Electric vehicle battery monitoring method and system based on dangerous smell monitoring

Abstract

The invention discloses an electric vehicle battery monitoring method and system based on dangerous smell monitoring, and the system comprises a smell monitoring system, a temperature monitoring system, a data processing platform, and an emergency management system. According to the electric vehicle battery monitoring method, a data processing platform configures an odor concentration threshold value corresponding to the safe odor concentration of a preset battery and a temperature threshold value corresponding to the safe temperature, and presets early warning grades based on historical battery data, the odor concentration threshold value and the temperature threshold value. The method comprises the following steps: acquiring current smell data and current temperature data of a battery in real time based on a smell chip and a temperature sensor, performing multi-modal data fusion on the current smell data and the current temperature data by an emergency safety management program to obtain a comprehensive index, and performing comprehensive calculation according to a comprehensive change rate to obtain a current early warning level; and a multi-modal data fusion technology and a grading early warning mechanism are adopted, so that the potential fault of the battery is pre-judged and effectively handled, and the use safety of the electric vehicle is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of battery monitoring, and in particular to an electric vehicle battery monitoring method and system based on monitoring dangerous odors. Background Art

[0002] With the development of the economy and society, although the popularity of cars is already very high, the convenience of electric vehicles is still irreplaceable, especially in the case of urban traffic congestion and parking difficulties. The large-scale use of electric vehicles has also brought some safety issues, especially battery safety issues. Batteries may overheat and short-circuit during use. However, there is no clear and effective monitoring method for traditional electric vehicle batteries on the market, and spontaneous combustion caused by batteries in electric vehicles occurs from time to time.

[0003] In order to strengthen the safety management of electric vehicle batteries, protect the lives and property of citizens, and promote the healthy and environmentally friendly development of the electric vehicle industry, some monitoring devices for electric vehicle batteries have gradually appeared on the market. They can monitor battery abnormalities by detecting a single parameter such as the battery's voltage, current or air pressure, and by setting a predetermined threshold to make an abnormal judgment. However, this type of monitoring method does not have the function of preventive monitoring, and the detection has a large error. When the abnormality is identified, the existing problem has usually developed into a more serious state and cannot be effectively intervened and controlled.

[0004] Therefore, it is necessary to provide an electric vehicle battery monitoring method and system based on monitoring dangerous odors to solve the above problems. Summary of the invention

[0005] The main purpose of the present invention is to provide an electric vehicle battery monitoring method and system based on monitoring dangerous odors, aiming to solve the technical problems mentioned in the above background technology.

[0006] The present invention adopts the following technical solutions: A method for monitoring an electric vehicle battery based on monitoring dangerous odors, comprising: The data processing platform is configured with an odor concentration threshold value corresponding to a safe odor concentration of a preset battery, and a temperature threshold value corresponding to a safe temperature; Acquire historical battery data, and divide the preset warning levels based on the historical battery data, the odor concentration threshold, and the temperature threshold, wherein the historical battery data includes historical odor data and historical temperature data; Acquire the current smell data and current temperature data of the battery in real time based on the smell chip and the temperature sensor, and calibrate the timestamp of the current smell data and the current temperature data; Preprocessing the current odor data and the current temperature data, setting the preprocessed current odor data and the odor concentration threshold as a first comparison result, setting the preprocessed current temperature data and the temperature threshold as a second comparison result, when either the first comparison result or the second comparison result exceeds the corresponding threshold, the emergency management system starts the emergency safety management program; The emergency safety management program performs multimodal data fusion on the current odor data and the current temperature data to obtain a comprehensive index, and obtains the comprehensive change rate of the comprehensive index based on the timestamps corresponding to the current odor data and the current temperature data, and calculates the current warning level in combination with the preset warning level, the comprehensive index and the comprehensive change rate.

[0007] Furthermore, the step of obtaining historical battery data and dividing the preset warning level based on the historical battery data, the odor concentration threshold and the temperature threshold includes: Acquire historical battery data, and perform cleaning processing on the historical battery data; Annotating the historical battery data with the preset battery status to obtain a classified data set; Calculate the conditional probability of each feature of the historical battery data in the classification data set and build a decision model; Based on the decision model, clustering the historical battery data into a plurality of clusters, calculating the distance between each data point of the historical battery data and the plurality of clusters, and reallocating the data points of the historical battery data according to the minimum distance, wherein different clusters are different preset warning levels; The center position of the cluster is adjusted, and each data point of the historical battery data is mapped to the corresponding preset warning level according to the clustering result.

[0008] Furthermore, the step of calibrating the timestamp of the current odor data and temperature data includes: Segmenting the current odor data and the current temperature data according to preset time intervals to form multiple data windows; Mark the start time and end time of each data window with a timestamp, and record the collection time of the odor data and temperature data in the data window; The odor data and temperature data in each data window are stored together with the corresponding timestamp.

