Valve opening detection method and related device

Abstract

The application provides a valve opening detection method and related equipment, including: performing acoustic detection based on an acoustic signal in an operation process of an electric core to obtain an acoustic detection result; when the acoustic detection result meets a preset trigger condition, obtaining an electrical parameter and a thermal parameter of the electric core based on a time corresponding to the acoustic signal; and detecting a valve opening condition of the electric core based on the acoustic detection result, the electrical parameter and the thermal parameter to obtain a valve opening detection result. Thus, the valve opening detection method provided by the application can improve the accuracy of safety valve opening detection of the energy storage electric core and the timeliness of early warning.

Description

Technical Field

[0001] This application relates to the field of valve opening detection technology, and in particular to a valve opening detection method and related equipment. Background Technology

[0002] Lithium-ion batteries are widely used in energy storage power stations due to their high energy density and long cycle life. During the operation of energy storage systems, under abnormal conditions such as overcharging and overheating, lithium-ion batteries undergo violent chemical reactions, producing a large amount of gas and causing a sharp increase in internal pressure. If the pressure cannot be released in time, it may lead to thermal runaway, resulting in serious safety accidents such as fire and explosion. Therefore, lithium-ion batteries are typically equipped with safety valves. When the internal pressure exceeds a preset threshold, the safety valve opens, releasing high-pressure gas to relieve pressure and reduce the risk of thermal runaway. Therefore, accurate detection of the safety valve's opening status is a crucial step in achieving early warning of thermal runaway in energy storage batteries.

[0003] Currently, existing solutions utilize the analysis of acoustic signals generated during battery cell operation to detect the opening of safety valves. These solutions typically deploy acoustic sensors near the battery cell to collect acoustic signals in real time. Upon detecting a sound signal, the time-domain and / or frequency-domain features are extracted and input into a pre-trained classifier for identification. Based on the identification result, it is determined whether the sound indicates the safety valve is opening.

[0004] However, the existing solutions mentioned above rely solely on sound signals for judgment, which are easily affected by interference sources such as air pump noise, equipment operation noise, and sudden impact noise in complex energy storage power station environments, resulting in a high false alarm rate. Summary of the Invention

[0005] In view of this, this application provides a valve opening detection method and related equipment, which can improve the accuracy and timeliness of the detection of the opening of the safety valve of the energy storage cell.

[0006] In a first aspect, embodiments of this application provide a valve opening detection method, the method comprising: Acoustic detection is performed based on acoustic signals during the operation of the battery cell to obtain acoustic detection results; When the acoustic detection result meets the preset triggering conditions, the electrical and thermal parameters of the battery cell are obtained based on the time corresponding to the acoustic signal. Based on the acoustic detection results, the electrical parameters, and the thermal parameters, the valve opening status of the battery cell is detected, and the valve opening detection results are obtained.

[0007] Therefore, in the embodiments of this application, acoustic detection of acoustic signals is performed. When the acoustic detection results meet the triggering conditions, electrical and thermal parameters are acquired based on the time corresponding to the acoustic signal. Finally, the detection results of acoustic, electrical, and thermal parameters are combined to make a final judgment and obtain the valve opening detection result. Thus, by integrating multiple physical quantity data, such as sound signals and electrical and thermal parameters already collected by the Battery Management System (BMS), and using electrical and thermal parameters to assist in confirmation when the characteristics of the sound signal are ambiguous, the problem of single sound signals being easily affected by environmental interference is effectively solved, improving the accuracy and timeliness of the safety valve opening detection of the energy storage cell.

[0008] In one possible implementation, the acoustic detection based on acoustic signals during cell operation to obtain acoustic detection results includes: Extract the time-domain features of the acoustic signal; When the time-domain features meet the preset alarm conditions, based on the time corresponding to the acoustic signal, the acoustic signal within a predetermined time range before and after the time is extracted to obtain the target acoustic signal. Extract the frequency domain features of the target acoustic signal; Based on the frequency domain characteristics, the confidence level of the cell opening valve is determined; The confidence level and alarm type are used as the acoustic detection results, and the alarm type is determined by the time-domain features and the alarm conditions.

[0009] In one possible implementation, the time-domain features include: Root Mean Square (RMS) energy, peak-to-average power ratio (PAPR), and high-frequency energy; The alarm conditions include: The RMS energy is greater than a first dynamic threshold, and the peak-to-average power ratio is greater than a preset first threshold or a second dynamic threshold; or, The high-frequency energy is greater than the third dynamic threshold. The first dynamic threshold, the second dynamic threshold, and the third dynamic threshold are related to the historical acoustic signals in the first dynamic window, and the first dynamic window is determined by the time.

[0010] In one possible implementation, when the RMS energy is greater than a first dynamic threshold and the peak-to-average power ratio is greater than a preset first threshold or a second dynamic threshold, the alarm type is determined to be pulse type. When the high-frequency energy is greater than the third dynamic threshold, the alarm type is determined to be high-frequency. When the rapid rise index is greater than the fourth and fifth dynamic thresholds, and the high-frequency energy is greater than the third dynamic threshold, the alarm type is determined to be a mixed type.

[0011] In one possible implementation, extracting the frequency domain features of the target acoustic signal includes: For each dimension of the Mel-Frequency Cepstral Coefficients (MFCC) of the target acoustic signal, the mean, standard deviation, skewness, kurtosis, quantile, maximum value, and minimum value are calculated to obtain multiple characteristic parameters; Determine the logarithmic RMS energy and the mean centroid of the spectral spectrum of the target acoustic signal; The plurality of characteristic parameters, the logarithmic RMS energy, and the mean centroid of the spectrum are used as the frequency domain features.

[0012] In one possible implementation, determining the confidence level of the cell opening valve based on the frequency domain characteristics includes: The frequency domain features are input into a Support Vector Machine (SVM) classifier to obtain the confidence score. The SVM classifier uses a Radial Basis Function (RBF) kernel function.

[0013] In one possible implementation, detecting the valve opening status of the battery cell based on the acoustic detection results, the electrical parameters, and the thermal parameters to obtain the valve opening detection results includes: If the confidence level in the acoustic test result is within the preset high confidence interval, the valve opening test result is determined to be a confirmed valve opening. If the confidence level is within the preset medium confidence interval, and the alarm type in the acoustic detection result is high-frequency or mixed, the voltage and current characteristics are determined based on the electrical parameters, the temperature characteristics are determined based on the thermal parameters, a comprehensive score is determined based on the confidence level, the voltage characteristics, the current characteristics, and the temperature characteristics, and the valve opening detection result is determined based on the comprehensive score. If the confidence level is within the preset low confidence interval, the valve opening detection result is determined to be a false alarm.

