CN118244126A - New energy automobile battery detection method and system based on integrated sensor - Google Patents
New energy automobile battery detection method and system based on integrated sensor Download PDFInfo
- Publication number
- CN118244126A CN118244126A CN202410667011.9A CN202410667011A CN118244126A CN 118244126 A CN118244126 A CN 118244126A CN 202410667011 A CN202410667011 A CN 202410667011A CN 118244126 A CN118244126 A CN 118244126A
- Authority
- CN
- China
- Prior art keywords
- data
- battery
- temperature
- new energy
- sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 230000000007 visual effect Effects 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000009529 body temperature measurement Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 4
- 238000001816 cooling Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 239000002826 coolant Substances 0.000 claims description 3
- 239000000110 cooling liquid Substances 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 2
- 238000003491 array Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013079 data visualisation Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Secondary Cells (AREA)
Abstract
The invention discloses a new energy automobile battery detection method and system based on an integrated sensor, and relates to the technical field of battery detection, wherein the method comprises the steps of deploying sensors on each group of batteries, constructing a sensor network to collect data in real time, and transmitting the collected data to an edge calculation module for preliminary processing; fusing the processed data and extracting features to construct a neural network prediction model to predict the temperature change of the battery; and automatically executing emergency measures according to the prediction results, and visually displaying the early warning information. According to the invention, the integrated sensors are deployed on each group of batteries, the sensor network is constructed to collect data in real time, the neural network prediction model is constructed to predict the battery temperature of the new energy automobile and generate emergency measures, so that the coverage range of the data and the efficiency of battery temperature detection are remarkably improved, any abnormal temperature change can be accurately identified and responded, the safety and efficiency of a battery system are improved, and the risk of thermal runaway of the battery of the new energy automobile is reduced.
Description
Technical Field
The invention relates to the technical field of battery detection, in particular to a new energy automobile battery detection method and system based on an integrated sensor.
Background
With the rapid expansion of new energy automobile markets, the optimization and safety monitoring of battery performance become particularly important, the traditional temperature monitoring system usually adopts a single sensor to detect the average temperature of the whole battery pack or battery module, the method is simple and low in cost, but in the rapidly-developed new energy automobile industry, the single sensor system cannot meet higher safety and performance requirements, with the increase of the requirements of the new energy automobile on high efficiency and safety, higher standards are also put forward on the technology of the battery system, particularly in the aspects of accurate monitoring and real-time reaction of battery temperature, currently, the single sensor technology adopted by most battery temperature monitoring systems has obvious limitations, only a single sensor can provide limited data points, faults or deviations of a single data source possibly cause wrong temperature readings, temperature gradients and hot spots possibly existing in the battery pack cannot be accurately monitored, the risk of thermal runaway is increased, the decision and response of the whole battery system are influenced, and the capability of the battery system in the aspects of efficiency improvement and control is limited.
Disclosure of Invention
The present invention has been made in view of the above-mentioned problems occurring in the conventional method and system for detecting a battery of a new energy automobile based on an integrated sensor.
Therefore, the problem to be solved by the present invention is that a single sensor can only provide limited data points and that a failure or deviation of a single data source may lead to erroneous temperature readings, and that temperature gradients and hot spots that may exist inside the battery pack cannot be accurately monitored, increasing the risk of thermal runaway, affecting the decision and response of the whole battery system, limiting the ability of the battery system in terms of efficiency improvement and risk control.
In order to solve the technical problems, the invention provides the following technical scheme: the new energy automobile battery detection method based on the integrated sensor comprises the steps of deploying sensors on each group of batteries, constructing a sensor network to collect data in real time, and transmitting the collected data to an edge calculation module for preliminary processing; fusing the processed data and extracting features to construct a neural network prediction model to predict the temperature change of the battery; and automatically executing emergency measures according to the prediction results, and visually displaying the early warning information.
As a preferable scheme of the new energy automobile battery detection method based on the integrated sensor, the invention comprises the following steps: the steps of deploying sensors on each group of new energy automobile batteries and constructing a sensor network to collect data in real time are that temperature sensors are deployed on the upper, middle and lower layers of the batteries, the temperature distribution of the batteries is comprehensively monitored, star network topology is used, intermediate nodes are used as edge calculation modules and connected with all the sensors, data collection frequency is set, and the deployed sensors are used for collecting the temperature data of the batteries in real time according to the set frequency.