[0009] Furthermore, the step of preprocessing the current odor data and the current temperature data includes: Performing data cleaning on the current odor data and the current temperature data; Using a preset algorithm to detect and remove abnormal values ​​from the current odor data and the current temperature data; The current odor data and the current temperature data are filtered, and the filtered current odor data and the current temperature data are normalized.

[0010] Furthermore, the emergency safety management program performs multimodal data fusion on the current odor data and the current temperature data, and calculates the current warning level based on the timestamp and according to the change trend of the fused data and the preset warning level, including: According to the contribution of the historical odor data and the historical temperature data, the weights of the current odor data and the current temperature data are respectively preset, wherein the weight of the current odor data is greater than the weight of the current temperature data; Based on the weight of the current odor data and the weight of the current temperature data, weighted fusion calculation is performed on the current odor data and the current temperature data to obtain a comprehensive index; Calling the timestamp of the current odor data and the current temperature data and the timestamp of the odor data and the temperature data at a previous moment, and calculating the comprehensive change rate of the comprehensive index corresponding to the time difference between the two timestamps; The comprehensive indicator is mapped to the preset warning level, and the current warning level is calculated and generated by combining the preset conversion coefficient between the comprehensive change rate and the preset warning level.

[0011] The present invention also proposes an electric vehicle battery monitoring system based on monitoring dangerous odors, comprising: An odor monitoring system and a temperature monitoring system, wherein the odor monitoring system includes an odor chip and a multi-level concentration warning module, and the temperature monitoring system includes a temperature sensor and a multi-level temperature warning module, wherein the odor chip is used to monitor and identify odor characteristics; A data processing platform, the data processing platform being communicatively connected to the odor chip and the temperature sensor respectively, and the data processing platform storing preset threshold values ​​set according to a safe odor concentration and a safe temperature of the battery; An emergency management system, the emergency management system being connected to the data processing platform, the multi-level concentration warning module and the multi-level temperature warning module respectively; Among them, when the data processing platform reads and compares the data of the odor chip and / or the temperature sensor and exceeds the preset threshold, the data processing platform will feed back the comparison result to the emergency management system, and the emergency management system will control the multi-level concentration warning module and / or the multi-level temperature warning module to respond in a graded manner according to the comparison result.

[0012] Furthermore, the odor monitoring system further comprises a post-warning odor monitoring module, and the temperature monitoring system further comprises a post-warning temperature monitoring module, and the post-warning odor monitoring module and the post-warning temperature monitoring module are respectively connected to the data processing platform for communication; Among them, the post-warning odor monitoring module is used to monitor odor characteristics after the multi-level concentration warning module responds, and the post-warning temperature monitoring module is used to monitor temperature changes after the multi-level temperature warning module responds.

[0013] Furthermore, the data processing platform includes a reading module, a comparison module, an effect judgment module and a notification module. The odor chip and the temperature sensor are respectively connected to the reading module in communication, the comparison module is connected to the reading module and the emergency management system, the effect judgment module is respectively connected to the post-warning odor monitoring module and the post-warning temperature monitoring module, and the notification module is connected to the terminal device in communication.

[0014] Furthermore, the emergency management system includes an edge control module, an early warning prompt module, a power off module and a protection device power supply module, and the edge control module, the early warning prompt module, the power off module and the protection device power supply module are respectively connected to the data processing platform, and the early warning prompt module is connected to the multi-level concentration early warning module and the multi-level temperature early warning module.

[0015] Further, the multi-level concentration warning module and the multi-level temperature warning module are connected with a warning device, and the warning device includes a buzzer and an alarm light, and the buzzer and the alarm light are both connected to the multi-level concentration warning module and the multi-level temperature warning module; The multi-level concentration warning module includes a low-level concentration warning module, a medium-level concentration warning module and a high-level concentration warning module, and the multi-level temperature warning module includes a low-level temperature warning module, a medium-level temperature warning module and a high-level temperature warning module; Among them, when the low-level concentration warning module and / or the low-level temperature warning module responds, the notification module, buzzer and alarm light work; when the intermediate concentration warning module and / or the intermediate temperature warning module responds, the notification module, power-off module, buzzer and alarm light work; when the high-level concentration warning module and / or the high-level temperature warning module responds, the notification module, power-off module, protection device power supply module, buzzer and alarm light work.

