Battery air valve leakage monitoring method and device and storage medium

Through acoustic emission sensors and spectral entropy analysis technology, the problem of inaccurate monitoring of traditional battery thermal runaway early warning systems in complex environments is solved, high-precision identification and early warning of battery air valve leakage is achieved, and the safety performance of the battery system is improved .

CN118961084APending Publication Date: 2024-11-15ANHUI ZHONGKE HAOYIN TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411092292.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Traditional battery thermal runaway early warning systems are difficult to accurately monitor battery air valve leakage in complex working conditions and noisy environments, and there are problems of high cost and inaccurate monitoring.

Method used

The acoustic emission sensor is used to collect the sound signals of the air valve running inside the battery, obtain the spectrum signal through preprocessing, calculate the power spectrum density and perform spectral entropy analysis to achieve high-precision monitoring of air valve leakage.

Benefits of technology

It significantly improves the sensitivity and accuracy of detection, can accurately capture leaked signals in the context of tiny leakage and high noise, reduce safety hazards, improve the overall safety performance of the battery system, and provide quantitative evaluation and intelligent early warning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118961084A_ABST
    Figure CN118961084A_ABST
Patent Text Reader

Abstract

The invention relates to the field of battery monitoring, and discloses a battery air valve leakage monitoring method and device and a storage medium, and the method comprises the steps: employing an acoustic emission sensor to collect a sound signal during the operation of an air valve in a battery, and carrying out the preprocessing, and obtaining a frequency spectrum signal; calculating power spectral density according to the preprocessed signal; performing spectral entropy calculation according to the power spectral density; and performing gas valve leakage monitoring by using the calculated spectrum entropy. The method has the beneficial effects that the accurate identification of the tiny leakage of the battery gas valve is realized through the spectral entropy analysis of the acoustic emission signal. The method combines the steps of signal preprocessing, spectral analysis, spectral entropy calculation, threshold setting and the like, has high sensitivity and reliability, and provides an effective means for safety monitoring of a battery system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of battery monitoring, and in particular to a battery gas valve leakage monitoring method, device and storage medium. Background Art

[0002] Lithium-ion battery energy storage system has become one of the key technologies to support the efficient use of renewable energy and ensure the stable operation of the power grid. However, with the continuous expansion of energy storage scale and the increasing complexity of application scenarios, the safety issues of battery systems have become increasingly prominent, especially fire and explosion accidents caused by battery thermal runaway, which have become an important factor restricting the healthy development of the energy storage industry.

[0003] Lithium-ion batteries may experience thermal runaway under abnormal operating conditions, such as overcharging, overheating, internal short circuit, etc., which is the main source of battery system safety issues. In the early stage of thermal runaway, a large amount of gas generated inside the battery will be released through the safety valve, which is an early and critical physical phenomenon in the thermal runaway process. Therefore, monitoring battery valve leakage has become an important means of preventing and warning battery thermal runaway.

[0004] Traditional battery thermal runaway warning systems mostly rely on single or combined monitoring indicators such as temperature, voltage, and gas concentration. However, these methods have obvious shortcomings when dealing with complex working conditions and noisy environments. For example, in container-type energy storage systems, a large amount of background noise will be generated due to the operation of PCS, air conditioning or cooling equipment. These noises constitute a serious interference to acoustic monitoring, making it difficult for traditional sound-based monitoring methods to effectively distinguish between the acoustic signal of the opening of the battery gas valve related to thermal runaway and the background noise. In addition, traditional monitoring methods also have problems such as environmental interference, monitoring lag, and high cost, making it difficult to issue early warnings in a timely and accurate manner in the early stages of thermal runaway.

