electrochemical energy storage device during charging and discharging. It can be the charge-time series data, the device surface temperature time series data, and the external environment temperature time series data of the chemical energy storage device during the current period during charging, or the charge-time series data, the device surface temperature time series data, and the external environment temperature time series data of the chemical energy storage device during the current period during discharging.

[0056] Step S102. Based on the charge and discharge state of the electrochemical energy storage device, a temperature prediction model corresponding to the charge and discharge state and based on enhanced deep learning is determined.

[0057] Wherein the charge and discharge state is a charging state or a discharging state.

[0058] In the embodiments of the present application, two temperature prediction models based on enhanced deep learning are pre-trained. The two temperature prediction models based on enhanced deep learning are respectively used for temperature prediction during the charging state and the discharging state of the electrochemical energy storage device. The training process of the temperature prediction model will be described later.

[0059] If the electrochemical energy storage device is in the charging state, the temperature prediction model corresponding to the charging state is selected. If the chemical energy storage device is in the discharging state, the temperature prediction model corresponding to the discharging state is selected.

[0060] Step S103. The charge-time series data, the device surface temperature time series data, and the external environment temperature time series data are used as the input of the temperature prediction model for calculation, and the device surface predicted temperature time series data of the electrochemical energy storage device in the next period is obtained.

[0061] In the embodiments of the present application, the charged time-series data, the device surface temperature time-series data, and the external environment temperature time-series data can be standardized and then combined to obtain a vector matrix, where each row in the vector matrix corresponds to data of one dimension. Then, the vector matrix is used as the input of the temperature prediction model for calculation to obtain the predicted device surface temperature time-series data of the electrochemical energy storage device in the next time period.

[0062] It should be noted that during the standardization process, mainly the charge data in the charged time-series data, the device surface temperature data in the device surface temperature time-series data, and the external environment temperature data in the external environment temperature time-series data are standardized, and the time data therein is not processed.

[0063] For example, the data sequence obtained by standardizing the charged time-series data is (0.2, 0.22, 0.25, 0.27, 0.28), the data sequence obtained by standardizing the device surface temperature time-series data is (0.5, 0.51, 0.51, 0.52, 0.53), and the data sequence obtained by standardizing the external environment temperature time-series data is (0.61, 0.6, 0.6, 0.61, 0.62). Then, after standardizing and combining the charged time-series data, the device surface temperature time-series data, and the external environment temperature time-series data, the obtained vector matrix can be expressed as

[0064] In the embodiments of the present application, when training the temperature prediction model, the historical vector matrix corresponding to the electrochemical energy storage device and the same-type energy storage devices of the electrochemical energy storage device (corresponding to the historical charged time-series data, the historical device surface temperature time-series data, and the historical external environment temperature time-series data) can be used as the sample input, and the device surface temperature time-series data in the next time period corresponding to the historical vector matrix can be used as the sample output for calculation.

[0065] Step S104. Based on the current charge data of the electrochemical energy storage device, determine the charged time-series data of the electrochemical energy storage device in the next time period.

[0066] In the embodiments of the present application, the charged time-series data of the electrochemical energy storage device in the next time period can be estimated according to the current charge data of the electrochemical energy storage device and at least the most recent charge and discharge records of the electrochemical energy storage device.

[0067] For example, the electrochemical energy storage device is currently in a charging state. The current state of charge data of the electrochemical energy storage device is 50%, and the time difference between the state of charge time series data is 1 minute. According to the recent multiple charge and discharge records, during the charging process of the electrochemical energy storage device, for some time after the state of charge data reaches 50%, the charging speed has been maintained at an average of 1.5% per minute. Assuming that the duration of the next time period is 5 minutes, the state of charge time series data (the state of charge data) in the next time period can be successively expressed as 51.5%, 53%, 54.5%, 56%, and 57.5%.