[0016] Beneficial effects: In the present invention, an electric vehicle battery monitoring method and system based on monitoring dangerous odors are used to monitor the electric vehicle battery in real time through an odor chip and a temperature sensor. Through multimodal data fusion, the odor data and temperature data are jointly analyzed, and three warning levels of low warning, medium warning and high warning are set. Graded alarms are performed according to different situations of odor concentration thresholds and temperature thresholds. In general, the use of multimodal data fusion technology and a graded warning mechanism significantly improves the safety monitoring capability of electric vehicle batteries, realizes early prediction and effective response to potential battery failures, and ensures the safe use of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of Embodiment 1 of the present invention; Figure 2 It is an overall architecture diagram of the second embodiment of the present invention.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0020] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0021] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0023] Embodiment 1: refer to Figure 1 The present invention proposes an electric vehicle battery monitoring method based on monitoring dangerous odors, comprising: S1: The data processing platform configures the odor concentration threshold corresponding to the safe odor concentration of the preset battery and the temperature threshold corresponding to the safe temperature; S2: Acquire historical battery data, and divide the preset warning levels based on the historical battery data, the odor concentration threshold, and the temperature threshold, wherein the historical battery data includes historical odor data and historical temperature data; S3: acquiring the current smell data and the current temperature data of the battery in real time based on the smell chip and the temperature sensor, and calibrating the timestamps for the current smell data and the current temperature data; S4: preprocessing the current odor data and the current temperature data, setting the preprocessed current odor data and the odor concentration threshold as a first comparison result, setting the preprocessed current temperature data and the temperature threshold as a second comparison result, when either the first comparison result or the second comparison result exceeds the corresponding threshold, the emergency management system starts the emergency safety management program; S5: The emergency safety management program performs multimodal data fusion on the current odor data and the current temperature data to obtain a comprehensive index, and obtains the comprehensive change rate of the comprehensive index based on the timestamps corresponding to the current odor data and the current temperature data, and calculates the current warning level in combination with the preset warning level, the comprehensive index and the comprehensive change rate.

[0024] In the above embodiment, in step S1, the data processing platform may be an embedded system, a server or a cloud platform, etc., which is responsible for processing and analyzing the battery monitoring data. The preset odor concentration threshold and temperature threshold may be adjusted according to different types of electric vehicle batteries to meet the needs of different application scenarios.

[0025] In step S2, the acquisition of historical battery data can be achieved by long-term monitoring and recording of battery odor and temperature changes. These data will be used to train the warning model to more accurately classify the warning level. The preset warning levels include low-level warning, medium-level warning and high-level warning. The division of the preset warning levels helps to quickly respond to potential battery failures and take corresponding measures.

[0026] In step S3, the current odor data and current temperature data acquired in real time need to be timestamped to ensure the accuracy and traceability of the data. The timestamp calibration helps to analyze the changing trend of the battery status over time, so as to better predict and prevent failures.

[0027] In step S4, the preprocessing of the current odor data and the current temperature data includes steps such as data cleaning, filtering and normalization to ensure data quality. When any comparison result of the first comparison result and the second comparison result exceeds the threshold, the emergency management system will start the emergency safety management procedure, which may include cutting off the battery power, sounding an alarm, notifying maintenance personnel, and other measures.

[0028] In step S5, the multimodal data fusion technology comprehensively analyzes the current odor data and the current temperature data to obtain more comprehensive battery status information. According to the change trend of the fused data, the current warning level is calculated to provide users with timely warning information and suggestions for taking corresponding measures.

[0029] In one embodiment, the step of obtaining historical battery data and dividing the preset warning level based on the historical battery data, the odor concentration threshold and the temperature threshold includes: S21: Acquire historical battery data, and clean the historical battery data; S22: labeling the historical battery data and the preset battery status to obtain a classified data set; S23: Calculate the conditional probability of each feature of the historical battery data in the classification data set and build a decision model; S24: clustering the historical battery data into a plurality of clusters based on the decision model, calculating the distance between each data point of the historical battery data and the plurality of clusters, and reallocating the data points of the historical battery data according to the minimum distance, wherein different clusters have different preset warning levels; S25: Adjust the center position of the cluster, and map each data point of the historical battery data to the corresponding preset warning level according to the clustering result.

[0030] In the above embodiment, the specific explanation and embodiment is that in step S21, the acquisition of historical battery data can be carried out by long-term monitoring through sensors installed in the battery pack of the electric vehicle. These sensors can be odor sensors and temperature sensors, which can record the odor concentration and temperature changes of the battery under different working conditions in real time. The purpose of data cleaning processing is to remove noise and outliers and ensure data quality for subsequent analysis.

[0031] In step S22, the historical battery data and the preset battery status are annotated to obtain a classification data set in order to train the decision model. The preset battery status may include a normal state, a slightly abnormal state, a severely abnormal state, etc. These states will be used as labels to annotate the historical data. By annotating, learning samples can be provided for the model so that it can recognize battery characteristics under different states.

[0032] In step S23, the conditional probability of each feature of the historical battery data in the classification data set is calculated and the decision model is constructed in order to establish a model that can predict the battery state based on the battery odor concentration and temperature data. The calculation of the conditional probability can be performed using a Bayesian classifier, a support vector machine (SVM) or other machine learning algorithms.

[0033] In step S24, the historical battery data is clustered into several clusters based on the decision model in order to classify data points with similar characteristics into the same category. The clustering algorithm can be K-means, hierarchical clustering, etc. Calculating the distance between each data point and each cluster and reallocating the data points according to the minimum distance helps to accurately classify the data points into the corresponding warning levels.

