Electric vehicle charging scene data acquisition device and electric vehicle charging system

Abstract

The utility model provides an electric vehicle charging scene data acquisition device and an electric vehicle charging system. In the electric vehicle charging scene data acquisition device, a processor is electrically connected with a memory, a temperature sensor, a current sensor, a network module and a camera respectively; the temperature sensor measures the battery temperature of the rechargeable battery, the current sensor measures the charging current of the rechargeable battery, and the camera obtains a real-time image of a charging place where the rechargeable battery is located; the processor sends the battery temperature and the charging current to the server through the network module, stores the real-time image in the memory, processes the real-time image through a fire recognition model, and sends a dangerous case image corresponding to a fire scene in the real-time image to the server through the network module when the fire scene is recognized; therefore, online supervision of the rechargeable battery is realized, and the safety of the charging process of the electric bicycle is improved.

Description

Technical Field

[0001] The utility model relates to the technical field of electric bicycle charging, and in particular to an electric bicycle charging scene data acquisition device and an electric bicycle charging system. Background Art

[0002] Lithium batteries have the characteristics of high energy density, long cycle life, and are not easily affected by the environment. They have become an energy component of modern electric vehicles and electric bicycles. Although lithium batteries have many advantages, as the use time and charging frequency increase, the battery performance gradually deteriorates. In high temperature environments or extrusion conditions, it is easy to cause micro short circuits inside the battery, and even cause the battery to spontaneously combust or explode, posing a major threat to personal and property safety.

[0003] At present, the commonly used methods for lithium battery charging analysis include the ampere-hour integration method, the open circuit voltage method, the Kalman filter method, etc. These methods can calculate the battery state of charge (SOC) well and improve the accuracy of lithium battery charging. However, these methods have poor real-time performance and lack the collection of real-time data on the charging site, and cannot meet the needs of online supervision of lithium battery charging.

[0004] At the same time, most existing centralized charging systems for electric vehicles are open-loop systems that only have charging, payment, and basic overcurrent protection functions. They do not monitor the charging scene in real time and lack full safety protection for the battery charging process.

[0005] Therefore, it is necessary to provide a technical solution that can collect electric vehicle charging scene data in real time for the system to perform real-time analysis. Utility Model Content

[0006] In order to solve the above technical problems, the utility model provides an electric vehicle charging scene data acquisition device and an electric vehicle charging system.

[0007] A technical solution adopted by the utility model to solve its technical problem is: an electric vehicle charging scene data acquisition device, including a processor, a memory, a temperature sensor, a current sensor, a network module, and a camera;

[0008] The data end of the processor is electrically connected to the data end of the memory, the first data acquisition end is electrically connected to the data end of the temperature sensor, the second data acquisition end is electrically connected to the data end of the current sensor, the transmission end is electrically connected to the data end of the network module, and the image data end is electrically connected to the data end of the camera;

[0009] The temperature sensor is used to measure the battery temperature of the rechargeable battery and transmit it to the processor, the current sensor is used to measure the charging current of the rechargeable battery and transmit it to the processor, and the camera is used to obtain a real-time image of the charging place where the rechargeable battery is located and transmit it to the processor;

[0010] The processor sends the acquired battery temperature and the charging current to the server through the network module, and stores the acquired real-time image in the memory;

[0011] The processor processes the real-time image through a fire recognition model, and when a fire scene is recognized, sends the dangerous image in the real-time image corresponding to the fire scene stored in the memory to the server through the network module.

[0012] In a possible implementation manner, the current sensor is a current transformer.

[0013] In a possible implementation, the temperature sensor is a thermistor.

[0014] In one possible implementation, the processor is a RISC-V processor.

[0015] In a possible implementation, the network module adopts a 5G DTU module.

[0016] In a possible implementation, it also includes a power supply that is electrically connected to the power supply end of the temperature sensor, the power supply end of the current sensor, the power supply end of the processor, the power supply end of the memory, the power supply end of the network module, and the power supply end of the camera.

[0017] The utility model also provides an electric vehicle charging system, comprising a server and the electric vehicle charging scene data collection device as described above;

[0018] The server is connected to the electric vehicle charging scene data collection device via a network.

[0019] Beneficial effects of the utility model:

[0020] By sending the measured battery temperature and charging current of the rechargeable battery to the server, it is convenient to monitor the working condition of the rechargeable battery online in real time. By processing the real-time image through the fire recognition model and sending the dangerous situation image to the server, the remote system can be informed of the dangerous situation in time, so as to take safety measures in time and reduce losses. This realizes online supervision of the rechargeable battery and improves the safety of the electric bicycle charging process. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1A schematic diagram of a structure of an electric vehicle charging scene data acquisition device provided by an embodiment of the utility model;

[0022] Figure 2 Another structural schematic diagram of the electric vehicle charging scene data acquisition device provided by an embodiment of the utility model;

[0023] Figure 3 The present invention provides a schematic diagram of the structure of an electric vehicle charging system. DETAILED DESCRIPTION

[0024] In order to deepen the understanding of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. The embodiments are only used to explain the present invention and do not limit the protection scope of the present invention.

