Power-off protection system and method for vehicle running

Abstract

The invention discloses a power-off protection system and method for vehicle driving, and belongs to the technical field of power-off protection systems.A central processing unit obtains temperature change establishing curve change state monitoring data, gas concentration establishing curve change state monitoring and a flame analysis module judges whether flames or flickering sparks exist or not; when the temperature is suddenly changed, spark data of flame or flickering judged by the flame analysis module is synchronously obtained for verification, if the spark data is verified, it is determined that the thermal runaway state is not the fire state, and the information is fed back to the alarm module for cooling treatment; and if the spark data is verified, it is determined that air is not circulated and gas generated by materials around the battery at high temperature is gathered, ventilation and cooling treatment is carried out, and the flame analysis module is used for determining that the flame is the flame.

Description

Technical Field

[0001] The present invention relates to a power-off protection system, in particular to a power-off protection system and method for vehicle driving, belonging to the technical field of power-off protection systems. Background Art

[0002] In the prior art, the power-off protection system for vehicle driving, when monitoring and protecting against fire, is disclosed in the publication number CN117124922A, which discloses a power-off protection device for a rechargeable battery of a new energy vehicle. This technical solution provides battery status monitoring, temperature monitoring and power-off protection, but there are still some technical problems: 1. It is impossible to distinguish whether it is a real misfire or a false misfire. If it is a false misfire, it will obviously affect driving; 2. It is impossible to predict and analyze the battery status and the detection is not comprehensive, so the power-off protection system is not intelligent enough; Therefore, a vehicle power-off protection system and method are designed to solve the above problems. Summary of the invention

[0003] The main purpose of the present invention is to provide a power-off protection system and method for vehicle driving.

[0004] The purpose of the present invention can be achieved by adopting the following technical solutions: A power-off protection system for vehicle driving includes a flame monitoring sensor for video monitoring of flames generated by a battery; Gas monitoring sensor, used to collect gas generated by the battery; Temperature monitoring sensor, used to collect temperature changes of the battery; The flame analysis module is used to analyze and determine the flames monitored by the video; Gas concentration analysis module, used to establish curve change status monitoring of collected gas concentration; Temperature change analysis module, used to analyze the collected temperature changes and establish curve change status monitoring; The central processing module is used to obtain the analysis data of the flame analysis module, the gas concentration analysis module and the temperature change analysis module and make a judgment; A power-off module, used to obtain the power-off information of the central processing module to perform power-off processing on the battery; An alarm module is used to obtain the alarm information from the central processing module and feed it back to the on-board processor for alarm processing; The fire extinguishing module is used to obtain the fire extinguishing information of the central processing module and control the fire extinguishing mechanism arranged near the battery to perform fire extinguishing processing.

[0005] Preferably, the method of using the flame analysis module to determine whether it is a flame or a flickering spark is as follows: S1: Use the flame monitoring sensor to monitor and shoot the battery for a long time and transmit the captured video stream to the flame analysis module; S2: De-noise, contrast enhancement, and color correction of the video stream; S3: Identify the flame area using image processing algorithms; S4: Continuously monitor the dynamic changes of the flame; S5: Compare and analyze the flame area identified in S3 with historical data; S6: When the historical data comparison algorithm determines that an area is a spark, it is transmitted to the central processor, and the alarm module alarm command is sent by the central processor to the vehicle processor for alarm processing; S7: When the historical data comparison algorithm determines that an area is a fire, it is transmitted to the central processing unit, and the central processing unit sends a fire extinguishing instruction to the fire extinguishing module for fire extinguishing.

[0006] Preferably, the image processing algorithm used in S3 is a color segmentation algorithm and specifically includes the following steps: S11: In the RGB color space, a corresponding threshold is set according to the color characteristics of the flame to segment the flame area; S12: The Sobel operator is used with two 3x3 kernels to calculate the horizontal and vertical gradients of the image respectively. The edge of the image is obtained by combining these two gradients. S13: smoothing the image by using a median filter, a Gaussian filter or using morphological operations; S14: Use connected domain analysis to identify edge regions in the image and merge similar regions; S15: Use edge enhancement filter or edge enhancement algorithm to highlight edge areas; S16: According to the characteristics of the image, a global adaptive threshold is selected to perform a binarization process on the edge; S17: Extract features from the binarized edges to obtain the flame area.

