A photovoltaic energy power domain vehicle control method

Abstract

The application discloses a photovoltaic energy power domain vehicle control method, and relates to the technical field of new energy vehicles, which comprises the following steps: collecting energy based on the energy collection efficiency of a photovoltaic panel and the data collected by a sensor, analyzing through a deep learning model, predicting an energy demand value, and generating an energy distribution ratio through an intelligent algorithm; performing energy management operation through an energy distribution strategy, continuously monitoring the energy collection condition of the photovoltaic panel and the energy consumption condition of the vehicle, and feeding back to a central processing unit to optimize the energy distribution strategy. The application combines environmental data and vehicle state data, dynamically adjusts the angle of the photovoltaic panel to face the sunlight by using a sun trajectory calculator, and measures the output power in real time and records the energy collection efficiency by using a current-voltage sensor.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy vehicles, in particular to a photovoltaic energy power domain vehicle control method. BACKGROUND

[0002] With the increasing demand for clean energy worldwide, solar energy, as a representative of sustainable development, has attracted more and more attention in the field of transportation, especially electric vehicles. Photovoltaic energy power domain vehicle control technology has been developed since the late 20th century. Early research focused on how to efficiently integrate photovoltaic panels into vehicles and test their energy collection capabilities in static environments. Early attempts usually involved installing photovoltaic panels at a fixed angle to capture solar energy. However, this method was inefficient as it failed to take into account the changes in the position of the sun over time and geographical location.

[0003] Despite significant progress, current photovoltaic energy control systems still have some limitations. First, most existing systems rely on preset schedules or basic algorithms to adjust the angle of photovoltaic panels, which limits their ability to make precise adjustments using environmental data and vehicle state data. Second, existing energy management systems lack effective prediction mechanisms for future energy demand and supply. This can lead to problems such as overcharging or undercharging of batteries, affecting vehicle performance and user experience. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a photovoltaic energy power domain vehicle control method to solve the problem of inaccurate photovoltaic panel angle adjustment and effective prediction of future energy demand in the prior art.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a photovoltaic energy power domain vehicle control method, which includes initializing settings and collecting environmental data and vehicle state data through integrated sensors; based on the environmental data and vehicle state data, calculating the optimal photovoltaic panel angle through a solar trajectory calculator, dynamically adjusting the photovoltaic panel angle, and recording the energy collection efficiency of the photovoltaic panel in real time; based on the photovoltaic panel energy collection efficiency and the data collected by the sensors, analyzing and predicting the energy demand value in a future period of time through a deep learning model, and generating an energy distribution strategy through an intelligent algorithm; performing energy management operations through the energy distribution strategy, continuously monitoring the energy collection of the photovoltaic panel and the energy consumption of the vehicle, and feeding back to the central processing unit to optimize the energy distribution strategy.

[0008] As a preferred scheme of the photovoltaic energy power domain vehicle control method, the initialization setting includes obtaining current position information, presetting the basic angle of the photovoltaic panel, checking the battery state, checking the software version, and calibrating the sensor.

[0009] As a preferred scheme of the photovoltaic energy power domain vehicle control method, the integrated sensor includes a GPS, an illumination sensor, a temperature sensor, a speed and acceleration sensor, and a BMS sensor.

[0010] As a preferred scheme of the photovoltaic energy power domain vehicle control method, the environmental data includes geographical position, solar radiation intensity, weather condition, temperature, and wind speed and direction.

[0011] The vehicle state data includes the parking direction of the vehicle, the current angle of the photovoltaic panel, the battery power state, the load condition of the vehicle, and the historical energy consumption data.

[0012] As a preferred scheme of the photovoltaic energy power domain vehicle control method, the photovoltaic panel angle is dynamically adjusted, and the energy collection efficiency of the photovoltaic panel is recorded in real time, and the specific steps are as follows,

[0013] The optimal photovoltaic panel angle is calculated based on the solar trajectory calculator, and the inclination angle and azimuth angle of the photovoltaic panel are changed through rotating and moving mechanical structures to make the photovoltaic panel face the sunlight.

[0014] The output voltage and current of the photovoltaic panel are measured through the current and voltage sensor, the actual output power is calculated, and the actual output power is compared with the theoretical maximum power defined based on the technical specifications provided by the photovoltaic panel manufacturer to obtain the energy collection efficiency and record it.

