A neural network prediction method for optimal working angle of a marine ship photovoltaic panel

Abstract

The application discloses a neural network prediction method for optimal working angle of a marine ship photovoltaic panel. The method considers the influence of sea wave fluctuation and solar position change on the ship photovoltaic power generation system, collects the operation data of the ship photovoltaic panel under different conditions, and establishes a neural network model to learn the output power curve of the ship photovoltaic panel on the basis, and then the trained ship photovoltaic panel power fluctuation neural network model is used to predict the output power of the photovoltaic panel under the current condition. According to the prediction result, the characteristics of the ship photovoltaic panel power fluctuation curve are analyzed to determine the optimal inclination angle of the current ship photovoltaic panel. The application can quickly obtain the optimal inclination angle of the photovoltaic panel to track the sun during the ship sailing process, effectively suppress the power fluctuation of the photovoltaic panel during the ship sailing at sea, reduce the power loss, and improve the output power.

Description

Technical Field

[0001] This invention relates to the field of marine new energy photovoltaic technology, specifically to a neural network prediction method for the optimal working angle of marine ship photovoltaic panels. Background Technology

[0002] Energy conservation and emission reduction technologies in the shipping industry have long attracted widespread attention both domestically and internationally. In May 2019, the Marine Environment Protection Committee (MEPC) set stricter emission targets for new shipbuilding, stipulating a 50% reduction in greenhouse gas emissions by 2050. To effectively implement these emission reduction standards, and given the increasing prominence of non-renewable resource issues and the growing public enthusiasm for environmental protection, new energy ships have become the main direction for future ship energy development. Among these, using clean energy as auxiliary energy for ships is particularly significant. It maximizes the utilization of green energy, providing ample energy for various ship facilities, reducing main engine energy consumption while ensuring smooth navigation. Solar energy, typically generated by energy harvesting devices installed on ships, continuously converts energy for utilization, making it a promising new energy source for ships.

[0003] Due to the influence of ocean wave fluctuations, the output power of marine ship photovoltaic systems fluctuates drastically, and the generated power cannot be maintained at its optimal level. This phenomenon significantly affects the power quality and battery life of the ship's electrical system. Land-based solar tracking systems are not adapted to the operating conditions of ships, and research in this area is currently lacking. Summary of the Invention

[0004] The technical problem to be solved by this invention is: to address the problem that the output power of photovoltaic cells cannot reach the maximum value and fluctuates due to the fluctuation of sea waves and the change of the sun's position during ship navigation, a neural network prediction method for the optimal working angle of marine ship photovoltaic panels is provided to better determine the optimal tilt angle of ship photovoltaic panels under different operating conditions.

[0005] To solve the above technical problems, the present invention provides the following technical solution: a neural network prediction method for the optimal working angle of photovoltaic panels on marine vessels, comprising the following steps:

[0006] S1. Construct a sample dataset of ship photovoltaic panels, including ship photovoltaic panel adjustment angle data, marine environment data and their corresponding output power data;

[0007] S2. Construct a neural network for the output power of ship photovoltaic panels. Train the neural network using a sample dataset of ship photovoltaic panels. During training, establish a power output relationship graph based on the relationship between the adjustment angle data of the ship photovoltaic panels, navigation environment data, and the corresponding output power of the ship photovoltaic panels. Obtain the power peak and valley values ​​and the power change trend. Finally, obtain the output power model of the ship photovoltaic panels and the optimal tilt angle of the ship photovoltaic panels corresponding to the power peak and valley values.

[0008] S3. Collect ship photovoltaic panel adjustment angle data and marine environment data. Use the ship photovoltaic panel output power model obtained in step S2 to predict the ship photovoltaic panel output power; adjust the ship photovoltaic panel to the optimal tilt angle.

[0009] Furthermore, in the aforementioned step S1, the ship photovoltaic panel angle data includes the ship photovoltaic panel angle, and the marine environment data includes light intensity, temperature, wave state, and the ship's position parameters relative to the sun.

[0010] Furthermore, the neural network used in step S2 above is a four-input, one-output network structure. The light intensity, temperature, ship roll angle caused by wave fluctuations, and current solar altitude angle in the ship's navigation environment are used as input layer neurons, and the maximum power value output by the photovoltaic cell is used as output layer neurons.

