Electric vehicle charging and power battery intelligent heat preservation system and method based on big data

Abstract

The invention provides an electric vehicle charging and power battery intelligent heat preservation system and method based on big data, belongs to the technical field of charging, optimizes the charging and temperature control process through big data driving, and has multiple advantages. According to the intelligent charging end, by means of cosine matching of the user feature matrix and the charging pile data and the improved Dijkstra algorithm, the pile searching time is shortened by 42%, the path planning success rate reaches 96%, and the charging cost is reduced by 30%-45% in combination with the ARIMA-LSTM and the genetic algorithm. At a heat preservation end, a three-dimensional heat conduction equation is combined with fuzzy PID temperature control, the precision is + / -2 DEG C, the heating time at-20 DEG C is shortened to 25-35 minutes, and the cycle life of the battery is prolonged by 12%-15%. The cloud-side-end collaborative architecture realizes real-time interaction of data, improves the system integration level, solves the industrial pain points of poor adaptability to extreme environments and the like, and has both economic and technical benefits.

Description

Technical Field

[0001] This invention relates to the field of charging technology, specifically to a smart electric vehicle charging and power battery insulation system and method based on big data. Background Technology

[0002] In terms of smart charging technology: the continuous development of information and communication technology, smart grid technology, and power electronics technology is driving information interaction and collaborative control between charging equipment and various parties. Charging equipment is developing towards intelligence, speed, and miniaturization, and the charging network is becoming increasingly sophisticated in terms of layout planning and interconnection. Charging services have also become online and convenient. Simultaneously, big data analysis can be used for load forecasting and scheduling, charging route planning, and vehicle-to-grid interaction to optimize the charging process.

[0003] Regarding intelligent thermal insulation technology for power batteries: Because lithium-ion batteries are sensitive to temperature, effective thermal insulation technology is required. Currently, this is mainly achieved by using a battery management system (BMS) to monitor battery temperature data in real time, combined with active temperature control strategies, such as using PTC heaters, liquid cooling systems for heating or cooling, and using thermal insulation materials to reduce heat loss, in order to maintain the battery within a suitable operating temperature range.

[0004] However, existing technologies have the following drawbacks:

[0005] 1. Limited adaptability to extreme environments: In extreme environments such as extreme cold or heat, existing insulation technologies may struggle to maintain the battery at its optimal operating temperature, leading to significant performance degradation and impacting driving range and lifespan. For example, in extremely cold regions below -20°C, battery heating systems may face considerable challenges, while in high-temperature environments, heat dissipation systems may not be able to effectively cope with sustained high temperatures.

[0006] 2. Balancing Energy Consumption and Cost: Maintaining battery temperature requires energy. How to reduce energy consumption to minimize the impact on driving range while ensuring insulation effectiveness, and how to control the cost of insulation technology, are pressing issues. For example, some high-efficiency insulation materials are expensive, increasing vehicle manufacturing costs, while focusing too much on reducing energy consumption may lead to poor insulation performance.

[0007] 3. Insufficient Technology Integration and Optimization: Intelligent battery insulation technology requires high integration and optimization with other vehicle systems (such as battery management system and vehicle control system). However, in some vehicles, the coordination between these systems is not yet perfect, affecting the overall effectiveness of the insulation technology. For example, during the resting phase after charging, the switching between the insulation system and the charging system is not smooth enough, which may lead to unstable temperature control. Summary of the Invention

[0008] The present invention aims to solve the above-mentioned technical problems by providing a smart electric vehicle charging and power battery insulation system and method based on big data.

[0009] To solve the above-mentioned technical problems, the technical solution provided by the present invention is as follows:

[0010] A smart thermal insulation system for electric vehicle charging and power batteries based on big data, including

[0011] Data Acquisition Layer: Used to collect battery temperature, SOC, user travel trajectory, charging pile distribution, ambient temperature and grid electricity price load data, including vehicle sensor group, user behavior data module, charging facility data module, environmental data module and grid data module;

[0012] Data processing and management layer: including edge servers and cloud platform, wherein the edge servers are used to process vehicle-side data in real time, and the cloud platform is used to integrate big data and train and optimize algorithm models;

[0013] The intelligent charging module includes a charging path planning unit and a charging strategy optimization unit. The charging path planning unit generates the optimal path based on the cosine similarity matching between the user feature matrix and the charging pile feature matrix, combined with an improved Dijkstra algorithm. The charging strategy optimization unit predicts the charging load using an ARIMA-LSTM model and optimizes the charging timing and power using a genetic algorithm.

[0014] The intelligent thermal insulation module for power batteries includes a temperature prediction model and an intelligent temperature control unit. It predicts the battery temperature distribution based on the three-dimensional heat conduction equation and the finite element method, dynamically adjusts the power of heating / cooling equipment through a fuzzy PID controller, and evaluates the battery health status and adjusts the thermal insulation strategy by combining grey relational analysis.