[0015] As a preferred scheme of the photovoltaic energy power domain vehicle control method, the photovoltaic panel energy collection efficiency and the data collected by the sensor are analyzed through a deep learning model to predict the energy demand value, and the specific steps are as follows,

[0016] Based on the photovoltaic panel energy collection efficiency and the data collected by the sensor, data cleaning, normalization, and data segmentation processing are performed, and photovoltaic energy management features are extracted from the processed data.

[0017] Based on the historical data, a time series is constructed, the energy collection efficiency, the illumination intensity, and the temperature in the historical data are used as input features, and the historical data is divided into a training set and a test set.

[0018] The structure of the LSTM model is defined, the training set data is used to train the LSTM model structure, and the test set is used to evaluate the generalization ability of the LSTM model.

[0019] Based on the trained LSTM model, the energy demand value is predicted.

[0020] As a preferred scheme of the photovoltaic energy power domain vehicle control method, the energy distribution strategy is generated by an intelligent algorithm, and the specific steps are as follows.

[0021] Based on the difference between the electric energy generated by the photovoltaic panel and the electric energy stored by the battery and the energy demand value, the energy balance condition at a certain moment is defined.

[0022] Based on the energy demand value, the predicted energy demand value, the energy balance condition at a certain moment, and the photovoltaic energy management feature are taken as inputs, and the energy distribution proportion of each component at the next time step is predicted by an intelligent algorithm.

[0023] According to the energy distribution proportion, the current output power of the photovoltaic panel and the remaining electric quantity of the battery are divided to each component, and through real-time monitoring and dynamic adjustment, the energy use is optimized according to the energy distribution proportion, and an effective energy distribution strategy is generated.

[0024] As a preferred scheme of the photovoltaic energy power domain vehicle control method, the energy management operation is performed by the energy distribution strategy, the energy collection of the photovoltaic panel and the energy consumption condition of the vehicle are continuously monitored, and feedback is given to the central processing unit to optimize the energy distribution strategy, and the specific steps are as follows.

[0025] Based on the energy distribution strategy generated by the intelligent algorithm, and according to the data of the light intensity, the remaining capacity of the battery, and the running state of the vehicle, the energy supply of each component is dynamically adjusted.

[0026] The data collected by the sensor is transmitted to the central processing unit, the central processing unit analyzes the received data, generates an adjustment energy distribution strategy, and evaluates the energy collection efficiency of the photovoltaic panel and the energy consumption condition of the vehicle.

[0027] In a second aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the computer program is executed by the processor to implement any step of the photovoltaic energy power domain vehicle control method according to the first aspect of the present application.

[0028] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement any step of the photovoltaic energy power domain vehicle control method according to the first aspect of the present application.

[0029] The present application has the beneficial effects that: by combining environmental data and vehicle state data, the solar trajectory calculator is used to dynamically adjust the angle of the photovoltaic panel to face the sunlight, and the current-voltage sensor is used to measure the output power and record the energy collection efficiency in real time. Based on these data, the LSTM model is used to predict the future energy demand and supply situation, and the intelligent algorithm dynamically generates the energy distribution ratio of each component accordingly. This method not only improves the energy utilization efficiency, but also prolongs the service life of the battery, enhances the overall performance of the vehicle and the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0031] Figure 1 Flowchart for the photovoltaic energy power domain vehicle control method in embodiment 1.

[0032] Figure 2 Flowchart for predicting the energy demand value in embodiment 1. DETAILED DESCRIPTION

[0033] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0034] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0035] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0036] Embodiment 1, reference Figure 1 and Figure 2 , the first embodiment of the present application provides a photovoltaic energy power domain vehicle control method, comprising the following steps:

[0037] S1: initialization setting is performed, and environmental data and vehicle state data are collected through integrated sensors.

[0038] S1.1: The initialization setting includes obtaining current location information, presetting the basic angle of the photovoltaic panel, checking the battery status, checking the software version, and calibrating the sensor.

[0039] It should be noted that the initialization setting first obtains the current location information of the device to determine the optimal operating parameters. Then, the basic angle of the photovoltaic panel is preset according to the geographical location to maximize the light receiving efficiency. At the same time, the status of the battery needs to be checked to ensure that it is working properly and can store energy stably. Then, the software version is checked to ensure that the system is running the latest software version, thereby avoiding possible errors or performance problems. Finally, the sensor calibration is performed to ensure the accuracy of data acquisition by accurately calibrating each sensor, providing reliable data support for the efficient operation of the system.

[0040] S1.2: The integrated sensors include GPS, light sensor, temperature sensor, speed and acceleration sensor, and BMS sensor.