[0025] Please refer to Figure 1 and Figure 2 , the embodiment disclosed in this application relates to a technical solution: an electric vehicle charging scene data acquisition device, including a processor, a memory, a temperature sensor, a current sensor, a network module, and a camera;

[0026] The data end of the processor is electrically connected to the data end of the memory, the first data acquisition end is electrically connected to the data end of the temperature sensor, the second data acquisition end is electrically connected to the data end of the current sensor, the transmission end is electrically connected to the data end of the network module, and the image data end is electrically connected to the data end of the camera;

[0027] The temperature sensor is used to measure the battery temperature of the rechargeable battery and transmit it to the processor, the current sensor is used to measure the charging current of the rechargeable battery and transmit it to the processor, and the camera is used to obtain a real-time image of the charging place where the rechargeable battery is located and transmit it to the processor;

[0028] The processor sends the acquired battery temperature and the charging current to the server through the network module, and stores the acquired real-time image in the memory;

[0029] The processor processes the real-time image through a fire recognition model, and when a fire scene is recognized, sends the dangerous image in the real-time image corresponding to the fire scene stored in the memory to the server through the network module.

[0030] In this embodiment, the processor can be of a conventional type and can run an algorithm model as needed, such as a RISC-V processor. The memory adopts a conventional model and can be used to store data such as images, such as a flash memory. Both the temperature sensor and the current sensor adopt conventional models. The network module and the camera can adopt existing finished products. The electric vehicle charging scene data acquisition device can be regarded as an intelligent lithium battery charging control device, which is essentially an edge computing and control device. The current sensor can adopt a current transformer, which monitors the charging current of the rechargeable battery in real time. After the current data is converted into a digital signal by an A / D converter, it is uploaded to the server by the processor through the network module. The A / D converter can be a functional module inside the processor, or it can be a separate conventional AD conversion circuit set outside the processor. The temperature sensor can adopt a thermistor, which measures the temperature of the rechargeable battery in real time. After the processor obtains the corresponding temperature data, it uploads it to the server through the network module. The camera collects the on-site image of the charging place and stores it in the local memory of the control device. The YOLO-based fire recognition model runs on the processor. If a fire is recognized, the images 10 seconds before and after the recognition are sent to the server using a network module (such as a 5G module). The parameters of the camera can be set by the processor, and the processor can set the camera angle, image parameters, etc. of the camera based on internal default settings or remote instructions from the server.

[0031] In a specific implementation, an electric bicycle is connected to an electric vehicle charging scene data acquisition device, and the parameters of the currently charged lithium battery are collected through the current sensor and temperature sensor on the electric vehicle charging scene data acquisition device. These parameters can be directly transmitted to the server, or they can be first stored in the local flash memory, and smoothed and filtered by a sliding window method. The processed data is uploaded to the application server on the Internet through a network module (such as a 5G DTU module), and the application server is deployed on a server where a corresponding entity exists. The application server can be deployed using Docker technology, and the received data is saved in a database. A charging algorithm model runs on the application server, which is a model composed of a GRU neural network with a memory function. It can predict the charging current based on the current charging data of the lithium battery. When it exceeds the stable threshold, it will push abnormal information to require user intervention. At the same time, a web system runs on the application server, which can realize functions such as charging data query, statistics and visualization, and meet the needs of user interaction and data display. This function adds a charging current prediction function using a neural network on the basis of the traditional centralized charging function, which can intervene in danger in advance.

[0032] At the same time, the camera in the electric vehicle charging scene data acquisition device can capture the charging image of the current charging place, such as the electric bicycle on the charging pile, and the image is saved locally (i.e., the memory) in a whole cycle of 1 minute. The processor (such as the RISC-V processor) of the electric vehicle charging scene data acquisition device runs the YOLO recognition model (i.e., the fire recognition model or the flame recognition model) locally. The model enhances the feature extraction for the flame and can quickly realize the automatic detection of the fire. When the fire is detected, the electric vehicle charging scene data acquisition device will upload the images within 10 seconds before and after the fire to the application server, and use the MQTT of the application server to quickly push the fire alarm to the user, so as to realize the closed-loop control of safe charging.

[0033] In a possible implementation manner, the current sensor is a current transformer.

[0034] In this embodiment, the current transformer can be a conventional model. In specific implementation, the current transformer can be set on the power supply that provides charging power for the electric vehicle, and the conventional connection method is used to realize the monitoring of the charging current.

[0035] In a possible implementation, the temperature sensor is a thermistor.

[0036] In this embodiment, the thermistor can be a conventional type. In specific implementation, the thermistor can be set at the heat dissipation position of the power supply that provides charging power for the electric vehicle, or at other positions that can directly or indirectly represent the temperature of the rechargeable battery, and can be selected according to actual needs.

[0037] In one possible implementation, the processor is a RISC-V processor.

[0038] In a possible implementation, the network module adopts a 5G DTU module.

[0039] In a possible implementation, it also includes a power supply that is electrically connected to the power supply end of the temperature sensor, the power supply end of the current sensor, the power supply end of the processor, the power supply end of the memory, the power supply end of the network module, and the power supply end of the camera.