As a preferable scheme of the new energy automobile battery detection method based on the integrated sensor, the invention comprises the following steps: the step of transmitting the acquired data to the edge computing module for preliminary processing means that a timestamp is added to the acquired data and the acquired data is transmitted to the edge computing module through a wireless network, the acquired data is denoised by using a Kalman filter after the data is cleaned and format standardized, abnormal values are identified by using an IQR method, and the detected abnormal value data is deleted.
As a preferable scheme of the new energy automobile battery detection method based on the integrated sensor, the invention comprises the following steps: the step of fusing the processed data and extracting the characteristics means that the data subjected to preliminary processing is received from an edge calculation module, and the time stamps of the temperature data from different battery packs are corrected:
，
In the method, in the process of the invention, Is a corrected timestamp,/>Is the original timestamp,/>Is the time offset;
after correction, the acquired temperature data is fused using a data fusion algorithm:
Dividing a temperature interval of a sensor, and defining information entropy of the sensor:
，
In the method, in the process of the invention, Is the information entropy of the ith sensor,/>The probability distribution of the ith sensor in the (q) th temperature interval, and c is the number of the temperature intervals;
Fusing temperature data:
，
Wherein T is the temperature data after fusion, Is the temperature reading of the ith sensor,/>Is the information entropy of the ith sensor, n is the number of sensors;
Storing the fused data into a central database and extracting data characteristics:
，
where F represents the extracted data feature, n is the number of sensors, Is the temperature reading of the ith sensor,/>Is the average temperature.
As a preferable scheme of the new energy automobile battery detection method based on the integrated sensor, the invention comprises the following steps: the constructing a neural network predictive model predicts battery temperature changes including,
Constructing a multi-layer full-connection network as a neural network prediction model, and taking the extracted characteristics as input;
the final output layer predicts the battery temperature using a linear activation function;
The neural network prediction model is expressed as:
，
Where f (x) is the predicted battery temperature, x is the input eigenvector, 、/>、……、/>Is the weight matrix of the full-connection network of each layer,/>、/>、…、/>Is an offset item of the full-connection network of each layer,/>Representing an activation function;
Model training is carried out by using a training set, and training set data are marked synchronously;
measuring deviation between the predicted temperature and the actual observed temperature of the neural network prediction model based on root mean square error;
adjusting parameters of the neural network prediction model based on the evaluation result;
and deploying the neural network prediction model into a central database, and predicting the battery temperature of the collected temperature data of each battery pack to obtain a predicted temperature.
As a preferable scheme of the new energy automobile battery detection method based on the integrated sensor, the invention comprises the following steps: the automatically performing emergency measures based on the prediction results includes,
Mean and standard deviation of temperature data were calculated:
，
，
In the method, in the process of the invention, Is the average of temperature data,/>Is the first temperature measurement, M is the total number of temperature measurements,/>Is the standard deviation of the temperature data;
calculating an alarm threshold for the temperature from the mean and standard deviation of the calculated temperature data:
The low-level alarm threshold is: ；
The medium alarm threshold is: ；
the advanced alert threshold is: ；
If it is The battery temperature is in a low risk state, a low-level alarm is triggered, the rotating speed of a cooling fan is increased, the battery charging rate is slightly reduced, the monitoring of the battery pack is enhanced, and temperature data are recorded;
If it is 2, Indicating that the battery temperature is in a medium risk state, triggering a medium-level alarm, limiting the output power of the battery, increasing the flow rate of the cooling liquid, and sending a warning to a driver, suggesting to reduce the speed and stop for rest;
If it is And 3, indicating that the temperature of the battery is in a high-risk state, triggering a high-level alarm, automatically disconnecting all the connections of the battery, stopping the charging and discharging operations of the battery, using a chemical-based coolant to rapidly cool, and automatically informing a road rescue service and a battery maintenance team to provide the position and the state of the vehicle.