[0014] Secondly, embodiments of this application provide a valve opening detection device, the device comprising: The detection module is used to perform acoustic detection based on acoustic signals during the operation of the battery cell and obtain acoustic detection results. The acquisition module is used to acquire the electrical and thermal parameters of the battery cell based on the time corresponding to the acoustic signal when the acoustic detection result meets the preset triggering conditions. The determination module is used to detect the valve opening status of the battery cell based on the acoustic detection results, the electrical parameters, and the thermal parameters, and obtain the valve opening detection results.

[0015] Thirdly, embodiments of this application provide an electronic device including a memory and a processor. The memory stores a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the steps in the method designed in the first aspect above.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the method of the first aspect of embodiments of this application.

[0017] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the method of the first aspect of embodiments of this application. The computer program product may be a software installation package.

[0018] The beneficial effects of the technical solutions in the second to fifth aspects can be found in the technical effects of the technical solution in the first aspect, and will not be repeated here. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 A schematic diagram of the structure of an energy storage system provided for an embodiment of this application; Figure 2 A schematic diagram of another energy storage system provided for an embodiment of this application; Figure 3 A schematic diagram of another energy storage system provided for an embodiment of this application; Figure 4 A schematic diagram of a valve opening detection device provided for an embodiment of this application; Figure 5 A schematic flowchart of a valve opening detection method provided for an embodiment of this application; Figure 6 A schematic diagram illustrating an example of visualization of the time-domain characteristics of valve opening sound provided for an embodiment of this application; Figure 7 A functional unit block diagram of a valve opening detection device provided for embodiments of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided for an embodiment of this application. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0023] In the embodiments of this application, "at least one item" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. "One or more" refers to one or more items, while "multiple" refers to two or more items. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0024] In the embodiments of this application, "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. The embodiments of this application do not impose any limitations on this. In the description of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "connection" should be interpreted broadly. In one example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or a connection that allows mutual communication; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal communication of two components or the interaction between two components.

[0025] In this document, the term "implementation" means that a specific feature, structure, or characteristic described in connection with an implementation may be included in at least one implementation of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same implementation, nor is it a separate or alternative implementation mutually exclusive with other implementations. It will be explicitly and implicitly understood by those skilled in the art that the implementations described herein can be combined with other implementations.

[0026] First, the scenarios in which this method is applicable will be explained.

[0027] Because the energy we need is highly time- and space-dependent, in order to utilize energy rationally and improve energy efficiency, it is necessary to store one form of energy in the same way or by converting it into another, and then release it in a specific energy form for future applications. Currently, the main way to generate green electricity is to develop green energy sources such as photovoltaics and wind power to replace fossil fuels. Currently, the generation of green electricity generally relies on solar, wind, and hydropower. However, wind and solar power are generally characterized by strong intermittency and large fluctuations, which can cause grid instability, insufficient power during peak demand periods, and excessive power during off-peak periods. Unstable voltage can also damage the power grid. Therefore, insufficient electricity demand or insufficient grid capacity may lead to the problem of "wind and solar curtailment." Solving these problems requires energy storage. This involves converting electrical energy into other forms of energy through physical or chemical means and storing it. When needed, this energy can be converted back into electrical energy and released. Simply put, energy storage is like a large "power bank," storing electrical energy when solar and wind power are abundant and releasing the stored electricity when needed.

[0028] Taking electrochemical energy storage as an example, this solution provides an energy storage device for use in energy storage systems. The energy storage device is equipped with a set of chemical batteries, which mainly use the chemical elements in the batteries as energy storage media. The charging and discharging process is accompanied by the chemical reaction or change of the energy storage media. Simply put, the electrical energy generated by wind and solar energy is stored in the chemical batteries. When the use of external electrical energy reaches its peak, the stored electricity is released for use, or transferred to places with a shortage of electricity for use.

[0029] Current energy storage applications are quite widespread, including generation-side energy storage, grid-side energy storage, and consumption-side energy storage. The corresponding types of energy storage devices include: (1) Large-scale energy storage power stations (composed of multiple prefabricated energy storage modules) applied to wind power and photovoltaic power stations can help renewable energy power generation meet grid connection requirements and improve the utilization rate of renewable energy. As a high-quality active / reactive power regulation power source on the power supply side, the energy storage power station realizes the load matching of power in time and space, enhances the renewable energy absorption capacity, reduces instantaneous power changes, reduces the impact on the power grid, improves the problem of new energy power generation absorption, and is of great significance in power grid system backup, alleviating peak load power supply pressure and peak regulation and frequency regulation. (2) The energy storage prefabricated cabin applied on the grid side mainly functions as peak regulation, frequency regulation and grid congestion relief. In terms of peak regulation, it can realize peak shaving and valley filling of electricity load, that is, charging the energy storage battery when the electricity load is low and releasing the stored electricity during the peak electricity load period, thereby achieving a balance between power production and consumption. (3) Small energy storage cabinets applied to the electricity consumption side mainly function as self-consumption of electricity, peak-valley price arbitrage, capacity cost management, and improvement of power supply reliability. Depending on the application scenario, electricity consumption side energy storage can be divided into industrial and commercial energy storage cabinets, household energy storage devices, energy storage charging piles, etc., which are generally used in conjunction with distributed photovoltaics. Industrial and commercial users can use energy storage for peak-valley price arbitrage and capacity cost management. In the electricity market implementing peak-valley pricing, by charging the energy storage system when the electricity price is low and discharging the energy storage system when the electricity price is high, peak-valley price arbitrage can be achieved, reducing electricity costs. In addition, industrial enterprises subject to two-part tariffs can use energy storage systems to store energy during off-peak hours and discharge during peak loads, thereby reducing peak power and the maximum demand declared, achieving the goal of reducing capacity costs. Household photovoltaics with energy storage can improve the level of self-consumption of electricity. Due to high electricity prices and poor power supply stability, the demand for household photovoltaic installations is driven. Given that photovoltaic power generation occurs during the day, while user load is generally higher at night, configuring energy storage can better utilize photovoltaic power, improve self-consumption levels, and reduce electricity costs. Furthermore, energy storage is needed in areas such as communication base stations and data centers for backup power.

[0030] In some implementations, please refer to Figure 1 , Figure 1 This application provides a schematic diagram of the structure of an energy storage system according to an embodiment of the present application. Figure 1 The implementation method is illustrated using a home energy storage scenario in user-side energy storage as an example. The energy storage device in this application is not limited to the home energy storage scenario.

[0031] This application provides an energy storage system 100, which includes a first power conversion device 110 (photovoltaic panel), a first user load 120 (household lighting fixture), a second user load 130 (e.g., household appliances such as air conditioners), and an energy storage device 140. The energy storage device 140 is a small energy storage box that can be wall-mounted on an outdoor wall. However, the energy storage device 140 is not limited to wall mounting and can also be placed in a user's residence in other ways. Specifically, the photovoltaic panel can convert solar energy into electrical energy during periods of low electricity prices, and the energy storage device 140 stores this electrical energy and supplies it to lighting fixtures and household appliances during peak electricity prices, or provides power during power outages / power interruptions.