[0041] Further, the integrated sensor suite includes GPS for positioning and navigation, light sensor for detecting ambient light intensity, temperature sensor for monitoring temperature changes during device operation, speed and acceleration sensor for tracking the motion state of the device, and BMS sensor for monitoring the health status and charging and discharging efficiency of the battery. These sensors work together to provide comprehensive environmental and state information monitoring.

[0042] S2: Based on environmental data and vehicle state data, the optimal photovoltaic panel angle is calculated by a solar trajectory calculator, the photovoltaic panel angle is dynamically adjusted, and the energy collection efficiency of the photovoltaic panel is recorded in real time.

[0043] S2.1: The environmental data includes geographical location, solar radiation intensity, weather conditions, temperature, and wind speed and direction;

[0044] The vehicle state data includes the parking direction of the vehicle, the current angle of the photovoltaic panel, the battery power state, the load condition of the vehicle, and the historical energy consumption data;

[0045] Based on the environmental data and vehicle state data, the optimal photovoltaic panel angle is calculated by a solar trajectory calculator, and the expression is:

[0046] θ=(α s (φ,t)+k1·v+k2·ΔT,A z (φ,t)+k3·a+k4·I s );

[0047] Where θ represents the optimal photovoltaic panel angle, t represents the current time, φ represents the dimension coordinate of the location where the vehicle is located, α s(φ, t) represents the solar elevation angle calculated according to the latitude φ and the time t, v represents the speed of the vehicle, k1 represents the influence coefficient of adjusting the speed v on the inclination angle of the photovoltaic panel, ΔT represents the temperature change value of the environment, k2 represents the influence coefficient of adjusting the temperature change value ΔT on the inclination angle of the photovoltaic panel, A z (φ, t) represents the solar azimuth angle calculated according to the latitude φ and the time t, k3 represents the influence coefficient of adjusting the acceleration a on the azimuth angle of the photovoltaic panel, a represents the acceleration of the vehicle, I s represents the light intensity, k4 represents the influence coefficient of adjusting the light intensity I s on the azimuth angle of the photovoltaic panel.

[0048] S2.2: Real-time record the energy collection efficiency of the photovoltaic panel.

[0049] Further, based on the solar trajectory calculator, the angle most suitable for the photovoltaic panel to absorb solar energy is calculated, and the inclination angle and azimuth angle of the photovoltaic panel can be adjusted by controlling the rotating and moving mechanical structure, to ensure that the photovoltaic panel accurately faces the sunlight, thereby maximizing the light receiving efficiency and optimizing the energy collection process. This automatic process dynamically adjusts the angle of the photovoltaic panel according to the position of the sun, to adapt to the solar trajectory at different times and places, and to improve the energy utilization efficiency.

[0050] S2.3: Measure the output voltage and current of the photovoltaic panel through the current-voltage sensor, calculate the actual output power, and compare the actual output power with the theoretical maximum power defined based on the technical specifications provided by the photovoltaic panel manufacturer, to obtain the energy collection efficiency and record it.

[0051] It should be noted that by measuring the output voltage and current of the photovoltaic panel through the current-voltage sensor, the actual output power can be calculated, and the theoretical maximum power can be defined according to the technical specifications provided by the photovoltaic panel manufacturer. Then, the actual output power is compared with the theoretical maximum power to obtain the energy collection efficiency, and the results of the entire process are recorded for subsequent performance evaluation and optimization adjustment. This series of steps helps to accurately understand the working efficiency of the photovoltaic panel and ensures the maximization of energy utilization.

[0052] S3: Based on the photovoltaic panel energy collection efficiency and the data collected by the sensor, analyze and predict the energy demand value through a deep learning model, and generate an energy distribution strategy through an intelligent algorithm.

[0053] S3.1: Based on the photovoltaic panel energy collection efficiency and the data collected by the sensor, perform data cleaning, normalization and data segmentation processing, and extract photovoltaic energy management features from the processed data.

[0054] Further, based on the photovoltaic panel energy collection efficiency and the data collected by the sensor, first, data cleaning is performed to remove outliers and inaccurate data, then the cleaned data is normalized to ensure that each data index is within a comparable range, and then data segmentation is performed to analyze the performance under different stages or conditions. From these processed data, key features that contribute to photovoltaic energy management are extracted, such as optimal angle, cleanliness impact, temperature coefficient, etc., to provide data support for improving energy collection efficiency and optimization.