[0034] In step S25, the position of the cluster center is adjusted, and each data point of the historical battery data is mapped to the corresponding preset warning level according to the clustering result, in order to optimize the clustering result. The cluster center can be adjusted by an iterative method, such as the centroid update process in the K-means algorithm. Ultimately, each data point will be mapped to a specific warning level, thereby providing a reference for real-time monitoring of the battery status.

[0035] Through the above steps, the dangerous odor of electric vehicle batteries can be effectively monitored, and the warning level can be divided according to the odor concentration and temperature data, so as to detect potential battery failures in advance and ensure the safe operation of electric vehicles.

[0036] In one embodiment, the step of calibrating the timestamp of the current odor data and temperature data specifically includes: S31: segmenting the current odor data and the current temperature data according to a preset time interval to form multiple data windows S32: Marking the start time and the end time of each data window with a timestamp, and recording the collection time of the odor data and the temperature data in the data window; S33: storing the odor data and temperature data in each data window together with the corresponding timestamp.

[0037] In the above embodiment, in step S31, the current odor data and the current temperature data are segmented according to the preset time interval to form multiple data windows in order to ensure the continuity and traceability of the data. The preset time interval can be adjusted according to the actual application scenario and monitoring requirements, such as every second, every minute or every hour. By segmenting the data into multiple windows, it is more convenient to analyze the changing trend of the battery status over time, thereby better predicting and preventing failures.

[0038] In step S32, the start time and the end time of each data window are respectively calibrated with timestamps, and the collection time of the odor data and temperature data in the data window is recorded to ensure the accuracy and traceability of the data. The calibration of timestamps helps to analyze the change trend of battery status over time, so as to better predict and prevent failures. Timestamps can be recorded in a variety of ways, such as using system timestamps or GPS timestamps.

[0039] In step S33, the odor data and temperature data in each data window are stored with the corresponding calibration timestamp to facilitate subsequent data analysis and processing. The stored data can be saved in a local storage device or a remote server for easy access and analysis at any time. The storage format can be a text file, a database or other suitable data storage format.

[0040] Through the above steps, the accuracy and traceability of battery monitoring data can be ensured, thus providing reliable data support for real-time monitoring and early warning of electric vehicle batteries. Combining multimodal data fusion technology and early warning models, the early warning level can be divided more accurately, potential battery failures can be discovered in time, and the safe operation of electric vehicles can be ensured.

[0041] In one embodiment, the step of preprocessing the current odor data and the current temperature data specifically includes: S41: performing data cleaning on the current odor data and the current temperature data; S42: using a preset algorithm to detect and remove abnormal values ​​from the current odor data and the current temperature data; S43: filtering the current odor data and the current temperature data, and normalizing the filtered current odor data and the current temperature data.

[0042] In the above embodiment, in step S41, the current odor data and the current temperature data are cleaned to remove noise and outliers and ensure data quality. Data cleaning may include operations such as removing duplicate data, filling missing values, and smoothing noise data. Through data cleaning, the accuracy and reliability of subsequent analysis can be improved.

[0043] In step S42, the current odor data and the current temperature data are detected and removed using a preset algorithm in order to further ensure the accuracy of the data. Outlier detection can be performed using methods such as box plots, Z scores, and IQR (interquartile range). By removing outliers, the impact of these data on subsequent analysis and early warning models can be avoided, thereby improving the accuracy and robustness of the model.

[0044] In step S43, the current odor data and the current temperature data are filtered and the filtered data are normalized to eliminate the noise in the signal and make the data comparable on the same scale. The filtering process can use methods such as low-pass filter and median filter to reduce the influence of random noise. The normalization process can use methods such as minimum-maximum normalization and Z-score standardization to ensure that the data is between 0 and 1 or has the same mean and standard deviation, so as to facilitate subsequent analysis and model training.

[0045] Through the above steps, the quality of current odor data and temperature data can be ensured, providing accurate and reliable data support for real-time monitoring and early warning. Combined with the analysis of historical battery data and the early warning model, electric vehicle batteries can be more effectively monitored in real time, potential battery failures can be discovered in time, and the safe operation of electric vehicles can be ensured.

[0046] In one embodiment, the emergency safety management program performs multimodal data fusion on the current odor data and the current temperature data to obtain a comprehensive index, obtains a comprehensive change rate of the comprehensive index based on the timestamps corresponding to the current odor data and the current temperature data, and calculates the current warning level in combination with the preset warning level, the comprehensive index and the comprehensive change rate, specifically including: S51: Presetting weights of the current smell data and the current temperature data respectively according to the contribution of the historical smell data and the historical temperature data, wherein the weight of the current smell data is greater than the weight of the current temperature data; S52: Based on the weight of the current odor data and the weight of the current temperature data, weighted fusion calculation is performed on the current odor data and the current temperature data to obtain a comprehensive index; S53: calling the timestamp of the current odor data and the current temperature data and the timestamp of the odor data and the temperature data at the previous moment, and calculating the comprehensive change rate of the comprehensive index corresponding to the time difference between the two timestamps; S54: Mapping the comprehensive indicator to the preset warning level, and calculating and generating the current warning level by combining the preset conversion coefficient between the comprehensive change rate and the preset warning level.