[0011] Furthermore, the aforementioned power output relationship diagram includes a power fluctuation curve.

[0012] Furthermore, the aforementioned power fluctuation curve was obtained through the following steps:

[0013] S401. Peak and valley value extraction of power fluctuation curve: Extract peak and valley values ​​from the power fluctuation curve. The peak value represents the highest point of the power fluctuation curve, and the valley value represents the lowest point of the power fluctuation curve.

[0014] S402. Analysis of the trend of peak and valley values ​​of power fluctuation curve: Analyze the changes of the extracted peak and valley values, including the amplitude and periodic changes of the peak and valley values. By analyzing the changes of peak and valley values, determine the overall trend and change pattern of the power fluctuation curve.

[0015] S403. Summary of power fluctuation curve patterns: Determine the optimal angle of the ship's photovoltaic panel under the conditions of light intensity, temperature, sea wave state, and ship position.

[0016] Another aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described in the present invention.

[0017] The present invention also proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described in the present invention.

[0018] Compared with the prior art, the beneficial technical effects of the above technical solution of the present invention are as follows: The present invention comprehensively considers the influence of different time positions and wave fluctuation characteristics on the output power of photovoltaic panels under the ship's navigation conditions. By establishing an accurate neural network model, the output power curve of the photovoltaic panel is predicted according to the input parameters. By analyzing the power fluctuation curve of the prediction results, the power curve features are extracted, classified and summarized, and then the optimal tilt angle under the current state is determined, thereby achieving the goal of reducing the power fluctuation of the photovoltaic panel and improving the output power under wave fluctuation conditions. Attached Figure Description

[0019] Figure 1 This is a flowchart of the steps of the present invention.

[0020] Figure 2 This is a diagram of the neural network structure of the present invention.

[0021] Figure 3 This is a comparison chart showing the power fluctuations of a ship's photovoltaic panels as they sway due to the impact of ocean waves when the solar altitude angle is 60°. Detailed Implementation

[0022] To better understand the technical content of the present invention, specific embodiments are described below in conjunction with the accompanying drawings.

[0023] In this invention, various aspects of the invention are described with reference to the accompanying drawings, in which numerous illustrative embodiments are shown. Embodiments of the invention are not limited to those depicted in the drawings. It should be understood that the invention is implemented through any of the various concepts and embodiments described above, as well as the concepts and embodiments described in detail below, because the concepts and embodiments disclosed herein are not limited to any particular implementation. Furthermore, some aspects of the invention disclosed may be used alone or in any suitable combination with other aspects of the invention disclosed.

[0024] like Figure 1 As shown, this invention provides a neural network prediction method for the optimal operating angle of photovoltaic panels on marine vessels, comprising the following steps:

[0025] S1. Construct a sample dataset of ship photovoltaic panels, including adjustment angle data of several ship photovoltaic panels, light intensity, temperature, wave state and ship position parameters data under ship navigation environment and their corresponding output power data.

[0026] S2. Construct a neural network for the output power of ship photovoltaic panels, with a four-input-output network structure as follows: Figure 2 As shown: The solar radiation intensity, temperature, ship roll angle caused by wave fluctuations, and current solar altitude angle in the ship's navigation environment are used as input layer neurons, and the maximum power output of the photovoltaic cells is used as output layer neurons. The neural network for the output power of ship photovoltaic panels is trained using a sample dataset of ship photovoltaic panels. After comparing different training results, five neurons are finally selected for the hidden layer. Based on the relationship between the adjustment angle data of ship photovoltaic panels, navigation environment data, and the corresponding output power of ship photovoltaic panels, a power output relationship graph is established to obtain the power peak and valley values ​​and the power change trend. Finally, the output power model of ship photovoltaic panels and the optimal tilt angle of ship photovoltaic panels corresponding to the power peak and valley values ​​are obtained.

[0027] The power output relationship diagram of the present invention includes a power fluctuation curve, which is obtained by the following steps:

[0028] S401. Peak and valley value extraction of power fluctuation curve: Extract peak and valley values ​​from the power fluctuation curve. The peak value represents the highest point of the power fluctuation curve, and the valley value represents the lowest point of the power fluctuation curve.