[0007] Preferably, the comparative analysis of the flame characteristics extracted in step S5 with the historical data comprises the following steps: S21: Extract features from the identified flame area using color, shape, texture, motion, and spectral feature extraction methods; S22: comparing the features extracted from the flame region in S21 with the features of the historical flame image by calculating a similarity index, where features with higher similarity are more likely to represent similar flame states; S23: classifying or predicting the new flame state using a classification algorithm according to the matching result; S24: Based on the results of the comparative analysis, the historical flame dataset is updated.

[0008] Preferably, in step S22, the similarity index is implemented using the Euclidean distance algorithm. For two points P and Q in the n-dimensional space, the calculation formula of the Euclidean distance is: ; The sum of the squares of the coordinate differences of the two points in each dimension is calculated, and the Euclidean distance between the two points is obtained by taking the square root ; in, , , ..., and , , ..., are the coordinate values ​​of points P and Q in each dimension respectively.

[0009] Preferably, the classification algorithm used in step S23 is any one of a decision tree, a random forest, and a support vector machine.

[0010] Preferably, the gas concentration establishment curve change state monitoring method is as follows: S31: The gas monitoring sensor continuously collects the data of the change of gas concentration near the battery and feeds it back to the gas concentration analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted gas concentration data in a data storage device, and plotting the stored data as a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it detects whether the gas concentration exceeds the safety range. If it exceeds the safety range, it will be fed back to the central processor for processing.

[0011] Preferably, the temperature change establishment curve change state monitoring method is as follows: S31: The temperature sensor continuously collects temperature change data near the battery and feeds it back to the temperature change analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted temperature data in a data storage device, and plotting the stored data into a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it is detected whether the temperature exceeds the safe range. If it exceeds the range, it will be fed back to the central processor for processing.

[0012] Beneficial technical effects of the present invention: The present invention provides a power-off protection system and method for vehicle driving. The present invention obtains temperature change through a central processor to establish curve change state monitoring data, gas concentration to establish curve change state monitoring, and flame analysis module determines whether it is a flame or a flickering spark for determination. When a temperature mutation is obtained, the flame analysis module determines whether it is a flame or a flickering spark data for verification at the same time. If it is verified to be spark data, it is determined to be a thermal runaway state rather than a fire state, and the information is fed back to the alarm module for cooling treatment. When a concentration mutation is obtained, the flame analysis module determines whether it is a flame or a flickering spark data for verification at the same time. If it is verified to be spark data, it is determined to be caused by air stagnation and gas accumulation generated by materials around the battery at high temperature, and ventilation and cooling treatment are performed. If the flame analysis module determines that it is a flame, the information is fed back to the fire extinguishing module and the power-off module to perform power-off and fire extinguishing treatment at the same time, thereby avoiding the problem of false fire and realizing multi-dimensional intelligent detection and analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 The system diagram is a preferred embodiment of a vehicle power-off protection system and method according to the present invention. DETAILED DESCRIPTION

[0014] In order to make the technical solution of the present invention more clear and specific to those skilled in the art, the present invention is further described in detail below in conjunction with embodiments and drawings, but the implementation manner of the present invention is not limited thereto.

[0015] Embodiment 1 like Figure 1 As shown, a power-off protection system and method for vehicle driving include a flame monitoring sensor for video monitoring of the flame generated by the battery; Gas monitoring sensor, used to collect gas generated by the battery; Temperature monitoring sensor, used to collect temperature changes of the battery; The flame analysis module is used to analyze and determine the flames monitored by the video; Gas concentration analysis module, used to establish curve change status monitoring of collected gas concentration; Temperature change analysis module, used to analyze the collected temperature changes and establish curve change status monitoring; The central processing module is used to obtain the analysis data of the flame analysis module, the gas concentration analysis module and the temperature change analysis module and make a judgment; A power-off module, used to obtain the power-off information of the central processing module to perform power-off processing on the battery; An alarm module is used to obtain the alarm information from the central processing module and feed it back to the on-board processor for alarm processing; The fire extinguishing module is used to obtain the fire extinguishing information of the central processing module and control the fire extinguishing mechanism arranged near the battery to perform fire extinguishing processing.

