Automatic protection type charging method for electric vehicle

Abstract

The invention discloses an electric vehicle automatic protection type charging method, and relates to the technical field of electric vehicle charging, and the method comprises the steps: carrying out the license plate recognition and vehicle type matching of a vehicle entering a charging area, carrying out the dual authentication of the identity of a vehicle owner through employing the face recognition technology, and carrying out the authority verification through combining background information; after the electric vehicle is charged, starting charging equipment, acquiring monitoring data of a charging parking space area, and performing fire risk monitoring; moving object features are distinguished through an intelligent recognition algorithm, a warning mode is automatically adjusted according to different types of objects, and abnormal events are pushed in real time. According to the invention, the safety in the charging process is improved, the intelligent management of the charging facility is enhanced, and the safety and operation efficiency of the charging station can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging, and particularly to an automatic protection charging method and system for electric vehicles. Background Art

[0002] In recent years, with the rapid development of the electric vehicle industry, the charging demand for electric vehicles has been increasing continuously. As an important part of the electric vehicle infrastructure, charging piles have become the research focus in the fields of intelligent transportation and energy management. Traditional charging pile systems mainly focus on providing charging interfaces and managing power supply, but there are still many problems in terms of safety and convenience during the charging process. With the popularization of electric vehicles, especially in public charging places, how to effectively ensure the safety during the charging process, improve the equipment utilization efficiency and prevent potential risks has become an important direction for technological development. In recent years, the application of technologies such as license plate recognition, face recognition, and object monitoring has been gradually introduced into intelligent charging management systems, which provides new solutions for improving the safety and automation level of charging piles.

[0003] Although existing charging management systems have integrated some intelligent technologies, such as license plate-based vehicle recognition and simple identity authentication functions, most systems still rely on manual intervention and simple power measurement, lacking the ability to monitor potential safety hazards during the charging process in real time and respond emergently. The existing technologies have the following deficiencies: First, the existing vehicle owner identity verification usually only relies on license plate recognition or account information, lacking a dual authentication mechanism, which may pose certain safety hazards; Second, the monitoring of charging equipment and the environment mainly relies on manual inspection or simple fire alarm systems, lacking an intelligent early warning mechanism for potential fire risks such as temperature and smoke; Finally, most existing object recognition technologies only stay at the basic motion detection stage and cannot adjust the intelligent warning mode according to the object type, resulting in the system's response to safety events being neither timely nor accurate enough. Summary of the Invention

[0004] Therefore, the problem to be solved by the present invention is how to improve the safety and automation level of charging stations by integrating advanced identity authentication, fire monitoring, and intelligent warning systems.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] In the first aspect, an embodiment of the present invention provides an automatic protection charging method for electric vehicles, which includes performing license plate recognition and vehicle type matching on vehicles entering the charging area, and at the same time using face recognition technology to perform dual authentication on the vehicle owner's identity and performing permission verification in combination with background information;

[0007] After the electric vehicle starts charging, start the charging device, obtain the monitoring data of the charging bay area, and conduct fire risk monitoring;

[0008] Distinguish the characteristics of moving objects through intelligent recognition algorithms, automatically adjust the warning method according to different object types, and push abnormal events in real time.

[0009] As a preferred solution of the automatic protection charging method for electric vehicles according to the present invention, wherein: the permission verification includes the following steps,

[0010] When the vehicle enters, in combination with the owner's reservation system, the system generates an authorization code according to the owner's reservation information, and verifies whether the vehicle has the charging permission by comparing the information in the authorization code;

[0011] If the license plate number in the owner's reservation information exactly matches the current license plate recognition result, and the owner successfully passes the face recognition authentication, then the owner's identity is verified as legal;

[0012] If the license plate number in the owner's reservation information partially matches the current license plate recognition result, and the owner successfully passes the face recognition authentication, then the system will additionally conduct a manual review of the owner's identity to confirm whether the owner is the owner of the vehicle, and only allow charging after the owner confirms;

[0013] If the vehicle model in the owner's reservation information matches the current vehicle model, and the owner passes the face recognition authentication, then continue to verify whether the owner's reserved time period coincides with the current time period;

[0014] If the vehicle model in the owner's reservation information does not match the current vehicle model, and the owner passes the face recognition authentication, then the system will remind the owner and request confirmation of the vehicle model. After the owner provides the correct vehicle model and the vehicle meets the electric vehicle standard, the system dynamically allocates a charging bay according to the current available bays and allows the vehicle to enter;

[0015] If the license plate number in the owner's reservation information matches the current license plate recognition result, the owner's face recognition passes, and the current time is within the reserved time period, then the verification passes and the vehicle is allowed to charge;

[0016] If the license plate number in the owner's reservation information matches the current license plate number, but the owner's face recognition fails, then the system starts secondary identity verification. If the license plate number in the owner's reservation information exactly matches the current license plate number, but the current vehicle does not meet the electric vehicle standard, then the system rejects the charging and prompts the owner that the vehicle does not meet the charging requirements.