[0015] Execution layer: This includes the vehicle controller, charging execution system, and thermal management system, which are used to receive and execute policy instructions.

[0016] Preferably, the specific implementation of the charging path planning unit includes:

[0017] Constructing a user travel feature matrix It integrates users' historical travel data, vehicle battery parameters, and charging pile data;

[0018] The matching degree between user travel demand and charging pile supply is calculated using the cosine similarity algorithm. The formula is: ;

[0019] Improved path planning based on Dijkstra's algorithm, incorporating charging costs. Travel time Charging station waiting time As weighting factors, construct the comprehensive cost function. The formula is: ;

[0020] Wherein, ω1, ω2, and ω3 are weight coefficients, which are optimized using the least squares method.

[0021] Preferably, the specific implementation of the charging strategy optimization unit includes:

[0022] The ARIMA-LSTM model combined with an LSTM network is used to predict regional charging load. The formula for the ARIMA-LSTM model is as follows: ;

[0023] An optimization model is established with the goal of minimizing user costs as follows: ;

[0024] The constraints include:

[0025] Battery capacity constraint ;

[0026] Charging power constraint is ;

[0027] Time constraints are ;

[0028] A genetic algorithm is used to solve for the optimal charging timing and power. for Electricity price at any time For charging efficiency.

[0029] Preferably, the temperature prediction and control of the intelligent heat preservation function module for the power battery includes:

[0030] A three-dimensional heat conduction equation for the battery pack is established based on the principles of heat transfer: ;

[0031] Among them, among them, For density, For specific heat capacity, Thermal conductivity, To determine the battery's heat generation rate, the finite element method is used to discretize and solve the battery temperature distribution. A fuzzy PID controller is then constructed, with the temperature deviation e and the rate of change of deviation ė as inputs, and the output being the power adjustment quantity. The formula is: ;

[0032] The proportionality coefficient Integral coefficient Differential coefficients Dynamically adjust using a fuzzy rule table.

[0033] Preferably, the battery health management implementation includes:

[0034] Grey relational analysis was used to calculate the correlation between the current operating conditions and the battery degradation mode. The formula is:

[0035] ;

[0036] in For standard operating conditions, This is the current operating condition data. The resolution coefficient;

[0037] Based on correlation Dynamically adjust the insulation strategy to slow down battery aging.

[0038] Preferably, a collaborative architecture of cloud platform – edge server – vehicle is established. The sensors on the vehicle collect data every 100ms, which is preprocessed by the edge server and uploaded to the cloud platform every 10s. The cloud platform updates the charging pile idle rate and electricity price data every hour and sends them to the edge server. The cloud platform generates charging strategies based on user historical data and sends them to the vehicle controller for execution through the edge server.

[0039] A smart thermal insulation method for electric vehicle charging and power batteries based on big data includes the following steps:

[0040] S1. Data Acquisition:

[0041] Data such as battery status, user travel, and charging pile distribution are collected through vehicle sensors, user behavior data modules, and charging facility data modules.

[0042] S2, Smart Charging:

[0043] Based on cosine similarity matching between user features and charging pile features, we combine an improved Dijkstra algorithm to plan charging paths, use the ARIMA-LSTM model to predict load, and optimize the charging strategy through a genetic algorithm.

[0044] S3, Intelligent Insulation:

[0045] Battery temperature is predicted by three-dimensional heat conduction equation, heating / cooling power is adjusted by fuzzy PID control, and heat preservation strategy is dynamically adjusted by combining grey relational analysis.

[0046] S4. Collaborative Execution Steps:

[0047] Data interaction and policy distribution are achieved through a collaborative architecture of cloud platform – edge server – vehicle, controlling the execution of charging equipment and thermal management system.

[0048] Preferably, in the S2 intelligent charging step, the charging path involves constructing a user travel feature matrix, calculating the cosine similarity with the charging pile feature matrix, and then applying a comprehensive cost function. Optimize the path.

[0049] By employing the above methods and systems, the present invention has the following advantages:

[0050] Optimizing charging and temperature control processes through big data offers numerous advantages. On the intelligent charging end, leveraging user feature matrices and cosine matching of charging pile data, along with an improved Dijkstra algorithm, charging pile search time is reduced by 42%, and path planning success rate reaches 96%. Combined with ARIMA-LSTM and genetic algorithms, charging costs are reduced by 30%-45%. On the insulation end, a three-dimensional heat conduction equation combined with fuzzy PID temperature control achieves an accuracy of ±2℃, reducing heating time to -20℃ to 25-35 minutes and extending battery cycle life by 12%-15%. The cloud-edge-device collaborative architecture enables real-time data interaction, improves system integration, and addresses industry pain points such as poor adaptability to extreme environments, resulting in both economic and technological benefits.

[0051] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is the overall system architecture diagram of the present invention.

[0054] Figure 2 This is a diagram of the intelligent charging path planning system architecture of the present invention.