As a preferable scheme of the new energy automobile battery detection method based on the integrated sensor, the invention comprises the following steps: the visual display of the early warning information means that a visual interface is built by using a modern Web development framework Vue. Js, a temperature change curve and an early warning indicator are drawn by using a data visual library, connection is built by a WebSocket protocol, the early warning information and the temperature change curve are updated to the visual interface in real time, an early warning system is integrated on the interface, different colors and early warning information are displayed according to alarms of different levels, a JavaScript library SWEETALERT is used for warning popup, and maintenance personnel are notified through electronic mail.
Another object of the present invention is to provide a new energy automobile battery detection system based on an integrated sensor, which includes,
The data acquisition and transmission module is used for deploying sensors on each group of batteries and constructing a sensor network, acquiring data in real time and transmitting the acquired data to the edge calculation module through a wireless network;
The edge calculation module is used for receiving the transmitted data, cleaning and format standardization the data, denoising and deleting abnormal values;
the feature extraction module is used for fusing the data subjected to the preliminary processing and extracting data features;
The prediction and emergency response module is used for constructing a prediction model to predict the battery temperature change trend and carrying out emergency response according to a prediction result;
and the visual display module is used for displaying the early warning information through a visual interface.
A computer device, comprising: a memory and a processor; the memory stores a computer program, and the processor realizes the steps of the new energy automobile battery detection method based on the integrated sensor when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of a method for detecting a battery of a new energy vehicle based on an integrated sensor.
The invention has the beneficial effects that: according to the invention, the integrated sensors are deployed on each group of batteries, the sensor network is constructed to collect data in real time, the neural network prediction model is constructed to predict the battery temperature of the new energy automobile and generate emergency measures, so that the coverage range of the data and the efficiency of battery temperature detection are remarkably improved, any abnormal temperature change can be accurately identified and responded, the safety and efficiency of a battery system are improved, and the risk of thermal runaway of the battery of the new energy automobile is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a new energy automobile battery detection method based on an integrated sensor.
Fig. 2 is a schematic diagram of an implementation of a new energy automobile battery detection method based on an integrated sensor.
Fig. 3 is a schematic structural diagram of a new energy automobile battery detection system based on an integrated sensor.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
Referring to fig. 1 and 2, a first embodiment of the present invention provides a new energy automobile battery detection method based on an integrated sensor, which includes,
S1, deploying sensors on each group of batteries, constructing a sensor network, collecting data in real time, and transmitting the collected data to an edge calculation module for preliminary processing;
Specifically, deploying sensors on each group of new energy automobile batteries and constructing a sensor network to collect data in real time means that temperature sensors are deployed on the upper, middle and lower layers of the batteries, the temperature distribution of the battery pack is comprehensively monitored, star network topology is used, intermediate nodes are used as edge calculation modules and connected with all the sensors, data collection frequency is set, and the deployed sensors are used for collecting temperature data of the battery pack in real time according to the set frequency.
The data acquisition frequency is optimized through experiments and system performance analysis, temperature sensors are deployed on different layers (upper, middle and lower) of each battery of an automobile, and a star network topology is constructed, so that the comprehensive monitoring of the temperature of the battery is realized.
Further, transmitting the collected data to the edge computing module for preliminary processing means that a timestamp is added to the collected data and the data is transmitted to the edge computing module through a wireless network, after the data is cleaned and format standardized, a Kalman filter is used for denoising the collected data, an IQR method is used for identifying abnormal values, and the detected abnormal value data is deleted.
IQR is a statistical method, is used for identifying abnormal values in a data set, the acquired temperature data is added with a time stamp, is transmitted to an edge calculation module for processing through a wireless network, uses a Kalman filter for denoising data and uses an IQR method for identifying and deleting strategies of abnormal values, so that the accuracy and reliability of the data are remarkably improved, the interference of noise on system decisions is reduced, the calculation burden of subsequent processing steps is reduced by screening out abnormal data, and by the method, the edge calculation module effectively improves the data processing efficiency, ensures the safety of data transmission and processing and provides a good basis for high-quality data analysis.