[0017] As a preferred solution of the automatic protection charging method for electric vehicles according to the present invention, wherein: the monitoring data includes smoke concentration data, temperature change data, and flame spectrum data; the infrared thermal imager scans the temperature distribution of the charging device and the vehicle chassis in real time to obtain the thermal imaging data of the charging bay area;

[0018] Normalize the collected smoke concentration data, temperature change data, flame spectrum data, and thermal imaging data, and extract the effective data features after removing the noise data;

[0019] Use the principal component analysis PCA to reduce the dimension of the effective data features and extract the key feature vectors. The calculation formula is:

[0020]

[0021] In the formula, n is the number of samples, X is the data matrix, X T is the transpose of the data matrix, C is the covariance matrix, and the feature vectors corresponding to the first k largest eigenvalues are selected as the principal components;

[0022] Adopt the convolutional neural network CNN in deep learning combined with the long short-term memory network LSTM to construct a fire risk prediction model, and use the convolutional neural network CNN to process the thermal imaging images;

[0023] Input the time series data of the smoke concentration data, temperature change data, and flame spectrum data into the long short-term memory network LSTM, and output the fire risk features in the time series data;

[0024] Merge the image features extracted by CNN and the time series features extracted by LSTM into a comprehensive feature vector;

[0025] Process the comprehensive feature vector through the fully connected layer, output the fire risk probability, and determine the risk level according to the fire risk probability to decide to take corresponding measures. The calculation formula is:

[0026] P = σ(W o F + b o )

[0027] Among them, P represents the fire risk probability, W o and b o are the weights and biases of the fully connected layer respectively, σ is the sigmoid function, which maps the output value to the interval [0,1], and F is the comprehensive feature vector;

[0028] Use historical fire data and normal charging data as the training set to train the model. During the training process, evaluate the model through the validation set.

[0029] As a preferred solution of the electric vehicle automatic protection charging method of the present invention, wherein: the risk level is judged according to the fire risk probability and the corresponding measures are taken, including calculating the risk preset threshold value, and the calculation formula is:

[0030]

[0031] Where P t Preset threshold for risk, P j is the fire risk probability calculated in the jth monitoring, w j is the weight factor, giving higher weight to more recent data, R 1 is the number of monitoring times;

[0032] When the fire risk probability P ≤ the risk preset threshold P t When the system determines that the current fire risk probability is in the low risk range, the system enters the low risk warning state. The system collects the environmental data of the charging parking space in real time through temperature sensors, smoke sensors, flame sensors and infrared thermal imagers, and transmits the data to the local controller and cloud server for storage and secondary analysis. The data is evaluated regularly. If the fire risk probability P is continuously monitored to be greater than the risk preset threshold P in the low risk warning state, the system will automatically enter the low risk warning state. t When the system automatically switches to the medium risk warning state, the medium risk response measures are triggered. The system sends a warning message to the manager's mobile terminal, indicating the potential fire risk and suggesting that the manager conduct an on-site inspection. At the same time, the charging power is automatically cut off, the charging process is stopped, the ventilation system is started, and the fire risk probability continues to be monitored. In the medium risk state, the fire risk probability P is greater than the risk preset threshold P t The system will automatically switch to high-risk warning status;

[0033] When the fire risk probability P> the risk preset threshold P t When the fire risk probability is in the high risk range, the system enters the high risk warning state. The system immediately sends an emergency alarm to the management personnel and the fire department, and sends the alarm information to the remote monitoring platform. If in the high risk state, the fire risk probability P> the risk preset threshold P t If the temperature does not drop, the system will automatically enter the emergency processing mode.

[0034] As a preferred solution of the electric vehicle automatic protection charging method of the present invention, the distinguishing characteristics of the moving object includes the following steps:

[0035] Use a high-definition camera to collect video frames of the charging area, and pre-process the collected images, including grayscale, denoising, and standardization;

[0036] A background model is established through the Gaussian Mixture Model (GMM). In each pre - processed frame of the image, the difference between the current image and the background model is calculated to detect moving objects. The motion direction and speed of the moving objects are calculated by the optical flow method;

[0037] Kalman filtering is used to track the trajectories of the objects' motion, calculate the displacement and speed of the moving objects, generate bounding boxes for each detected object, and record the motion information of the bounding boxes;

[0038] For each moving object, its shape features and motion features are extracted;

[0039] A convolutional neural network (CNN) is used to train an object classification model. The features of the detected moving objects are used as inputs for object classification. The cross - entropy loss function is adopted, and the network weights are optimized through the standard backpropagation algorithm. The loss function is defined as:

[0040]

[0041] where L is the value of the loss function, N is the number of samples, y i is the true label of the i - th sample, and P i is the predicted fire risk probability of the i - th sample;

[0042] The features of the detected moving objects are input, and the object types are classified through the trained CNN model to obtain the object categories, and the category labels and probability values of the objects are output;

[0043] According to the recognition results of the object types, the warning method is automatically adjusted to ensure the safety of the charging area.

[0044] As a preferred scheme of the automatic protection charging method for electric vehicles described in the present invention, wherein: the recognition results of the object types include,

[0045] When the system recognizes that there are animals in the charging area, the system starts the ultrasonic dispersion device, adjusts the frequency and intensity of the ultrasonic waves according to the size and type of the animals, and adjusts the emission direction and intensity of the ultrasonic waves according to the movement speed and relative position of the animals;

[0046] When the system recognizes that there are humans in the charging area, the system starts both voice alarms and visual warnings at the same time. The system reminds personnel through voice broadcasts, gives safety tips to the personnel entering the charging area, dynamically adjusts the frequency and volume of the voice according to the distance and staying time of the personnel. When humans continue to approach the charging area, the warning lights flash, and the safety warning board displays warning messages to remind personnel to keep a safe distance;

[0047] When the system detects other objects in the charging area, it activates a low-frequency warning, either through voice prompts or by displaying warning messages on the screen, to alert the vehicle owner of the presence of other objects.