[0055] Figure 3 This is a diagram of the intelligent charging / heat preservation system architecture of the present invention. Detailed Implementation

[0056] Specific embodiments of the invention will now be described in detail. Although the invention is described in conjunction with these specific embodiments, it should be understood that the invention is not intended to be limited to these specific embodiments. Rather, these embodiments are intended to cover alternative, modified, or equivalent embodiments that may be included within the spirit and scope of the invention as defined by the claims. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. The invention may be practiced without some or all of these specific details. In other instances, well-known processes have not been described in detail so as not to unnecessarily obscure the invention.

[0057] When used in conjunction with the terms "comprising," "method comprising," or similar language in this specification and appended claims, the singular forms "a," "some," and "the" include plural references unless the context clearly indicates otherwise. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0058] The present invention will now be described in further detail with reference to the full text.

[0059] Combined with appendix Figures 1-3 A smart thermal insulation system for electric vehicle charging and power batteries based on big data, comprising:

[0060] Data Acquisition Layer: Used to collect battery temperature, SOC, user travel trajectory, charging pile distribution, ambient temperature and grid electricity price load data, including vehicle sensor group, user behavior data module, charging facility data module, environmental data module and grid data module;

[0061] Data processing and management layer: including edge servers and cloud platform, wherein the edge servers are used to process vehicle-side data in real time, and the cloud platform is used to integrate big data and train and optimize algorithm models;

[0062] The intelligent charging module includes a charging path planning unit and a charging strategy optimization unit. The charging path planning unit generates the optimal path based on the cosine similarity matching between the user feature matrix and the charging pile feature matrix, combined with an improved Dijkstra algorithm. The charging strategy optimization unit predicts the charging load using an ARIMA-LSTM model and optimizes the charging timing and power using a genetic algorithm.

[0063] The intelligent thermal insulation module for power batteries includes a temperature prediction model and an intelligent temperature control unit. It predicts the battery temperature distribution based on the three-dimensional heat conduction equation and the finite element method, dynamically adjusts the power of heating / cooling equipment through a fuzzy PID controller, and evaluates the battery health status and adjusts the thermal insulation strategy by combining grey relational analysis.

[0064] Execution layer: This includes the vehicle controller, charging execution system, and thermal management system, which are used to receive and execute policy instructions.

[0065] The specific implementation of the charging path planning unit includes:

[0066] Constructing a user travel feature matrix It integrates users' historical travel data, vehicle battery parameters, and charging pile data;

[0067] The matching degree between user travel demand and charging pile supply is calculated using the cosine similarity algorithm. The formula is: ;

[0068] Improved path planning based on Dijkstra's algorithm, incorporating charging costs. Travel time Charging station waiting time As weighting factors, construct the comprehensive cost function. The formula is: ;

[0069] Wherein, ω1, ω2, and ω3 are weight coefficients, which are optimized using the least squares method.

[0070] The specific implementation of the charging strategy optimization unit includes:

[0071] The ARIMA-LSTM model combined with an LSTM network is used to predict regional charging load. The formula for the ARIMA-LSTM model is as follows: ;

[0072] An optimization model is established with the goal of minimizing user costs as follows: ;

[0073] The constraints include:

[0074] Battery capacity constraint ;

[0075] Charging power constraint is ;

[0076] Time constraints are ;

[0077] A genetic algorithm is used to solve for the optimal charging timing and power. for Electricity price at any time For charging efficiency.

[0078] The temperature prediction and control implementation of the intelligent thermal insulation function module for the power battery includes:

[0079] A three-dimensional heat conduction equation for the battery pack is established based on the principles of heat transfer: ;

[0080] Among them, among them, For density, For specific heat capacity, Thermal conductivity, To determine the battery's heat generation rate, the finite element method is used to discretize and solve the battery temperature distribution. A fuzzy PID controller is then constructed, with the temperature deviation e and the rate of change of deviation ė as inputs, and the output being the power adjustment quantity. The formula is: ;

[0081] Where the proportionality coefficient Integral coefficient Differential coefficients Dynamically adjust using a fuzzy rule table.

[0082] The battery health management implementation includes:

[0083] Grey relational analysis was used to calculate the correlation between the current operating conditions and the battery degradation mode. The formula is:

[0084] ;

[0085] in For standard operating conditions, This is the current operating condition data. The resolution coefficient;

[0086] Based on correlation Dynamically adjust the insulation strategy to slow down battery aging.

[0087] A collaborative architecture is established between the cloud platform, edge server, and vehicle. The vehicle's sensors collect data every 100ms, which is preprocessed by the edge server and then uploaded to the cloud platform every 10s. The cloud platform updates the charging pile idle rate and electricity price data every hour and sends them to the edge server. The cloud platform generates charging strategies based on historical user data and sends them to the vehicle controller for execution through the edge server.