S2, fusing the processed data and extracting features to construct a neural network prediction model to predict the temperature change of the battery;
Specifically, fusing the processed data and performing feature extraction means that the data subjected to preliminary processing is received from the edge calculation module, and the time stamps of the temperature data from different battery packs are corrected:
，
In the method, in the process of the invention, Is a corrected timestamp,/>Is the original timestamp,/>The time deviation is calculated by network delay and physical distance from the sensor to the data center, the network delay is calculated by round-trip time of data tested by Ping command, and the time delay caused by the physical distance from the sensor to the data center can be calculated by dividing the distance from the sensor to the data center by the signal transmission speed (usually the light speed);
after correction, the acquired temperature data is fused using a data fusion algorithm:
Dividing a temperature interval of a sensor, and defining information entropy of the sensor:
，
In the method, in the process of the invention, Is the information entropy of the ith sensor,/>The probability distribution of the ith sensor in the (q) th temperature interval, and c is the number of the temperature intervals;
Fusing temperature data:
，
Wherein T is the temperature data after fusion, Is the temperature reading of the ith sensor,/>Is the information entropy of the ith sensor, n is the number of sensors;
Storing the fused data into a central database and extracting data characteristics:
，
where F represents the extracted data feature, n is the number of sensors, Is the temperature reading of the ith sensor,/>Is the average temperature.
The method has the advantages that the temperature interval of the sensor is divided by using histogram segmentation, the collected sensor data are uncertain and continuously changed data, after the data are subjected to preliminary processing of an edge calculation module, further timestamp correction and data fusion algorithm are implemented, time synchronization and precision consistency of the data from different sensors are ensured, the sensor data from different positions are effectively integrated by calculating the information entropy of each sensor and carrying out weighted fusion on the temperature data, the accuracy and the representativeness of temperature monitoring are enhanced, the fused data can reflect the overall temperature state of the battery pack, and high-quality input data are provided for a subsequent prediction model.
Further, constructing a neural network predictive model to predict battery temperature changes includes,
Constructing a multi-layer full-connection network as a neural network prediction model, and taking the extracted characteristics as input;
the final output layer predicts the battery temperature using a linear activation function;
The neural network prediction model is expressed as:
，
Where f (x) is the predicted battery temperature, x is the input eigenvector, 、/>、……、/>Is the weight matrix of the full-connection network of each layer,/>、/>、…、/>Is an offset item of the full-connection network of each layer,/>Representing an activation function;
Model training is carried out by using a training set, and training set data are marked synchronously;
the deviation between the predicted temperature and the actual observed temperature of the neural network prediction model is measured based on root mean square error, the formula is,
，
Where m is the number of training samples,Is the actual temperature of the j-th sample,/>The temperature of the j sample predicted by the neural network prediction model;
adjusting parameters of the neural network prediction model based on the evaluation result;
and deploying the neural network prediction model into a central database, and predicting the battery temperature of the collected temperature data of each battery pack to obtain a predicted temperature.
The activation function comprises a Sigmoid function, a ReLU function, a Softmax function and the like, in the embodiment, the ReLU function is optimized, the fused feature vector is processed by using a deep neural network, a multi-layer full-connection network is constructed as a neural network prediction model, high-precision prediction of battery temperature change is achieved, the neural network model predicts the battery temperature at a final output layer by using a linear activation function, the model is allowed to learn a complex nonlinear relation, so that the prediction accuracy is improved, the model can be continuously adapted to new battery performance data by continuously training the model and synchronously labeling training set data, the real-time performance and accuracy of a prediction effect are maintained, a model evaluation mechanism based on root mean square error ensures the model prediction accuracy, timely parameter adjustment is facilitated to adapt to the real-time working state of a battery, the reaction speed and early warning accuracy of the battery system are improved, scientific basis is provided for subsequent risk management, and the use safety and efficiency of the battery are remarkably improved.