[0048] The beneficial effects of the present invention are as follows: by combining license plate and face recognition technologies for dual authentication, integrating a fire risk monitoring and intelligent response mechanism, and object type recognition and dynamic warning adjustment, it not only improves the safety during charging but also enhances the intelligent management of charging facilities. Through precise identity authentication, real-time fire monitoring, and personalized warning mechanisms, it effectively improves the safety and operational efficiency of charging stations, belonging to a technological innovation in the field of electric vehicle charging systems and intelligent safety monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0050] Figure 1 It is a flowchart of the automatic protection charging method for electric vehicles in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To make the above objects, features, and advantages of the present invention more clearly understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0052] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from the description herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0053] Secondly, the so-called "one embodiment" or "embodiment" herein refers to specific features, structures, or characteristics that can be included in at least one implementation of the present invention. The phrase "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or selectively exclusive embodiment with other embodiments.

[0054] Embodiment 1

[0055] Refer to Figure 1 , which is the first embodiment of the present invention. This embodiment provides an automatic protection charging method for electric vehicles. As Figure 1 shown, it includes the following:

[0056] S1: Identify the license plate and match the vehicle model of the vehicle entering the charging area. At the same time, use face recognition technology to conduct dual authentication of the vehicle owner's identity, and perform permission verification in combination with the background information.

[0057] Specifically, use a high-definition camera to identify the license plate of the vehicle entering the charging area from multiple angles and match the vehicle model. At the same time, use face recognition technology to conduct dual authentication of the vehicle owner's identity, and perform permission verification in combination with the background reservation information to achieve precise access management in the charging area.

[0058] 1. The vehicle owner's reservation information generates an authorization code

[0059] Before charging, the vehicle owner needs to make a reservation through a designated reservation platform (such as a charging pile APP, website, etc.). The reservation content usually includes vehicle owner information (such as name, vehicle owner ID number or mobile phone number), vehicle information (such as license plate number, vehicle model, etc.), and the charging time period and location.

[0060] After the vehicle owner completes the reservation, the system will store this information in the background database and generate a unique authorization code according to the specific content of the reservation. The authorization code is not just an ordinary identification mark. It also contains data such as the vehicle owner's reservation information, vehicle information, and reservation time, ensuring that each reservation is bound to a specific vehicle owner and vehicle.

[0061] When the vehicle owner arrives at the charging area, the system will generate an authorization code according to the vehicle owner's reservation information and send it to the vehicle owner by means of SMS, APP push, or QR code for identity verification through the authorization code.

[0062] 2. Vehicle owner face recognition and identity authentication

[0063] Install a high-definition camera at the entrance of the charging area. When the vehicle owner needs to pass through this area, the system will automatically capture the vehicle owner's facial image. The high-definition camera is equipped with infrared induction and dynamic adjustment functions to ensure clear shooting regardless of the vehicle owner's facial orientation.

[0064] When the vehicle owner enters the recognition range, the system performs real-time scanning of the vehicle owner's face through a deep learning algorithm (such as the convolutional neural network CNN) and extracts facial features (such as the positions and relative proportions of the eyes, nose, mouth, etc.).

[0065] The system compares the captured facial features with the facial data uploaded by the vehicle owner on the reservation platform. This process uses face recognition technology and judges whether it is the same person through methods such as feature point matching and deep feature learning. If the match is successful, the system considers the vehicle owner to be a legitimate user and enters the next verification link; if the match fails, the system prompts that the vehicle owner's identity verification fails and the operation cannot continue.

[0066] 3. Matching of vehicle owner identity and reservation information

[0067] After the vehicle owner passes the face recognition, the system continues to recognize the license plate number of the vehicle through a high-definition camera and confirm the type of the vehicle through image recognition technology. The system will use character recognition technology (such as OCR technology) to extract the license plate number and compare it with the license plate number provided by the vehicle owner during the reservation.

[0068] The system will also check whether the license plate number and vehicle type information in the vehicle owner's reservation information match the currently recognized vehicle. If the match is successful, it indicates that the vehicle has the charging permission during the reservation period; if the license plate or vehicle type does not match the reservation information, the system will reject the vehicle owner's charging request and remind the vehicle owner to check the reservation information or provide modifications.

[0069] 4. Confirmation of Charging Permission

[0070] After the vehicle and the vehicle owner's identity are confirmed correctly, the system will verify again whether the vehicle owner enters the charging area during the reserved time period by comparing the information in the authorization code (such as vehicle owner information, reserved time period, etc.).

[0071] If all information matches and passes the verification, the system will allow the vehicle owner to enter the charging area, the charging pile will be turned on, and the vehicle owner can start the charging operation.

[0072] If any abnormality is found in any link (such as the vehicle owner's identity does not match, the license plate does not match, the reserved time does not match, etc.), the system will automatically terminate the access permission and inform the vehicle owner of the reason for refusal to enter through voice or screen prompts.