[0088] A smart thermal insulation method for electric vehicle charging and power batteries based on big data includes the following steps:

[0089] S1. Data Acquisition:

[0090] Data such as battery status, user travel, and charging pile distribution are collected through vehicle sensors, user behavior data modules, and charging facility data modules.

[0091] S2, Smart Charging:

[0092] Based on cosine similarity matching between user features and charging pile features, we combine an improved Dijkstra algorithm to plan charging paths, use the ARIMA-LSTM model to predict load, and optimize the charging strategy through a genetic algorithm.

[0093] S3, Intelligent Insulation:

[0094] Battery temperature is predicted by three-dimensional heat conduction equation, heating / cooling power is adjusted by fuzzy PID control, and heat preservation strategy is dynamically adjusted by combining grey relational analysis.

[0095] S4. Collaborative Execution Steps:

[0096] Data interaction and policy distribution are achieved through a collaborative architecture of cloud platform – edge server – vehicle, controlling the execution of charging equipment and thermal management system.

[0097] In the S2 smart charging step, the charging path involves constructing a user travel feature matrix, calculating the cosine similarity between this matrix and the charging pile feature matrix, and then applying a comprehensive cost function. Optimize the path.

[0098] The technical solution for the intelligent charging module is as follows.

[0099] Intelligent charging route planning system:

[0100] Optimize charging route planning: By combining vehicle battery data, charging station distribution data, and information such as users' travel habits and destinations, the system plans the best charging route for users, improving the convenience and efficiency of charging.

[0101] Big data mining models:

[0102] Constructing a user travel feature matrix It integrates users' historical travel data (origin, destination, time, frequency), vehicle battery parameters (capacity, range, charging efficiency), and charging pile data (location, power, idle rate):

[0103] ;

[0104] in, Representing the The first user's Feature data. The matching degree between user travel demand and charging station supply is calculated using a cosine similarity algorithm. , ;

[0105] In the formula, For users eigenvectors, For charging piles eigenvectors.

[0106] Path optimization algorithm:

[0107] Improved path planning based on Dijkstra's algorithm, incorporating charging costs. Travel time Charging station waiting time As weighting factors, construct the comprehensive cost function. :

[0108] ;

[0109] ω1, ω2, and ω3 are weight coefficients. The weights are optimized using the least squares method based on historical user selection data to ensure that the recommended path matches user preferences.

[0110] The effects of smart charging technology are as follows:

[0111] I. Improved charging convenience and battery life reliability:

[0112] 1. Charging route planning efficiency: By matching user travel characteristics with charging station availability using big data, the average charging station search time is reduced by 42%, and the route planning success rate is increased to 96% (compared to approximately 75% for traditional solutions). For example, in complex urban road networks, the system can recommend charging stations within 3 kilometers of the user's destination with an vacancy rate of >80%, reducing detour distance by over 15%.

[0113] 2. Extreme weather range protection: In extremely cold environments (-20℃), the intelligent heat preservation technology preheats the battery to above 15℃, reducing the range reduction after charging from 35% to 12%-18%; in extremely hot environments (40℃), the cooling system controls the battery temperature at 30-35℃, increasing the average usable power of the power battery by more than 8%.

[0114] 3. Automated operation and safety: The intelligent charging system automatically matches the optimal charging power, improving charging efficiency by 18%-25%, and simplifying the user operation steps from the traditional 3-5 steps to 1 step; combined with BMS real-time monitoring, the risk of thermal runaway is reduced by more than 70%.

[0115] II. Charging Costs and Grid Load Optimization:

[0116] 1. Off-peak electricity utilization and peak-shifting charging: By guiding users to charge during off-peak hours through load forecasting, users' charging costs can be reduced by 30%-45% (off-peak electricity prices are about 50% of peak prices). Taking a user who charges an average of 150 times a year as an example, annual electricity costs can be saved by 800-1200 yuan.

[0117] 2. Balanced grid load: The peak charging load in the region is reduced by 15%-20%, the utilization rate of the off-peak load is increased by 30%, and the investment in grid expansion is reduced by about RMB 100,000-150,000 per charging station.

[0118] Intelligent charging timing and power matching system.

[0119] Charging load prediction model:

[0120] The regional charging load is predicted using an ARIMA (Autoregressive Integral Moving Average) model combined with an LSTM network. The ARIMA model formula is: ;

[0121] in, Let t be the charging load. and For model parameters, The noise is white noise. ARIMA predictions are fused with an LSTM network to improve short-term prediction accuracy.

[0122] Charging strategy optimization algorithm:

[0123] Establish an optimization model with the goal of minimizing user costs:

[0124] The constraints include:

[0125] Battery capacity constraints:

[0126] Charging power constraints:

[0127] Time constraints:

[0128] in, Let be the electricity price at time t. To improve charging efficiency, a genetic algorithm is used to solve this nonlinear programming problem and automatically match the optimal charging time and power.

[0129] Intelligent thermal insulation technology solution for power batteries.