S3, automatically executing emergency measures according to the prediction result, and visually displaying the early warning information;
specifically, automatically performing the contingency measure based on the prediction result includes,
Mean and standard deviation of temperature data were calculated:
，
，
In the method, in the process of the invention, Is the average of temperature data,/>Is the first temperature measurement, M is the total number of temperature measurements,/>Is the standard deviation of the temperature data;
calculating an alarm threshold for the temperature from the mean and standard deviation of the calculated temperature data:
The low-level alarm threshold is: ；
The medium alarm threshold is: ；
the advanced alert threshold is: ；
If it is The battery temperature is in a low risk state, a low-level alarm is triggered, the rotating speed of a cooling fan is increased, the battery charging rate is slightly reduced, the monitoring of the battery pack is enhanced, and temperature data are recorded;
If it is The method comprises the steps of indicating that the temperature of a battery is in a medium risk state, triggering a medium-level alarm, limiting the output power of the battery, increasing the flow rate of cooling liquid, and sending a warning to a driver, suggesting a speed reduction and stopping for rest;
If it is And the battery temperature is in a high-risk state, a high-level alarm is triggered, all the connections of the battery are automatically disconnected, the charging and discharging operations of the battery are stopped, the chemical-based coolant is used for rapid cooling, and the road rescue service and the battery maintenance team are automatically notified to provide the position and the state of the vehicle.
The threshold is set according to normal distribution assumption in statistical sense, and the average value and standard deviation of battery temperature data are calculated in real time, so that the temperature alarm threshold is automatically calculated and set, and temperature changes of different levels are responded quickly.
Further, the visual display of the early warning information means that a visual interface is built by using a modern Web development framework Vue. Js, a temperature change curve and an early warning indicator are drawn by using a data visual library, connection is built by a WebSocket protocol, the early warning information and the temperature change curve are updated to the visual interface in real time, an early warning system is integrated on the interface, different colors and early warning information are displayed according to alarms of different levels, a JavaScript library SWEETALERT is used for carrying out alarm popup, and maintenance personnel are notified through electronic mail.
The data visualization library refers to a JavaScript library, the WebSocket is a network communication protocol, a full duplex communication channel is provided, a real-time data visualization interface constructed by using a Vue.js frame and the WebSocket protocol can dynamically display battery temperature change and early warning information, the temperature change curve and the visualization of an early warning indicator not only help operators to intuitively know the battery state, but also can display early warning information with different colors according to different alarm levels, the attention of the operators can be quickly brought, the SWEETALERT library is used for carrying out alarm popup and notifying maintenance personnel through electronic mail, the transmission effect of the early warning information is further enhanced, the interactivity and the response capability of battery management are improved, and the timely transmission and processing of key information are ensured, so that the operation safety and reliability of a battery system are improved.
Example 2
Referring to fig. 3, in order to provide a second embodiment of the present invention, which is different from the previous embodiment, there is provided a new energy automobile battery detection system based on an integrated sensor, which includes,
The data acquisition and transmission module is used for deploying sensors on each group of batteries and constructing a sensor network, acquiring data in real time and transmitting the acquired data to the edge calculation module through a wireless network;
The edge calculation module is used for receiving the transmitted data, cleaning and format standardization the data, denoising and deleting abnormal values;
the feature extraction module is used for fusing the data subjected to the preliminary processing and extracting data features;
The prediction and emergency response module is used for constructing a prediction model to predict the battery temperature change trend and carrying out emergency response according to a prediction result;
and the visual display module is used for displaying the early warning information through a visual interface.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Claims (10)
1. A new energy automobile battery detection method based on an integrated sensor is characterized in that: comprising the steps of (a) a step of,
Deploying sensors on each group of batteries, constructing a sensor network, collecting data in real time, and transmitting the collected data to an edge computing module for preliminary processing;
Fusing the processed data and extracting features to construct a neural network prediction model to predict the temperature change of the battery;
and automatically executing emergency measures according to the prediction results, and visually displaying the early warning information.
2. The method for detecting the battery of the new energy automobile based on the integrated sensor as claimed in claim 1, wherein the method comprises the following steps: the steps of deploying sensors on each group of batteries and constructing a sensor network to collect data in real time are to deploy temperature sensors on the upper, middle and lower three layers of each group of new energy automobile batteries, comprehensively monitor the temperature distribution of the battery packs, use star network topology, use intermediate nodes as edge calculation modules, connect all the sensors, set data collection frequency, and use the deployed sensors to collect the temperature data of the battery packs in real time according to the set frequency.