[0029] S402. Analysis of the trend of peak and valley values ​​of power fluctuation curve: Analyze the changes of the extracted peak and valley values, including the amplitude and periodic changes of the peak and valley values. By analyzing the changes of peak and valley values, determine the overall trend and change pattern of the power fluctuation curve.

[0030] S403. Summary of power fluctuation curve patterns: Determine the optimal angle of the ship's photovoltaic panel under the conditions of light intensity, temperature, sea wave state, and ship position.

[0031] S3. Collect ship photovoltaic panel adjustment angle data and marine environment data. Using the ship photovoltaic panel output power model obtained in step S2, predict the ship photovoltaic panel output power; adjust the ship photovoltaic panel to the optimal tilt angle to minimize the output power fluctuation loss of the ship photovoltaic system. This invention uses a ship photovoltaic panel control system to control the motor under the photovoltaic panel to rotate, thereby adjusting the tilt angle of the photovoltaic panel, tracking the sun under the current state to obtain maximum illuminance, and reducing the output power fluctuation loss of the ship photovoltaic system.

[0032] like Figure 3As shown in the figure, when the solar altitude angle is 60° and the ship is subjected to wave impact causing a sinusoidal roll angle of ±30°, the power fluctuation curve predicted by the neural network is marked in the figure. It can be seen that the curve fluctuation is not a standard sine wave and has a large fluctuation range. At this time, by adjusting the rotation of the photovoltaic panel's motor to tilt the photovoltaic panel by 30° to face the sun directly and obtain maximum light intensity, the resulting fluctuation curve is marked in the figure. It can be seen that after adjusting the angle, the output power fluctuation of the photovoltaic panel is significantly reduced, and the output power is also improved.

[0033] Another aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described in the present invention.

[0034] The present invention also proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described in the present invention.

[0035] While the present invention has been described above with reference to preferred embodiments, it is not intended to limit the invention. Those skilled in the art can make various modifications and refinements without departing from the spirit and scope of the invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. A neural network prediction method for the optimal working angle of photovoltaic panels on marine vessels, characterized in that, Includes the following steps: S1. Construct a sample dataset of ship photovoltaic panels, including ship photovoltaic panel adjustment angle data, marine environment data and their corresponding output power data; S2. Construct a neural network for the output power of ship photovoltaic panels. Train the neural network for the output power of ship photovoltaic panels using a sample dataset of ship photovoltaic panels. During the training process, establish a power output relationship graph based on the adjustment angle data of ship photovoltaic panels, navigation environment data, and the relationship between the corresponding output power of ship photovoltaic panels. Obtain the peak and valley values ​​of power and the trend of power change. Finally, obtain the output power model of ship photovoltaic panels and the optimal tilt angle of ship photovoltaic panels corresponding to the peak and valley values ​​of power. The neural network used is a four-input, one-output network structure. The light intensity, temperature, ship roll angle caused by wave fluctuations in the ship's navigation environment, and the current solar altitude angle are used as input layer neurons, and the maximum power value output by the photovoltaic cell is used as output layer neurons. The power output relationship diagram includes a power fluctuation curve, which is obtained according to the following steps S401 to S403: S401. Peak and valley value extraction of power fluctuation curve: Extract peak and valley values ​​from the power fluctuation curve. The peak value represents the highest point of the power fluctuation curve, and the valley value represents the lowest point of the power fluctuation curve. S402. Analysis of the trend of peak and valley values ​​of power fluctuation curve: Analyze the changes of the extracted peak and valley values, including the amplitude and periodic changes of the peak and valley values. By analyzing the changes of peak and valley values, determine the overall trend and change pattern of the power fluctuation curve. S403. Summary of power fluctuation curve patterns: Determine the optimal angle of the ship's photovoltaic panel under the conditions of light intensity, temperature, sea wave state, and ship position. S3. Collect ship photovoltaic panel adjustment angle data and marine environment data. Use the ship photovoltaic panel output power model obtained in step S2 to predict the ship photovoltaic panel output power; adjust the ship photovoltaic panel to the optimal tilt angle.

2. The neural network prediction method for the optimal working angle of a marine ship photovoltaic panel according to claim 1, characterized in that, In step S1, the ship photovoltaic panel angle data includes the ship photovoltaic panel angle, and the marine environment data includes light intensity, temperature, wave state, and the ship's position relative to the sun.

3. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 2.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.

Images