[0005] For example, Chinese patent CN202211414561.7, a battery thermal runaway diagnosis method and system based on acoustic signals for an energy storage system, proposes an innovative method and system that uses acoustic signals to diagnose battery thermal runaway in an energy storage system. The following are the core contents and advantages of the invention: Core content: 1. Acoustic signal acquisition and analysis: This method first collects mixed acoustic signals from the battery energy storage system cabin. These signals include exhaust acoustic signals (generated by the exhaust gas discharged by the safety valve during thermal runaway), environmental noise and other noises. The spectral subtraction technique is used to effectively remove environmental noise, making the exhaust acoustic signal clearer and more distinguishable. 2. Exhaust acoustic signal recognition model construction: An exhaust acoustic signal recognition model is constructed through machine learning or deep learning technology. Model training is based on feature extraction, which converts exhaust acoustic signals into feature vectors. These feature vectors are used as training sets. After repeated iterative optimization, a model that can accurately identify exhaust acoustic signals is formed. 3. Feature extraction and classification: Mel frequency cepstral coefficient (MFCC) and other technologies are used to extract features from the denoised mixed sound signal, and the extracted feature vector is input into the recognition model for classification, thereby identifying the exhaust sound signal and judging whether there is a risk of thermal runaway of the battery. 4. System structure: The invention also includes a system architecture consisting of an acquisition unit, a denoising unit, and an identification unit. Each unit works together to realize an automated process from sound signal acquisition to thermal runaway diagnosis.

[0006] In practical applications, this method may encounter the problem of scarcity of negative sample data, which affects the training quality and generalization ability of the model. At the same time, although spectral subtraction is intended to highlight the sound of the valve, in a complex cabin environment, similar spectral noise generated by other equipment may confuse the audience and reduce the accuracy of the warning. Summary of the invention

[0007] The purpose of the present invention is to propose a battery valve leakage monitoring method, device and storage medium to solve the technical problems that traditional sound-based battery monitoring methods are expensive and easily affected by the environment, resulting in inaccurate monitoring.

[0008] The present invention provides a battery gas valve leakage monitoring method, comprising the following steps:

[0009] S1: Use an acoustic emission sensor to collect the sound signal of the gas valve inside the battery when it is running, and pre-process it to obtain a spectrum signal;

[0010] S2: Calculate the power spectral density based on the preprocessed signal;

[0011] S3: Calculate spectral entropy based on power spectral density;

[0012] S4: Use the calculated spectral entropy to monitor valve leakage.

[0013] A storage medium stores instructions and data for implementing a battery gas valve leakage monitoring method.

[0014] A battery gas valve leakage monitoring device comprises: a processor and a storage medium; the processor loads and executes instructions and data in the storage medium to implement a battery gas valve leakage monitoring method.

[0015] The beneficial effects provided by the present invention are:

[0016] 1. Innovative monitoring technology: This method innovatively combines acoustic emission signals with spectral entropy analysis to conduct in-depth analysis of weak acoustic signals of battery valve leakage. By capturing the elastic wave characteristics generated by material stress, high-precision identification of leakage signals is achieved, filling the gap in traditional monitoring technology in the detection of tiny leaks.

[0017] 2. Improve detection efficiency: Significantly enhance the sensitivity and accuracy of detection, and accurately capture leakage signals even in the presence of tiny leaks and high noise, achieve early warning, reduce safety hazards caused by leakage, and improve the overall safety performance of the battery system.

[0018] 3. Real-time monitoring and wide adaptability: It has real-time monitoring capabilities, adapts to various battery systems and complex environmental conditions, and ensures immediate response to valve leaks. The flexibility and versatility of this method enable it to maintain efficient monitoring in a variety of application scenarios.

[0019] 4. Optimize the false alarm and missed alarm rate: Through the sophisticated spectral entropy analysis algorithm, the leakage signal is effectively distinguished from the environmental noise, which significantly reduces the false alarm and missed alarm events and improves the reliability and accuracy of the monitoring system.

[0020] 5. Quantitative evaluation and intelligent early warning: Provide quantitative evaluation of leakage events, which can not only monitor in real time, but also evaluate the severity of leakage based on the results of spectral entropy analysis, provide a scientific basis for maintenance decision-making, and realize intelligent early warning and efficient maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic flow chart of the method of the present invention;

[0022] Figure 2 It is a working schematic diagram of the hardware device of the present invention. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0024] Before formally describing the present invention, the scheme of the present invention is first generally described for easy understanding.