[0073] If the license plate number in the vehicle owner's reservation information exactly matches the current license plate recognition result and the vehicle owner successfully passes the face recognition authentication, the vehicle owner's identity is verified as legal.

[0074] If the license plate number in the vehicle owner's reservation information partially matches the current license plate recognition result (such as some blurred characters appear in the license plate recognition) and the vehicle owner successfully passes the face recognition authentication, the system will conduct an additional manual review of the vehicle owner's identity to confirm whether the vehicle owner is the owner of the vehicle, and only allow charging after the vehicle owner confirms.

[0075] If the vehicle type in the vehicle owner's reservation information matches the current vehicle type and the vehicle owner passes the face recognition authentication, the system verifies that the vehicle owner's reserved time period overlaps with the current time period.

[0076] If the vehicle type in the vehicle owner's reservation information does not match the current vehicle type and the vehicle owner passes the face recognition authentication, the system will warn the vehicle owner and require confirmation of the vehicle type; if the vehicle owner provides the correct vehicle type, the system will dynamically allocate a parking space according to the current available parking spaces and allow entry.

[0077] If the license plate number in the vehicle owner's reservation information matches the license plate number of the current vehicle, and the vehicle owner's face recognition is passed, and the current time is within the reservation period, then the verification is passed and charging is allowed.

[0078] If the license plate number in the vehicle owner's reservation information matches the current license plate number, but the vehicle owner's face recognition fails, the system will initiate secondary identity verification: requiring the vehicle owner to present an identity document or verify the mobile phone number.

[0079] If the license plate number in the vehicle owner's reservation information exactly matches the current license plate number, and the current vehicle belongs to the electric vehicle type, and the vehicle owner's identity passes the face recognition authentication, the system verifies the remaining battery power of the vehicle and reasonably arranges the charging period according to the remaining power to avoid overcharging.

[0080] If the license plate number in the vehicle owner's reservation information exactly matches the current license plate number, but the current vehicle does not meet the electric vehicle standard (such as the license plate is recognized as a hybrid or fuel vehicle), the system rejects the charging and prompts the vehicle owner that the vehicle does not meet the charging requirements.

[0081] By performing license plate recognition and vehicle type matching on the vehicles entering the charging area, and at the same time using face recognition technology for double authentication of the vehicle owner's identity, strict identity verification during the charging process is achieved. Compared with the traditional system that only relies on the license plate recognition system, double authentication can significantly improve the accuracy and security of identity verification, prevent unauthorized vehicles from using the charging equipment, and thus effectively eliminate potential safety hazards and resource abuse. This step not only ensures the safety of the charging system, but also improves the utilization efficiency of the charging station resources, ensuring that only authorized electric vehicles can charge, and enhancing the user experience and the precision of equipment management.

[0082] Combined with the background information, the system conducts permission verification on the vehicle owner's reservation system. After the vehicle owner completes the identity verification through license plate, vehicle type and face recognition information, the system can automatically match and dynamically allocate charging spaces. This ensures the reasonable allocation of charging spaces, avoids human intervention and queuing, and at the same time optimizes the overall operation efficiency of the charging station. In addition, the system can handle the situation where the vehicle owner's identity authentication fails, and through manual review, ensure that every link in the charging process complies with safety specifications. This not only effectively prevents charging fraud, but also enhances the automated management ability of the charging system.

[0083] S2: After the electric vehicle starts charging, start the charging equipment, obtain the monitoring data of the charging space area, and conduct fire risk monitoring;

[0084] Specifically, a distributed temperature sensor network and AI intelligent infrared thermal imaging system are used to conduct a full-scale thermal distribution scan of the charging parking area, and a temperature change curve model of the vehicle charging process is established. When abnormal temperature fluctuations or hot spot accumulation are detected, the system will issue a graded warning.

[0085] After the vehicle identity verification is passed, the charging equipment is started, and the system initializes the fire monitoring, small animal repelling and intelligent prediction functions. Activate the fire sensor (smoke sensor, temperature sensor, flame sensor). Start the infrared thermal imager to scan the temperature distribution of the charging equipment and vehicle chassis in real time. Start the small animal activity sensor (infrared induction, microwave radar).

[0086] Each sensor collects data in real time and transmits the data to the local controller through the wireless communication module. The local controller aggregates the data and uploads it to the cloud server through the 5G network for analysis by intelligent algorithms.

[0087] Fire monitoring and identification, the temperature sensor monitors the temperature changes of the charging parking space in real time. If the temperature exceeds the preset temperature threshold, the system marks it as a potential fire risk point. The smoke sensor detects the smoke concentration in the air. If the smoke concentration exceeds the preset smoke concentration threshold, the system triggers an alarm. The flame sensor detects the spectral characteristics of the flame. If a flame is detected, the system immediately triggers a fire alarm.

[0088] The infrared thermal imager scans the temperature distribution of the charging equipment and the vehicle chassis at a frequency of 10 frames per second to generate real-time thermal images. The system identifies high-temperature areas through image processing algorithms and marks them as potential hot spots. The high-temperature areas are continuously monitored. If the temperature rises by more than 20°C in a short period of time, the system determines it as a fire risk area.