[0068] Step S105. Based on the historical time series data of the device surface temperature and the predicted time series data of the device surface temperature during the current charge and discharge process of the electrochemical energy storage device, as well as the historical state of charge time series data of the electrochemical energy storage device during the current charge and discharge process and the state of charge time series data of the electrochemical energy storage device in the next time period, establish a device surface temperature curve that changes with the state of charge data of the electrochemical energy storage device from the start of the current charge and discharge to the next time period.

[0069] Specifically, based on the historical time series data of the device surface temperature and the predicted time series data of the device surface temperature during the current charge and discharge process of the electrochemical energy storage device, the time series data of the device surface temperature of the electrochemical energy storage device from the start of the current charge and discharge to the next time period can be determined. And based on the historical state of charge time series data of the electrochemical energy storage device during the current charge and discharge process and the state of charge time series data of the electrochemical energy storage device in the next time period, the state of charge time series data of the electrochemical energy storage device from the start of the current charge and discharge to the next time period can be determined. Then, according to the time series data of the device surface temperature of the electrochemical energy storage device from the start of the current charge and discharge to the next time period and the state of charge time series data of the electrochemical energy storage device from the start of the current charge and discharge to the next time period, establish a device surface temperature curve that changes with the state of charge data of the electrochemical energy storage device from the start of the current charge and discharge to the next time period.

[0070] Step S106. Determine whether there is a risk of thermal abuse in the electrochemical energy storage device based on the device surface temperature curve.

[0071] In the embodiments of the present application, the device surface temperature curve can be compared with the historical device surface temperature curve of the electrochemical energy storage device or the same model energy storage device of the electrochemical energy storage device when there is no risk of thermal abuse to determine whether there is a risk of thermal abuse in the electrochemical energy storage device. Specifically, the device surface temperature curve can be compared with the historical device surface temperature curve of the electrochemical energy storage device or the same model energy storage device of the electrochemical energy storage device that is similar to the initial curve and has no risk of thermal abuse to determine whether there is a risk of thermal abuse in the electrochemical energy storage device.

[0072] More specifically, the temperature value at the last moment in the surface temperature curve of the device can be compared with the temperature value at the corresponding moment in the historical surface temperature curve of an electrochemical energy storage device or an energy storage device of the same model of the electrochemical energy storage device that has no risk of thermal abuse and has the same or similar initial charge data and initial temperature. If the temperature value at the last moment in the surface temperature curve of the device is higher than the temperature value at the corresponding moment in the historical surface temperature curve of the device, and the difference exceeds the preset threshold or the exceeding ratio exceeds the preset ratio, it is determined that the electrochemical energy storage device has a risk of thermal abuse; otherwise, it is determined that the electrochemical energy storage device has no risk of thermal abuse.

[0073] Step S107. When the electrochemical energy storage device has a risk of thermal abuse, generate a warning message.

[0074] When the judgment result is that the electrochemical energy storage device has a risk of thermal abuse, a warning message can be generated to remind relevant personnel to take corresponding measures, such as stopping charging and discharging and cooling the electrochemical energy storage device through water cooling. In this way, early warning and corresponding measures can be taken before thermal abuse occurs, preventing thermal abuse and avoiding unnecessary losses caused by thermal abuse.