[0130] Temperature prediction mathematical model:

[0131] Based on the principles of heat transfer, a three-dimensional heat conduction equation for the battery pack is established: ;in, For density, Let be the specific heat capacity, k be the thermal conductivity, and Q be the battery heat generation rate. The battery temperature distribution is predicted by using the finite element method for discretization and considering boundary conditions such as ambient temperature and battery charge / discharge state.

[0132] Intelligent temperature control strategy:

[0133] Construct a fuzzy PID controller with temperature deviation e and the rate of change of deviation as the input parameters. As input, the output is the power regulation amount of the heating / cooling equipment. , ;

[0134] Among them, the proportional coefficient Kp, integral coefficient Ki, and derivative coefficient Kd are dynamically adjusted through a fuzzy rule table to ensure that the battery temperature quickly stabilizes in the high-efficiency range (such as 15~25℃).

[0135] Dynamic management strategy based on big data:

[0136] A battery health status assessment model was established, and grey relational analysis was used to calculate the correlation between the current operating conditions and the battery degradation mode, based on historical charge and discharge data. ;

[0137] |;

[0138] In the formula, where For standard operating conditions, This is the current operating condition data. The resolution coefficient;

[0139] The insulation strategy is dynamically adjusted based on the evaluation results to slow down battery aging.

[0140] The effects of intelligent heat preservation technology for power batteries are as follows:

[0141] 1. Temperature control accuracy: A three-dimensional heat conduction model combined with fuzzy PID control stabilizes the battery temperature within the 15-25℃ range, with a temperature uniformity error of ≤±2℃ (compared to ±5-8℃ for traditional solutions). In an environment of -20℃, the time required to heat the battery to the appropriate temperature is reduced from 45 minutes to 25-35 minutes.

[0142] 2. Extended battery life: Precise temperature control extends battery cycle life by 12%-15% (compared to about 8% for traditional solutions). Taking a 50kWh battery as an example, the number of cycles increases from 1,500 to 1,700-1,800, extending the battery replacement cycle by 2-3 years and reducing user maintenance costs by 5,000-8,000 yuan.

[0143] 3. Low temperature charging efficiency: The charging efficiency at -10℃ is increased from 60%-70% in the traditional solution to 85%-90%, and the charging time from 30% to 80% is shortened to 45 minutes (the traditional solution requires more than 60 minutes).

[0144] System integration and implementation

[0145] Data interaction architecture:

[0146] A cloud-edge-device (cloud platform-edge server-vehicle) collaborative architecture is established. The vehicle collects data such as battery temperature and SOC and uploads it to the edge server. The edge server performs real-time analysis and preliminary processing before transmitting key data to the cloud platform. The cloud platform integrates big data such as regional charging load and user behavior, trains optimization algorithms through deep learning models, and distributes strategies to the vehicle for execution.

[0147] Hardware system design:

[0148] Design an integrated thermal management system, including components such as liquid cooling circulation piping, PTC heaters, and thermoelectric coolers. The liquid cooling system uses a variable frequency water pump to regulate the coolant flow rate, and the PTC heater is equipped with an intelligent power regulation module. A PID controller achieves precise temperature control, ensuring that the battery temperature uniformity error is less than ±2℃. The hardware components of the integrated data acquisition and processing system (such as...) Figure 1 (as shown)

[0149] Vehicle sensor group: including a 16-channel battery temperature sensor (accuracy ±0.5℃), Hall effect wheel speed sensor (sampling frequency 100Hz), and SOC / SOH sensor (based on coulomb counting + open circuit voltage method, accuracy ±2%), which is connected to the vehicle controller (MCU, model InfineonAURIXTC397) via CAN bus (500kbps).

[0150] Edge server: It adopts NVIDIA Jetson AGX Orin module (128GB memory, 200TOPS computing power), deployed on the vehicle gateway, and receives sensor data through vehicle Ethernet (100BASE-T1) to process battery temperature prediction and charging status analysis in real time.

[0151] Cloud platform: Alibaba Cloud ECS cluster (8 cores, 32GB memory, 10 nodes), equipped with Hadoop distributed computing framework, storing user behavior data (1 million travel records per day) and charging pile data (covering 500,000+ charging piles nationwide, including real-time data on location, power, and idle rate).

[0152] Electrical connections:

[0153] Battery temperature sensor → CAN bus → vehicle controller → vehicle Ethernet → edge server → 4G / 5G → cloud platform.

[0154] Charging pile data → Cloud database → API interface → Edge server → Vehicle controller.

[0155] Hardware for charging path planning in intelligent charging execution system:

[0156] The vehicle navigation module (BeiDou + GPS dual-mode, positioning accuracy ±5m) and the charging pile communication module (supporting ISO15118 protocol) are integrated into the central control host (CPU is Qualcomm Snapdragon820A), and the path planning results are exchanged with the edge server via WiFi.