[0089] Normalize the collected temperature, smoke concentration, flame signal and thermal imaging data, remove noise data, and extract effective features (such as temperature change rate, smoke concentration change rate, high temperature area, etc.).

[0090] Temperature features: extract temperature change rate, temperature peak, temperature gradient and other features. Smoke features: extract smoke concentration change rate, smoke diffusion speed and other features. Thermal imaging features: extract high temperature area, high temperature area temperature change rate, thermal imaging texture features and other features.

[0091] Use principal component analysis PCA to reduce the dimension of effective data features and extract key feature vectors. The calculation formula is:

[0092]

[0093] In the formula, n is the number of samples, X is the data matrix, and X Tis the transpose of the data matrix, C is the covariance matrix, and the eigenvectors corresponding to the top k largest eigenvalues are selected as the principal components;

[0094] A fire risk prediction model is constructed by combining the convolutional neural network (CNN) in deep learning with the long short-term memory network (LSTM).

[0095] Use the convolutional neural network (CNN) to process the thermal imaging images. Extract local features in the images, such as the shape and size of the high-temperature areas. Reduce the dimension of the features through pooling (usually max pooling), while retaining the most important information. After multiple layers of convolution and pooling, the image features related to the fire risk are extracted.

[0096] Input the time series data of temperature, smoke concentration, and flame signal into the long short-term memory network (LSTM). Capture dynamic changes: LSTM can remember past inputs and determine whether the current changes are abnormal. For example, a rapid increase in temperature or a sudden increase in smoke concentration.

[0097] LSTM outputs a feature vector representing the fire risk features in the time series data.

[0098] Combine the image features and time series features to comprehensively evaluate the fire risk. Merge the image features extracted by CNN and the time series features extracted by LSTM into a comprehensive feature vector.

[0099] Process the comprehensive feature vector through a fully connected layer, and finally output a value between 0 and 1, representing the probability of a fire occurring. If this probability value is close to 1, it indicates a high fire risk; if it is close to 0, it indicates a low fire risk. The system decides whether measures need to be taken (such as sounding an alarm or activating a fire extinguishing device), and the calculation formula is:

[0100] P = σ(W o F + b o )

[0101] where P represents the fire risk probability, W o and b o are the weights and biases of the fully connected layer respectively, σ is the sigmoid function that maps the output value to the interval [0,1], and F is the comprehensive feature vector;

[0102] Use historical fire data and normal charging data as the training set to train the model. The loss function uses the cross-entropy loss function, and the optimizer selects the Adam optimizer. During the training process, evaluate the model through the validation set to prevent overfitting.

[0103] Input the feature data collected in real time into the trained model, and the model outputs the fire risk probability. If the fire risk probability P exceeds the risk preset threshold, the system determines it as a high fire risk.

[0104]

[0105] In the formula, P t is the risk preset threshold, and P j is the fire risk probability calculated in the jth monitoring, and w j is the weight factor, which assigns a higher weight to more recent data, and R 1 is the number of monitoring times;

[0106] When the fire risk probability P ≤ the risk preset threshold P t the fire risk is in the low-risk range, and the system enters the low-risk warning state. In this state, the system mainly takes measures of real-time monitoring and data recording. Specifically, the system collects the environmental data of the charging parking space in real time through temperature sensors, smoke sensors, flame sensors, and infrared thermal imagers, and transmits these data to the local controller and the cloud server for storage and analysis. At the same time, the system will regularly evaluate the data to ensure that the risk probability will not suddenly increase. If it is continuously monitored that the risk probability shows an upward trend in the low-risk state, the system will automatically switch to the medium-risk warning state and trigger corresponding response measures. This low-risk warning and response mechanism can timely detect potential problems in the initial stage of the fire risk, provide basic data support for subsequent warnings and responses, and ensure that the system can take prompt actions when the risk probability increases.

[0107] When the fire risk probability P > the risk preset threshold P t and the medium-risk probability is in the medium-risk range, the system enters the medium-risk warning state. In this state, the system not only continues to monitor and record data in real time, but also takes a series of active warning and local control measures. Specifically, the system will send a warning message to the mobile terminal of the management personnel, indicating the existence of potential fire risks, and suggesting that the management personnel conduct on-site inspections. At the same time, the system will automatically cut off the charging power supply and stop the charging process to prevent the fire risk from further expanding. In addition, the system will start the ventilation system to reduce the temperature and smoke concentration of the charging parking space and reduce the possibility of fire. If the risk probability continues to increase in the medium-risk state, the system will automatically switch to the high-risk warning state and trigger higher-level response measures. This risk warning and response mechanism can timely take local control measures in the middle stage of the fire risk, effectively reduce the possibility of fire, and ensure the safety of personnel and equipment.

[0108] When the probability of fire risk is in the high-risk range, the system enters a high-risk warning state. In this state, the system will take the highest level of warning and emergency response measures. Specifically, the system will immediately send an emergency alarm to the management personnel and the fire department, notifying them to take action as soon as possible. At the same time, the system will automatically start the fire extinguishing device (such as a carbon dioxide fire extinguisher or a sprinkler system) to extinguish the charging parking space. In addition, the system will send the alarm information to the remote monitoring platform through the 5G network or the Internet of Things technology to ensure that the management personnel and the fire department can receive the alarm in time and conduct emergency command. If the risk probability continues to increase under the high-risk state, the system will automatically enter the emergency handling mode, link with the emergency command system of the fire department, provide real-time data and video surveillance information of the fire scene, and assist the fire department in fire fighting and rescue. This high-risk early warning and response mechanism can quickly take emergency measures when the risk of fire is high, minimize the damage to people and property caused by fire, and ensure that the fire is controlled and extinguished in time.

[0109] By collecting smoke concentration, temperature change and flame spectrum data in the charging area and combining them with infrared thermal imaging images, the fire risk during the charging process is monitored and analyzed in real time. The multi-dimensional data is reduced in dimension through principal component analysis (PCA), and the fire risk is predicted and the risk level is judged through a deep learning model combining a convolutional neural network (CNN) and a long short-term memory network (LSTM), thereby realizing intelligent early warning of fire risks. The fire prevention capability during the charging process is significantly improved, the limitations of manual monitoring are reduced, and through the automated alarm system and emergency response mechanism, intervention can be made before the fire risk occurs to ensure the safe operation of charging facilities.

[0110] S3: Use intelligent recognition algorithms to distinguish the characteristics of moving objects, automatically adjust warning methods according to different types of objects, and push abnormal events in real time.

[0111] Specifically, high-precision infrared motion sensor arrays and ultrasonic transmitters are deployed around the charging area. Through intelligent recognition algorithms, the activity characteristics of small animals can be distinguished. The ultrasonic frequency and sound pressure can be automatically adjusted according to different types of small animals to achieve precise dispersion while avoiding interference with charging vehicles and personnel.

[0112] Infrared sensors and microwave radars monitor the activities of small animals around the charging space in real time. If a small animal is detected approaching the charging device or the vehicle chassis, the system marks it as an interference event. The ultrasonic repeller is activated to emit an ultrasonic signal with a frequency of 40kHz to drive away the small animal. If the ultrasonic repeller is ineffective, the light flashing device is activated to interfere with the small animal's vision through strong light flashing, forcing it to leave.

[0113] The system records the time, location, and deterrence measures of small animal interference events. If small animal interference is detected multiple times in a row, the system sends an alarm to the management personnel and recommends taking further measures (such as installing a protective net).

[0114] Feed back the processing results of each fire monitoring and small animal deterrence event to the intelligent algorithm model. Use the incremental learning method to dynamically update the model and optimize the fire risk prediction and small animal deterrence strategies.

[0115] Regularly retrain the model, introduce new fire data and small animal interference data, and improve the accuracy and robustness of the model.

[0116] Optimize the model parameters through simulation tests and comparison with actual operation data to ensure the reliability of the system in different environments.

[0117] Use a high-definition camera to collect video frames in the charging area (for example, 30 frames per second). Preprocess the collected images, including grayscale conversion, denoising (using Gaussian filtering), and normalization (normalizing pixel values to the [0, 1] interval).

[0118] Based on the combination of optical flow method and background subtraction method for moving object detection. In each frame, calculate the difference between the current image and the background model to detect moving objects. The background model can be modeled by the Gaussian mixture model GMM to adapt to light changes and dynamic scenes. Combining the background subtraction results, further calculate the movement direction and speed of the moving objects through the optical flow method. The optical flow method can use the Hough transform to analyze the movement trajectory of the object and track the movement pattern of the moving object.

[0119] Use Kalman filtering to track the movement trajectory of the object, calculate the displacement and speed of the moving object. Generate a bounding box for each detected object and record the movement information of the bounding box as the input for subsequent classification and warning.

[0120] For each moving object, extract its shape features (such as contour, size, shape) and movement features (such as speed, direction). Methods such as HOG (Histogram of Oriented Gradients) and SIFT (Scale-Invariant Feature Transform) can be used for feature extraction.

[0121] Use a convolutional neural network CNN to train an object classification model. The CNN model uses the features of the detected moving objects as input for object classification. Assume that the types of objects to be classified include "animals", "humans", and "other objects", and a training set can be prepared for each category. Adopt the cross-entropy loss function and optimize the network weights through the standard backpropagation algorithm. The loss function is defined as:

[0122]

[0123] Wherein, L is the value of the loss function, N is the number of samples, and y i is the true label of the i-th sample, and P i is the predicted fire risk probability of the i-th sample;

[0124] Input the features of the detected moving object, and classify the object type through the trained CNN model to obtain the object category.

[0125] Output the category label of the object (such as animal, person, other) and the relevant probability value (indicating the confidence level that the object belongs to this category).

[0126] Automatically adjust the warning method according to the recognition result of the object type to ensure the safety of the charging area.

[0127] Animal objects: When the system recognizes that there is an animal in the charging area, the system will activate the ultrasonic dispersion device and adjust the frequency and intensity of the ultrasonic according to the size and type of the animal. For example, small animals may require a higher frequency of ultrasonic, while large animals use a lower frequency. The system can also adjust the emission direction and intensity of the ultrasonic according to the movement speed and relative position of the animal, so as to maximize the dispersion effect and avoid interference with surrounding people or equipment.

[0128] Human objects: If it is recognized that a human enters the charging area, the system will activate both voice alarm and visual warning at the same time. The system will remind the person through voice broadcast, such as "Please stay away from the charging pile", to ensure that the person entering the charging area can obtain safety tips in time. The system will dynamically adjust the frequency and volume of the voice according to the distance and staying time of the person to ensure that the warning sound is loud enough to arouse vigilance.

[0129] When a human approaches the charging area, the warning light will flash, and the safety reminder board will display obvious warning information to remind the person to keep a certain safe distance. The system will adjust the flashing frequency and brightness of the warning light according to the degree of approach of the person to the charging device and the staying time to attract enough attention.

[0130] Other objects: For objects classified as "other objects" (such as pieces of paper, leaves blown by the wind, etc.), the system will activate a low-frequency warning. The system will remind the person of the existence of the object through a short voice prompt or display warning information on the screen. If the recognized object stays for a very short time or its speed is too low, the system will automatically ignore or reduce the warning level to reduce unnecessary interference and resource waste.

[0131] If there are multiple objects in the charging area at the same time, the system will set priorities according to the type and threat level of the objects. Generally, the threat levels of humans and animals are relatively high, so the corresponding warnings will be triggered first.

[0132] The system automatically adjusts the warning plan according to the dynamic changes of the object. For example, when the movement trajectory of an animal becomes irregular, the system will adjust the ultrasonic frequency to enhance the dispersal effect.

[0133] Push the abnormal event to the monitoring center, property management office, user APP and fire department in real time. The pushed information includes the event type, location coordinates, on-site images and disposal suggestions, and automatically generates an emergency disposal process to ensure rapid collaborative response from all parties.

[0134] Collect video frames of the charging area through a high-definition camera, use a combination of Gaussian mixture model (GMM) and optical flow method for object detection, and track the movement trajectory of the object through Kalman filtering, which can accurately identify and classify animals, humans and other objects in the charging area. According to the different types of objects, the system automatically adjusts the warning method. Through the dynamic monitoring and intelligent analysis of the charging area, it ensures that the system's response to different objects is more accurate and effective, avoids unnecessary warnings, and improves the safety of users and equipment.

[0135] This embodiment also provides a computer device applicable to the case of the automatic protection charging method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the automatic protection charging method proposed in the above embodiment.

[0136] The computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Wi-Fi, a carrier network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0137] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the automatic protection charging method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (abbreviated as SRAM), electrically erasable programmable read-only memory (abbreviated as EEPROM), erasable programmable read-only memory (abbreviated as EPROM), programmable read-only memory (abbreviated as PROM), read-only memory (abbreviated as ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0138] In summary, by combining license plate and face recognition technologies for dual authentication, integrating fire risk monitoring and intelligent response mechanisms, and object type recognition and dynamic warning adjustment, the present invention not only improves the safety during charging, but also enhances the intelligent management of charging facilities. Through precise identity authentication, real-time fire monitoring and personalized warning mechanisms, the invention effectively improves the safety and operation efficiency of charging stations, and belongs to the technological innovation in the field of electric vehicle charging systems and intelligent safety monitoring.

[0139] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An automatic protection charging method for electric vehicles, characterized in that: include: Cars entering the charging area are identified by license plate and model, and the owner's identity is double-authenticated using facial recognition technology, and permissions are verified in combination with background information; After the electric vehicle enters the charging station, the charging equipment is started to obtain the monitoring data of the charging parking area and conduct fire risk monitoring; Through intelligent recognition algorithms, the characteristics of moving objects can be distinguished, the warning method can be automatically adjusted according to the different types of objects, and abnormal events can be pushed in real time.

2. The electric vehicle automatic protection charging method according to claim 1, characterized in that: The authorization verification comprises the following steps: When the vehicle enters, combined with the owner's reservation system, the system generates an authorization code based on the owner's reservation information, and verifies whether the vehicle has charging permission by comparing the information in the authorization code; If the license plate number in the owner's reservation information completely matches the current license plate recognition result, and the owner passes the face recognition authentication successfully, the owner's identity is verified to be legal; If the license plate number in the owner's reservation information partially matches the current license plate recognition result, and the owner passes the facial recognition authentication successfully, the system will additionally conduct a manual review of the owner's identity to confirm whether the owner is the owner of the vehicle, and charging will only be allowed after the owner confirms; If the car model in the owner's reservation information matches the current vehicle model, and the owner passes the face recognition authentication, then continue to verify whether the owner's reservation time period coincides with the current time period; If the model in the owner's reservation information does not match the current vehicle model, and the owner's facial recognition authentication is passed, the system will remind the owner and ask for model confirmation. After the owner provides the correct model and the vehicle meets the electric vehicle standards, the system will dynamically allocate a charging parking space based on the current available parking spaces and allow the vehicle to enter; If the license plate number in the owner's reservation information matches the current license plate recognition result, the owner's face recognition passes, and the current time is within the reservation period, the verification is passed and the vehicle is allowed to charge; If the license plate number in the owner's reservation information matches the current license plate number and the owner's facial recognition fails, the system will initiate secondary identity authentication. If the license plate number in the owner's reservation information completely matches the current license plate number, but the current vehicle does not meet the electric vehicle standards, the system will refuse to charge and prompt the owner that the vehicle does not meet the charging requirements.

3. The electric vehicle automatic protection charging method as claimed in claim 2, characterized in that: The monitoring data includes smoke concentration data, temperature change data and flame spectrum data; the infrared thermal imager scans the temperature distribution of the charging equipment and the vehicle chassis in real time to obtain thermal imaging data of the charging parking area; Normalize the collected smoke concentration data, temperature change data, flame spectrum data and thermal imaging data, remove noise data and extract effective data features; Use principal component analysis PCA to reduce the dimension of effective data features and extract key feature vectors. The calculation formula is: In the formula, n is the number of samples, X is the data matrix, and X T is the transpose of the data matrix, C is the covariance matrix, and the eigenvectors corresponding to the first k largest eigenvalues ​​are selected as principal components; The fire risk prediction model is constructed by combining the convolutional neural network (CNN) in deep learning with the long short-term memory (LSTM) network, and the convolutional neural network (CNN) is used to process thermal imaging images. The time series data of smoke concentration data, temperature change data and flame spectrum data are input into the long short-term memory network LSTM, and the fire risk characteristics in the time series data are output; Combine the image features extracted by CNN and the time series features extracted by LSTM into a comprehensive feature vector; The comprehensive feature vector is processed through the fully connected layer, and the fire risk probability is output. The risk level is judged according to the fire risk probability to decide the corresponding measures. The calculation formula is: P=σ(W o F+b o ) Where P represents the fire risk probability, W o and b o are the weight and bias of the fully connected layer, σ is the sigmoid function, which maps the output value to the interval [0,1], and F is the comprehensive feature vector; The model is trained using historical fire data and normal charging data as training sets. During the training process, the model is evaluated using the validation set.

4. The electric vehicle automatic protection charging method as claimed in claim 3, characterized in that: The method of determining the risk level according to the fire risk probability and taking corresponding measures includes calculating the risk preset threshold value, and the calculation formula is: Where P t Preset threshold for risk, P j is the fire risk probability calculated in the jth monitoring, w j is the weight factor, giving higher weight to more recent data, and R1 is the number of monitoring times; When the fire risk probability P ≤ the risk preset threshold P t When the system determines that the current fire risk probability is in the low risk range, the system enters the low risk warning state. The system collects the environmental data of the charging parking space in real time through temperature sensors, smoke sensors, flame sensors and infrared thermal imagers, and transmits the data to the local controller and cloud server for storage and secondary analysis. The data is evaluated regularly. If the fire risk probability P is continuously monitored to be greater than the risk preset threshold P in the low risk warning state, the system will automatically enter the low risk warning state. t When the system automatically switches to the medium risk warning state, the medium risk response measures are triggered. The system sends a warning message to the manager's mobile terminal, indicating the potential fire risk and suggesting that the manager conduct an on-site inspection. At the same time, the charging power is automatically cut off, the charging process is stopped, the ventilation system is started, and the fire risk probability continues to be monitored. In the medium risk state, the fire risk probability P is greater than the risk preset threshold P t The system will automatically switch to high-risk warning status; When the fire risk probability P> the risk preset threshold P t When the fire risk probability is in the high risk range, the system enters the high risk warning state. The system immediately sends an emergency alarm to the management personnel and the fire department, and sends the alarm information to the remote monitoring platform. If in the high risk state, the fire risk probability P> the risk preset threshold P t If the temperature does not drop, the system will automatically enter the emergency processing mode.

5. The electric vehicle automatic protection charging method as claimed in claim 4, characterized in that: The method of distinguishing the characteristics of moving objects comprises the following steps: Use a high-definition camera to collect video frames of the charging area, and pre-process the collected images, including grayscale, denoising, and standardization; The background model is established through the Gaussian mixture model GMM. In each frame of the preprocessed image, the difference between the current image and the background model is calculated to detect the moving object, and the moving direction and speed of the moving object are calculated by the optical flow method. Use Kalman filtering to track the movement of objects, calculate the displacement and speed of moving objects, generate bounding boxes for each detected object, and record the movement information of the bounding boxes; For each moving object, extract its shape features and motion features; The convolutional neural network (CNN) is used to train the object classification model. The features of the extracted moving objects are used as input to classify the objects. The cross entropy loss function is used to optimize the network weights through the standard back propagation algorithm. The loss function is defined as: In the formula, L is the loss function value, N is the number of samples, and y i is the true label of the i-th sample, P i is the predicted fire risk probability of the i-th sample; Input the features of the detected moving object, classify the object type through the trained CNN model, obtain the object category, and output the object category label and probability value; Based on the recognition results of the object type, the warning method is automatically adjusted to ensure the safety of the charging area.

6. The electric vehicle automatic protection charging method as claimed in claim 5, characterized in that: The object type recognition result includes: When the system identifies an animal in the charging area, it activates the ultrasonic dispersal device, adjusts the frequency and intensity of the ultrasonic wave according to the size and type of the animal, and adjusts the emission direction and intensity of the ultrasonic wave according to the animal's movement speed and relative position; When the system recognizes that there are humans in the charging area, the system activates voice alarms and visual warnings at the same time. The system reminds people through voice broadcasts and gives safety tips to people entering the charging area. The frequency and volume of the voice are dynamically adjusted according to the distance and residence time of the people. When people continue to approach the charging area, the warning light flashes and the safety reminder board displays a warning message to remind people to keep a safe distance. When the system detects other objects in the charging area, it activates a low-frequency warning and displays a warning message through voice prompts or on the display to remind the owner of the presence of other objects.

Images