[0016] In this embodiment, the method of using the flame analysis module to determine whether it is a flame or a flickering spark is as follows: S1: Use the flame monitoring sensor to monitor and shoot the battery for a long time and transmit the captured video stream to the flame analysis module; S2: De-noise, contrast enhancement, and color correction of the video stream; S3: Identify the flame area using image processing algorithms; S4: Continuously monitor the dynamic changes of the flame; S5: Compare and analyze the flame area identified in S3 with historical data; S6: When the historical data comparison algorithm determines that an area is a spark, it is transmitted to the central processor, and the alarm module alarm command is sent by the central processor to the vehicle processor for alarm processing; S7: When the historical data comparison algorithm determines that an area is a fire, it is transmitted to the central processing unit, and the central processing unit sends a fire extinguishing instruction to the fire extinguishing module for fire extinguishing.

[0017] In this embodiment, the image processing algorithm used in S3 is a color segmentation algorithm which specifically includes the following steps: S11: In the RGB color space, a corresponding threshold is set according to the color characteristics of the flame to segment the flame area; S12: The Sobel operator is used with two 3x3 kernels to calculate the horizontal and vertical gradients of the image respectively. The edge of the image is obtained by combining these two gradients. S13: smoothing the image by using a median filter, a Gaussian filter or using morphological operations; S14: Use connected domain analysis to identify edge regions in the image and merge similar regions; S15: Use edge enhancement filter or edge enhancement algorithm to highlight edge areas; S16: According to the characteristics of the image, a global adaptive threshold is selected to perform a binarization process on the edge; S17: Extract features from the binarized edges to obtain the flame area.

[0018] In this embodiment, the comparative analysis of the flame characteristics extracted in step S5 and the historical data includes the following steps: S21: Extract features from the identified flame area using color, shape, texture, motion, and spectral feature extraction methods; S22: comparing the features extracted from the flame region in S21 with the features of the historical flame image by calculating a similarity index, where features with higher similarity are more likely to represent similar flame states; S23: classifying or predicting the new flame state using a classification algorithm according to the matching result; S24: Based on the results of the comparative analysis, the historical flame dataset is updated.

[0019] In this embodiment, the similarity index in step S22 is implemented using the Euclidean distance algorithm. For two points P and Q in the n-dimensional space, the calculation formula of the Euclidean distance is: ; The sum of the squares of the coordinate differences of the two points in each dimension is calculated, and the Euclidean distance between the two points is obtained by taking the square root ; in, , , ..., and , , ..., are the coordinate values ​​of points P and Q in each dimension respectively.

[0020] In this embodiment, the classification algorithm used in step S23 is any one of a decision tree, a random forest, and a support vector machine.

[0021] In this embodiment, the gas concentration establishment curve change state monitoring method is as follows: S31: The gas monitoring sensor continuously collects the data of the change of gas concentration near the battery and feeds it back to the gas concentration analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted gas concentration data in a data storage device, and plotting the stored data as a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it detects whether the gas concentration exceeds the safety range. If it exceeds the safety range, it will be fed back to the central processor for processing.

[0022] In this embodiment, the temperature change establishment curve change state monitoring method is as follows: S31: The temperature sensor continuously collects temperature change data near the battery and feeds it back to the temperature change analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted temperature data in a data storage device, and plotting the stored data into a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it is detected whether the temperature exceeds the safe range. If it exceeds the range, it will be fed back to the central processor for processing.

[0023] A power-off protection method for a vehicle in motion, wherein a central processing unit obtains temperature change to establish curve change state monitoring data, gas concentration to establish curve change state monitoring, and a flame analysis module determines whether it is a flame or a flickering spark, and then performs the following protection method: S41: when a temperature mutation is obtained, the flame analysis module simultaneously obtains the flame or flickering spark data for verification; S42: If the spark data is verified, it is determined to be a thermal runaway state rather than a fire state, and the information is fed back to the alarm module for temperature reduction processing; S43: when a concentration mutation is obtained, the flame analysis module simultaneously obtains the spark data determined as flame or flickering for verification; S44: If the spark data is verified, it is determined that the fire is caused by the lack of air circulation and the accumulation of gas generated by the materials around the battery at high temperature, and ventilation and cooling treatment are carried out; S45: If the flame analysis module determines that there is a flame, the information is fed back to the fire extinguishing module and the power off module to perform power off and fire extinguishing processing at the same time.