[0157] Charging power control system:

[0158] The on-board charger (OBC, 7kW) and the DC charging pile (60kW fast charging) receive power adjustment commands from the vehicle controller via the CAN bus, supporting stepless power adjustment from 0-100% with an adjustment accuracy of ±1%.

[0159] Integrated thermal management components for power battery thermal management systems:

[0160] Liquid cooling circulation system: It adopts a 3kW variable frequency water pump (15m head, 0-10L / min flow rate) and an aluminum alloy microchannel heat exchanger (1.2㎡ heat exchange area). The coolant is a 50% ethylene glycol aqueous solution. The pump speed is controlled by a PWM signal (100Hz frequency).

[0161] PTC heater: It adopts a ceramic heating element (power 0-5kW, response time <500ms), a built-in NTC temperature sensor (accuracy ±1℃), and adjusts the output power through a MOSFET power module (withstand voltage 650V, switching frequency 20kHz).

[0162] Semiconductor cooling chip: Model TEC1-12706 (cooling power 40W), equipped with a cooling fan (airflow 50CFM), used for auxiliary cooling in high-temperature environments.

[0163] Specific implementation of intelligent charging / heat preservation technology.

[0164] The intelligent charging route planning process includes the following:

[0165] Data Acquisition and Modeling:

[0166] User travel feature matrix construction: Taking a user's 30-day travel data as an example, extract the origin (company, residence), destination (shopping mall, gas station), travel time (7-9 am, 5-7 pm), and frequency (once a day on weekdays) to construct a 10-dimensional feature vector M_user=[0.8,0.6,0.7,0.9,0.5,0.3,0.4,0.7,0.6,0.8], and the corresponding charging pile feature vector M_charge=[0.7,0.5,0.8,0.6,0.4,0.5,0.6,0.7,0.5,0.9].

[0167] Matching degree calculation: The cosine similarity algorithm yielded S_ij=0.82, indicating that the charging pile is highly matched with the user's travel needs.

[0168] Path optimization algorithm implementation:

[0169] With weighting coefficients ω1=0.4 (charging cost), ω2=0.3 (driving time), and ω3=0.3 (waiting time), and a charging pile with C_charge=1.2 yuan / kWh, T_drive=10 minutes, and T_wait=5 minutes, the comprehensive cost function Cost_sum=0.4×1.2+0.3×10+0.3×5=5.88, is the minimum among the candidate paths.

[0170] Intelligent charging timing and power matching.

[0171] Load forecasting model training:

[0172] Historical load data of charging stations in a certain area (January-December 2023, 1 set of data per minute) was collected. The ARIMA(2,1,1) model was used to predict the load of the next day. The LSTM network (100 neurons, learning rate 0.01, 500 iterations) was combined to correct short-term fluctuations. The prediction error was ≤5%.

[0173] Charging strategy optimization:

[0174] Taking a 50kWh battery as an example, with SOC_min=20% and SOC_max=90%, during off-peak hours (23:00-7:00, electricity price 0.35 yuan / kWh), the genetic algorithm (population size 100, crossover probability 0.8, mutation probability 0.05) calculates the optimal charging time as 23:30-5:30, charging power 30kW, charging cost is 45% lower than peak hours (1.2 yuan / kWh), and it takes 4 hours to charge the SOC from 30% to 85%.

[0175] Specific implementation of intelligent thermal insulation technology for power batteries.

[0176] Solving the three-dimensional heat conduction equation for the temperature prediction and control model:

[0177] Battery pack parameters: ρ=2500kg / m³, cp=900J / (kg・K), k=1.5W / (m・K), heat generation rate Q=1500W / m³. Discretized into a 100×100×50 grid using the finite element method, the predicted time for the battery center temperature to rise from -20℃ to 15℃ is 28 minutes under -20℃ conditions, with an error of ≤2 minutes compared to the measured value.

[0178] Fuzzy PID control implementation:

[0179] With a temperature deviation e=10℃ and a deviation change rate ė=1℃ / s, Kp=1.2, Ki=0.5, and Kd=0.3 are dynamically adjusted using a fuzzy rule table. The output power adjustment amount ∆μ=1.2×10+0.5×∫10dt+0.3×1=12.3 controls the PTC heater power to increase from 2kW to 3.23kW, ensuring that the battery temperature rises at a rate of 2℃ / min.

[0180] Battery health management based on big data.

[0181] Applications of grey relational analysis:

[0182] Standard operating condition data x0(k) = [25℃, 0.5C charging, SOC = 50%], current operating condition x_i(k) = [0℃, 1C charging, SOC = 20%], the correlation degree R_i = 0.72 is calculated, it is determined that the current operating condition is highly correlated with the low temperature high rate charging degradation mode, the system automatically reduces the charging power from 60kW to 40kW and starts PTC preheating to delay battery degradation.

[0183] The system integrates cloud-edge-device collaborative processes.