[0047] In the above embodiment, in step S51, the weights of the current odor data and the current temperature data are preset according to the contribution of the historical odor data and the historical temperature data, wherein the weight of the current odor data is greater than the weight of the current temperature data, in order to highlight the importance of the odor data in the battery fault warning. Since odor changes often reflect abnormal reactions inside the battery earlier than temperature changes, giving the odor data a higher weight can improve the sensitivity and accuracy of the warning system.

[0048] In step S52, based on the weight of the current odor data and the weight of the current temperature data, the current odor data and the current temperature data are weighted and fused to obtain a comprehensive index, in order to comprehensively consider the information from different data sources and improve the comprehensiveness and reliability of the early warning. The weighted fusion calculation can adopt a variety of methods, such as weighted average, weighted sum, etc., to ensure that the comprehensive index can truly reflect the battery status.

[0049] In step S53, the timestamps of the current odor data and the current temperature data and the timestamps of the odor data and the temperature data at the previous moment are called to calculate the comprehensive change rate corresponding to the time difference between the two timestamps in order to analyze the change trend of the battery status over time. By calculating the change rate, the dynamic change of the battery status can be judged more accurately, so as to discover potential faults in time.

[0050] In step S54, the comprehensive index is mapped to the preset warning level, and the preset conversion coefficient between the comprehensive change rate and the preset warning level is combined to calculate and generate the current warning level, in order to convert the comprehensive index into specific warning information. The preset conversion coefficient can be adjusted according to the actual application scenario and historical data to ensure the accuracy and timeliness of the warning level. Specifically, when the comprehensive change rate is positive, the current warning level is increased by one level. When the comprehensive change rate is flat, the warning level obtained by directly mapping the comprehensive index to the preset warning level is used. When the comprehensive change rate is negative, the current warning level can be reduced to avoid unnecessary alarms. In this way, intuitive warning information can be provided to electric vehicle operators, and timely measures can be taken to ensure the safe operation of electric vehicles.

[0051] In summary, by comprehensively considering the weights, change trends and contribution of historical data of odor data and temperature data, the current warning level can be calculated more accurately, thus providing strong support for real-time monitoring and warning of electric vehicle batteries. Combined with advanced warning models and emergency safety management procedures, the risks brought by battery failures can be effectively prevented and reduced, ensuring the safe and stable operation of electric vehicles.

[0052] Embodiment 2: Reference Figure 2 The present invention also proposes an electric vehicle battery monitoring system based on monitoring dangerous odors, comprising: an odor monitoring system and a temperature monitoring system, wherein the odor monitoring system comprises an odor chip and a multi-level concentration warning module, and the temperature monitoring system comprises a temperature sensor and a multi-level temperature warning module, wherein the odor chip is used to monitor and identify odor characteristics; a data processing platform, wherein the data processing platform is respectively connected to the odor chip and the temperature sensor for communication, and wherein the data processing platform stores preset thresholds set according to the safe odor concentration and safe temperature of the battery; an emergency management system, wherein the emergency management system is respectively connected to the data processing platform, the multi-level concentration warning module and the multi-level temperature warning module; wherein when the data processing platform reads and compares the data of the odor chip and / or the temperature sensor and exceeds the preset threshold, the data processing platform feeds back the comparison result to the emergency management system, and the emergency management system controls the multi-level concentration warning module and / or the multi-level temperature warning module to perform a graded response according to the comparison result.

[0053] In the above embodiments, the electric vehicle battery monitoring system of the present invention can effectively prevent fires and harmful gas leakage accidents caused by battery failure. For example, in actual use scenarios, when the electric vehicle is charging, the odor monitoring system will monitor the air composition in the battery compartment in real time. If an abnormal odor is detected, such as excessive hydrogen or sulfuric acid, the odor chip will immediately identify it and send a signal to the data processing platform. The data processing platform will determine whether the danger level has been reached based on the preset threshold and pass the result to the emergency management system.

[0054] When the emergency management system receives a danger signal, it will immediately activate the corresponding warning module. For example, if the odor concentration exceeds the safety threshold, the multi-level concentration warning module will first issue an audible and visual alarm to alert the user and surrounding personnel. If the odor concentration continues to rise, the system will automatically cut off the battery power supply to prevent potential fires, and send an alarm message to the remote monitoring center through the wireless communication module so that further measures can be taken.

[0055] Similarly, the temperature monitoring system will also play a role when the battery temperature rises abnormally. The temperature sensor will monitor the temperature changes of the battery in real time. Once the preset safety temperature threshold is exceeded, the multi-level temperature warning module will be activated, first reminding the user through sound and light alarms. Then, depending on the degree of temperature increase, the system may start the cooling system to cool down, or cut off the battery power supply when necessary to ensure battery safety. The entire process is coordinated by the data processing platform to ensure that electric vehicles can be monitored and protected in a timely and effective manner under various circumstances.