[0024] Embodiment 2 like Figure 1 As shown, a power-off protection system and method for vehicle driving include a flame monitoring sensor for video monitoring of the flame generated by the battery; Gas monitoring sensor, used to collect gas generated by the battery; Temperature monitoring sensor, used to collect temperature changes of the battery; The flame analysis module is used to analyze and determine the flames monitored by the video; Gas concentration analysis module, used to establish curve change status monitoring of collected gas concentration; Temperature change analysis module, used to analyze the collected temperature changes and establish curve change status monitoring; The central processing module is used to obtain the analysis data of the flame analysis module, the gas concentration analysis module and the temperature change analysis module and make a judgment; A power-off module, used to obtain the power-off information of the central processing module to perform power-off processing on the battery; An alarm module is used to obtain the alarm information from the central processing module and feed it back to the on-board processor for alarm processing; The fire extinguishing module is used to obtain the fire extinguishing information of the central processing module and control the fire extinguishing mechanism arranged near the battery to perform fire extinguishing processing.

[0025] In this embodiment, the method of using the flame analysis module to determine whether it is a flame or a flickering spark is as follows: S1: Use the flame monitoring sensor to monitor and shoot the battery for a long time and transmit the captured video stream to the flame analysis module; S2: De-noise, contrast enhancement, and color correction of the video stream; S3: Identify the flame area using image processing algorithms; S4: Continuously monitor the dynamic changes of the flame; S5: Compare and analyze the flame area identified in S3 with historical data; S6: When the historical data comparison algorithm determines that an area is a spark, it is transmitted to the central processor, and the alarm module alarm command is sent by the central processor to the vehicle processor for alarm processing; S7: When the historical data comparison algorithm determines that an area is a fire, it is transmitted to the central processing unit, and the central processing unit sends a fire extinguishing instruction to the fire extinguishing module for fire extinguishing.

[0026] In this embodiment, the image processing algorithm used in S3 is a color segmentation algorithm which specifically includes the following steps: S11: In the RGB color space, a corresponding threshold is set according to the color characteristics of the flame to segment the flame area; S12: The Sobel operator is used with two 3x3 kernels to calculate the horizontal and vertical gradients of the image respectively. The edge of the image is obtained by combining these two gradients. S13: smoothing the image by using a median filter, a Gaussian filter or using morphological operations; S14: Use connected domain analysis to identify edge regions in the image and merge similar regions; S15: Use edge enhancement filter or edge enhancement algorithm to highlight edge areas; S16: According to the characteristics of the image, a global adaptive threshold is selected to perform a binarization process on the edge; S17: Extract features from the binarized edges to obtain the flame area.

[0027] In this embodiment, the comparative analysis of the flame characteristics extracted in step S5 and the historical data includes the following steps: S21: Extract features from the identified flame area using color, shape, texture, motion, and spectral feature extraction methods; S22: comparing the features extracted from the flame region in S21 with the features of the historical flame image by calculating a similarity index, where features with higher similarity are more likely to represent similar flame states; S23: classifying or predicting the new flame state using a classification algorithm according to the matching result; S24: Based on the results of the comparative analysis, the historical flame dataset is updated.

[0028] In this embodiment, the similarity index in step S22 is implemented using a cosine similarity algorithm, and the value of the cosine similarity is between -1 and 1, where: 1 means that the two vectors are exactly the same (i.e., they have the same direction and magnitude); 0 means the two vectors are orthogonal (i.e. completely different); -1 means that the two vectors are completely opposite (i.e., in opposite directions); and , their dot product for: = + +...+ ; The magnitude of vector A for: ; The magnitude of vector B for: ; Cosine similarity measures the directional similarity of two vectors by calculating the ratio of the dot product of two vectors to the product of their magnitudes.

[0029] Its value is between -1 and 1. The closer the value is to 1, the closer the directions of the two vectors are. The closer the value is to -1, the more opposite the directions of the two vectors are. When the value is , it means that the two vectors are perpendicular.

[0030] In this embodiment, the classification algorithm used in step S23 is any one of a decision tree, a random forest, and a support vector machine.

[0031] In this embodiment, the gas concentration establishment curve change state monitoring method is as follows: S31: The gas monitoring sensor continuously collects the data of the change of gas concentration near the battery and feeds it back to the gas concentration analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted gas concentration data in a data storage device, and plotting the stored data as a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it detects whether the gas concentration exceeds the safety range. If it exceeds the safety range, it will be fed back to the central processor for processing.