[0075] In summary, the method for warning of thermal abuse of an electrochemical energy storage based on enhanced deep learning provided by the present invention includes obtaining the charge time series data, the device surface temperature time series data, and the external environment temperature time series data of the electrochemical energy storage device during charging and discharging in the current period; determining a temperature prediction model corresponding to the charging and discharging state and based on enhanced deep learning according to the charging and discharging state of the electrochemical energy storage device; using the charge time series data, the device surface temperature time series data, and the external environment temperature time series data as the input of the temperature prediction model for calculation to obtain the predicted device surface temperature time series data of the electrochemical energy storage device in the next period; determining the charge time series data of the electrochemical energy storage device in the next period based on the current charge data of the electrochemical energy storage device; establishing a device surface temperature curve that changes with the charge data of the electrochemical energy storage device from the start of this charge and discharge to the next period based on the historical time series data of the device surface temperature and the predicted device surface temperature time series data of the electrochemical energy storage device during this charge and discharge process, and the historical charge time series data of the electrochemical energy storage device during this charge and discharge process and the charge time series data of the electrochemical energy storage device in the next period; determining whether the electrochemical energy storage device has a risk of thermal abuse based on the device surface temperature curve; and generating a warning message when the electrochemical energy storage device has a risk of thermal abuse. In this way, it can be predicted whether the electrochemical energy storage device has a risk of thermal abuse in the next period, and a warning message is generated when there is a risk of thermal abuse, so as to achieve early warning before thermal abuse occurs, so as to take corresponding measures in advance to prevent the occurrence of thermal abuse, avoid unnecessary losses caused by thermal abuse, and facilitate practical application and promotion.

[0076] Please refer to Figure 2 , in the second aspect of the embodiments of the present application, a thermal abuse warning device for electrochemical energy storage based on enhanced deep learning is provided. The thermal abuse warning device for electrochemical energy storage based on enhanced deep learning includes:

[0077] An acquisition unit, configured to acquire the charge-time sequence data, the device surface temperature time sequence data, and the external environment temperature time sequence data of the electrochemical energy storage device during the current period of charge and discharge;

[0078] A first determination unit, configured to determine a temperature prediction model corresponding to the charge and discharge state and based on enhanced deep learning based on the charge and discharge state of the electrochemical energy storage device, where the charge and discharge state is a charge state or a discharge state;

[0079] A calculation unit, configured to perform an operation by using the charge-time sequence data, the device surface temperature time sequence data, and the external environment temperature time sequence data as inputs of the temperature prediction model to obtain the device surface predicted temperature time sequence data of the electrochemical energy storage device in the next period;

[0080] A second determination unit, configured to determine the charge-time sequence data of the electrochemical energy storage device in the next period based on the current charge data of the electrochemical energy storage device;

[0081] A building unit, configured to build a device surface temperature curve that changes with the charge data of the electrochemical energy storage device from the start of the current charge and discharge to the next period based on the device surface temperature historical time sequence data and the device surface predicted temperature time sequence data of the electrochemical energy storage device during the current charge and discharge process, and the historical charge-time sequence data and the charge-time sequence data of the electrochemical energy storage device in the next period of the electrochemical energy storage device during the current charge and discharge process;

[0082] A third determination unit, configured to determine whether the electrochemical energy storage device has a thermal abuse risk based on the device surface temperature curve;

[0083] A warning unit, configured to generate a warning message when the electrochemical energy storage device has a thermal abuse risk.

[0084] For the working process, working details, and technical effects of the thermal abuse warning device for electrochemical energy storage based on enhanced deep learning provided in the second aspect of this embodiment, reference can be made to the first aspect of the embodiment, which will not be elaborated here.

[0085] Such as Figure 3As shown in the figure, the third aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a transceiver that are communicatively connected in sequence. Among them, the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the method for pre-warning thermal abuse of electrochemical energy storage based on enhanced deep learning as described in the first aspect of the embodiments.

[0086] Specifically, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in first-out memory (FIFO), and / or first-in last-out memory (FILO), etc.; the processor may not be limited to using a microprocessor of the STM32F105 series, an ARM (Advanced RISC Machines), an X86 architecture processor, or a processor integrated with an NPU (neural-network processing units); the transceiver may include, but is not limited to, a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee (a low-power local area network protocol based on the IEEE802.15.4 standard) wireless transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver, etc.