[0032] In some implementations, please refer to Figure 2 , Figure 2 A schematic diagram of another energy storage system provided for an embodiment of this application, and this application Figure 2 The implementation method is illustrated using a shared energy storage scenario on the generation / distribution side as an example. The energy storage device in this application is not limited to the energy storage scenario on the generation / distribution side.

[0033] This application provides an energy storage system 200, which includes: a high-voltage cable 250, a first power conversion device 210, a second power conversion device 260, and an energy storage device 240 provided in this application. In some embodiments of the power generation scenario, the second power conversion device 260 can be a wind power conversion device. Since the electricity generated by wind power conversion is volatile, random, and intermittent, the unstable electricity output by the wind power conversion device can be stored in the energy storage device 240 through grid connection. The energy storage device 240 is connected to the high-voltage cable and outputs smooth electricity to the power consumption side of the distribution network, realizing peak shaving and frequency regulation, and stable grid operation; or, wind power... The energy conversion device is always connected to the high-voltage cable. Under normal power generation conditions, the power output of the wind power conversion device is supplied to the power consumption side of the distribution network through the high-voltage cable. When the current power load is low and the wind power conversion device generates excess power, the excess power is first stored in the energy storage device 240 to reduce wind and solar curtailment rates and improve the problem of new energy power generation consumption. When the power load is high, the power grid issues an instruction to transmit the power stored in the energy storage device 240 together with the high-voltage cable 250 in grid-connected mode to supply power to the power consumption side. This provides the power grid with various services such as peak shaving, frequency regulation, and backup, giving full play to the peak shaving role of the power grid, promoting peak shaving and valley filling, and alleviating the power supply pressure of the power grid.

[0034] In some implementations on the distribution network side, the first power conversion device 210 can be a photovoltaic panel, and the energy storage device 240 is connected to the high-voltage cable 250 and installed downstream of the high-voltage cable 250 and between the user load. The electrical energy output by the photovoltaic power conversion device is stored in the energy storage device 240, which can respond in a timely manner and act as a backup power source when the power grid / distribution network fails; or, it can provide power supply support to alleviate line congestion when the high-voltage cable 250 transmission line is blocked, and to delay the economic pressure caused by the expansion of the power grid / distribution capacity when the power grid is planned to be expanded.

[0035] In some implementations, please refer to Figure 3 , Figure 3 A schematic diagram of another energy storage system provided for an embodiment of this application, and this application Figure 3 The implementation method is illustrated using an industrial and commercial energy storage scenario as an example. The energy storage device in this application is not limited to industrial and commercial energy storage scenarios.

[0036] This application provides an energy storage system 300, which includes: an energy storage device 340, a high-voltage cable 350, a factory equipped with a first power conversion device 310, a photovoltaic-energy storage-charging station 360, and a vehicle 370. In some implementations of industrial and commercial scenarios, the first power conversion device 310 can be a photovoltaic panel, which converts solar energy into electrical energy and stores it in the energy storage device 340 in the factory. In the event of a power grid failure, the energy storage device 340 provides power to ensure the safe and stable operation of the factory without interruption. Alternatively, when the factory's power load is high, the power grid issues an instruction to transmit the electricity stored in the energy storage device 340 in conjunction with the high-voltage cable 350 in a grid-connected mode to supply the factory with electricity, providing various services such as peak shaving / frequency regulation and backup for the power grid operation. In addition, the first power conversion device 310 can also convert solar energy into electrical energy and store it in the energy storage device 340 of the photovoltaic-energy storage-charging station 360, which can then directly charge the vehicle 370, providing a fast and convenient solution.

[0037] Optionally, the first power conversion device 310 may include, but is not limited to, a photovoltaic panel, and the second power conversion device 260 may include, but is not limited to, a wind power conversion device. The first power conversion device 310 and the second power conversion device 260 can convert at least one of solar energy, light energy, wind energy, thermal energy, tidal energy, biomass energy, and mechanical energy into electrical energy.

[0038] Optionally, the energy storage device 340 may include, but is not limited to, energy storage applications such as energy storage power stations, hydropower / thermal / wind power generation systems, solar power generation systems, mobile power systems, smart home systems, or temporary power supply systems, and may also be applied in multiple fields such as data centers, military equipment, aerospace, charging piles, and electric vehicles.

[0039] Optionally, the energy storage device 340 may include, but is not limited to, single-cell batteries, or battery modules, battery packs, battery clusters, power banks, energy storage cabinets / prefabricated energy storage compartments, and other battery integrated systems composed of single-cell batteries. The actual application form of the energy storage device 340 provided in this application embodiment may be, but is not limited to, the listed products, and may also be other application forms. This application embodiment does not strictly limit the application form of the energy storage device 340.

[0040] Optionally, the individual cell can be, but is not limited to, at least one of cylindrical, prismatic, prismatic, or other shaped cells.

[0041] Optionally, the single cell can be a rechargeable battery, which refers to a single cell that can be recharged after discharge to activate the active materials and continue to be used. The single cell can be a lithium-ion battery, sodium-ion battery, sodium-lithium-ion battery, lithium metal battery, sodium metal battery, lithium-sulfur battery, magnesium-ion battery, nickel-metal hydride battery, nickel-cadmium battery, lead-acid battery, etc., and this application does not specifically limit it.

[0042] In all the scenarios described above, energy storage devices can be battery modules composed of multiple individual battery cells. Under abnormal operating conditions such as overcharging or overheating, a cell undergoes a violent chemical reaction, producing a large amount of gas and causing a sharp increase in internal pressure. If this pressure cannot be released in time, it may lead to thermal runaway, resulting in serious safety accidents such as fires and explosions. Therefore, battery cells are typically equipped with safety valves. When the internal pressure exceeds a preset threshold, the safety valve opens, releasing high-pressure gas to relieve pressure and reduce the risk of thermal runaway. Therefore, accurate detection of the safety valve's opening status is a crucial step in ensuring the safe operation of energy storage devices in the aforementioned scenarios.

[0043] To address the aforementioned issues, this application provides a valve opening detection method and related equipment, which can improve the accuracy and timeliness of safety valve opening detection in energy storage cells, thereby reducing safety hazards during the operation of energy storage devices, extending the service life of energy storage devices, and ultimately improving the stability and reliability of energy storage systems.

[0044] Secondly, see Figure 4 , Figure 4 This diagram illustrates a valve opening detection device according to an embodiment of this application. A valve opening detection method according to this embodiment can be executed by this valve opening detection device. The valve opening detection device 400 may include detection software 410, an operating system 420, and hardware 430. The hardware 430 may include a central processing unit (CPU) 431, a memory 432, and external devices 433.