3. The method for detecting the battery of the new energy automobile based on the integrated sensor as claimed in claim 2, wherein the method comprises the following steps: the step of transmitting the acquired data to the edge computing module for preliminary processing means that a timestamp is added to the acquired data and the acquired data is transmitted to the edge computing module through a wireless network, the acquired data is denoised by using a Kalman filter after the data is cleaned and format standardized, abnormal values are identified by using an IQR method, and the detected abnormal value data is deleted.
4. The method for detecting the battery of the new energy automobile based on the integrated sensor as claimed in claim 3, wherein the method comprises the following steps of: the step of fusing the processed data and extracting the characteristics means that the data subjected to preliminary processing is received from an edge calculation module, and the time stamps of the temperature data from different battery packs are corrected:
，
In the method, in the process of the invention, Is a corrected timestamp,/>Is the original timestamp,/>Is the time offset;
after correction, the acquired temperature data is fused using a data fusion algorithm:
Dividing a temperature interval of a sensor, and defining information entropy of the sensor:
，
In the method, in the process of the invention, Is the information entropy of the ith sensor,/>The probability distribution of the ith sensor in the (q) th temperature interval, and c is the number of the temperature intervals;
Fusing temperature data:
，
Wherein T is the temperature data after fusion, Is the temperature reading of the ith sensor,/>Is the information entropy of the ith sensor, n is the number of sensors;
Storing the fused data into a central database and extracting data characteristics:
，
where F represents the extracted data feature, n is the number of sensors, Is the temperature reading of the ith sensor,/>Is the average temperature.
5. The method for detecting the battery of the new energy automobile based on the integrated sensor as claimed in claim 4, wherein the method comprises the following steps: the constructing a neural network predictive model predicts battery temperature changes including,
Constructing a multi-layer full-connection network as a neural network prediction model, and taking the extracted characteristics as input;
the final output layer predicts the battery temperature using a linear activation function;
The neural network prediction model is expressed as:
，
Where f (x) is the predicted battery temperature, x is the input eigenvector, 、/>、……、/>Is the weight matrix of the full-connection network of each layer,/>、/>、…、/>Is an offset item of the full-connection network of each layer,/>Representing an activation function;
Model training is carried out by using a training set, and training set data are marked synchronously;
measuring deviation between the predicted temperature and the actual observed temperature of the neural network prediction model based on root mean square error;
adjusting parameters of the neural network prediction model based on the evaluation result;
and deploying the neural network prediction model into a central database, and predicting the battery temperature of the collected temperature data of each battery pack to obtain a predicted temperature.
6. The method for detecting the battery of the new energy automobile based on the integrated sensor as claimed in claim 5, wherein the method comprises the following steps: the automatically performing emergency measures based on the prediction results includes,
Mean and standard deviation of temperature data were calculated:
，
，
In the method, in the process of the invention, Is the average of temperature data,/>Is the first temperature measurement, M is the total number of temperature measurements,/>Is the standard deviation of the temperature data;
calculating an alarm threshold for the temperature from the mean and standard deviation of the calculated temperature data:
The low-level alarm threshold is: ；
The medium alarm threshold is: ；
the advanced alert threshold is: ；
If it is The battery temperature is in a low risk state, a low-level alarm is triggered, the rotating speed of a cooling fan is increased, the battery charging rate is slightly reduced, the monitoring of the battery pack is enhanced, and temperature data are recorded;
If it is The method comprises the steps of indicating that the temperature of a battery is in a medium risk state, triggering a medium-level alarm, limiting the output power of the battery, increasing the flow rate of cooling liquid, and sending a warning to a driver, suggesting a speed reduction and stopping for rest;
If it is And 3, indicating that the temperature of the battery is in a high-risk state, triggering a high-level alarm, automatically disconnecting all the connections of the battery, stopping the charging and discharging operations of the battery, using a chemical-based coolant to rapidly cool, and automatically informing a road rescue service and a battery maintenance team to provide the position and the state of the vehicle.