[0087] The fourth aspect of this embodiment provides a computer-readable storage medium storing instructions including the method for pre-warning thermal abuse of electrochemical energy storage based on enhanced deep learning as described in the first aspect of the embodiments, that is, instructions are stored on the computer-readable storage medium. When the instructions run on a computer, the method for pre-warning thermal abuse of electrochemical energy storage based on enhanced deep learning as described in the first aspect is executed. Among them, the computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disc, a hard disk, a flash memory, a USB flash drive, and / or a Memory Stick, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0088] The fifth aspect of this embodiment provides a computer program product including instructions. When the instructions run on a computer, the computer is made to execute the method for pre-warning thermal abuse of electrochemical energy storage based on enhanced deep learning as described in the first aspect of the embodiments. Among them, the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0089] It should be understood that specific details are provided in the following description to facilitate a complete understanding of the exemplary embodiments. However, those of ordinary skill in the art should understand that the exemplary embodiments can be implemented without these specific details. For example, the system may be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other instances, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the exemplary embodiments.

[0090] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An early warning method for thermal abuse of electrochemical energy storage based on enhanced deep learning, characterized in that, Including: Obtaining the charge-time sequence data, the device surface temperature time-sequence data, and the external environment temperature time-sequence data of the electrochemical energy storage device during the current period for charge and discharge; Based on the charge and discharge state of the electrochemical energy storage device, determining a temperature prediction model corresponding to the charge and discharge state and based on enhanced deep learning, where the charge and discharge state is a charging state or a discharging state; Using the charge-time sequence data, the device surface temperature time-sequence data, and the external environment temperature time-sequence data as inputs to the temperature prediction model for calculation to obtain the device surface predicted temperature time-sequence data of the electrochemical energy storage device in the next period; Based on the current charge data of the electrochemical energy storage device, determining the charge-time sequence data of the electrochemical energy storage device in the next period; Based on the device surface temperature historical time-sequence data and the device surface predicted temperature time-sequence data of the electrochemical energy storage device during the current charge and discharge process, as well as the historical charge-time sequence data of the electrochemical energy storage device during the current charge and discharge process and the charge-time sequence data of the electrochemical energy storage device in the next period, establishing a device surface temperature curve of the electrochemical energy storage device that changes with the charge data from the start of the current charge and discharge to the next period; Determining whether the electrochemical energy storage device has a thermal abuse risk based on the device surface temperature curve; When the electrochemical energy storage device has a thermal abuse risk, generating a warning message.

2. The method for predicting thermal abuse of electrochemical energy storage based on enhanced deep learning according to claim 1, wherein The step of using the charge-time sequence data, the device surface temperature time-sequence data, and the external environment temperature time-sequence data as inputs to the temperature prediction model for calculation to obtain the device surface predicted temperature time-sequence data of the electrochemical energy storage device in the next period includes: Normalizing and combining the charge-time sequence data, the device surface temperature time-sequence data, and the external environment temperature time-sequence data to obtain a vector matrix, where each row in the vector matrix corresponds to data of one dimension; Using the vector matrix as an input to the temperature prediction model for calculation to obtain the device surface predicted temperature time-sequence data of the electrochemical energy storage device in the next period.

3. The method for predicting thermal abuse of electrochemical energy storage based on enhanced deep learning according to claim 1, wherein, The step of based on the current charge data of the electrochemical energy storage device, determining the charge-time sequence data of the electrochemical energy storage device in the next period includes: Based on the current charge data of the electrochemical energy storage device and at least the most recent charge and discharge records of the electrochemical energy storage device, estimating the charge-time sequence data of the electrochemical energy storage device in the next period.