[0056] In the present invention, the electric vehicle battery is monitored in real time through the odor chip and the temperature sensor, and with the coordinated action of the emergency management system and the data processing platform, the data from the odor chip and the temperature sensor can be quickly processed and analyzed. When the detected value exceeds the set safety threshold, the system can immediately control the multi-level concentration warning module and / or the multi-level temperature warning module to perform a corresponding emergency response according to the degree of urgency, ensuring timely control and intervention before the danger occurs.

[0057] In one embodiment, the odor monitoring system also includes a post-warning odor monitoring module, and the temperature monitoring system also includes a post-warning temperature monitoring module, and the post-warning odor monitoring module and the post-warning temperature monitoring module are respectively communicatively connected to the data processing platform; wherein, the post-warning odor monitoring module is used to monitor odor characteristics after the multi-level concentration warning module responds, and the post-warning temperature monitoring module is used to monitor temperature changes after the multi-level temperature warning module responds.

[0058] In the above embodiment, the post-warning odor monitoring module is equipped with a highly sensitive gas sensor array that can capture and identify a variety of volatile organic compounds in the air in real time. It can distinguish different types of odor characteristics, such as smoke, chemical leaks or biological contamination, and transmit the data to the data processing platform for further analysis. The data processing platform classifies and evaluates the odor characteristics according to preset thresholds and algorithms to determine whether there is a potential dangerous situation.

[0059] The post-warning temperature monitoring module uses high-precision temperature sensors to monitor ambient temperature changes in real time. These sensors can detect small temperature fluctuations and transmit the data in real time to the data processing platform. The data processing platform combines temperature change trends and historical data to assess whether there is a risk of fire or other abnormal conditions. Once a temperature change outside the normal range is detected, the system will immediately activate the corresponding early warning mechanism, such as sounding an alarm, activating firefighting equipment, or notifying relevant personnel.

[0060] In one example, the data processing platform includes a reading module, a comparison module, an effect judgment module and a notification module. The odor chip and the temperature sensor are respectively connected to the reading module in communication, the comparison module is connected to the reading module and the emergency management system, the effect judgment module is respectively connected to the post-warning odor monitoring module and the post-warning temperature monitoring module, and the notification module is connected to the terminal device in communication.

[0061] In the above embodiment, in the data processing platform, the reading module is responsible for collecting data information from the odor chip and the temperature sensor in real time. The comparison module compares the collected data with the preset threshold to determine whether there is an abnormality. If an abnormality is detected, the comparison module will pass the relevant information to the emergency management system so that corresponding measures can be taken in time.

[0062] The effect judgment module evaluates the actual effect of the early warning measures based on the data provided by the post-warning odor monitoring module and the post-warning temperature monitoring module. For example, if the odor monitoring module shows that the odor concentration has decreased, and the temperature monitoring module shows that the temperature has returned to the normal range, the effect judgment module will determine that the early warning measures are effective.

[0063] The notification module is responsible for sending the comparison results and effect evaluation results to terminal devices, such as smartphones, tablets or computers. End users can receive real-time notifications through the APP in these devices to understand the current environmental conditions and the operating status of the early warning system. In addition, the notification module can also send emails or text messages to relevant personnel as needed to ensure the timeliness and effectiveness of information transmission.

[0064] In one embodiment, the emergency management system includes an edge control module, an early warning prompt module, a power off module and a protection device power supply module, and the edge control module, the early warning prompt module, the power off module and the protection device power supply module are respectively connected to the data processing platform, and the early warning prompt module is connected to the multi-level concentration early warning module and the multi-level temperature early warning module.

[0065] In the above embodiment, the edge control module is responsible for collecting and processing field data in real time to ensure rapid response and transmission of information. The early warning prompt module monitors environmental parameters in real time based on the data provided by the multi-level concentration early warning module and the multi-level temperature early warning module. Once the preset safety threshold is exceeded, an audible and visual alarm is immediately issued to remind on-site personnel to take corresponding measures. The power-off module can quickly cut off the power supply in an emergency to prevent the spread of potential dangers. The protection device power supply module ensures that in the event of a power outage, key early warning and communication equipment can still work normally to ensure the reliability of the system. Through the collaborative work of these modules, the emergency management system can effectively improve the safety level on site and reduce the risk of accidents.

[0066] In one embodiment, the multi-level concentration warning module and the multi-level temperature warning module are connected with a warning device, and the warning device includes a buzzer and an alarm light, and the buzzer and the alarm light are both connected to the multi-level concentration warning module and the multi-level temperature warning module; The multi-level concentration warning module includes a low-level concentration warning module, a medium-level concentration warning module and a high-level concentration warning module, and the multi-level temperature warning module includes a low-level temperature warning module, a medium-level temperature warning module and a high-level temperature warning module; Among them, when the low-level concentration warning module and / or the low-level temperature warning module responds, the notification module, buzzer and alarm light work; when the intermediate concentration warning module and / or the intermediate temperature warning module responds, the notification module, power-off module, buzzer and alarm light work; when the high-level concentration warning module and / or the high-level temperature warning module responds, the notification module, power-off module, protection device power supply module, buzzer and alarm light work.

[0067] In the above embodiment, the multi-level concentration warning module and the multi-level temperature warning module are connected to the buzzer and the alarm light through the control circuit. When it is detected that the concentration of harmful gases exceeds the preset safety threshold or the temperature exceeds the normal working range, the control circuit will immediately start the buzzer to emit continuous warning sounds and light up the alarm light to attract the attention of on-site personnel. The response time of the buzzer and the alarm light is less than one second, ensuring that a quick response can be made in an emergency. In addition, the early warning device also has a self-test function, which regularly checks whether the buzzer and the alarm light are working properly to ensure that the early warning signal can be reliably issued at critical moments.

[0068] When the low-level concentration warning module and the low-level temperature warning module respond, the system will send a warning message to the operator through the notification module, start the buzzer to emit a continuous alarm sound, and light up the alarm light to attract the attention of on-site personnel. If the situation deteriorates further, when the intermediate concentration warning module and the intermediate temperature warning module respond, in addition to the above measures, the system will automatically cut off the power supply of related equipment to prevent the spread of potential dangers. When the advanced concentration warning module and the advanced temperature warning module respond, the system will implement the most comprehensive emergency measures. In addition to all the above responses, the protection device power supply module will be activated to ensure that key safety and first aid equipment can work normally in an emergency, thereby maximizing the safety of personnel and equipment.

[0069] Furthermore, it also includes a communication unit, the odor chip and the temperature sensor are connected to the communication unit, and the communication unit is communicatively connected to the data processing platform so that the monitoring data of the odor chip and the temperature sensor are communicatively connected to the data processing platform.

[0070] In the above embodiment, in this specific implementation, the communication unit uses wireless transmission technology, such as 4G, 5G, Bluetooth or Wi-Fi, to ensure that the real-time data of the odor chip and temperature sensor can be seamlessly transmitted to the data processing platform. The data processing platform analyzes and processes the collected data through dedicated software to generate a detailed environmental monitoring report. In addition, the communication unit also supports remote control function, allowing users to configure and adjust the odor chip and temperature sensor through mobile devices, thereby realizing personalized monitoring needs.

[0071] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for monitoring electric vehicle batteries based on monitoring dangerous odors, characterized in that: include: The data processing platform is configured with an odor concentration threshold value corresponding to a safe odor concentration of a preset battery, and a temperature threshold value corresponding to a safe temperature; Acquire historical battery data, and divide the preset warning levels based on the historical battery data, the odor concentration threshold, and the temperature threshold, wherein the historical battery data includes historical odor data and historical temperature data; Acquire the current smell data and current temperature data of the battery in real time based on the smell chip and the temperature sensor, and calibrate the timestamp of the current smell data and the current temperature data; Preprocessing the current odor data and the current temperature data, setting the preprocessed current odor data and the odor concentration threshold as a first comparison result, setting the preprocessed current temperature data and the temperature threshold as a second comparison result, when either the first comparison result or the second comparison result exceeds the corresponding threshold, the emergency management system starts the emergency safety management program; The emergency safety management program performs multimodal data fusion on the current odor data and the current temperature data to obtain a comprehensive index, and obtains the comprehensive change rate of the comprehensive index based on the timestamps corresponding to the current odor data and the current temperature data, and calculates the current warning level in combination with the preset warning level, the comprehensive index and the comprehensive change rate.

2. The electric vehicle battery monitoring method based on monitoring dangerous odors according to claim 1 is characterized in that: The step of obtaining historical battery data and dividing the preset warning level based on the historical battery data, the odor concentration threshold and the temperature threshold includes: Acquire historical battery data, and perform cleaning processing on the historical battery data; Annotating the historical battery data with the preset battery status to obtain a classified data set; Calculate the conditional probability of each feature of the historical battery data in the classification data set and build a decision model; Based on the decision model, clustering the historical battery data into a plurality of clusters, calculating the distance between each data point of the historical battery data and the plurality of clusters, and reallocating the data points of the historical battery data according to the minimum distance, wherein different clusters are different preset warning levels; The center position of the cluster is adjusted, and each data point of the historical battery data is mapped to the corresponding preset warning level according to the clustering result.

3. The electric vehicle battery monitoring method based on monitoring dangerous odors according to claim 1 is characterized in that: The step of calibrating the timestamp of the current odor data and temperature data comprises: Segmenting the current odor data and the current temperature data according to preset time intervals to form multiple data windows; Mark the start time and end time of each data window with a timestamp, and record the collection time of the odor data and temperature data in the data window; The odor data and temperature data in each data window are stored together with the corresponding timestamp.