[0032] In this embodiment, the temperature change establishment curve change state monitoring method is as follows: S31: The temperature sensor continuously collects temperature change data near the battery and feeds it back to the temperature change analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted temperature data in a data storage device, and plotting the stored data into a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it is detected whether the temperature exceeds the safe range. If it exceeds the range, it will be fed back to the central processor for processing.

[0033] A power-off protection method for a vehicle in motion, wherein a central processing unit obtains temperature change to establish curve change state monitoring data, gas concentration to establish curve change state monitoring, and a flame analysis module determines whether it is a flame or a flickering spark, and then performs the following protection method: S41: when a temperature mutation is obtained, the flame analysis module simultaneously obtains the flame or flickering spark data for verification; S42: If the spark data is verified, it is determined to be a thermal runaway state rather than a fire state, and the information is fed back to the alarm module for temperature reduction processing; S43: when a concentration mutation is obtained, the flame analysis module simultaneously obtains the spark data determined as flame or flickering for verification; S44: If the spark data is verified, it is determined that the fire is caused by the lack of air circulation and the accumulation of gas generated by the materials around the battery at high temperature, and ventilation and cooling treatment are carried out; S45: If the flame analysis module determines that there is a flame, the information is fed back to the fire extinguishing module and the power off module to perform power off and fire extinguishing processing at the same time.

[0034] Embodiment 3 like Figure 1 As shown, a power-off protection system and method for vehicle driving include a flame monitoring sensor for video monitoring of the flame generated by the battery; Gas monitoring sensor, used to collect gas generated by the battery; Temperature monitoring sensor, used to collect temperature changes of the battery; The flame analysis module is used to analyze and determine the flames monitored by the video; Gas concentration analysis module, used to establish curve change status monitoring of collected gas concentration; Temperature change analysis module, used to analyze the collected temperature changes and establish curve change status monitoring; The central processing module is used to obtain the analysis data of the flame analysis module, the gas concentration analysis module and the temperature change analysis module and make a judgment; A power-off module, used to obtain the power-off information of the central processing module to perform power-off processing on the battery; An alarm module is used to obtain the alarm information from the central processing module and feed it back to the on-board processor for alarm processing; The fire extinguishing module is used to obtain the fire extinguishing information of the central processing module and control the fire extinguishing mechanism arranged near the battery to perform fire extinguishing processing.

[0035] In this embodiment, the method of using the flame analysis module to determine whether it is a flame or a flickering spark is as follows: S1: Use the flame monitoring sensor to monitor and shoot the battery for a long time and transmit the captured video stream to the flame analysis module; S2: De-noise, contrast enhancement, and color correction of the video stream; S3: Identify the flame area using image processing algorithms; S4: Continuously monitor the dynamic changes of the flame; S5: Compare and analyze the flame area identified in S3 with historical data; S6: When the historical data comparison algorithm determines that an area is a spark, it is transmitted to the central processor, and the alarm module alarm command is sent by the central processor to the vehicle processor for alarm processing; S7: When the historical data comparison algorithm determines that an area is a fire, it is transmitted to the central processing unit, and the central processing unit sends a fire extinguishing instruction to the fire extinguishing module for fire extinguishing.

[0036] In this embodiment, the image processing algorithm used in S3 is a color segmentation algorithm which specifically includes the following steps: S11: In the RGB color space, a corresponding threshold is set according to the color characteristics of the flame to segment the flame area; S12: The Sobel operator is used with two 3x3 kernels to calculate the horizontal and vertical gradients of the image respectively. The edge of the image is obtained by combining these two gradients. S13: smoothing the image by using a median filter, a Gaussian filter or using morphological operations; S14: Use connected domain analysis to identify edge regions in the image and merge similar regions; S15: Use edge enhancement filter or edge enhancement algorithm to highlight edge areas; S16: According to the characteristics of the image, a global adaptive threshold is selected to perform a binarization process on the edge; S17: Extract features from the binarized edges to obtain the flame area.

[0037] In this embodiment, the comparative analysis of the flame characteristics extracted in step S5 and the historical data includes the following steps: S21: Extract features from the identified flame area using color, shape, texture, motion, and spectral feature extraction methods; S22: comparing the features extracted from the flame region in S21 with the features of the historical flame image by calculating a similarity index, where features with higher similarity are more likely to represent similar flame states; S23: classifying or predicting the new flame state using a classification algorithm according to the matching result; S24: Based on the results of the comparative analysis, the historical flame dataset is updated.