[0025] Please refer to Figure 1 , Figure 1 It is a schematic flow diagram of the method of the present invention;

[0026] The present invention provides a battery gas valve leakage monitoring method, comprising the following steps:

[0027] S1: Use an acoustic emission sensor to collect the sound signal of the gas valve inside the battery when it is running, and pre-process it to obtain a spectrum signal;

[0028] It should be noted that step S1 is specifically as follows:

[0029] S11, recording the acoustic emission signal by using an equal-interval sampling method to obtain a discrete time series;

[0030] As an embodiment, the present invention adopts an equal-interval time sampling method to record the acoustic emission signal to obtain a discrete time series x[n], where n is the sampling point number.

[0031] S12, filtering the discrete time series for noise to obtain a filtered signal;

[0032] As an embodiment, the present invention uses a digital filter (such as a low-pass filter) to filter the original signal to remove high-frequency noise, and obtains a filtered signal.

[0033] S13, performing fast Fourier transform on the filtered signal to obtain a spectrum signal.

[0034] As an embodiment, the present invention performs FFT conversion on the filtered signal, converting it from the time domain to the frequency domain to obtain a complex spectrum X[k]. The formula of FFT is:

[0035]

[0036] where k is the frequency index.

[0037] S2: Calculate the power spectral density based on the preprocessed signal;

[0038] It should be noted that step S2 is specifically as follows:

[0039] S21, performing modulus square calculation on the frequency spectrum signal to obtain a power spectrum;

[0040] As an embodiment, the present invention calculates the square of the modulus of the complex spectrum to obtain the power spectrum P[k], that is:

[0041] P[k]=|X[k]| 2 (2)

[0042] S22, averaging and normalizing the power spectrum to obtain a power spectrum density.

[0043] As an embodiment, the present invention uses the periodogram method to estimate the power spectral density (PSD) to eliminate the influence of frequency resolution. It is usually necessary to apply a window function w[n] and perform averaging to obtain a normalized PSD:

[0044]

[0045] The window function can be a rectangular window, a Hanning window, a Hamming window, or a Gaussian window. When the periodogram method is used to estimate PSD, a window function w[n] is usually required to reduce spectrum leakage. The window function is a function applied to the time series of a signal to reduce the mutations at both ends of the signal, thereby reducing spectrum leakage. Preferably, the Gaussian window is very effective in reducing spectrum leakage.

[0046] Gaussian Window is a window function with a Gaussian shape, and its mathematical expression is:

[0047]

[0048] σ is the standard deviation of the Gaussian window and controls the width of the window.

[0049] S3: Calculate spectral entropy based on power spectral density;

[0050] It should be noted that step S3 is specifically as follows:

[0051] S31, the power spectrum density is used as the energy probability distribution p of each frequency component k ;

[0052] As an embodiment, the present invention regards the power spectrum density as the energy probability distribution of each frequency component, and the calculation formula is:

[0053]

[0054] S32. Calculate the spectral entropy H according to the probability distribution, as follows:

[0055] As an embodiment, the spectral entropy H is calculated according to the information entropy formula to measure the uncertainty of the frequency distribution. The calculation formula of the spectral entropy is:

[0056]

[0057] S4: Use the calculated spectral entropy to monitor valve leakage.

[0058] It should be noted that step S4 is specifically as follows: comparing the spectral entropy of the current signal with a preset reference spectral entropy, and if the difference between the two exceeds a preset value, it is determined that the battery gas valve is leaking.

[0059] As an embodiment, the specific operations in the present invention are as follows:

[0060] ①Determination of the reference entropy value: Determine the reference spectral entropy value H under normal working conditions through experiments or historical data. base .

[0061] ② Leakage judgment criteria: Real-time calculation of the spectral entropy H of the current signal realtime , and compare it with the baseline entropy value H base If the difference exceeds the preset threshold ΔH, it is determined to be a leak. The condition for leak alarm can be expressed as: leak alarm = (H realtime -H base )>ΔH.

[0062] See also Figure 2 , Figure 2 4 is a schematic diagram of the working of the hardware device of an embodiment of the present invention, wherein the hardware device specifically comprises: a battery valve leakage monitoring device 401, a processor 402 and a storage medium 403.

[0063] A battery gas valve leakage monitoring device 401: The battery gas valve leakage monitoring device 401 implements the battery gas valve leakage monitoring method.