[0045] In this embodiment, the valve opening detection device 400 can be a device with communication capabilities, and may be referred to as a terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal device, vehicle-mounted terminal device, industrial control terminal device, UE unit, UE station, mobile station, remote station, remote terminal device, mobile device, UE terminal device, wireless communication device, UE agent, or UE device, etc. The valve opening detection device 400 can be fixed or mobile. It should be noted that the valve opening detection device 400 can support at least one wireless communication technology, such as LTE, new radio (NR), wideband code division multiple access (WCDMA), etc. For example, the host computer can be a mobile phone, tablet, desktop computer, laptop computer, all-in-one computer, vehicle terminal, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, wearable device, terminal device in future mobile communication networks, or terminal device in future evolved public land mobile network (PLMN), etc. In some embodiments of this application, the valve opening detection device 400 may also be a device with transceiver functions, such as a chip system. The chip system may include a chip, and may also include other discrete components.

[0046] In this embodiment, the valve opening detection device 400 can also be a server. For example, it can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. This application does not make any specific limitations on this.

[0047] In this embodiment, the memory 432 may be: a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions; a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions; or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device; or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. This application does not specifically limit this type of storage.

[0048] In this embodiment, the user can control the valve opening detection device 400 through the operating system 420. Simultaneously, with the support of hardware 430, the valve opening detection device 400 can run detection software 410 to perform valve opening detection. During the detection process, the valve opening detection device 400 can acquire relevant data from signal acquisition device 440, database 450, server 460, etc.

[0049] Understandable Figure 4 The form and quantity of the detection software 410, operating system 420 and hardware 430 in the valve opening detection device 400 shown are for illustrative purposes only and do not constitute a limitation on the implementation of this application.

[0050] For example, the valve opening detection device 400 may include other software besides the detection software 410 shown.

[0051] For example, the valve opening detection device 400 may include other operating systems besides the operating system 420 shown.

[0052] For example, the valve opening detection device 400 may include other hardware in addition to the hardware 430 shown.

[0053] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the above content and the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. At the same time, these embodiments can be related to each other or independent of each other, and the same content between different embodiments can be referenced by each other, which will not be elaborated here.

[0054] The following will combine Figure 5 This application describes a valve opening detection method according to one of its embodiments. Figure 5 A flowchart illustrating a valve opening detection method provided in this application embodiment is shown. This method can be applied to... Figure 4 The valve opening detection device 400 shown is executed, and the method includes the following steps: S501: Acoustic detection is performed based on acoustic signals during the operation of the battery cell to obtain acoustic detection results.

[0055] In this embodiment, acoustic signals can be acquired in real time using acoustic sensors (e.g., microphones) deployed near the battery cell. For example, a mono acoustic signal can be acquired at a sampling rate of 48 kHz and a quantization precision of 16 bits. The acquired acoustic signal can be processed in frames, with a frame length of 1024 (approximately 21.3 ms) and a frame shift of 512 (approximately 10.7 ms). Frame-by-frame monitoring of the audio stream is achieved by processing each frame.

[0056] In this embodiment, to avoid the computational power consumption caused by continuous high-frequency sampling, the present application adopts a two-stage cascaded acoustic detection architecture. Specifically, the first stage is a coarse screening in the time domain, which continuously monitors the audio stream by extracting the time domain features of the acoustic signal and utilizing time domain statistical features with extremely low computational cost. When the time domain features meet preset alarm conditions, the second stage of detection is triggered. The second stage of detection is a fine screening based on the frequency domain, which obtains the target acoustic signal by intercepting the acoustic signal within a predetermined time range before and after the trigger time, and extracts the frequency domain features of the target acoustic signal. Finally, the confidence level of cell valve opening is determined based on the frequency domain features, and the confidence level and alarm type are output together as the acoustic detection result.

[0057] The following sections will provide a detailed explanation of the two-stage cascaded acoustic detection architecture.

[0058] (1) Time-domain coarse screening: In this embodiment, the sound signal generated when the cell safety valve opens may overlap with other interference sounds in the energy storage power station environment (such as air pump sounds, equipment operation sounds, and sudden impact sounds) in a single dimension, but it has significant and distinguishable characteristics in some dimensions of the time domain. Specifically, the opening of the safety valve is a pulse sound generated by the instantaneous ejection of high-pressure gas, which not only has obvious loudness increase and sharp waveform characteristics, but is also accompanied by rich high-frequency turbulence components and extremely fast transient oscillation speed, while most environmental interference sounds do not possess all of the above characteristics at the same time.

[0059] Specifically, see Figure 6 , Figure 6 This is a schematic diagram illustrating an example of visualizing the time-domain characteristics of valve opening sound as provided in an embodiment of this application. For example... Figure 6 As shown, taking the acoustic signal under a real overcharge valve opening scenario as an example, within ±0.2 seconds at the valve opening moment (approximately 45.5 seconds), the parameters of the four dimensions—RMS energy, peak-to-average power ratio, high-frequency energy, and rapid rise index—show significantly different change characteristics from the interference sound. Specifically, the RMS energy envelope exhibits a huge spike at the valve opening moment, far exceeding the baseline; the peak-to-average power ratio jumps to greater than 12 at the instant of valve opening; the high-frequency energy (7kHz to 24kHz frequency band) surges at valve opening; and in the rapid rise index, the short-time window mean steeply crosses the long-time window mean at valve opening.

[0060] Subsequently, in this embodiment, the time-domain characteristics can be selected from the aforementioned RMS energy, peak-to-average power ratio, high-frequency energy, and rapid rise index to quickly capture the suspected valve opening sound signal.

[0061] Specifically, RMS energy reflects the overall loudness of a signal, and it is calculated as the square root of the mean of the squares of the amplitudes of all sampling points within the current frame, which can be expressed by formula ①: ① Where, x i Let be the amplitude of the i-th sampling point in the current frame, and n be the number of sampling points in the current frame.

[0062] In this embodiment, the peak-to-average power ratio (PAPR) reflects the sharpness of the waveform. It is calculated as the ratio of the maximum amplitude within the current frame to the RMS energy, and can be expressed by formula ②: ② In this embodiment, the high-frequency energy reflects the energy distribution of the signal in the 7kHz to 24kHz frequency band, and is obtained by calculating the RMS energy after bandpass filtering the signal.

[0063] In this embodiment, the rapid rise index reflects the transient oscillation speed of the signal. It is calculated by comparing the signal mean within a short window (nearly 10 frames, about 107ms) with the signal mean within a long window (historical 50 frames, about 535ms).

[0064] In this embodiment, the alarm conditions include: <1> The RMS energy is greater than the first dynamic threshold, and the peak-to-average power ratio is greater than the preset first threshold or second dynamic threshold.

[0065] Specifically, the first dynamic threshold is related to the historical acoustic signal within the first dynamic window, which is determined by the moment corresponding to the acoustic signal. For example, the first dynamic window can be a sliding window spanning 10 seconds, ending at the moment corresponding to the acoustic signal. The first dynamic threshold can then be determined based on the median RMS energy within the first dynamic window, as expressed by formula ③: ③ Among them, median(RMS) hist The median (RMS) represents the median of the RMS energy within a historical 10-second sliding window. hist Xa is the baseline of the RMS energy, and the first dynamic threshold is b times the baseline of the RMS energy. For example, a can be 1.2 and b can be 3.