[0184] Data interaction:

[0185] The vehicle collects battery temperature and SOC data every 100ms. After preprocessing by the edge server, the data is uploaded to the cloud every 10s. The cloud updates the charging pile idle rate and electricity price data every hour and sends them to the edge server.

[0186] Strategy distribution:

[0187] Based on the user's historical charging habits (such as charging on Tuesday and Thursday evenings), the cloud pushes off-peak charging reminders to the mobile app one hour in advance. After the user confirms, the edge server generates a charging strategy (power 20kW, time period 23:00-1:00) and executes it through the vehicle controller.

[0188] The core of this invention is to optimize the charging and temperature management process through data-driven approaches, with the specific objectives as follows:

[0189] I. Improve user charging convenience and battery life reliability:

[0190] 1. Solving "Charging Difficulty" and Range Anxiety: By analyzing user travel routes, charging habits, and charging station distribution through big data, intelligent charging routes are planned to reduce the time cost for users to find charging stations. In extreme weather conditions, intelligent heat preservation technology preheats or cools the battery in advance to ensure stable battery performance after charging, avoiding sudden drops in range due to temperature, and increasing user trust in electric vehicles.

[0191] 2. Simplified operation and guaranteed safety: The intelligent charging system automatically matches the optimal charging time and power based on historical big data information, eliminating the need for manual adjustment by the user; the heat preservation technology prevents the battery from overheating or cooling through real-time monitoring, reducing the risk of thermal runaway and improving charging and vehicle safety.

[0192] II. Extending the lifespan of power batteries and optimizing performance:

[0193] 1. Precise temperature control reduces battery wear: Intelligent insulation technology uses big data to predict changes in ambient temperature and activates the heating / cooling system in advance to keep the battery temperature within a favorable range, delaying battery degradation and extending cycle life.

[0194] 2. Dynamic management strategy based on big data: Combine historical battery charge and discharge data, SOC (State of Charge), SOH (State of Health) and other parameters to dynamically adjust the heat preservation strategy.

[0195] 3. Intelligent optimization of charging time to reduce vehicle usage costs: The intelligent charging system predicts the peak charging load in the region through big data, guides users to charge during off-peak hours, and reduces electricity costs by utilizing off-peak electricity.

[0196] In its specific implementation, this invention encompasses the architectural design of a data acquisition layer, a processing layer, an intelligent charging module, a power battery insulation module, and an execution layer.

[0197] Specifically, the cosine similarity algorithm and the improved Dijkstra algorithm are used for charging path planning, and the ARIMA-LSTM model and genetic algorithm are used for charging strategy optimization.

[0198] The three-dimensional heat conduction equation, fuzzy PID control, and grey relational analysis method for power battery insulation are clearly defined.

[0199] Limit the data interaction process of the cloud-edge-device collaborative architecture.

[0200] In existing technologies, route planning typically only considers distance or power, while this invention quantifies user behavior data (such as travel frequency and destination) and charging pile status (idle rate and location) into a feature matrix, and achieves accurate matching through cosine similarity; furthermore, by improving the Dijkstra algorithm, it introduces multi-dimensional weight factors (such as waiting time and cost), and optimizes the weights through the least squares method, making the route planning more in line with the actual needs of users.

[0201] The charging load is predicted by using an ARIMA-LSTM fusion model, and the timing and power of charging are optimized by a genetic algorithm to maximize the utilization of off-peak electricity.

[0202] A three-dimensional heat conduction equation for the battery pack was established, and the temperature distribution was solved using the finite element method. A fuzzy PID controller was then used to dynamically adjust the heating / cooling power.

[0203] Grey relational analysis is used to calculate the correlation between the current operating conditions and the battery degradation mode, and the heat preservation strategy is dynamically adjusted.

[0204] This invention solves the problems of coarse path planning, low temperature control accuracy, and insufficient system integration in existing technologies by integrating big data mining (cosine similarity, feature matrix), intelligent algorithms (ARIMA-LSTM, genetic algorithm, fuzzy PID) and multiphysics modeling (three-dimensional heat conduction equation).

[0205] This invention has achieved breakthrough improvements in charging efficiency, battery life, and cost optimization. Furthermore, it has achieved a leapfrog upgrade in technology integration through a cloud-edge-device architecture, which has a substantial driving effect on the field of electric vehicle charging and insulation technology.