[0055] S3.2: Based on historical data, construct a time series, take the energy collection efficiency, light intensity and temperature in the historical data as input features, and divide them into training set and test set.

[0056] Based on historical data, construct a time series, take the energy collection efficiency, light intensity and temperature in the past records as input features, analyze the change pattern of these features over time to predict future performance, and divide these data into training set and test set to evaluate the accuracy and reliability of the model. The whole process aims to optimize photovoltaic energy management and improve energy collection efficiency using past data.

[0057] S3.3: Define the structure of the LSTM model, train the LSTM model structure using the training set data, and evaluate the generalization ability of the LSTM model using the test set.

[0058] Further, define the structure of the LSTM model, train this model using the training set data, learn the patterns and rules in the time series through input features, and then evaluate the generalization ability of the model using the test set to ensure that it can accurately predict on unseen data. The whole process aims to improve the accuracy and reliability of photovoltaic energy management.

[0059] S3.4: Based on the trained LSTM model, predict the energy demand value, the specific expression is:

[0060]

[0061] where, represents the energy demand value at future time t, t represents different time nodes in the sequence, W y represents the weight matrix of the output layer, b y represents the bias term of the output layer, h represents the hidden state, h t represents the hidden state of LSTM at time step t, W h represents the weight matrix of the LSTM hidden state, h t s represents the decoder state, W sdenotes the weight matrix at decoder state s, v denotes the weight vector in the attention mechanism, T denotes the transpose operation of a vector, v T denotes the transpose form of the weight vector v in the attention mechanism, h n denotes the hidden state of the last time step after the LSTM has processed all inputs, b y denotes the bias term of the output layer, n denotes the length of the input sequence, b denotes the bias term of the nonlinear transformation, k denotes the index of all time steps of the input sequence.

[0062] S3.5: Based on the difference between the electrical energy generated by the photovoltaic panel and the electrical energy stored in the battery and the energy demand value, the energy balance status at a certain moment is defined.

[0063] Further, based on the difference between the electrical energy generated by the photovoltaic panel and the electrical energy stored in the battery and the energy demand value, the energy balance status at a certain moment can be defined, that is, by comparing the three, the real-time electrical energy generated by the photovoltaic panel, the available electrical energy stored in the battery, and the energy demand value at that moment, it is determined whether the energy supply and demand balance is reached at present. If the electrical energy generated by the photovoltaic panel plus the electrical energy released by the battery meets the immediate energy demand, it is considered to be in energy balance state; otherwise, there is a situation of energy surplus or shortage, and the energy management strategy needs to be adjusted to cope with different energy demand and supply changes. This process helps to accurately control energy distribution and ensure efficient use of renewable energy resources.

[0064] S3.6: Based on the predicted energy demand value, the predicted energy demand value, the energy balance status at a certain moment, and the photovoltaic energy management characteristics are taken as inputs, and the energy distribution ratio of each component at the next time step is predicted through intelligent algorithm, and the specific expression is:

[0065]

[0066] Where, t+1 represents the next time step immediately after it, a(t+1) represents the energy distribution ratio at t+1, A represents the optimization algorithm based on reinforcement learning, represents the predicted energy supply, Δt represents the time interval from time t to t+1, represents the energy supply prediction value at future time point t+Δt obtained through the prediction model, represents the predicted energy demand, represents the energy demand prediction value at future time point t+Δt obtained through the prediction model, E b represents the energy balance, E b (t) represents the energy balance status at time t, X t represents the photovoltaic energy management characteristics collected at time t.

[0067] S3.7: According to the energy allocation ratio, the current output power of the photovoltaic panel and the remaining capacity of the battery are divided among the various components. Through real-time monitoring and dynamic adjustment, the energy use is optimized according to the energy allocation ratio, and an effective energy allocation strategy is generated.

[0068] Further, according to the energy allocation ratio, the current output power of the photovoltaic panel and the remaining capacity of the battery are reasonably divided among the various components. Through real-time monitoring of the energy use of each component and dynamic adjustment of the allocation ratio, the optimization of energy use is ensured. This process involves flexible energy allocation based on the needs and priorities of different components, aiming to maximize the use of photovoltaic panel-generated electricity and battery-stored electricity, while ensuring that key components receive sufficient energy support. The entire mechanism generates an effective energy allocation strategy through continuous monitoring and intelligent adjustment, thereby improving overall energy utilization efficiency.

[0069] S4: Energy management operation is carried out through the energy allocation strategy, continuously monitoring the energy collection of the photovoltaic panel and the energy consumption of the vehicle, and feeding back to the central processing unit to optimize the energy allocation strategy.

[0070] S4.1: Based on the energy allocation strategy generated by the intelligent algorithm, and according to the data of light intensity, battery remaining capacity and vehicle running state, the energy supply of each component is dynamically adjusted.

[0071] It should be noted that based on the energy allocation strategy generated by the intelligent algorithm, and according to the real-time monitoring data of light intensity, battery remaining capacity and vehicle running state, the energy supply of each component is dynamically adjusted. This process first relies on advanced optimization algorithms that can analyze and process data from multiple sources, including current lighting conditions, battery charging and discharging status, and vehicle driving conditions, etc., to develop a scientific and reasonable energy allocation plan. By continuously monitoring the changes of these key parameters, changes in environmental and operating conditions can be identified in a timely manner, such as prioritizing the use of photovoltaic energy for vehicle power supply and battery charging when the light is strong during the day; while in the case of insufficient light or low battery capacity, the limited energy resources are redistributed to ensure the energy supply to key components, such as prioritizing the power demand of driving safety-related electronic devices.

[0072] Further, this dynamic adjustment mechanism can also predict the energy demand and production situation in the future period of time, make corresponding energy reserve or release decisions in advance, to avoid energy shortage or waste. For example, increase the energy output of the battery when entering the tunnel or driving at night is expected, while reducing the energy consumption of unnecessary components. This method not only improves the efficiency of energy use, but also prolongs the service life of the battery, reduces the overall operating cost, and makes the whole energy management more intelligent and efficient. In this way, even in complex and variable actual operating environment, the effective allocation and use of energy can be ensured, and the renewable energy can be maximized, while ensuring that all key components obtain sufficient and stable energy supply.

[0073] S4.2: The data collected by the sensors is transmitted to the central processing unit, which analyzes the received data, generates an adjustment energy distribution strategy, and evaluates the energy collection efficiency of the photovoltaic panel and the energy consumption of the vehicle.

[0074] It should be noted that the data collected by the sensors, including light intensity, temperature, battery remaining capacity and vehicle running state information, are transmitted to the central processing unit, which analyzes these data in depth to identify the current energy production and consumption mode. Based on the analysis results, the energy distribution strategy is generated or adjusted to ensure that the energy generated by the photovoltaic panel and the energy stored in the battery can be efficiently and reasonably distributed to each component to meet the immediate energy demand and optimize the overall energy utilization efficiency.

[0075] Further, by comparing the actual output power of the photovoltaic panel with the theoretical maximum power, the energy collection efficiency is evaluated, and the possible performance bottleneck or improvement space is identified. For the energy consumption of the vehicle, it will also be comprehensively evaluated according to the driving distance, speed, load and other factors to determine the rationality of energy use and provide a reference for future energy management. The whole process aims to maximize the utilization of photovoltaic energy through accurate data analysis and intelligent decision-making, while ensuring the efficient and stable operation of the vehicle under various conditions, achieving the goal of energy saving and emission reduction and prolonging the service life of the battery. Through continuous circulation of this process, the energy distribution strategy can be continuously optimized, the ability to cope with different environmental and operating conditions can be improved, and the optimal allocation and use of energy resources can be ensured.

[0076] The embodiment also provides a computer device suitable for the photovoltaic energy power domain vehicle control method, which comprises 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 realize the photovoltaic energy power domain vehicle control method proposed in the above embodiment.

[0077] The computer device can be a terminal, which includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. 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 external terminals in a wired or wireless manner. The wireless manner can be achieved by WIFI, operator 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. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0078] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the control method of the photovoltaic energy power domain vehicle 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 (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0079] In summary, the present application dynamically adjusts the angle of the photovoltaic panel to face the sunlight by combining environmental data and vehicle state data using a solar trajectory calculator, and uses a current-voltage sensor to measure output power and record energy collection efficiency in real time. Based on these data, an LSTM model is used to predict future energy demand and supply, and an intelligent algorithm dynamically generates energy distribution ratios for each component accordingly. This method not only improves energy utilization efficiency, but also prolongs the service life of the battery, enhances the overall performance of the vehicle and the user experience.

[0080] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A photovoltaic energy power domain vehicle control method, characterized by: The application relates to a photovoltaic energy management system for a vehicle, which comprises, initialization setting is performed, and environmental data and vehicle state data are collected through integrated sensors; based on the environmental data and the vehicle state data, a most suitable photovoltaic panel angle is calculated through a sun trajectory calculator, the photovoltaic panel angle is dynamically adjusted, and the energy collection efficiency of the photovoltaic panel is recorded in real time; based on the photovoltaic panel energy collection efficiency and the data collected by the sensors, analysis is performed through a deep learning model, an energy demand value is predicted, and an energy distribution strategy is generated through an intelligent algorithm; energy management operation is performed through the energy distribution strategy, the energy collection of the photovoltaic panel and the energy consumption of the vehicle are continuously monitored, and feedback is given to the central processing unit to optimize the energy distribution strategy; wherein based on the photovoltaic panel energy collection efficiency and the data collected by the sensors, analysis is performed through a deep learning model, and an energy demand value is predicted, the specific steps are as follows, based on the photovoltaic panel energy collection efficiency and the data collected by the sensors, data cleaning, normalization and data segmentation processing are performed, and photovoltaic energy management features are extracted from the processed data; based on historical data, a time sequence is constructed, the energy collection efficiency, the light intensity and the temperature in the historical data are taken as input features, and the historical data are divided into a training set and a test set; an LSTM model structure is defined, the training set data is used to train the LSTM model structure, and the test set is used to evaluate the generalization ability of the LSTM model; based on the trained LSTM model, an energy demand value is predicted; wherein the energy distribution strategy is generated through an intelligent algorithm, and the specific steps are as follows, based on the difference between the electric energy generated by the photovoltaic panel and the electric energy stored in the battery and the energy demand value, an energy balance condition is defined; based on the energy demand value, the predicted energy demand value, the energy balance condition at a certain moment and the photovoltaic energy management features are taken as inputs, and the energy distribution proportion of each component at the next time step is predicted through an intelligent algorithm; according to the energy distribution proportion, the current output power of the photovoltaic panel and the residual electric quantity of the battery are divided into each component, energy use is optimized according to the energy distribution proportion through real-time monitoring and dynamic adjustment, and an effective energy distribution strategy is generated.

2. The photovoltaic energy powertrain vehicle control method of claim 1, wherein: The initialization setting comprises obtaining current position information, presetting a basic angle of the photovoltaic panel, checking a battery state, checking a software version and calibrating a sensor.

3. The photovoltaic energy powertrain vehicle control method of claim 2, wherein: The integrated sensors comprise a GPS, a light sensor, a temperature sensor, a speed and acceleration sensor and a BMS sensor.

4. The photovoltaic energy powertrain vehicle control method of claim 3, wherein: The environmental data comprises a geographical position, a solar radiation intensity, a weather condition, a temperature and a wind speed and direction; The vehicle state data comprises a vehicle parking direction, a current angle of the photovoltaic panel, a battery electric quantity state, a vehicle load condition and historical energy consumption data.

5. The photovoltaic energy powertrain vehicle control method of claim 4, wherein: The dynamic adjustment of the photovoltaic panel angle and the real-time recording of the energy collection efficiency of the photovoltaic panel are performed, and the specific steps are as follows, the most suitable photovoltaic panel angle is calculated through the sun trajectory calculator, and the inclination angle and the azimuth angle of the photovoltaic panel are changed through rotating and moving mechanical structures so that the photovoltaic panel faces the sunlight. The output voltage and current of the photovoltaic panel are measured by a current-voltage sensor, the actual output power is calculated, and the theoretical maximum power is defined based on the technical specifications provided by the photovoltaic panel manufacturer, the actual output power is compared with the theoretical maximum power, the energy collection efficiency is obtained, and the record is recorded.

6. The photovoltaic energy powertrain vehicle control method of claim 1, wherein: The energy management operation through the energy distribution strategy, the energy collection of the photovoltaic panel and the energy consumption of the vehicle are monitored, and feedback is given to the central processing unit to optimize the energy distribution strategy, and the specific steps are as follows, Based on the energy distribution strategy generated by the intelligent algorithm, and according to the data of light intensity, battery remaining capacity and vehicle running state, the energy supply of each component is dynamically adjusted; The data collected by the sensor is transmitted to the central processing unit, the central processing unit analyzes the received data, generates an adjustment energy distribution strategy, and evaluates the energy collection efficiency of the photovoltaic panel and the energy consumption of the vehicle. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the photovoltaic energy power domain vehicle control method of any one of claims 1-6.

8. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the photovoltaic energy power domain vehicle control method of any one of claims 1-6.

Images