[0066] In this embodiment, the preset first threshold can be determined based on the specific execution environment and requirements, for example, it can be set to 12. The second dynamic threshold is also related to the historical acoustic signal in the first dynamic window. For example, the second dynamic threshold is determined based on the median of the peak-to-average power ratio and the median absolute deviation (MAD) within the historical 10-second sliding window, which can be specifically expressed by formula ④: ④ Among them, median(Crest) hist ) represents the median of the peak-to-average ratio within a historical 10-second sliding window. For example, c can be 5.

[0067] <2> The high-frequency energy is greater than the third dynamic threshold.

[0068] Specifically, the third dynamic threshold is related to the historical acoustic signal within the first dynamic window. For example, the third dynamic threshold is determined based on the median of high-frequency energy within a historical 10-second sliding window, and can be expressed by formula ⑤: ⑤ Among them, median(HF) hist) represents the median of high-frequency energy within a historical 10-second sliding window, median(HF) hist Xd represents the baseline of the high-frequency energy, and the third dynamic threshold is e times the baseline of the high-frequency energy. For example, d can be 1.5 and e can be 6.

[0069] <3> The rapid rise indicator is greater than the fourth and fifth dynamic thresholds, and the high-frequency energy is greater than the third dynamic threshold.

[0070] Specifically, the rapid rise index can be determined by calculating the average amplitude of the sampling points in the historical acoustic signal within the first dynamic window. Based on this, the fourth dynamic threshold can be correlated with the historical acoustic signal in the second dynamic window, which has a longer time span than the first dynamic window and can also be determined by the time corresponding to the acoustic signal. For example, the second dynamic window can be a sliding window spanning 60 seconds, ending at the time corresponding to the acoustic signal. The fourth dynamic threshold can then be determined by calculating the average amplitude of the sampling points in the historical acoustic signal within the second dynamic window, as specifically expressed by formula ⑥: ⑥ Here, mean(AMP) represents the average amplitude of the sampled points in the historical acoustic signal within a historical 60-second sliding window. For example, f can be 2.

[0071] In this embodiment, the fifth dynamic threshold is correlated with the historical acoustic signal within the first dynamic window. For example, the fifth dynamic threshold is determined based on the median of the signal amplitude within a historical 10-second sliding window, and can be specifically expressed by formula ⑦: ⑦ Among them, median(AMP) hist ) represents the median of the signal amplitude within a historical 10-second sliding window. For example, g can be 1.5.

[0072] It should be noted that the parameters in the above dynamic thresholds are a preferred example of the implementation of this application, and can be adaptively adjusted according to specific scenarios in practical applications.

[0073] In this embodiment, a dual de-jitter mechanism is implemented to avoid false triggering caused by transient noise glitches. Specifically, regarding continuous frame counting de-jitter, an alarm is only output after the same triggering cause continuously meets the alarm conditions for a predetermined number of frames (e.g., 3 consecutive frames, corresponding to approximately 63 milliseconds). Regarding minimum interval limitation, the interval between two valid alarms is required to be greater than a predetermined value (e.g., 0.2 seconds). Through the above dual de-jitter mechanism, microsecond-level circuit noise and periodic mechanical interference signals can be effectively filtered out, improving the reliability of the alarm.

[0074] In this implementation, after a Level 1 alarm is triggered, the system determines the alarm type based on the combination of alarm triggering conditions. Specifically, when the triggered alarm conditions are... <1> When the alarm type is determined to be pulse type (P type), the alarm condition that triggers the alarm is... <2> When the alarm type is determined to be high-frequency (H type), and the alarm condition is triggered as follows: <3> When the alarm is detected, the alarm type is determined to be hybrid (M type). Among the three alarm types mentioned above, the pulse type has obvious transient impact characteristics but lacks high-frequency components, the high-frequency type has obvious high-frequency jet characteristics but lacks transient impact characteristics, and the hybrid type has both of the above characteristics, which best matches the acoustic characteristics produced by the high-pressure gas jet when the safety valve is opened.

[0075] In this embodiment, after a Level 1 alarm is triggered, the system automatically backtracks forward by a first predetermined time (e.g., 0.3 seconds) and extends backward by a second predetermined time (e.g., 0.7 seconds) based on the trigger time, extracting an audio segment of a predetermined length (e.g., 1 second) as the target acoustic signal. The purpose of backtracking forward is to ensure that the complete prelude from "silence" to "oscillation" before the trigger point is included, and the purpose of extending backward is to capture the complete signal attenuation envelope, thereby ensuring that the target acoustic signal contains complete acoustic event information and providing a sufficient data foundation for subsequent frequency domain feature extraction.

[0076] (2) Frequency domain fine screening: In this embodiment, the frequency domain characteristics of the target acoustic signal may include MFCC, log-RMS energy, and mean centroid of the spectrum. MFCC simulates the nonlinear auditory characteristics of the human ear at different frequencies, effectively characterizing the spectral envelope characteristics of sound. Subsequently, for each dimension of the MFCC parameter, various statistics are calculated on the time axis, including mean, standard deviation, skewness, kurtosis, quantiles (e.g., 25th and 75th quantiles), maximum and minimum values, yielding multiple characteristic parameters. These statistics can characterize the overall distribution of the target acoustic signal within a one-second time window, including central tendency, dispersion, distribution symmetry, tail characteristics, and extreme value range. Log-RMS energy reflects the absolute loudness of the signal, and the mean centroid of the spectrum reflects the distribution position of the signal's spectral centroid. These two, as global features, can characterize the overall characteristics of the target acoustic signal in terms of loudness and spectral centroid, compensating for the absolute energy and spectral centroid information lost during MFCC extraction, and together with the aforementioned MFCC statistical characteristic parameters, constitute the frequency domain characteristics of the target acoustic signal.

[0077] Specifically, 13-dimensional MFCC coefficients can be extracted, and eight statistics (mean, standard deviation, skewness, kurtosis, 25th percentile, 75th percentile, maximum, and minimum) can be calculated for each MFCC coefficient, resulting in 104-dimensional feature parameters. Then, two global features—log-RMS energy and the mean of the spectral centroid—are added, ultimately forming a 106-dimensional feature vector. This 106-dimensional feature vector contains information about the sound's spectral shape (MFCC statistics), absolute loudness (log-RMS energy), and spectral centroid (mean of the spectral centroid), providing sufficient basis for subsequent classifier discrimination.

[0078] In this embodiment, the extracted 106-dimensional frequency domain features can be input into a pre-trained SVM classifier. This classifier uses the RBF kernel function and enables probability output mode (probability=True). The output value is the probability that the target acoustic signal belongs to the opening sound of a safety valve, which serves as the confidence P of the cell opening. acoustic The SVM classifier exhibits good generalization performance under small sample conditions, making it suitable for real-world scenarios where large quantities of safety valve opening sound samples are difficult to obtain. The RBF kernel function can map nonlinearly separable data to a high-dimensional space, making it linearly separable. The probability output pattern, through Platt scaling, maps the classifier's decision distance to a confidence value with clear probabilistic meaning, facilitating subsequent hierarchical decision-making based on confidence thresholds. Specifically, the SVM classifier parameters are set to C=1.0 and gamma='scale'.

[0079] In this embodiment, the confidence level and alarm type are both output as the acoustic detection result. The confidence level reflects the degree of matching between the acoustic signal and the safety valve opening sound at the frequency domain feature level, while the alarm type reflects the feature combination type that triggers the alarm during the time domain coarse screening stage. These two aspects describe the acoustic detection result from different dimensions, providing complementary information input for subsequent fusion and determination.

[0080] S502: When the acoustic detection result meets the preset triggering conditions, the electrical and thermal parameters of the battery cell are obtained based on the time corresponding to the acoustic signal.

[0081] In this embodiment, the acoustic detection results include the alarm type determined at the first level and the confidence level P determined at the second level. acoustic The preset trigger condition is: the confidence level P determined at the second level. acoustic It is within the preset medium confidence interval, and the alarm type determined in the first level is high-frequency or mixed.

[0082] Specifically, [0.85, 1] ​​is set as the high confidence interval, when P acousticWhen the value is ≥0.85, it indicates that the voiceprint characteristics are extremely clear, requiring no multi-source verification, and valve opening confirmation can be directly output. Setting [0, 0.5] as the low confidence interval, when P... acoustic When the confidence interval is ≤0.5, it indicates that the voiceprint is highly similar to the interference, and multi-source verification is unlikely to change the conclusion. Therefore, it can be discarded directly, confirming the valve opening detection result as a false alarm due to interference. Setting (0.5, 0.85) as the medium confidence interval, only within 0.50... <P acoustic When the value is less than 0.85, and the alarm type determined in the first stage is high-frequency or mixed, the process of acquiring the electrical and thermal parameters of the battery cell is initiated. The final valve opening detection result is then determined by combining the acquired electrical and thermal parameters. This conditional triggering strategy saves approximately 95% of computing power compared to a full-process multi-sensor fusion solution.

[0083] In this implementation, a time window can be constructed using the physical moment T0 when the first-level alarm is triggered as the reference point. Specifically, the historical window is T0. The time window is 60 seconds to T0, used to establish normal baselines for each physical quantity. The event window is from T0 to T0+10 seconds, used to detect abnormal changes. Electrical and thermal parameters within this time window are retrieved from the BMS. Electrical parameters include voltage and current data, and thermal parameters include temperature data. For example, temperature data can be cell surface temperature or electrode temperature, with a sampling rate of at least 1Hz; voltage data is the voltage of a single cell, with a sampling rate of at least 10Hz; and current data is the charging and discharging current, with a sampling rate of at least 10Hz. All of the above data are existing data already collected in real-time by the BMS during the operation of the energy storage system, requiring no additional hardware sensors.

[0084] S503: Based on acoustic detection results, electrical parameters, and thermal parameters, the valve opening status of the battery cell is detected, and the valve opening detection results are obtained.

[0085] In this embodiment, the historical window (T0) retrieved from the BMS After analyzing the electrical and thermal parameters within the 60s to T0 and event windows (T0 to T0+10s), the temporal variation characteristics of each physical quantity are extracted.

[0086] Specifically, voltage and current characteristics can be determined for electrical parameters, and temperature characteristics can be determined for thermal parameters. Then, a comprehensive score can be determined based on the confidence level, voltage characteristics, current characteristics, and temperature characteristics, and the valve opening detection result can be determined based on this comprehensive score.

[0087] The temporal variation characteristics of each physical quantity will be explained in detail below.

[0088] (1) Voltage characteristics.

[0089] In this embodiment, the voltage characteristic is the voltage deviation ΔV, which is used to measure the degree of deviation of the instantaneous voltage of a single cell within the event window from the nominal voltage under the same state of charge (SOC). Specifically, it can be expressed by formula ⑧: ⑧ Among them, V instant V represents the instantaneous voltage value of a single battery cell within the event window. nominal This is the nominal voltage value of the battery cell at the same SOC, obtained from the BMS.

[0090] Furthermore, based on the magnitude of the voltage deviation, the voltage anomaly score S can be determined. voltage .

[0091] For example, when ΔV > 0.5V, it is determined to be a significant voltage anomaly, S voltage =1.0; When 0.2V < ΔV ≤ 0.5V, the voltage abnormality is considered minor. voltage =0.6; When ΔV ≤ 0.2V, the voltage is considered normal. voltage =0.2.

[0092] (2) Current characteristics.

[0093] In this embodiment, current characteristics are used for operating condition determination. The current operating condition score S can be determined based on the different current directions and magnitudes within the event window. current .

[0094] For example, when I>0 and |I|>0.1C, it is determined to be a charging condition (overcharge risk scenario), S current =1.0; When I < 0 and |I| > 0.1C, it is determined to be a discharge condition, S current =0.5; When |I| ≤ 0.1C, it is determined to be in a static state, S current =0.2.

[0095] (3) Temperature characteristics.

[0096] In this embodiment, the temperature characteristic is the rate of temperature change ΔT / Δt, which measures the rate of temperature change relative to the historical baseline within the event window. Specifically, it can be expressed by formula ⑨: 9 Among them, T event T represents the maximum temperature within the event window. baseline Δt represents the median temperature within the historical window, and Δt represents the duration of the event window.

[0097] Furthermore, based on the magnitude of the temperature change rate, the temperature anomaly score S can be determined. temp .

[0098] For example, when ΔT / Δt > 0.5℃ / s, it is determined to be a drastic temperature anomaly. temp =1.0; When 0.2℃ / s < ΔT / Δt ≤ 0.5℃ / s, it is determined to be an abnormally mild temperature. temp =0.6; When ΔT / Δt ≤ 0.2℃ / s, the temperature is considered normal. temp =0.2.

[0099] It should be noted that the above parameters are a preferred example of the implementation method of this application, and can be adapted to specific scenarios in actual applications.

[0100] In this embodiment, after determining the voltage, current, and temperature characteristics, a weighted fusion based on confidence levels can be performed to obtain the comprehensive score FusionScore, which can be expressed by formula ⑩: ⑩ Among them, α+β+γ+δ=1, and α>β>γ>δ.