[0038] In this embodiment, the similarity index in step S22 uses the Pearson correlation coefficient; Calculated based on the covariance of two variables and their respective variances, and its value is between -1 and 1: When ρ=1, it means that the two variables are completely positively correlated.

[0039] When ρ=-1, it means that the two variables are completely negatively correlated.

[0040] When ρ = 0, it means there is no linear relationship between the two variables.

[0041] The calculation formula of Pearson correlation coefficient is: ; in, and are the i-th observation values ​​of the two variables, and are the means of the two variables, respectively, and n is the number of observations; The value of the Pearson correlation coefficient is between -1 and 1. When 1, it means that the two variables are completely positively correlated; when When -1, it means that the two variables are completely negatively correlated.

[0042] In this embodiment, the classification algorithm used in step S23 is any one of a decision tree, a random forest, and a support vector machine.

[0043] In this embodiment, the gas concentration establishment curve change state monitoring method is as follows: S31: The gas monitoring sensor continuously collects the data of the change of gas concentration near the battery and feeds it back to the gas concentration analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted gas concentration data in a data storage device, and plotting the stored data as a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it detects whether the gas concentration exceeds the safety range. If it exceeds the safety range, it will be fed back to the central processor for processing.

[0044] In this embodiment, the temperature change establishment curve change state monitoring method is as follows: S31: The temperature sensor continuously collects temperature change data near the battery and feeds it back to the temperature change analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted temperature data in a data storage device, and plotting the stored data into a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it is detected whether the temperature exceeds the safe range. If it exceeds the range, it will be fed back to the central processor for processing.

[0045] A power-off protection method for a vehicle in motion, wherein a central processing unit obtains temperature change to establish curve change state monitoring data, gas concentration to establish curve change state monitoring, and a flame analysis module determines whether it is a flame or a flickering spark, and then performs the following protection method: S41: when a temperature mutation is obtained, the flame analysis module simultaneously obtains the flame or flickering spark data for verification; S42: If the spark data is verified, it is determined to be a thermal runaway state rather than a fire state, and the information is fed back to the alarm module for temperature reduction processing; S43: when a concentration mutation is obtained, the flame analysis module simultaneously obtains the spark data determined as flame or flickering for verification; S44: If the spark data is verified, it is determined that the fire is caused by the lack of air circulation and the accumulation of gas generated by the materials around the battery at high temperature, and ventilation and cooling treatment are carried out; S45: If the flame analysis module determines that there is a flame, the information is fed back to the fire extinguishing module and the power off module to perform power off and fire extinguishing processing at the same time.

[0046] The above description is only a further embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and concepts of the present invention within the scope disclosed by the present invention, which belong to the protection scope of the present invention.

Claims

1. A power-off protection system for a vehicle, characterized in that: Includes flame monitoring sensor for video monitoring of flames generated by the battery; Gas monitoring sensor, used to collect gas generated by the battery; Temperature monitoring sensor, used to collect temperature changes of the battery; The flame analysis module is used to analyze and determine the flames monitored by the video; Gas concentration analysis module, used to establish curve change status monitoring of collected gas concentration; Temperature change analysis module, used to analyze the collected temperature changes and establish curve change status monitoring; The central processing module is used to obtain the analysis data of the flame analysis module, the gas concentration analysis module and the temperature change analysis module and make a judgment; A power-off module, used to obtain the power-off information of the central processing module to perform power-off processing on the battery; An alarm module is used to obtain the alarm information from the central processing module and feed it back to the on-board processor for alarm processing; The fire extinguishing module is used to obtain the fire extinguishing information of the central processing module and control the fire extinguishing mechanism arranged near the battery to perform fire extinguishing processing.

2. A vehicle power-off protection system according to claim 1, characterized in that: The method of using the flame analysis module to determine whether it is a flame or a flickering spark is as follows: S1: Use the flame monitoring sensor to monitor and shoot the battery for a long time and transmit the captured video stream to the flame analysis module; S2: De-noise, contrast enhancement, and color correction of the video stream; S3: Identify the flame area using image processing algorithms; S4: Continuously monitor the dynamic changes of the flame; S5: Compare and analyze the flame area identified in S3 with historical data; S6: When the historical data comparison algorithm determines that an area is a spark, it is transmitted to the central processor, and the alarm module alarm command is sent by the central processor to the vehicle processor for alarm processing; S7: When the historical data comparison algorithm determines that an area is a fire, it is transmitted to the central processing unit, and the central processing unit sends a fire extinguishing instruction to the fire extinguishing module for fire extinguishing.