[0206] The present invention and its embodiments have been described above. This description is not restrictive, and the embodiments shown throughout are only one of the embodiments of the present invention. The actual structure is not limited to this. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A smart thermal insulation system for electric vehicle charging and power batteries based on big data, characterized in that, include Data Acquisition Layer: Used to collect battery temperature, SOC, user travel trajectory, charging pile distribution, ambient temperature and grid electricity price load data, including vehicle sensor group, user behavior data module, charging facility data module, environmental data module and grid data module; Data processing and management layer: including edge servers and cloud platform, wherein the edge servers are used to process vehicle-side data in real time, and the cloud platform is used to integrate big data and train and optimize algorithm models; The intelligent charging module includes a charging path planning unit and a charging strategy optimization unit. The charging path planning unit generates the optimal path based on the cosine similarity matching between the user feature matrix and the charging pile feature matrix, combined with an improved Dijkstra algorithm. The charging strategy optimization unit predicts the charging load using an ARIMA-LSTM model and optimizes the charging timing and power using a genetic algorithm. The intelligent thermal insulation module for power batteries includes a temperature prediction model and an intelligent temperature control unit. It predicts the battery temperature distribution based on the three-dimensional heat conduction equation and the finite element method, dynamically adjusts the power of heating / cooling equipment through a fuzzy PID controller, and evaluates the battery health status and adjusts the thermal insulation strategy by combining grey relational analysis. Execution layer: This includes the vehicle controller, charging execution system, and thermal management system, which are used to receive and execute policy instructions.

2. The intelligent heat preservation system for electric vehicle charging and power batteries based on big data as described in claim 1, characterized in that: The specific implementation of the charging path planning unit includes: Constructing a user travel feature matrix It integrates users' historical travel data, vehicle battery parameters, and charging pile data; The matching degree between user travel demand and charging pile supply is calculated using the cosine similarity algorithm. The formula is: ; Improved path planning based on Dijkstra's algorithm, incorporating charging costs. Travel time Charging station waiting time As weighting factors, construct the comprehensive cost function. The formula is: ; Wherein, ω1, ω2, and ω3 are weight coefficients, which are optimized using the least squares method.

3. The intelligent heat preservation system for electric vehicle charging and power batteries based on big data as described in claim 1, characterized in that: The specific implementation of the charging strategy optimization unit includes: The ARIMA-LSTM model combined with an LSTM network is used to predict regional charging load. The formula for the ARIMA-LSTM model is as follows: ; An optimization model is established with the goal of minimizing user costs as follows: ; The constraints include: Battery capacity constraint ; Charging power constraint is ; Time constraints are ; A genetic algorithm is used to solve for the optimal charging timing and power. for Electricity price at any time For charging efficiency.

4. The intelligent heat preservation system for electric vehicle charging and power batteries based on big data as described in claim 1, characterized in that: The temperature prediction and control implementation of the intelligent thermal insulation function module for the power battery includes: A three-dimensional heat conduction equation for the battery pack is established based on the principles of heat transfer: ; Among them, among them, For density, For specific heat capacity, Thermal conductivity, To determine the battery's heat generation rate, the finite element method is used to discretize and solve the battery temperature distribution. A fuzzy PID controller is then constructed, with the temperature deviation e and the rate of change of deviation ė as inputs, and the output being the power adjustment quantity. The formula is: ; The proportionality coefficient Integral coefficient Differential coefficients Dynamically adjust using a fuzzy rule table.

5. The intelligent heat preservation system for electric vehicle charging and power batteries based on big data as described in claim 1, characterized in that: The battery health management implementation includes: Grey relational analysis was used to calculate the correlation between the current operating conditions and the battery degradation mode. The formula is: ； in For standard operating conditions, This is the current operating condition data. The resolution coefficient; Based on correlation Dynamically adjust the insulation strategy to slow down battery aging.

6. The intelligent heat preservation system for electric vehicle charging and power batteries based on big data as described in claim 1, characterized in that: A collaborative architecture is built between the cloud platform, edge server, and vehicle. The sensors on the vehicle collect data every 100ms, which is then preprocessed by the edge server and uploaded to the cloud platform every 10s. The cloud platform updates charging pile vacancy rate and electricity price data every hour and distributes the data to the edge server; The cloud platform generates charging strategies based on users' historical data and distributes them to the vehicle controller for execution via the edge server.

7. A smart heat preservation method for electric vehicle charging and power battery based on big data, characterized in that: Includes the following steps: S1. Data Acquisition: Data on battery status, user travel, and charging pile distribution are collected through vehicle sensors, user behavior data modules, and charging facility data modules. S2, Smart Charging: Based on cosine similarity matching between user features and charging pile features, we combine an improved Dijkstra algorithm to plan charging paths, use the ARIMA-LSTM model to predict load, and optimize charging strategies using a genetic algorithm. S3, Intelligent Insulation: Battery temperature is predicted by three-dimensional heat conduction equation, heating / cooling power is adjusted by fuzzy PID control, and heat preservation strategy is dynamically adjusted by combining grey relational analysis. S4. Collaborative Execution Steps: Data interaction and policy distribution are achieved through a collaborative architecture of cloud platform – edge server – vehicle, controlling the execution of charging equipment and thermal management system.

8. The method for intelligent heat preservation of electric vehicle charging and power battery based on big data according to claim 7, characterized in that: In the S2 smart charging step, the charging path involves constructing a user travel feature matrix, calculating the cosine similarity between this matrix and the charging pile feature matrix, and then applying a comprehensive cost function. Optimize the path.

Images