[0101] It should be noted that the confidence level P acoustic The fastest response time (milliseconds) is the trigger source for the entire multi-parameter fusion decision, therefore it is assigned the highest weight; temperature change rate S temp It is the most reliable physical indicator of thermal runaway, but its response speed is relatively slow (on the order of seconds), so its weight is secondary; voltage deviation S voltage This is direct evidence of overcharging, but not all safety valve opening events are accompanied by a significant voltage drop, therefore the weighting is again; Current condition S current It is only used to assist in determining whether the current battery cell is in an overcharge risk scenario, and does not make a separate decision, so it has the lowest weight. For example, α can be 0.40, β can be 0.30, γ can be 0.20, and δ can be 0.10.

[0102] In this embodiment, the final valve opening detection result can be determined based on the threshold range into which the comprehensive score FusionScore falls.

[0103] For example, when FusionScore ≥ 0.75, it is determined as valve opening confirmation, and a valve opening alarm is output; When 0.50≤FusionScore<0.75, it is judged as suspected valve opening, a valve opening warning is output, and manual review is recommended; When FusionScore < 0.50, it is judged as a false alarm and is silently discarded.

[0104] As can be seen, the method of this application performs acoustic detection on the acoustic signal. When the acoustic detection result meets the triggering condition, electrical and thermal parameters are acquired based on the time corresponding to the acoustic signal. The final judgment is then made by combining the detection results of acoustic, electrical, and thermal parameters to obtain the valve opening detection result. Therefore, by integrating multiple physical quantity data, such as sound signals and electrical and thermal parameters already collected by the BMS, and using electrical and thermal parameters to assist in confirmation when the characteristics of the sound signal are ambiguous, the method effectively solves the problem that a single sound signal is easily affected by environmental interference, and improves the accuracy and timeliness of the safety valve opening detection of the energy storage cell.

[0105] The foregoing primarily describes the implementation scheme of this application from a methodological perspective. It is understood that, to achieve the above functions, the apparatus may include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0106] The embodiments of this application can divide the device into functional units according to the above method examples. For example, each function can be divided into separate functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software program module. It should be noted that the unit division in the embodiments of this application is illustrative and is only a logical functional division, while other division methods may be used in actual implementation.

[0107] When using integrated units, Figure 7 This is a functional unit block diagram of a valve opening detection device according to an embodiment of this application. The valve opening detection device 700 includes a detection module 701, an acquisition module 702, and a determination module 703.

[0108] In this embodiment, the detection module 701, the acquisition module 702, and the determination module 703 can be any module unit used to receive and process signals, information, etc., or to determine a monitoring mechanism, and there are no specific limitations on this.

[0109] In this embodiment, the valve opening detection device 700 may further include a storage unit for storing computer program code or instructions executed by the valve opening detection device 700. The storage unit may be a memory.

[0110] In this embodiment, the valve opening detection device 700 can be a chip or a chip module.

[0111] In this embodiment, the detection module 701, the acquisition module 702, and the determination module 703 can be integrated into the communication unit. The communication unit can be a communication interface, transceiver, transceiver circuit, etc.

[0112] In this embodiment, the detection module 701, the acquisition module 702, and the determination module 703 can be integrated into the processing unit.

[0113] It should be noted that the processing unit can be a processor or controller, such as a baseband processor, baseband chip, central processing unit (CPU), general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processing unit can also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0114] In this embodiment, the valve opening detection device 700 is used to perform any of the steps performed by network devices / chips / chip modules, etc., as described in the above method embodiments.

[0115] In specific implementation, the detection module 701, the acquisition module 702, and the determination module 703 are used to execute any of the steps in the above method implementation, and when performing actions such as sending, other units can be selectively invoked to complete the corresponding operation. A detailed explanation follows.

[0116] The detection module 701 is used to perform acoustic detection based on acoustic signals during the operation of the battery cell and obtain acoustic detection results. The acquisition module 702 is used to acquire the electrical and thermal parameters of the battery cell based on the time corresponding to the acoustic signal when the acoustic detection result meets the preset triggering conditions. The determination module 703 is used to detect the valve opening status of the battery cell based on the acoustic detection results, the electrical parameters, and the thermal parameters, and obtain the valve opening detection results.

[0117] In this embodiment, regarding the acoustic detection based on acoustic signals during cell operation to obtain acoustic detection results, the detection module 701 is specifically used for: Extract the time-domain features of the acoustic signal; When the time-domain features meet the preset alarm conditions, based on the time corresponding to the acoustic signal, the acoustic signal within a predetermined time range before and after the time is extracted to obtain the target acoustic signal. Extract the frequency domain features of the target acoustic signal; Based on the frequency domain characteristics, the confidence level of the cell opening valve is determined; The confidence level and alarm type are used as the acoustic detection results, and the alarm type is determined by the time-domain features and the alarm conditions.

[0118] In this embodiment, the time-domain features include: RMS energy, peak-to-average power ratio, and high-frequency energy; The alarm conditions include: The RMS energy is greater than a first dynamic threshold, and the peak-to-average power ratio is greater than a preset first threshold or a second dynamic threshold; or, The high-frequency energy is greater than the third dynamic threshold. The first dynamic threshold, the second dynamic threshold, and the third dynamic threshold are related to the historical acoustic signals in the first dynamic window, and the first dynamic window is determined by the time.

[0119] In this embodiment, when the RMS energy is greater than the first dynamic threshold and the peak-to-average power ratio is greater than the preset first threshold or the second dynamic threshold, the alarm type is determined to be pulse type. When the high-frequency energy is greater than the third dynamic threshold, the alarm type is determined to be high-frequency. When the rapid rise index is greater than the fourth and fifth dynamic thresholds, and the high-frequency energy is greater than the third dynamic threshold, the alarm type is determined to be a mixed type.

[0120] In this embodiment, the detection module 701, in terms of extracting the frequency domain features of the target acoustic signal, is specifically used for: For each dimension of the MFCC parameter of the target acoustic signal, the mean, standard deviation, skewness, kurtosis, quantile, maximum value and minimum value are calculated to obtain multiple characteristic parameters; Determine the logarithmic RMS energy and the mean centroid of the spectral spectrum of the target acoustic signal; The plurality of characteristic parameters, the logarithmic RMS energy, and the mean centroid of the spectrum are used as the frequency domain features.

[0121] In this embodiment, regarding determining the confidence level of the cell opening valve based on the frequency domain characteristics, the detection module 701 is specifically used for: The frequency domain features are input into an SVM classifier to obtain the confidence score. The SVM classifier uses the RBF kernel function.

[0122] In this embodiment, the determination module 703, in determining the valve opening status of the battery cell based on the acoustic detection results, the electrical parameters, and the thermal parameters to obtain the valve opening detection result, is specifically used for: If the confidence level in the acoustic test result is within the preset high confidence interval, the valve opening test result is determined to be a confirmed valve opening. If the confidence level is within the preset medium confidence interval, and the alarm type in the acoustic detection result is high-frequency or mixed, the voltage and current characteristics are determined based on the electrical parameters, the temperature characteristics are determined based on the thermal parameters, a comprehensive score is determined based on the confidence level, the voltage characteristics, the current characteristics, and the temperature characteristics, and the valve opening detection result is determined based on the comprehensive score. If the confidence level is within the preset low confidence interval, the valve opening detection result is determined to be a false alarm.

[0123] It should be noted that, Figure 7 The specific implementation of each operation in the implementation method can be found in the description of the method implementation method shown above, and will not be repeated here.

[0124] In this embodiment, refer to Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided for an embodiment of this application. For example... Figure 8 As shown, the electronic device 800 includes a processor 801 and a memory 802. The processor 801 is coupled to the memory 802. The memory 802 is used to store computer programs or instructions / data. The processor 801 is used to execute the computer programs or instructions / data stored in the memory 802, or to read the data stored in the memory 802.

[0125] Optionally, there may be one or more processors 801.

[0126] Optionally, the memory 802 may be one or more.

[0127] Alternatively, the memory 802 can be integrated with the processor 801, or it can be set separately.

[0128] Optionally, the electronic device 800 may also include a transceiver for receiving and / or transmitting signals. For example, a processor 801 may be used to control the transceiver to receive and / or transmit signals.

[0129] In a specific implementation, the processor 801 in the electronic device 800 executes the computer program or instructions stored in the memory 802 to perform the following operations: Acoustic detection is performed based on acoustic signals during the operation of the battery cell to obtain acoustic detection results; When the acoustic detection result meets the preset triggering conditions, the electrical and thermal parameters of the battery cell are obtained based on the time corresponding to the acoustic signal. Based on the acoustic detection results, the electrical parameters, and the thermal parameters, the valve opening status of the battery cell is detected, and the valve opening detection results are obtained.

[0130] It should be noted that, Figure 8 The specific implementation of each operation in the above-described method implementation can be found in the description of the method implementation, and will not be repeated here.

[0131] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0132] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0133] It should be noted that, for the sake of simplicity, the various embodiments described above are all presented as a series of actions. Those skilled in the art should understand that this application is not limited by the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0134] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0135] The steps of the methods or algorithms described in this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0136] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0137] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0138] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above description is only a specific embodiment of the embodiments of this application and is not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A valve opening detection method, characterized in that, The method includes: Acoustic detection is performed based on acoustic signals during the operation of the battery cell to obtain acoustic detection results; When the acoustic detection result meets the preset triggering conditions, the electrical and thermal parameters of the battery cell are obtained based on the time corresponding to the acoustic signal. Based on the acoustic detection results, the electrical parameters, and the thermal parameters, the valve opening status of the battery cell is detected to obtain the valve opening detection results; The acoustic detection based on acoustic signals during battery cell operation to obtain acoustic detection results includes: Extract the time-domain features of the acoustic signal; When the time-domain features meet the preset alarm conditions, based on the time corresponding to the acoustic signal, the acoustic signal within a predetermined time range before and after the time is extracted to obtain the target acoustic signal. Extract the frequency domain features of the target acoustic signal; Based on the frequency domain characteristics, the confidence level of the cell opening valve is determined; The confidence level and alarm type are used as the acoustic detection results, and the alarm type is determined by the time-domain features and the alarm conditions.

2. The method according to claim 1, characterized in that, The time-domain features include: Root mean square (RMS) energy, peak-to-average power ratio (PAPR), and high-frequency energy; The alarm conditions include: The RMS energy is greater than a first dynamic threshold, and the peak-to-average power ratio is greater than a preset first threshold or a second dynamic threshold; or, The high-frequency energy is greater than the third dynamic threshold. The first dynamic threshold, the second dynamic threshold, and the third dynamic threshold are related to the historical acoustic signals in the first dynamic window, and the first dynamic window is determined by the time.

3. The method according to claim 2, characterized in that, When the RMS energy is greater than the first dynamic threshold and the peak-to-average power ratio is greater than the preset first threshold or the second dynamic threshold, the alarm type is determined to be pulse type. When the high-frequency energy is greater than the third dynamic threshold, the alarm type is determined to be high-frequency. When the rapid rise index is greater than the fourth and fifth dynamic thresholds, and the high-frequency energy is greater than the third dynamic threshold, the alarm type is determined to be a mixed type.

4. The method according to claim 1, characterized in that, The extraction of frequency domain features of the target acoustic signal includes: For each dimension of the Mel-frequency cepstral coefficients (MFCC) of the target acoustic signal, the mean, standard deviation, skewness, kurtosis, quantile, maximum value, and minimum value are calculated to obtain multiple characteristic parameters; Determine the logarithmic RMS energy and the mean centroid of the spectral spectrum of the target acoustic signal; The plurality of characteristic parameters, the logarithmic RMS energy, and the mean centroid of the spectrum are used as the frequency domain features.

5. The method according to claim 1, characterized in that, Determining the confidence level of the cell opening valve based on the frequency domain characteristics includes: The frequency domain features are input into a support vector machine (SVM) classifier to obtain the confidence score. The SVM classifier uses a radial basis function (RBF) kernel.

6. The method according to any one of claims 1-5, characterized in that, The process of detecting the valve opening status of the battery cell based on the acoustic detection results, the electrical parameters, and the thermal parameters, and obtaining the valve opening detection results, includes: If the confidence level in the acoustic test result is within the preset high confidence interval, the valve opening test result is determined to be a confirmed valve opening. If the confidence level is within the preset medium confidence interval, and the alarm type in the acoustic detection result is high-frequency or mixed, the voltage and current characteristics are determined based on the electrical parameters, the temperature characteristics are determined based on the thermal parameters, a comprehensive score is determined based on the confidence level, the voltage characteristics, the current characteristics, and the temperature characteristics, and the valve opening detection result is determined based on the comprehensive score. If the confidence level is within the preset low confidence interval, the valve opening detection result is determined to be a false alarm.

7. A valve opening detection device, characterized in that, The device includes: The detection module is used to perform acoustic detection based on acoustic signals during the operation of the battery cell and obtain acoustic detection results. The acquisition module is used to acquire the electrical and thermal parameters of the battery cell based on the time corresponding to the acoustic signal when the acoustic detection result meets the preset triggering conditions. The determination module is used to detect the valve opening status of the battery cell based on the acoustic detection results, the electrical parameters, and the thermal parameters, and to obtain the valve opening detection result; Specifically, in the aspect of performing acoustic detection based on acoustic signals during the operation of the battery cell to obtain acoustic detection results, the detection module is used for: Extract the time-domain features of the acoustic signal; When the time-domain features meet the preset alarm conditions, based on the time corresponding to the acoustic signal, the acoustic signal within a predetermined time range before and after the time is extracted to obtain the target acoustic signal. Extract the frequency domain features of the target acoustic signal; Based on the frequency domain characteristics, the confidence level of the cell opening valve is determined; The confidence level and alarm type are used as the acoustic detection results, and the alarm type is determined by the time-domain features and the alarm conditions.

8. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, the computer program including program instructions, and the processor being configured to invoke the program instructions to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1-6.

Images