3. A vehicle power-off protection system according to claim 2, characterized in that: The image processing algorithm used in S3 is a color segmentation algorithm, which specifically includes the following steps: S11: In the RGB color space, a corresponding threshold is set according to the color characteristics of the flame to segment the flame area; S12: The Sobel operator is used with two 3x3 kernels to calculate the horizontal and vertical gradients of the image respectively. The edge of the image is obtained by combining these two gradients. S13: smoothing the image by using a median filter, a Gaussian filter or using morphological operations; S14: Use connected domain analysis to identify edge regions in the image and merge similar regions; S15: Use edge enhancement filter or edge enhancement algorithm to highlight edge areas; S16: According to the characteristics of the image, a global adaptive threshold is selected to perform a binarization process on the edge; S17: Extract features from the binarized edges to obtain the flame area.

4. A vehicle power-off protection system according to claim 3, characterized in that: The flame characteristics extracted in step S5 are compared and analyzed with the historical data, including the following steps: S21: Extract features from the identified flame area using color, shape, texture, motion, and spectral feature extraction methods; S22: comparing the features extracted from the flame region in S21 with the features of the historical flame image by calculating a similarity index, where features with higher similarity are more likely to represent similar flame states; S23: classifying or predicting the new flame state using a classification algorithm according to the matching result; S24: Based on the results of the comparative analysis, the historical flame dataset is updated.

5. A vehicle power-off protection system according to claim 4, characterized in that: In step S22, the similarity index is implemented using the Euclidean distance algorithm. For two points P and Q in the n-dimensional space, the calculation formula of the Euclidean distance is: ； The sum of the squares of the coordinate differences of the two points in each dimension is calculated, and the Euclidean distance between the two points is obtained by taking the square root ; in, , , ..., and , , ..., are the coordinate values ​​of points P and Q in each dimension respectively.

6. A vehicle power-off protection system according to claim 4, characterized in that: The classification algorithm used in step S23 is any one of decision tree, random forest, and support vector machine.

7. A vehicle power-off protection system according to claim 1, characterized in that: The method for monitoring the change status of the gas concentration curve is as follows: S31: The gas monitoring sensor continuously collects the data of the change of gas concentration near the battery and feeds it back to the gas concentration analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted gas concentration data in a data storage device, and plotting the stored data as a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it detects whether the gas concentration exceeds the safety range. If it exceeds the safety range, it will be fed back to the central processor for processing.

8. A vehicle power-off protection system according to claim 1, characterized in that: The temperature change curve change status monitoring method is as follows: S31: The temperature sensor continuously collects temperature change data near the battery and feeds it back to the temperature change analysis module; S32: preprocessing the collected original signal, including signal amplification, filtering, denoising and converting the analog signal into a digital signal through a digital-to-analog converter; S33: storing the converted temperature data in a data storage device, and plotting the stored data into a curve graph using a data analysis and visualization tool; S34: By setting a threshold, it is detected whether the temperature exceeds the safe range. If it exceeds the range, it will be fed back to the central processor for processing.

9. A method for protecting a vehicle from power failure while in motion, based on a system for protecting a vehicle from power failure while in motion as claimed in any one of claims 1 to 8, characterized in that: The central processing unit obtains the temperature change to establish the curve change state monitoring data, the gas concentration to establish the curve change state monitoring and the flame analysis module determines whether it is a flame or a flickering spark and then performs the following protection method: S41: when a temperature mutation is obtained, the flame analysis module simultaneously obtains the flame or flickering spark data for verification; S42: If the spark data is verified, it is determined to be a thermal runaway state rather than a fire state, and the information is fed back to the alarm module for temperature reduction processing; S43: when a concentration mutation is obtained, the flame analysis module simultaneously obtains the spark data determined as flame or flickering for verification; S44: If the spark data is verified, it is determined that the fire is caused by the lack of air circulation and the accumulation of gas generated by the materials around the battery at high temperature, and ventilation and cooling treatment are carried out; S45: If the flame analysis module determines that there is a flame, the information is fed back to the fire extinguishing module and the power off module to perform power off and fire extinguishing processing at the same time.

Images