4. The method for warning of thermal abuse of electrochemical energy storage based on enhanced deep learning according to claim 1, wherein, The step of based on the device surface temperature historical time-sequence data and the device surface predicted temperature time-sequence data of the electrochemical energy storage device during the current charge and discharge process, as well as the historical charge-time sequence data of the electrochemical energy storage device during the current charge and discharge process and the charge-time sequence data of the electrochemical energy storage device in the next period, establishing a device surface temperature curve of the electrochemical energy storage device that changes with the charge data from the start of the current charge and discharge to the next period includes: Based on the historical time-series data of the surface temperature of the electrochemical energy storage device during the current charge-discharge process and the predicted temperature time-series data of the device surface, determine the device surface temperature time-series data of the electrochemical energy storage device from the start of the current charge-discharge to the next time period; Based on the historical charge time-series data of the electrochemical energy storage device during the current charge-discharge process and the charge time-series data of the electrochemical energy storage device in the next time period, determine the charge time-series data of the electrochemical energy storage device from the start of the current charge-discharge to the next time period; Based on the device surface temperature time-series data of the electrochemical energy storage device from the start of the current charge-discharge to the next time period and the charge time-series data of the electrochemical energy storage device from the start of the current charge-discharge to the next time period, establish the device surface temperature curve of the electrochemical energy storage device changing with the charge data from the start of the current charge-discharge to the next time period.

5. The method for warning of thermal abuse of electrochemical energy storage based on enhanced deep learning according to claim 1, wherein, Determining whether the electrochemical energy storage device has a thermal abuse risk based on the device surface temperature curve includes: Compare the device surface temperature curve with the device historical surface temperature curve of the electrochemical energy storage device or the same model energy storage device of the electrochemical energy storage device when no thermal abuse risk occurs, and determine whether the electrochemical energy storage device has a thermal abuse risk.

6. The electrochemical energy storage thermal abuse warning method based on enhanced deep learning according to claim 5, characterized in that, The comparing the device surface temperature curve with the device historical surface temperature curve of the electrochemical energy storage device or the same model energy storage device of the electrochemical energy storage device when no thermal abuse risk occurs includes: Compare the device surface temperature curve with the device historical surface temperature curve of the electrochemical energy storage device or the same model energy storage device of the electrochemical energy storage device that is similar to the initial curve and has no thermal abuse risk.

7. The electrochemical energy storage thermal abuse warning method based on enhanced deep learning according to claim 1, wherein The electrochemical energy storage device is a lithium-ion battery or a sodium-sulfur battery.

8. An electrochemical energy storage thermal abuse warning device based on enhanced deep learning, characterized in that, Including: An acquisition unit for acquiring the charge time-series data, the device surface temperature time-series data, and the external environment temperature time-series data of the electrochemical energy storage device during charging and discharging in the current period; A first determination unit for determining a temperature prediction model based on enhanced deep learning corresponding to the charge-discharge state based on the charge-discharge state of the electrochemical energy storage device, where the charge-discharge state is a charging state or a discharging state; A calculation unit for using the charge time-series data, the device surface temperature time-series data, and the external environment temperature time-series data as inputs of the temperature prediction model for calculation to obtain the predicted temperature time-series data of the device surface of the electrochemical energy storage device in the next time period; A second determination unit for determining the charge time-series data of the electrochemical energy storage device in the next time period based on the current charge data of the electrochemical energy storage device; A building unit is configured to establish a device surface temperature curve of the electrochemical energy storage device varying with the charge data from the start of the current charge-discharge process to the next time period, based on the historical time series data of the device surface temperature and the predicted time series data of the device surface temperature during the current charge-discharge process of the electrochemical energy storage device, as well as the historical charge time series data of the electrochemical energy storage device during the current charge-discharge process and the charge time series data of the electrochemical energy storage device in the next time period. A third determination unit is configured to determine whether there is a thermal abuse risk of the electrochemical energy storage device based on the device surface temperature curve. An early warning unit is configured to generate a warning message when there is a thermal abuse risk of the electrochemical energy storage device.

9. An electronic device, characterized in that, It includes a memory, a processor, and a transceiver that are communicatively connected in sequence. Among them, the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the method for early warning of thermal abuse of electrochemical energy storage based on enhanced deep learning as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or the instructions, when executed by a computer, implement the method for early warning of thermal abuse of electrochemical energy storage based on enhanced deep learning as described in any one of claims 1 to 7.

Images