[0040] In this embodiment, the power supply may be in conventional form, such as a conventional rechargeable battery, or a power supply module that converts alternating current through a transformer. The specific form may be selected according to actual implementation needs.

[0041] Please refer to Figure 3 , the utility model also provides an electric vehicle charging system, including a server and the electric vehicle charging scene data acquisition device as described above;

[0042] The server is connected to the electric vehicle charging scene data collection device via a network.

[0043] In this embodiment, the electric vehicle charging scene data acquisition device can be regarded as an edge computing device to realize intelligent lithium battery charging control. Fire AI recognition can be realized through the camera. At the same time, based on the monitoring of the charging data of the lithium battery, AI charging safety prediction and intervention can be realized. The server and the electric vehicle charging scene data acquisition device can be connected by a 5G network or a fiber optic network to realize timely transmission of data. When the server determines that a dangerous situation has occurred, it can also promptly notify relevant personnel through MQTT information push so that they can take corresponding safety measures in time to prevent the occurrence of dangerous situations or reduce the losses caused by dangerous situations that have already occurred.

[0044] To facilitate the normal operation of the electric vehicle charging system, its overall architecture includes: data acquisition layer, transmission layer, data processing layer and application layer. The data acquisition layer collects key parameters such as charging current and temperature of lithium batteries through the electric vehicle charging scene data acquisition device, and the camera can obtain real-time images of centralized charging places. The transmission layer transmits these data to the processing layer in real time through network communication technology, including wired and wireless data transmission (mainly 5G communication technology and Internet technology). The transmission network provides a high-speed, low-latency data transmission channel, which can transmit the data collected on site to the application server. Considering factors such as signal strength and base station coverage, the 5G communication network can be used. The processing layer processes and analyzes the received data, calculates the charging status through the algorithm model built on the server, and estimates the charging status and power of the battery. The application layer is an application system built on the server, which is responsible for control, user operation interaction and push of special information during the charging process.

[0045] The application server is mainly used for data processing, analysis and storage. It uses Docker technology to improve rapid deployment and expansion capabilities. It also provides web-based data query, statistics and visualization functions to achieve user interaction and data display. The charging algorithm model is a neural network model based on a machine learning algorithm, built on the application server. The model can automatically identify and estimate the SOC value of the lithium battery based on the collected current data. The weight parameters of the recognition model are trained in advance and can continue to be trained and optimized on the server to improve the estimation accuracy and stability.

[0046] The electric vehicle charging system proposed by the utility model can collect the charging data of the electric vehicle lithium battery in real time and upload it to the server, build a charging algorithm model on the server, and predict the charging process by calculating the uploaded real-time data to prevent the danger caused by overcharging. The on-site equipment obtains the charging scene image through the camera, and through the flame recognition model on the local device (i.e., the electric vehicle charging scene data acquisition device), it issues a fire alarm for the spontaneous combustion situation, and pushes the alarm or charging abnormality to the user through the platform, realizing closed-loop control of charging safety.

[0047] The above embodiments should not limit the present invention in any way, and any technical solutions obtained by equivalent replacement or equivalent conversion shall fall within the protection scope of the present invention.

Claims

1. An electric vehicle charging scene data collection device, characterized in that: Including processor, memory, temperature sensor, current sensor, network module, camera; The data end of the processor is electrically connected to the data end of the memory, the first data acquisition end is electrically connected to the data end of the temperature sensor, the second data acquisition end is electrically connected to the data end of the current sensor, the transmission end is electrically connected to the data end of the network module, and the image data end is electrically connected to the data end of the camera; The temperature sensor is used to measure the battery temperature of the rechargeable battery and transmit it to the processor, the current sensor is used to measure the charging current of the rechargeable battery and transmit it to the processor, and the camera is used to obtain a real-time image of the charging place where the rechargeable battery is located and transmit it to the processor; The processor sends the acquired battery temperature and the charging current to the server through the network module, and stores the acquired real-time image in the memory; The processor processes the real-time image through a fire recognition model, and when a fire scene is recognized, sends the dangerous image in the real-time image corresponding to the fire scene stored in the memory to the server through the network module.

2. The electric vehicle charging scene data acquisition device according to claim 1, characterized in that: The current sensor is a current transformer.

3. The electric vehicle charging scene data acquisition device according to claim 1, characterized in that: The temperature sensor is a thermistor.

4. The electric vehicle charging scene data acquisition device according to claim 1, characterized in that: The processor is a RISC-V processor.

5. The electric vehicle charging scene data acquisition device according to claim 1, characterized in that: The network module adopts a 5G DTU module.

6. The electric vehicle charging scene data acquisition device according to claim 1, characterized in that: It also includes a power supply that is electrically connected to the power supply end of the temperature sensor, the power supply end of the current sensor, the power supply end of the processor, the power supply end of the memory, the power supply end of the network module, and the power supply end of the camera.

7. An electric vehicle charging system, characterized in that: It comprises a server and the electric vehicle charging scene data acquisition device as claimed in claim 1; The server is connected to the electric vehicle charging scene data collection device via a network.

Images