7. The method for detecting the battery of the new energy automobile based on the integrated sensor as claimed in claim 6, wherein the method comprises the following steps: the visual display of the early warning information means that a visual interface is built by using a modern Web development framework Vue. Js, a temperature change curve and an early warning indicator are drawn by using a data visual library, connection is built by a WebSocket protocol, the early warning information and the temperature change curve are updated to the visual interface in real time, an early warning system is integrated on the interface, different colors and early warning information are displayed according to alarms of different levels, a JavaScript library SWEETALERT is used for warning popup, and maintenance personnel are notified through electronic mail.
8. A new energy automobile battery detection system based on an integrated sensor, which adopts the method as set forth in any one of claims 1-7, and is characterized in that: comprising the steps of (a) a step of,
The data acquisition and transmission module is used for deploying sensors on each group of batteries and constructing a sensor network, acquiring data in real time and transmitting the acquired data to the edge calculation module through a wireless network;
The edge calculation module is used for receiving the transmitted data, cleaning and format standardization the data, denoising and deleting abnormal values;
the feature extraction module is used for fusing the data subjected to the preliminary processing and extracting data features;
The prediction and emergency response module is used for constructing a prediction model to predict the battery temperature change trend and carrying out emergency response according to a prediction result;
and the visual display module is used for displaying the early warning information through a visual interface.
9. A computer device, comprising: a memory and a processor; the memory stores a computer program characterized in that: the processor, when executing the computer program, implements the steps of the new energy automobile battery detection method based on the integrated sensor of any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program, when executed by a processor, implements the steps of the new energy vehicle battery detection method based on an integrated sensor of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667011.9A CN118244126A (en) | 2024-05-28 | 2024-05-28 | New energy automobile battery detection method and system based on integrated sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667011.9A CN118244126A (en) | 2024-05-28 | 2024-05-28 | New energy automobile battery detection method and system based on integrated sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118244126A true CN118244126A (en) | 2024-06-25 |
Family
ID=91555130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410667011.9A Pending CN118244126A (en) | 2024-05-28 | 2024-05-28 | New energy automobile battery detection method and system based on integrated sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118244126A (en) |
-
2024
- 2024-05-28 CN CN202410667011.9A patent/CN118244126A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108569607B (en) | Elevator fault early warning method based on bidirectional gating cyclic neural network | |
| CN109186813A (en) | A kind of temperature sensor self-checking unit and method | |
| KR102427205B1 (en) | Apparatus and method for generating training data of artificial intelligence model | |
| CN112925279A (en) | Fault comprehensive analysis system based on MES system | |
| CN108529380A (en) | Elevator safety prediction technique and system | |
| CN104471542A (en) | Discriminative hidden kalman filters for classification of streaming sensor data in condition monitoring | |
| KR101989962B1 (en) | Integrated management server and building management system using the same | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN114781476B (en) | System and method for analyzing faults of measuring equipment | |
| CN116758656A (en) | Vehicle-mounted terminal, system and method for vehicle supervision | |
| CN116520236B (en) | Abnormality detection method and system for intelligent ammeter | |
| CN106348119A (en) | Isolated elevator running safety monitoring system and method based on Internet of Things | |
| CN112232405A (en) | Fault prediction, monitoring and diagnosis method of gearbox and corresponding device | |
| CN117235443A (en) | Electric power operation safety monitoring method and system based on edge AI | |
| CN111579001A (en) | Fault detection method and device for robot | |
| CN109115271B (en) | Digit control machine tool remote monitoring system | |
| CN117170303B (en) | PLC fault intelligent diagnosis maintenance system based on multivariate time sequence prediction | |
| CN117367589A (en) | All-weather auxiliary temperature measurement system for substation main equipment based on AI technology | |
| CN117607780A (en) | Abnormality analysis system and analysis method for electric energy metering device | |
| CN118244126A (en) | New energy automobile battery detection method and system based on integrated sensor | |
| CN116048915A (en) | Index abnormality monitoring method and device, electronic equipment and storage medium | |
| CN206656749U (en) | Heat-engine plant sensor fault diagnosis system | |
| CN113934601A (en) | State evaluation method and system for switch cabinet acceptance robot | |
| CN114200334A (en) | Storage battery early warning method and device, vehicle and medium | |
| CN112363432A (en) | Monitoring system and monitoring method for hydropower station auxiliary equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |