Solar hydrogen hybrid flying car energy management method based on solar distribution map

Abstract

The application provides a solar hydrogen energy hybrid flying car energy management method based on a solar distribution map, and belongs to the field of solar hydrogen energy hybrid flying car energy management, and the method comprises the following steps: S1, predicting the solar radiation intensity distribution by using a BP neural network; S2, determining a flying car trajectory by using an Astar algorithm based on solar radiation; S3, establishing a trajectory optimization and energy management coupling model; and S4, solving the coupling model by using a sequential quadratic programming algorithm. The application reasonably allocates the power of each power source of the hybrid flying car, so that the state of charge of the power battery of the hydrogen fuel cell flying car is kept balanced, the hydrogen energy consumption is reduced, and the drivability and riding comfort of the hydrogen fuel cell flying car are improved.

Description

Technical Field

[0001] This invention relates to the field of energy management technology for solar-powered hydrogen hybrid flying cars, and more particularly to an energy management method for solar-powered hydrogen hybrid flying cars based on a solar energy distribution map. Background Technology

[0002] Against the backdrop of a worsening energy crisis, solar and hydrogen energy, as two clean and renewable energy sources, have demonstrated enormous potential. Solar energy directly converts sunlight into electricity, while hydrogen energy is generated through methods such as water electrolysis. Neither relies on fossil fuels, significantly reducing greenhouse gas emissions. The combination of solar and hydrogen energy can not only provide a stable and reliable energy supply but also reduce dependence on traditional energy sources such as oil, improving energy independence and security. This combination offers a viable path to addressing the energy crisis, propelling the world towards a more sustainable and environmentally friendly future. The combination of solar energy and hydrogen fuel cell flying cars represents the future direction of transportation. Solar panels can collect solar energy during flight or while parked, converting it into electricity to power the car or charge the hydrogen fuel cell. The hydrogen fuel cell provides high energy density and long range, ensuring efficient operation even at night or on cloudy days when solar energy is insufficient. This energy combination not only significantly reduces carbon emissions and environmental pollution but also improves energy efficiency and reduces reliance on fossil fuels. This reduction in reliance on raw materials lays the foundation for building a more sustainable and environmentally friendly transportation system.

[0003] However, most existing flying cars rely on traditional mechanical or electric power, lacking the integration of solar and hydrogen energy for their development. This hinders improvements in operational efficiency and sustainability, and fails to reduce energy consumption and environmental impact, thus failing to provide strong support for the development of green transportation. Therefore, this paper proposes an energy management method for solar-hydrogen hybrid flying cars based on a solar energy distribution map to address these issues. Summary of the Invention

[0004] Therefore, the purpose of this invention is to provide an energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map, so as to at least solve the above problems.

[0005] The technical solution adopted in this invention is as follows: A method for energy management of a solar-powered hydrogen hybrid flying car based on a solar energy distribution map, the method comprising the following steps: S1. Predict the distribution of solar radiation intensity by using a BP neural network; S2. The trajectory of the flying car is determined by using the Astar algorithm based on solar radiation. S3. Establish a coupled model for trajectory optimization and energy management; S4. Solve the coupled model using the sequential quadratic programming algorithm.

[0006] Furthermore, in step S1, the prediction of solar radiation intensity distribution using a BP neural network specifically involves: By dividing the BP neural network into Layers, and any node The output is For the first The input, the () ) layer The output of each node is , Represents the activation function, the first... Layer The node and the first Layer The connection weight of each node is , No. The number of nodes in the layer is The output is Then the first The first-level input of each node is Then the first Layer The output of each node is The specific formula is as follows:

[0007] .

[0008] Furthermore, the input parameters of the BP neural network are time, flying car accuracy, latitude, pressure, humidity, and solar radiation parameters, and the output parameter of the BP neural network is solar radiation intensity.

[0009] Furthermore, step S2 also includes the following steps: S21. Grid the area from the starting point to the destination of the flying car; S22. Define the OPEN and CLOSED lists, and initialize them to empty; S23. Assign the starting point A to the OPEN list and the obstacles to the CLOSED list; S24. Calculate the f(s) value of the nodes in the OPEN list; S25. Find the node with the smallest f(s) value, add it as the parent node to the CLOSED list, and add its neighboring nodes to the OPEN list; S26. Determine whether the target node is contained in the CLOSED list. If yes, proceed to step S27. If no, proceed to step S24. S27. Calculate the optimal path from the starting point to the target location in the CLOSED list to complete the path planning.

[0010] Furthermore, in step S25, the node with the smallest f(s) value is found, and it is added to the CLOSED list as its parent node, and its neighboring nodes are added to the OPEN list. Specifically: The calculation is performed using the following formula:

[0011] Where: f(s) is the cost estimate from the initial state to the target state via state s, g(s) is the actual cost from the initial state to state s in the state space, and h(s) is the estimated cost of the optimal path from state n to the target state. It is the cost of solar radiation from the initial state to state s in the state space, specifically expressed as the difference in radiation intensity. The value represents the radiation equivalence factor, indicating whether the path planning is biased towards relying on solar radiation values. The formula uses Euclidean distance as a description of the cost of movement between two nodes:

[0012]

[0013] in Let be the x-coordinate of node i. Let be the ordinate of node i. Let be the radiation intensity at node i. Let be the radiation intensity at node j.

[0014] Furthermore, in step S3, the establishment of the trajectory optimization and energy management coupled model is specifically as follows: By constructing a hybrid system of solar energy, hydrogen energy, and batteries, and setting the state variables of the hybrid system as... The control variable is set to Equations of state as follows

[0015] The three-dimensional position of the flying car is defined by the following formula ( , The flight speed is defined by the following formula: The flight path angle is defined by the following formula The heading angle represents the angle between flight speed and altitude. The heading angle is defined by the following formula: , represents the flight direction of the flying car, and the thrust of the flying car during flight is represented by . Vertical load and horizontal load , represents the load factor in the direction corresponding to the flight path. Indicates the mass of the flying car and Indicates the reference wing area, coefficient , These represent the parasitic drag coefficient and the aerodynamic coefficient, respectively. and This represents gravitational acceleration and atmospheric density. It is the angle between the sunlight and the normal vector of the flying car. It is the PV area. It is the solar irradiance in the environment. It refers to the photovoltaic conversion efficiency from solar energy to electrical energy. To minimize the energy consumption of the hybrid system, this is shifted to optimizing FC hydrogen consumption and battery-equivalent hydrogen consumption, with the loss function being:

[0016] in It is the battery equivalent hydrogen consumption coefficient, and the battery power consumption can be obtained through... Converted into hydrogen consumption Based on the dynamic changes in battery state of charge (SOC), a PID controller is used for control. Changes, The final flight time, trajectory optimization, and energy management coupled model is as follows:

[0017]

[0018] in It is the driving force behind the demand for flying cars. , , These are the battery output power, fuel cell output power, and solar panel output power, respectively. and These are the DC / DC conversion efficiency and the maximum power point tracker conversion efficiency, respectively.

[0019] Furthermore, in step S4, the sequential quadratic programming algorithm is used to solve the coupled model as follows: Define an objective function J that minimizes while satisfying constraints. , ,in It is an optimization variable. (1) By constructing the Lagrange function: The Lagrange function is defined as follows:

[0020] in and These are Lagrange multipliers, used to handle inequality constraints. Sum of equality constraints ; (2) Calculate the gradient and Hessian matrix: Calculate the gradient of the objective function J. J, and constraint functions and gradient , and their Hessian matrices , , ; (3) Construct a quadratic programming subproblem: at the current iteration point Construct a quadratic programming subproblem:

[0021]

[0022]

[0023] (4) Solve the quadratic programming problem: By solving the above quadratic programming problem, the search direction is obtained. ; (5) Update iteration point: Calculate the next iteration point + And update the Lagrange multipliers ; (6) Iteration: Repeat steps 2 to 5 until the convergence criterion is met, that is, the objective function changes very little.

[0024] Compared with the prior art, the beneficial effects of the present invention are: This invention proposes an energy management method for solar-hydrogen hybrid flying cars based on a solar energy distribution map. The combination of trajectory optimization and energy management in solar-hydrogen flying cars can significantly improve their operational efficiency and sustainability. Through advanced trajectory optimization technology, the flying car can select the most energy-efficient route, maximizing the utilization of solar and hydrogen energy resources. Simultaneously, the intelligent energy management system can monitor and adjust the energy distribution of solar panels and hydrogen fuel cells in real time, ensuring optimal energy utilization under different flight conditions. This comprehensive optimization not only improves the flying car's range and reliability but also reduces energy consumption and environmental impact, providing strong support for the development of green transportation. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only preferred embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the overall process proposed in the embodiments of the present invention.

[0027] Figure 2 This is a schematic diagram of the overall structure of predicting solar radiation intensity distribution using a BP neural network according to an embodiment of the present invention.

[0028] Figure 3 This is a schematic diagram of the overall structure of the flying car trajectory determined using the Astar algorithm based on solar radiation, according to an embodiment of the present invention.

[0029] Figure 4 This is a flowchart illustrating a sub-step of step S2 in an embodiment of the present invention.

[0030] Figure 5 This is a schematic diagram of the trajectory optimization and energy management coupling model according to an embodiment of the present invention. Detailed Implementation

[0031] The principles and features of the present invention are described below with reference to the accompanying drawings. The listed embodiments are only used to explain the present invention and are not intended to limit the scope of the present invention.

[0032] Reference Figures 1 to 5 This invention provides an energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map, the method comprising the following steps: S1. Predict the distribution of solar radiation intensity by using a BP neural network; S2. The trajectory of the flying car is determined by using the Astar algorithm based on solar radiation. S3. Establish a coupled model for trajectory optimization and energy management; S4. Solve the coupled model using the sequential quadratic programming algorithm.

[0033] In step S1, the solar radiation intensity distribution is predicted using a BP neural network as follows: By dividing the BP neural network into Layers, and any node The output is For the first The input, the () ) layer The output of each node is , Represents the activation function, the first... Layer The node and the first Layer The connection weight of each node is , No. The number of nodes in the layer is The output is Then the first The first-level input of each node is Then the first Layer The output of each node is The specific formula is as follows:

[0034] .

[0035] The input parameters of the BP neural network are time, flying car accuracy, latitude, pressure, humidity, solar radiation, etc., and the output parameter of the BP neural network is solar radiation intensity.

[0036] Step S2 also includes the following steps: S21. Grid the area from the starting point to the destination of the flying car; S22. Define the OPEN and CLOSED lists, and initialize them to empty; S23. Assign the starting point A to the OPEN list and the obstacles to the CLOSED list; S24. Calculate the f(s) value of the nodes in the OPEN list; S25. Find the node with the smallest f(s) value, add it as the parent node to the CLOSED list, and add its neighboring nodes to the OPEN list; S26. Determine whether the target node is contained in the CLOSED list. If yes, proceed to step S27. If no, proceed to step S24. S27. Calculate the optimal path from the starting point to the target location in the CLOSED list to complete the path planning.

[0037] In step S25, the node with the smallest f(s) value is found, and it is added to the CLOSED list as its parent node. Its neighboring nodes are then added to the OPEN list. Specifically: The Astar algorithm based on improved solar radiation intensity is as follows: Figure 2The algorithm expands outwards from the starting point, calculating the cost of each surrounding node using an evaluation function. The node with the minimum cost is selected as the next node to expand, and this process is repeated until the target point is reached, generating the final path. During the search, since each node on the path has the minimum cost, the total cost of the resulting path is minimized. The evaluation function f(n) of the Astar algorithm is expressed as:

[0038] Where: f(s) is the cost estimate from the initial state to the target state via state s, g(s) is the actual cost from the initial state to state s in the state space, and h(s) is the estimated cost of the optimal path from state n to the target state. It is the cost of solar radiation from the initial state to state s in the state space, specifically expressed as the difference in radiation intensity. The value represents the radiation equivalence factor, indicating whether the path planning is biased towards relying on solar radiation values. The formula uses Euclidean distance as a description of the cost of movement between two nodes:

[0039]

[0040] in Let be the x-coordinate of node i. Let be the ordinate of node i. Let be the radiation intensity at node i. Let be the radiation intensity at node j.

[0041] In step S3, the establishment of the trajectory optimization and energy management coupled model is specifically as follows: By constructing a hybrid system of solar energy, hydrogen energy, and batteries, and setting the state variables of the hybrid system as... The control variable is set to Equations of state as follows

[0042] The three-dimensional position of the flying car is defined by the following formula ( , The flight speed is defined by the following formula: The flight path angle is defined by the following formula The heading angle represents the angle between flight speed and altitude. The heading angle is defined by the following formula: , represents the flight direction of the flying car, and the thrust of the flying car during flight is represented by . Vertical load and horizontal load , represents the load factor in the direction corresponding to the flight path. Indicates the mass of the flying car and Indicates the reference wing area, coefficient , These represent the parasitic drag coefficient and the aerodynamic coefficient, respectively. and This represents gravitational acceleration and atmospheric density. It is the angle between the sunlight and the normal vector of the flying car. It is the PV area. It is the solar irradiance in the environment. It refers to the photovoltaic conversion efficiency from solar energy to electrical energy. To minimize the energy consumption of the hybrid system, this is shifted to optimizing FC hydrogen consumption and battery-equivalent hydrogen consumption, with the loss function being:

[0043] in It is the battery equivalent hydrogen consumption coefficient, and the battery power consumption can be obtained through... Converted into hydrogen consumption Based on the dynamic changes in battery state of charge (SOC), a PID controller is used for control. Changes, The final flight time, trajectory optimization, and energy management coupled model is as follows:

[0044]

[0045] in It is the driving force behind the demand for flying cars. , , These are the battery output power, fuel cell output power, and solar panel output power, respectively. and These are the DC / DC conversion efficiency and the maximum power point tracker conversion efficiency, respectively.

[0046] In step S4, the sequential quadratic programming algorithm is used to solve the coupled model as follows: Define an objective function J that minimizes while satisfying constraints. , ,in It is an optimization variable. (1) By constructing the Lagrange function: The Lagrange function is defined as follows:

[0047] in and These are Lagrange multipliers, used to handle inequality constraints. Sum of equality constraints ; (2) Calculate the gradient and Hessian matrix: Calculate the gradient of the objective function J. J, and constraint functions and gradient , and their Hessian matrices , , ; (3) Construct a quadratic programming subproblem: at the current iteration point Construct a quadratic programming subproblem:

[0048]

[0049]

[0050] (4) Solve the quadratic programming problem: By solving the above quadratic programming problem, the search direction is obtained. ; (5) Update the iteration point: Calculate the next iteration point. + And update the Lagrange multipliers ; (6) Iteration: Repeat steps 2 to 5 until the convergence criterion is met, that is, the objective function changes very little.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map, characterized in that, The method includes the following steps: S1. Predict the distribution of solar radiation intensity by using a BP neural network; S2. The trajectory of the flying car is determined by using the Astar algorithm based on solar radiation. S3. Establish a coupled model for trajectory optimization and energy management, specifically as follows: By constructing a hybrid system of solar energy, hydrogen energy, and batteries, and setting the state variables of the hybrid system as... The control variable is set to Equations of state as follows in,( , ) represents the three-dimensional position of the flying car. Indicates flight speed and flight path angle The heading angle represents the angle between flight speed and altitude. This indicates the flying car's flight direction and the thrust generated during flight. Vertical load and horizontal load , represents the load factor in the direction corresponding to the flight path. Indicates the mass of the flying car and Indicates the reference wing area, coefficient , These represent the parasitic drag coefficient and the aerodynamic coefficient, respectively. and Represents gravitational acceleration and atmospheric density. It is the angle between the sunlight and the normal vector of the flying car. It is the PV area. It is the solar irradiance in the environment. It refers to the conversion efficiency of photovoltaics from solar energy to electrical energy. To minimize the energy consumption of the hybrid system, this is shifted to optimizing FC hydrogen consumption and battery-equivalent hydrogen consumption, with the loss function being: in It is the battery equivalent hydrogen consumption coefficient, and the battery power consumption can be obtained through... Converted into hydrogen consumption Based on the dynamic changes in battery state of charge (SOC), a PID controller is used for control. Changes, The final flight time, trajectory optimization, and energy management coupled model is as follows: in It is the driving force behind the demand for flying cars. , , These are the battery output power, fuel cell output power, and solar panel output power, respectively. and These are the DC / DC conversion efficiency and the maximum power point tracker conversion efficiency, respectively. S4. Solve the coupled model using the sequential quadratic programming algorithm.

2. The energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map according to claim 1, characterized in that, In step S1, the solar radiation intensity distribution is predicted using a BP neural network as follows: By dividing the BP neural network into Layers, and any node The output is For the first The input, the () ) layer The output of each node is , Represents the activation function, the first... Layer The node and the first Layer The connection weight of each node is , No. The number of nodes in the layer is The output is Then the first The first-level input of each node is Then the first Layer The output of each node is The specific formula is as follows: 。 3. The energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map according to claim 2, characterized in that, The input parameters of the BP neural network are time, flying car accuracy, latitude, pressure, humidity, and solar radiation parameters, and the output parameter of the BP neural network is solar radiation intensity.

4. The energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map according to claim 3, characterized in that, Step S2 also includes the following steps: S21. Grid the area from the starting point to the destination of the flying car; S22. Define the OPEN and CLOSED lists, and initialize them to empty; S23. Assign the starting point A to the OPEN list and the obstacles to the CLOSED list; S24. Calculate the f(s) value of the nodes in the OPEN list; S25. Find the node with the smallest f(s) value, add it as the parent node to the CLOSED list, and add its neighboring nodes to the OPEN list; S26. Determine whether the target node is contained in the CLOSED list. If yes, proceed to step S27. If no, proceed to step S24. S27. Calculate the optimal path from the starting point to the target location in the CLOSED list to complete the path planning.

5. The energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map according to claim 4, characterized in that, In step S25, the node with the smallest f(s) value is found, and it is added to the CLOSED list as its parent node. Its neighboring nodes are then added to the OPEN list. Specifically: The calculation is performed using the following formula: Where: f(s) is the cost estimate from the initial state to the target state via state s, g(s) is the actual cost from the initial state to state s in the state space, and h(s) is the estimated cost of the optimal path from state n to the target state. It is the cost of solar radiation from the initial state to state s in the state space, specifically expressed as the difference in radiation intensity. The value represents the radiation equivalence factor, indicating whether the path planning is biased towards relying on solar radiation values. The formula uses Euclidean distance as a description of the cost of movement between two nodes: in Let be the x-coordinate of node i. Let be the ordinate of node i. Let be the radiation intensity at node i. Let be the radiation intensity at node j.

6. The energy management method for a solar-hydrogen hybrid flying car based on a solar energy distribution map according to claim 5, characterized in that, In step S4, the sequential quadratic programming algorithm is used to solve the coupled model as follows: Define an objective function J that minimizes while satisfying constraints. , ,in It is an optimization variable. (1) By constructing the Lagrange function: The Lagrange function is defined as follows: in and These are Lagrange multipliers, used to handle inequality constraints. Sum of equality constraints ; (2) Calculate the gradient and Hessian matrix: Calculate the gradient of the objective function J. J, and constraint functions and gradient , and their Hessian matrices , , ; (3) Construct a quadratic programming subproblem: at the current iteration point Construct a quadratic programming subproblem: (4) Solve the quadratic programming problem: By solving the above quadratic programming problem, the search direction is obtained. ; (5) Update the iteration point: Calculate the next iteration point. + And update the Lagrange multipliers ; (6) Iteration: Repeat steps 2 to 5 until the convergence criterion is met, that is, the objective function changes very little.

Images