[0064] Processor 402: The processor 402 loads and executes the instructions and data in the storage medium 403 to implement the battery gas valve leakage monitoring method.

[0065] Storage medium 403: The storage medium 403 stores instructions and data; the storage medium 403 is used to implement the battery gas valve leakage monitoring method.

[0066] The beneficial effects of the present invention are:

[0067] 1. Innovative monitoring technology: This method innovatively combines acoustic emission signals with spectral entropy analysis to conduct in-depth analysis of weak acoustic signals of battery valve leakage. By capturing the elastic wave characteristics generated by material stress, high-precision identification of leakage signals is achieved, filling the gap in traditional monitoring technology in the detection of tiny leaks.

[0068] 2. Improve detection efficiency: Significantly enhance the sensitivity and accuracy of detection, and accurately capture leakage signals even in the presence of tiny leaks and high noise, achieve early warning, reduce safety hazards caused by leakage, and improve the overall safety performance of the battery system.

[0069] 3. Real-time monitoring and wide adaptability: It has real-time monitoring capabilities, adapts to various battery systems and complex environmental conditions, and ensures immediate response to valve leaks. The flexibility and versatility of this method enable it to maintain efficient monitoring in a variety of application scenarios.

[0070] 4. Optimize the false alarm and missed alarm rate: Through the sophisticated spectral entropy analysis algorithm, the leakage signal is effectively distinguished from the environmental noise, which significantly reduces the false alarm and missed alarm events and improves the reliability and accuracy of the monitoring system.

[0071] 5. Quantitative evaluation and intelligent early warning: Provide quantitative evaluation of leakage events, which can not only monitor in real time, but also evaluate the severity of leakage based on the results of spectral entropy analysis, provide a scientific basis for maintenance decision-making, and realize intelligent early warning and efficient maintenance management.

[0072] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A battery valve leakage monitoring method, characterized in that: The method comprises the following steps: S1: Use an acoustic emission sensor to collect the sound signal of the gas valve inside the battery when it is running, and pre-process it to obtain a spectrum signal; S2: Calculate the power spectral density based on the preprocessed signal; S3: Calculate spectral entropy based on power spectral density; S4: Use the calculated spectral entropy to monitor valve leakage.

2. A battery gas valve leakage monitoring method as claimed in claim 1, characterized in that: Step S1 is specifically as follows: S11, recording the acoustic emission signal by using an equal-interval sampling method to obtain a discrete time series; S12, filtering the discrete time series for noise to obtain a filtered signal; S13, performing fast Fourier transform on the filtered signal to obtain a spectrum signal.

3. A battery gas valve leakage monitoring method as claimed in claim 1, characterized in that: Step S2 is specifically as follows: S21, performing modulus square calculation on the frequency spectrum signal to obtain a power spectrum; S22, averaging and normalizing the power spectrum to obtain a power spectrum density.

4. A battery gas valve leakage monitoring method as claimed in claim 3, characterized in that: In step S22, a window function is applied to perform averaging processing, and the window function includes a rectangular window, a Hanning window, a Hamming window and a Gaussian window.

5. A battery gas valve leakage monitoring method as claimed in claim 1, characterized in that: Step S3 is as follows: S31, the power spectrum density is used as the energy probability distribution p of each frequency component k ; S32. Calculate the spectral entropy H according to the probability distribution, as follows:

6. A battery gas valve leakage monitoring method as claimed in claim 1, characterized in that: Step S4 is specifically as follows: comparing the spectral entropy of the current signal with a preset reference spectral entropy, and if the difference between the two exceeds a preset value, it is determined that the battery gas valve is leaking.

7. A storage medium, characterized in that: The storage medium stores instructions and data for implementing a battery gas valve leakage monitoring method as described in any one of claims 1 to 6.

8. A battery valve leakage monitoring device, characterized in that: include: Processor and storage medium; the processor loads and executes instructions and data in the storage medium to implement a battery gas valve leakage monitoring method as described in any one of claims 1 to 6.

Citation Information

Cited By

  • Pipeline leakage detection method and device applied to high-pressure heater

    CN120760077A

  • Method for asserting a risk of a thermal runaway in a battery pack

    WO2026187234A1