4. The electric vehicle battery monitoring method based on monitoring dangerous odors according to claim 1 is characterized in that: The step of preprocessing the current odor data and the current temperature data comprises: Performing data cleaning on the current odor data and the current temperature data; Using a preset algorithm to detect and remove abnormal values ​​from the current odor data and the current temperature data; The current odor data and the current temperature data are filtered, and the filtered current odor data and the current temperature data are normalized.

5. The electric vehicle battery monitoring method based on monitoring dangerous odors according to claim 1 is characterized in that: The emergency safety management program performs multimodal data fusion on the current odor data and the current temperature data to obtain a comprehensive index, obtains a comprehensive change rate of the comprehensive index based on the timestamps corresponding to the current odor data and the current temperature data, and calculates the current warning level in combination with the preset warning level, the comprehensive index and the comprehensive change rate, including: According to the contribution of the historical odor data and the historical temperature data, the weights of the current odor data and the current temperature data are respectively preset, wherein the weight of the current odor data is greater than the weight of the current temperature data; Based on the weight of the current odor data and the weight of the current temperature data, weighted fusion calculation is performed on the current odor data and the current temperature data to obtain a comprehensive index; Calling the timestamp of the current odor data and the current temperature data and the timestamp of the odor data and the temperature data at a previous moment, and calculating the comprehensive change rate of the comprehensive index corresponding to the time difference between the two timestamps; The comprehensive indicator is mapped to the preset warning level, and the current warning level is calculated and generated by combining the preset conversion coefficient between the comprehensive change rate and the preset warning level.

6. An electric vehicle battery monitoring system based on monitoring dangerous odors, characterized in that: include: An odor monitoring system and a temperature monitoring system, wherein the odor monitoring system includes an odor chip and a multi-level concentration warning module, and the temperature monitoring system includes a temperature sensor and a multi-level temperature warning module, wherein the odor chip is used to monitor and identify odor characteristics; A data processing platform, the data processing platform being communicatively connected to the odor chip and the temperature sensor respectively, and the data processing platform storing preset threshold values ​​set according to a safe odor concentration and a safe temperature of the battery; An emergency management system, the emergency management system being connected to the data processing platform, the multi-level concentration warning module and the multi-level temperature warning module respectively; Among them, when the data processing platform reads and compares the data of the odor chip and / or the temperature sensor and exceeds the preset threshold, the data processing platform will feed back the comparison result to the emergency management system, and the emergency management system will control the multi-level concentration warning module and / or the multi-level temperature warning module to respond in a graded manner according to the comparison result.

7. The electric vehicle battery monitoring system based on monitoring dangerous odors according to claim 6 is characterized in that: The odor monitoring system further includes a post-warning odor monitoring module, and the temperature monitoring system further includes a post-warning temperature monitoring module, and the post-warning odor monitoring module and the post-warning temperature monitoring module are respectively connected to the data processing platform for communication; Among them, the post-warning odor monitoring module is used to monitor odor characteristics after the multi-level concentration warning module responds, and the post-warning temperature monitoring module is used to monitor temperature changes after the multi-level temperature warning module responds.

8. The electric vehicle battery monitoring system based on monitoring dangerous odors according to claim 6 is characterized in that: The data processing platform includes a reading module, a comparison module, an effect judgment module and a notification module. The odor chip and the temperature sensor are respectively connected to the reading module for communication, the comparison module is connected to the reading module and the emergency management system, the effect judgment module is respectively connected to the post-warning odor monitoring module and the post-warning temperature monitoring module, and the notification module is connected to the terminal device for communication.

9. The electric vehicle battery monitoring system based on monitoring dangerous odors according to claim 8, characterized in that: The emergency management system includes an edge control module, an early warning prompt module, a power off module and a protection device power supply module. The edge control module, the early warning prompt module, the power off module and the protection device power supply module are respectively connected to the data processing platform, and the early warning prompt module is connected to the multi-level concentration early warning module and the multi-level temperature early warning module.

10. The electric vehicle battery monitoring system based on monitoring dangerous odors according to claim 9, characterized in that: The multi-level concentration warning module and the multi-level temperature warning module are connected with a warning device, and the warning device includes a buzzer and an alarm light, and the buzzer and the alarm light are both connected to the multi-level concentration warning module and the multi-level temperature warning module; The multi-level concentration warning module includes a low-level concentration warning module, a medium-level concentration warning module and a high-level concentration warning module, and the multi-level temperature warning module includes a low-level temperature warning module, a medium-level temperature warning module and a high-level temperature warning module; Among them, when the low-level concentration warning module and / or the low-level temperature warning module responds, the notification module, buzzer and alarm light work; when the intermediate concentration warning module and / or the intermediate temperature warning module responds, the notification module, power-off module, buzzer and alarm light work; when the high-level concentration warning module and / or the high-level temperature warning module responds, the notification module, power-off module, protection device power supply module, buzzer and alarm light work.

Images